\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Doug Greisen v. Jon Hanken\nCourt: U.S. Court of Appeals for the Ninth Circuit\nDate decided: 2019-05-31\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nDOUG GREISEN, No. 17-35472\n Plaintiff-Appellee,\n D.C. No.\n v. 3:14-cv-01399-SI\n\nJON HANKEN,\n Defendant-Appellant. OPINION\n\n\n\n Appeal from the United States District Court\n for the District of Oregon\n Michael H. Simon, District Judge, Presiding\n\n Argued and Submitted October 11, 2018\n Portland, Oregon\n\n Filed May 31, 2019\n\n Before: Raymond C. Fisher, Richard R. Clifton\n and Consuelo M. Callahan, Circuit Judges.\n\n Opinion by Judge Fisher\n\f2 GREISEN V. HANKEN\n\n SUMMARY *\n\n\n Civil Rights / Employment Retaliation\n\n The panel affirmed the district court’s judgment\nfollowing a jury verdict in favor of Doug Greisen, a former\nchief of police for the City of Scappoose, Oregon, in his\naction brought pursuant to 42 U.S.C. § 1983 alleging that Jon\nHanken, the former city manager, violated the First\nAmendment by subjecting Greisen to adverse employment\nactions in retaliation for his protected speech.\n\n After Greisen discussed his concerns with city council\nmembers and government officials about the city’s\naccounting and budgeting practices under Hanken, Hanken\ninitiated investigations of Greisen, suspended him, placed\nhim on an indefinite leave and prevented him from speaking\npublicly, even as Hanken was releasing information about\nthe investigations to the media. After a city review\ncommittee recommended retraction of Greisen’s suspension,\nHanken resigned.\n\n The panel held that: (1) Greisen provided sufficient\ndetail about his speech to establish that it substantially\ninvolved a matter of public concern; (2) he spoke as a private\ncitizen rather than a public employee; (3) the district court\nproperly concluded that Greisen’s retaliation claim could be\nbased in part on Hanken’s own speech acts, in the form of\ndefamatory communications to the media; (4) Hanken\nwaived his argument that his actions were supported by an\n\n *\n This summary constitutes no part of the opinion of the court. It\nhas been prepared by court staff for the convenience of the reader.\n\f GREISEN V. HANKEN 3\n\nadequate justification; and (5) sufficient evidence supported\nthe conclusion that Hanken’s retaliatory actions proximately\ncaused Greisen’s termination, and any error in instructing\nthe jury on proximate cause was harmless. The panel further\nheld that Hanken was not entitled to qualified immunity.\n\n\n COUNSEL\n\nThomas M. Christ (argued) and Julie A. Smith, Cosgrave\nVergeer Kester LLP, Portland, Oregon, for Defendant-\nAppellant.\n\nWilliam Allen Drew (argued) and John D. Ostrander, Elliott\nOstrander & Preston P.C., Portland, Oregon, for Plaintiff-\nAppellee.\n\n\n OPINION\n\nFISHER, Circuit Judge:\n\n Doug Greisen was the chief of police for the City of\nScappoose, Oregon. In 2012, after more than 10 years in that\nposition, he became suspicious about the city’s accounting\nand budgeting practices. He worried Jon Hanken, the city\nmanager, was hiding something; he believed Hanken was\nsuspiciously defensive about the budget, improperly delayed\npaying invoices at the end of the fiscal year and had\nweakened the city’s external auditing process. Greisen\ndiscussed his concerns with various city council members\nand others in city government over the following year. In\nthe summer and fall of 2013, Hanken initiated three\ninvestigations of Greisen, suspended him, placed him on an\nindefinite leave and prevented him from speaking publicly,\n\f4 GREISEN V. HANKEN\n\neven as Hanken was releasing information about the\ninvestigations to the media. After a city review committee\nrecommended retraction of Greisen’s suspension, Hanken\nresigned. Hanken’s replacement subsequently fired Greisen,\nwho has since been unable to find work.\n\n Greisen sued under 42 U.S.C. § 1983, alleging Hanken\nviolated the First Amendment by subjecting him to adverse\nemployment actions in retaliation for his protected speech.\nA jury found in Greisen’s favor, and Hanken appeals.\n\n We affirm. We hold: (1) Greisen provided sufficient\ndetail about his speech to establish that it substantially\ninvolved a matter of public concern; (2) Greisen spoke as a\nprivate citizen rather than a public employee; (3) the district\ncourt properly concluded that Greisen’s retaliation claim\ncould be based in part on Hanken’s own speech acts, in the\nform of defamatory communications to the media;\n(4) Hanken waived his argument that his actions were\nsupported by an adequate justification; and (5) sufficient\nevidence supports the conclusion that Hanken’s retaliatory\nactions proximately caused Greisen’s termination, and any\nerror in instructing the jury on proximate cause was\nharmless. We further hold Hanken is not entitled to qualified\nimmunity.\n\n I.\n\n Jon Hanken, the former city manager of Scappoose, was\nresponsible for overseeing the city’s budget and for annually\nsubmitting a budget to the city council for review. 1\nAccording to City Councilor Judi Ingham, Hanken generally\n\n 1\n We state the facts in the light most favorable to Greisen. See\nHarper v. City of Los Angeles, 533 F.3d 1010, 1021 (9th Cir. 2008).\n\f GREISEN V. HANKEN 5\n\nsubmitted his budget to the council soon before the\nbeginning of the budget process, allowing little time for\nreview, and he was defensive about issues relating to the\nbudget. In mid-2012, the city had a particularly contentious\nbudget approval process during which some city councilors\nadvocated unsuccessfully for a budget that would add a\npolice officer to the force. Although Hanken had told Chief\nof Police Doug Greisen to support the budget at the hearing,\nGreisen voiced neither support nor dissent. The next day,\nHanken told Greisen: “I’m mad at you. You stay on your\nside of City Hall. I don’t want to see you over here.”\nGreisen understood this as an admonition to focus solely on\nthe police department, and to leave the overall city budget to\nHanken.\n\n Greisen then learned the city delayed paying police\ndepartment invoices, sometimes for as long as four months,\nbefore the end of the fiscal year on July 1. He became\nsuspicious Hanken was hiding something, and he began\nasking “a lot of” other people, including the city finance\nadministrator, city councilors and other city department\nheads, about the city’s budgeting practices during the\nremainder of 2012 and early 2013. He learned the city was\nwithholding payment on invoices from other departments as\nwell. He also learned the city had transitioned from a four-\nperson, on-site auditing team to a one-person, off-site\nauditing firm, and he was concerned about the differences\nbetween the firms: by contrast to the first auditing team, he\nfound that the new auditor was less diligent, was unable to\nstate an opinion on the city’s finances and followed different\npractices that he worried were inconsistent with generally\naccepted accounting principles. He discussed this issue with\nthe city finance administrator and city councilors. He also\ntook a college course on government budgeting and financial\nmanagement.\n\f6 GREISEN V. HANKEN\n\n Around August 2012, Greisen tried to meet with Hanken\nto discuss the budget. Hanken was not receptive; he told\nGreisen that “Ms. Ingham will be the one that will ruin your\ncareer here in the City of Scappoose.” He also said Greisen\n“didn’t know what [he was] talking about” when it came to\nbudgeting and financial management.\n\n In early 2013, Greisen was involved in a police pursuit\nduring which he authorized an officer to perform a “PIT\nmaneuver,” a method of stopping a fleeing car by bumping\nit with a patrol vehicle, sending the fleeing car into a spin.\nAlthough the maneuver was successful, another officer,\nSergeant Doug Carpenter, wrote a memo to his lieutenant\nalleging it was executed at a high speed without proper\nprocedure. Carpenter’s criticism focused on the officer who\nactually performed the PIT maneuver, but it implicated\nGreisen’s actions as well. The lieutenant forwarded the\nmemo to Hanken, along with his own memo clarifying\nGreisen’s role in the maneuver and recommending an\ninvestigation.\n\n Hanken arranged for an outside public agency to\ninvestigate Greisen. The investigation’s purpose, according\nto the investigator, was to determine “whether or not there\nwere policy violations,” not to weigh whether a policy\nviolation was justified. After interviewing various staff, the\nagency submitted a 25-page report finding Greisen\ncommitted 10 policy violations associated with the PIT\nmaneuver. 2\n\n\n 2\n The violations included the findings that Greisen had: (1) “failed\nto assume proper and informed control of a police pursuit”; (2) “failed to\nproperly document the pursuit”; (3) “entered into a motor vehicle pursuit\nwith insufficient knowledge and justification”; (4) “engaged in a pursuit,\n\f GREISEN V. HANKEN 7\n\n Upon receiving the report, Hanken suspended Greisen\nfor two weeks without pay. According to the report’s author,\nthe subject of such an investigation would “typically” have\nthe opportunity to be heard after the report was complete, but\nHanken did not afford Greisen this opportunity. In his\nsuspension letter, Hanken wrote: “As I draft this letter, I\ncannot help but wonder if you would be able to maintain\nyour position if this report was known by or reported to the\nnews media.”\n\n Greisen appealed his discipline to the city’s Personnel\nReview Committee (PRC), which absolved him of\nwrongdoing. The PRC characterized the outside agency’s\nreport as “an erroneous mischaracterization of the events . . .\nthat also purposely omitted pertinent and material facts, to\narrive at a conclusion that the PRC finds untenable, out of\ncontext and an egregious lack of professionalism.” In the\nPRC’s view, the outside agency’s report was “not an\nobjective review, but a prosecutorial document that was\ncolored to arrive at a predetermined result.” The PRC\nfurther found that “the degree of discipline issued to Police\nChief Doug Greisen, for minor discrepancies of best\npractices, is entirely out of proportion based on the totality\nof the circumstances,” and it recommended that “the City\n\n\n\noperating an unauthorized and improperly equipped police vehicle”;\n(5) “disregarded policy related to the established procedure for a\nsecondary pursuing vehicle”; (6) “violated safe driving principles related\nto pursuit driving”; (7) “failed to properly evaluate the need for a\ncontinuation of a pursuit”; (8) “demonstrated a lack of knowledge related\nto applicable standards and police practice related to pursuit intervention\ntactics and authorized a prohibited tactic by an untrained subordinate\nofficer”; (9) “failed to participate in annual training related to pursuit\ndriving”; and (10) “failed to read and maintain a current working\nknowledge of his departmental policy manual.”\n\f8 GREISEN V. HANKEN\n\nManager retract, and the Scappoose City Council oversee the\nretraction [of], all discipline issued to Chief Greisen.”\n\n While the PIT maneuver investigation was ongoing,\nHanken received another complaint about Greisen from\nSergeant Carpenter, this time alleging Greisen had created a\nhostile work environment. In response, Hanken initiated\nanother investigation by the same outside agency and placed\nGreisen on indefinite paid administrative leave pending the\nresults of this investigation. Ultimately, the investigation\nconcluded the allegations were not supported by substantial\nevidence.\n\n In September 2013, while Greisen remained on leave,\nHanken informed him the city would conduct a third\ninvestigation into his activities. This investigation charged\nGreisen with unauthorized financial practices relating to\n$2,500 in donations to the police department that Greisen\nkept in cash in his office. The investigation, conducted by\nthe same outside agency, found five violations of city\npolicy. 3\n\n Hanken sent letters to Greisen precluding him from\nspeaking about the three investigations with anyone other\nthan his wife and attorney. Hanken, however, released\n\n 3\n The investigation found Greisen violated the city’s policy by:\n(1) “having unaccounted for cash in his desk drawer”; (2) “adhering to\nhis own set of rules related to expense reimbursement and submitting\nreimbursement requests for meal expenses within 25 miles of\nScappoose”; (3) “fail[ing] to make bank deposits in a timely manner”;\n(4) “open[ing] and manag[ing] a bank account to be used as a slush fund\nfor Police Department business and to avoid making purchases through\nthe City’s budget process”; and (5) “fail[ing] to donate . . . gift cards\n(recovered crime evidence) to a charitable organization as requested by\nthe crime victim.”\n\f GREISEN V. HANKEN 9\n\ninformation about all three investigations to the media. In\nSeptember 2013, soon after Greisen appealed his two-week\nsuspension, Hanken released information about the first two\ninvestigations. He admitted at trial that his release of\ninformation about the ongoing second investigation “wasn’t\nappropriate.”\n\n Similarly, shortly before he resigned as city manager,\nHanken spoke to the media about the third investigation,\nstating “that a bank bag was discovered in the chief’s desk\nand that its contents raised questions about whether the chief\nwas maintaining an unauthorized account.” Hanken also\nsaid that, “[i]f any other officer had been caught using an\nunauthorized account, they would have been fired on the\nspot.” He further provided the media with a photo of the\ncash that he admitted looked like a photo associated with a\ndrug bust or money seizure. Hanken conceded at trial,\nhowever, that others in the city knew about the money, that\nit was associated with authorized accounts and that he spoke\nto the press to ensure that the second and third investigations\nhe had initiated were not discontinued.\n\n On November 8, 2013, less than a month after the PRC\nissued its findings that Greisen’s discipline for the PIT\nmaneuver was unfounded, Hanken resigned, citing these\nfindings as the reason. He was replaced by Donald Otterman\nin an interim capacity, and in early 2014 Otterman utilized a\n“no-cause” clause in Greisen’s contract to terminate Greisen,\nwho had not returned from administrative leave. Otterman\nmade his decision after reviewing the investigator’s reports\nand speaking with various people, whose views were highly\npolarized.\n\n Greisen attempted to find other employment, but was\nunable to do so. A manager from another city who\nconsidered hiring Greisen testified that although he knew\n\f10 GREISEN V. HANKEN\n\nGreisen personally and respected him, he could not hire\nGreisen as police chief given the negative media attention he\nhad endured.\n\n In 2014, Greisen filed this action. As relevant here, he\nbrought a First Amendment retaliation claim against Hanken\nunder 42 U.S.C. § 1983. Before trial, Hanken moved for\nsummary judgment on qualified immunity, and the district\ncourt denied the motion. The claim was tried to a jury, which\nfound in favor of Greisen, awarding him $1,117,488 in\neconomic damages and $3,000,000 in non-economic\ndamages. Hanken filed post-trial motions seeking a new trial\non the ground that the district court’s jury instruction on\ncausation was erroneous and seeking judgment as a matter\nof law on other grounds. The district court denied the\nmotions, and Hanken timely appealed.\n\n II.\n\n We review de novo a district court’s denial of a motion\nfor judgment as a matter of law, but “[a] jury’s verdict must\nbe upheld if it is supported by substantial evidence, . . . even\nif it is also possible to draw a contrary conclusion.” Pavao\nv. Pagay, 307 F.3d 915, 918 (9th Cir. 2002). We “must view\nall evidence in the light most favorable to the nonmoving\nparty, draw all reasonable inferences in the favor of the non-\nmover, and disregard all evidence favorable to the moving\nparty that the jury is not required to believe.” Harper v. City\nof Los Angeles, 533 F.3d 1010, 1021 (9th Cir. 2008).\n“‘[W]hen reviewing a motion for judgment as a matter of\nlaw, we apply the law as it should be, rather than the law as\nit was read to the jury,’ even if the party did not object to the\njury instructions.” Fisher v. City of San Jose, 558 F.3d 1069,\n1074 (9th Cir. 2009) (en banc) (alteration in original)\n(quoting Pincay v. Andrews, 238 F.3d 1106, 1109 n.4 (9th\nCir. 2001)).\n\f GREISEN V. HANKEN 11\n\n We review de novo a district court’s decision on\nqualified immunity. See Elder v. Holloway, 510 U.S. 510,\n516 (1994). Once the jury has reached a verdict, however,\n“we must defer to the facts as they were reasonably found by\nthe jury – we do not draw our own inferences from them.”\nA.D. v. Cal. Highway Patrol, 712 F.3d 446, 459 (9th Cir.\n2013).\n\n “We review de novo whether [a jury] instruction[]\nmisstated the law.” Fireman’s Fund Ins. Cos. v. Alaskan\nPride P’ship, 106 F.3d 1465, 1469 (9th Cir. 1997). An error\nin instructing the jury in a civil case does not require reversal\nif it is harmless. See Altera Corp. v. Clear Logic, Inc.,\n424 F.3d 1079, 1087 (9th Cir. 2005).\n\n III.\n\n A First Amendment retaliation claim turns on a\nsequential five-step series of questions:\n\n (1) whether the plaintiff spoke on a matter of\n public concern; (2) whether the plaintiff\n spoke as a private citizen or public employee;\n (3) whether the plaintiff’s protected speech\n was a substantial or motivating factor in the\n adverse employment action; (4) whether the\n state had an adequate justification for treating\n the employee differently from other members\n of the general public; and (5) whether the\n state would have taken the adverse\n employment action even absent the protected\n speech.\n\nEng v. Cooley, 552 F.3d 1062, 1070 (9th Cir. 2009). The\nplaintiff bears the burden on the first three questions. See id.\nat 1070–71. If the plaintiff meets this burden, the burden\n\f12 GREISEN V. HANKEN\n\nshifts to the defendant on the last two questions. See id.\nat 1071–72. When a constitutional violation has been\nestablished, a plaintiff may recover damages that are\nproximately caused thereby. See County of Los Angeles v.\nMendez, 137 S. Ct. 1539, 1548–49 (2017). The plaintiff\nmust also establish that the defendant’s retaliatory conduct\nwas a but-for cause of the defendant’s damages. See Mendez\nv. County of Los Angeles, 897 F.3d 1067, 1074 (9th Cir.\n2018).\n\n Here, Greisen contends Hanken retaliated against him\nfor discussing the city’s budgeting and accounting practices\nwith other city officials. He contends that this speech\ninvolved a matter of public concern – the mismanagement of\ncity finances. He further contends that his discussions with\ncity officials regarding suspected mismanagement were not\npart of his job duties, and hence that he engaged in this\nspeech as a private citizen rather than as a public employee.\nHe alleges a number of adverse employment actions – e.g.,\ncommencement of the PIT maneuver, hostile work\nenvironment and financial mismanagement investigations;\nthe two-week suspension; the indefinite administrative\nleave; the “gag order” prohibiting him from speaking to the\npress; and the false and inflammatory information Hanken\nprovided to the press about him – and he contends that his\nprotected speech was a substantial or motivating factor in\nHanken’s decisions to take each of these actions. In\naddition, although he does not contend that Otterman’s\ndecision to terminate him was itself retaliatory, he seeks\ndamages arising from the termination on the ground that it\nwas proximately caused by Hanken’s retaliatory actions.\n\n Hanken challenges the verdict in favor of Greisen on the\nfirst, second, third and fourth of the questions in the\nsequential analysis. In addition, he challenges Greisen’s\n\f GREISEN V. HANKEN 13\n\nrecovery of damages arising from the termination. We\naddress these contentions in turn.\n\n A number of Hanken’s arguments also implicate\nqualified immunity. In resolving whether a government\nofficial is entitled to qualified immunity, a court “must\ndecide whether the facts that a plaintiff has alleged or shown\nmake out a violation of a constitutional right,” and, if so,\n“whether the right at issue was ‘clearly established’ at the\ntime of defendant’s alleged misconduct.” Pearson v.\nCallahan, 555 U.S. 223, 232 (2009) (citations omitted)\n(quoting Saucier v. Katz, 533 U.S. 194, 201 (2001)). To\ndetermine that a right was clearly established, the court\n“must identify precedent as of [the date of the alleged\nviolation] that put [the defendant] on clear notice” that his or\nher actions were unconstitutional. S.B. v. County of San\nDiego, 864 F.3d 1010, 1015 (9th Cir. 2017). “We do not\nrequire a case directly on point, but existing precedent must\nhave placed the statutory or constitutional question beyond\ndebate.” Ashcroft v. al-Kidd, 563 U.S. 731, 741 (2011).\nCourts must not define clearly established law at a high level\nof generality. See Mullenix v. Luna, 136 S. Ct. 305, 308\n(2015) (per curiam).\n\n A. Matter of Public Concern\n\n With respect to the first step in the analysis, “the plaintiff\nbears the burden of showing that the speech addressed an\nissue of public concern.” Eng, 552 F.3d at 1070.\n\n Whether speech is on a matter of public concern is a\nquestion of law, determined by the court, and reviewed by\nus de novo. See Berry v. Dep’t of Soc. Servs., 447 F.3d 642,\n648 (9th Cir. 2006). The speech need not be entirely about\nmatters of public concern, but it must “substantially involve”\nsuch matters. Johnson v. Multnomah County, 48 F.3d 420,\n\f14 GREISEN V. HANKEN\n\n425 (9th Cir. 1995). “[S]peech warrants protection when it\n‘seek[s] to bring to light actual or potential wrongdoing or\nbreach of public trust.’” Barone v. City of Springfield,\n902 F.3d 1091, 1098 (9th Cir. 2018) (second alteration in\noriginal) (quoting Connick v. Myers, 461 U.S. 138, 148\n(1983)). The “misuse of public funds . . . [is a] matter[] of\ninherent public concern.” Johnson, 48 F.3d at 425.\n\n “Whether an employee’s speech addresses a matter of\npublic concern must be determined by the content, form, and\ncontext of a given statement, as revealed by the whole\nrecord.” Connick, 461 U.S. at 147–48. “[T]he content of the\nspeech is generally the most important.” Karl v. City of\nMountlake Terrace, 678 F.3d 1062, 1069 (9th Cir. 2012). In\nreviewing form and context, “we focus on the point of the\nspeech, looking to such factors as the employee’s motivation\nand the audience chosen for the speech.” Ulrich v. City &\nCounty of San Francisco, 308 F.3d 968, 979 (9th Cir. 2002)\n(citation and internal quotation marks omitted). This\nanalysis seeks to determine whether the employee aimed “‘to\nbring wrongdoing to light,’ not ‘merely to further some\npurely private interest.’” Id. (quoting Havekost v. U.S. Dep’t\nof Navy, 925 F.2d 316, 318 (9th Cir. 1991)). “[S]peech that\ndeals with ‘individual personnel disputes and grievances’\nand that would be of ‘no relevance to the public’s evaluation\nof the performance of governmental agencies’ is generally\nnot of ‘public concern.’” Coszalter v. City of Salem,\n320 F.3d 968, 973 (9th Cir. 2003) (quoting McKinley v. City\nof Eloy, 705 F.2d 1110, 1114 (9th Cir. 1983)).\n\n Hanken does not dispute that the potential\nmismanagement of city funds is a matter of public concern.\nHe argues, however, that he was entitled to judgment as a\nmatter of law on this question on three independent grounds:\n(1) the district court had insufficient information before it to\n\f GREISEN V. HANKEN 15\n\nconclude the speech involved matters of public concern;\n(2) the speech did not involve matters of public concern,\nbecause Greisen was motivated by a personal grievance\nagainst him rather than exposing government wrongdoing;\nand (3) qualified immunity.\n\n 1. The district court had sufficient information to\n determine Greisen’s speech substantially involved\n matters of public concern\n\n Hanken argues the district court lacked sufficient\ninformation about the content, form and context of Greisen’s\nspeech to conclude it substantially involved matters of public\nconcern. Although Greisen testified about his discussions\nwith other city officials, Hanken contends “he did not\ndescribe the substantive content of those conversations in\nany detail.” He contends the descriptions Greisen provided\nwere insufficient “to allow a court to make a determination\nthat [the] speech related to a matter of public concern.”\nKurtz v. Vickrey, 855 F.2d 723, 730 n.4 (11th Cir. 1988); see\nalso Nixon v. City & County of Denver, 784 F.3d 1364, 1369\n(10th Cir. 2015); Moss v. City of Pembroke Pines, 782 F.3d\n613, 620–21 (11th Cir. 2015). We disagree.\n\n We agree, of course, that a court must have sufficient\ninformation about the content, form and context of speech to\ndetermine whether it was on a matter of public concern. A\nplaintiff, however, need not provide transcriptions of the\nconversations. Here, Greisen provided enough. With regard\nto the content of the speech, Greisen testified about the\ndiscussions he had with the city finance administrator and\nother department heads regarding Hanken’s practice of\ndelaying payment of invoices. Greisen used these\ndiscussions, among other things, to learn about how other\ndepartments handled invoice payments. Greisen also\ntestified that he discussed his concerns about the new auditor\n\f16 GREISEN V. HANKEN\n\nwith some city councilors and with the city finance\nadministrator. His concerns included the fact that the auditor\nwas not on-site, the auditor’s inability to offer an opinion\nabout the city’s finances and the quality of the auditor’s\nwritten reports. As to form and context, Greisen provided a\ngeneral timeline, identified the roles of his interlocutors and\ndescribed his motivations for the discussions. The district\ncourt, therefore, had enough information before it.\n\n 2. The district court properly concluded the speech\n substantially involved matters of public concern\n\n Even assuming the information was sufficient, Hanken\nargues the district court erred by concluding that Greisen’s\nspeech substantially involved matters of public concern. He\nargues that, even if “the content of the speech does at first\nglance look like it raises a public concern because it involves\nthe city’s finances,” “the form and context suggest that the\nspeech is really about a power struggle between plaintiff and\ndefendant – more specifically, about a power play by\nplaintiff.” Hanken maintains that Greisen’s speech “was\nmore like the airing of an internal grievance, the grinding of\na private ax, not [an] effort to provoke a public debate on an\nissue of public concern.”\n\n The evidence does not support this contention. It shows\nthat Greisen was interested in uncovering mismanagement\ninvolving city funds. He spoke to other city officials to learn\nabout the financial management process. He took a college\ncourse on budgeting and finance. His interest in the welfare\nof the city is clear from the record. His family had lived in\nScappoose for 30 years, and he “was very involved in the\ncommunity,” where he had “volunteered endlessly.” He also\ntestified he was motivated by “the cop in [him]” to\ninvestigate whether something was being hidden.\n\f GREISEN V. HANKEN 17\n\n That Greisen spoke privately to other city officials,\nrather than publicly, does not show that he was motivated by\na private grudge rather than a desire to detect and expose\npotential mismanagement. The choice “to convey . . . views\nprivately rather than publicly is not determinative of whether\n. . . expression is entitled to protection.” Thomas v. City of\nBeaverton, 379 F.3d 802, 810 (9th Cir. 2004). Private\nspeech may serve to “bring wrongdoing to light.” Ulrich,\n308 F.3d at 979 (quoting Havekost, 925 F.2d at 318).\n\n In sum, the district court properly concluded, based on\nthe “content, form, and context” of Greisen’s speech, that his\nconversations substantially involved a matter of public\nconcern. Connick, 461 U.S. at 147.\n\n 3. Hanken is not entitled to qualified immunity on the\n public concern issue\n\n By 1995, it was clearly established that the misuse of\npublic funds is a matter of public concern. See Johnson,\n48 F.3d at 425. Given the nature of Greisen’s concerns and\nhis longtime connection to the community, Hanken could\nnot reasonably have concluded that Greisen’s speech\n“deal[t] with ‘individual personnel disputes and grievances’\n. . . that would be of ‘no relevance to the public’s evaluation\nof the performance of governmental agencies.’” Coszalter,\n320 F.3d at 973 (quoting McKinley, 705 F.2d at 1114). The\ndistrict court therefore properly denied qualified immunity.\n\n B. Private Citizen\n\n In a First Amendment retaliation case, the plaintiff also\n“bears the burden of showing the speech was spoken in the\ncapacity of a private citizen and not a public employee.”\nEng, 552 F.3d at 1071.\n\f18 GREISEN V. HANKEN\n\n In Garcetti v. Ceballos, 547 U.S. 410, 421 (2006), the\nSupreme Court held that, “when public employees make\nstatements pursuant to their official duties, the employees\nare not speaking as citizens for First Amendment purposes,\nand the Constitution does not insulate their communications\nfrom employer discipline.” “[S]tatements are made in the\nspeaker’s capacity as citizen if the speaker had no official\nduty to make the questioned statements, or if the speech was\nnot the product of performing the tasks the employee was\npaid to perform.” Posey v. Lake Pend Oreille Sch. Dist. No.\n84, 546 F.3d 1121, 1127 n.2 (9th Cir. 2008) (alterations,\ncitation and internal quotation marks omitted). We look to\nthree non-exhaustive factors to make this assessment:\n(1) whether “the employee confined his communications to\nhis chain of command”; (2) whether “the subject matter of\nthe communication” fell within the plaintiff’s regular job\nduties; and (3) whether the “employee sp[oke] in direct\ncontravention to his supervisor’s order[].” Dahlia v.\nRodriguez, 735 F.3d 1060, 1074–75 (9th Cir. 2013) (en\nbanc). The scope and content of a plaintiff’s official duties\nare questions of fact, but a court must “independently . . .\nevaluate the ultimate constitutional significance of the facts\nas found.” Posey, 546 F.3d at 1129.\n\n 1. The district court properly determined Greisen\n spoke as a private citizen\n\n Here, viewing the evidence in the light most favorable to\nGreisen, every Dahlia factor favors the jury’s conclusion\nthat Greisen spoke as a private citizen. With regard to the\nfirst factor (chain of command), the record shows Greisen\nhad conversations with the city finance administrator, city\ncouncilors and at least three other department heads, none of\nwhom were within his chain of command.\n\f GREISEN V. HANKEN 19\n\n With regard to the second factor (subject matter), Dahlia\nnoted:\n\n [I]f a public employee raises within the\n department broad concerns about corruption\n or systemic abuse, it is unlikely that such\n complaints can reasonably be classified as\n being within the job duties of an average\n public employee, except when the\n employee’s regular job duties involve\n investigating such conduct, e.g., when the\n employee works for Internal Affairs or\n another such watchdog unit.\n\n735 F.3d at 1075. Here, Greisen’s concerns related to\nferreting out “corruption or systemic abuse” in city finances\nand management, and these functions were not part of his\nofficial duties as chief of police. His concerns about the\nbudget related to secrecy and potential wrongdoing: a lack\nof oversight on the part of the new auditor, Hanken’s\nunwillingness to let anyone into the budgeting process and\nthe failure to pay vendors on time. No evidence suggests\nthese matters fell within Greisen’s regular job duties.\n\n With regard to the last factor (contravention of\nsupervisors), there is strong evidence that Hanken, Greisen’s\nsupervisor, did not want him discussing or looking into the\noverall city budget or Hanken’s accounting practices.\nHanken instructed Greisen to stay on his “side” of city hall,\nand discouraged him from speaking to Councilor Ingham\nabout the overall budget.\n\n Hanken does not argue that the Dahlia factors favor\nreversal, but attempts to distinguish Dahlia, which involved\na lower-ranking employee, on the basis that Greisen, as a\npolice chief, had broader duties. See id. at 1063. He argues\n\f20 GREISEN V. HANKEN\n\nthis case is more analogous to Johnson v. Poway Unified\nSchool District, 658 F.3d 954 (9th Cir. 2011), and Kennedy\nv. Bremerton School District, 869 F.3d 813 (9th Cir. 2017).\nPoway Unified held that, “because of the position of trust\nand authority they hold and the impressionable young minds\nwith which they interact, teachers necessarily act as teachers\n. . . when at school or a school function, in the general\npresence of students, in a capacity one might reasonably\nview as official.” Poway Unified, 658 F.3d at 968. Kennedy\nheld that a school coach acted as a public employee where\nhis job duties “entailed both teaching and serving as a role\nmodel and moral exemplar” and he was “acting in an official\ncapacity in the presence of students and spectators.”\nKennedy, 869 F.3d at 827. Hanken contends a police chief,\nlike a teacher, occupies a “position of trust, authority, and\nresponsibility,” which means that a police chief is\n“necessarily acting as the police chief whenever he [is]\ninteracting with other high- and higher-ranking city\nofficials.”\n\n We disagree. We have never extended Kennedy and\nPoway Unified beyond the school context, and the cases are\ndistinguishable. Kennedy and Poway Unified focused on the\n“impressionable and captive minds” to whom the employees\nat issue espoused their views. Kennedy, 869 F.3d at 828\n(quoting Poway Unified, 658 F.3d at 968). Leading a police\nforce of adults does not implicate the same concerns, so\nHanken’s analogies to the public school context are\nunpersuasive.\n\n Hanken also looks to Moss v. City of Pembroke Pines,\n782 F.3d 613 (11th Cir. 2015). There, the assistant fire chief\n– who also served as an elected member of the city’s pension\nboard – spoke to various employees within his department\nregarding city-wide pension and wage issues that would\n\f GREISEN V. HANKEN 21\n\ninfluence the department. See id. at 616–17. In holding the\ncommunications were within the plaintiff’s job duties, the\ncourt noted the “[p]laintiff’s statements . . . were made in\naccordance with his role as a liaison between the Fire Chief\nand employees down the chain of command.” Id. at 620.\nHere, by contrast, Greisen spoke outside his chain of\ncommand and outside his defined role in the budget process.\nMoss thus does not support Hanken’s position.\n\n 2. Hanken is not entitled to qualified immunity on the\n private citizen issue\n\n In Karl v. City of Mountlake Terrace, 678 F.3d 1062 (9th\nCir. 2012), we held that “a reasonable official would . . .\nhave known that a public employee’s speech on a matter of\npublic concern is protected if the speech is not made\npursuant to her official job duties, even if the testimony itself\naddresses matters of employment.” Id. at 1074 (citing\nGarcetti, 547 U.S. at 421; Eng, 552 F.3d at 1075–76; Posey,\n546 F.3d at 1126–27). Viewing the record in the light most\nfavorable to Greisen, Hanken told Greisen on two occasions\nthat Greisen was not to concern himself with issues relating\nto the management of the overall city budget. No evidence\nsuggests a reasonable official in Hanken’s position would\nhave believed analyzing the timing of invoice payments in\nother departments or city-wide audit practices was within\nGreisen’s job duties. Hanken is thus not entitled to qualified\nimmunity.\n\n C. Adverse Employment Action and Causation\n\n At the third step in a First Amendment retaliation\nanalysis, the plaintiff bears the burden of showing the state\ntook an adverse employment action against the plaintiff and\nthat the plaintiff’s speech was a substantial or motivating\nfactor in the adverse action. See Eng, 552 F.3d at 1071.\n\f22 GREISEN V. HANKEN\n\n Thus, to find in Greisen’s favor on the First Amendment\nretaliation claim, the jury had to find Greisen suffered an\nadverse employment action. “In a First Amendment\nretaliation case, an adverse employment action is an act that\nis reasonably likely to deter employees from engaging in\nconstitutionally protected speech.” Coszalter, 320 F.3d\nat 970. The jury was instructed on several potential adverse\nemployment actions here, including two that involved\nHanken’s own speech: “misrepresenting . . . accounts to the\npress as ‘unauthorized’ before the completion of the\ninvestigation; and giving the press access to an inventory\nphotograph that . . . Greisen says was ‘inflammatory.’”\n\n Hanken argues the district court should have granted\npartial judgment as a matter of law on the ground that his\ncommunications with the media “do not qualify as adverse\nemployment actions because they involved the exercise of\nhis own free speech rights.” Alternatively, he contends he is\nentitled to qualified immunity on this basis.\n\n “Retaliation claims involving government speech\nwarrant a cautious approach by courts,” because\n“[r]estricting the ability of government decisionmakers to\nengage in speech risks interfering with their ability to\neffectively perform their duties” and “ignores the competing\nFirst Amendment rights of the officials themselves.”\nMulligan v. Nichols, 835 F.3d 983, 989 (9th Cir. 2016). “[A]\nbalance must be struck between the citizen’s right to exercise\nhis First Amendment rights and the public official’s personal\nFirst Amendment rights, as well as his duty to the public to\nspeak out about matters of public concern.” Suarez Corp.\nIndus. v. McGraw, 202 F.3d 676, 687 n.13 (4th Cir. 2000).\nThus, we have on several occasions rejected retaliation\nclaims based exclusively on retaliatory speech, noting that\n“[i]t would be the height of irony, indeed, if mere speech, in\n\f GREISEN V. HANKEN 23\n\nresponse to speech, could constitute a First Amendment\nviolation.” Nunez v. City of Los Angeles, 147 F.3d 867, 875\n(9th Cir. 1998); see also Mulligan, 835 F.3d at 989–91; Gini\nv. Las Vegas Metro. Police Dep’t, 40 F.3d 1041, 1045 (9th\nCir. 1994).\n\n We have, however, held that retaliatory speech can serve\nas a basis for liability for a First Amendment retaliation\nclaim under at least two circumstances.\n\n First, a First Amendment retaliation claim may be based\non retaliatory speech when that speech is part of a campaign\nof harassment designed to burden the plaintiff’s protected\nexpression. In Allen v. Scribner, 812 F.2d 426 (9th Cir.\n1987), for example, the plaintiff alleged “he was the subject\nof continued harassment designed both to prevent him from\nvoicing his opinion and to punish him for his having already\ndone so.” Id. at 429. Specifically, he alleged the defendants\nintimidated him, threatened him, harassed him and “made\ndefamatory statements to the media with the intent of\ndiscrediting him.” Id. In addition, he alleged he was\ntransferred in retaliation for his protected speech. See id.\n\n We rejected the defendants’ argument that “any\nallegation of harassment grounded in a claim of defamation”\nwas not actionable. See id. at 434 n.17. We accepted the\nproposition that, “to establish a claim under § 1983, more\nmust be involved than defamation by a state official.” Id.\nBut that principle was inapplicable to the facts of the case:\n“Here, something more is involved. [The plaintiff] alleges\nthat the defamation he suffered was part of a concerted effort\nto burden his first amendment expression.” Id.; see also\nCoszalter, 320 F.3d at 975–77 (citing Allen and holding that\n“engaging in [a] campaign[] of harassment and humiliation”\ncan be the basis for liability in a First Amendment retaliation\nclaim).\n\f24 GREISEN V. HANKEN\n\n Second, even when it is not part of a campaign of\nharassment designed to burden the plaintiff’s protected\nexpression, retaliatory speech may serve as the basis for a\nFirst Amendment retaliation claim when it “intimat[es] that\nsome form of punishment or adverse regulatory action would\nfollow.” Brodheim v. Cry, 584 F.3d 1262, 1270 (9th Cir.\n2009) (quoting Okwedy v. Molinari, 333 F.3d 339, 343 (2d\nCir. 2003)); see Goldstein v. Galvin, 719 F.3d 16, 30–31 (1st\nCir. 2013); Hutchins v. Clarke, 661 F.3d 947, 956 (7th Cir.\n2011); Balt. Sun Co. v. Ehrlich, 437 F.3d 410, 417 (4th Cir.\n2006); X-Men Sec., Inc. v. Pataki, 196 F.3d 56, 71 (2d Cir.\n1999); see also Mulligan, 835 F.3d at 989 n.5 (rejecting the\nproposition that “speech by government officials can never\ngive rise to a claim of First Amendment retaliation,” id.\n(emphasis omitted), and explaining that “informal measures,\nsuch as the threat of invoking legal sanctions and other\nmeans of coercion, persuasion, and intimidation, can violate\nthe First Amendment,” id. (internal quotation marks and\nalteration omitted) (quoting White v. Lee, 227 F.3d 1214,\n1228 (9th Cir. 2000))). 4\n\n This case falls squarely within Allen. As in Allen,\nGreisen’s retaliation claim involves something more than\ndefamation by a public official. He alleged the defamation\nhe suffered was part of a concerted effort to deter him from,\nand punish him for, engaging in constitutionally protected\nspeech. He alleged Hanken engaged in a campaign of\nharassment against him that included not only defamatory\ncommunications with the press but also a suspension, an\n\n 4\n We have left undecided the question of whether retaliatory speech\nmay also be actionable in some circumstances when it involves the\n“disclosure of deeply private personal details.” Mulligan, 835 F.3d\nat 990; see also Balt. Sun, 437 F.3d at 417; Bloch v. Ribar, 156 F.3d 673,\n676 (6th Cir. 1998).\n\f GREISEN V. HANKEN 25\n\nindefinite leave, a one-sided gag order and the instigation of\nthree spurious investigations. Greisen thus permissibly\npremised his retaliation claim in part on Hanken’s\ncommunications with the media. In addition, Hanken is not\nentitled to qualified immunity on the theory that he would\nnot reasonably have known at the time of his actions that a\nFirst Amendment retaliation claim could be based in part on\nacts of retaliatory speech. In light of Allen, decided in 1987,\nhe was on notice. 5\n\n D. Adequate Justification: Pickering Balancing\n\n “[I]f the plaintiff has passed the first three steps, the\nburden shifts to the government to show that under the\nbalancing test established by Pickering, the state’s legitimate\nadministrative interests outweigh the employee’s First\nAmendment rights.” Eng, 552 F.3d at 1071 (alterations and\ninternal quotation marks omitted). “This inquiry, known as\nthe Pickering balancing test, asks ‘whether the relevant\ngovernment entity had an adequate justification for treating\nthe employee differently from any other member of the\ngeneral public.’” Id. (quoting Garcetti, 547 U.S. at 418); see\nPickering v. Bd. of Educ., 391 U.S. 563, 568 (1968).\n\n Hanken seeks to raise this defense here, but “an appellate\ncourt will not consider issues not properly raised before the\ndistrict court.” Smith v. Marsh, 194 F.3d 1045, 1052 (9th\nCir. 1999) (emphasis added). Here, Hanken briefly asserted\nthis argument for the first time in his reply brief on his\n\n 5\n Because this case falls squarely within Allen, we need not\ndetermine whether Hanken’s communications with the media also\nintimated that some form of punishment or adverse regulatory action\nwould follow. See Brodheim, 584 F.3d at 1269-71.\n\f26 GREISEN V. HANKEN\n\nrenewed motion for judgment as a matter of law, and the\ndistrict court appropriately declined to consider it. See\nZamani v. Carnes, 491 F.3d 990, 997 (9th Cir. 2007) (“The\ndistrict court need not consider arguments raised for the first\ntime in a reply brief.”). 6 The argument, therefore, is waived.\n\n Hanken argues the question is “purely one of law,”\nwhich could allow us to exercise discretion to review the\nargument under Bolker v. Commissioner of Internal\nRevenue, 760 F.2d 1039, 1042 (9th Cir. 1985). We disagree.\nAlthough the Pickering balancing test “is ultimately a legal\nquestion, . . . its resolution often entails underlying factual\ndisputes.” Eng, 552 F.3d at 1071. Here, the record is\nundeveloped. It is thus inappropriate to review Hanken’s\nargument under the pure question of law exception because\nwe “cannot rule out the possibility that . . . the merits of the\n. . . argument cannot be resolved without further hearings\nbefore the district court.” A-1 Ambulance Serv., Inc. v.\nCounty of Monterey, 90 F.3d 333, 339 (9th Cir. 1996).\n\n E. Damages\n\n As noted, Greisen did not argue that his termination was\nan adverse employment action. He argued, however, that it\n\n\n\n\n 6\n Although Hanken briefly alluded to Pickering balancing in his\nopening brief in support of his Rule 50(b) motion, this cryptic allusion\nwas insufficient to raise the issue. See Whittaker Corp. v. Execuair\nCorp., 953 F.2d 510, 515 (9th Cir. 1992) (an argument is properly raised\nbelow when it is “raised sufficiently for the trial court to rule on it”\n(quoting In re E.R. Fegert, Inc., 887 F.2d 955, 957 (9th Cir. 1989)).\nBecause the issue was waived for this reason, we need not consider other\npossible bases for waiver. See, e.g., EEOC v. Go Daddy Software, Inc.,\n581 F.3d 951, 961 (9th Cir. 2009).\n\f GREISEN V. HANKEN 27\n\nwas proximately caused by Hanken’s actions. He therefore\nsought damages arising from his termination.\n\n Hanken challenges these damages. Quoting Lakeside-\nScott v. Multnomah County, 556 F.3d 797, 804 (9th Cir.\n2009), he contends his conduct did not proximately cause\nGreisen’s termination, because Otterman, Hanken’s\nsuccessor, “made a wholly independent, legitimate decision\nto discharge” Greisen, and any reasonable jury would have\nso found. Alternatively, he asks us to remand for a new trial\nbecause jury instruction number 17 misstated the law of\nproximate cause by failing to require a direct relation\nbetween Hanken’s actions and Greisen’s termination. See\nStaub v. Proctor Hosp., 562 U.S. 411, 419 (2011)\n(“Proximate cause requires only ‘some direct relation\nbetween the injury asserted and the injurious conduct\nalleged,’ and excludes only those ‘link[s] that are too remote,\npurely contingent, or indirect.’” (alteration in original)\n(quoting Hemi Grp., LLC v. City of New York, 559 U.S. 1, 9\n(2010))). This failure, in his view, prevented the jury from\nconsidering whether Otterman’s decision to terminate\nGreisen severed the chain of causation. We address these\ncontentions in turn.\n\n 1. Substantial evidence supports the jury’s conclusion\n that Hanken’s actions proximately caused\n Greisen’s termination\n\n We are not persuaded by Hanken’s argument that any\nreasonable jury would have concluded that his actions did\nnot proximately cause Greisen’s termination. The Supreme\nCourt considered an analogous issue in Staub. There, the\nplaintiff, a member of the United States Army Reserve,\nbrought a claim under the Uniformed Services Employment\nand Reemployment Rights Act, claiming his employer\ndischarged him as a result of his military obligations. See id.\n\f28 GREISEN V. HANKEN\n\nat 415. The plaintiff’s biased supervisor had reported the\nplaintiff to a superior, who reviewed the plaintiff’s file and\nfired him partially on the basis of the supervisor’s report.\nSee id. at 414–15.\n\n The Court framed the question before it as whether “an\nemployer may be held liable for employment discrimination\nbased on the discriminatory animus of an employee who\ninfluenced, but did not make, the ultimate employment\ndecision.” Id. at 413. Answering this question required the\nCourt to consider whether “the biased supervisor’s action”\nwas “a proximate cause of the ultimate employment action”\n– the precise question at issue here. Id. at 420, 422. The\nproximate cause inquiry, in turn, hinged on whether the\nbiased supervisor’s actions “were causal factors underlying\n[the] decision to fire” the plaintiff. Id. at 423. The Court\nexplained:\n\n [I]f the employer’s investigation results in an\n adverse action for reasons unrelated to the\n supervisor’s original biased action . . . , then\n the employer will not be liable. But the\n supervisor’s biased report may remain a\n causal factor if the independent investigation\n takes it into account without determining that\n the adverse action was, apart from the\n supervisor’s recommendation, entirely\n justified.\n\nId. at 421.\n\n Under Staub, the question is whether Hanken’s actions\nwere a “causal factor” in Otterman’s decision to fire Greisen\n– i.e., whether Otterman fired Greisen “for reasons unrelated\nto [Hanken’s] original biased action[s].” Id. Compare\nLakeside-Scott, 556 F.3d at 807–09 (holding that a biased\n\f GREISEN V. HANKEN 29\n\nsupervisor’s actions, including initiating an investigation\nthat led to the plaintiff’s discharge, were not causal factors\nin the plaintiff’s discharge where the ultimate termination\ndecision was based on a thorough investigation that was\nindependent of the supervisor’s improper influence), with\nPoland v. Chertoff, 494 F.3d 1174, 1182–84 (9th Cir. 2007)\n(holding that a biased supervisor’s actions were causal\nfactors in the plaintiff’s transfer where the employer failed\nto shield the disciplinary inquiry from the supervisor’s\ninfluence, the supervisor played a role in selecting witnesses\nfor the inquiry and the supervisor’s memo that initiated the\ninquiry was available to the disciplinary board making the\nultimate transfer decision).\n\n Here, the evidence does not show that Otterman’s\ndecision was “unrelated to” Hanken’s conduct. See Staub,\n562 U.S. at 421. Hanken points to Otterman’s testimony that\nhis decision was based on the results of the three\ninvestigations Hanken initiated. There is some reason to\ndoubt that these investigations were independent. Hanken\nselected the outside agency that performed the\ninvestigations, and, more strikingly, he admitted at trial that\nwhen he learned that the city council was considering ending\nthe investigations, he made a false report to the media in a\nseemingly successful effort to keep them going.\n\n Even assuming, however, that the investigations were\nfully independent and that Hanken cannot be held\nresponsible for what they uncovered, cf. Lakeside-Scott,\n556 F.3d at 806–07, they are not the whole story. Otterman\nacknowledged that there were “some other things”\nmotivating his decision, including the negative media\nattention surrounding Greisen and the fact that “the police\ndepartment employees felt that they could no longer rely on\n. . . Greisen as the chief of police.” Hanken’s wrongful\n\f30 GREISEN V. HANKEN\n\nactions – which amounted to a campaign of public\nhumiliation through, among other things, false and\nmisleading representations – almost certainly played a direct\nand substantial role in creating or exacerbating these\nconditions. Otterman did not assert that he made any effort\nto shield his termination decision from the influence of\nHanken’s actions. Cf. Poland, 494 F.3d at 1183. And there\nis no contemporaneous evidence that Otterman’s decision\nwas based solely on the investigation results. On the\ncontrary, rather than identifying a particular justification for\nthe dismissal – like the employer did in Lakeside-Scott,\n556 F.3d at 809 – he concluded “that the best situation for\nthe City was to exercise the, quote, ‘no-cause,’ unquote,\nclause” in Greisen’s contract. Otterman further made clear\nthat Hanken’s actions created an environment of unrest that\nframed and dictated the timeline of the decision:\n\n There were several articles about [Greisen]\n and about what was going on in the City. . . .\n The police chief was on administrative leave.\n And that causes commotion or turmoil in the\n organization and needs to be resolved as soon\n as possible.\n\nOn this evidence, a reasonable jury could have found that\nHanken’s actions were a causal factor in Otterman’s\ndecision.\n\n 2. Any error in the jury instruction on proximate\n cause was harmless\n\n As noted, Hanken argues he is entitled to a new trial\nbecause jury instruction number 17 misstated the law of\nproximate cause by failing to require a direct relation\nbetween Hanken’s actions and Greisen’s termination. In\nrelevant part, that instruction stated:\n\f GREISEN V. HANKEN 31\n\n You can award money only for those\n damages that arise naturally and necessarily\n from the violation of law that the Plaintiff has\n proven. . . .\n\n If you find that the Defendant wrongfully\n retaliated against the Plaintiff in violation of\n the Plaintiff’s constitutional rights, and if you\n also find that it was reasonably foreseeable\n that such wrongful retaliatory conduct, if any,\n by the Defendant would render the Plaintiff\n unable to maintain either his position or his\n salary (either at the City of Scappoose or at\n another employer), then you may award the\n Plaintiff any non-speculative, foreseeable\n economic damages caused by the\n Defendant’s wrongful retaliatory conduct.\n\n We need not determine whether jury instruction\nnumber 17 was erroneous because any error was harmless.\nSee Dunlap v. Liberty Nat. Prods., Inc., 878 F.3d 794, 798\n(9th Cir. 2017) (“Where ‘it is more probable than not that the\njury would have reached the same verdict had it been\nproperly instructed,’ the erroneous instruction is harmless.”\n(quoting Clem v. Lomeli, 566 F.3d 1177, 1182 (9th Cir.\n2009))).\n\n As described above, the evidence here strongly supports\nthe conclusion that Otterman’s termination decision was\ninfluenced by Hanken’s retaliatory actions. Even fully\ncrediting Otterman’s testimony, he acknowledged that the\nmedia attention and Greisen’s recent reputation in the\ndepartment – almost certainly influenced by Hanken’s\nactions – played a role in his termination decision. Otterman\nfurther admitted that Hanken’s actions had placed the city in\n\f32 GREISEN V. HANKEN\n\nturmoil, which he felt “need[ed] to be resolved as soon as\npossible.” He did not provide formal reasons for the\ntermination but rather used a “no-cause” provision in\nGreisen’s contract. Cf. Lakeside-Scott, 556 F.3d at 809.\nNothing in his informal review process shielded Otterman\nfrom the influence of Hanken’s actions. In sum, the\nevidence strongly suggests Hanken’s actions were a causal\nfactor in Otterman’s termination decision, and thus it is more\nprobable than not a jury would have so found.\n\n Moreover, the instructions required the jury to find that\nany damages arose “naturally and necessarily” from\nHanken’s unlawful conduct. It would be illogical for a jury\nto find that Otterman’s decision to terminate Greisen\nfollowed naturally and necessarily from Hanken’s adverse\nemployment actions, but nevertheless was unrelated to those\nactions. 7\n\n We thus hold that any error in jury instruction number 17\nwas harmless because it is more probable than not that the\njury would have reached the same result had it been\ninstructed as Hanken argues.\n\n IV.\n\n The district court properly denied Hanken’s renewed\nmotion for judgment as a matter of law and motion for a new\ntrial. The judgment of the district court is therefore affirmed.\n\n AFFIRMED.\n\n\n\n\n 7\n We do not endorse the “naturally and necessarily” instruction or\nimply that it correctly stated the applicable law in this case.\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Doug Greisen v. Jon Hanken\\nCourt: U.S. Court of Appeals for the Ninth Circuit\\nDate decided: 2019-05-31\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFOR PUBLICATION\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE NINTH CIRCUIT\\n\\n\\nDOUG GREISEN, No. 17-35472\\n Plaintiff-Appellee,\\n D.C. No.\\n v. 3:14-cv-01399-SI\\n\\nJON HANKEN,\\n Defendant-Appellant. OPINION\\n\\n\\n\\n Appeal from the United States District Court\\n for the District of Oregon\\n Michael H. Simon, District Judge, Presiding\\n\\n Argued and Submitted October 11, 2018\\n Portland, Oregon\\n\\n Filed May 31, 2019\\n\\n Before: Raymond C. Fisher, Richard R. Clifton\\n and Consuelo M. Callahan, Circuit Judges.\\n\\n Opinion by Judge Fisher\\n\\f2 GREISEN V. HANKEN\\n\\n SUMMARY *\\n\\n\\n Civil Rights / Employment Retaliation\\n\\n The panel affirmed the district court’s judgment\\nfollowing a jury verdict in favor of Doug Greisen, a former\\nchief of police for the City of Scappoose, Oregon, in his\\naction brought pursuant to 42 U.S.C. § 1983 alleging that Jon\\nHanken, the former city manager, violated the First\\nAmendment by subjecting Greisen to adverse employment\\nactions in retaliation for his protected speech.\\n\\n After Greisen discussed his concerns with city council\\nmembers and government officials about the city’s\\naccounting and budgeting practices under Hanken, Hanken\\ninitiated investigations of Greisen, suspended him, placed\\nhim on an indefinite leave and prevented him from speaking\\npublicly, even as Hanken was releasing information about\\nthe investigations to the media. After a city review\\ncommittee recommended retraction of Greisen’s suspension,\\nHanken resigned.\\n\\n The panel held that: (1) Greisen provided sufficient\\ndetail about his speech to establish that it substantially\\ninvolved a matter of public concern; (2) he spoke as a private\\ncitizen rather than a public employee; (3) the district court\\nproperly concluded that Greisen’s retaliation claim could be\\nbased in part on Hanken’s own speech acts, in the form of\\ndefamatory communications to the media; (4) Hanken\\nwaived his argument that his actions were supported by an\\n\\n *\\n This summary constitutes no part of the opinion of the court. It\\nhas been prepared by court staff for the convenience of the reader.\\n\\f GREISEN V. HANKEN 3\\n\\nadequate justification; and (5) sufficient evidence supported\\nthe conclusion that Hanken’s retaliatory actions proximately\\ncaused Greisen’s termination, and any error in instructing\\nthe jury on proximate cause was harmless. The panel further\\nheld that Hanken was not entitled to qualified immunity.\\n\\n\\n COUNSEL\\n\\nThomas M. Christ (argued) and Julie A. Smith, Cosgrave\\nVergeer Kester LLP, Portland, Oregon, for Defendant-\\nAppellant.\\n\\nWilliam Allen Drew (argued) and John D. Ostrander, Elliott\\nOstrander & Preston P.C., Portland, Oregon, for Plaintiff-\\nAppellee.\\n\\n\\n OPINION\\n\\nFISHER, Circuit Judge:\\n\\n Doug Greisen was the chief of police for the City of\\nScappoose, Oregon. In 2012, after more than 10 years in that\\nposition, he became suspicious about the city’s accounting\\nand budgeting practices. He worried Jon Hanken, the city\\nmanager, was hiding something; he believed Hanken was\\nsuspiciously defensive about the budget, improperly delayed\\npaying invoices at the end of the fiscal year and had\\nweakened the city’s external auditing process. Greisen\\ndiscussed his concerns with various city council members\\nand others in city government over the following year. In\\nthe summer and fall of 2013, Hanken initiated three\\ninvestigations of Greisen, suspended him, placed him on an\\nindefinite leave and prevented him from speaking publicly,\\n\\f4 GREISEN V. HANKEN\\n\\neven as Hanken was releasing information about the\\ninvestigations to the media. After a city review committee\\nrecommended retraction of Greisen’s suspension, Hanken\\nresigned. Hanken’s replacement subsequently fired Greisen,\\nwho has since been unable to find work.\\n\\n Greisen sued under 42 U.S.C. § 1983, alleging Hanken\\nviolated the First Amendment by subjecting him to adverse\\nemployment actions in retaliation for his protected speech.\\nA jury found in Greisen’s favor, and Hanken appeals.\\n\\n We affirm. We hold: (1) Greisen provided sufficient\\ndetail about his speech to establish that it substantially\\ninvolved a matter of public concern; (2) Greisen spoke as a\\nprivate citizen rather than a public employee; (3) the district\\ncourt properly concluded that Greisen’s retaliation claim\\ncould be based in part on Hanken’s own speech acts, in the\\nform of defamatory communications to the media;\\n(4) Hanken waived his argument that his actions were\\nsupported by an adequate justification; and (5) sufficient\\nevidence supports the conclusion that Hanken’s retaliatory\\nactions proximately caused Greisen’s termination, and any\\nerror in instructing the jury on proximate cause was\\nharmless. We further hold Hanken is not entitled to qualified\\nimmunity.\\n\\n I.\\n\\n Jon Hanken, the former city manager of Scappoose, was\\nresponsible for overseeing the city’s budget and for annually\\nsubmitting a budget to the city council for review. 1\\nAccording to City Councilor Judi Ingham, Hanken generally\\n\\n 1\\n We state the facts in the light most favorable to Greisen. See\\nHarper v. City of Los Angeles, 533 F.3d 1010, 1021 (9th Cir. 2008).\\n\\f GREISEN V. HANKEN 5\\n\\nsubmitted his budget to the council soon before the\\nbeginning of the budget process, allowing little time for\\nreview, and he was defensive about issues relating to the\\nbudget. In mid-2012, the city had a particularly contentious\\nbudget approval process during which some city councilors\\nadvocated unsuccessfully for a budget that would add a\\npolice officer to the force. Although Hanken had told Chief\\nof Police Doug Greisen to support the budget at the hearing,\\nGreisen voiced neither support nor dissent. The next day,\\nHanken told Greisen: “I’m mad at you. You stay on your\\nside of City Hall. I don’t want to see you over here.”\\nGreisen understood this as an admonition to focus solely on\\nthe police department, and to leave the overall city budget to\\nHanken.\\n\\n Greisen then learned the city delayed paying police\\ndepartment invoices, sometimes for as long as four months,\\nbefore the end of the fiscal year on July 1. He became\\nsuspicious Hanken was hiding something, and he began\\nasking “a lot of” other people, including the city finance\\nadministrator, city councilors and other city department\\nheads, about the city’s budgeting practices during the\\nremainder of 2012 and early 2013. He learned the city was\\nwithholding payment on invoices from other departments as\\nwell. He also learned the city had transitioned from a four-\\nperson, on-site auditing team to a one-person, off-site\\nauditing firm, and he was concerned about the differences\\nbetween the firms: by contrast to the first auditing team, he\\nfound that the new auditor was less diligent, was unable to\\nstate an opinion on the city’s finances and followed different\\npractices that he worried were inconsistent with generally\\naccepted accounting principles. He discussed this issue with\\nthe city finance administrator and city councilors. He also\\ntook a college course on government budgeting and financial\\nmanagement.\\n\\f6 GREISEN V. HANKEN\\n\\n Around August 2012, Greisen tried to meet with Hanken\\nto discuss the budget. Hanken was not receptive; he told\\nGreisen that “Ms. Ingham will be the one that will ruin your\\ncareer here in the City of Scappoose.” He also said Greisen\\n“didn’t know what [he was] talking about” when it came to\\nbudgeting and financial management.\\n\\n In early 2013, Greisen was involved in a police pursuit\\nduring which he authorized an officer to perform a “PIT\\nmaneuver,” a method of stopping a fleeing car by bumping\\nit with a patrol vehicle, sending the fleeing car into a spin.\\nAlthough the maneuver was successful, another officer,\\nSergeant Doug Carpenter, wrote a memo to his lieutenant\\nalleging it was executed at a high speed without proper\\nprocedure. Carpenter’s criticism focused on the officer who\\nactually performed the PIT maneuver, but it implicated\\nGreisen’s actions as well. The lieutenant forwarded the\\nmemo to Hanken, along with his own memo clarifying\\nGreisen’s role in the maneuver and recommending an\\ninvestigation.\\n\\n Hanken arranged for an outside public agency to\\ninvestigate Greisen. The investigation’s purpose, according\\nto the investigator, was to determine “whether or not there\\nwere policy violations,” not to weigh whether a policy\\nviolation was justified. After interviewing various staff, the\\nagency submitted a 25-page report finding Greisen\\ncommitted 10 policy violations associated with the PIT\\nmaneuver. 2\\n\\n\\n 2\\n The violations included the findings that Greisen had: (1) “failed\\nto assume proper and informed control of a police pursuit”; (2) “failed to\\nproperly document the pursuit”; (3) “entered into a motor vehicle pursuit\\nwith insufficient knowledge and justification”; (4) “engaged in a pursuit,\\n\\f GREISEN V. HANKEN 7\\n\\n Upon receiving the report, Hanken suspended Greisen\\nfor two weeks without pay. According to the report’s author,\\nthe subject of such an investigation would “typically” have\\nthe opportunity to be heard after the report was complete, but\\nHanken did not afford Greisen this opportunity. In his\\nsuspension letter, Hanken wrote: “As I draft this letter, I\\ncannot help but wonder if you would be able to maintain\\nyour position if this report was known by or reported to the\\nnews media.”\\n\\n Greisen appealed his discipline to the city’s Personnel\\nReview Committee (PRC), which absolved him of\\nwrongdoing. The PRC characterized the outside agency’s\\nreport as “an erroneous mischaracterization of the events . . .\\nthat also purposely omitted pertinent and material facts, to\\narrive at a conclusion that the PRC finds untenable, out of\\ncontext and an egregious lack of professionalism.” In the\\nPRC’s view, the outside agency’s report was “not an\\nobjective review, but a prosecutorial document that was\\ncolored to arrive at a predetermined result.” The PRC\\nfurther found that “the degree of discipline issued to Police\\nChief Doug Greisen, for minor discrepancies of best\\npractices, is entirely out of proportion based on the totality\\nof the circumstances,” and it recommended that “the City\\n\\n\\n\\noperating an unauthorized and improperly equipped police vehicle”;\\n(5) “disregarded policy related to the established procedure for a\\nsecondary pursuing vehicle”; (6) “violated safe driving principles related\\nto pursuit driving”; (7) “failed to properly evaluate the need for a\\ncontinuation of a pursuit”; (8) “demonstrated a lack of knowledge related\\nto applicable standards and police practice related to pursuit intervention\\ntactics and authorized a prohibited tactic by an untrained subordinate\\nofficer”; (9) “failed to participate in annual training related to pursuit\\ndriving”; and (10) “failed to read and maintain a current working\\nknowledge of his departmental policy manual.”\\n\\f8 GREISEN V. HANKEN\\n\\nManager retract, and the Scappoose City Council oversee the\\nretraction [of], all discipline issued to Chief Greisen.”\\n\\n While the PIT maneuver investigation was ongoing,\\nHanken received another complaint about Greisen from\\nSergeant Carpenter, this time alleging Greisen had created a\\nhostile work environment. In response, Hanken initiated\\nanother investigation by the same outside agency and placed\\nGreisen on indefinite paid administrative leave pending the\\nresults of this investigation. Ultimately, the investigation\\nconcluded the allegations were not supported by substantial\\nevidence.\\n\\n In September 2013, while Greisen remained on leave,\\nHanken informed him the city would conduct a third\\ninvestigation into his activities. This investigation charged\\nGreisen with unauthorized financial practices relating to\\n$2,500 in donations to the police department that Greisen\\nkept in cash in his office. The investigation, conducted by\\nthe same outside agency, found five violations of city\\npolicy. 3\\n\\n Hanken sent letters to Greisen precluding him from\\nspeaking about the three investigations with anyone other\\nthan his wife and attorney. Hanken, however, released\\n\\n 3\\n The investigation found Greisen violated the city’s policy by:\\n(1) “having unaccounted for cash in his desk drawer”; (2) “adhering to\\nhis own set of rules related to expense reimbursement and submitting\\nreimbursement requests for meal expenses within 25 miles of\\nScappoose”; (3) “fail[ing] to make bank deposits in a timely manner”;\\n(4) “open[ing] and manag[ing] a bank account to be used as a slush fund\\nfor Police Department business and to avoid making purchases through\\nthe City’s budget process”; and (5) “fail[ing] to donate . . . gift cards\\n(recovered crime evidence) to a charitable organization as requested by\\nthe crime victim.”\\n\\f GREISEN V. HANKEN 9\\n\\ninformation about all three investigations to the media. In\\nSeptember 2013, soon after Greisen appealed his two-week\\nsuspension, Hanken released information about the first two\\ninvestigations. He admitted at trial that his release of\\ninformation about the ongoing second investigation “wasn’t\\nappropriate.”\\n\\n Similarly, shortly before he resigned as city manager,\\nHanken spoke to the media about the third investigation,\\nstating “that a bank bag was discovered in the chief’s desk\\nand that its contents raised questions about whether the chief\\nwas maintaining an unauthorized account.” Hanken also\\nsaid that, “[i]f any other officer had been caught using an\\nunauthorized account, they would have been fired on the\\nspot.” He further provided the media with a photo of the\\ncash that he admitted looked like a photo associated with a\\ndrug bust or money seizure. Hanken conceded at trial,\\nhowever, that others in the city knew about the money, that\\nit was associated with authorized accounts and that he spoke\\nto the press to ensure that the second and third investigations\\nhe had initiated were not discontinued.\\n\\n On November 8, 2013, less than a month after the PRC\\nissued its findings that Greisen’s discipline for the PIT\\nmaneuver was unfounded, Hanken resigned, citing these\\nfindings as the reason. He was replaced by Donald Otterman\\nin an interim capacity, and in early 2014 Otterman utilized a\\n“no-cause” clause in Greisen’s contract to terminate Greisen,\\nwho had not returned from administrative leave. Otterman\\nmade his decision after reviewing the investigator’s reports\\nand speaking with various people, whose views were highly\\npolarized.\\n\\n Greisen attempted to find other employment, but was\\nunable to do so. A manager from another city who\\nconsidered hiring Greisen testified that although he knew\\n\\f10 GREISEN V. HANKEN\\n\\nGreisen personally and respected him, he could not hire\\nGreisen as police chief given the negative media attention he\\nhad endured.\\n\\n In 2014, Greisen filed this action. As relevant here, he\\nbrought a First Amendment retaliation claim against Hanken\\nunder 42 U.S.C. § 1983. Before trial, Hanken moved for\\nsummary judgment on qualified immunity, and the district\\ncourt denied the motion. The claim was tried to a jury, which\\nfound in favor of Greisen, awarding him $1,117,488 in\\neconomic damages and $3,000,000 in non-economic\\ndamages. Hanken filed post-trial motions seeking a new trial\\non the ground that the district court’s jury instruction on\\ncausation was erroneous and seeking judgment as a matter\\nof law on other grounds. The district court denied the\\nmotions, and Hanken timely appealed.\\n\\n II.\\n\\n We review de novo a district court’s denial of a motion\\nfor judgment as a matter of law, but “[a] jury’s verdict must\\nbe upheld if it is supported by substantial evidence, . . . even\\nif it is also possible to draw a contrary conclusion.” Pavao\\nv. Pagay, 307 F.3d 915, 918 (9th Cir. 2002). We “must view\\nall evidence in the light most favorable to the nonmoving\\nparty, draw all reasonable inferences in the favor of the non-\\nmover, and disregard all evidence favorable to the moving\\nparty that the jury is not required to believe.” Harper v. City\\nof Los Angeles, 533 F.3d 1010, 1021 (9th Cir. 2008).\\n“‘[W]hen reviewing a motion for judgment as a matter of\\nlaw, we apply the law as it should be, rather than the law as\\nit was read to the jury,’ even if the party did not object to the\\njury instructions.” Fisher v. City of San Jose, 558 F.3d 1069,\\n1074 (9th Cir. 2009) (en banc) (alteration in original)\\n(quoting Pincay v. Andrews, 238 F.3d 1106, 1109 n.4 (9th\\nCir. 2001)).\\n\\f GREISEN V. HANKEN 11\\n\\n We review de novo a district court’s decision on\\nqualified immunity. See Elder v. Holloway, 510 U.S. 510,\\n516 (1994). Once the jury has reached a verdict, however,\\n“we must defer to the facts as they were reasonably found by\\nthe jury – we do not draw our own inferences from them.”\\nA.D. v. Cal. Highway Patrol, 712 F.3d 446, 459 (9th Cir.\\n2013).\\n\\n “We review de novo whether [a jury] instruction[]\\nmisstated the law.” Fireman’s Fund Ins. Cos. v. Alaskan\\nPride P’ship, 106 F.3d 1465, 1469 (9th Cir. 1997). An error\\nin instructing the jury in a civil case does not require reversal\\nif it is harmless. See Altera Corp. v. Clear Logic, Inc.,\\n424 F.3d 1079, 1087 (9th Cir. 2005).\\n\\n III.\\n\\n A First Amendment retaliation claim turns on a\\nsequential five-step series of questions:\\n\\n (1) whether the plaintiff spoke on a matter of\\n public concern; (2) whether the plaintiff\\n spoke as a private citizen or public employee;\\n (3) whether the plaintiff’s protected speech\\n was a substantial or motivating factor in the\\n adverse employment action; (4) whether the\\n state had an adequate justification for treating\\n the employee differently from other members\\n of the general public; and (5) whether the\\n state would have taken the adverse\\n employment action even absent the protected\\n speech.\\n\\nEng v. Cooley, 552 F.3d 1062, 1070 (9th Cir. 2009). The\\nplaintiff bears the burden on the first three questions. See id.\\nat 1070–71. If the plaintiff meets this burden, the burden\\n\\f12 GREISEN V. HANKEN\\n\\nshifts to the defendant on the last two questions. See id.\\nat 1071–72. When a constitutional violation has been\\nestablished, a plaintiff may recover damages that are\\nproximately caused thereby. See County of Los Angeles v.\\nMendez, 137 S. Ct. 1539, 1548–49 (2017). The plaintiff\\nmust also establish that the defendant’s retaliatory conduct\\nwas a but-for cause of the defendant’s damages. See Mendez\\nv. County of Los Angeles, 897 F.3d 1067, 1074 (9th Cir.\\n2018).\\n\\n Here, Greisen contends Hanken retaliated against him\\nfor discussing the city’s budgeting and accounting practices\\nwith other city officials. He contends that this speech\\ninvolved a matter of public concern – the mismanagement of\\ncity finances. He further contends that his discussions with\\ncity officials regarding suspected mismanagement were not\\npart of his job duties, and hence that he engaged in this\\nspeech as a private citizen rather than as a public employee.\\nHe alleges a number of adverse employment actions – e.g.,\\ncommencement of the PIT maneuver, hostile work\\nenvironment and financial mismanagement investigations;\\nthe two-week suspension; the indefinite administrative\\nleave; the “gag order” prohibiting him from speaking to the\\npress; and the false and inflammatory information Hanken\\nprovided to the press about him – and he contends that his\\nprotected speech was a substantial or motivating factor in\\nHanken’s decisions to take each of these actions. In\\naddition, although he does not contend that Otterman’s\\ndecision to terminate him was itself retaliatory, he seeks\\ndamages arising from the termination on the ground that it\\nwas proximately caused by Hanken’s retaliatory actions.\\n\\n Hanken challenges the verdict in favor of Greisen on the\\nfirst, second, third and fourth of the questions in the\\nsequential analysis. In addition, he challenges Greisen’s\\n\\f GREISEN V. HANKEN 13\\n\\nrecovery of damages arising from the termination. We\\naddress these contentions in turn.\\n\\n A number of Hanken’s arguments also implicate\\nqualified immunity. In resolving whether a government\\nofficial is entitled to qualified immunity, a court “must\\ndecide whether the facts that a plaintiff has alleged or shown\\nmake out a violation of a constitutional right,” and, if so,\\n“whether the right at issue was ‘clearly established’ at the\\ntime of defendant’s alleged misconduct.” Pearson v.\\nCallahan, 555 U.S. 223, 232 (2009) (citations omitted)\\n(quoting Saucier v. Katz, 533 U.S. 194, 201 (2001)). To\\ndetermine that a right was clearly established, the court\\n“must identify precedent as of [the date of the alleged\\nviolation] that put [the defendant] on clear notice” that his or\\nher actions were unconstitutional. S.B. v. County of San\\nDiego, 864 F.3d 1010, 1015 (9th Cir. 2017). “We do not\\nrequire a case directly on point, but existing precedent must\\nhave placed the statutory or constitutional question beyond\\ndebate.” Ashcroft v. al-Kidd, 563 U.S. 731, 741 (2011).\\nCourts must not define clearly established law at a high level\\nof generality. See Mullenix v. Luna, 136 S. Ct. 305, 308\\n(2015) (per curiam).\\n\\n A. Matter of Public Concern\\n\\n With respect to the first step in the analysis, “the plaintiff\\nbears the burden of showing that the speech addressed an\\nissue of public concern.” Eng, 552 F.3d at 1070.\\n\\n Whether speech is on a matter of public concern is a\\nquestion of law, determined by the court, and reviewed by\\nus de novo. See Berry v. Dep’t of Soc. Servs., 447 F.3d 642,\\n648 (9th Cir. 2006). The speech need not be entirely about\\nmatters of public concern, but it must “substantially involve”\\nsuch matters. Johnson v. Multnomah County, 48 F.3d 420,\\n\\f14 GREISEN V. HANKEN\\n\\n425 (9th Cir. 1995). “[S]peech warrants protection when it\\n‘seek[s] to bring to light actual or potential wrongdoing or\\nbreach of public trust.’” Barone v. City of Springfield,\\n902 F.3d 1091, 1098 (9th Cir. 2018) (second alteration in\\noriginal) (quoting Connick v. Myers, 461 U.S. 138, 148\\n(1983)). The “misuse of public funds . . . [is a] matter[] of\\ninherent public concern.” Johnson, 48 F.3d at 425.\\n\\n “Whether an employee’s speech addresses a matter of\\npublic concern must be determined by the content, form, and\\ncontext of a given statement, as revealed by the whole\\nrecord.” Connick, 461 U.S. at 147–48. “[T]he content of the\\nspeech is generally the most important.” Karl v. City of\\nMountlake Terrace, 678 F.3d 1062, 1069 (9th Cir. 2012). In\\nreviewing form and context, “we focus on the point of the\\nspeech, looking to such factors as the employee’s motivation\\nand the audience chosen for the speech.” Ulrich v. City &\\nCounty of San Francisco, 308 F.3d 968, 979 (9th Cir. 2002)\\n(citation and internal quotation marks omitted). This\\nanalysis seeks to determine whether the employee aimed “‘to\\nbring wrongdoing to light,’ not ‘merely to further some\\npurely private interest.’” Id. (quoting Havekost v. U.S. Dep’t\\nof Navy, 925 F.2d 316, 318 (9th Cir. 1991)). “[S]peech that\\ndeals with ‘individual personnel disputes and grievances’\\nand that would be of ‘no relevance to the public’s evaluation\\nof the performance of governmental agencies’ is generally\\nnot of ‘public concern.’” Coszalter v. City of Salem,\\n320 F.3d 968, 973 (9th Cir. 2003) (quoting McKinley v. City\\nof Eloy, 705 F.2d 1110, 1114 (9th Cir. 1983)).\\n\\n Hanken does not dispute that the potential\\nmismanagement of city funds is a matter of public concern.\\nHe argues, however, that he was entitled to judgment as a\\nmatter of law on this question on three independent grounds:\\n(1) the district court had insufficient information before it to\\n\\f GREISEN V. HANKEN 15\\n\\nconclude the speech involved matters of public concern;\\n(2) the speech did not involve matters of public concern,\\nbecause Greisen was motivated by a personal grievance\\nagainst him rather than exposing government wrongdoing;\\nand (3) qualified immunity.\\n\\n 1. The district court had sufficient information to\\n determine Greisen’s speech substantially involved\\n matters of public concern\\n\\n Hanken argues the district court lacked sufficient\\ninformation about the content, form and context of Greisen’s\\nspeech to conclude it substantially involved matters of public\\nconcern. Although Greisen testified about his discussions\\nwith other city officials, Hanken contends “he did not\\ndescribe the substantive content of those conversations in\\nany detail.” He contends the descriptions Greisen provided\\nwere insufficient “to allow a court to make a determination\\nthat [the] speech related to a matter of public concern.”\\nKurtz v. Vickrey, 855 F.2d 723, 730 n.4 (11th Cir. 1988); see\\nalso Nixon v. City & County of Denver, 784 F.3d 1364, 1369\\n(10th Cir. 2015); Moss v. City of Pembroke Pines, 782 F.3d\\n613, 620–21 (11th Cir. 2015). We disagree.\\n\\n We agree, of course, that a court must have sufficient\\ninformation about the content, form and context of speech to\\ndetermine whether it was on a matter of public concern. A\\nplaintiff, however, need not provide transcriptions of the\\nconversations. Here, Greisen provided enough. With regard\\nto the content of the speech, Greisen testified about the\\ndiscussions he had with the city finance administrator and\\nother department heads regarding Hanken’s practice of\\ndelaying payment of invoices. Greisen used these\\ndiscussions, among other things, to learn about how other\\ndepartments handled invoice payments. Greisen also\\ntestified that he discussed his concerns about the new auditor\\n\\f16 GREISEN V. HANKEN\\n\\nwith some city councilors and with the city finance\\nadministrator. His concerns included the fact that the auditor\\nwas not on-site, the auditor’s inability to offer an opinion\\nabout the city’s finances and the quality of the auditor’s\\nwritten reports. As to form and context, Greisen provided a\\ngeneral timeline, identified the roles of his interlocutors and\\ndescribed his motivations for the discussions. The district\\ncourt, therefore, had enough information before it.\\n\\n 2. The district court properly concluded the speech\\n substantially involved matters of public concern\\n\\n Even assuming the information was sufficient, Hanken\\nargues the district court erred by concluding that Greisen’s\\nspeech substantially involved matters of public concern. He\\nargues that, even if “the content of the speech does at first\\nglance look like it raises a public concern because it involves\\nthe city’s finances,” “the form and context suggest that the\\nspeech is really about a power struggle between plaintiff and\\ndefendant – more specifically, about a power play by\\nplaintiff.” Hanken maintains that Greisen’s speech “was\\nmore like the airing of an internal grievance, the grinding of\\na private ax, not [an] effort to provoke a public debate on an\\nissue of public concern.”\\n\\n The evidence does not support this contention. It shows\\nthat Greisen was interested in uncovering mismanagement\\ninvolving city funds. He spoke to other city officials to learn\\nabout the financial management process. He took a college\\ncourse on budgeting and finance. His interest in the welfare\\nof the city is clear from the record. His family had lived in\\nScappoose for 30 years, and he “was very involved in the\\ncommunity,” where he had “volunteered endlessly.” He also\\ntestified he was motivated by “the cop in [him]” to\\ninvestigate whether something was being hidden.\\n\\f GREISEN V. HANKEN 17\\n\\n That Greisen spoke privately to other city officials,\\nrather than publicly, does not show that he was motivated by\\na private grudge rather than a desire to detect and expose\\npotential mismanagement. The choice “to convey . . . views\\nprivately rather than publicly is not determinative of whether\\n. . . expression is entitled to protection.” Thomas v. City of\\nBeaverton, 379 F.3d 802, 810 (9th Cir. 2004). Private\\nspeech may serve to “bring wrongdoing to light.” Ulrich,\\n308 F.3d at 979 (quoting Havekost, 925 F.2d at 318).\\n\\n In sum, the district court properly concluded, based on\\nthe “content, form, and context” of Greisen’s speech, that his\\nconversations substantially involved a matter of public\\nconcern. Connick, 461 U.S. at 147.\\n\\n 3. Hanken is not entitled to qualified immunity on the\\n public concern issue\\n\\n By 1995, it was clearly established that the misuse of\\npublic funds is a matter of public concern. See Johnson,\\n48 F.3d at 425. Given the nature of Greisen’s concerns and\\nhis longtime connection to the community, Hanken could\\nnot reasonably have concluded that Greisen’s speech\\n“deal[t] with ‘individual personnel disputes and grievances’\\n. . . that would be of ‘no relevance to the public’s evaluation\\nof the performance of governmental agencies.’” Coszalter,\\n320 F.3d at 973 (quoting McKinley, 705 F.2d at 1114). The\\ndistrict court therefore properly denied qualified immunity.\\n\\n B. Private Citizen\\n\\n In a First Amendment retaliation case, the plaintiff also\\n“bears the burden of showing the speech was spoken in the\\ncapacity of a private citizen and not a public employee.”\\nEng, 552 F.3d at 1071.\\n\\f18 GREISEN V. HANKEN\\n\\n In Garcetti v. Ceballos, 547 U.S. 410, 421 (2006), the\\nSupreme Court held that, “when public employees make\\nstatements pursuant to their official duties, the employees\\nare not speaking as citizens for First Amendment purposes,\\nand the Constitution does not insulate their communications\\nfrom employer discipline.” “[S]tatements are made in the\\nspeaker’s capacity as citizen if the speaker had no official\\nduty to make the questioned statements, or if the speech was\\nnot the product of performing the tasks the employee was\\npaid to perform.” Posey v. Lake Pend Oreille Sch. Dist. No.\\n84, 546 F.3d 1121, 1127 n.2 (9th Cir. 2008) (alterations,\\ncitation and internal quotation marks omitted). We look to\\nthree non-exhaustive factors to make this assessment:\\n(1) whether “the employee confined his communications to\\nhis chain of command”; (2) whether “the subject matter of\\nthe communication” fell within the plaintiff’s regular job\\nduties; and (3) whether the “employee sp[oke] in direct\\ncontravention to his supervisor’s order[].” Dahlia v.\\nRodriguez, 735 F.3d 1060, 1074–75 (9th Cir. 2013) (en\\nbanc). The scope and content of a plaintiff’s official duties\\nare questions of fact, but a court must “independently . . .\\nevaluate the ultimate constitutional significance of the facts\\nas found.” Posey, 546 F.3d at 1129.\\n\\n 1. The district court properly determined Greisen\\n spoke as a private citizen\\n\\n Here, viewing the evidence in the light most favorable to\\nGreisen, every Dahlia factor favors the jury’s conclusion\\nthat Greisen spoke as a private citizen. With regard to the\\nfirst factor (chain of command), the record shows Greisen\\nhad conversations with the city finance administrator, city\\ncouncilors and at least three other department heads, none of\\nwhom were within his chain of command.\\n\\f GREISEN V. HANKEN 19\\n\\n With regard to the second factor (subject matter), Dahlia\\nnoted:\\n\\n [I]f a public employee raises within the\\n department broad concerns about corruption\\n or systemic abuse, it is unlikely that such\\n complaints can reasonably be classified as\\n being within the job duties of an average\\n public employee, except when the\\n employee’s regular job duties involve\\n investigating such conduct, e.g., when the\\n employee works for Internal Affairs or\\n another such watchdog unit.\\n\\n735 F.3d at 1075. Here, Greisen’s concerns related to\\nferreting out “corruption or systemic abuse” in city finances\\nand management, and these functions were not part of his\\nofficial duties as chief of police. His concerns about the\\nbudget related to secrecy and potential wrongdoing: a lack\\nof oversight on the part of the new auditor, Hanken’s\\nunwillingness to let anyone into the budgeting process and\\nthe failure to pay vendors on time. No evidence suggests\\nthese matters fell within Greisen’s regular job duties.\\n\\n With regard to the last factor (contravention of\\nsupervisors), there is strong evidence that Hanken, Greisen’s\\nsupervisor, did not want him discussing or looking into the\\noverall city budget or Hanken’s accounting practices.\\nHanken instructed Greisen to stay on his “side” of city hall,\\nand discouraged him from speaking to Councilor Ingham\\nabout the overall budget.\\n\\n Hanken does not argue that the Dahlia factors favor\\nreversal, but attempts to distinguish Dahlia, which involved\\na lower-ranking employee, on the basis that Greisen, as a\\npolice chief, had broader duties. See id. at 1063. He argues\\n\\f20 GREISEN V. HANKEN\\n\\nthis case is more analogous to Johnson v. Poway Unified\\nSchool District, 658 F.3d 954 (9th Cir. 2011), and Kennedy\\nv. Bremerton School District, 869 F.3d 813 (9th Cir. 2017).\\nPoway Unified held that, “because of the position of trust\\nand authority they hold and the impressionable young minds\\nwith which they interact, teachers necessarily act as teachers\\n. . . when at school or a school function, in the general\\npresence of students, in a capacity one might reasonably\\nview as official.” Poway Unified, 658 F.3d at 968. Kennedy\\nheld that a school coach acted as a public employee where\\nhis job duties “entailed both teaching and serving as a role\\nmodel and moral exemplar” and he was “acting in an official\\ncapacity in the presence of students and spectators.”\\nKennedy, 869 F.3d at 827. Hanken contends a police chief,\\nlike a teacher, occupies a “position of trust, authority, and\\nresponsibility,” which means that a police chief is\\n“necessarily acting as the police chief whenever he [is]\\ninteracting with other high- and higher-ranking city\\nofficials.”\\n\\n We disagree. We have never extended Kennedy and\\nPoway Unified beyond the school context, and the cases are\\ndistinguishable. Kennedy and Poway Unified focused on the\\n“impressionable and captive minds” to whom the employees\\nat issue espoused their views. Kennedy, 869 F.3d at 828\\n(quoting Poway Unified, 658 F.3d at 968). Leading a police\\nforce of adults does not implicate the same concerns, so\\nHanken’s analogies to the public school context are\\nunpersuasive.\\n\\n Hanken also looks to Moss v. City of Pembroke Pines,\\n782 F.3d 613 (11th Cir. 2015). There, the assistant fire chief\\n– who also served as an elected member of the city’s pension\\nboard – spoke to various employees within his department\\nregarding city-wide pension and wage issues that would\\n\\f GREISEN V. HANKEN 21\\n\\ninfluence the department. See id. at 616–17. In holding the\\ncommunications were within the plaintiff’s job duties, the\\ncourt noted the “[p]laintiff’s statements . . . were made in\\naccordance with his role as a liaison between the Fire Chief\\nand employees down the chain of command.” Id. at 620.\\nHere, by contrast, Greisen spoke outside his chain of\\ncommand and outside his defined role in the budget process.\\nMoss thus does not support Hanken’s position.\\n\\n 2. Hanken is not entitled to qualified immunity on the\\n private citizen issue\\n\\n In Karl v. City of Mountlake Terrace, 678 F.3d 1062 (9th\\nCir. 2012), we held that “a reasonable official would . . .\\nhave known that a public employee’s speech on a matter of\\npublic concern is protected if the speech is not made\\npursuant to her official job duties, even if the testimony itself\\naddresses matters of employment.” Id. at 1074 (citing\\nGarcetti, 547 U.S. at 421; Eng, 552 F.3d at 1075–76; Posey,\\n546 F.3d at 1126–27). Viewing the record in the light most\\nfavorable to Greisen, Hanken told Greisen on two occasions\\nthat Greisen was not to concern himself with issues relating\\nto the management of the overall city budget. No evidence\\nsuggests a reasonable official in Hanken’s position would\\nhave believed analyzing the timing of invoice payments in\\nother departments or city-wide audit practices was within\\nGreisen’s job duties. Hanken is thus not entitled to qualified\\nimmunity.\\n\\n C. Adverse Employment Action and Causation\\n\\n At the third step in a First Amendment retaliation\\nanalysis, the plaintiff bears the burden of showing the state\\ntook an adverse employment action against the plaintiff and\\nthat the plaintiff’s speech was a substantial or motivating\\nfactor in the adverse action. See Eng, 552 F.3d at 1071.\\n\\f22 GREISEN V. HANKEN\\n\\n Thus, to find in Greisen’s favor on the First Amendment\\nretaliation claim, the jury had to find Greisen suffered an\\nadverse employment action. “In a First Amendment\\nretaliation case, an adverse employment action is an act that\\nis reasonably likely to deter employees from engaging in\\nconstitutionally protected speech.” Coszalter, 320 F.3d\\nat 970. The jury was instructed on several potential adverse\\nemployment actions here, including two that involved\\nHanken’s own speech: “misrepresenting . . . accounts to the\\npress as ‘unauthorized’ before the completion of the\\ninvestigation; and giving the press access to an inventory\\nphotograph that . . . Greisen says was ‘inflammatory.’”\\n\\n Hanken argues the district court should have granted\\npartial judgment as a matter of law on the ground that his\\ncommunications with the media “do not qualify as adverse\\nemployment actions because they involved the exercise of\\nhis own free speech rights.” Alternatively, he contends he is\\nentitled to qualified immunity on this basis.\\n\\n “Retaliation claims involving government speech\\nwarrant a cautious approach by courts,” because\\n“[r]estricting the ability of government decisionmakers to\\nengage in speech risks interfering with their ability to\\neffectively perform their duties” and “ignores the competing\\nFirst Amendment rights of the officials themselves.”\\nMulligan v. Nichols, 835 F.3d 983, 989 (9th Cir. 2016). “[A]\\nbalance must be struck between the citizen’s right to exercise\\nhis First Amendment rights and the public official’s personal\\nFirst Amendment rights, as well as his duty to the public to\\nspeak out about matters of public concern.” Suarez Corp.\\nIndus. v. McGraw, 202 F.3d 676, 687 n.13 (4th Cir. 2000).\\nThus, we have on several occasions rejected retaliation\\nclaims based exclusively on retaliatory speech, noting that\\n“[i]t would be the height of irony, indeed, if mere speech, in\\n\\f GREISEN V. HANKEN 23\\n\\nresponse to speech, could constitute a First Amendment\\nviolation.” Nunez v. City of Los Angeles, 147 F.3d 867, 875\\n(9th Cir. 1998); see also Mulligan, 835 F.3d at 989–91; Gini\\nv. Las Vegas Metro. Police Dep’t, 40 F.3d 1041, 1045 (9th\\nCir. 1994).\\n\\n We have, however, held that retaliatory speech can serve\\nas a basis for liability for a First Amendment retaliation\\nclaim under at least two circumstances.\\n\\n First, a First Amendment retaliation claim may be based\\non retaliatory speech when that speech is part of a campaign\\nof harassment designed to burden the plaintiff’s protected\\nexpression. In Allen v. Scribner, 812 F.2d 426 (9th Cir.\\n1987), for example, the plaintiff alleged “he was the subject\\nof continued harassment designed both to prevent him from\\nvoicing his opinion and to punish him for his having already\\ndone so.” Id. at 429. Specifically, he alleged the defendants\\nintimidated him, threatened him, harassed him and “made\\ndefamatory statements to the media with the intent of\\ndiscrediting him.” Id. In addition, he alleged he was\\ntransferred in retaliation for his protected speech. See id.\\n\\n We rejected the defendants’ argument that “any\\nallegation of harassment grounded in a claim of defamation”\\nwas not actionable. See id. at 434 n.17. We accepted the\\nproposition that, “to establish a claim under § 1983, more\\nmust be involved than defamation by a state official.” Id.\\nBut that principle was inapplicable to the facts of the case:\\n“Here, something more is involved. [The plaintiff] alleges\\nthat the defamation he suffered was part of a concerted effort\\nto burden his first amendment expression.” Id.; see also\\nCoszalter, 320 F.3d at 975–77 (citing Allen and holding that\\n“engaging in [a] campaign[] of harassment and humiliation”\\ncan be the basis for liability in a First Amendment retaliation\\nclaim).\\n\\f24 GREISEN V. HANKEN\\n\\n Second, even when it is not part of a campaign of\\nharassment designed to burden the plaintiff’s protected\\nexpression, retaliatory speech may serve as the basis for a\\nFirst Amendment retaliation claim when it “intimat[es] that\\nsome form of punishment or adverse regulatory action would\\nfollow.” Brodheim v. Cry, 584 F.3d 1262, 1270 (9th Cir.\\n2009) (quoting Okwedy v. Molinari, 333 F.3d 339, 343 (2d\\nCir. 2003)); see Goldstein v. Galvin, 719 F.3d 16, 30–31 (1st\\nCir. 2013); Hutchins v. Clarke, 661 F.3d 947, 956 (7th Cir.\\n2011); Balt. Sun Co. v. Ehrlich, 437 F.3d 410, 417 (4th Cir.\\n2006); X-Men Sec., Inc. v. Pataki, 196 F.3d 56, 71 (2d Cir.\\n1999); see also Mulligan, 835 F.3d at 989 n.5 (rejecting the\\nproposition that “speech by government officials can never\\ngive rise to a claim of First Amendment retaliation,” id.\\n(emphasis omitted), and explaining that “informal measures,\\nsuch as the threat of invoking legal sanctions and other\\nmeans of coercion, persuasion, and intimidation, can violate\\nthe First Amendment,” id. (internal quotation marks and\\nalteration omitted) (quoting White v. Lee, 227 F.3d 1214,\\n1228 (9th Cir. 2000))). 4\\n\\n This case falls squarely within Allen. As in Allen,\\nGreisen’s retaliation claim involves something more than\\ndefamation by a public official. He alleged the defamation\\nhe suffered was part of a concerted effort to deter him from,\\nand punish him for, engaging in constitutionally protected\\nspeech. He alleged Hanken engaged in a campaign of\\nharassment against him that included not only defamatory\\ncommunications with the press but also a suspension, an\\n\\n 4\\n We have left undecided the question of whether retaliatory speech\\nmay also be actionable in some circumstances when it involves the\\n“disclosure of deeply private personal details.” Mulligan, 835 F.3d\\nat 990; see also Balt. Sun, 437 F.3d at 417; Bloch v. Ribar, 156 F.3d 673,\\n676 (6th Cir. 1998).\\n\\f GREISEN V. HANKEN 25\\n\\nindefinite leave, a one-sided gag order and the instigation of\\nthree spurious investigations. Greisen thus permissibly\\npremised his retaliation claim in part on Hanken’s\\ncommunications with the media. In addition, Hanken is not\\nentitled to qualified immunity on the theory that he would\\nnot reasonably have known at the time of his actions that a\\nFirst Amendment retaliation claim could be based in part on\\nacts of retaliatory speech. In light of Allen, decided in 1987,\\nhe was on notice. 5\\n\\n D. Adequate Justification: Pickering Balancing\\n\\n “[I]f the plaintiff has passed the first three steps, the\\nburden shifts to the government to show that under the\\nbalancing test established by Pickering, the state’s legitimate\\nadministrative interests outweigh the employee’s First\\nAmendment rights.” Eng, 552 F.3d at 1071 (alterations and\\ninternal quotation marks omitted). “This inquiry, known as\\nthe Pickering balancing test, asks ‘whether the relevant\\ngovernment entity had an adequate justification for treating\\nthe employee differently from any other member of the\\ngeneral public.’” Id. (quoting Garcetti, 547 U.S. at 418); see\\nPickering v. Bd. of Educ., 391 U.S. 563, 568 (1968).\\n\\n Hanken seeks to raise this defense here, but “an appellate\\ncourt will not consider issues not properly raised before the\\ndistrict court.” Smith v. Marsh, 194 F.3d 1045, 1052 (9th\\nCir. 1999) (emphasis added). Here, Hanken briefly asserted\\nthis argument for the first time in his reply brief on his\\n\\n 5\\n Because this case falls squarely within Allen, we need not\\ndetermine whether Hanken’s communications with the media also\\nintimated that some form of punishment or adverse regulatory action\\nwould follow. See Brodheim, 584 F.3d at 1269-71.\\n\\f26 GREISEN V. HANKEN\\n\\nrenewed motion for judgment as a matter of law, and the\\ndistrict court appropriately declined to consider it. See\\nZamani v. Carnes, 491 F.3d 990, 997 (9th Cir. 2007) (“The\\ndistrict court need not consider arguments raised for the first\\ntime in a reply brief.”). 6 The argument, therefore, is waived.\\n\\n Hanken argues the question is “purely one of law,”\\nwhich could allow us to exercise discretion to review the\\nargument under Bolker v. Commissioner of Internal\\nRevenue, 760 F.2d 1039, 1042 (9th Cir. 1985). We disagree.\\nAlthough the Pickering balancing test “is ultimately a legal\\nquestion, . . . its resolution often entails underlying factual\\ndisputes.” Eng, 552 F.3d at 1071. Here, the record is\\nundeveloped. It is thus inappropriate to review Hanken’s\\nargument under the pure question of law exception because\\nwe “cannot rule out the possibility that . . . the merits of the\\n. . . argument cannot be resolved without further hearings\\nbefore the district court.” A-1 Ambulance Serv., Inc. v.\\nCounty of Monterey, 90 F.3d 333, 339 (9th Cir. 1996).\\n\\n E. Damages\\n\\n As noted, Greisen did not argue that his termination was\\nan adverse employment action. He argued, however, that it\\n\\n\\n\\n\\n 6\\n Although Hanken briefly alluded to Pickering balancing in his\\nopening brief in support of his Rule 50(b) motion, this cryptic allusion\\nwas insufficient to raise the issue. See Whittaker Corp. v. Execuair\\nCorp., 953 F.2d 510, 515 (9th Cir. 1992) (an argument is properly raised\\nbelow when it is “raised sufficiently for the trial court to rule on it”\\n(quoting In re E.R. Fegert, Inc., 887 F.2d 955, 957 (9th Cir. 1989)).\\nBecause the issue was waived for this reason, we need not consider other\\npossible bases for waiver. See, e.g., EEOC v. Go Daddy Software, Inc.,\\n581 F.3d 951, 961 (9th Cir. 2009).\\n\\f GREISEN V. HANKEN 27\\n\\nwas proximately caused by Hanken’s actions. He therefore\\nsought damages arising from his termination.\\n\\n Hanken challenges these damages. Quoting Lakeside-\\nScott v. Multnomah County, 556 F.3d 797, 804 (9th Cir.\\n2009), he contends his conduct did not proximately cause\\nGreisen’s termination, because Otterman, Hanken’s\\nsuccessor, “made a wholly independent, legitimate decision\\nto discharge” Greisen, and any reasonable jury would have\\nso found. Alternatively, he asks us to remand for a new trial\\nbecause jury instruction number 17 misstated the law of\\nproximate cause by failing to require a direct relation\\nbetween Hanken’s actions and Greisen’s termination. See\\nStaub v. Proctor Hosp., 562 U.S. 411, 419 (2011)\\n(“Proximate cause requires only ‘some direct relation\\nbetween the injury asserted and the injurious conduct\\nalleged,’ and excludes only those ‘link[s] that are too remote,\\npurely contingent, or indirect.’” (alteration in original)\\n(quoting Hemi Grp., LLC v. City of New York, 559 U.S. 1, 9\\n(2010))). This failure, in his view, prevented the jury from\\nconsidering whether Otterman’s decision to terminate\\nGreisen severed the chain of causation. We address these\\ncontentions in turn.\\n\\n 1. Substantial evidence supports the jury’s conclusion\\n that Hanken’s actions proximately caused\\n Greisen’s termination\\n\\n We are not persuaded by Hanken’s argument that any\\nreasonable jury would have concluded that his actions did\\nnot proximately cause Greisen’s termination. The Supreme\\nCourt considered an analogous issue in Staub. There, the\\nplaintiff, a member of the United States Army Reserve,\\nbrought a claim under the Uniformed Services Employment\\nand Reemployment Rights Act, claiming his employer\\ndischarged him as a result of his military obligations. See id.\\n\\f28 GREISEN V. HANKEN\\n\\nat 415. The plaintiff’s biased supervisor had reported the\\nplaintiff to a superior, who reviewed the plaintiff’s file and\\nfired him partially on the basis of the supervisor’s report.\\nSee id. at 414–15.\\n\\n The Court framed the question before it as whether “an\\nemployer may be held liable for employment discrimination\\nbased on the discriminatory animus of an employee who\\ninfluenced, but did not make, the ultimate employment\\ndecision.” Id. at 413. Answering this question required the\\nCourt to consider whether “the biased supervisor’s action”\\nwas “a proximate cause of the ultimate employment action”\\n– the precise question at issue here. Id. at 420, 422. The\\nproximate cause inquiry, in turn, hinged on whether the\\nbiased supervisor’s actions “were causal factors underlying\\n[the] decision to fire” the plaintiff. Id. at 423. The Court\\nexplained:\\n\\n [I]f the employer’s investigation results in an\\n adverse action for reasons unrelated to the\\n supervisor’s original biased action . . . , then\\n the employer will not be liable. But the\\n supervisor’s biased report may remain a\\n causal factor if the independent investigation\\n takes it into account without determining that\\n the adverse action was, apart from the\\n supervisor’s recommendation, entirely\\n justified.\\n\\nId. at 421.\\n\\n Under Staub, the question is whether Hanken’s actions\\nwere a “causal factor” in Otterman’s decision to fire Greisen\\n– i.e., whether Otterman fired Greisen “for reasons unrelated\\nto [Hanken’s] original biased action[s].” Id. Compare\\nLakeside-Scott, 556 F.3d at 807–09 (holding that a biased\\n\\f GREISEN V. HANKEN 29\\n\\nsupervisor’s actions, including initiating an investigation\\nthat led to the plaintiff’s discharge, were not causal factors\\nin the plaintiff’s discharge where the ultimate termination\\ndecision was based on a thorough investigation that was\\nindependent of the supervisor’s improper influence), with\\nPoland v. Chertoff, 494 F.3d 1174, 1182–84 (9th Cir. 2007)\\n(holding that a biased supervisor’s actions were causal\\nfactors in the plaintiff’s transfer where the employer failed\\nto shield the disciplinary inquiry from the supervisor’s\\ninfluence, the supervisor played a role in selecting witnesses\\nfor the inquiry and the supervisor’s memo that initiated the\\ninquiry was available to the disciplinary board making the\\nultimate transfer decision).\\n\\n Here, the evidence does not show that Otterman’s\\ndecision was “unrelated to” Hanken’s conduct. See Staub,\\n562 U.S. at 421. Hanken points to Otterman’s testimony that\\nhis decision was based on the results of the three\\ninvestigations Hanken initiated. There is some reason to\\ndoubt that these investigations were independent. Hanken\\nselected the outside agency that performed the\\ninvestigations, and, more strikingly, he admitted at trial that\\nwhen he learned that the city council was considering ending\\nthe investigations, he made a false report to the media in a\\nseemingly successful effort to keep them going.\\n\\n Even assuming, however, that the investigations were\\nfully independent and that Hanken cannot be held\\nresponsible for what they uncovered, cf. Lakeside-Scott,\\n556 F.3d at 806–07, they are not the whole story. Otterman\\nacknowledged that there were “some other things”\\nmotivating his decision, including the negative media\\nattention surrounding Greisen and the fact that “the police\\ndepartment employees felt that they could no longer rely on\\n. . . Greisen as the chief of police.” Hanken’s wrongful\\n\\f30 GREISEN V. HANKEN\\n\\nactions – which amounted to a campaign of public\\nhumiliation through, among other things, false and\\nmisleading representations – almost certainly played a direct\\nand substantial role in creating or exacerbating these\\nconditions. Otterman did not assert that he made any effort\\nto shield his termination decision from the influence of\\nHanken’s actions. Cf. Poland, 494 F.3d at 1183. And there\\nis no contemporaneous evidence that Otterman’s decision\\nwas based solely on the investigation results. On the\\ncontrary, rather than identifying a particular justification for\\nthe dismissal – like the employer did in Lakeside-Scott,\\n556 F.3d at 809 – he concluded “that the best situation for\\nthe City was to exercise the, quote, ‘no-cause,’ unquote,\\nclause” in Greisen’s contract. Otterman further made clear\\nthat Hanken’s actions created an environment of unrest that\\nframed and dictated the timeline of the decision:\\n\\n There were several articles about [Greisen]\\n and about what was going on in the City. . . .\\n The police chief was on administrative leave.\\n And that causes commotion or turmoil in the\\n organization and needs to be resolved as soon\\n as possible.\\n\\nOn this evidence, a reasonable jury could have found that\\nHanken’s actions were a causal factor in Otterman’s\\ndecision.\\n\\n 2. Any error in the jury instruction on proximate\\n cause was harmless\\n\\n As noted, Hanken argues he is entitled to a new trial\\nbecause jury instruction number 17 misstated the law of\\nproximate cause by failing to require a direct relation\\nbetween Hanken’s actions and Greisen’s termination. In\\nrelevant part, that instruction stated:\\n\\f GREISEN V. HANKEN 31\\n\\n You can award money only for those\\n damages that arise naturally and necessarily\\n from the violation of law that the Plaintiff has\\n proven. . . .\\n\\n If you find that the Defendant wrongfully\\n retaliated against the Plaintiff in violation of\\n the Plaintiff’s constitutional rights, and if you\\n also find that it was reasonably foreseeable\\n that such wrongful retaliatory conduct, if any,\\n by the Defendant would render the Plaintiff\\n unable to maintain either his position or his\\n salary (either at the City of Scappoose or at\\n another employer), then you may award the\\n Plaintiff any non-speculative, foreseeable\\n economic damages caused by the\\n Defendant’s wrongful retaliatory conduct.\\n\\n We need not determine whether jury instruction\\nnumber 17 was erroneous because any error was harmless.\\nSee Dunlap v. Liberty Nat. Prods., Inc., 878 F.3d 794, 798\\n(9th Cir. 2017) (“Where ‘it is more probable than not that the\\njury would have reached the same verdict had it been\\nproperly instructed,’ the erroneous instruction is harmless.”\\n(quoting Clem v. Lomeli, 566 F.3d 1177, 1182 (9th Cir.\\n2009))).\\n\\n As described above, the evidence here strongly supports\\nthe conclusion that Otterman’s termination decision was\\ninfluenced by Hanken’s retaliatory actions. Even fully\\ncrediting Otterman’s testimony, he acknowledged that the\\nmedia attention and Greisen’s recent reputation in the\\ndepartment – almost certainly influenced by Hanken’s\\nactions – played a role in his termination decision. Otterman\\nfurther admitted that Hanken’s actions had placed the city in\\n\\f32 GREISEN V. HANKEN\\n\\nturmoil, which he felt “need[ed] to be resolved as soon as\\npossible.” He did not provide formal reasons for the\\ntermination but rather used a “no-cause” provision in\\nGreisen’s contract. Cf. Lakeside-Scott, 556 F.3d at 809.\\nNothing in his informal review process shielded Otterman\\nfrom the influence of Hanken’s actions. In sum, the\\nevidence strongly suggests Hanken’s actions were a causal\\nfactor in Otterman’s termination decision, and thus it is more\\nprobable than not a jury would have so found.\\n\\n Moreover, the instructions required the jury to find that\\nany damages arose “naturally and necessarily” from\\nHanken’s unlawful conduct. It would be illogical for a jury\\nto find that Otterman’s decision to terminate Greisen\\nfollowed naturally and necessarily from Hanken’s adverse\\nemployment actions, but nevertheless was unrelated to those\\nactions. 7\\n\\n We thus hold that any error in jury instruction number 17\\nwas harmless because it is more probable than not that the\\njury would have reached the same result had it been\\ninstructed as Hanken argues.\\n\\n IV.\\n\\n The district court properly denied Hanken’s renewed\\nmotion for judgment as a matter of law and motion for a new\\ntrial. The judgment of the district court is therefore affirmed.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 7\\n We do not endorse the “naturally and necessarily” instruction or\\nimply that it correctly stated the applicable law in this case.\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2251,"cells":{"id":{"kind":"number","value":4625276,"string":"4,625,276"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Arizona Libertarian Party v. Katie Hobbs"},"decision_date":{"kind":"string","value":"2019-05-31"},"docket_number":{"kind":"string","value":"17-16491"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Ninth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: J. Clifford Wallace, A. Wallace Tashima, and M. Margaret McKeown, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"McKEOWN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"FOR PUBLICATION\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE NINTH CIRCUIT\\n\\n\\nARIZONA LIBERTARIAN PARTY; No. 17-16491\\nMICHAEL KIELSKY,\\n Plaintiffs-Appellants, D.C. No.\\n 2:16-cv-01019-\\n v. DGC\\n\\nKATIE HOBBS, in her official\\ncapacity as Secretary of State of OPINION\\nArizona,\\n Defendant-Appellee.\\n\\n\\n\\n Appeal from the United States District Court\\n for the District of Arizona\\n David G. Campbell, District Judge, Presiding\\n\\n Argued and Submitted March 12, 2019\\n San Francisco, California\\n\\n Filed May 31, 2019\\n\\n Before: J. Clifford Wallace, A. Wallace Tashima, and\\n M. Margaret McKeown, Circuit Judges.\\n\\n Opinion by Judge McKeown\\n\\f2 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\n SUMMARY *\\n\\n\\n Civil Rights / Elections\\n\\n The panel affirmed the district court’s summary\\njudgment in favor of Arizona’s Secretary of State in an\\naction brought by the Arizona Libertarian Party challenging,\\nunder the First and Fourteenth Amendments, a state law\\nrequiring up to 1% of voters eligible to participate in\\nArizona’s primary to sign a nominating petition for a\\nLibertarian candidate to earn a place on the primary ballot.\\n\\n Applying the balancing framework set forth in Anderson\\nv. Celebrezze, 460 U.S. 780 (1983), and Burdick v. Takushi,\\n504 U.S. 428 (1992), the panel first held that the State’s\\nsignature requirement imposed a minimal burden on the\\nLibertarian Party’s right to access the primary ballot.\\nAccordingly, the panel determined that a less exacting\\nscrutiny was appropriate. The panel concluded that\\nArizona’s signature requirements reasonably furthered\\nArizona’s regulatory interest in preventing voter confusion,\\nballot overcrowding, and frivolous candidacies and justified\\nthe modest burden on the Libertarian Party’s right to ballot\\naccess.\\n\\n The panel rejected the Libertarian Party’s contention that\\nthe Arizona law infringed upon its right to free association\\nby effectively requiring its candidates to solicit signatures\\nfrom non-members. The panel held that any burden on the\\nLibertarian Party’s associational freedom was modest, and\\n\\n *\\n This summary constitutes no part of the opinion of the court. It\\nhas been prepared by court staff for the convenience of the reader.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 3\\n\\nagain applying less exacting scrutiny, the panel credited\\nArizona’s important interests to justify the reasonable\\nrequirements.\\n\\n The panel further rejected the Libertarian Party’s\\ncontention that Arizona’s signature requirement violated\\nequal protection, noting that the Libertarian, Democratic,\\nand Republican Parties were all subject to the same statutory\\nrequirements. The panel observed no equal protection issue\\nin Arizona’s treatment of the Green Party, a new party that\\nwas subject to different statutory requirements.\\n\\n\\n COUNSEL\\n\\nOliver B. Hall (argued), Center for Competitive Democracy,\\nWashington, D.C., for Plaintiffs-Appellants.\\n\\nKara M. Karlson (argued) and Joseph E. La Rue, Assistant\\nAttorneys General; Mark Brnovich, Attorney General;\\nOffice of the Attorney General, Phoenix, Arizona; for\\nDefendant-Appellee.\\n\\n\\n OPINION\\n\\nMcKEOWN, Circuit Judge:\\n\\n Once again, we have before us a challenge to Arizona’s\\nrequirements to earn a place on the ballot. See, e.g., Ariz.\\nGreen Party v. Reagan, 838 F.3d 983 (9th Cir. 2016); Nader\\nv. Brewer, 531 F.3d 1028 (9th Cir. 2008). The Arizona\\nLibertarian Party challenges under the First and Fourteenth\\nAmendments a state law requiring up to 1% of voters eligible\\nto participate in its primary to sign a nominating petition for\\n\\f4 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\na Libertarian candidate to earn a place on the primary ballot.\\nThe district court granted summary judgment to the Arizona\\nSecretary of State (the “Secretary”), and we affirm.\\n\\n BACKGROUND\\n\\n Under Arizona law, there are two types of political\\nparties: “established” parties and “new” parties. A party is\\n“established” in a jurisdiction if it (i) obtained at least 5% of\\nthe total votes cast in the prior general election, or\\n(ii) maintains membership exceeding 0.66% of registered\\nvoters in that jurisdiction. Ariz. Rev. Stat. § 16-804\\n(applying to state, county, city, and town elections). An\\nestablished party is entitled to “continued representation” on\\nthe general election ballot. Id. The Libertarian, Democratic,\\nand Republican Parties are established statewide. 1\\n\\n Before 2016, to qualify for the primary ballot, an\\nestablished party candidate needed to submit signatures 2\\nexceeding a certain percentage (ranging between 0.5% and\\n2%, depending on the office sought) of the party’s registered\\nvoters in the jurisdiction where he sought election. Ariz.\\nRev. Stat. § 16-322(A) (2015). A candidate was permitted\\nto submit signatures from party members, members of any\\n 1\\n The Libertarian Party satisfies the voter registration requirement,\\nand the Democratic and Republican Parties satisfy both requirements.\\nAs of January 1, 2019, Arizona had 1.31 million registered Republicans,\\n1.17 million registered Democrats, and 32,056 registered Libertarians.\\nAriz. Sec. of State, Voter Registration & Historical Election Data,\\nhttps://azsos.gov/elections/voter-registration-historical-election-data\\n(last visited May 7, 2019).\\n 2\\n A voter may only sign one nominating petition per office per\\nelection, unless more than one candidate is to be elected to that office.\\nAriz. Rev. Stat. § 16-321(A).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 5\\n\\nnew party, or unaffiliated registered voters. 3 Id.\\n§ 16-321(D).\\n\\n In 2015, the Arizona legislature amended the signature\\nrequirements for established party candidates. 2015 Ariz.\\nSess. Laws Ch. 293, §§ 2–3 (H.B. 2608). Now, to qualify\\nfor a primary ballot, an established party candidate must\\nsubmit signatures exceeding a certain percentage of\\n“qualified signer[s],” which include the party’s registered\\nvoters, as well as all new party voters and unaffiliated\\nregistered voters. Ariz. Rev. Stat. § 16-321(F). The\\namendments reduced the signature threshold for each office\\nto between 0.25% and 1%. Id. § 16-322(A). In 2016—the\\nfirst election governed by the amended rules—there\\nwere significantly fewer Libertarian candidates on the\\nprimary and general election ballots than in prior elections.\\nSee generally Ariz. Sec. of State, Historical Election\\nResults & Information, https://azsos.gov/elections/\\nvoter-registration-historical-election-data/historical-election-\\nresults-information (last visited May 7, 2019) (collecting\\ndata for recent Arizona elections).\\n\\n A “new” party is subject to different rules. A new party\\nmust first submit a petition for recognition and signatures\\nfrom eligible voters exceeding 1.33% of total votes cast\\nstatewide in the prior gubernatorial election. Ariz. Rev. Stat.\\n§§ 16-801(A), 16-803. After doing so, the party’s\\ncandidates are eligible to pursue placement on the primary\\nand general election ballots for the next four years. Ariz.\\nRev. Stat. § 16-801(B). To retain its recognition and ballot\\n\\n 3\\n As of January 1, 2019, Arizona had 1.25 million unaffiliated\\nregistered voters. Ariz. Sec. of State, Voter Registration & Historical\\nElection Data, https://azsos.gov/elections/voter-registration-historical-\\nelection-data (last visited May 7, 2019).\\n\\f6 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\neligibility at the end of the four years, the party must either\\nqualify as an established party or file another petition for\\nrecognition and the accompanying signatures. Id.; see Ariz.\\nRev. Stat. §§ 16-803–04.\\n\\n To qualify for the primary ballot, a new party candidate\\nmust submit signatures exceeding 0.1% “of the total vote for\\nthe winning candidate or candidates for governor or\\npresidential electors at the last general election within the\\ndistrict.” Ariz. Rev. Stat. § 16-322(C). The Arizona Green\\nParty first qualified as a new party in 1990, and, never having\\nqualified as an established party, has successfully re-filed\\npetitions for new party recognition and the accompanying\\nsignatures several times, most recently in 2014. 4 Since the\\nbeginning of 2017, Arizona has permitted digital solicitation\\nand streamlined submission of voter signatures through an\\nonline portal. Ariz. Rev. Stat. §§ 16-316–18.\\n\\n Under Arizona law, an established party member may\\nnot vote in another party’s primary, but it is up to the\\nestablished parties to decide whether new party members or\\nunaffiliated voters can participate in their primaries. See\\nAriz. Rev. Stat. § 16-467. 5 The Libertarian Party excludes\\n\\n\\n\\n\\n 4\\n As of January 1, 2019, the Green Party had 6,450 registered\\nmembers in Arizona. Ariz. Sec. of State, Voter Registration & Historical\\nElection Data, https://azsos.gov/elections/voter-registration-historical-\\nelection-data (last visited May 7, 2019).\\n\\n 5\\n A state may not keep a party from welcoming unaffiliated voters\\nto participate in its primary, Tashjian v. Republican Party of Conn.,\\n479 U.S. 208, 213–29 (1986), though it may prohibit party members\\nfrom participating in another party’s primary. Clingman v. Beaver,\\n544 U.S. 581, 586–97 (2005).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 7\\n\\nsuch voters, while the Democratic and Republican Parties do\\nnot.\\n\\n In April 2016, the Libertarian Party and its chairman\\nMichael Kielsky (collectively, the “Libertarian Party”) filed\\nthis action challenging the primary signature requirements.\\nThe district court denied the Libertarian Party’s request for\\na preliminary injunction prohibiting enforcement of the\\namended requirements for the 2016 election. The parties\\nfiled cross-motions for summary judgment, and, in\\nJuly 2017, the district court granted summary judgment to\\nthe Secretary.\\n\\n ANALYSIS\\n\\n The Libertarian Party contends that Arizona’s ballot\\naccess scheme violates equal protection and infringes upon\\nthe right to place its candidates on the ballot 6 and the right\\nto free association. 7 Only the rules governing access to the\\nprimary election ballot are at issue on this appeal—the\\nLibertarian Party does not call into question the rules for\\nearning a place on the general election ballot. With that in\\nmind, we first set forth the balancing framework that guides\\nour review and then explain why Arizona’s rules for\\naccessing the primary ballot are constitutionally sound.\\n\\n\\n\\n 6\\n The Libertarian Party also contends that the statute violates its right\\nto create and establish a political party. See Norman v. Reed, 502 U.S.\\n279, 288 (1992). This claim merely recites the right to access the ballot\\nclaim, and it fails for the same reasons. See infra pp.9–14.\\n 7\\n The Libertarian Party also appeals the district court’s exclusion of\\ncertain evidence. That issue is moot because summary judgment for the\\nSecretary is warranted even if we consider the excluded evidence.\\n\\f8 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nI. The Anderson/Burdick Balancing Framework\\n\\n There is an inevitable tension between a state’s authority\\nand need to regulate its elections and the First and Fourteenth\\nAmendment rights of voters, candidates, and political\\nparties. See Storer v. Brown, 415 U.S. 724, 729–30 (1974).\\nTo harmonize these competing demands, we look to\\nAnderson v. Celebrezze, 460 U.S. 780 (1983), and Burdick\\nv. Takushi, 504 U.S. 428 (1992), which provide a “flexible\\nstandard” for reviewing constitutional challenges to state\\nelection regulations:\\n\\n A court considering a challenge to a state\\n election law must weigh “the character and\\n magnitude of the asserted injury to the rights\\n protected by the First and Fourteenth\\n Amendments that the plaintiff seeks to\\n vindicate” against “the precise interests put\\n forward by the State as justifications for the\\n burden imposed by its rule,” taking into\\n consideration “the extent to which those\\n interests make it necessary to burden the\\n plaintiff’s rights.”\\n\\nBurdick, 504 U.S. at 434 (quoting Anderson, 460 U.S.\\nat 789). We have described this approach as a “sliding\\nscale”—the more severe the burden imposed, the more\\nexacting our scrutiny; the less severe, the more relaxed our\\nscrutiny. Ariz. Green Party, 838 F.3d at 988. To pass\\nconstitutional muster, a state law imposing a severe burden\\nmust be narrowly tailored to advance “compelling” interests.\\nNorman, 502 U.S. at 289. On the other hand, a law imposing\\na minimal burden need only reasonably advance “important”\\ninterests. Timmons v. Twin Cities Area New Party, 520 U.S.\\n351, 358 (1997) (quoting Burdick, 504 U.S. at 434).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 9\\n\\n We now consider each of the Libertarian Party’s\\nconstitutional challenges under the Anderson/Burdick\\nbalancing framework.\\n\\nII. Right to Access the Ballot\\n\\n It was long ago established that a state may condition\\nballot placement on a “preliminary showing of a significant\\nmodicum of support.” Jenness v. Fortson, 403 U.S. 431, 442\\n(1971). And there is no dispute that a state may require a\\ncandidate to demonstrate support from slightly, but not\\n“substantially,” more than 5% of voters without imposing a\\nsevere burden triggering heightened scrutiny. Storer,\\n415 U.S. at 739–40; see Jenness, 403 U.S. at 442; Williams\\nv. Rhodes, 393 U.S. 23, 24–25 (1968) (invalidating\\n15% requirement). The Libertarian Party contends that\\nArizona law imposes an impermissibly high signature\\nburden, reaching as high as 30% for certain candidates. Yet,\\nthe threshold—and dispositive—question is which pool of\\nvoters we should consider when measuring this showing.\\n\\n Under Arizona law, all qualified signers—Libertarian\\nParty members, unaffiliated registered voters, and new party\\nmembers—are eligible to participate in the Libertarian Party\\nprimary and to sign a Libertarian Party nominating petition.\\nBy its very terms, the statute never requires signatures from\\nmore than 1% of these voters. However, by choice, the\\nLibertarian Party has barred non-members from voting in its\\nprimary—under party policy, only members can vote in the\\nprimary. And it does not want its candidates to solicit\\nsignatures from non-members; as a consequence, Libertarian\\ncandidates must submit signatures equal to 11% to 30% of\\nparty membership in their jurisdiction to qualify for the\\nprimary ballot. Thus, our dilemma: is the “significant\\nmodicum of support” measured against all voters eligible\\nunder state law to sign a nominating petition and participate\\n\\f10 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nin the primary? Or do we factor in a party’s decision to\\nexclude certain eligible voters from its primary and instead\\nconsider the resulting, significantly circumscribed pool?\\n\\n The Supreme Court has never expressly answered this\\nquestion, but its framework in ballot access cases is\\ninstructive. The state laws challenged in Norman, Jenness,\\nand Williams required candidates and parties seeking\\nplacement on the general election ballot to submit signatures\\nfrom registered voters equaling a designated percentage of\\nthe general election electorate. 8 The Court’s approach in\\nthese cases was straightforward: it determined whether the\\nrequired signatures represented a reasonable share of the\\nvoters eligible to participate in the upcoming election. See\\nNorman, 502 U.S. at 295; Jenness, 403 U.S. at 438–40, 442;\\nWilliams, 393 U.S. at 24–25, 30–34. In American Party of\\nTexas 9 and Storer, the state laws imposed similar\\nrequirements, with an additional limitation: a voter who\\nparticipated in another party’s primary or convention or\\nsigned another candidate’s petition was ineligible to sign a\\nnominating petition. 10 In both cases, the Court determined\\nwhether the required signatures represented a reasonable\\n\\n 8\\n The laws challenged in Norman and Williams approximated the\\nelectorate by reference to the number of voters who participated in the\\npreceding general election. Norman, 502 U.S. at 282 n.2; Williams,\\n393 U.S. at 24–25. The law challenged in Jenness approximated the\\nelectorate by reference to the number of registered voters during the\\nprevious general election. 403 U.S. at 432–33.\\n\\n 9\\n Am. Party of Tex. v. White, 415 U.S. 767 (1974).\\n\\n 10\\n Like the laws challenged in Norman and Williams, those at issue\\nin American Party of Texas and Storer approximated the electorate by\\nreference to the number of voters who participated in the preceding\\ngeneral election. Am. Party, 415 U.S. at 774–75 & nn.6–7; Storer,\\n415 U.S. at 726–27, 739–40.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 11\\n\\nshare of the “available pool” of signers, i.e., voters who had\\nnot disqualified themselves by participating in another\\nprimary or convention or by signing a previous petition.\\nStorer, 415 U.S. at 739–40; see Am. Party, 415 U.S. at 774–\\n91.\\n\\n In each of these cases, the Court asked whether the\\nrequired signatures constituted an unfairly large percentage\\nof those voters eligible under state law to offer their\\nsignatures. There was no adjustment to account for the\\nsignificant portion of this pool comprised of registered\\nmembers of other parties, many of whom, it can be\\nreasonably presumed, were unlikely to help nominate a\\ncompeting candidate or party. Nor was there any suggestion\\nthat a candidate should be limited to seeking signatures from\\nvoters who have already pledged their support to the\\ncandidate or his party or cause. Rather, the Court time and\\nagain affirmed that requiring a demonstration of “significant,\\nmeasurable quantum of community support” does not\\nimpose a severe burden. Am. Party, 415 U.S. at 782.\\n\\n We invoked a similar analysis in Nader v. Cronin,\\n620 F.3d 1214, 1217 (9th Cir. 2010). And we do so again\\nhere. Arizona law permits all qualified signers— Libertarian\\nParty members, new party members, and registered\\nunaffiliated voters—to sign a Libertarian candidate’s\\nnominating petition and to vote in the Libertarian primary.\\nHowever, qualified signers who already signed another\\ncandidate’s nominating petition are excluded from the\\n“available pool” of voters able to sign a Libertarian\\ncandidate’s petition.\\n\\n No evidence suggests that, in practice, the statute’s (at\\nmost) 1% signature requirement even approaches 5% of this\\nremaining pool of eligible signers. It falls upon the\\nLibertarian Party to demonstrate that Arizona imposes a\\n\\f12 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nsevere burden, and it has failed to do so here. The party’s\\npolicy choice to exclude all non-members from its primary\\nand its preference to obtain signatures only from party\\nmembers do not change the calculus. To hold otherwise\\nwould permit a party to determine the number of signatures\\nrequired by manipulating its nominating petition and\\nprimary voting requirements. At the same time, the\\nLibertarian Party’s proposed rule would incentivize parties\\nto have fewer registered members and therefore artificially\\nreduce the signature requirements. Just as important: where,\\nin this scheme, is the offensive state action? There is no\\nquestion that the signature requirement would be\\nconstitutional if the Libertarian Party permitted non-\\nmembers to vote in its primary. A political party cannot\\nmanipulate its internal preferences and processes to\\ntransform a constitutional statute into an unconstitutional\\none. 11\\n\\n Crucially, Arizona law does not impose any other\\nrequirements, such as a strict time period for signature\\ncollection, that might nonetheless render the 1% requirement\\n“an impossible burden” or “an impractical undertaking.”\\nStorer, 415 U.S. at 740 (requiring 1,000 canvassers to collect\\n14 signatures each day for 24 days likely imposes a modest\\nburden); see Clingman, 544 U.S. at 589–90 (limiting a\\nparty’s internal structure, decision-making processes, and\\nability to communicate with the electorate likely imposes a\\n\\n 11\\n Neither of the cases cited by the Libertarian Party persuades us\\notherwise. One addressed a law that made it “impossible either\\nabsolutely . . . or practically” for a candidate to meet a signature\\nrequirement. See Consumer Party v. Davis, 633 F. Supp. 877, 883 (E.D.\\nPa. 1986). The other struck down signature requirements because they\\nimposed disparate requirements on similarly situated parties that were,\\nthe state conceded, impossible to justify. In re Candidacy of Indep. Party\\nCandidates v. Kiffmeyer, 688 N.W.2d 854, 859–61 (Minn. 2004).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 13\\n\\nsevere burden); Timmons, 520 U.S. at 363 (same); Anderson,\\n460 U.S. at 790–94 (requiring an independent candidate to\\nfile several months before party conventions imposes severe\\nburden); Am. Party, 415 U.S. at 778–81 (requiring all\\nsignatures to be notarized and submitted in 55-day period\\ndoes not impose severe burden); Jenness, 403 U.S. at 434,\\n438 (permitting 180 days for collection of nominating\\nsignatures and requiring submission of signatures five\\nmonths before election does not impose severe burden);\\nWilliams, 393 U.S. at 24–25 & n.1 (conditioning minor\\nparty’s ballot access on formation of statewide and county-\\nlevel party committees, participation in a national party\\nconvention, and submission of nominating signatures by an\\nearly deadline exclusively from voters who never voted in a\\nprevious election imposes significant burden). To the\\ncontrary, Arizona permits candidates to solicit and submit\\nsignatures through an easy-to-use and streamlined online\\nportal. A candidate collecting hand-written signatures must,\\nin practice, collect more than the minimum number of\\nsignatures required because, inevitably, some will be\\ndeemed ineligible. In contrast, signatures submitted through\\nthe online portal are instantaneously verified, thereby\\nreducing the need to submit signatures above the threshold.\\n\\n The limited evidence describing the Libertarian Party’s\\nmodest efforts to mobilize voters and several candidates’\\nunsuccessful write-in campaigns fails to establish that, in\\npractice, Arizona law “imposes insurmountable obstacles”\\nto getting on the primary ballot. Am. Party, 415 U.S. at 784.\\nNor does the simple fact that the Libertarian Party had more\\ncandidates on past primary and general election ballots\\nreflect such an obstacle under the amended rules. See Munro\\nv. Socialist Workers Party, 479 U.S. 189, 196–97 (1986).\\nAccordingly, we apply “less exacting” scrutiny because\\nArizona law imposes a minimal burden on the Libertarian\\n\\f14 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nParty’s right to access the primary ballot. Timmons,\\n520 U.S. at 358; see Cronin, 620 F.3d at 1218.\\n\\n We now turn to whether Arizona has an “important\\nregulatory interest” that justifies this modest burden.\\nTimmons, 520 U.S. at 358 (quoting Burdick, 504 U.S.\\nat 434). Arizona’s asserted interests in preventing voter\\nconfusion, ballot overcrowding, and frivolous candidacies\\nare important interests that have justified equally, if not\\nmore, burdensome general election ballot restrictions. See\\nMunro, 479 U.S. at 194–95. These interests are also\\nimportant in the primary context, given the “obvious and\\nstrong interconnection” between primary and general\\nelections, which together operate as a “single instrumentality\\nfor choice of officers.” Pub. Integrity All., Inc. v. City of\\nTucson, 836 F.3d 1019, 1026 (9th Cir. 2016) (quoting Smith\\nv. Allwright, 321 U.S. 649, 660 (1944)); see Storer, 415 U.S.\\nat 735 (A primary election “functions to winnow out and\\nfinally reject all but the chosen candidates.”). Conditioning\\nprimary ballot placement on a demonstration of significant\\ncommunity support advances Arizona’s interests in the\\nadministration of its primary and general elections. See\\nAnderson, 460 U.S. at 788–89; see also Jenness, 403 U.S.\\nat 442; Munro, 479 U.S. at 193–94.\\n\\n Because we neither require “a particularized showing of\\nthe existence of voter confusion, ballot overcrowding, or the\\npresence of frivolous candidacies,” Munro, 479 U.S. at 194–\\n95, nor proof that ballot rules are “the only or the best way\\nto further the proffered interests,” Dudum v. Arntz, 640 F.3d\\n1098, 1114 (9th Cir. 2011), Arizona has easily met its\\nburden. The primary signature requirements reasonably\\nfurther Arizona’s important regulatory interests and\\ntherefore justify a modest burden on the Libertarian Party’s\\nright to ballot access.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 15\\n\\nIII. Right to Free Association\\n\\n The Libertarian Party contends that Arizona law\\ninfringes upon its right to free association by effectively\\nrequiring its candidates to solicit signatures from non-\\nmembers. Although the Constitution protects a political\\nparty’s right to not associate with non-members, that right\\nhas its limits. U.S. Civil Serv. Comm’n v. Nat’l Ass’n of\\nLetter Carriers, AFL-CIO, 413 U.S. 548, 567 (1973). We\\nfirst ask whether Arizona in any way “forces” the Libertarian\\nParty to associate with non-members. Cal. Democratic\\nParty v. Jones, 530 U.S. 567, 577, 581–82, 586 (2000). If\\nso, we then consider whether such forced association creates\\na “risk that nonparty members will skew either primary\\nresults or candidates’ positions.” Ariz. Libertarian Party,\\nInc. v. Bayless, 351 F.3d 1277, 1282 (9th Cir. 2003). We\\nanswer both questions in the negative.\\n\\n Unlike the state laws at issue in Jones and Bayless,\\nArizona law permits political parties to exclude non-\\nmembers from voting in their primaries. At their option,\\nLibertarian candidates may use signatures from non-party\\nmembers to qualify for the primary ballot—but Arizona law\\ndoes not require them to do so. Soliciting non-member\\nsignatures would seemingly prove helpful in placing more\\ncandidates on the primary ballot, but it is the Libertarian\\nParty’s modest membership, not a “state-imposed restriction\\non [its] freedom of association,” that imposes upon it this\\n“hard choice.” Jones, 530 U.S. at 584. 12\\n\\n\\n 12\\n In Jenness, the Supreme Court noted that, for an independent or\\nminor party candidate seeking “signatures of 5% of the eligible\\nelectorate[,] . . . the way is open [because] Georgia imposes no\\nsuffocating restrictions whatever upon the free circulation of nominating\\n\\f16 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\n We acknowledge, without deciding, that there may be\\nsome point where the ratio between party members and\\nrequired signatures constitutes de facto forced association\\nwith non-members. For example, if the signature\\nrequirement exceeded the number of party members, then a\\ncandidate necessarily would, as a matter of arithmetic, have\\nto solicit non-member signatures to qualify for the ballot.\\nBut we face no such situation here. Libertarian candidates\\ncan qualify for the primary ballot with signatures from 11%\\nto 30% of party members in their jurisdictions, and no\\nevidence suggests it is impossible to do so as a practical\\nmatter. Even if collecting these signatures is difficult, we\\nexpect “[h]ard work and sacrifice by dedicated volunteers”\\nin the operation of “any political organization.” Am. Party,\\n415 U.S. at 787. Such expectations do not in any way\\n“force” Libertarian candidates or voters to associate with\\nnon-members.\\n\\n Nor has the Libertarian Party demonstrated that the\\nsolicitation and submission of some non-member signatures\\n“will skew either primary results or candidates’ positions.”\\nBayless, 351 F.3d at 1282. We decline to embrace such a\\nspeculative conclusion. Any burden on the Libertarian\\nParty’s associational freedom is modest, so we again apply\\nless exacting scrutiny and, as above, credit Arizona’s\\nimportant interests to justify these reasonable requirements.\\nSee Timmons, 520 U.S. at 358.\\n\\n\\n\\npetitions.” 403 U.S. at 438. The Court identified various limitations on\\nsignature collection that could be, but were not, imposed under Georgia\\nlaw. Id. at 438–39. That a minor party candidate would likely obtain\\nsignatures from non-party members was presupposed by the Court, not\\nas a bug of this system, but as a positive feature. Id.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 17\\n\\nIV. Equal Protection\\n\\n Finally, the Libertarian Party contends that the signature\\nrequirements violate equal protection because they impose\\nlesser burdens on other parties. 13 The Libertarian,\\nDemocratic, and Republican Parties are all established\\nparties subject to the same statutory requirements.\\nAlthough, on its face, Arizona law treats them identically,\\nwe look to see whether the requirements provide “a real and\\nessentially equal opportunity for ballot qualification.” Am.\\nParty, 415 U.S. at 788. That standard is clearly satisfied\\nhere. A Libertarian candidate vying for the primary ballot\\nactually faces a significantly lower burden than his\\nDemocratic and Republican counterparts. For example, a\\nstatewide Libertarian candidate needs to submit\\napproximately 3,200 signatures, compared to 6,000 and\\n6,400 signatures for the Democratic and Republican\\ncompetitors, respectively. See Ariz. Rev. Stat.\\n§ 16-322(A)(1); Ariz. Sec. of State, Voter Registration &\\nHistorical Election Data, https://azsos.gov/elections/voter-\\nregistration-historical-election-data (last visited May 7,\\n2019). 14\\n\\n That a Libertarian candidate must submit signatures\\nrepresenting a higher percentage of his party membership\\nthan a Democratic or Republican candidate is a consequence\\n\\n 13\\n Despite their differences, we assume, without deciding, that the\\nLibertarian Party is similarly situated to the Democratic, Republican, and\\nGreen Parties and that the Equal Protection Clause applies. See Cronin,\\n620 F.3d at 1218.\\n\\n 14\\n Of course, the signature ratio between parties varies within each\\npolitical subdivision, as voters are not perfectly distributed throughout\\nthe state. The statewide figures are sufficiently representative for our\\npurposes.\\n\\f18 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nof the Libertarian Party’s modest size, not a fatal flaw of the\\nstatutory scheme. The Supreme Court has indicated that an\\nanalogous imbalance lacks constitutional significance. In\\nIllinois State Board of Elections v. Socialist Workers Party,\\nthe Court struck down on equal protection grounds a state\\nlaw requiring local candidates to submit substantially more\\nsignatures to qualify for the ballot than statewide candidates.\\n440 U.S. 173, 186–87 (1979). The remedy: imposing the\\nsame, 25,000 signature requirement for both local and\\nstatewide candidates, even though the eligible voter pool for\\nstatewide candidates was six times larger than for certain\\nlocal candidates. See id. at 183–87. If such an outcome\\ncomports with equal protection, then surely so does the\\nsituation here.\\n\\n Even if we assume that the signature requirements\\nimpose a marginally higher burden on the Libertarian Party,\\nthat additional burden is far from severe. Cf. Williams,\\n393 U.S. at 25 (striking down state law that imposed\\n“substantially smaller burdens” on certain parties, while\\nmaking it “virtually impossible” for others to place a\\ncandidate on the ballot). Under less exacting scrutiny, we\\nagain conclude that the same important regulatory interests\\njustify the signature requirements. In setting the threshold\\nfor a “significant modicum of support,” Jenness, 403 U.S. at\\n442, a state must use either an absolute number of voters or\\na percentage of some group. Not only is it mathematically\\nimpossible to craft a statute where the burden on each party\\nis identical under both measurements, Arizona has no\\nobligation to seek such precision. See Dudum, 640 F.3d\\nat 1114 (recognizing regulations need not be “narrowly\\ntailored”). Nor was Arizona required to replicate or fold in\\nthe preexisting burdens on each party when it amended the\\nballot access rules in 2015. Cf. Ohio Democratic Party v.\\nHusted, 834 F.3d 620, 623 (6th Cir. 2016) (rejecting an\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 19\\n\\nargument “creat[ing] a ‘one-way ratchet’ that would\\ndiscourage states from” increasing ballot access, “lest they\\nbe prohibited by federal courts from later modifying their\\nelection procedures in response to changing\\ncircumstances”). Arizona’s choice to set the threshold as a\\npercentage of qualified signers for each established party\\nwas neither discriminatory nor unreasonable.\\n\\n Arizona opted to apply these signature requirements for\\nall parties that have a significant membership and therefore\\nexempt such parties from the quadrennial party-wide re-\\ncertification requirements imposed on new parties. This\\npolicy affords significant benefits to all established parties\\nand furthers the state’s interests in avoiding voter confusion,\\nminimizing clutter on the primary and general ballots, and\\neliminating frivolous candidacies. 15\\n\\n We likewise observe no equal protection issue in\\nArizona’s treatment of the Green Party, a new party subject\\nto different statutory requirements. When, as here, we\\n“examin[e] differing treatments of [different types of\\npolitical parties], . . . [i]n determining the nature and\\nmagnitude of the burden that [the state’s] election\\nprocedures impose on the [complaining party], we must\\nexamine the entire scheme regulating ballot access.”\\nCronin, 620 F.3d at 1217 (internal quotations and citation\\nomitted). Equal protection is violated when one set of\\n\\n 15\\n The Libertarian Party’s reliance on Kiffmeyer is, once again,\\nunpersuasive. There, two minor political parties were subject to the same\\nballot access rules; under those rules, one party had all of its candidates\\nplaced on the general election ballot, and the other had none on the ballot,\\neven though the latter received significantly more votes in the primary.\\nKiffmeyer, 688 N.W.2d at 859–61. Minnesota conceded that its these\\nrules were arbitrary and lacked any “rational . . . purpose.” Id. at 861.\\n\\f20 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nrequirements is “inherently” or “invidiously” more\\nburdensome than the other. Am. Party, 415 U.S. at 781;\\nJenness, 403 U.S. at 440–41; Cronin, 620 F.3d at 1218–19.\\n\\n The Libertarian Party’s chief complaint is that Green\\nParty candidates qualified for the 2016 primary ballot with\\nsignificantly fewer signatures than Libertarian candidates\\nfor the same races. 16 This argument fails to account for the\\nsignificant quadrennial re-filing burden placed on the Green\\nParty to retain its new party status. Every four years, the\\nGreen Party, which currently boasts less than\\n6,500 members, must submit more than 20,000 signatures\\nfor its candidates to be eligible to pursue placement on the\\nballot. That is, signatures from three times more voters than\\nit has registered members. Meeting the re-filing\\nrequirements is “an all-consuming endeavor” for the Green\\nParty, which relies on “a core group of about 10 volunteers”\\nto work “every weekend on Saturdays and Sundays for\\nseveral hours each” for more than a year. It is only once this\\nstep is complete that the modest individual candidate\\nsignature thresholds apply. Thus, it is obvious that the\\nprimary ballot signature requirements for the Libertarian\\nParty are not “inherently” or “invidiously” more\\nburdensome than those imposed on the Green Party. Am.\\nParty, 415 U.S. at 781; Jenness, 403 U.S. at 440–41. To be\\nsure, “[t]he procedures are different, but the Equal Protection\\n\\n\\n 16\\n The Libertarian Party also complains that a write-in new party\\ncandidate automatically qualifies for the general election ballot by\\nwinning his primary, while a write-in established party candidate only\\nqualifies for the general election ballot if he wins his primary with votes\\nequaling the number of signatures needed to qualify for the primary\\nballot. See Ariz. Rev. Stat. § 16-645(D)–(E). Because the Libertarian\\nParty expressly disclaims any challenge to Arizona’s general election\\nballot access requirements, we do not consider this argument.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 21\\n\\nClause does not necessarily forbid the one in preference to\\nthe other.” Am. Party, 415 U.S. at 781–82.\\n\\n CONCLUSION\\n\\n Arizona has no “constitutional imperative to reduce\\nvoter apathy or to ‘handicap’ an unpopular [party] to\\nincrease the likelihood that [its] candidate[s] will” qualify\\nfor the primary ballot. Munro, 479 U.S. at 198. The state’s\\nsignature requirements are reasonable restrictions that\\nimpose, at most, a modest burden on the Libertarian Party’s\\nFirst and Fourteenth Amendment rights, while directly\\nadvancing Arizona’s important regulatory interests. The\\ndistrict court correctly granted summary judgment to the\\nSecretary.\\n\\n AFFIRMED.\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4402529/\", \"author_raw\": \"McKEOWN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"J CLIFFORD WALLACE"},"judge2":{"kind":"string","value":"A WALLACE TASHIMA"},"judge3":{"kind":"string","value":"M MARGARET MCKEOWN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4625276/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Arizona Libertarian Party v. Katie Hobbs\nCourt: U.S. Court of Appeals for the Ninth Circuit\nDate decided: 2019-05-31\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nARIZONA LIBERTARIAN PARTY; No. 17-16491\nMICHAEL KIELSKY,\n Plaintiffs-Appellants, D.C. No.\n 2:16-cv-01019-\n v. DGC\n\nKATIE HOBBS, in her official\ncapacity as Secretary of State of OPINION\nArizona,\n Defendant-Appellee.\n\n\n\n Appeal from the United States District Court\n for the District of Arizona\n David G. Campbell, District Judge, Presiding\n\n Argued and Submitted March 12, 2019\n San Francisco, California\n\n Filed May 31, 2019\n\n Before: J. Clifford Wallace, A. Wallace Tashima, and\n M. Margaret McKeown, Circuit Judges.\n\n Opinion by Judge McKeown\n\f2 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\n SUMMARY *\n\n\n Civil Rights / Elections\n\n The panel affirmed the district court’s summary\njudgment in favor of Arizona’s Secretary of State in an\naction brought by the Arizona Libertarian Party challenging,\nunder the First and Fourteenth Amendments, a state law\nrequiring up to 1% of voters eligible to participate in\nArizona’s primary to sign a nominating petition for a\nLibertarian candidate to earn a place on the primary ballot.\n\n Applying the balancing framework set forth in Anderson\nv. Celebrezze, 460 U.S. 780 (1983), and Burdick v. Takushi,\n504 U.S. 428 (1992), the panel first held that the State’s\nsignature requirement imposed a minimal burden on the\nLibertarian Party’s right to access the primary ballot.\nAccordingly, the panel determined that a less exacting\nscrutiny was appropriate. The panel concluded that\nArizona’s signature requirements reasonably furthered\nArizona’s regulatory interest in preventing voter confusion,\nballot overcrowding, and frivolous candidacies and justified\nthe modest burden on the Libertarian Party’s right to ballot\naccess.\n\n The panel rejected the Libertarian Party’s contention that\nthe Arizona law infringed upon its right to free association\nby effectively requiring its candidates to solicit signatures\nfrom non-members. The panel held that any burden on the\nLibertarian Party’s associational freedom was modest, and\n\n *\n This summary constitutes no part of the opinion of the court. It\nhas been prepared by court staff for the convenience of the reader.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 3\n\nagain applying less exacting scrutiny, the panel credited\nArizona’s important interests to justify the reasonable\nrequirements.\n\n The panel further rejected the Libertarian Party’s\ncontention that Arizona’s signature requirement violated\nequal protection, noting that the Libertarian, Democratic,\nand Republican Parties were all subject to the same statutory\nrequirements. The panel observed no equal protection issue\nin Arizona’s treatment of the Green Party, a new party that\nwas subject to different statutory requirements.\n\n\n COUNSEL\n\nOliver B. Hall (argued), Center for Competitive Democracy,\nWashington, D.C., for Plaintiffs-Appellants.\n\nKara M. Karlson (argued) and Joseph E. La Rue, Assistant\nAttorneys General; Mark Brnovich, Attorney General;\nOffice of the Attorney General, Phoenix, Arizona; for\nDefendant-Appellee.\n\n\n OPINION\n\nMcKEOWN, Circuit Judge:\n\n Once again, we have before us a challenge to Arizona’s\nrequirements to earn a place on the ballot. See, e.g., Ariz.\nGreen Party v. Reagan, 838 F.3d 983 (9th Cir. 2016); Nader\nv. Brewer, 531 F.3d 1028 (9th Cir. 2008). The Arizona\nLibertarian Party challenges under the First and Fourteenth\nAmendments a state law requiring up to 1% of voters eligible\nto participate in its primary to sign a nominating petition for\n\f4 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\na Libertarian candidate to earn a place on the primary ballot.\nThe district court granted summary judgment to the Arizona\nSecretary of State (the “Secretary”), and we affirm.\n\n BACKGROUND\n\n Under Arizona law, there are two types of political\nparties: “established” parties and “new” parties. A party is\n“established” in a jurisdiction if it (i) obtained at least 5% of\nthe total votes cast in the prior general election, or\n(ii) maintains membership exceeding 0.66% of registered\nvoters in that jurisdiction. Ariz. Rev. Stat. § 16-804\n(applying to state, county, city, and town elections). An\nestablished party is entitled to “continued representation” on\nthe general election ballot. Id. The Libertarian, Democratic,\nand Republican Parties are established statewide. 1\n\n Before 2016, to qualify for the primary ballot, an\nestablished party candidate needed to submit signatures 2\nexceeding a certain percentage (ranging between 0.5% and\n2%, depending on the office sought) of the party’s registered\nvoters in the jurisdiction where he sought election. Ariz.\nRev. Stat. § 16-322(A) (2015). A candidate was permitted\nto submit signatures from party members, members of any\n 1\n The Libertarian Party satisfies the voter registration requirement,\nand the Democratic and Republican Parties satisfy both requirements.\nAs of January 1, 2019, Arizona had 1.31 million registered Republicans,\n1.17 million registered Democrats, and 32,056 registered Libertarians.\nAriz. Sec. of State, Voter Registration & Historical Election Data,\nhttps://azsos.gov/elections/voter-registration-historical-election-data\n(last visited May 7, 2019).\n 2\n A voter may only sign one nominating petition per office per\nelection, unless more than one candidate is to be elected to that office.\nAriz. Rev. Stat. § 16-321(A).\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 5\n\nnew party, or unaffiliated registered voters. 3 Id.\n§ 16-321(D).\n\n In 2015, the Arizona legislature amended the signature\nrequirements for established party candidates. 2015 Ariz.\nSess. Laws Ch. 293, §§ 2–3 (H.B. 2608). Now, to qualify\nfor a primary ballot, an established party candidate must\nsubmit signatures exceeding a certain percentage of\n“qualified signer[s],” which include the party’s registered\nvoters, as well as all new party voters and unaffiliated\nregistered voters. Ariz. Rev. Stat. § 16-321(F). The\namendments reduced the signature threshold for each office\nto between 0.25% and 1%. Id. § 16-322(A). In 2016—the\nfirst election governed by the amended rules—there\nwere significantly fewer Libertarian candidates on the\nprimary and general election ballots than in prior elections.\nSee generally Ariz. Sec. of State, Historical Election\nResults & Information, https://azsos.gov/elections/\nvoter-registration-historical-election-data/historical-election-\nresults-information (last visited May 7, 2019) (collecting\ndata for recent Arizona elections).\n\n A “new” party is subject to different rules. A new party\nmust first submit a petition for recognition and signatures\nfrom eligible voters exceeding 1.33% of total votes cast\nstatewide in the prior gubernatorial election. Ariz. Rev. Stat.\n§§ 16-801(A), 16-803. After doing so, the party’s\ncandidates are eligible to pursue placement on the primary\nand general election ballots for the next four years. Ariz.\nRev. Stat. § 16-801(B). To retain its recognition and ballot\n\n 3\n As of January 1, 2019, Arizona had 1.25 million unaffiliated\nregistered voters. Ariz. Sec. of State, Voter Registration & Historical\nElection Data, https://azsos.gov/elections/voter-registration-historical-\nelection-data (last visited May 7, 2019).\n\f6 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\neligibility at the end of the four years, the party must either\nqualify as an established party or file another petition for\nrecognition and the accompanying signatures. Id.; see Ariz.\nRev. Stat. §§ 16-803–04.\n\n To qualify for the primary ballot, a new party candidate\nmust submit signatures exceeding 0.1% “of the total vote for\nthe winning candidate or candidates for governor or\npresidential electors at the last general election within the\ndistrict.” Ariz. Rev. Stat. § 16-322(C). The Arizona Green\nParty first qualified as a new party in 1990, and, never having\nqualified as an established party, has successfully re-filed\npetitions for new party recognition and the accompanying\nsignatures several times, most recently in 2014. 4 Since the\nbeginning of 2017, Arizona has permitted digital solicitation\nand streamlined submission of voter signatures through an\nonline portal. Ariz. Rev. Stat. §§ 16-316–18.\n\n Under Arizona law, an established party member may\nnot vote in another party’s primary, but it is up to the\nestablished parties to decide whether new party members or\nunaffiliated voters can participate in their primaries. See\nAriz. Rev. Stat. § 16-467. 5 The Libertarian Party excludes\n\n\n\n\n 4\n As of January 1, 2019, the Green Party had 6,450 registered\nmembers in Arizona. Ariz. Sec. of State, Voter Registration & Historical\nElection Data, https://azsos.gov/elections/voter-registration-historical-\nelection-data (last visited May 7, 2019).\n\n 5\n A state may not keep a party from welcoming unaffiliated voters\nto participate in its primary, Tashjian v. Republican Party of Conn.,\n479 U.S. 208, 213–29 (1986), though it may prohibit party members\nfrom participating in another party’s primary. Clingman v. Beaver,\n544 U.S. 581, 586–97 (2005).\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 7\n\nsuch voters, while the Democratic and Republican Parties do\nnot.\n\n In April 2016, the Libertarian Party and its chairman\nMichael Kielsky (collectively, the “Libertarian Party”) filed\nthis action challenging the primary signature requirements.\nThe district court denied the Libertarian Party’s request for\na preliminary injunction prohibiting enforcement of the\namended requirements for the 2016 election. The parties\nfiled cross-motions for summary judgment, and, in\nJuly 2017, the district court granted summary judgment to\nthe Secretary.\n\n ANALYSIS\n\n The Libertarian Party contends that Arizona’s ballot\naccess scheme violates equal protection and infringes upon\nthe right to place its candidates on the ballot 6 and the right\nto free association. 7 Only the rules governing access to the\nprimary election ballot are at issue on this appeal—the\nLibertarian Party does not call into question the rules for\nearning a place on the general election ballot. With that in\nmind, we first set forth the balancing framework that guides\nour review and then explain why Arizona’s rules for\naccessing the primary ballot are constitutionally sound.\n\n\n\n 6\n The Libertarian Party also contends that the statute violates its right\nto create and establish a political party. See Norman v. Reed, 502 U.S.\n279, 288 (1992). This claim merely recites the right to access the ballot\nclaim, and it fails for the same reasons. See infra pp.9–14.\n 7\n The Libertarian Party also appeals the district court’s exclusion of\ncertain evidence. That issue is moot because summary judgment for the\nSecretary is warranted even if we consider the excluded evidence.\n\f8 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nI. The Anderson/Burdick Balancing Framework\n\n There is an inevitable tension between a state’s authority\nand need to regulate its elections and the First and Fourteenth\nAmendment rights of voters, candidates, and political\nparties. See Storer v. Brown, 415 U.S. 724, 729–30 (1974).\nTo harmonize these competing demands, we look to\nAnderson v. Celebrezze, 460 U.S. 780 (1983), and Burdick\nv. Takushi, 504 U.S. 428 (1992), which provide a “flexible\nstandard” for reviewing constitutional challenges to state\nelection regulations:\n\n A court considering a challenge to a state\n election law must weigh “the character and\n magnitude of the asserted injury to the rights\n protected by the First and Fourteenth\n Amendments that the plaintiff seeks to\n vindicate” against “the precise interests put\n forward by the State as justifications for the\n burden imposed by its rule,” taking into\n consideration “the extent to which those\n interests make it necessary to burden the\n plaintiff’s rights.”\n\nBurdick, 504 U.S. at 434 (quoting Anderson, 460 U.S.\nat 789). We have described this approach as a “sliding\nscale”—the more severe the burden imposed, the more\nexacting our scrutiny; the less severe, the more relaxed our\nscrutiny. Ariz. Green Party, 838 F.3d at 988. To pass\nconstitutional muster, a state law imposing a severe burden\nmust be narrowly tailored to advance “compelling” interests.\nNorman, 502 U.S. at 289. On the other hand, a law imposing\na minimal burden need only reasonably advance “important”\ninterests. Timmons v. Twin Cities Area New Party, 520 U.S.\n351, 358 (1997) (quoting Burdick, 504 U.S. at 434).\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 9\n\n We now consider each of the Libertarian Party’s\nconstitutional challenges under the Anderson/Burdick\nbalancing framework.\n\nII. Right to Access the Ballot\n\n It was long ago established that a state may condition\nballot placement on a “preliminary showing of a significant\nmodicum of support.” Jenness v. Fortson, 403 U.S. 431, 442\n(1971). And there is no dispute that a state may require a\ncandidate to demonstrate support from slightly, but not\n“substantially,” more than 5% of voters without imposing a\nsevere burden triggering heightened scrutiny. Storer,\n415 U.S. at 739–40; see Jenness, 403 U.S. at 442; Williams\nv. Rhodes, 393 U.S. 23, 24–25 (1968) (invalidating\n15% requirement). The Libertarian Party contends that\nArizona law imposes an impermissibly high signature\nburden, reaching as high as 30% for certain candidates. Yet,\nthe threshold—and dispositive—question is which pool of\nvoters we should consider when measuring this showing.\n\n Under Arizona law, all qualified signers—Libertarian\nParty members, unaffiliated registered voters, and new party\nmembers—are eligible to participate in the Libertarian Party\nprimary and to sign a Libertarian Party nominating petition.\nBy its very terms, the statute never requires signatures from\nmore than 1% of these voters. However, by choice, the\nLibertarian Party has barred non-members from voting in its\nprimary—under party policy, only members can vote in the\nprimary. And it does not want its candidates to solicit\nsignatures from non-members; as a consequence, Libertarian\ncandidates must submit signatures equal to 11% to 30% of\nparty membership in their jurisdiction to qualify for the\nprimary ballot. Thus, our dilemma: is the “significant\nmodicum of support” measured against all voters eligible\nunder state law to sign a nominating petition and participate\n\f10 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nin the primary? Or do we factor in a party’s decision to\nexclude certain eligible voters from its primary and instead\nconsider the resulting, significantly circumscribed pool?\n\n The Supreme Court has never expressly answered this\nquestion, but its framework in ballot access cases is\ninstructive. The state laws challenged in Norman, Jenness,\nand Williams required candidates and parties seeking\nplacement on the general election ballot to submit signatures\nfrom registered voters equaling a designated percentage of\nthe general election electorate. 8 The Court’s approach in\nthese cases was straightforward: it determined whether the\nrequired signatures represented a reasonable share of the\nvoters eligible to participate in the upcoming election. See\nNorman, 502 U.S. at 295; Jenness, 403 U.S. at 438–40, 442;\nWilliams, 393 U.S. at 24–25, 30–34. In American Party of\nTexas 9 and Storer, the state laws imposed similar\nrequirements, with an additional limitation: a voter who\nparticipated in another party’s primary or convention or\nsigned another candidate’s petition was ineligible to sign a\nnominating petition. 10 In both cases, the Court determined\nwhether the required signatures represented a reasonable\n\n 8\n The laws challenged in Norman and Williams approximated the\nelectorate by reference to the number of voters who participated in the\npreceding general election. Norman, 502 U.S. at 282 n.2; Williams,\n393 U.S. at 24–25. The law challenged in Jenness approximated the\nelectorate by reference to the number of registered voters during the\nprevious general election. 403 U.S. at 432–33.\n\n 9\n Am. Party of Tex. v. White, 415 U.S. 767 (1974).\n\n 10\n Like the laws challenged in Norman and Williams, those at issue\nin American Party of Texas and Storer approximated the electorate by\nreference to the number of voters who participated in the preceding\ngeneral election. Am. Party, 415 U.S. at 774–75 & nn.6–7; Storer,\n415 U.S. at 726–27, 739–40.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 11\n\nshare of the “available pool” of signers, i.e., voters who had\nnot disqualified themselves by participating in another\nprimary or convention or by signing a previous petition.\nStorer, 415 U.S. at 739–40; see Am. Party, 415 U.S. at 774–\n91.\n\n In each of these cases, the Court asked whether the\nrequired signatures constituted an unfairly large percentage\nof those voters eligible under state law to offer their\nsignatures. There was no adjustment to account for the\nsignificant portion of this pool comprised of registered\nmembers of other parties, many of whom, it can be\nreasonably presumed, were unlikely to help nominate a\ncompeting candidate or party. Nor was there any suggestion\nthat a candidate should be limited to seeking signatures from\nvoters who have already pledged their support to the\ncandidate or his party or cause. Rather, the Court time and\nagain affirmed that requiring a demonstration of “significant,\nmeasurable quantum of community support” does not\nimpose a severe burden. Am. Party, 415 U.S. at 782.\n\n We invoked a similar analysis in Nader v. Cronin,\n620 F.3d 1214, 1217 (9th Cir. 2010). And we do so again\nhere. Arizona law permits all qualified signers— Libertarian\nParty members, new party members, and registered\nunaffiliated voters—to sign a Libertarian candidate’s\nnominating petition and to vote in the Libertarian primary.\nHowever, qualified signers who already signed another\ncandidate’s nominating petition are excluded from the\n“available pool” of voters able to sign a Libertarian\ncandidate’s petition.\n\n No evidence suggests that, in practice, the statute’s (at\nmost) 1% signature requirement even approaches 5% of this\nremaining pool of eligible signers. It falls upon the\nLibertarian Party to demonstrate that Arizona imposes a\n\f12 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nsevere burden, and it has failed to do so here. The party’s\npolicy choice to exclude all non-members from its primary\nand its preference to obtain signatures only from party\nmembers do not change the calculus. To hold otherwise\nwould permit a party to determine the number of signatures\nrequired by manipulating its nominating petition and\nprimary voting requirements. At the same time, the\nLibertarian Party’s proposed rule would incentivize parties\nto have fewer registered members and therefore artificially\nreduce the signature requirements. Just as important: where,\nin this scheme, is the offensive state action? There is no\nquestion that the signature requirement would be\nconstitutional if the Libertarian Party permitted non-\nmembers to vote in its primary. A political party cannot\nmanipulate its internal preferences and processes to\ntransform a constitutional statute into an unconstitutional\none. 11\n\n Crucially, Arizona law does not impose any other\nrequirements, such as a strict time period for signature\ncollection, that might nonetheless render the 1% requirement\n“an impossible burden” or “an impractical undertaking.”\nStorer, 415 U.S. at 740 (requiring 1,000 canvassers to collect\n14 signatures each day for 24 days likely imposes a modest\nburden); see Clingman, 544 U.S. at 589–90 (limiting a\nparty’s internal structure, decision-making processes, and\nability to communicate with the electorate likely imposes a\n\n 11\n Neither of the cases cited by the Libertarian Party persuades us\notherwise. One addressed a law that made it “impossible either\nabsolutely . . . or practically” for a candidate to meet a signature\nrequirement. See Consumer Party v. Davis, 633 F. Supp. 877, 883 (E.D.\nPa. 1986). The other struck down signature requirements because they\nimposed disparate requirements on similarly situated parties that were,\nthe state conceded, impossible to justify. In re Candidacy of Indep. Party\nCandidates v. Kiffmeyer, 688 N.W.2d 854, 859–61 (Minn. 2004).\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 13\n\nsevere burden); Timmons, 520 U.S. at 363 (same); Anderson,\n460 U.S. at 790–94 (requiring an independent candidate to\nfile several months before party conventions imposes severe\nburden); Am. Party, 415 U.S. at 778–81 (requiring all\nsignatures to be notarized and submitted in 55-day period\ndoes not impose severe burden); Jenness, 403 U.S. at 434,\n438 (permitting 180 days for collection of nominating\nsignatures and requiring submission of signatures five\nmonths before election does not impose severe burden);\nWilliams, 393 U.S. at 24–25 & n.1 (conditioning minor\nparty’s ballot access on formation of statewide and county-\nlevel party committees, participation in a national party\nconvention, and submission of nominating signatures by an\nearly deadline exclusively from voters who never voted in a\nprevious election imposes significant burden). To the\ncontrary, Arizona permits candidates to solicit and submit\nsignatures through an easy-to-use and streamlined online\nportal. A candidate collecting hand-written signatures must,\nin practice, collect more than the minimum number of\nsignatures required because, inevitably, some will be\ndeemed ineligible. In contrast, signatures submitted through\nthe online portal are instantaneously verified, thereby\nreducing the need to submit signatures above the threshold.\n\n The limited evidence describing the Libertarian Party’s\nmodest efforts to mobilize voters and several candidates’\nunsuccessful write-in campaigns fails to establish that, in\npractice, Arizona law “imposes insurmountable obstacles”\nto getting on the primary ballot. Am. Party, 415 U.S. at 784.\nNor does the simple fact that the Libertarian Party had more\ncandidates on past primary and general election ballots\nreflect such an obstacle under the amended rules. See Munro\nv. Socialist Workers Party, 479 U.S. 189, 196–97 (1986).\nAccordingly, we apply “less exacting” scrutiny because\nArizona law imposes a minimal burden on the Libertarian\n\f14 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nParty’s right to access the primary ballot. Timmons,\n520 U.S. at 358; see Cronin, 620 F.3d at 1218.\n\n We now turn to whether Arizona has an “important\nregulatory interest” that justifies this modest burden.\nTimmons, 520 U.S. at 358 (quoting Burdick, 504 U.S.\nat 434). Arizona’s asserted interests in preventing voter\nconfusion, ballot overcrowding, and frivolous candidacies\nare important interests that have justified equally, if not\nmore, burdensome general election ballot restrictions. See\nMunro, 479 U.S. at 194–95. These interests are also\nimportant in the primary context, given the “obvious and\nstrong interconnection” between primary and general\nelections, which together operate as a “single instrumentality\nfor choice of officers.” Pub. Integrity All., Inc. v. City of\nTucson, 836 F.3d 1019, 1026 (9th Cir. 2016) (quoting Smith\nv. Allwright, 321 U.S. 649, 660 (1944)); see Storer, 415 U.S.\nat 735 (A primary election “functions to winnow out and\nfinally reject all but the chosen candidates.”). Conditioning\nprimary ballot placement on a demonstration of significant\ncommunity support advances Arizona’s interests in the\nadministration of its primary and general elections. See\nAnderson, 460 U.S. at 788–89; see also Jenness, 403 U.S.\nat 442; Munro, 479 U.S. at 193–94.\n\n Because we neither require “a particularized showing of\nthe existence of voter confusion, ballot overcrowding, or the\npresence of frivolous candidacies,” Munro, 479 U.S. at 194–\n95, nor proof that ballot rules are “the only or the best way\nto further the proffered interests,” Dudum v. Arntz, 640 F.3d\n1098, 1114 (9th Cir. 2011), Arizona has easily met its\nburden. The primary signature requirements reasonably\nfurther Arizona’s important regulatory interests and\ntherefore justify a modest burden on the Libertarian Party’s\nright to ballot access.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 15\n\nIII. Right to Free Association\n\n The Libertarian Party contends that Arizona law\ninfringes upon its right to free association by effectively\nrequiring its candidates to solicit signatures from non-\nmembers. Although the Constitution protects a political\nparty’s right to not associate with non-members, that right\nhas its limits. U.S. Civil Serv. Comm’n v. Nat’l Ass’n of\nLetter Carriers, AFL-CIO, 413 U.S. 548, 567 (1973). We\nfirst ask whether Arizona in any way “forces” the Libertarian\nParty to associate with non-members. Cal. Democratic\nParty v. Jones, 530 U.S. 567, 577, 581–82, 586 (2000). If\nso, we then consider whether such forced association creates\na “risk that nonparty members will skew either primary\nresults or candidates’ positions.” Ariz. Libertarian Party,\nInc. v. Bayless, 351 F.3d 1277, 1282 (9th Cir. 2003). We\nanswer both questions in the negative.\n\n Unlike the state laws at issue in Jones and Bayless,\nArizona law permits political parties to exclude non-\nmembers from voting in their primaries. At their option,\nLibertarian candidates may use signatures from non-party\nmembers to qualify for the primary ballot—but Arizona law\ndoes not require them to do so. Soliciting non-member\nsignatures would seemingly prove helpful in placing more\ncandidates on the primary ballot, but it is the Libertarian\nParty’s modest membership, not a “state-imposed restriction\non [its] freedom of association,” that imposes upon it this\n“hard choice.” Jones, 530 U.S. at 584. 12\n\n\n 12\n In Jenness, the Supreme Court noted that, for an independent or\nminor party candidate seeking “signatures of 5% of the eligible\nelectorate[,] . . . the way is open [because] Georgia imposes no\nsuffocating restrictions whatever upon the free circulation of nominating\n\f16 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\n We acknowledge, without deciding, that there may be\nsome point where the ratio between party members and\nrequired signatures constitutes de facto forced association\nwith non-members. For example, if the signature\nrequirement exceeded the number of party members, then a\ncandidate necessarily would, as a matter of arithmetic, have\nto solicit non-member signatures to qualify for the ballot.\nBut we face no such situation here. Libertarian candidates\ncan qualify for the primary ballot with signatures from 11%\nto 30% of party members in their jurisdictions, and no\nevidence suggests it is impossible to do so as a practical\nmatter. Even if collecting these signatures is difficult, we\nexpect “[h]ard work and sacrifice by dedicated volunteers”\nin the operation of “any political organization.” Am. Party,\n415 U.S. at 787. Such expectations do not in any way\n“force” Libertarian candidates or voters to associate with\nnon-members.\n\n Nor has the Libertarian Party demonstrated that the\nsolicitation and submission of some non-member signatures\n“will skew either primary results or candidates’ positions.”\nBayless, 351 F.3d at 1282. We decline to embrace such a\nspeculative conclusion. Any burden on the Libertarian\nParty’s associational freedom is modest, so we again apply\nless exacting scrutiny and, as above, credit Arizona’s\nimportant interests to justify these reasonable requirements.\nSee Timmons, 520 U.S. at 358.\n\n\n\npetitions.” 403 U.S. at 438. The Court identified various limitations on\nsignature collection that could be, but were not, imposed under Georgia\nlaw. Id. at 438–39. That a minor party candidate would likely obtain\nsignatures from non-party members was presupposed by the Court, not\nas a bug of this system, but as a positive feature. Id.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 17\n\nIV. Equal Protection\n\n Finally, the Libertarian Party contends that the signature\nrequirements violate equal protection because they impose\nlesser burdens on other parties. 13 The Libertarian,\nDemocratic, and Republican Parties are all established\nparties subject to the same statutory requirements.\nAlthough, on its face, Arizona law treats them identically,\nwe look to see whether the requirements provide “a real and\nessentially equal opportunity for ballot qualification.” Am.\nParty, 415 U.S. at 788. That standard is clearly satisfied\nhere. A Libertarian candidate vying for the primary ballot\nactually faces a significantly lower burden than his\nDemocratic and Republican counterparts. For example, a\nstatewide Libertarian candidate needs to submit\napproximately 3,200 signatures, compared to 6,000 and\n6,400 signatures for the Democratic and Republican\ncompetitors, respectively. See Ariz. Rev. Stat.\n§ 16-322(A)(1); Ariz. Sec. of State, Voter Registration &\nHistorical Election Data, https://azsos.gov/elections/voter-\nregistration-historical-election-data (last visited May 7,\n2019). 14\n\n That a Libertarian candidate must submit signatures\nrepresenting a higher percentage of his party membership\nthan a Democratic or Republican candidate is a consequence\n\n 13\n Despite their differences, we assume, without deciding, that the\nLibertarian Party is similarly situated to the Democratic, Republican, and\nGreen Parties and that the Equal Protection Clause applies. See Cronin,\n620 F.3d at 1218.\n\n 14\n Of course, the signature ratio between parties varies within each\npolitical subdivision, as voters are not perfectly distributed throughout\nthe state. The statewide figures are sufficiently representative for our\npurposes.\n\f18 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nof the Libertarian Party’s modest size, not a fatal flaw of the\nstatutory scheme. The Supreme Court has indicated that an\nanalogous imbalance lacks constitutional significance. In\nIllinois State Board of Elections v. Socialist Workers Party,\nthe Court struck down on equal protection grounds a state\nlaw requiring local candidates to submit substantially more\nsignatures to qualify for the ballot than statewide candidates.\n440 U.S. 173, 186–87 (1979). The remedy: imposing the\nsame, 25,000 signature requirement for both local and\nstatewide candidates, even though the eligible voter pool for\nstatewide candidates was six times larger than for certain\nlocal candidates. See id. at 183–87. If such an outcome\ncomports with equal protection, then surely so does the\nsituation here.\n\n Even if we assume that the signature requirements\nimpose a marginally higher burden on the Libertarian Party,\nthat additional burden is far from severe. Cf. Williams,\n393 U.S. at 25 (striking down state law that imposed\n“substantially smaller burdens” on certain parties, while\nmaking it “virtually impossible” for others to place a\ncandidate on the ballot). Under less exacting scrutiny, we\nagain conclude that the same important regulatory interests\njustify the signature requirements. In setting the threshold\nfor a “significant modicum of support,” Jenness, 403 U.S. at\n442, a state must use either an absolute number of voters or\na percentage of some group. Not only is it mathematically\nimpossible to craft a statute where the burden on each party\nis identical under both measurements, Arizona has no\nobligation to seek such precision. See Dudum, 640 F.3d\nat 1114 (recognizing regulations need not be “narrowly\ntailored”). Nor was Arizona required to replicate or fold in\nthe preexisting burdens on each party when it amended the\nballot access rules in 2015. Cf. Ohio Democratic Party v.\nHusted, 834 F.3d 620, 623 (6th Cir. 2016) (rejecting an\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 19\n\nargument “creat[ing] a ‘one-way ratchet’ that would\ndiscourage states from” increasing ballot access, “lest they\nbe prohibited by federal courts from later modifying their\nelection procedures in response to changing\ncircumstances”). Arizona’s choice to set the threshold as a\npercentage of qualified signers for each established party\nwas neither discriminatory nor unreasonable.\n\n Arizona opted to apply these signature requirements for\nall parties that have a significant membership and therefore\nexempt such parties from the quadrennial party-wide re-\ncertification requirements imposed on new parties. This\npolicy affords significant benefits to all established parties\nand furthers the state’s interests in avoiding voter confusion,\nminimizing clutter on the primary and general ballots, and\neliminating frivolous candidacies. 15\n\n We likewise observe no equal protection issue in\nArizona’s treatment of the Green Party, a new party subject\nto different statutory requirements. When, as here, we\n“examin[e] differing treatments of [different types of\npolitical parties], . . . [i]n determining the nature and\nmagnitude of the burden that [the state’s] election\nprocedures impose on the [complaining party], we must\nexamine the entire scheme regulating ballot access.”\nCronin, 620 F.3d at 1217 (internal quotations and citation\nomitted). Equal protection is violated when one set of\n\n 15\n The Libertarian Party’s reliance on Kiffmeyer is, once again,\nunpersuasive. There, two minor political parties were subject to the same\nballot access rules; under those rules, one party had all of its candidates\nplaced on the general election ballot, and the other had none on the ballot,\neven though the latter received significantly more votes in the primary.\nKiffmeyer, 688 N.W.2d at 859–61. Minnesota conceded that its these\nrules were arbitrary and lacked any “rational . . . purpose.” Id. at 861.\n\f20 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nrequirements is “inherently” or “invidiously” more\nburdensome than the other. Am. Party, 415 U.S. at 781;\nJenness, 403 U.S. at 440–41; Cronin, 620 F.3d at 1218–19.\n\n The Libertarian Party’s chief complaint is that Green\nParty candidates qualified for the 2016 primary ballot with\nsignificantly fewer signatures than Libertarian candidates\nfor the same races. 16 This argument fails to account for the\nsignificant quadrennial re-filing burden placed on the Green\nParty to retain its new party status. Every four years, the\nGreen Party, which currently boasts less than\n6,500 members, must submit more than 20,000 signatures\nfor its candidates to be eligible to pursue placement on the\nballot. That is, signatures from three times more voters than\nit has registered members. Meeting the re-filing\nrequirements is “an all-consuming endeavor” for the Green\nParty, which relies on “a core group of about 10 volunteers”\nto work “every weekend on Saturdays and Sundays for\nseveral hours each” for more than a year. It is only once this\nstep is complete that the modest individual candidate\nsignature thresholds apply. Thus, it is obvious that the\nprimary ballot signature requirements for the Libertarian\nParty are not “inherently” or “invidiously” more\nburdensome than those imposed on the Green Party. Am.\nParty, 415 U.S. at 781; Jenness, 403 U.S. at 440–41. To be\nsure, “[t]he procedures are different, but the Equal Protection\n\n\n 16\n The Libertarian Party also complains that a write-in new party\ncandidate automatically qualifies for the general election ballot by\nwinning his primary, while a write-in established party candidate only\nqualifies for the general election ballot if he wins his primary with votes\nequaling the number of signatures needed to qualify for the primary\nballot. See Ariz. Rev. Stat. § 16-645(D)–(E). Because the Libertarian\nParty expressly disclaims any challenge to Arizona’s general election\nballot access requirements, we do not consider this argument.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 21\n\nClause does not necessarily forbid the one in preference to\nthe other.” Am. Party, 415 U.S. at 781–82.\n\n CONCLUSION\n\n Arizona has no “constitutional imperative to reduce\nvoter apathy or to ‘handicap’ an unpopular [party] to\nincrease the likelihood that [its] candidate[s] will” qualify\nfor the primary ballot. Munro, 479 U.S. at 198. The state’s\nsignature requirements are reasonable restrictions that\nimpose, at most, a modest burden on the Libertarian Party’s\nFirst and Fourteenth Amendment rights, while directly\nadvancing Arizona’s important regulatory interests. The\ndistrict court correctly granted summary judgment to the\nSecretary.\n\n AFFIRMED.\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Arizona Libertarian Party v. Katie Hobbs\\nCourt: U.S. Court of Appeals for the Ninth Circuit\\nDate decided: 2019-05-31\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFOR PUBLICATION\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE NINTH CIRCUIT\\n\\n\\nARIZONA LIBERTARIAN PARTY; No. 17-16491\\nMICHAEL KIELSKY,\\n Plaintiffs-Appellants, D.C. No.\\n 2:16-cv-01019-\\n v. DGC\\n\\nKATIE HOBBS, in her official\\ncapacity as Secretary of State of OPINION\\nArizona,\\n Defendant-Appellee.\\n\\n\\n\\n Appeal from the United States District Court\\n for the District of Arizona\\n David G. Campbell, District Judge, Presiding\\n\\n Argued and Submitted March 12, 2019\\n San Francisco, California\\n\\n Filed May 31, 2019\\n\\n Before: J. Clifford Wallace, A. Wallace Tashima, and\\n M. Margaret McKeown, Circuit Judges.\\n\\n Opinion by Judge McKeown\\n\\f2 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\n SUMMARY *\\n\\n\\n Civil Rights / Elections\\n\\n The panel affirmed the district court’s summary\\njudgment in favor of Arizona’s Secretary of State in an\\naction brought by the Arizona Libertarian Party challenging,\\nunder the First and Fourteenth Amendments, a state law\\nrequiring up to 1% of voters eligible to participate in\\nArizona’s primary to sign a nominating petition for a\\nLibertarian candidate to earn a place on the primary ballot.\\n\\n Applying the balancing framework set forth in Anderson\\nv. Celebrezze, 460 U.S. 780 (1983), and Burdick v. Takushi,\\n504 U.S. 428 (1992), the panel first held that the State’s\\nsignature requirement imposed a minimal burden on the\\nLibertarian Party’s right to access the primary ballot.\\nAccordingly, the panel determined that a less exacting\\nscrutiny was appropriate. The panel concluded that\\nArizona’s signature requirements reasonably furthered\\nArizona’s regulatory interest in preventing voter confusion,\\nballot overcrowding, and frivolous candidacies and justified\\nthe modest burden on the Libertarian Party’s right to ballot\\naccess.\\n\\n The panel rejected the Libertarian Party’s contention that\\nthe Arizona law infringed upon its right to free association\\nby effectively requiring its candidates to solicit signatures\\nfrom non-members. The panel held that any burden on the\\nLibertarian Party’s associational freedom was modest, and\\n\\n *\\n This summary constitutes no part of the opinion of the court. It\\nhas been prepared by court staff for the convenience of the reader.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 3\\n\\nagain applying less exacting scrutiny, the panel credited\\nArizona’s important interests to justify the reasonable\\nrequirements.\\n\\n The panel further rejected the Libertarian Party’s\\ncontention that Arizona’s signature requirement violated\\nequal protection, noting that the Libertarian, Democratic,\\nand Republican Parties were all subject to the same statutory\\nrequirements. The panel observed no equal protection issue\\nin Arizona’s treatment of the Green Party, a new party that\\nwas subject to different statutory requirements.\\n\\n\\n COUNSEL\\n\\nOliver B. Hall (argued), Center for Competitive Democracy,\\nWashington, D.C., for Plaintiffs-Appellants.\\n\\nKara M. Karlson (argued) and Joseph E. La Rue, Assistant\\nAttorneys General; Mark Brnovich, Attorney General;\\nOffice of the Attorney General, Phoenix, Arizona; for\\nDefendant-Appellee.\\n\\n\\n OPINION\\n\\nMcKEOWN, Circuit Judge:\\n\\n Once again, we have before us a challenge to Arizona’s\\nrequirements to earn a place on the ballot. See, e.g., Ariz.\\nGreen Party v. Reagan, 838 F.3d 983 (9th Cir. 2016); Nader\\nv. Brewer, 531 F.3d 1028 (9th Cir. 2008). The Arizona\\nLibertarian Party challenges under the First and Fourteenth\\nAmendments a state law requiring up to 1% of voters eligible\\nto participate in its primary to sign a nominating petition for\\n\\f4 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\na Libertarian candidate to earn a place on the primary ballot.\\nThe district court granted summary judgment to the Arizona\\nSecretary of State (the “Secretary”), and we affirm.\\n\\n BACKGROUND\\n\\n Under Arizona law, there are two types of political\\nparties: “established” parties and “new” parties. A party is\\n“established” in a jurisdiction if it (i) obtained at least 5% of\\nthe total votes cast in the prior general election, or\\n(ii) maintains membership exceeding 0.66% of registered\\nvoters in that jurisdiction. Ariz. Rev. Stat. § 16-804\\n(applying to state, county, city, and town elections). An\\nestablished party is entitled to “continued representation” on\\nthe general election ballot. Id. The Libertarian, Democratic,\\nand Republican Parties are established statewide. 1\\n\\n Before 2016, to qualify for the primary ballot, an\\nestablished party candidate needed to submit signatures 2\\nexceeding a certain percentage (ranging between 0.5% and\\n2%, depending on the office sought) of the party’s registered\\nvoters in the jurisdiction where he sought election. Ariz.\\nRev. Stat. § 16-322(A) (2015). A candidate was permitted\\nto submit signatures from party members, members of any\\n 1\\n The Libertarian Party satisfies the voter registration requirement,\\nand the Democratic and Republican Parties satisfy both requirements.\\nAs of January 1, 2019, Arizona had 1.31 million registered Republicans,\\n1.17 million registered Democrats, and 32,056 registered Libertarians.\\nAriz. Sec. of State, Voter Registration & Historical Election Data,\\nhttps://azsos.gov/elections/voter-registration-historical-election-data\\n(last visited May 7, 2019).\\n 2\\n A voter may only sign one nominating petition per office per\\nelection, unless more than one candidate is to be elected to that office.\\nAriz. Rev. Stat. § 16-321(A).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 5\\n\\nnew party, or unaffiliated registered voters. 3 Id.\\n§ 16-321(D).\\n\\n In 2015, the Arizona legislature amended the signature\\nrequirements for established party candidates. 2015 Ariz.\\nSess. Laws Ch. 293, §§ 2–3 (H.B. 2608). Now, to qualify\\nfor a primary ballot, an established party candidate must\\nsubmit signatures exceeding a certain percentage of\\n“qualified signer[s],” which include the party’s registered\\nvoters, as well as all new party voters and unaffiliated\\nregistered voters. Ariz. Rev. Stat. § 16-321(F). The\\namendments reduced the signature threshold for each office\\nto between 0.25% and 1%. Id. § 16-322(A). In 2016—the\\nfirst election governed by the amended rules—there\\nwere significantly fewer Libertarian candidates on the\\nprimary and general election ballots than in prior elections.\\nSee generally Ariz. Sec. of State, Historical Election\\nResults & Information, https://azsos.gov/elections/\\nvoter-registration-historical-election-data/historical-election-\\nresults-information (last visited May 7, 2019) (collecting\\ndata for recent Arizona elections).\\n\\n A “new” party is subject to different rules. A new party\\nmust first submit a petition for recognition and signatures\\nfrom eligible voters exceeding 1.33% of total votes cast\\nstatewide in the prior gubernatorial election. Ariz. Rev. Stat.\\n§§ 16-801(A), 16-803. After doing so, the party’s\\ncandidates are eligible to pursue placement on the primary\\nand general election ballots for the next four years. Ariz.\\nRev. Stat. § 16-801(B). To retain its recognition and ballot\\n\\n 3\\n As of January 1, 2019, Arizona had 1.25 million unaffiliated\\nregistered voters. Ariz. Sec. of State, Voter Registration & Historical\\nElection Data, https://azsos.gov/elections/voter-registration-historical-\\nelection-data (last visited May 7, 2019).\\n\\f6 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\neligibility at the end of the four years, the party must either\\nqualify as an established party or file another petition for\\nrecognition and the accompanying signatures. Id.; see Ariz.\\nRev. Stat. §§ 16-803–04.\\n\\n To qualify for the primary ballot, a new party candidate\\nmust submit signatures exceeding 0.1% “of the total vote for\\nthe winning candidate or candidates for governor or\\npresidential electors at the last general election within the\\ndistrict.” Ariz. Rev. Stat. § 16-322(C). The Arizona Green\\nParty first qualified as a new party in 1990, and, never having\\nqualified as an established party, has successfully re-filed\\npetitions for new party recognition and the accompanying\\nsignatures several times, most recently in 2014. 4 Since the\\nbeginning of 2017, Arizona has permitted digital solicitation\\nand streamlined submission of voter signatures through an\\nonline portal. Ariz. Rev. Stat. §§ 16-316–18.\\n\\n Under Arizona law, an established party member may\\nnot vote in another party’s primary, but it is up to the\\nestablished parties to decide whether new party members or\\nunaffiliated voters can participate in their primaries. See\\nAriz. Rev. Stat. § 16-467. 5 The Libertarian Party excludes\\n\\n\\n\\n\\n 4\\n As of January 1, 2019, the Green Party had 6,450 registered\\nmembers in Arizona. Ariz. Sec. of State, Voter Registration & Historical\\nElection Data, https://azsos.gov/elections/voter-registration-historical-\\nelection-data (last visited May 7, 2019).\\n\\n 5\\n A state may not keep a party from welcoming unaffiliated voters\\nto participate in its primary, Tashjian v. Republican Party of Conn.,\\n479 U.S. 208, 213–29 (1986), though it may prohibit party members\\nfrom participating in another party’s primary. Clingman v. Beaver,\\n544 U.S. 581, 586–97 (2005).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 7\\n\\nsuch voters, while the Democratic and Republican Parties do\\nnot.\\n\\n In April 2016, the Libertarian Party and its chairman\\nMichael Kielsky (collectively, the “Libertarian Party”) filed\\nthis action challenging the primary signature requirements.\\nThe district court denied the Libertarian Party’s request for\\na preliminary injunction prohibiting enforcement of the\\namended requirements for the 2016 election. The parties\\nfiled cross-motions for summary judgment, and, in\\nJuly 2017, the district court granted summary judgment to\\nthe Secretary.\\n\\n ANALYSIS\\n\\n The Libertarian Party contends that Arizona’s ballot\\naccess scheme violates equal protection and infringes upon\\nthe right to place its candidates on the ballot 6 and the right\\nto free association. 7 Only the rules governing access to the\\nprimary election ballot are at issue on this appeal—the\\nLibertarian Party does not call into question the rules for\\nearning a place on the general election ballot. With that in\\nmind, we first set forth the balancing framework that guides\\nour review and then explain why Arizona’s rules for\\naccessing the primary ballot are constitutionally sound.\\n\\n\\n\\n 6\\n The Libertarian Party also contends that the statute violates its right\\nto create and establish a political party. See Norman v. Reed, 502 U.S.\\n279, 288 (1992). This claim merely recites the right to access the ballot\\nclaim, and it fails for the same reasons. See infra pp.9–14.\\n 7\\n The Libertarian Party also appeals the district court’s exclusion of\\ncertain evidence. That issue is moot because summary judgment for the\\nSecretary is warranted even if we consider the excluded evidence.\\n\\f8 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nI. The Anderson/Burdick Balancing Framework\\n\\n There is an inevitable tension between a state’s authority\\nand need to regulate its elections and the First and Fourteenth\\nAmendment rights of voters, candidates, and political\\nparties. See Storer v. Brown, 415 U.S. 724, 729–30 (1974).\\nTo harmonize these competing demands, we look to\\nAnderson v. Celebrezze, 460 U.S. 780 (1983), and Burdick\\nv. Takushi, 504 U.S. 428 (1992), which provide a “flexible\\nstandard” for reviewing constitutional challenges to state\\nelection regulations:\\n\\n A court considering a challenge to a state\\n election law must weigh “the character and\\n magnitude of the asserted injury to the rights\\n protected by the First and Fourteenth\\n Amendments that the plaintiff seeks to\\n vindicate” against “the precise interests put\\n forward by the State as justifications for the\\n burden imposed by its rule,” taking into\\n consideration “the extent to which those\\n interests make it necessary to burden the\\n plaintiff’s rights.”\\n\\nBurdick, 504 U.S. at 434 (quoting Anderson, 460 U.S.\\nat 789). We have described this approach as a “sliding\\nscale”—the more severe the burden imposed, the more\\nexacting our scrutiny; the less severe, the more relaxed our\\nscrutiny. Ariz. Green Party, 838 F.3d at 988. To pass\\nconstitutional muster, a state law imposing a severe burden\\nmust be narrowly tailored to advance “compelling” interests.\\nNorman, 502 U.S. at 289. On the other hand, a law imposing\\na minimal burden need only reasonably advance “important”\\ninterests. Timmons v. Twin Cities Area New Party, 520 U.S.\\n351, 358 (1997) (quoting Burdick, 504 U.S. at 434).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 9\\n\\n We now consider each of the Libertarian Party’s\\nconstitutional challenges under the Anderson/Burdick\\nbalancing framework.\\n\\nII. Right to Access the Ballot\\n\\n It was long ago established that a state may condition\\nballot placement on a “preliminary showing of a significant\\nmodicum of support.” Jenness v. Fortson, 403 U.S. 431, 442\\n(1971). And there is no dispute that a state may require a\\ncandidate to demonstrate support from slightly, but not\\n“substantially,” more than 5% of voters without imposing a\\nsevere burden triggering heightened scrutiny. Storer,\\n415 U.S. at 739–40; see Jenness, 403 U.S. at 442; Williams\\nv. Rhodes, 393 U.S. 23, 24–25 (1968) (invalidating\\n15% requirement). The Libertarian Party contends that\\nArizona law imposes an impermissibly high signature\\nburden, reaching as high as 30% for certain candidates. Yet,\\nthe threshold—and dispositive—question is which pool of\\nvoters we should consider when measuring this showing.\\n\\n Under Arizona law, all qualified signers—Libertarian\\nParty members, unaffiliated registered voters, and new party\\nmembers—are eligible to participate in the Libertarian Party\\nprimary and to sign a Libertarian Party nominating petition.\\nBy its very terms, the statute never requires signatures from\\nmore than 1% of these voters. However, by choice, the\\nLibertarian Party has barred non-members from voting in its\\nprimary—under party policy, only members can vote in the\\nprimary. And it does not want its candidates to solicit\\nsignatures from non-members; as a consequence, Libertarian\\ncandidates must submit signatures equal to 11% to 30% of\\nparty membership in their jurisdiction to qualify for the\\nprimary ballot. Thus, our dilemma: is the “significant\\nmodicum of support” measured against all voters eligible\\nunder state law to sign a nominating petition and participate\\n\\f10 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nin the primary? Or do we factor in a party’s decision to\\nexclude certain eligible voters from its primary and instead\\nconsider the resulting, significantly circumscribed pool?\\n\\n The Supreme Court has never expressly answered this\\nquestion, but its framework in ballot access cases is\\ninstructive. The state laws challenged in Norman, Jenness,\\nand Williams required candidates and parties seeking\\nplacement on the general election ballot to submit signatures\\nfrom registered voters equaling a designated percentage of\\nthe general election electorate. 8 The Court’s approach in\\nthese cases was straightforward: it determined whether the\\nrequired signatures represented a reasonable share of the\\nvoters eligible to participate in the upcoming election. See\\nNorman, 502 U.S. at 295; Jenness, 403 U.S. at 438–40, 442;\\nWilliams, 393 U.S. at 24–25, 30–34. In American Party of\\nTexas 9 and Storer, the state laws imposed similar\\nrequirements, with an additional limitation: a voter who\\nparticipated in another party’s primary or convention or\\nsigned another candidate’s petition was ineligible to sign a\\nnominating petition. 10 In both cases, the Court determined\\nwhether the required signatures represented a reasonable\\n\\n 8\\n The laws challenged in Norman and Williams approximated the\\nelectorate by reference to the number of voters who participated in the\\npreceding general election. Norman, 502 U.S. at 282 n.2; Williams,\\n393 U.S. at 24–25. The law challenged in Jenness approximated the\\nelectorate by reference to the number of registered voters during the\\nprevious general election. 403 U.S. at 432–33.\\n\\n 9\\n Am. Party of Tex. v. White, 415 U.S. 767 (1974).\\n\\n 10\\n Like the laws challenged in Norman and Williams, those at issue\\nin American Party of Texas and Storer approximated the electorate by\\nreference to the number of voters who participated in the preceding\\ngeneral election. Am. Party, 415 U.S. at 774–75 & nn.6–7; Storer,\\n415 U.S. at 726–27, 739–40.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 11\\n\\nshare of the “available pool” of signers, i.e., voters who had\\nnot disqualified themselves by participating in another\\nprimary or convention or by signing a previous petition.\\nStorer, 415 U.S. at 739–40; see Am. Party, 415 U.S. at 774–\\n91.\\n\\n In each of these cases, the Court asked whether the\\nrequired signatures constituted an unfairly large percentage\\nof those voters eligible under state law to offer their\\nsignatures. There was no adjustment to account for the\\nsignificant portion of this pool comprised of registered\\nmembers of other parties, many of whom, it can be\\nreasonably presumed, were unlikely to help nominate a\\ncompeting candidate or party. Nor was there any suggestion\\nthat a candidate should be limited to seeking signatures from\\nvoters who have already pledged their support to the\\ncandidate or his party or cause. Rather, the Court time and\\nagain affirmed that requiring a demonstration of “significant,\\nmeasurable quantum of community support” does not\\nimpose a severe burden. Am. Party, 415 U.S. at 782.\\n\\n We invoked a similar analysis in Nader v. Cronin,\\n620 F.3d 1214, 1217 (9th Cir. 2010). And we do so again\\nhere. Arizona law permits all qualified signers— Libertarian\\nParty members, new party members, and registered\\nunaffiliated voters—to sign a Libertarian candidate’s\\nnominating petition and to vote in the Libertarian primary.\\nHowever, qualified signers who already signed another\\ncandidate’s nominating petition are excluded from the\\n“available pool” of voters able to sign a Libertarian\\ncandidate’s petition.\\n\\n No evidence suggests that, in practice, the statute’s (at\\nmost) 1% signature requirement even approaches 5% of this\\nremaining pool of eligible signers. It falls upon the\\nLibertarian Party to demonstrate that Arizona imposes a\\n\\f12 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nsevere burden, and it has failed to do so here. The party’s\\npolicy choice to exclude all non-members from its primary\\nand its preference to obtain signatures only from party\\nmembers do not change the calculus. To hold otherwise\\nwould permit a party to determine the number of signatures\\nrequired by manipulating its nominating petition and\\nprimary voting requirements. At the same time, the\\nLibertarian Party’s proposed rule would incentivize parties\\nto have fewer registered members and therefore artificially\\nreduce the signature requirements. Just as important: where,\\nin this scheme, is the offensive state action? There is no\\nquestion that the signature requirement would be\\nconstitutional if the Libertarian Party permitted non-\\nmembers to vote in its primary. A political party cannot\\nmanipulate its internal preferences and processes to\\ntransform a constitutional statute into an unconstitutional\\none. 11\\n\\n Crucially, Arizona law does not impose any other\\nrequirements, such as a strict time period for signature\\ncollection, that might nonetheless render the 1% requirement\\n“an impossible burden” or “an impractical undertaking.”\\nStorer, 415 U.S. at 740 (requiring 1,000 canvassers to collect\\n14 signatures each day for 24 days likely imposes a modest\\nburden); see Clingman, 544 U.S. at 589–90 (limiting a\\nparty’s internal structure, decision-making processes, and\\nability to communicate with the electorate likely imposes a\\n\\n 11\\n Neither of the cases cited by the Libertarian Party persuades us\\notherwise. One addressed a law that made it “impossible either\\nabsolutely . . . or practically” for a candidate to meet a signature\\nrequirement. See Consumer Party v. Davis, 633 F. Supp. 877, 883 (E.D.\\nPa. 1986). The other struck down signature requirements because they\\nimposed disparate requirements on similarly situated parties that were,\\nthe state conceded, impossible to justify. In re Candidacy of Indep. Party\\nCandidates v. Kiffmeyer, 688 N.W.2d 854, 859–61 (Minn. 2004).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 13\\n\\nsevere burden); Timmons, 520 U.S. at 363 (same); Anderson,\\n460 U.S. at 790–94 (requiring an independent candidate to\\nfile several months before party conventions imposes severe\\nburden); Am. Party, 415 U.S. at 778–81 (requiring all\\nsignatures to be notarized and submitted in 55-day period\\ndoes not impose severe burden); Jenness, 403 U.S. at 434,\\n438 (permitting 180 days for collection of nominating\\nsignatures and requiring submission of signatures five\\nmonths before election does not impose severe burden);\\nWilliams, 393 U.S. at 24–25 & n.1 (conditioning minor\\nparty’s ballot access on formation of statewide and county-\\nlevel party committees, participation in a national party\\nconvention, and submission of nominating signatures by an\\nearly deadline exclusively from voters who never voted in a\\nprevious election imposes significant burden). To the\\ncontrary, Arizona permits candidates to solicit and submit\\nsignatures through an easy-to-use and streamlined online\\nportal. A candidate collecting hand-written signatures must,\\nin practice, collect more than the minimum number of\\nsignatures required because, inevitably, some will be\\ndeemed ineligible. In contrast, signatures submitted through\\nthe online portal are instantaneously verified, thereby\\nreducing the need to submit signatures above the threshold.\\n\\n The limited evidence describing the Libertarian Party’s\\nmodest efforts to mobilize voters and several candidates’\\nunsuccessful write-in campaigns fails to establish that, in\\npractice, Arizona law “imposes insurmountable obstacles”\\nto getting on the primary ballot. Am. Party, 415 U.S. at 784.\\nNor does the simple fact that the Libertarian Party had more\\ncandidates on past primary and general election ballots\\nreflect such an obstacle under the amended rules. See Munro\\nv. Socialist Workers Party, 479 U.S. 189, 196–97 (1986).\\nAccordingly, we apply “less exacting” scrutiny because\\nArizona law imposes a minimal burden on the Libertarian\\n\\f14 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nParty’s right to access the primary ballot. Timmons,\\n520 U.S. at 358; see Cronin, 620 F.3d at 1218.\\n\\n We now turn to whether Arizona has an “important\\nregulatory interest” that justifies this modest burden.\\nTimmons, 520 U.S. at 358 (quoting Burdick, 504 U.S.\\nat 434). Arizona’s asserted interests in preventing voter\\nconfusion, ballot overcrowding, and frivolous candidacies\\nare important interests that have justified equally, if not\\nmore, burdensome general election ballot restrictions. See\\nMunro, 479 U.S. at 194–95. These interests are also\\nimportant in the primary context, given the “obvious and\\nstrong interconnection” between primary and general\\nelections, which together operate as a “single instrumentality\\nfor choice of officers.” Pub. Integrity All., Inc. v. City of\\nTucson, 836 F.3d 1019, 1026 (9th Cir. 2016) (quoting Smith\\nv. Allwright, 321 U.S. 649, 660 (1944)); see Storer, 415 U.S.\\nat 735 (A primary election “functions to winnow out and\\nfinally reject all but the chosen candidates.”). Conditioning\\nprimary ballot placement on a demonstration of significant\\ncommunity support advances Arizona’s interests in the\\nadministration of its primary and general elections. See\\nAnderson, 460 U.S. at 788–89; see also Jenness, 403 U.S.\\nat 442; Munro, 479 U.S. at 193–94.\\n\\n Because we neither require “a particularized showing of\\nthe existence of voter confusion, ballot overcrowding, or the\\npresence of frivolous candidacies,” Munro, 479 U.S. at 194–\\n95, nor proof that ballot rules are “the only or the best way\\nto further the proffered interests,” Dudum v. Arntz, 640 F.3d\\n1098, 1114 (9th Cir. 2011), Arizona has easily met its\\nburden. The primary signature requirements reasonably\\nfurther Arizona’s important regulatory interests and\\ntherefore justify a modest burden on the Libertarian Party’s\\nright to ballot access.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 15\\n\\nIII. Right to Free Association\\n\\n The Libertarian Party contends that Arizona law\\ninfringes upon its right to free association by effectively\\nrequiring its candidates to solicit signatures from non-\\nmembers. Although the Constitution protects a political\\nparty’s right to not associate with non-members, that right\\nhas its limits. U.S. Civil Serv. Comm’n v. Nat’l Ass’n of\\nLetter Carriers, AFL-CIO, 413 U.S. 548, 567 (1973). We\\nfirst ask whether Arizona in any way “forces” the Libertarian\\nParty to associate with non-members. Cal. Democratic\\nParty v. Jones, 530 U.S. 567, 577, 581–82, 586 (2000). If\\nso, we then consider whether such forced association creates\\na “risk that nonparty members will skew either primary\\nresults or candidates’ positions.” Ariz. Libertarian Party,\\nInc. v. Bayless, 351 F.3d 1277, 1282 (9th Cir. 2003). We\\nanswer both questions in the negative.\\n\\n Unlike the state laws at issue in Jones and Bayless,\\nArizona law permits political parties to exclude non-\\nmembers from voting in their primaries. At their option,\\nLibertarian candidates may use signatures from non-party\\nmembers to qualify for the primary ballot—but Arizona law\\ndoes not require them to do so. Soliciting non-member\\nsignatures would seemingly prove helpful in placing more\\ncandidates on the primary ballot, but it is the Libertarian\\nParty’s modest membership, not a “state-imposed restriction\\non [its] freedom of association,” that imposes upon it this\\n“hard choice.” Jones, 530 U.S. at 584. 12\\n\\n\\n 12\\n In Jenness, the Supreme Court noted that, for an independent or\\nminor party candidate seeking “signatures of 5% of the eligible\\nelectorate[,] . . . the way is open [because] Georgia imposes no\\nsuffocating restrictions whatever upon the free circulation of nominating\\n\\f16 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\n We acknowledge, without deciding, that there may be\\nsome point where the ratio between party members and\\nrequired signatures constitutes de facto forced association\\nwith non-members. For example, if the signature\\nrequirement exceeded the number of party members, then a\\ncandidate necessarily would, as a matter of arithmetic, have\\nto solicit non-member signatures to qualify for the ballot.\\nBut we face no such situation here. Libertarian candidates\\ncan qualify for the primary ballot with signatures from 11%\\nto 30% of party members in their jurisdictions, and no\\nevidence suggests it is impossible to do so as a practical\\nmatter. Even if collecting these signatures is difficult, we\\nexpect “[h]ard work and sacrifice by dedicated volunteers”\\nin the operation of “any political organization.” Am. Party,\\n415 U.S. at 787. Such expectations do not in any way\\n“force” Libertarian candidates or voters to associate with\\nnon-members.\\n\\n Nor has the Libertarian Party demonstrated that the\\nsolicitation and submission of some non-member signatures\\n“will skew either primary results or candidates’ positions.”\\nBayless, 351 F.3d at 1282. We decline to embrace such a\\nspeculative conclusion. Any burden on the Libertarian\\nParty’s associational freedom is modest, so we again apply\\nless exacting scrutiny and, as above, credit Arizona’s\\nimportant interests to justify these reasonable requirements.\\nSee Timmons, 520 U.S. at 358.\\n\\n\\n\\npetitions.” 403 U.S. at 438. The Court identified various limitations on\\nsignature collection that could be, but were not, imposed under Georgia\\nlaw. Id. at 438–39. That a minor party candidate would likely obtain\\nsignatures from non-party members was presupposed by the Court, not\\nas a bug of this system, but as a positive feature. Id.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 17\\n\\nIV. Equal Protection\\n\\n Finally, the Libertarian Party contends that the signature\\nrequirements violate equal protection because they impose\\nlesser burdens on other parties. 13 The Libertarian,\\nDemocratic, and Republican Parties are all established\\nparties subject to the same statutory requirements.\\nAlthough, on its face, Arizona law treats them identically,\\nwe look to see whether the requirements provide “a real and\\nessentially equal opportunity for ballot qualification.” Am.\\nParty, 415 U.S. at 788. That standard is clearly satisfied\\nhere. A Libertarian candidate vying for the primary ballot\\nactually faces a significantly lower burden than his\\nDemocratic and Republican counterparts. For example, a\\nstatewide Libertarian candidate needs to submit\\napproximately 3,200 signatures, compared to 6,000 and\\n6,400 signatures for the Democratic and Republican\\ncompetitors, respectively. See Ariz. Rev. Stat.\\n§ 16-322(A)(1); Ariz. Sec. of State, Voter Registration &\\nHistorical Election Data, https://azsos.gov/elections/voter-\\nregistration-historical-election-data (last visited May 7,\\n2019). 14\\n\\n That a Libertarian candidate must submit signatures\\nrepresenting a higher percentage of his party membership\\nthan a Democratic or Republican candidate is a consequence\\n\\n 13\\n Despite their differences, we assume, without deciding, that the\\nLibertarian Party is similarly situated to the Democratic, Republican, and\\nGreen Parties and that the Equal Protection Clause applies. See Cronin,\\n620 F.3d at 1218.\\n\\n 14\\n Of course, the signature ratio between parties varies within each\\npolitical subdivision, as voters are not perfectly distributed throughout\\nthe state. The statewide figures are sufficiently representative for our\\npurposes.\\n\\f18 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nof the Libertarian Party’s modest size, not a fatal flaw of the\\nstatutory scheme. The Supreme Court has indicated that an\\nanalogous imbalance lacks constitutional significance. In\\nIllinois State Board of Elections v. Socialist Workers Party,\\nthe Court struck down on equal protection grounds a state\\nlaw requiring local candidates to submit substantially more\\nsignatures to qualify for the ballot than statewide candidates.\\n440 U.S. 173, 186–87 (1979). The remedy: imposing the\\nsame, 25,000 signature requirement for both local and\\nstatewide candidates, even though the eligible voter pool for\\nstatewide candidates was six times larger than for certain\\nlocal candidates. See id. at 183–87. If such an outcome\\ncomports with equal protection, then surely so does the\\nsituation here.\\n\\n Even if we assume that the signature requirements\\nimpose a marginally higher burden on the Libertarian Party,\\nthat additional burden is far from severe. Cf. Williams,\\n393 U.S. at 25 (striking down state law that imposed\\n“substantially smaller burdens” on certain parties, while\\nmaking it “virtually impossible” for others to place a\\ncandidate on the ballot). Under less exacting scrutiny, we\\nagain conclude that the same important regulatory interests\\njustify the signature requirements. In setting the threshold\\nfor a “significant modicum of support,” Jenness, 403 U.S. at\\n442, a state must use either an absolute number of voters or\\na percentage of some group. Not only is it mathematically\\nimpossible to craft a statute where the burden on each party\\nis identical under both measurements, Arizona has no\\nobligation to seek such precision. See Dudum, 640 F.3d\\nat 1114 (recognizing regulations need not be “narrowly\\ntailored”). Nor was Arizona required to replicate or fold in\\nthe preexisting burdens on each party when it amended the\\nballot access rules in 2015. Cf. Ohio Democratic Party v.\\nHusted, 834 F.3d 620, 623 (6th Cir. 2016) (rejecting an\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 19\\n\\nargument “creat[ing] a ‘one-way ratchet’ that would\\ndiscourage states from” increasing ballot access, “lest they\\nbe prohibited by federal courts from later modifying their\\nelection procedures in response to changing\\ncircumstances”). Arizona’s choice to set the threshold as a\\npercentage of qualified signers for each established party\\nwas neither discriminatory nor unreasonable.\\n\\n Arizona opted to apply these signature requirements for\\nall parties that have a significant membership and therefore\\nexempt such parties from the quadrennial party-wide re-\\ncertification requirements imposed on new parties. This\\npolicy affords significant benefits to all established parties\\nand furthers the state’s interests in avoiding voter confusion,\\nminimizing clutter on the primary and general ballots, and\\neliminating frivolous candidacies. 15\\n\\n We likewise observe no equal protection issue in\\nArizona’s treatment of the Green Party, a new party subject\\nto different statutory requirements. When, as here, we\\n“examin[e] differing treatments of [different types of\\npolitical parties], . . . [i]n determining the nature and\\nmagnitude of the burden that [the state’s] election\\nprocedures impose on the [complaining party], we must\\nexamine the entire scheme regulating ballot access.”\\nCronin, 620 F.3d at 1217 (internal quotations and citation\\nomitted). Equal protection is violated when one set of\\n\\n 15\\n The Libertarian Party’s reliance on Kiffmeyer is, once again,\\nunpersuasive. There, two minor political parties were subject to the same\\nballot access rules; under those rules, one party had all of its candidates\\nplaced on the general election ballot, and the other had none on the ballot,\\neven though the latter received significantly more votes in the primary.\\nKiffmeyer, 688 N.W.2d at 859–61. Minnesota conceded that its these\\nrules were arbitrary and lacked any “rational . . . purpose.” Id. at 861.\\n\\f20 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nrequirements is “inherently” or “invidiously” more\\nburdensome than the other. Am. Party, 415 U.S. at 781;\\nJenness, 403 U.S. at 440–41; Cronin, 620 F.3d at 1218–19.\\n\\n The Libertarian Party’s chief complaint is that Green\\nParty candidates qualified for the 2016 primary ballot with\\nsignificantly fewer signatures than Libertarian candidates\\nfor the same races. 16 This argument fails to account for the\\nsignificant quadrennial re-filing burden placed on the Green\\nParty to retain its new party status. Every four years, the\\nGreen Party, which currently boasts less than\\n6,500 members, must submit more than 20,000 signatures\\nfor its candidates to be eligible to pursue placement on the\\nballot. That is, signatures from three times more voters than\\nit has registered members. Meeting the re-filing\\nrequirements is “an all-consuming endeavor” for the Green\\nParty, which relies on “a core group of about 10 volunteers”\\nto work “every weekend on Saturdays and Sundays for\\nseveral hours each” for more than a year. It is only once this\\nstep is complete that the modest individual candidate\\nsignature thresholds apply. Thus, it is obvious that the\\nprimary ballot signature requirements for the Libertarian\\nParty are not “inherently” or “invidiously” more\\nburdensome than those imposed on the Green Party. Am.\\nParty, 415 U.S. at 781; Jenness, 403 U.S. at 440–41. To be\\nsure, “[t]he procedures are different, but the Equal Protection\\n\\n\\n 16\\n The Libertarian Party also complains that a write-in new party\\ncandidate automatically qualifies for the general election ballot by\\nwinning his primary, while a write-in established party candidate only\\nqualifies for the general election ballot if he wins his primary with votes\\nequaling the number of signatures needed to qualify for the primary\\nballot. See Ariz. Rev. Stat. § 16-645(D)–(E). Because the Libertarian\\nParty expressly disclaims any challenge to Arizona’s general election\\nballot access requirements, we do not consider this argument.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 21\\n\\nClause does not necessarily forbid the one in preference to\\nthe other.” Am. Party, 415 U.S. at 781–82.\\n\\n CONCLUSION\\n\\n Arizona has no “constitutional imperative to reduce\\nvoter apathy or to ‘handicap’ an unpopular [party] to\\nincrease the likelihood that [its] candidate[s] will” qualify\\nfor the primary ballot. Munro, 479 U.S. at 198. The state’s\\nsignature requirements are reasonable restrictions that\\nimpose, at most, a modest burden on the Libertarian Party’s\\nFirst and Fourteenth Amendment rights, while directly\\nadvancing Arizona’s important regulatory interests. The\\ndistrict court correctly granted summary judgment to the\\nSecretary.\\n\\n AFFIRMED.\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2252,"cells":{"id":{"kind":"number","value":4625596,"string":"4,625,596"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Arizona Libertarian Party v. Katie Hobbs"},"decision_date":{"kind":"string","value":"2019-05-31"},"docket_number":{"kind":"string","value":"17-16491"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Ninth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before: J. Clifford Wallace, A. Wallace Tashima, and M. Margaret McKeown, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"McKEOWN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"FOR PUBLICATION\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE NINTH CIRCUIT\\n\\n\\nARIZONA LIBERTARIAN PARTY; No. 17-16491\\nMICHAEL KIELSKY,\\n Plaintiffs-Appellants, D.C. No.\\n 2:16-cv-01019-\\n v. DGC\\n\\nKATIE HOBBS, in her official\\ncapacity as Secretary of State of OPINION\\nArizona,\\n Defendant-Appellee.\\n\\n\\n\\n Appeal from the United States District Court\\n for the District of Arizona\\n David G. Campbell, District Judge, Presiding\\n\\n Argued and Submitted March 12, 2019\\n San Francisco, California\\n\\n Filed May 31, 2019\\n\\n Before: J. Clifford Wallace, A. Wallace Tashima, and\\n M. Margaret McKeown, Circuit Judges.\\n\\n Opinion by Judge McKeown\\n\\f2 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\n SUMMARY *\\n\\n\\n Civil Rights / Elections\\n\\n The panel affirmed the district court’s summary\\njudgment in favor of Arizona’s Secretary of State in an\\naction brought by the Arizona Libertarian Party challenging,\\nunder the First and Fourteenth Amendments, a state law\\nrequiring up to 1% of voters eligible to participate in\\nArizona’s primary to sign a nominating petition for a\\nLibertarian candidate to earn a place on the primary ballot.\\n\\n Applying the balancing framework set forth in Anderson\\nv. Celebrezze, 460 U.S. 780 (1983), and Burdick v. Takushi,\\n504 U.S. 428 (1992), the panel first held that the State’s\\nsignature requirement imposed a minimal burden on the\\nLibertarian Party’s right to access the primary ballot.\\nAccordingly, the panel determined that a less exacting\\nscrutiny was appropriate. The panel concluded that\\nArizona’s signature requirements reasonably furthered\\nArizona’s regulatory interest in preventing voter confusion,\\nballot overcrowding, and frivolous candidacies and justified\\nthe modest burden on the Libertarian Party’s right to ballot\\naccess.\\n\\n The panel rejected the Libertarian Party’s contention that\\nthe Arizona law infringed upon its right to free association\\nby effectively requiring its candidates to solicit signatures\\nfrom non-members. The panel held that any burden on the\\nLibertarian Party’s associational freedom was modest, and\\n\\n *\\n This summary constitutes no part of the opinion of the court. It\\nhas been prepared by court staff for the convenience of the reader.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 3\\n\\nagain applying less exacting scrutiny, the panel credited\\nArizona’s important interests to justify the reasonable\\nrequirements.\\n\\n The panel further rejected the Libertarian Party’s\\ncontention that Arizona’s signature requirement violated\\nequal protection, noting that the Libertarian, Democratic,\\nand Republican Parties were all subject to the same statutory\\nrequirements. The panel observed no equal protection issue\\nin Arizona’s treatment of the Green Party, a new party that\\nwas subject to different statutory requirements.\\n\\n\\n COUNSEL\\n\\nOliver B. Hall (argued), Center for Competitive Democracy,\\nWashington, D.C., for Plaintiffs-Appellants.\\n\\nKara M. Karlson (argued) and Joseph E. La Rue, Assistant\\nAttorneys General; Mark Brnovich, Attorney General;\\nOffice of the Attorney General, Phoenix, Arizona; for\\nDefendant-Appellee.\\n\\n\\n OPINION\\n\\nMcKEOWN, Circuit Judge:\\n\\n Once again, we have before us a challenge to Arizona’s\\nrequirements to earn a place on the ballot. See, e.g., Ariz.\\nGreen Party v. Reagan, 838 F.3d 983 (9th Cir. 2016); Nader\\nv. Brewer, 531 F.3d 1028 (9th Cir. 2008). The Arizona\\nLibertarian Party challenges under the First and Fourteenth\\nAmendments a state law requiring up to 1% of voters eligible\\nto participate in its primary to sign a nominating petition for\\n\\f4 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\na Libertarian candidate to earn a place on the primary ballot.\\nThe district court granted summary judgment to the Arizona\\nSecretary of State (the “Secretary”), and we affirm.\\n\\n BACKGROUND\\n\\n Under Arizona law, there are two types of political\\nparties: “established” parties and “new” parties. A party is\\n“established” in a jurisdiction if it (i) obtained at least 5% of\\nthe total votes cast in the prior general election, or\\n(ii) maintains membership exceeding 0.66% of registered\\nvoters in that jurisdiction. Ariz. Rev. Stat. § 16-804\\n(applying to state, county, city, and town elections). An\\nestablished party is entitled to “continued representation” on\\nthe general election ballot. Id. The Libertarian, Democratic,\\nand Republican Parties are established statewide. 1\\n\\n Before 2016, to qualify for the primary ballot, an\\nestablished party candidate needed to submit signatures 2\\nexceeding a certain percentage (ranging between 0.5% and\\n2%, depending on the office sought) of the party’s registered\\nvoters in the jurisdiction where he sought election. Ariz.\\nRev. Stat. § 16-322(A) (2015). A candidate was permitted\\nto submit signatures from party members, members of any\\n 1\\n The Libertarian Party satisfies the voter registration requirement,\\nand the Democratic and Republican Parties satisfy both requirements.\\nAs of January 1, 2019, Arizona had 1.31 million registered Republicans,\\n1.17 million registered Democrats, and 32,056 registered Libertarians.\\nAriz. Sec. of State, Voter Registration & Historical Election Data,\\nhttps://azsos.gov/elections/voter-registration-historical-election-data\\n(last visited May 7, 2019).\\n 2\\n A voter may only sign one nominating petition per office per\\nelection, unless more than one candidate is to be elected to that office.\\nAriz. Rev. Stat. § 16-321(A).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 5\\n\\nnew party, or unaffiliated registered voters. 3 Id.\\n§ 16-321(D).\\n\\n In 2015, the Arizona legislature amended the signature\\nrequirements for established party candidates. 2015 Ariz.\\nSess. Laws Ch. 293, §§ 2–3 (H.B. 2608). Now, to qualify\\nfor a primary ballot, an established party candidate must\\nsubmit signatures exceeding a certain percentage of\\n“qualified signer[s],” which include the party’s registered\\nvoters, as well as all new party voters and unaffiliated\\nregistered voters. Ariz. Rev. Stat. § 16-321(F). The\\namendments reduced the signature threshold for each office\\nto between 0.25% and 1%. Id. § 16-322(A). In 2016—the\\nfirst election governed by the amended rules—there\\nwere significantly fewer Libertarian candidates on the\\nprimary and general election ballots than in prior elections.\\nSee generally Ariz. Sec. of State, Historical Election\\nResults & Information, https://azsos.gov/elections/\\nvoter-registration-historical-election-data/historical-election-\\nresults-information (last visited May 7, 2019) (collecting\\ndata for recent Arizona elections).\\n\\n A “new” party is subject to different rules. A new party\\nmust first submit a petition for recognition and signatures\\nfrom eligible voters exceeding 1.33% of total votes cast\\nstatewide in the prior gubernatorial election. Ariz. Rev. Stat.\\n§§ 16-801(A), 16-803. After doing so, the party’s\\ncandidates are eligible to pursue placement on the primary\\nand general election ballots for the next four years. Ariz.\\nRev. Stat. § 16-801(B). To retain its recognition and ballot\\n\\n 3\\n As of January 1, 2019, Arizona had 1.25 million unaffiliated\\nregistered voters. Ariz. Sec. of State, Voter Registration & Historical\\nElection Data, https://azsos.gov/elections/voter-registration-historical-\\nelection-data (last visited May 7, 2019).\\n\\f6 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\neligibility at the end of the four years, the party must either\\nqualify as an established party or file another petition for\\nrecognition and the accompanying signatures. Id.; see Ariz.\\nRev. Stat. §§ 16-803–04.\\n\\n To qualify for the primary ballot, a new party candidate\\nmust submit signatures exceeding 0.1% “of the total vote for\\nthe winning candidate or candidates for governor or\\npresidential electors at the last general election within the\\ndistrict.” Ariz. Rev. Stat. § 16-322(C). The Arizona Green\\nParty first qualified as a new party in 1990, and, never having\\nqualified as an established party, has successfully re-filed\\npetitions for new party recognition and the accompanying\\nsignatures several times, most recently in 2014. 4 Since the\\nbeginning of 2017, Arizona has permitted digital solicitation\\nand streamlined submission of voter signatures through an\\nonline portal. Ariz. Rev. Stat. §§ 16-316–18.\\n\\n Under Arizona law, an established party member may\\nnot vote in another party’s primary, but it is up to the\\nestablished parties to decide whether new party members or\\nunaffiliated voters can participate in their primaries. See\\nAriz. Rev. Stat. § 16-467. 5 The Libertarian Party excludes\\n\\n\\n\\n\\n 4\\n As of January 1, 2019, the Green Party had 6,450 registered\\nmembers in Arizona. Ariz. Sec. of State, Voter Registration & Historical\\nElection Data, https://azsos.gov/elections/voter-registration-historical-\\nelection-data (last visited May 7, 2019).\\n\\n 5\\n A state may not keep a party from welcoming unaffiliated voters\\nto participate in its primary, Tashjian v. Republican Party of Conn.,\\n479 U.S. 208, 213–29 (1986), though it may prohibit party members\\nfrom participating in another party’s primary. Clingman v. Beaver,\\n544 U.S. 581, 586–97 (2005).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 7\\n\\nsuch voters, while the Democratic and Republican Parties do\\nnot.\\n\\n In April 2016, the Libertarian Party and its chairman\\nMichael Kielsky (collectively, the “Libertarian Party”) filed\\nthis action challenging the primary signature requirements.\\nThe district court denied the Libertarian Party’s request for\\na preliminary injunction prohibiting enforcement of the\\namended requirements for the 2016 election. The parties\\nfiled cross-motions for summary judgment, and, in\\nJuly 2017, the district court granted summary judgment to\\nthe Secretary.\\n\\n ANALYSIS\\n\\n The Libertarian Party contends that Arizona’s ballot\\naccess scheme violates equal protection and infringes upon\\nthe right to place its candidates on the ballot 6 and the right\\nto free association. 7 Only the rules governing access to the\\nprimary election ballot are at issue on this appeal—the\\nLibertarian Party does not call into question the rules for\\nearning a place on the general election ballot. With that in\\nmind, we first set forth the balancing framework that guides\\nour review and then explain why Arizona’s rules for\\naccessing the primary ballot are constitutionally sound.\\n\\n\\n\\n 6\\n The Libertarian Party also contends that the statute violates its right\\nto create and establish a political party. See Norman v. Reed, 502 U.S.\\n279, 288 (1992). This claim merely recites the right to access the ballot\\nclaim, and it fails for the same reasons. See infra pp.9–14.\\n 7\\n The Libertarian Party also appeals the district court’s exclusion of\\ncertain evidence. That issue is moot because summary judgment for the\\nSecretary is warranted even if we consider the excluded evidence.\\n\\f8 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nI. The Anderson/Burdick Balancing Framework\\n\\n There is an inevitable tension between a state’s authority\\nand need to regulate its elections and the First and Fourteenth\\nAmendment rights of voters, candidates, and political\\nparties. See Storer v. Brown, 415 U.S. 724, 729–30 (1974).\\nTo harmonize these competing demands, we look to\\nAnderson v. Celebrezze, 460 U.S. 780 (1983), and Burdick\\nv. Takushi, 504 U.S. 428 (1992), which provide a “flexible\\nstandard” for reviewing constitutional challenges to state\\nelection regulations:\\n\\n A court considering a challenge to a state\\n election law must weigh “the character and\\n magnitude of the asserted injury to the rights\\n protected by the First and Fourteenth\\n Amendments that the plaintiff seeks to\\n vindicate” against “the precise interests put\\n forward by the State as justifications for the\\n burden imposed by its rule,” taking into\\n consideration “the extent to which those\\n interests make it necessary to burden the\\n plaintiff’s rights.”\\n\\nBurdick, 504 U.S. at 434 (quoting Anderson, 460 U.S.\\nat 789). We have described this approach as a “sliding\\nscale”—the more severe the burden imposed, the more\\nexacting our scrutiny; the less severe, the more relaxed our\\nscrutiny. Ariz. Green Party, 838 F.3d at 988. To pass\\nconstitutional muster, a state law imposing a severe burden\\nmust be narrowly tailored to advance “compelling” interests.\\nNorman, 502 U.S. at 289. On the other hand, a law imposing\\na minimal burden need only reasonably advance “important”\\ninterests. Timmons v. Twin Cities Area New Party, 520 U.S.\\n351, 358 (1997) (quoting Burdick, 504 U.S. at 434).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 9\\n\\n We now consider each of the Libertarian Party’s\\nconstitutional challenges under the Anderson/Burdick\\nbalancing framework.\\n\\nII. Right to Access the Ballot\\n\\n It was long ago established that a state may condition\\nballot placement on a “preliminary showing of a significant\\nmodicum of support.” Jenness v. Fortson, 403 U.S. 431, 442\\n(1971). And there is no dispute that a state may require a\\ncandidate to demonstrate support from slightly, but not\\n“substantially,” more than 5% of voters without imposing a\\nsevere burden triggering heightened scrutiny. Storer,\\n415 U.S. at 739–40; see Jenness, 403 U.S. at 442; Williams\\nv. Rhodes, 393 U.S. 23, 24–25 (1968) (invalidating\\n15% requirement). The Libertarian Party contends that\\nArizona law imposes an impermissibly high signature\\nburden, reaching as high as 30% for certain candidates. Yet,\\nthe threshold—and dispositive—question is which pool of\\nvoters we should consider when measuring this showing.\\n\\n Under Arizona law, all qualified signers—Libertarian\\nParty members, unaffiliated registered voters, and new party\\nmembers—are eligible to participate in the Libertarian Party\\nprimary and to sign a Libertarian Party nominating petition.\\nBy its very terms, the statute never requires signatures from\\nmore than 1% of these voters. However, by choice, the\\nLibertarian Party has barred non-members from voting in its\\nprimary—under party policy, only members can vote in the\\nprimary. And it does not want its candidates to solicit\\nsignatures from non-members; as a consequence, Libertarian\\ncandidates must submit signatures equal to 11% to 30% of\\nparty membership in their jurisdiction to qualify for the\\nprimary ballot. Thus, our dilemma: is the “significant\\nmodicum of support” measured against all voters eligible\\nunder state law to sign a nominating petition and participate\\n\\f10 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nin the primary? Or do we factor in a party’s decision to\\nexclude certain eligible voters from its primary and instead\\nconsider the resulting, significantly circumscribed pool?\\n\\n The Supreme Court has never expressly answered this\\nquestion, but its framework in ballot access cases is\\ninstructive. The state laws challenged in Norman, Jenness,\\nand Williams required candidates and parties seeking\\nplacement on the general election ballot to submit signatures\\nfrom registered voters equaling a designated percentage of\\nthe general election electorate. 8 The Court’s approach in\\nthese cases was straightforward: it determined whether the\\nrequired signatures represented a reasonable share of the\\nvoters eligible to participate in the upcoming election. See\\nNorman, 502 U.S. at 295; Jenness, 403 U.S. at 438–40, 442;\\nWilliams, 393 U.S. at 24–25, 30–34. In American Party of\\nTexas 9 and Storer, the state laws imposed similar\\nrequirements, with an additional limitation: a voter who\\nparticipated in another party’s primary or convention or\\nsigned another candidate’s petition was ineligible to sign a\\nnominating petition. 10 In both cases, the Court determined\\nwhether the required signatures represented a reasonable\\n\\n 8\\n The laws challenged in Norman and Williams approximated the\\nelectorate by reference to the number of voters who participated in the\\npreceding general election. Norman, 502 U.S. at 282 n.2; Williams,\\n393 U.S. at 24–25. The law challenged in Jenness approximated the\\nelectorate by reference to the number of registered voters during the\\nprevious general election. 403 U.S. at 432–33.\\n\\n 9\\n Am. Party of Tex. v. White, 415 U.S. 767 (1974).\\n\\n 10\\n Like the laws challenged in Norman and Williams, those at issue\\nin American Party of Texas and Storer approximated the electorate by\\nreference to the number of voters who participated in the preceding\\ngeneral election. Am. Party, 415 U.S. at 774–75 & nn.6–7; Storer,\\n415 U.S. at 726–27, 739–40.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 11\\n\\nshare of the “available pool” of signers, i.e., voters who had\\nnot disqualified themselves by participating in another\\nprimary or convention or by signing a previous petition.\\nStorer, 415 U.S. at 739–40; see Am. Party, 415 U.S. at 774–\\n91.\\n\\n In each of these cases, the Court asked whether the\\nrequired signatures constituted an unfairly large percentage\\nof those voters eligible under state law to offer their\\nsignatures. There was no adjustment to account for the\\nsignificant portion of this pool comprised of registered\\nmembers of other parties, many of whom, it can be\\nreasonably presumed, were unlikely to help nominate a\\ncompeting candidate or party. Nor was there any suggestion\\nthat a candidate should be limited to seeking signatures from\\nvoters who have already pledged their support to the\\ncandidate or his party or cause. Rather, the Court time and\\nagain affirmed that requiring a demonstration of “significant,\\nmeasurable quantum of community support” does not\\nimpose a severe burden. Am. Party, 415 U.S. at 782.\\n\\n We invoked a similar analysis in Nader v. Cronin,\\n620 F.3d 1214, 1217 (9th Cir. 2010). And we do so again\\nhere. Arizona law permits all qualified signers— Libertarian\\nParty members, new party members, and registered\\nunaffiliated voters—to sign a Libertarian candidate’s\\nnominating petition and to vote in the Libertarian primary.\\nHowever, qualified signers who already signed another\\ncandidate’s nominating petition are excluded from the\\n“available pool” of voters able to sign a Libertarian\\ncandidate’s petition.\\n\\n No evidence suggests that, in practice, the statute’s (at\\nmost) 1% signature requirement even approaches 5% of this\\nremaining pool of eligible signers. It falls upon the\\nLibertarian Party to demonstrate that Arizona imposes a\\n\\f12 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nsevere burden, and it has failed to do so here. The party’s\\npolicy choice to exclude all non-members from its primary\\nand its preference to obtain signatures only from party\\nmembers do not change the calculus. To hold otherwise\\nwould permit a party to determine the number of signatures\\nrequired by manipulating its nominating petition and\\nprimary voting requirements. At the same time, the\\nLibertarian Party’s proposed rule would incentivize parties\\nto have fewer registered members and therefore artificially\\nreduce the signature requirements. Just as important: where,\\nin this scheme, is the offensive state action? There is no\\nquestion that the signature requirement would be\\nconstitutional if the Libertarian Party permitted non-\\nmembers to vote in its primary. A political party cannot\\nmanipulate its internal preferences and processes to\\ntransform a constitutional statute into an unconstitutional\\none. 11\\n\\n Crucially, Arizona law does not impose any other\\nrequirements, such as a strict time period for signature\\ncollection, that might nonetheless render the 1% requirement\\n“an impossible burden” or “an impractical undertaking.”\\nStorer, 415 U.S. at 740 (requiring 1,000 canvassers to collect\\n14 signatures each day for 24 days likely imposes a modest\\nburden); see Clingman, 544 U.S. at 589–90 (limiting a\\nparty’s internal structure, decision-making processes, and\\nability to communicate with the electorate likely imposes a\\n\\n 11\\n Neither of the cases cited by the Libertarian Party persuades us\\notherwise. One addressed a law that made it “impossible either\\nabsolutely . . . or practically” for a candidate to meet a signature\\nrequirement. See Consumer Party v. Davis, 633 F. Supp. 877, 883 (E.D.\\nPa. 1986). The other struck down signature requirements because they\\nimposed disparate requirements on similarly situated parties that were,\\nthe state conceded, impossible to justify. In re Candidacy of Indep. Party\\nCandidates v. Kiffmeyer, 688 N.W.2d 854, 859–61 (Minn. 2004).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 13\\n\\nsevere burden); Timmons, 520 U.S. at 363 (same); Anderson,\\n460 U.S. at 790–94 (requiring an independent candidate to\\nfile several months before party conventions imposes severe\\nburden); Am. Party, 415 U.S. at 778–81 (requiring all\\nsignatures to be notarized and submitted in 55-day period\\ndoes not impose severe burden); Jenness, 403 U.S. at 434,\\n438 (permitting 180 days for collection of nominating\\nsignatures and requiring submission of signatures five\\nmonths before election does not impose severe burden);\\nWilliams, 393 U.S. at 24–25 & n.1 (conditioning minor\\nparty’s ballot access on formation of statewide and county-\\nlevel party committees, participation in a national party\\nconvention, and submission of nominating signatures by an\\nearly deadline exclusively from voters who never voted in a\\nprevious election imposes significant burden). To the\\ncontrary, Arizona permits candidates to solicit and submit\\nsignatures through an easy-to-use and streamlined online\\nportal. A candidate collecting hand-written signatures must,\\nin practice, collect more than the minimum number of\\nsignatures required because, inevitably, some will be\\ndeemed ineligible. In contrast, signatures submitted through\\nthe online portal are instantaneously verified, thereby\\nreducing the need to submit signatures above the threshold.\\n\\n The limited evidence describing the Libertarian Party’s\\nmodest efforts to mobilize voters and several candidates’\\nunsuccessful write-in campaigns fails to establish that, in\\npractice, Arizona law “imposes insurmountable obstacles”\\nto getting on the primary ballot. Am. Party, 415 U.S. at 784.\\nNor does the simple fact that the Libertarian Party had more\\ncandidates on past primary and general election ballots\\nreflect such an obstacle under the amended rules. See Munro\\nv. Socialist Workers Party, 479 U.S. 189, 196–97 (1986).\\nAccordingly, we apply “less exacting” scrutiny because\\nArizona law imposes a minimal burden on the Libertarian\\n\\f14 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nParty’s right to access the primary ballot. Timmons,\\n520 U.S. at 358; see Cronin, 620 F.3d at 1218.\\n\\n We now turn to whether Arizona has an “important\\nregulatory interest” that justifies this modest burden.\\nTimmons, 520 U.S. at 358 (quoting Burdick, 504 U.S.\\nat 434). Arizona’s asserted interests in preventing voter\\nconfusion, ballot overcrowding, and frivolous candidacies\\nare important interests that have justified equally, if not\\nmore, burdensome general election ballot restrictions. See\\nMunro, 479 U.S. at 194–95. These interests are also\\nimportant in the primary context, given the “obvious and\\nstrong interconnection” between primary and general\\nelections, which together operate as a “single instrumentality\\nfor choice of officers.” Pub. Integrity All., Inc. v. City of\\nTucson, 836 F.3d 1019, 1026 (9th Cir. 2016) (quoting Smith\\nv. Allwright, 321 U.S. 649, 660 (1944)); see Storer, 415 U.S.\\nat 735 (A primary election “functions to winnow out and\\nfinally reject all but the chosen candidates.”). Conditioning\\nprimary ballot placement on a demonstration of significant\\ncommunity support advances Arizona’s interests in the\\nadministration of its primary and general elections. See\\nAnderson, 460 U.S. at 788–89; see also Jenness, 403 U.S.\\nat 442; Munro, 479 U.S. at 193–94.\\n\\n Because we neither require “a particularized showing of\\nthe existence of voter confusion, ballot overcrowding, or the\\npresence of frivolous candidacies,” Munro, 479 U.S. at 194–\\n95, nor proof that ballot rules are “the only or the best way\\nto further the proffered interests,” Dudum v. Arntz, 640 F.3d\\n1098, 1114 (9th Cir. 2011), Arizona has easily met its\\nburden. The primary signature requirements reasonably\\nfurther Arizona’s important regulatory interests and\\ntherefore justify a modest burden on the Libertarian Party’s\\nright to ballot access.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 15\\n\\nIII. Right to Free Association\\n\\n The Libertarian Party contends that Arizona law\\ninfringes upon its right to free association by effectively\\nrequiring its candidates to solicit signatures from non-\\nmembers. Although the Constitution protects a political\\nparty’s right to not associate with non-members, that right\\nhas its limits. U.S. Civil Serv. Comm’n v. Nat’l Ass’n of\\nLetter Carriers, AFL-CIO, 413 U.S. 548, 567 (1973). We\\nfirst ask whether Arizona in any way “forces” the Libertarian\\nParty to associate with non-members. Cal. Democratic\\nParty v. Jones, 530 U.S. 567, 577, 581–82, 586 (2000). If\\nso, we then consider whether such forced association creates\\na “risk that nonparty members will skew either primary\\nresults or candidates’ positions.” Ariz. Libertarian Party,\\nInc. v. Bayless, 351 F.3d 1277, 1282 (9th Cir. 2003). We\\nanswer both questions in the negative.\\n\\n Unlike the state laws at issue in Jones and Bayless,\\nArizona law permits political parties to exclude non-\\nmembers from voting in their primaries. At their option,\\nLibertarian candidates may use signatures from non-party\\nmembers to qualify for the primary ballot—but Arizona law\\ndoes not require them to do so. Soliciting non-member\\nsignatures would seemingly prove helpful in placing more\\ncandidates on the primary ballot, but it is the Libertarian\\nParty’s modest membership, not a “state-imposed restriction\\non [its] freedom of association,” that imposes upon it this\\n“hard choice.” Jones, 530 U.S. at 584. 12\\n\\n\\n 12\\n In Jenness, the Supreme Court noted that, for an independent or\\nminor party candidate seeking “signatures of 5% of the eligible\\nelectorate[,] . . . the way is open [because] Georgia imposes no\\nsuffocating restrictions whatever upon the free circulation of nominating\\n\\f16 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\n We acknowledge, without deciding, that there may be\\nsome point where the ratio between party members and\\nrequired signatures constitutes de facto forced association\\nwith non-members. For example, if the signature\\nrequirement exceeded the number of party members, then a\\ncandidate necessarily would, as a matter of arithmetic, have\\nto solicit non-member signatures to qualify for the ballot.\\nBut we face no such situation here. Libertarian candidates\\ncan qualify for the primary ballot with signatures from 11%\\nto 30% of party members in their jurisdictions, and no\\nevidence suggests it is impossible to do so as a practical\\nmatter. Even if collecting these signatures is difficult, we\\nexpect “[h]ard work and sacrifice by dedicated volunteers”\\nin the operation of “any political organization.” Am. Party,\\n415 U.S. at 787. Such expectations do not in any way\\n“force” Libertarian candidates or voters to associate with\\nnon-members.\\n\\n Nor has the Libertarian Party demonstrated that the\\nsolicitation and submission of some non-member signatures\\n“will skew either primary results or candidates’ positions.”\\nBayless, 351 F.3d at 1282. We decline to embrace such a\\nspeculative conclusion. Any burden on the Libertarian\\nParty’s associational freedom is modest, so we again apply\\nless exacting scrutiny and, as above, credit Arizona’s\\nimportant interests to justify these reasonable requirements.\\nSee Timmons, 520 U.S. at 358.\\n\\n\\n\\npetitions.” 403 U.S. at 438. The Court identified various limitations on\\nsignature collection that could be, but were not, imposed under Georgia\\nlaw. Id. at 438–39. That a minor party candidate would likely obtain\\nsignatures from non-party members was presupposed by the Court, not\\nas a bug of this system, but as a positive feature. Id.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 17\\n\\nIV. Equal Protection\\n\\n Finally, the Libertarian Party contends that the signature\\nrequirements violate equal protection because they impose\\nlesser burdens on other parties. 13 The Libertarian,\\nDemocratic, and Republican Parties are all established\\nparties subject to the same statutory requirements.\\nAlthough, on its face, Arizona law treats them identically,\\nwe look to see whether the requirements provide “a real and\\nessentially equal opportunity for ballot qualification.” Am.\\nParty, 415 U.S. at 788. That standard is clearly satisfied\\nhere. A Libertarian candidate vying for the primary ballot\\nactually faces a significantly lower burden than his\\nDemocratic and Republican counterparts. For example, a\\nstatewide Libertarian candidate needs to submit\\napproximately 3,200 signatures, compared to 6,000 and\\n6,400 signatures for the Democratic and Republican\\ncompetitors, respectively. See Ariz. Rev. Stat.\\n§ 16-322(A)(1); Ariz. Sec. of State, Voter Registration &\\nHistorical Election Data, https://azsos.gov/elections/voter-\\nregistration-historical-election-data (last visited May 7,\\n2019). 14\\n\\n That a Libertarian candidate must submit signatures\\nrepresenting a higher percentage of his party membership\\nthan a Democratic or Republican candidate is a consequence\\n\\n 13\\n Despite their differences, we assume, without deciding, that the\\nLibertarian Party is similarly situated to the Democratic, Republican, and\\nGreen Parties and that the Equal Protection Clause applies. See Cronin,\\n620 F.3d at 1218.\\n\\n 14\\n Of course, the signature ratio between parties varies within each\\npolitical subdivision, as voters are not perfectly distributed throughout\\nthe state. The statewide figures are sufficiently representative for our\\npurposes.\\n\\f18 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nof the Libertarian Party’s modest size, not a fatal flaw of the\\nstatutory scheme. The Supreme Court has indicated that an\\nanalogous imbalance lacks constitutional significance. In\\nIllinois State Board of Elections v. Socialist Workers Party,\\nthe Court struck down on equal protection grounds a state\\nlaw requiring local candidates to submit substantially more\\nsignatures to qualify for the ballot than statewide candidates.\\n440 U.S. 173, 186–87 (1979). The remedy: imposing the\\nsame, 25,000 signature requirement for both local and\\nstatewide candidates, even though the eligible voter pool for\\nstatewide candidates was six times larger than the pool for\\ncertain local candidates. See id. at 183–87. If such an\\noutcome comports with equal protection, then surely so does\\nthe situation here.\\n\\n Even if we assume that the signature requirements\\nimpose a marginally higher burden on the Libertarian Party,\\nthat additional burden is far from severe. Cf. Williams,\\n393 U.S. at 25 (striking down state law that imposed\\n“substantially smaller burdens” on certain parties, while\\nmaking it “virtually impossible” for others to place a\\ncandidate on the ballot). Under less exacting scrutiny, we\\nagain conclude that the same important regulatory interests\\njustify the signature requirements. In setting the threshold\\nfor a “significant modicum of support,” Jenness, 403 U.S. at\\n442, a state must use either an absolute number of voters or\\na percentage of some group. Not only is it mathematically\\nimpossible to craft a statute where the burden on each party\\nis identical under both measurements, Arizona has no\\nobligation to seek such precision. See Dudum, 640 F.3d\\nat 1114 (recognizing regulations need not be “narrowly\\ntailored”). Nor was Arizona required to replicate or fold in\\nthe preexisting burdens on each party when it amended the\\nballot access rules in 2015. Cf. Ohio Democratic Party v.\\nHusted, 834 F.3d 620, 623 (6th Cir. 2016) (rejecting an\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 19\\n\\nargument “creat[ing] a ‘one-way ratchet’ that would\\ndiscourage states from” increasing ballot access, “lest they\\nbe prohibited by federal courts from later modifying their\\nelection procedures in response to changing\\ncircumstances”). Arizona’s choice to set the threshold as a\\npercentage of qualified signers for each established party\\nwas neither discriminatory nor unreasonable.\\n\\n Arizona opted to apply these signature requirements for\\nall parties that have a significant membership and therefore\\nexempt such parties from the quadrennial party-wide re-\\ncertification requirements imposed on new parties. This\\npolicy affords significant benefits to all established parties\\nand furthers the state’s interests in avoiding voter confusion,\\nminimizing clutter on the primary and general ballots, and\\neliminating frivolous candidacies. 15\\n\\n We likewise observe no equal protection issue in\\nArizona’s treatment of the Green Party, a new party subject\\nto different statutory requirements. When, as here, we\\n“examin[e] differing treatments of [different types of\\npolitical parties], . . . [i]n determining the nature and\\nmagnitude of the burden that [the state’s] election\\nprocedures impose on the [complaining party], we must\\nexamine the entire scheme regulating ballot access.”\\nCronin, 620 F.3d at 1217 (internal quotations and citation\\nomitted). Equal protection is violated when one set of\\n\\n 15\\n The Libertarian Party’s reliance on Kiffmeyer is, once again,\\nunpersuasive. There, two minor political parties were subject to the same\\nballot access rules; under those rules, one party had all of its candidates\\nplaced on the general election ballot, and the other had none on the ballot,\\neven though the latter received significantly more votes in the primary.\\nKiffmeyer, 688 N.W.2d at 859–61. Minnesota conceded that these rules\\nwere arbitrary and lacked any “rational . . . purpose.” Id. at 861.\\n\\f20 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nrequirements is “inherently” or “invidiously” more\\nburdensome than the other. Am. Party, 415 U.S. at 781;\\nJenness, 403 U.S. at 440–41; Cronin, 620 F.3d at 1218–19.\\n\\n The Libertarian Party’s chief complaint is that Green\\nParty candidates qualified for the 2016 primary ballot with\\nsignificantly fewer signatures than Libertarian candidates\\nfor the same races. 16 This argument fails to account for the\\nsignificant quadrennial re-filing burden placed on the Green\\nParty to retain its new party status. Every four years, the\\nGreen Party, which currently boasts less than\\n6,500 members, must submit more than 20,000 signatures\\nfor its candidates to be eligible to pursue placement on the\\nballot. That is, signatures from three times more voters than\\nit has registered members. Meeting the re-filing\\nrequirements is “an all-consuming endeavor” for the Green\\nParty, which relies on “a core group of about 10 volunteers”\\nto work “every weekend on Saturdays and Sundays for\\nseveral hours each” for more than a year. It is only once this\\nstep is complete that the modest individual candidate\\nsignature thresholds apply. Thus, it is obvious that the\\nprimary ballot signature requirements for the Libertarian\\nParty are not “inherently” or “invidiously” more\\nburdensome than those imposed on the Green Party. Am.\\nParty, 415 U.S. at 781; Jenness, 403 U.S. at 440–41. To be\\nsure, “[t]he procedures are different, but the Equal Protection\\n\\n\\n 16\\n The Libertarian Party also complains that a write-in new party\\ncandidate automatically qualifies for the general election ballot by\\nwinning his primary, while a write-in established party candidate only\\nqualifies for the general election ballot if he wins his primary with votes\\nequaling the number of signatures needed to qualify for the primary\\nballot. See Ariz. Rev. Stat. § 16-645(D)–(E). Because the Libertarian\\nParty expressly disclaims any challenge to Arizona’s general election\\nballot access requirements, we do not consider this argument.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 21\\n\\nClause does not necessarily forbid the one in preference to\\nthe other.” Am. Party, 415 U.S. at 781–82.\\n\\n CONCLUSION\\n\\n Arizona has no “constitutional imperative to reduce\\nvoter apathy or to ‘handicap’ an unpopular [party] to\\nincrease the likelihood that [its] candidate[s] will” qualify\\nfor the primary ballot. Munro, 479 U.S. at 198. The state’s\\nsignature requirements are reasonable restrictions that\\nimpose, at most, a modest burden on the Libertarian Party’s\\nFirst and Fourteenth Amendment rights, while directly\\nadvancing Arizona’s important regulatory interests. The\\ndistrict court correctly granted summary judgment to the\\nSecretary.\\n\\n AFFIRMED.\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4402849/\", \"author_raw\": \"McKEOWN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"J CLIFFORD WALLACE"},"judge2":{"kind":"string","value":"A WALLACE TASHIMA"},"judge3":{"kind":"string","value":"M MARGARET MCKEOWN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4625596/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Arizona Libertarian Party v. Katie Hobbs\nCourt: U.S. Court of Appeals for the Ninth Circuit\nDate decided: 2019-05-31\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nARIZONA LIBERTARIAN PARTY; No. 17-16491\nMICHAEL KIELSKY,\n Plaintiffs-Appellants, D.C. No.\n 2:16-cv-01019-\n v. DGC\n\nKATIE HOBBS, in her official\ncapacity as Secretary of State of OPINION\nArizona,\n Defendant-Appellee.\n\n\n\n Appeal from the United States District Court\n for the District of Arizona\n David G. Campbell, District Judge, Presiding\n\n Argued and Submitted March 12, 2019\n San Francisco, California\n\n Filed May 31, 2019\n\n Before: J. Clifford Wallace, A. Wallace Tashima, and\n M. Margaret McKeown, Circuit Judges.\n\n Opinion by Judge McKeown\n\f2 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\n SUMMARY *\n\n\n Civil Rights / Elections\n\n The panel affirmed the district court’s summary\njudgment in favor of Arizona’s Secretary of State in an\naction brought by the Arizona Libertarian Party challenging,\nunder the First and Fourteenth Amendments, a state law\nrequiring up to 1% of voters eligible to participate in\nArizona’s primary to sign a nominating petition for a\nLibertarian candidate to earn a place on the primary ballot.\n\n Applying the balancing framework set forth in Anderson\nv. Celebrezze, 460 U.S. 780 (1983), and Burdick v. Takushi,\n504 U.S. 428 (1992), the panel first held that the State’s\nsignature requirement imposed a minimal burden on the\nLibertarian Party’s right to access the primary ballot.\nAccordingly, the panel determined that a less exacting\nscrutiny was appropriate. The panel concluded that\nArizona’s signature requirements reasonably furthered\nArizona’s regulatory interest in preventing voter confusion,\nballot overcrowding, and frivolous candidacies and justified\nthe modest burden on the Libertarian Party’s right to ballot\naccess.\n\n The panel rejected the Libertarian Party’s contention that\nthe Arizona law infringed upon its right to free association\nby effectively requiring its candidates to solicit signatures\nfrom non-members. The panel held that any burden on the\nLibertarian Party’s associational freedom was modest, and\n\n *\n This summary constitutes no part of the opinion of the court. It\nhas been prepared by court staff for the convenience of the reader.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 3\n\nagain applying less exacting scrutiny, the panel credited\nArizona’s important interests to justify the reasonable\nrequirements.\n\n The panel further rejected the Libertarian Party’s\ncontention that Arizona’s signature requirement violated\nequal protection, noting that the Libertarian, Democratic,\nand Republican Parties were all subject to the same statutory\nrequirements. The panel observed no equal protection issue\nin Arizona’s treatment of the Green Party, a new party that\nwas subject to different statutory requirements.\n\n\n COUNSEL\n\nOliver B. Hall (argued), Center for Competitive Democracy,\nWashington, D.C., for Plaintiffs-Appellants.\n\nKara M. Karlson (argued) and Joseph E. La Rue, Assistant\nAttorneys General; Mark Brnovich, Attorney General;\nOffice of the Attorney General, Phoenix, Arizona; for\nDefendant-Appellee.\n\n\n OPINION\n\nMcKEOWN, Circuit Judge:\n\n Once again, we have before us a challenge to Arizona’s\nrequirements to earn a place on the ballot. See, e.g., Ariz.\nGreen Party v. Reagan, 838 F.3d 983 (9th Cir. 2016); Nader\nv. Brewer, 531 F.3d 1028 (9th Cir. 2008). The Arizona\nLibertarian Party challenges under the First and Fourteenth\nAmendments a state law requiring up to 1% of voters eligible\nto participate in its primary to sign a nominating petition for\n\f4 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\na Libertarian candidate to earn a place on the primary ballot.\nThe district court granted summary judgment to the Arizona\nSecretary of State (the “Secretary”), and we affirm.\n\n BACKGROUND\n\n Under Arizona law, there are two types of political\nparties: “established” parties and “new” parties. A party is\n“established” in a jurisdiction if it (i) obtained at least 5% of\nthe total votes cast in the prior general election, or\n(ii) maintains membership exceeding 0.66% of registered\nvoters in that jurisdiction. Ariz. Rev. Stat. § 16-804\n(applying to state, county, city, and town elections). An\nestablished party is entitled to “continued representation” on\nthe general election ballot. Id. The Libertarian, Democratic,\nand Republican Parties are established statewide. 1\n\n Before 2016, to qualify for the primary ballot, an\nestablished party candidate needed to submit signatures 2\nexceeding a certain percentage (ranging between 0.5% and\n2%, depending on the office sought) of the party’s registered\nvoters in the jurisdiction where he sought election. Ariz.\nRev. Stat. § 16-322(A) (2015). A candidate was permitted\nto submit signatures from party members, members of any\n 1\n The Libertarian Party satisfies the voter registration requirement,\nand the Democratic and Republican Parties satisfy both requirements.\nAs of January 1, 2019, Arizona had 1.31 million registered Republicans,\n1.17 million registered Democrats, and 32,056 registered Libertarians.\nAriz. Sec. of State, Voter Registration & Historical Election Data,\nhttps://azsos.gov/elections/voter-registration-historical-election-data\n(last visited May 7, 2019).\n 2\n A voter may only sign one nominating petition per office per\nelection, unless more than one candidate is to be elected to that office.\nAriz. Rev. Stat. § 16-321(A).\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 5\n\nnew party, or unaffiliated registered voters. 3 Id.\n§ 16-321(D).\n\n In 2015, the Arizona legislature amended the signature\nrequirements for established party candidates. 2015 Ariz.\nSess. Laws Ch. 293, §§ 2–3 (H.B. 2608). Now, to qualify\nfor a primary ballot, an established party candidate must\nsubmit signatures exceeding a certain percentage of\n“qualified signer[s],” which include the party’s registered\nvoters, as well as all new party voters and unaffiliated\nregistered voters. Ariz. Rev. Stat. § 16-321(F). The\namendments reduced the signature threshold for each office\nto between 0.25% and 1%. Id. § 16-322(A). In 2016—the\nfirst election governed by the amended rules—there\nwere significantly fewer Libertarian candidates on the\nprimary and general election ballots than in prior elections.\nSee generally Ariz. Sec. of State, Historical Election\nResults & Information, https://azsos.gov/elections/\nvoter-registration-historical-election-data/historical-election-\nresults-information (last visited May 7, 2019) (collecting\ndata for recent Arizona elections).\n\n A “new” party is subject to different rules. A new party\nmust first submit a petition for recognition and signatures\nfrom eligible voters exceeding 1.33% of total votes cast\nstatewide in the prior gubernatorial election. Ariz. Rev. Stat.\n§§ 16-801(A), 16-803. After doing so, the party’s\ncandidates are eligible to pursue placement on the primary\nand general election ballots for the next four years. Ariz.\nRev. Stat. § 16-801(B). To retain its recognition and ballot\n\n 3\n As of January 1, 2019, Arizona had 1.25 million unaffiliated\nregistered voters. Ariz. Sec. of State, Voter Registration & Historical\nElection Data, https://azsos.gov/elections/voter-registration-historical-\nelection-data (last visited May 7, 2019).\n\f6 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\neligibility at the end of the four years, the party must either\nqualify as an established party or file another petition for\nrecognition and the accompanying signatures. Id.; see Ariz.\nRev. Stat. §§ 16-803–04.\n\n To qualify for the primary ballot, a new party candidate\nmust submit signatures exceeding 0.1% “of the total vote for\nthe winning candidate or candidates for governor or\npresidential electors at the last general election within the\ndistrict.” Ariz. Rev. Stat. § 16-322(C). The Arizona Green\nParty first qualified as a new party in 1990, and, never having\nqualified as an established party, has successfully re-filed\npetitions for new party recognition and the accompanying\nsignatures several times, most recently in 2014. 4 Since the\nbeginning of 2017, Arizona has permitted digital solicitation\nand streamlined submission of voter signatures through an\nonline portal. Ariz. Rev. Stat. §§ 16-316–18.\n\n Under Arizona law, an established party member may\nnot vote in another party’s primary, but it is up to the\nestablished parties to decide whether new party members or\nunaffiliated voters can participate in their primaries. See\nAriz. Rev. Stat. § 16-467. 5 The Libertarian Party excludes\n\n\n\n\n 4\n As of January 1, 2019, the Green Party had 6,450 registered\nmembers in Arizona. Ariz. Sec. of State, Voter Registration & Historical\nElection Data, https://azsos.gov/elections/voter-registration-historical-\nelection-data (last visited May 7, 2019).\n\n 5\n A state may not keep a party from welcoming unaffiliated voters\nto participate in its primary, Tashjian v. Republican Party of Conn.,\n479 U.S. 208, 213–29 (1986), though it may prohibit party members\nfrom participating in another party’s primary. Clingman v. Beaver,\n544 U.S. 581, 586–97 (2005).\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 7\n\nsuch voters, while the Democratic and Republican Parties do\nnot.\n\n In April 2016, the Libertarian Party and its chairman\nMichael Kielsky (collectively, the “Libertarian Party”) filed\nthis action challenging the primary signature requirements.\nThe district court denied the Libertarian Party’s request for\na preliminary injunction prohibiting enforcement of the\namended requirements for the 2016 election. The parties\nfiled cross-motions for summary judgment, and, in\nJuly 2017, the district court granted summary judgment to\nthe Secretary.\n\n ANALYSIS\n\n The Libertarian Party contends that Arizona’s ballot\naccess scheme violates equal protection and infringes upon\nthe right to place its candidates on the ballot 6 and the right\nto free association. 7 Only the rules governing access to the\nprimary election ballot are at issue on this appeal—the\nLibertarian Party does not call into question the rules for\nearning a place on the general election ballot. With that in\nmind, we first set forth the balancing framework that guides\nour review and then explain why Arizona’s rules for\naccessing the primary ballot are constitutionally sound.\n\n\n\n 6\n The Libertarian Party also contends that the statute violates its right\nto create and establish a political party. See Norman v. Reed, 502 U.S.\n279, 288 (1992). This claim merely recites the right to access the ballot\nclaim, and it fails for the same reasons. See infra pp.9–14.\n 7\n The Libertarian Party also appeals the district court’s exclusion of\ncertain evidence. That issue is moot because summary judgment for the\nSecretary is warranted even if we consider the excluded evidence.\n\f8 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nI. The Anderson/Burdick Balancing Framework\n\n There is an inevitable tension between a state’s authority\nand need to regulate its elections and the First and Fourteenth\nAmendment rights of voters, candidates, and political\nparties. See Storer v. Brown, 415 U.S. 724, 729–30 (1974).\nTo harmonize these competing demands, we look to\nAnderson v. Celebrezze, 460 U.S. 780 (1983), and Burdick\nv. Takushi, 504 U.S. 428 (1992), which provide a “flexible\nstandard” for reviewing constitutional challenges to state\nelection regulations:\n\n A court considering a challenge to a state\n election law must weigh “the character and\n magnitude of the asserted injury to the rights\n protected by the First and Fourteenth\n Amendments that the plaintiff seeks to\n vindicate” against “the precise interests put\n forward by the State as justifications for the\n burden imposed by its rule,” taking into\n consideration “the extent to which those\n interests make it necessary to burden the\n plaintiff’s rights.”\n\nBurdick, 504 U.S. at 434 (quoting Anderson, 460 U.S.\nat 789). We have described this approach as a “sliding\nscale”—the more severe the burden imposed, the more\nexacting our scrutiny; the less severe, the more relaxed our\nscrutiny. Ariz. Green Party, 838 F.3d at 988. To pass\nconstitutional muster, a state law imposing a severe burden\nmust be narrowly tailored to advance “compelling” interests.\nNorman, 502 U.S. at 289. On the other hand, a law imposing\na minimal burden need only reasonably advance “important”\ninterests. Timmons v. Twin Cities Area New Party, 520 U.S.\n351, 358 (1997) (quoting Burdick, 504 U.S. at 434).\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 9\n\n We now consider each of the Libertarian Party’s\nconstitutional challenges under the Anderson/Burdick\nbalancing framework.\n\nII. Right to Access the Ballot\n\n It was long ago established that a state may condition\nballot placement on a “preliminary showing of a significant\nmodicum of support.” Jenness v. Fortson, 403 U.S. 431, 442\n(1971). And there is no dispute that a state may require a\ncandidate to demonstrate support from slightly, but not\n“substantially,” more than 5% of voters without imposing a\nsevere burden triggering heightened scrutiny. Storer,\n415 U.S. at 739–40; see Jenness, 403 U.S. at 442; Williams\nv. Rhodes, 393 U.S. 23, 24–25 (1968) (invalidating\n15% requirement). The Libertarian Party contends that\nArizona law imposes an impermissibly high signature\nburden, reaching as high as 30% for certain candidates. Yet,\nthe threshold—and dispositive—question is which pool of\nvoters we should consider when measuring this showing.\n\n Under Arizona law, all qualified signers—Libertarian\nParty members, unaffiliated registered voters, and new party\nmembers—are eligible to participate in the Libertarian Party\nprimary and to sign a Libertarian Party nominating petition.\nBy its very terms, the statute never requires signatures from\nmore than 1% of these voters. However, by choice, the\nLibertarian Party has barred non-members from voting in its\nprimary—under party policy, only members can vote in the\nprimary. And it does not want its candidates to solicit\nsignatures from non-members; as a consequence, Libertarian\ncandidates must submit signatures equal to 11% to 30% of\nparty membership in their jurisdiction to qualify for the\nprimary ballot. Thus, our dilemma: is the “significant\nmodicum of support” measured against all voters eligible\nunder state law to sign a nominating petition and participate\n\f10 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nin the primary? Or do we factor in a party’s decision to\nexclude certain eligible voters from its primary and instead\nconsider the resulting, significantly circumscribed pool?\n\n The Supreme Court has never expressly answered this\nquestion, but its framework in ballot access cases is\ninstructive. The state laws challenged in Norman, Jenness,\nand Williams required candidates and parties seeking\nplacement on the general election ballot to submit signatures\nfrom registered voters equaling a designated percentage of\nthe general election electorate. 8 The Court’s approach in\nthese cases was straightforward: it determined whether the\nrequired signatures represented a reasonable share of the\nvoters eligible to participate in the upcoming election. See\nNorman, 502 U.S. at 295; Jenness, 403 U.S. at 438–40, 442;\nWilliams, 393 U.S. at 24–25, 30–34. In American Party of\nTexas 9 and Storer, the state laws imposed similar\nrequirements, with an additional limitation: a voter who\nparticipated in another party’s primary or convention or\nsigned another candidate’s petition was ineligible to sign a\nnominating petition. 10 In both cases, the Court determined\nwhether the required signatures represented a reasonable\n\n 8\n The laws challenged in Norman and Williams approximated the\nelectorate by reference to the number of voters who participated in the\npreceding general election. Norman, 502 U.S. at 282 n.2; Williams,\n393 U.S. at 24–25. The law challenged in Jenness approximated the\nelectorate by reference to the number of registered voters during the\nprevious general election. 403 U.S. at 432–33.\n\n 9\n Am. Party of Tex. v. White, 415 U.S. 767 (1974).\n\n 10\n Like the laws challenged in Norman and Williams, those at issue\nin American Party of Texas and Storer approximated the electorate by\nreference to the number of voters who participated in the preceding\ngeneral election. Am. Party, 415 U.S. at 774–75 & nn.6–7; Storer,\n415 U.S. at 726–27, 739–40.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 11\n\nshare of the “available pool” of signers, i.e., voters who had\nnot disqualified themselves by participating in another\nprimary or convention or by signing a previous petition.\nStorer, 415 U.S. at 739–40; see Am. Party, 415 U.S. at 774–\n91.\n\n In each of these cases, the Court asked whether the\nrequired signatures constituted an unfairly large percentage\nof those voters eligible under state law to offer their\nsignatures. There was no adjustment to account for the\nsignificant portion of this pool comprised of registered\nmembers of other parties, many of whom, it can be\nreasonably presumed, were unlikely to help nominate a\ncompeting candidate or party. Nor was there any suggestion\nthat a candidate should be limited to seeking signatures from\nvoters who have already pledged their support to the\ncandidate or his party or cause. Rather, the Court time and\nagain affirmed that requiring a demonstration of “significant,\nmeasurable quantum of community support” does not\nimpose a severe burden. Am. Party, 415 U.S. at 782.\n\n We invoked a similar analysis in Nader v. Cronin,\n620 F.3d 1214, 1217 (9th Cir. 2010). And we do so again\nhere. Arizona law permits all qualified signers— Libertarian\nParty members, new party members, and registered\nunaffiliated voters—to sign a Libertarian candidate’s\nnominating petition and to vote in the Libertarian primary.\nHowever, qualified signers who already signed another\ncandidate’s nominating petition are excluded from the\n“available pool” of voters able to sign a Libertarian\ncandidate’s petition.\n\n No evidence suggests that, in practice, the statute’s (at\nmost) 1% signature requirement even approaches 5% of this\nremaining pool of eligible signers. It falls upon the\nLibertarian Party to demonstrate that Arizona imposes a\n\f12 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nsevere burden, and it has failed to do so here. The party’s\npolicy choice to exclude all non-members from its primary\nand its preference to obtain signatures only from party\nmembers do not change the calculus. To hold otherwise\nwould permit a party to determine the number of signatures\nrequired by manipulating its nominating petition and\nprimary voting requirements. At the same time, the\nLibertarian Party’s proposed rule would incentivize parties\nto have fewer registered members and therefore artificially\nreduce the signature requirements. Just as important: where,\nin this scheme, is the offensive state action? There is no\nquestion that the signature requirement would be\nconstitutional if the Libertarian Party permitted non-\nmembers to vote in its primary. A political party cannot\nmanipulate its internal preferences and processes to\ntransform a constitutional statute into an unconstitutional\none. 11\n\n Crucially, Arizona law does not impose any other\nrequirements, such as a strict time period for signature\ncollection, that might nonetheless render the 1% requirement\n“an impossible burden” or “an impractical undertaking.”\nStorer, 415 U.S. at 740 (requiring 1,000 canvassers to collect\n14 signatures each day for 24 days likely imposes a modest\nburden); see Clingman, 544 U.S. at 589–90 (limiting a\nparty’s internal structure, decision-making processes, and\nability to communicate with the electorate likely imposes a\n\n 11\n Neither of the cases cited by the Libertarian Party persuades us\notherwise. One addressed a law that made it “impossible either\nabsolutely . . . or practically” for a candidate to meet a signature\nrequirement. See Consumer Party v. Davis, 633 F. Supp. 877, 883 (E.D.\nPa. 1986). The other struck down signature requirements because they\nimposed disparate requirements on similarly situated parties that were,\nthe state conceded, impossible to justify. In re Candidacy of Indep. Party\nCandidates v. Kiffmeyer, 688 N.W.2d 854, 859–61 (Minn. 2004).\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 13\n\nsevere burden); Timmons, 520 U.S. at 363 (same); Anderson,\n460 U.S. at 790–94 (requiring an independent candidate to\nfile several months before party conventions imposes severe\nburden); Am. Party, 415 U.S. at 778–81 (requiring all\nsignatures to be notarized and submitted in 55-day period\ndoes not impose severe burden); Jenness, 403 U.S. at 434,\n438 (permitting 180 days for collection of nominating\nsignatures and requiring submission of signatures five\nmonths before election does not impose severe burden);\nWilliams, 393 U.S. at 24–25 & n.1 (conditioning minor\nparty’s ballot access on formation of statewide and county-\nlevel party committees, participation in a national party\nconvention, and submission of nominating signatures by an\nearly deadline exclusively from voters who never voted in a\nprevious election imposes significant burden). To the\ncontrary, Arizona permits candidates to solicit and submit\nsignatures through an easy-to-use and streamlined online\nportal. A candidate collecting hand-written signatures must,\nin practice, collect more than the minimum number of\nsignatures required because, inevitably, some will be\ndeemed ineligible. In contrast, signatures submitted through\nthe online portal are instantaneously verified, thereby\nreducing the need to submit signatures above the threshold.\n\n The limited evidence describing the Libertarian Party’s\nmodest efforts to mobilize voters and several candidates’\nunsuccessful write-in campaigns fails to establish that, in\npractice, Arizona law “imposes insurmountable obstacles”\nto getting on the primary ballot. Am. Party, 415 U.S. at 784.\nNor does the simple fact that the Libertarian Party had more\ncandidates on past primary and general election ballots\nreflect such an obstacle under the amended rules. See Munro\nv. Socialist Workers Party, 479 U.S. 189, 196–97 (1986).\nAccordingly, we apply “less exacting” scrutiny because\nArizona law imposes a minimal burden on the Libertarian\n\f14 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nParty’s right to access the primary ballot. Timmons,\n520 U.S. at 358; see Cronin, 620 F.3d at 1218.\n\n We now turn to whether Arizona has an “important\nregulatory interest” that justifies this modest burden.\nTimmons, 520 U.S. at 358 (quoting Burdick, 504 U.S.\nat 434). Arizona’s asserted interests in preventing voter\nconfusion, ballot overcrowding, and frivolous candidacies\nare important interests that have justified equally, if not\nmore, burdensome general election ballot restrictions. See\nMunro, 479 U.S. at 194–95. These interests are also\nimportant in the primary context, given the “obvious and\nstrong interconnection” between primary and general\nelections, which together operate as a “single instrumentality\nfor choice of officers.” Pub. Integrity All., Inc. v. City of\nTucson, 836 F.3d 1019, 1026 (9th Cir. 2016) (quoting Smith\nv. Allwright, 321 U.S. 649, 660 (1944)); see Storer, 415 U.S.\nat 735 (A primary election “functions to winnow out and\nfinally reject all but the chosen candidates.”). Conditioning\nprimary ballot placement on a demonstration of significant\ncommunity support advances Arizona’s interests in the\nadministration of its primary and general elections. See\nAnderson, 460 U.S. at 788–89; see also Jenness, 403 U.S.\nat 442; Munro, 479 U.S. at 193–94.\n\n Because we neither require “a particularized showing of\nthe existence of voter confusion, ballot overcrowding, or the\npresence of frivolous candidacies,” Munro, 479 U.S. at 194–\n95, nor proof that ballot rules are “the only or the best way\nto further the proffered interests,” Dudum v. Arntz, 640 F.3d\n1098, 1114 (9th Cir. 2011), Arizona has easily met its\nburden. The primary signature requirements reasonably\nfurther Arizona’s important regulatory interests and\ntherefore justify a modest burden on the Libertarian Party’s\nright to ballot access.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 15\n\nIII. Right to Free Association\n\n The Libertarian Party contends that Arizona law\ninfringes upon its right to free association by effectively\nrequiring its candidates to solicit signatures from non-\nmembers. Although the Constitution protects a political\nparty’s right to not associate with non-members, that right\nhas its limits. U.S. Civil Serv. Comm’n v. Nat’l Ass’n of\nLetter Carriers, AFL-CIO, 413 U.S. 548, 567 (1973). We\nfirst ask whether Arizona in any way “forces” the Libertarian\nParty to associate with non-members. Cal. Democratic\nParty v. Jones, 530 U.S. 567, 577, 581–82, 586 (2000). If\nso, we then consider whether such forced association creates\na “risk that nonparty members will skew either primary\nresults or candidates’ positions.” Ariz. Libertarian Party,\nInc. v. Bayless, 351 F.3d 1277, 1282 (9th Cir. 2003). We\nanswer both questions in the negative.\n\n Unlike the state laws at issue in Jones and Bayless,\nArizona law permits political parties to exclude non-\nmembers from voting in their primaries. At their option,\nLibertarian candidates may use signatures from non-party\nmembers to qualify for the primary ballot—but Arizona law\ndoes not require them to do so. Soliciting non-member\nsignatures would seemingly prove helpful in placing more\ncandidates on the primary ballot, but it is the Libertarian\nParty’s modest membership, not a “state-imposed restriction\non [its] freedom of association,” that imposes upon it this\n“hard choice.” Jones, 530 U.S. at 584. 12\n\n\n 12\n In Jenness, the Supreme Court noted that, for an independent or\nminor party candidate seeking “signatures of 5% of the eligible\nelectorate[,] . . . the way is open [because] Georgia imposes no\nsuffocating restrictions whatever upon the free circulation of nominating\n\f16 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\n We acknowledge, without deciding, that there may be\nsome point where the ratio between party members and\nrequired signatures constitutes de facto forced association\nwith non-members. For example, if the signature\nrequirement exceeded the number of party members, then a\ncandidate necessarily would, as a matter of arithmetic, have\nto solicit non-member signatures to qualify for the ballot.\nBut we face no such situation here. Libertarian candidates\ncan qualify for the primary ballot with signatures from 11%\nto 30% of party members in their jurisdictions, and no\nevidence suggests it is impossible to do so as a practical\nmatter. Even if collecting these signatures is difficult, we\nexpect “[h]ard work and sacrifice by dedicated volunteers”\nin the operation of “any political organization.” Am. Party,\n415 U.S. at 787. Such expectations do not in any way\n“force” Libertarian candidates or voters to associate with\nnon-members.\n\n Nor has the Libertarian Party demonstrated that the\nsolicitation and submission of some non-member signatures\n“will skew either primary results or candidates’ positions.”\nBayless, 351 F.3d at 1282. We decline to embrace such a\nspeculative conclusion. Any burden on the Libertarian\nParty’s associational freedom is modest, so we again apply\nless exacting scrutiny and, as above, credit Arizona’s\nimportant interests to justify these reasonable requirements.\nSee Timmons, 520 U.S. at 358.\n\n\n\npetitions.” 403 U.S. at 438. The Court identified various limitations on\nsignature collection that could be, but were not, imposed under Georgia\nlaw. Id. at 438–39. That a minor party candidate would likely obtain\nsignatures from non-party members was presupposed by the Court, not\nas a bug of this system, but as a positive feature. Id.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 17\n\nIV. Equal Protection\n\n Finally, the Libertarian Party contends that the signature\nrequirements violate equal protection because they impose\nlesser burdens on other parties. 13 The Libertarian,\nDemocratic, and Republican Parties are all established\nparties subject to the same statutory requirements.\nAlthough, on its face, Arizona law treats them identically,\nwe look to see whether the requirements provide “a real and\nessentially equal opportunity for ballot qualification.” Am.\nParty, 415 U.S. at 788. That standard is clearly satisfied\nhere. A Libertarian candidate vying for the primary ballot\nactually faces a significantly lower burden than his\nDemocratic and Republican counterparts. For example, a\nstatewide Libertarian candidate needs to submit\napproximately 3,200 signatures, compared to 6,000 and\n6,400 signatures for the Democratic and Republican\ncompetitors, respectively. See Ariz. Rev. Stat.\n§ 16-322(A)(1); Ariz. Sec. of State, Voter Registration &\nHistorical Election Data, https://azsos.gov/elections/voter-\nregistration-historical-election-data (last visited May 7,\n2019). 14\n\n That a Libertarian candidate must submit signatures\nrepresenting a higher percentage of his party membership\nthan a Democratic or Republican candidate is a consequence\n\n 13\n Despite their differences, we assume, without deciding, that the\nLibertarian Party is similarly situated to the Democratic, Republican, and\nGreen Parties and that the Equal Protection Clause applies. See Cronin,\n620 F.3d at 1218.\n\n 14\n Of course, the signature ratio between parties varies within each\npolitical subdivision, as voters are not perfectly distributed throughout\nthe state. The statewide figures are sufficiently representative for our\npurposes.\n\f18 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nof the Libertarian Party’s modest size, not a fatal flaw of the\nstatutory scheme. The Supreme Court has indicated that an\nanalogous imbalance lacks constitutional significance. In\nIllinois State Board of Elections v. Socialist Workers Party,\nthe Court struck down on equal protection grounds a state\nlaw requiring local candidates to submit substantially more\nsignatures to qualify for the ballot than statewide candidates.\n440 U.S. 173, 186–87 (1979). The remedy: imposing the\nsame, 25,000 signature requirement for both local and\nstatewide candidates, even though the eligible voter pool for\nstatewide candidates was six times larger than the pool for\ncertain local candidates. See id. at 183–87. If such an\noutcome comports with equal protection, then surely so does\nthe situation here.\n\n Even if we assume that the signature requirements\nimpose a marginally higher burden on the Libertarian Party,\nthat additional burden is far from severe. Cf. Williams,\n393 U.S. at 25 (striking down state law that imposed\n“substantially smaller burdens” on certain parties, while\nmaking it “virtually impossible” for others to place a\ncandidate on the ballot). Under less exacting scrutiny, we\nagain conclude that the same important regulatory interests\njustify the signature requirements. In setting the threshold\nfor a “significant modicum of support,” Jenness, 403 U.S. at\n442, a state must use either an absolute number of voters or\na percentage of some group. Not only is it mathematically\nimpossible to craft a statute where the burden on each party\nis identical under both measurements, Arizona has no\nobligation to seek such precision. See Dudum, 640 F.3d\nat 1114 (recognizing regulations need not be “narrowly\ntailored”). Nor was Arizona required to replicate or fold in\nthe preexisting burdens on each party when it amended the\nballot access rules in 2015. Cf. Ohio Democratic Party v.\nHusted, 834 F.3d 620, 623 (6th Cir. 2016) (rejecting an\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 19\n\nargument “creat[ing] a ‘one-way ratchet’ that would\ndiscourage states from” increasing ballot access, “lest they\nbe prohibited by federal courts from later modifying their\nelection procedures in response to changing\ncircumstances”). Arizona’s choice to set the threshold as a\npercentage of qualified signers for each established party\nwas neither discriminatory nor unreasonable.\n\n Arizona opted to apply these signature requirements for\nall parties that have a significant membership and therefore\nexempt such parties from the quadrennial party-wide re-\ncertification requirements imposed on new parties. This\npolicy affords significant benefits to all established parties\nand furthers the state’s interests in avoiding voter confusion,\nminimizing clutter on the primary and general ballots, and\neliminating frivolous candidacies. 15\n\n We likewise observe no equal protection issue in\nArizona’s treatment of the Green Party, a new party subject\nto different statutory requirements. When, as here, we\n“examin[e] differing treatments of [different types of\npolitical parties], . . . [i]n determining the nature and\nmagnitude of the burden that [the state’s] election\nprocedures impose on the [complaining party], we must\nexamine the entire scheme regulating ballot access.”\nCronin, 620 F.3d at 1217 (internal quotations and citation\nomitted). Equal protection is violated when one set of\n\n 15\n The Libertarian Party’s reliance on Kiffmeyer is, once again,\nunpersuasive. There, two minor political parties were subject to the same\nballot access rules; under those rules, one party had all of its candidates\nplaced on the general election ballot, and the other had none on the ballot,\neven though the latter received significantly more votes in the primary.\nKiffmeyer, 688 N.W.2d at 859–61. Minnesota conceded that these rules\nwere arbitrary and lacked any “rational . . . purpose.” Id. at 861.\n\f20 ARIZ. LIBERTARIAN PARTY V. HOBBS\n\nrequirements is “inherently” or “invidiously” more\nburdensome than the other. Am. Party, 415 U.S. at 781;\nJenness, 403 U.S. at 440–41; Cronin, 620 F.3d at 1218–19.\n\n The Libertarian Party’s chief complaint is that Green\nParty candidates qualified for the 2016 primary ballot with\nsignificantly fewer signatures than Libertarian candidates\nfor the same races. 16 This argument fails to account for the\nsignificant quadrennial re-filing burden placed on the Green\nParty to retain its new party status. Every four years, the\nGreen Party, which currently boasts less than\n6,500 members, must submit more than 20,000 signatures\nfor its candidates to be eligible to pursue placement on the\nballot. That is, signatures from three times more voters than\nit has registered members. Meeting the re-filing\nrequirements is “an all-consuming endeavor” for the Green\nParty, which relies on “a core group of about 10 volunteers”\nto work “every weekend on Saturdays and Sundays for\nseveral hours each” for more than a year. It is only once this\nstep is complete that the modest individual candidate\nsignature thresholds apply. Thus, it is obvious that the\nprimary ballot signature requirements for the Libertarian\nParty are not “inherently” or “invidiously” more\nburdensome than those imposed on the Green Party. Am.\nParty, 415 U.S. at 781; Jenness, 403 U.S. at 440–41. To be\nsure, “[t]he procedures are different, but the Equal Protection\n\n\n 16\n The Libertarian Party also complains that a write-in new party\ncandidate automatically qualifies for the general election ballot by\nwinning his primary, while a write-in established party candidate only\nqualifies for the general election ballot if he wins his primary with votes\nequaling the number of signatures needed to qualify for the primary\nballot. See Ariz. Rev. Stat. § 16-645(D)–(E). Because the Libertarian\nParty expressly disclaims any challenge to Arizona’s general election\nballot access requirements, we do not consider this argument.\n\f ARIZ. LIBERTARIAN PARTY V. HOBBS 21\n\nClause does not necessarily forbid the one in preference to\nthe other.” Am. Party, 415 U.S. at 781–82.\n\n CONCLUSION\n\n Arizona has no “constitutional imperative to reduce\nvoter apathy or to ‘handicap’ an unpopular [party] to\nincrease the likelihood that [its] candidate[s] will” qualify\nfor the primary ballot. Munro, 479 U.S. at 198. The state’s\nsignature requirements are reasonable restrictions that\nimpose, at most, a modest burden on the Libertarian Party’s\nFirst and Fourteenth Amendment rights, while directly\nadvancing Arizona’s important regulatory interests. The\ndistrict court correctly granted summary judgment to the\nSecretary.\n\n AFFIRMED.\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Arizona Libertarian Party v. Katie Hobbs\\nCourt: U.S. Court of Appeals for the Ninth Circuit\\nDate decided: 2019-05-31\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFOR PUBLICATION\\n\\n UNITED STATES COURT OF APPEALS\\n FOR THE NINTH CIRCUIT\\n\\n\\nARIZONA LIBERTARIAN PARTY; No. 17-16491\\nMICHAEL KIELSKY,\\n Plaintiffs-Appellants, D.C. No.\\n 2:16-cv-01019-\\n v. DGC\\n\\nKATIE HOBBS, in her official\\ncapacity as Secretary of State of OPINION\\nArizona,\\n Defendant-Appellee.\\n\\n\\n\\n Appeal from the United States District Court\\n for the District of Arizona\\n David G. Campbell, District Judge, Presiding\\n\\n Argued and Submitted March 12, 2019\\n San Francisco, California\\n\\n Filed May 31, 2019\\n\\n Before: J. Clifford Wallace, A. Wallace Tashima, and\\n M. Margaret McKeown, Circuit Judges.\\n\\n Opinion by Judge McKeown\\n\\f2 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\n SUMMARY *\\n\\n\\n Civil Rights / Elections\\n\\n The panel affirmed the district court’s summary\\njudgment in favor of Arizona’s Secretary of State in an\\naction brought by the Arizona Libertarian Party challenging,\\nunder the First and Fourteenth Amendments, a state law\\nrequiring up to 1% of voters eligible to participate in\\nArizona’s primary to sign a nominating petition for a\\nLibertarian candidate to earn a place on the primary ballot.\\n\\n Applying the balancing framework set forth in Anderson\\nv. Celebrezze, 460 U.S. 780 (1983), and Burdick v. Takushi,\\n504 U.S. 428 (1992), the panel first held that the State’s\\nsignature requirement imposed a minimal burden on the\\nLibertarian Party’s right to access the primary ballot.\\nAccordingly, the panel determined that a less exacting\\nscrutiny was appropriate. The panel concluded that\\nArizona’s signature requirements reasonably furthered\\nArizona’s regulatory interest in preventing voter confusion,\\nballot overcrowding, and frivolous candidacies and justified\\nthe modest burden on the Libertarian Party’s right to ballot\\naccess.\\n\\n The panel rejected the Libertarian Party’s contention that\\nthe Arizona law infringed upon its right to free association\\nby effectively requiring its candidates to solicit signatures\\nfrom non-members. The panel held that any burden on the\\nLibertarian Party’s associational freedom was modest, and\\n\\n *\\n This summary constitutes no part of the opinion of the court. It\\nhas been prepared by court staff for the convenience of the reader.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 3\\n\\nagain applying less exacting scrutiny, the panel credited\\nArizona’s important interests to justify the reasonable\\nrequirements.\\n\\n The panel further rejected the Libertarian Party’s\\ncontention that Arizona’s signature requirement violated\\nequal protection, noting that the Libertarian, Democratic,\\nand Republican Parties were all subject to the same statutory\\nrequirements. The panel observed no equal protection issue\\nin Arizona’s treatment of the Green Party, a new party that\\nwas subject to different statutory requirements.\\n\\n\\n COUNSEL\\n\\nOliver B. Hall (argued), Center for Competitive Democracy,\\nWashington, D.C., for Plaintiffs-Appellants.\\n\\nKara M. Karlson (argued) and Joseph E. La Rue, Assistant\\nAttorneys General; Mark Brnovich, Attorney General;\\nOffice of the Attorney General, Phoenix, Arizona; for\\nDefendant-Appellee.\\n\\n\\n OPINION\\n\\nMcKEOWN, Circuit Judge:\\n\\n Once again, we have before us a challenge to Arizona’s\\nrequirements to earn a place on the ballot. See, e.g., Ariz.\\nGreen Party v. Reagan, 838 F.3d 983 (9th Cir. 2016); Nader\\nv. Brewer, 531 F.3d 1028 (9th Cir. 2008). The Arizona\\nLibertarian Party challenges under the First and Fourteenth\\nAmendments a state law requiring up to 1% of voters eligible\\nto participate in its primary to sign a nominating petition for\\n\\f4 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\na Libertarian candidate to earn a place on the primary ballot.\\nThe district court granted summary judgment to the Arizona\\nSecretary of State (the “Secretary”), and we affirm.\\n\\n BACKGROUND\\n\\n Under Arizona law, there are two types of political\\nparties: “established” parties and “new” parties. A party is\\n“established” in a jurisdiction if it (i) obtained at least 5% of\\nthe total votes cast in the prior general election, or\\n(ii) maintains membership exceeding 0.66% of registered\\nvoters in that jurisdiction. Ariz. Rev. Stat. § 16-804\\n(applying to state, county, city, and town elections). An\\nestablished party is entitled to “continued representation” on\\nthe general election ballot. Id. The Libertarian, Democratic,\\nand Republican Parties are established statewide. 1\\n\\n Before 2016, to qualify for the primary ballot, an\\nestablished party candidate needed to submit signatures 2\\nexceeding a certain percentage (ranging between 0.5% and\\n2%, depending on the office sought) of the party’s registered\\nvoters in the jurisdiction where he sought election. Ariz.\\nRev. Stat. § 16-322(A) (2015). A candidate was permitted\\nto submit signatures from party members, members of any\\n 1\\n The Libertarian Party satisfies the voter registration requirement,\\nand the Democratic and Republican Parties satisfy both requirements.\\nAs of January 1, 2019, Arizona had 1.31 million registered Republicans,\\n1.17 million registered Democrats, and 32,056 registered Libertarians.\\nAriz. Sec. of State, Voter Registration & Historical Election Data,\\nhttps://azsos.gov/elections/voter-registration-historical-election-data\\n(last visited May 7, 2019).\\n 2\\n A voter may only sign one nominating petition per office per\\nelection, unless more than one candidate is to be elected to that office.\\nAriz. Rev. Stat. § 16-321(A).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 5\\n\\nnew party, or unaffiliated registered voters. 3 Id.\\n§ 16-321(D).\\n\\n In 2015, the Arizona legislature amended the signature\\nrequirements for established party candidates. 2015 Ariz.\\nSess. Laws Ch. 293, §§ 2–3 (H.B. 2608). Now, to qualify\\nfor a primary ballot, an established party candidate must\\nsubmit signatures exceeding a certain percentage of\\n“qualified signer[s],” which include the party’s registered\\nvoters, as well as all new party voters and unaffiliated\\nregistered voters. Ariz. Rev. Stat. § 16-321(F). The\\namendments reduced the signature threshold for each office\\nto between 0.25% and 1%. Id. § 16-322(A). In 2016—the\\nfirst election governed by the amended rules—there\\nwere significantly fewer Libertarian candidates on the\\nprimary and general election ballots than in prior elections.\\nSee generally Ariz. Sec. of State, Historical Election\\nResults & Information, https://azsos.gov/elections/\\nvoter-registration-historical-election-data/historical-election-\\nresults-information (last visited May 7, 2019) (collecting\\ndata for recent Arizona elections).\\n\\n A “new” party is subject to different rules. A new party\\nmust first submit a petition for recognition and signatures\\nfrom eligible voters exceeding 1.33% of total votes cast\\nstatewide in the prior gubernatorial election. Ariz. Rev. Stat.\\n§§ 16-801(A), 16-803. After doing so, the party’s\\ncandidates are eligible to pursue placement on the primary\\nand general election ballots for the next four years. Ariz.\\nRev. Stat. § 16-801(B). To retain its recognition and ballot\\n\\n 3\\n As of January 1, 2019, Arizona had 1.25 million unaffiliated\\nregistered voters. Ariz. Sec. of State, Voter Registration & Historical\\nElection Data, https://azsos.gov/elections/voter-registration-historical-\\nelection-data (last visited May 7, 2019).\\n\\f6 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\neligibility at the end of the four years, the party must either\\nqualify as an established party or file another petition for\\nrecognition and the accompanying signatures. Id.; see Ariz.\\nRev. Stat. §§ 16-803–04.\\n\\n To qualify for the primary ballot, a new party candidate\\nmust submit signatures exceeding 0.1% “of the total vote for\\nthe winning candidate or candidates for governor or\\npresidential electors at the last general election within the\\ndistrict.” Ariz. Rev. Stat. § 16-322(C). The Arizona Green\\nParty first qualified as a new party in 1990, and, never having\\nqualified as an established party, has successfully re-filed\\npetitions for new party recognition and the accompanying\\nsignatures several times, most recently in 2014. 4 Since the\\nbeginning of 2017, Arizona has permitted digital solicitation\\nand streamlined submission of voter signatures through an\\nonline portal. Ariz. Rev. Stat. §§ 16-316–18.\\n\\n Under Arizona law, an established party member may\\nnot vote in another party’s primary, but it is up to the\\nestablished parties to decide whether new party members or\\nunaffiliated voters can participate in their primaries. See\\nAriz. Rev. Stat. § 16-467. 5 The Libertarian Party excludes\\n\\n\\n\\n\\n 4\\n As of January 1, 2019, the Green Party had 6,450 registered\\nmembers in Arizona. Ariz. Sec. of State, Voter Registration & Historical\\nElection Data, https://azsos.gov/elections/voter-registration-historical-\\nelection-data (last visited May 7, 2019).\\n\\n 5\\n A state may not keep a party from welcoming unaffiliated voters\\nto participate in its primary, Tashjian v. Republican Party of Conn.,\\n479 U.S. 208, 213–29 (1986), though it may prohibit party members\\nfrom participating in another party’s primary. Clingman v. Beaver,\\n544 U.S. 581, 586–97 (2005).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 7\\n\\nsuch voters, while the Democratic and Republican Parties do\\nnot.\\n\\n In April 2016, the Libertarian Party and its chairman\\nMichael Kielsky (collectively, the “Libertarian Party”) filed\\nthis action challenging the primary signature requirements.\\nThe district court denied the Libertarian Party’s request for\\na preliminary injunction prohibiting enforcement of the\\namended requirements for the 2016 election. The parties\\nfiled cross-motions for summary judgment, and, in\\nJuly 2017, the district court granted summary judgment to\\nthe Secretary.\\n\\n ANALYSIS\\n\\n The Libertarian Party contends that Arizona’s ballot\\naccess scheme violates equal protection and infringes upon\\nthe right to place its candidates on the ballot 6 and the right\\nto free association. 7 Only the rules governing access to the\\nprimary election ballot are at issue on this appeal—the\\nLibertarian Party does not call into question the rules for\\nearning a place on the general election ballot. With that in\\nmind, we first set forth the balancing framework that guides\\nour review and then explain why Arizona’s rules for\\naccessing the primary ballot are constitutionally sound.\\n\\n\\n\\n 6\\n The Libertarian Party also contends that the statute violates its right\\nto create and establish a political party. See Norman v. Reed, 502 U.S.\\n279, 288 (1992). This claim merely recites the right to access the ballot\\nclaim, and it fails for the same reasons. See infra pp.9–14.\\n 7\\n The Libertarian Party also appeals the district court’s exclusion of\\ncertain evidence. That issue is moot because summary judgment for the\\nSecretary is warranted even if we consider the excluded evidence.\\n\\f8 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nI. The Anderson/Burdick Balancing Framework\\n\\n There is an inevitable tension between a state’s authority\\nand need to regulate its elections and the First and Fourteenth\\nAmendment rights of voters, candidates, and political\\nparties. See Storer v. Brown, 415 U.S. 724, 729–30 (1974).\\nTo harmonize these competing demands, we look to\\nAnderson v. Celebrezze, 460 U.S. 780 (1983), and Burdick\\nv. Takushi, 504 U.S. 428 (1992), which provide a “flexible\\nstandard” for reviewing constitutional challenges to state\\nelection regulations:\\n\\n A court considering a challenge to a state\\n election law must weigh “the character and\\n magnitude of the asserted injury to the rights\\n protected by the First and Fourteenth\\n Amendments that the plaintiff seeks to\\n vindicate” against “the precise interests put\\n forward by the State as justifications for the\\n burden imposed by its rule,” taking into\\n consideration “the extent to which those\\n interests make it necessary to burden the\\n plaintiff’s rights.”\\n\\nBurdick, 504 U.S. at 434 (quoting Anderson, 460 U.S.\\nat 789). We have described this approach as a “sliding\\nscale”—the more severe the burden imposed, the more\\nexacting our scrutiny; the less severe, the more relaxed our\\nscrutiny. Ariz. Green Party, 838 F.3d at 988. To pass\\nconstitutional muster, a state law imposing a severe burden\\nmust be narrowly tailored to advance “compelling” interests.\\nNorman, 502 U.S. at 289. On the other hand, a law imposing\\na minimal burden need only reasonably advance “important”\\ninterests. Timmons v. Twin Cities Area New Party, 520 U.S.\\n351, 358 (1997) (quoting Burdick, 504 U.S. at 434).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 9\\n\\n We now consider each of the Libertarian Party’s\\nconstitutional challenges under the Anderson/Burdick\\nbalancing framework.\\n\\nII. Right to Access the Ballot\\n\\n It was long ago established that a state may condition\\nballot placement on a “preliminary showing of a significant\\nmodicum of support.” Jenness v. Fortson, 403 U.S. 431, 442\\n(1971). And there is no dispute that a state may require a\\ncandidate to demonstrate support from slightly, but not\\n“substantially,” more than 5% of voters without imposing a\\nsevere burden triggering heightened scrutiny. Storer,\\n415 U.S. at 739–40; see Jenness, 403 U.S. at 442; Williams\\nv. Rhodes, 393 U.S. 23, 24–25 (1968) (invalidating\\n15% requirement). The Libertarian Party contends that\\nArizona law imposes an impermissibly high signature\\nburden, reaching as high as 30% for certain candidates. Yet,\\nthe threshold—and dispositive—question is which pool of\\nvoters we should consider when measuring this showing.\\n\\n Under Arizona law, all qualified signers—Libertarian\\nParty members, unaffiliated registered voters, and new party\\nmembers—are eligible to participate in the Libertarian Party\\nprimary and to sign a Libertarian Party nominating petition.\\nBy its very terms, the statute never requires signatures from\\nmore than 1% of these voters. However, by choice, the\\nLibertarian Party has barred non-members from voting in its\\nprimary—under party policy, only members can vote in the\\nprimary. And it does not want its candidates to solicit\\nsignatures from non-members; as a consequence, Libertarian\\ncandidates must submit signatures equal to 11% to 30% of\\nparty membership in their jurisdiction to qualify for the\\nprimary ballot. Thus, our dilemma: is the “significant\\nmodicum of support” measured against all voters eligible\\nunder state law to sign a nominating petition and participate\\n\\f10 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nin the primary? Or do we factor in a party’s decision to\\nexclude certain eligible voters from its primary and instead\\nconsider the resulting, significantly circumscribed pool?\\n\\n The Supreme Court has never expressly answered this\\nquestion, but its framework in ballot access cases is\\ninstructive. The state laws challenged in Norman, Jenness,\\nand Williams required candidates and parties seeking\\nplacement on the general election ballot to submit signatures\\nfrom registered voters equaling a designated percentage of\\nthe general election electorate. 8 The Court’s approach in\\nthese cases was straightforward: it determined whether the\\nrequired signatures represented a reasonable share of the\\nvoters eligible to participate in the upcoming election. See\\nNorman, 502 U.S. at 295; Jenness, 403 U.S. at 438–40, 442;\\nWilliams, 393 U.S. at 24–25, 30–34. In American Party of\\nTexas 9 and Storer, the state laws imposed similar\\nrequirements, with an additional limitation: a voter who\\nparticipated in another party’s primary or convention or\\nsigned another candidate’s petition was ineligible to sign a\\nnominating petition. 10 In both cases, the Court determined\\nwhether the required signatures represented a reasonable\\n\\n 8\\n The laws challenged in Norman and Williams approximated the\\nelectorate by reference to the number of voters who participated in the\\npreceding general election. Norman, 502 U.S. at 282 n.2; Williams,\\n393 U.S. at 24–25. The law challenged in Jenness approximated the\\nelectorate by reference to the number of registered voters during the\\nprevious general election. 403 U.S. at 432–33.\\n\\n 9\\n Am. Party of Tex. v. White, 415 U.S. 767 (1974).\\n\\n 10\\n Like the laws challenged in Norman and Williams, those at issue\\nin American Party of Texas and Storer approximated the electorate by\\nreference to the number of voters who participated in the preceding\\ngeneral election. Am. Party, 415 U.S. at 774–75 & nn.6–7; Storer,\\n415 U.S. at 726–27, 739–40.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 11\\n\\nshare of the “available pool” of signers, i.e., voters who had\\nnot disqualified themselves by participating in another\\nprimary or convention or by signing a previous petition.\\nStorer, 415 U.S. at 739–40; see Am. Party, 415 U.S. at 774–\\n91.\\n\\n In each of these cases, the Court asked whether the\\nrequired signatures constituted an unfairly large percentage\\nof those voters eligible under state law to offer their\\nsignatures. There was no adjustment to account for the\\nsignificant portion of this pool comprised of registered\\nmembers of other parties, many of whom, it can be\\nreasonably presumed, were unlikely to help nominate a\\ncompeting candidate or party. Nor was there any suggestion\\nthat a candidate should be limited to seeking signatures from\\nvoters who have already pledged their support to the\\ncandidate or his party or cause. Rather, the Court time and\\nagain affirmed that requiring a demonstration of “significant,\\nmeasurable quantum of community support” does not\\nimpose a severe burden. Am. Party, 415 U.S. at 782.\\n\\n We invoked a similar analysis in Nader v. Cronin,\\n620 F.3d 1214, 1217 (9th Cir. 2010). And we do so again\\nhere. Arizona law permits all qualified signers— Libertarian\\nParty members, new party members, and registered\\nunaffiliated voters—to sign a Libertarian candidate’s\\nnominating petition and to vote in the Libertarian primary.\\nHowever, qualified signers who already signed another\\ncandidate’s nominating petition are excluded from the\\n“available pool” of voters able to sign a Libertarian\\ncandidate’s petition.\\n\\n No evidence suggests that, in practice, the statute’s (at\\nmost) 1% signature requirement even approaches 5% of this\\nremaining pool of eligible signers. It falls upon the\\nLibertarian Party to demonstrate that Arizona imposes a\\n\\f12 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nsevere burden, and it has failed to do so here. The party’s\\npolicy choice to exclude all non-members from its primary\\nand its preference to obtain signatures only from party\\nmembers do not change the calculus. To hold otherwise\\nwould permit a party to determine the number of signatures\\nrequired by manipulating its nominating petition and\\nprimary voting requirements. At the same time, the\\nLibertarian Party’s proposed rule would incentivize parties\\nto have fewer registered members and therefore artificially\\nreduce the signature requirements. Just as important: where,\\nin this scheme, is the offensive state action? There is no\\nquestion that the signature requirement would be\\nconstitutional if the Libertarian Party permitted non-\\nmembers to vote in its primary. A political party cannot\\nmanipulate its internal preferences and processes to\\ntransform a constitutional statute into an unconstitutional\\none. 11\\n\\n Crucially, Arizona law does not impose any other\\nrequirements, such as a strict time period for signature\\ncollection, that might nonetheless render the 1% requirement\\n“an impossible burden” or “an impractical undertaking.”\\nStorer, 415 U.S. at 740 (requiring 1,000 canvassers to collect\\n14 signatures each day for 24 days likely imposes a modest\\nburden); see Clingman, 544 U.S. at 589–90 (limiting a\\nparty’s internal structure, decision-making processes, and\\nability to communicate with the electorate likely imposes a\\n\\n 11\\n Neither of the cases cited by the Libertarian Party persuades us\\notherwise. One addressed a law that made it “impossible either\\nabsolutely . . . or practically” for a candidate to meet a signature\\nrequirement. See Consumer Party v. Davis, 633 F. Supp. 877, 883 (E.D.\\nPa. 1986). The other struck down signature requirements because they\\nimposed disparate requirements on similarly situated parties that were,\\nthe state conceded, impossible to justify. In re Candidacy of Indep. Party\\nCandidates v. Kiffmeyer, 688 N.W.2d 854, 859–61 (Minn. 2004).\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 13\\n\\nsevere burden); Timmons, 520 U.S. at 363 (same); Anderson,\\n460 U.S. at 790–94 (requiring an independent candidate to\\nfile several months before party conventions imposes severe\\nburden); Am. Party, 415 U.S. at 778–81 (requiring all\\nsignatures to be notarized and submitted in 55-day period\\ndoes not impose severe burden); Jenness, 403 U.S. at 434,\\n438 (permitting 180 days for collection of nominating\\nsignatures and requiring submission of signatures five\\nmonths before election does not impose severe burden);\\nWilliams, 393 U.S. at 24–25 & n.1 (conditioning minor\\nparty’s ballot access on formation of statewide and county-\\nlevel party committees, participation in a national party\\nconvention, and submission of nominating signatures by an\\nearly deadline exclusively from voters who never voted in a\\nprevious election imposes significant burden). To the\\ncontrary, Arizona permits candidates to solicit and submit\\nsignatures through an easy-to-use and streamlined online\\nportal. A candidate collecting hand-written signatures must,\\nin practice, collect more than the minimum number of\\nsignatures required because, inevitably, some will be\\ndeemed ineligible. In contrast, signatures submitted through\\nthe online portal are instantaneously verified, thereby\\nreducing the need to submit signatures above the threshold.\\n\\n The limited evidence describing the Libertarian Party’s\\nmodest efforts to mobilize voters and several candidates’\\nunsuccessful write-in campaigns fails to establish that, in\\npractice, Arizona law “imposes insurmountable obstacles”\\nto getting on the primary ballot. Am. Party, 415 U.S. at 784.\\nNor does the simple fact that the Libertarian Party had more\\ncandidates on past primary and general election ballots\\nreflect such an obstacle under the amended rules. See Munro\\nv. Socialist Workers Party, 479 U.S. 189, 196–97 (1986).\\nAccordingly, we apply “less exacting” scrutiny because\\nArizona law imposes a minimal burden on the Libertarian\\n\\f14 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nParty’s right to access the primary ballot. Timmons,\\n520 U.S. at 358; see Cronin, 620 F.3d at 1218.\\n\\n We now turn to whether Arizona has an “important\\nregulatory interest” that justifies this modest burden.\\nTimmons, 520 U.S. at 358 (quoting Burdick, 504 U.S.\\nat 434). Arizona’s asserted interests in preventing voter\\nconfusion, ballot overcrowding, and frivolous candidacies\\nare important interests that have justified equally, if not\\nmore, burdensome general election ballot restrictions. See\\nMunro, 479 U.S. at 194–95. These interests are also\\nimportant in the primary context, given the “obvious and\\nstrong interconnection” between primary and general\\nelections, which together operate as a “single instrumentality\\nfor choice of officers.” Pub. Integrity All., Inc. v. City of\\nTucson, 836 F.3d 1019, 1026 (9th Cir. 2016) (quoting Smith\\nv. Allwright, 321 U.S. 649, 660 (1944)); see Storer, 415 U.S.\\nat 735 (A primary election “functions to winnow out and\\nfinally reject all but the chosen candidates.”). Conditioning\\nprimary ballot placement on a demonstration of significant\\ncommunity support advances Arizona’s interests in the\\nadministration of its primary and general elections. See\\nAnderson, 460 U.S. at 788–89; see also Jenness, 403 U.S.\\nat 442; Munro, 479 U.S. at 193–94.\\n\\n Because we neither require “a particularized showing of\\nthe existence of voter confusion, ballot overcrowding, or the\\npresence of frivolous candidacies,” Munro, 479 U.S. at 194–\\n95, nor proof that ballot rules are “the only or the best way\\nto further the proffered interests,” Dudum v. Arntz, 640 F.3d\\n1098, 1114 (9th Cir. 2011), Arizona has easily met its\\nburden. The primary signature requirements reasonably\\nfurther Arizona’s important regulatory interests and\\ntherefore justify a modest burden on the Libertarian Party’s\\nright to ballot access.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 15\\n\\nIII. Right to Free Association\\n\\n The Libertarian Party contends that Arizona law\\ninfringes upon its right to free association by effectively\\nrequiring its candidates to solicit signatures from non-\\nmembers. Although the Constitution protects a political\\nparty’s right to not associate with non-members, that right\\nhas its limits. U.S. Civil Serv. Comm’n v. Nat’l Ass’n of\\nLetter Carriers, AFL-CIO, 413 U.S. 548, 567 (1973). We\\nfirst ask whether Arizona in any way “forces” the Libertarian\\nParty to associate with non-members. Cal. Democratic\\nParty v. Jones, 530 U.S. 567, 577, 581–82, 586 (2000). If\\nso, we then consider whether such forced association creates\\na “risk that nonparty members will skew either primary\\nresults or candidates’ positions.” Ariz. Libertarian Party,\\nInc. v. Bayless, 351 F.3d 1277, 1282 (9th Cir. 2003). We\\nanswer both questions in the negative.\\n\\n Unlike the state laws at issue in Jones and Bayless,\\nArizona law permits political parties to exclude non-\\nmembers from voting in their primaries. At their option,\\nLibertarian candidates may use signatures from non-party\\nmembers to qualify for the primary ballot—but Arizona law\\ndoes not require them to do so. Soliciting non-member\\nsignatures would seemingly prove helpful in placing more\\ncandidates on the primary ballot, but it is the Libertarian\\nParty’s modest membership, not a “state-imposed restriction\\non [its] freedom of association,” that imposes upon it this\\n“hard choice.” Jones, 530 U.S. at 584. 12\\n\\n\\n 12\\n In Jenness, the Supreme Court noted that, for an independent or\\nminor party candidate seeking “signatures of 5% of the eligible\\nelectorate[,] . . . the way is open [because] Georgia imposes no\\nsuffocating restrictions whatever upon the free circulation of nominating\\n\\f16 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\n We acknowledge, without deciding, that there may be\\nsome point where the ratio between party members and\\nrequired signatures constitutes de facto forced association\\nwith non-members. For example, if the signature\\nrequirement exceeded the number of party members, then a\\ncandidate necessarily would, as a matter of arithmetic, have\\nto solicit non-member signatures to qualify for the ballot.\\nBut we face no such situation here. Libertarian candidates\\ncan qualify for the primary ballot with signatures from 11%\\nto 30% of party members in their jurisdictions, and no\\nevidence suggests it is impossible to do so as a practical\\nmatter. Even if collecting these signatures is difficult, we\\nexpect “[h]ard work and sacrifice by dedicated volunteers”\\nin the operation of “any political organization.” Am. Party,\\n415 U.S. at 787. Such expectations do not in any way\\n“force” Libertarian candidates or voters to associate with\\nnon-members.\\n\\n Nor has the Libertarian Party demonstrated that the\\nsolicitation and submission of some non-member signatures\\n“will skew either primary results or candidates’ positions.”\\nBayless, 351 F.3d at 1282. We decline to embrace such a\\nspeculative conclusion. Any burden on the Libertarian\\nParty’s associational freedom is modest, so we again apply\\nless exacting scrutiny and, as above, credit Arizona’s\\nimportant interests to justify these reasonable requirements.\\nSee Timmons, 520 U.S. at 358.\\n\\n\\n\\npetitions.” 403 U.S. at 438. The Court identified various limitations on\\nsignature collection that could be, but were not, imposed under Georgia\\nlaw. Id. at 438–39. That a minor party candidate would likely obtain\\nsignatures from non-party members was presupposed by the Court, not\\nas a bug of this system, but as a positive feature. Id.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 17\\n\\nIV. Equal Protection\\n\\n Finally, the Libertarian Party contends that the signature\\nrequirements violate equal protection because they impose\\nlesser burdens on other parties. 13 The Libertarian,\\nDemocratic, and Republican Parties are all established\\nparties subject to the same statutory requirements.\\nAlthough, on its face, Arizona law treats them identically,\\nwe look to see whether the requirements provide “a real and\\nessentially equal opportunity for ballot qualification.” Am.\\nParty, 415 U.S. at 788. That standard is clearly satisfied\\nhere. A Libertarian candidate vying for the primary ballot\\nactually faces a significantly lower burden than his\\nDemocratic and Republican counterparts. For example, a\\nstatewide Libertarian candidate needs to submit\\napproximately 3,200 signatures, compared to 6,000 and\\n6,400 signatures for the Democratic and Republican\\ncompetitors, respectively. See Ariz. Rev. Stat.\\n§ 16-322(A)(1); Ariz. Sec. of State, Voter Registration &\\nHistorical Election Data, https://azsos.gov/elections/voter-\\nregistration-historical-election-data (last visited May 7,\\n2019). 14\\n\\n That a Libertarian candidate must submit signatures\\nrepresenting a higher percentage of his party membership\\nthan a Democratic or Republican candidate is a consequence\\n\\n 13\\n Despite their differences, we assume, without deciding, that the\\nLibertarian Party is similarly situated to the Democratic, Republican, and\\nGreen Parties and that the Equal Protection Clause applies. See Cronin,\\n620 F.3d at 1218.\\n\\n 14\\n Of course, the signature ratio between parties varies within each\\npolitical subdivision, as voters are not perfectly distributed throughout\\nthe state. The statewide figures are sufficiently representative for our\\npurposes.\\n\\f18 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nof the Libertarian Party’s modest size, not a fatal flaw of the\\nstatutory scheme. The Supreme Court has indicated that an\\nanalogous imbalance lacks constitutional significance. In\\nIllinois State Board of Elections v. Socialist Workers Party,\\nthe Court struck down on equal protection grounds a state\\nlaw requiring local candidates to submit substantially more\\nsignatures to qualify for the ballot than statewide candidates.\\n440 U.S. 173, 186–87 (1979). The remedy: imposing the\\nsame, 25,000 signature requirement for both local and\\nstatewide candidates, even though the eligible voter pool for\\nstatewide candidates was six times larger than the pool for\\ncertain local candidates. See id. at 183–87. If such an\\noutcome comports with equal protection, then surely so does\\nthe situation here.\\n\\n Even if we assume that the signature requirements\\nimpose a marginally higher burden on the Libertarian Party,\\nthat additional burden is far from severe. Cf. Williams,\\n393 U.S. at 25 (striking down state law that imposed\\n“substantially smaller burdens” on certain parties, while\\nmaking it “virtually impossible” for others to place a\\ncandidate on the ballot). Under less exacting scrutiny, we\\nagain conclude that the same important regulatory interests\\njustify the signature requirements. In setting the threshold\\nfor a “significant modicum of support,” Jenness, 403 U.S. at\\n442, a state must use either an absolute number of voters or\\na percentage of some group. Not only is it mathematically\\nimpossible to craft a statute where the burden on each party\\nis identical under both measurements, Arizona has no\\nobligation to seek such precision. See Dudum, 640 F.3d\\nat 1114 (recognizing regulations need not be “narrowly\\ntailored”). Nor was Arizona required to replicate or fold in\\nthe preexisting burdens on each party when it amended the\\nballot access rules in 2015. Cf. Ohio Democratic Party v.\\nHusted, 834 F.3d 620, 623 (6th Cir. 2016) (rejecting an\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 19\\n\\nargument “creat[ing] a ‘one-way ratchet’ that would\\ndiscourage states from” increasing ballot access, “lest they\\nbe prohibited by federal courts from later modifying their\\nelection procedures in response to changing\\ncircumstances”). Arizona’s choice to set the threshold as a\\npercentage of qualified signers for each established party\\nwas neither discriminatory nor unreasonable.\\n\\n Arizona opted to apply these signature requirements for\\nall parties that have a significant membership and therefore\\nexempt such parties from the quadrennial party-wide re-\\ncertification requirements imposed on new parties. This\\npolicy affords significant benefits to all established parties\\nand furthers the state’s interests in avoiding voter confusion,\\nminimizing clutter on the primary and general ballots, and\\neliminating frivolous candidacies. 15\\n\\n We likewise observe no equal protection issue in\\nArizona’s treatment of the Green Party, a new party subject\\nto different statutory requirements. When, as here, we\\n“examin[e] differing treatments of [different types of\\npolitical parties], . . . [i]n determining the nature and\\nmagnitude of the burden that [the state’s] election\\nprocedures impose on the [complaining party], we must\\nexamine the entire scheme regulating ballot access.”\\nCronin, 620 F.3d at 1217 (internal quotations and citation\\nomitted). Equal protection is violated when one set of\\n\\n 15\\n The Libertarian Party’s reliance on Kiffmeyer is, once again,\\nunpersuasive. There, two minor political parties were subject to the same\\nballot access rules; under those rules, one party had all of its candidates\\nplaced on the general election ballot, and the other had none on the ballot,\\neven though the latter received significantly more votes in the primary.\\nKiffmeyer, 688 N.W.2d at 859–61. Minnesota conceded that these rules\\nwere arbitrary and lacked any “rational . . . purpose.” Id. at 861.\\n\\f20 ARIZ. LIBERTARIAN PARTY V. HOBBS\\n\\nrequirements is “inherently” or “invidiously” more\\nburdensome than the other. Am. Party, 415 U.S. at 781;\\nJenness, 403 U.S. at 440–41; Cronin, 620 F.3d at 1218–19.\\n\\n The Libertarian Party’s chief complaint is that Green\\nParty candidates qualified for the 2016 primary ballot with\\nsignificantly fewer signatures than Libertarian candidates\\nfor the same races. 16 This argument fails to account for the\\nsignificant quadrennial re-filing burden placed on the Green\\nParty to retain its new party status. Every four years, the\\nGreen Party, which currently boasts less than\\n6,500 members, must submit more than 20,000 signatures\\nfor its candidates to be eligible to pursue placement on the\\nballot. That is, signatures from three times more voters than\\nit has registered members. Meeting the re-filing\\nrequirements is “an all-consuming endeavor” for the Green\\nParty, which relies on “a core group of about 10 volunteers”\\nto work “every weekend on Saturdays and Sundays for\\nseveral hours each” for more than a year. It is only once this\\nstep is complete that the modest individual candidate\\nsignature thresholds apply. Thus, it is obvious that the\\nprimary ballot signature requirements for the Libertarian\\nParty are not “inherently” or “invidiously” more\\nburdensome than those imposed on the Green Party. Am.\\nParty, 415 U.S. at 781; Jenness, 403 U.S. at 440–41. To be\\nsure, “[t]he procedures are different, but the Equal Protection\\n\\n\\n 16\\n The Libertarian Party also complains that a write-in new party\\ncandidate automatically qualifies for the general election ballot by\\nwinning his primary, while a write-in established party candidate only\\nqualifies for the general election ballot if he wins his primary with votes\\nequaling the number of signatures needed to qualify for the primary\\nballot. See Ariz. Rev. Stat. § 16-645(D)–(E). Because the Libertarian\\nParty expressly disclaims any challenge to Arizona’s general election\\nballot access requirements, we do not consider this argument.\\n\\f ARIZ. LIBERTARIAN PARTY V. HOBBS 21\\n\\nClause does not necessarily forbid the one in preference to\\nthe other.” Am. Party, 415 U.S. at 781–82.\\n\\n CONCLUSION\\n\\n Arizona has no “constitutional imperative to reduce\\nvoter apathy or to ‘handicap’ an unpopular [party] to\\nincrease the likelihood that [its] candidate[s] will” qualify\\nfor the primary ballot. Munro, 479 U.S. at 198. The state’s\\nsignature requirements are reasonable restrictions that\\nimpose, at most, a modest burden on the Libertarian Party’s\\nFirst and Fourteenth Amendment rights, while directly\\nadvancing Arizona’s important regulatory interests. The\\ndistrict court correctly granted summary judgment to the\\nSecretary.\\n\\n AFFIRMED.\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2253,"cells":{"id":{"kind":"number","value":4616602,"string":"4,616,602"},"name":{"kind":"string","value":"NAYLOR FARMS, INC. ; Harrel's LLC, Plaintiffs-Appellees, v. CHAPARRAL ENERGY, LLC, Defendant-Appellant, Black Stone Minerals Company, L.P., Amicus Curiae."},"name_abbreviation":{"kind":"string","value":"Naylor Farms, Inc. v. Chaparral Energy, LLC"},"decision_date":{"kind":"string","value":"2019-05-03"},"docket_number":{"kind":"string","value":"17-6146"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Moritz, Murphy, Eid\", \"parties\": \"\", \"opinions\": [{\"author\": \"MORITZ, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 3, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n NAYLOR FARMS, INC.; HARREL’S\\n LLC,\\n\\n Plaintiffs - Appellees,\\n\\n v. No. 17-6146\\n\\n CHAPARRAL ENERGY, LLC,\\n\\n Defendant – Appellant,\\n\\n _____________________\\n\\n BLACK STONE MINERALS\\n COMPANY, L.P.,\\n\\n Amicus Curiae.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the Western District of Oklahoma\\n (D.C. No. 5:11-CV-00634-HE)\\n _________________________________\\n\\nAnthony J. Shaheen, Holland & Hart LLP, Denver, Colorado (Christopher A. Chrisman\\nand Jessica M. Schmidt, Holland & Hart LLP, Denver, Colorado; Linda J. Byford,\\nChaparral Energy, LLC, Oklahoma City, Oklahoma; John J. Griffin, Jr., Harvey D. Ellis,\\nJr., and Charles V. Knutter, Crowe & Dunlevy, Oklahoma City, Oklahoma, with him on\\nthe briefs), for Defendant-Appellant Chaparral Energy, LLC.\\n\\nConner L. Helms (Gary R. Underwood and Erin M. Moore, with him on the brief), Helms\\nUnderwood & Cook, Oklahoma City, Oklahoma, for Plaintiffs-Appellees Naylor Farms,\\nInc. and Harrel’s LLC.\\n\\fDaniel H. Charest and Warren T. Burns, Burns Charest LLP, Dallas, Texas, filed an\\namicus curiae brief for Black Stone Minerals Company, L.P. in support of Plaintiffs-\\nAppellees Naylor Farms, Inc. and Harrel’s L.L.C.\\n _________________________________\\n\\nBefore MORITZ, MURPHY, and EID, Circuit Judges.\\n _________________________________\\n\\nMORITZ, Circuit Judge.\\n _________________________________\\n\\n Defendant Chaparral Energy, L.L.C. (Chaparral) operates approximately 2,500\\n\\noil and gas wells in Oklahoma. Plaintiffs Naylor Farms, Inc. and Harrel’s, L.L.C.\\n\\n(collectively, Naylor Farms) have royalty interests in some of those wells. As a\\n\\nresult, Naylor Farms receives a portion of the proceeds those wells generate. But\\n\\naccording to Naylor Farms, Chaparral systematically underpaid Naylor Farms and\\n\\nother similarly situated royalty owners by improperly deducting from their royalty\\n\\npayments certain gas-treatment costs—costs that Naylor Farms says Chaparral was\\n\\nrequired to shoulder under Oklahoma law. Thus, Naylor Farms brought a putative\\n\\nclass-action lawsuit against Chaparral and moved to certify the class under Rule 23\\n\\nof the Federal Rules of Civil Procedure. The district court granted Naylor Farms’\\n\\nmotion to certify, and Chaparral now appeals the district court’s certification order.\\n\\nFor the reasons discussed below, we affirm.\\n\\n Background\\n\\n Under Oklahoma law, lessees like Chaparral are subject to an implied duty of\\n\\nmarketability (IDM).1 The IDM imposes upon lessees “a duty to provide a\\n\\n\\n 1\\n The parties agree that Oklahoma substantive law controls.\\n 2\\n\\fmarketable product available to market.” Mittelstaedt v. Santa Fe Minerals, Inc., 954\\n\\nP.2d 1203, 1206 (Okla. 1998). Consistent with this duty, lessees are generally\\n\\nprecluded from passing along to royalty owners any costs the lessees incur in making\\n\\na product marketable. See id. at 1208. And because “raw or unprocessed gas” must\\n\\ntypically “undergo[] certain field processes”—such as gathering, compressing,\\n\\ndehydrating, transporting, and producing (GCDTP services)—to make the gas\\n\\nmarketable, lessees generally bear the costs associated with performing such services.\\n\\nId. at 1205, 1208.\\n\\n Citing the IDM, Naylor Farms brought a putative class-action lawsuit against\\n\\nChaparral, asserting claims for breach of contract, breach of fiduciary duty, fraud,\\n\\nunjust enrichment, and failure to produce in paying quantities. As relevant here,\\n\\nNaylor Farms’ complaint alleges that Chaparral breached the IDM by improperly\\n\\ndeducting GCDTP-service costs from the royalty payments Chaparral made to Naylor\\n\\nFarms and to other similarly-situated royalty owners. More specifically, Naylor\\n\\nFarms contends that in an attempt to circumvent the IDM, Chaparral enters into\\n\\nwellhead sales contracts with midstream processing companies. Under the terms of\\n\\nthose contracts, the midstream companies acquire title or possession of unprocessed\\n\\ngas at or near the wellhead.2 Yet according to Naylor Farms, the midstream\\n\\n\\n 2\\n The contracts fall into two categories: percentage-of-proceeds (POP)\\ncontracts and percentage-of-liquids (POL) contracts. The vast majority of the\\ncontracts at issue are POP contracts. Under a POP contract, the midstream processing\\ncompany takes possession of the entire gas stream, processes the gas, sells it to a\\ndownstream purchaser, and then pays Chaparral a percentage of the resulting\\nproceeds. Under a POL contract, the midstream processing company obtains\\n 3\\n\\fcompanies don’t actually pay Chaparral for the gas at this time. Instead, the\\n\\nmidstream companies first perform certain GCDTP services and then sell the treated\\n\\ngas to downstream purchasers.\\n\\n At that point, Naylor Farms asserts, the midstream companies (1) take the\\n\\ngross proceeds they receive from the downstream sales; (2) deduct from those gross\\n\\nproceeds the costs and fees associated with performing the GCDTP services;3 and\\n\\n(3) pay Chaparral for the gas they previously acquired at the wellhead by giving\\n\\nChaparral the resulting net proceeds. Chaparral then calculates royalty payments\\n\\nbased on the net proceeds it receives from the midstream companies, rather than\\n\\ncalculating royalty payments based on the gross proceeds the midstream companies\\n\\nreceive from the downstream sales. And in doing so, Naylor Farms alleges, Chaparral\\n\\nimpermissibly “requires royalty owners to bear the costs of transforming unprocessed\\n\\ngas into a marketable product,” thus violating the IDM. Id. at 13.\\n\\n Based on this theory of liability, Naylor Farms moved to certify a class\\n\\ncomprising it and other similarly situated royalty owners.4 In relevant part, Naylor\\n\\n\\n\\n(1) possession of and title to the natural gas liquids (NGLs) and (2) possession of\\n(but not title to) the residue gas at the wellhead. Chaparral retains title to the residue\\ngas, which the midstream processing company returns to Chaparral after performing\\ncertain GCDTP services. The midstream processing company then charges Chaparral\\na fee for performing the GCDTP services and also retains the NGLs.\\n 3\\n Under a POL contract, the midstream processing company charges a fee and\\nretains the NGLs.\\n 4\\n After Naylor Farms moved to certify, Chaparral filed for bankruptcy. The\\nbankruptcy court initially imposed an automatic stay on the underlying proceedings.\\nBut it then partially lifted that stay so the district court could rule on Naylor Farms’\\nmotion to certify.\\n 4\\n\\fFarms argued that certification was appropriate under Rule 23 because (1) whether\\n\\nChaparral breached the IDM is a common question, see Fed. R. Civ. P. 23(a)(2); and\\n\\n(2) this and other common questions predominate over any individual ones, see Fed.\\n\\nR. Civ. P. 23(b)(3).\\n\\n In response, Chaparral asserted that whether it breached the IDM isn’t a\\n\\ncommon question because a jury won’t be able to answer it without first assessing\\n\\n“individualized issues, including the obligation created by each” individual lease\\n\\n“and the gas produced from each” individual well. App. vol. 2, 410. Further,\\n\\nChaparral asserted, these individual questions about lease language and gas quality,\\n\\nas well as individual questions about damages, predominate over any common\\n\\nquestions Naylor Farms might identify. Thus, Chaparral argued, Naylor Farms cannot\\n\\nsatisfy Rule 23’s certification requirements.\\n\\n The district court disagreed and concluded that certification was appropriate.\\n\\nAs an initial matter, the court ruled that Naylor Farms identified at least one common\\n\\nquestion: whether Chaparral breached the IDM. The district court then rejected\\n\\nChaparral’s arguments that answering this common question will require an\\n\\nindividualized assessment of either the language that appears in each lease or the\\n\\nquality of the gas that comes from each well. Next, the district court ruled that\\n\\ncommon questions, including whether Chaparral breached the IDM, predominate\\n\\nover any individual ones. Ultimately, after addressing Rule 23’s remaining\\n\\n\\n\\n\\n 5\\n\\frequirements, the district court granted Naylor Farms’ motion to certify.5 Chaparral\\n\\nnow appeals the district court’s class-certification order.\\n\\n Analysis\\n\\n According to Chaparral, the district court erred in certifying the class under\\n\\nRule 23. In support, Chaparral advances three discrete arguments. It first asserts the\\n\\ndistrict court erred in failing to recognize that marketability constitutes an individual\\n\\nquestion—one that necessarily predominates over any common ones in this litigation.\\n\\nIt next contends the district court erred in rejecting Chaparral’s argument that\\n\\ndistinctions in lease language also give rise to individual questions, and that those\\n\\nindividual questions likewise predominate. Finally, it insists the district court erred in\\n\\nfailing to recognize that in the absence of evidence indicating Chaparral employs a\\n\\nuniform payment methodology, certification is inappropriate. We address each of\\n\\nthese arguments in turn.\\n\\nI. Marketability\\n\\n As discussed above, the cornerstone of Naylor Farms’ class-action lawsuit is\\n\\nits allegation that Chaparral breached the IDM by improperly saddling Naylor Farms\\n\\nand other similarly situated royalty owners with certain gas-treatment costs.\\n\\n The parties agree that the success of this allegation turns in large part on when\\n\\nthe gas at issue became marketable. But they disagree about whether, in assessing\\n\\nmarketability, a jury will need to individually analyze the quality of gas that each\\n\\n\\n 5\\n The district court excluded Naylor Farms’ fraud claim from the class-\\ncertification order.\\n 6\\n\\fwell produced. And by extension, they also disagree about whether the attendant need\\n\\nto conduct such an individualized assessment renders class certification\\n\\ninappropriate.\\n\\n To resolve the parties’ disagreement on this point, we begin with an overview\\n\\nof Oklahoma state law. We then discuss Rule 23’s certification requirements. Next,\\n\\nwe explain how the district court applied Rule 23 in the context of Naylor Farms’\\n\\nstate-law claims. Finally, we set forth the applicable standard of review and discuss\\n\\nwhether, considering that deferential standard, Chaparral’s marketability arguments\\n\\nrequire us to reverse the district court’s class-certification order.\\n\\n A. Oklahoma Law\\n\\n As discussed in more detail below, the ultimate issue before us in this appeal is\\n\\nwhether the district court abused its discretion in concluding that Naylor Farms\\n\\nsatisfied Rule 23’s certification requirements. See Vallario v. Vandehey, 554 F.3d\\n\\n1259, 1264 (10th Cir. 2009). And this ultimate issue presents a question of federal\\n\\nlaw. But that doesn’t doom Oklahoma law to irrelevancy. On the contrary, at the\\n\\nheart of the parties’ Rule 23 dispute lies an intermediate state-law question: When is\\n\\ngas marketable under Oklahoma law? Thus, we begin our discussion with an\\n\\noverview of that law. Cf. Wal–Mart Stores, Inc. v. Dukes, 564 U.S. 338, 351 (2011)\\n\\n(noting that Rule 23 analysis will often “overlap with the merits of the plaintiff’s\\n\\nunderlying claim”); CGC Holding Co., LLC v. Broad & Cassel, 773 F.3d 1076, 1087\\n\\n(10th Cir. 2014) (explaining that Rule 23 inquiry requires “consideration of how the\\n\\n\\n\\n 7\\n\\fclass intends to answer factual and legal questions to prove its claim” and thus “will\\n\\nfrequently entail some discussion of the claim itself”).\\n\\n To the extent we “are called upon to interpret state law” in resolving this\\n\\nappeal, we begin by “look[ing] to the rulings of [Oklahoma’s] highest state court.”\\n\\nStickley v. State Farm Mut. Auto. Ins. Co., 505 F.3d 1070, 1077 (10th Cir. 2007)\\n\\n(quoting Johnson v. Riddle, 305 F.3d 1107, 1118 (10th Cir. 2002)). It has been more\\n\\nthan two decades since the Oklahoma Supreme Court (OSC) has said anything\\n\\nmeaningful about marketability. See Mittelstaedt, 954 P.2d 1203. And neither party\\n\\nsuggests Mittelstaedt involved (or even contemplated, for that matter) the type of\\n\\nwellhead sales contracts that Chaparral allegedly utilized here. Thus, in the absence\\n\\nof any guidance from the OSC on the specific marketability questions before us in\\n\\nthis appeal, our task is “to predict how [the OSC] would rule” if it were to answer\\n\\nthose questions. Stickley, 505 F.3d at 1077 (quoting Johnson, 305 F.3d at 1118). In\\n\\nundertaking that task, we find certain aspects of Mittelstaedt relevant to, albeit not\\n\\ndispositive of, the issues before us.\\n\\n In Mittelstaedt, the OSC began by explaining that the IDM imparts upon\\n\\nlessees like Chaparral a duty “to provide a marketable product available to market.”\\n\\n954 P.2d at 1208. And as the OSC noted, “[i]t is common knowledge that raw or\\n\\nunprocessed gas” must usually undergo one or more GCDTP services to make that\\n\\ngas marketable.6 Id. Thus, because the costs of such GCDTP services are often\\n\\n\\n 6\\n In Mittelstaedt, the OSC discussed “separation, dehydration, compression,\\nand treatment” but didn’t mention gathering or transporting. 954 P.2d at 1208.\\n 8\\n\\f“associated with” making gas marketable, the OSC explained that the IDM typically\\n\\nprecludes a lessee from “deducting a proportionate share” of those costs from royalty\\n\\npayments. Id. at 1205. But the OSC then recognized that a lessee may sometimes be\\n\\nable to demonstrate that gas is “in a marketable form at the well[head].” Id. at 1208.\\n\\nIn that scenario, GCDTP services aren’t “necessary” to transform the already-\\n\\nmarketable gas into a marketable product. Id. at 1208. Yet a lessee may nevertheless\\n\\nopt to perform such services with an eye toward “enhancing” the value of the\\n\\n“already[-]marketable” gas. Id. at 1210. And when it does so, the OSC explained, the\\n\\ncost of performing such GCDTP services “may be allocated to the royalty interests”\\n\\nif the lessee can make certain additional showings. Id.\\n\\n We derive two controlling principles from Mittelstaedt. First, Mittelstaedt\\n\\nresolved that when unmarketable gas undergoes GCDTP services for the purpose of\\n\\ntransforming that unmarketable gas into a marketable product, the lessee must bear\\n\\nthe cost of the GCDTP services. Second, Mittelstaedt resolved that when marketable\\n\\ngas undergoes GCDTP services to enhance the value of gas that is already\\n\\nmarketable, the lessee may, under certain circumstances, allocate the cost of the\\n\\nGCDTP services to royalty holders.\\n\\n Yet Mittelstaedt left unresolved a whole host of other questions. The most\\n\\nobvious are these: What does the term “marketable” mean, and what factors\\n\\n\\n\\nNevertheless, because neither party identifies any legally significant distinctions\\nbetween these services, we continue to use the term “GCDTP services” when\\ndiscussing Mittelstaedt.\\n 9\\n\\fdetermine when, where, and if gas became marketable for purposes of applying\\n\\nMittelstaedt’s marketable-product rule?\\n\\n Notably, the OSC has declined at least two recent invitations to address these\\n\\nquestions. See Order Denying Certiorari, Whisenant v. Strat Land Expl. Co., No.\\n\\n115,660 (Okla. Oct. 1, 2018); Order Denying Certiorari, Pummill v. Hancock Expl.\\n\\nLLC, No. 114,703 (Okla. May 21, 2018). Further, the OSC declined one of these\\n\\ninvitations over the dissenting voices of two of its own members. See Dissent from\\n\\nOrder Denying Certiorari, Pummill, No. 114,703 (May 21, 2018) (Winchester, J.)\\n\\n(noting that OSC “should grant certiorari to refine what constitutes a ‘marketable\\n\\nproduct’ as that term is used in [Mittelstaedt]”).\\n\\n Nevertheless, the Oklahoma Court of Civil Appeals (OCOCA) has attempted\\n\\nto fill the resulting legal vacuum, albeit with somewhat inconsistent outcomes. See\\n\\nWhisenant v. Strat Land Expl. Co., 429 P.3d 703, 707, 708–10 (Okla. Civ. App.\\n\\n2018) (recognizing that term “marketable product” isn’t susceptible to and has no\\n\\nuniform definition, but then implicitly suggesting marketability always turns, at least\\n\\nin part, on individual characteristics of gas at issue); Pummill v. Hancock Expl. LLC,\\n\\n419 P.3d 1268, 1278 (Oka. Civ. App. 2018) (indicating that in some cases, it may be\\n\\npossible to answer marketability question based on characteristics of relevant market,\\n\\nthus rendering individualized gas-quality assessment unnecessary).\\n\\n In Whisenant, for instance, the OCOCA held that the state trial court erred\\n\\nwhen, in proceeding under Okla. Stat. Ann. tit. 12, § 2023(B)(3), it certified a class\\n\\nof Oklahoma royalty owners who brought claims similar to those Naylor Farms\\n\\n 10\\n\\fadvances here.7 See 429 P.3d at 706–07. Specifically, those royalty owners alleged\\n\\nthat the defendant, who operated several Oklahoma gas wells, breached the IDM by\\n\\ncalculating “royalties based on what it received from” a midstream processing\\n\\ncompany, “rather than based on what” that midstream processing company “received\\n\\nfor the gas at the interstate (or intrastate) pipeline inlet.” Id. at 706.\\n\\n In reversing the district court’s certification order, the Whisenant court\\n\\ninitially expressed its view that the OSC has, “for good reasons,” declined to “define\\n\\nthe meaning of ‘marketable product,’” opting instead to leave the marketability\\n\\nquestion “open to resolution on a case-by-case basis.” Whisenant 429 P.3d at 708\\n\\n(quoting Mittelstaedt, 954 P.2d at 1208). Nevertheless, immediately after suggesting\\n\\nthat the concept of marketability isn’t susceptible to any uniform definition or test,\\n\\nthe Whisenant court indicated that the answer to the marketability question will\\n\\nalways turn, at least in part, on “the quality of [the] gas” at issue. Id. at 710–12. Thus,\\n\\nthe Whisenant court reasoned, a “highly individualized and fact-intensive review of\\n\\neach [class member’s] claim,” as informed by the quality of the gas at each\\n\\nindividual well, “would be necessary to determine if” the defendant in that case\\n\\nbreached the IDM. Id. at 707, 709–10 (quoting Strack v. Cont’l Res., Inc., 405 P.3d\\n\\n131, 140 (Okla. Ct. Civ. App. 2017)).\\n\\n In Pummill, on the other hand, a different panel of the OCOCA indicated that,\\n\\nin some circumstances, it may be possible to determine whether gas is marketable\\n\\n\\n 7\\n Section 2023(B)(3) is Rule 23(b)(3)’s state-law counterpart. See Whisenant,\\n429 P.3d at 706.\\n 11\\n\\fwithout undertaking such a gas-quality assessment. In that case, the state trial court\\n\\nruled that the gas at issue wasn’t marketable “at or near the wellhead” and that\\n\\ninstead the gas only became marketable once it “reache[d] the tailgate of” a\\n\\nmidstream processing plant—i.e., once the midstream processing company completed\\n\\ncertain GCDTP services. Pummill, 419 P.3d at 1271, 1276–78.\\n\\n In reaching that conclusion, the trial court focused not on a qualitative analysis\\n\\nof the gas itself, but on evidence about “the market in which” the defendants (there,\\n\\nthe well operator and multiple lessees) “chose[] to participate.” Id. at 1270–71, 1278.\\n\\nIn particular, although the gas at issue was physically transferred to the midstream\\n\\nprocessing company near the wellhead, the trial court concluded that the well\\n\\noperator was “not in the wellhead market.” Id. at 1271, 1278. Instead, the trial court\\n\\nreasoned, no “actual sale” occurred until the gas was “acceptable for transport in”\\n\\nand capable of being “transferred into” high-pressure pipelines. Id. at 1278. Thus, the\\n\\ntrial court deduced, the well operator was in the high-pressure pipeline market. And\\n\\nbecause the gas wasn’t capable of being sold on the high-pressure pipeline market\\n\\nuntil it was “compressed, treated, dehydrated, separated, and processed,” the trial\\n\\ncourt ruled the gas wasn’t marketable until it underwent those services. Id.\\n\\n The Pummill court affirmed. Id. at 1280. In doing so, it expressly endorsed the\\n\\ntrial court’s method of “focus[ing] on” when the gas at issue was first capable of\\n\\nbeing sold on “the market in which” the well operator “chose[] to participate”—there,\\n\\nthe high-pressure pipeline market. Id. at 1278. And because the gas at issue wasn’t\\n\\ncapable of being sold on the high-pressure pipeline market until GCDTP services\\n\\n 12\\n\\frendered the gas “acceptable for transport in high-pressure pipelines,” the OCOCA\\n\\nagreed the gas wasn’t marketable until that point. Id. Thus, the OCOCA held, the\\n\\nIDM precluded the defendants from passing on to royalty owners the costs associated\\n\\nwith performing those GCTDP services. Id. at 1280.\\n\\n Notably, en route to affirming the trial court’s ruling, the OCOCA declined to\\n\\nadopt Kansas’s rule that gas is marketable once it is “acceptable to a purchaser in a\\n\\ngood[-]faith transaction.” Id. at 1276 (quoting Fawcett v. Oil Producers, Inc., 352\\n\\nP.3d 1032, 1034 (Kan. Ct. App. 2015)). And the OCOCA likewise rejected the\\n\\ndefendants’ related argument that “raw or minimally processed gas” becomes\\n\\nmarketable as soon as a “limited group of potential purchasers” is willing to\\n\\n“purchase” that gas “for further processing and sale downstream.” Id. at 1277; see\\n\\nalso id. at 1278 (explaining that “[e]vidence of hypothetical sales of raw product to a\\n\\nlimited group of potential purchasers to whom such gas would be acceptable[] does\\n\\nnot readily lend itself to a conclusion that the product being sold is ‘marketable’ in a\\n\\nfree and competitive market”). Instead, the Pummill court reasoned, gas becomes\\n\\nmarketable when it’s subject to an “actual sale.” Id. at 1278 (explaining that this\\n\\nconclusion is “consistent with” OSC precedent describing “market value” of gas “as\\n\\nbeing based on what [gas] will sell for, between a willing buyer and seller, in ‘a free\\n\\nand open market’” (quoting Howell v. Texaco Inc., 112 P.3d 1154, 1159 (Okla.\\n\\n2004))).\\n\\n The OCOCA’s 2018 decisions in Pummill and Whisenant illustrate what has\\n\\nlong been clear: although “it is easy to articulate [Mittelstaedt’s] marketable-product\\n\\n 13\\n\\frule, application of it to a particular circumstance is difficult.” Foster v. Apache\\n\\nCorp., 285 F.R.D. 632, 638 & n.14 (W.D. Okla. 2012). And for reasons we turn to\\n\\nnext, “[d]oing so in the class action context”—as the district court was required to\\n\\ndo here—is more difficult still. Id. at 638.\\n\\n B. Rule 23’s Certification Requirements\\n\\n Rule 23 sets forth the requirements for class certification.8 See Wal–Mart\\n\\nStores, Inc., 564 U.S. at 345. Only two of those requirements are at issue here: Rule\\n\\n23(a)(2)’s commonality requirement and Rule 23(b)(3)’s predominance requirement.9\\n\\nA plaintiff seeking class certification satisfies Rule 23(a)(2)’s commonality\\n\\nrequirement by demonstrating that “there are questions of law or fact common to the\\n\\nclass.” Fed. R. Civ. P. 23(a)(2). A plaintiff satisfies Rule 23(b)(3)’s related\\n\\npredominance requirement by showing that “questions of law or fact common to\\n\\nclass members predominate over any questions affecting only individual members.”\\n\\nFed. R. Civ. P. 23(b)(3).\\n\\n\\n 8\\n Rule 23’s requirements inform our analysis of each of the three discrete\\narguments Chaparral presents on appeal. See infra Sections II, III.\\n 9\\n Chaparral asserts that “Rule 23 includes an ‘implied requirement of\\nascertainability’” and that Naylor Farms cannot satisfy this “implied requirement”\\nhere. Aplt. Br. 14 (quoting Brecher v. Republic of Argentina, 806 F.3d 22, 24 (2d Cir.\\n2015)). But Chaparral fails to “cite the precise references in the record where” this\\nascertainability argument “was raised and ruled on” below. 10th Cir. Rule 28.1(A).\\nAnd it also fails to make a case for plain error on appeal. Accordingly, we decline to\\naddress this argument. See Richison v. Ernest Grp., Inc., 634 F.3d 1123, 1131 (10th\\nCir. 2011); Harolds Stores, Inc. v. Dillard Dep’t Stores, Inc., 82 F.3d 1533, 1540 n.3\\n(10th Cir. 1996). Likewise, although Chaparral makes passing reference to Rule\\n23(a)(3)’s typicality requirement, see Aplt. Br. 23, 33, we find these “stray\\nsentences” insufficient to adequately brief any argument on this point. Eizember v.\\nTrammell, 803 F.3d 1129, 1141 (10th Cir. 2015).\\n 14\\n\\f Rule 23(a)(2)’s commonality requirement “is easy to misread.” Wal–Mart\\n\\nStores, Inc., 564 U.S. at 349. It requires a plaintiff to do more than merely identify “a\\n\\ncommon contention”; instead, that “common contention . . . must be of such a nature\\n\\nthat it is capable of classwide resolution—which means that determination of its truth\\n\\nor falsity will resolve an issue that is central to the validity of each one of the claims\\n\\nin one stroke.” Id. at 350. In other words, the focus of Rule 23(a)(2)’s commonality\\n\\nrequirement is not so much on whether there exist common questions, but rather on\\n\\n“the capacity of a classwide proceeding to generate common answers apt to drive the\\n\\nresolution of the litigation.” Id. at 350 (quoting Richard A. Nagareda, Class\\n\\nCertification in the Age of Aggregate Proof, 84 N.Y.U. L. Rev. 97, 132 (2009)).\\n\\n Rule 23(b)(3)’s predominance requirement is related to, albeit “more\\n\\ndemanding than,” Rule 23(a)(2)’s commonality requirement. Comcast Corp. v.\\n\\nBehrend, 569 U.S. 27, 34 (2013). To satisfy Rule 23(b)(3), a plaintiff must “show\\n\\nthat common questions subject to generalized, classwide proof predominate over\\n\\nindividual questions.” CGC Holding Co., 773 F.3d at 1087; see also Tyson Foods,\\n\\nInc. v. Bouaphakeo, 136 S. Ct. 1036, 1045 (2016) (“An individual question is one\\n\\nwhere ‘members of a proposed class will need to present evidence that varies from\\n\\nmember to member,’ while a common question is one where ‘the same evidence will\\n\\nsuffice for each member to make a prima facie showing [or] the issue is susceptible\\n\\nto generalized, class[]wide proof.’” (alteration in original) (quoting 2 William B.\\n\\nRubenstein et al., Newberg on Class Actions § 4:50 (5th ed. 2012))).\\n\\n\\n\\n 15\\n\\f Notably, this doesn’t mean a plaintiff must show “that all of the elements of\\n\\nthe claim entail questions of fact and law that are common to the class” or “that the\\n\\nanswers to those common questions [are] dispositive” of the claim. CGC Holding\\n\\nCo., 773 F.3d at 1087. Instead, the predominance inquiry “asks whether the common,\\n\\naggregation-enabling[] issues in the case are more prevalent or important than the\\n\\nnon-common, aggregation-defeating, individual issues.” Id. (quoting Newberg on\\n\\nClass Actions § 4:49). Thus, to determine whether a plaintiff can satisfy Rule\\n\\n23(b)(3)’s predominance requirement, a court must first “characterize the issues in\\n\\nthe case as common or not, and then weigh which issues predominate.” Id. (quoting\\n\\nNewberg on Class Actions § 4:50). Critically, so long as at least one common issue\\n\\npredominates, a plaintiff can satisfy Rule 23(b)(3)—even if there remain individual\\n\\nissues, such as damages, that must be tried separately. Tyson Foods, Inc., 136 S. Ct.\\n\\nat 1045.\\n\\n Having reviewed the relevant Rule 23 requirements and examined Oklahoma’s\\n\\ntreatment of the marketability question, we next explain how the district court treated\\n\\nthe interplay between the former and the latter in ruling on Naylor Farms’ motion to\\n\\ncertify.\\n\\n C. The District Court’s Ruling\\n\\n The district court found that Naylor Farms successfully identified at least one\\n\\ncommon question: whether Chaparral breached the IDM.10 And the court then ruled\\n\\n\\n 10\\n Chaparral contends the district court erred in concluding that the threshold\\nissue of whether each lease contains an IDM is “in and of itself” a common question.\\n 16\\n\\fthat this common question predominates over any individual ones.\\n\\n Critically, in doing so, the district court first narrowed the class to include only\\n\\nthose royalty owners whose leases contain clauses that are similar to the royalty\\n\\nclauses (collectively, Mittelstaedt Clauses) the OSC considered in three cases:\\n\\n(1) Mittelstaedt, (2) TXO Production Corp. v. State ex rel. Commissioners of Land\\n\\nOffice, 903 P.2d 259 (Okla. 1995), and (3) Wood v. TXO Production Corp., 854 P.2d\\n\\n880 (Okla. 1993). Because the OSC has held that the language of these Mittelstaedt\\n\\nClauses “does not negate the IDM” and “is consistent with the marketable[-]product\\n\\nrule,” the district court reasoned that—contrary to Chaparral’s arguments—any\\n\\nremaining “variations in lease language” do not defeat commonality or\\n\\npredominance. App. vol. 5, 1148, 1153.\\n\\n Next, the district court rejected Chaparral’s argument that in order to\\n\\ndetermine whether Chaparral breached the IDM, a jury will have to engage in an\\n\\n\\nAplt. Br. 11. As an initial matter, we disagree with the premise of this argument; at\\nmost, it appears the district court treated the existence of the IDM “and its alleged\\nbreach” as a compound common question. App. vol. 5, 1154 (emphasis added).\\n\\n In any event, even assuming the district court treated the existence of the IDM\\nas a standalone common question and even assuming it erred in doing so, the error\\nwas harmless; the district court correctly concluded that whether Chaparral breached\\nthe IDM is a common question. See Wal–Mart Stores, Inc., 564 U.S. at 350\\n(explaining that question is common for purposes of Rule 23(a)(2) if its answer “will\\nresolve an issue that is central to the validity of each one of the claims in one\\nstroke”); cf. Menocal v. GEO Grp., Inc., 882 F.3d 905, 916–17 (10th Cir.) (holding\\nthat question of whether defendant’s policy violated federal statute constituted\\ncommon question), cert. denied, 139 S. Ct. 143 (2018). Chaparral doesn’t seriously\\nargue otherwise. And when it comes to satisfying Rule 23(a)(2)’s commonality\\nrequirement, the existence of this single common question “will do.” Wal–Mart\\nStores, Inc., 564 U.S. at 359.\\n 17\\n\\findividualized “well-by-well analysis” to determine when the gas from each well\\n\\nbecame marketable. Id. at 1149. In rejecting this argument, the district court\\n\\nacknowledged that gas quality might vary from well to well and that, as a result,\\n\\nsome gas might require more or different GCTDP services to become marketable\\n\\nthan other gas. But the district court explained that in order to determine whether\\n\\nChaparral breached the IDM, an individualized gas-quality analysis is nevertheless\\n\\n“unnecessary” in this case because, as Naylor Farms demonstrated, all the gas at\\n\\nissue “require[d]” at least one GCDTP service “to become marketable.” Id. at 1149,\\n\\n1151, 1157.\\n\\n Thus, the district court appeared to recognize, differences in the precise\\n\\nnumber and nature of GCDTP services required to make the gas from each well\\n\\nmarketable are relevant only to the post-breach question of damages. And because\\n\\nNaylor Farms “provided evidence that [its] expert can determine damages on a\\n\\nclass[]wide basis through use of a model,” the district court ruled these distinctions\\n\\ndon’t defeat predominance. Id. at 1155. Alternatively, the district court pointed out\\n\\nthat if necessary, it can divide the class into subclasses at a later date for purposes of\\n\\ndetermining damages. See Fed. R. Civ. P. 23(c)(1)(C) (“An order that grants or\\n\\ndenies class certification may be altered or amended before final judgment.”), (c)(5)\\n\\n(“When appropriate, a class may be divided into subclasses that are each treated as a\\n\\nclass under this rule.”). Accordingly, the district granted Naylor Farms’ motion to\\n\\ncertify.\\n\\n\\n\\n 18\\n\\f D. Our Standard of Review\\n\\n Our review of the district court’s decision is highly deferential. So long as the\\n\\ndistrict court “applied the proper standard in deciding whether to certify [the] class,\\n\\nwe may reverse that decision only for abuse of discretion.” CGC Holding Co., 773\\n\\nF.3d at 1085 (quoting Adamson v. Bowen, 855 F.2d 668, 675 (10th Cir. 1988)); see\\n\\nalso Vallario, 554 F.3d at 1264 (“Because class certification decisions are necessarily\\n\\ncase specific, district courts possess significant latitude in deciding whether or not to\\n\\ncertify a class.” (citation omitted)). A “district court abuses its discretion when it\\n\\nmisapplies the Rule 23 factors—either through a clearly erroneous finding of fact or\\n\\nan erroneous conclusion of law—in deciding whether class certification is\\n\\nappropriate.” CGC Holding Co., 773 F.3d at 1085–86.\\n\\n Here, Chaparral doesn’t argue that the district court failed to apply the proper\\n\\nRule 23 standard. Thus, in addressing those arguments Chaparral does make, we must\\n\\ndefer to the district court’s ruling unless Chaparral shows the district court’s\\n\\ncertification decision falls outside “the bounds of rationally available choices given\\n\\nthe facts and law involved in the matter at hand.” Id. at 1086 (quoting Vallario, 554\\n\\nF.3d at 1264). For the reasons discussed below, we conclude that Chaparral fails to\\n\\nmake this demanding showing.\\n\\n E. Chaparral’s Marketability Arguments\\n\\n Chaparral’s primary argument on appeal is that the district court abused its\\n\\ndiscretion in ruling that Naylor Farms demonstrated commonality and predominance\\n\\nbecause such a ruling is irreconcilable with Oklahoma’s approach to determining\\n\\n 19\\n\\fmarketability. Or, as Chaparral puts it, “Certifying a class of ‘Mittelstaedt Clause\\n\\n[l]eases’ is contrary to Mittelstaedt.” Aplt. Br. 16.\\n\\n Recall that, under Mittelstaedt, two things are clear. First, when unmarketable\\n\\ngas undergoes GCDTP services for purposes of transforming the unmarketable gas\\n\\ninto a marketable product, a lessee breaches the IDM by passing on to royalty owners\\n\\nthe cost of performing those GCDTP services. See Mittelstaedt, 954 P.2d at 1205.\\n\\nSecond, when marketable gas undergoes GCDTP services to enhance the value of\\n\\ngas that is already marketable, a lessee may, under certain circumstance, allocate the\\n\\ncost of those services to royalty owners without breaching the IDM. Id. at 1210.\\n\\nThus, to determine whether Chaparral breached the IDM—i.e., to answer the question\\n\\nthe district court determined was common to the class for purposes of satisfying Rule\\n\\n23(a)(2)’s commonality requirement—a jury will have to determine when the gas at\\n\\nissue became marketable.\\n\\n Here, as Chaparral points out, the district court ruled that (1) the question of\\n\\nwhen the gas became marketable can be answered via generalized, classwide proof\\n\\nand (2) as a result, the marketability question doesn’t defeat predominance. See Fed.\\n\\nR. Civ. P. 23(b)(3) (allowing for certification if common questions predominate over\\n\\nindividual ones); Tyson Foods, Inc., 136 S. Ct. at 1045 (“An individual question is\\n\\none where ‘members of a proposed class will need to present evidence that varies\\n\\nfrom member to member,’ while a common question is one where ‘the same evidence\\n\\nwill suffice for each member to make a prima facie showing [or] the issue is\\n\\n\\n\\n 20\\n\\fsusceptible to generalized, class[]wide proof.’” (first alteration in original) (quoting\\n\\nNewberg on Class Actions § 4:50)).\\n\\n But according to Chaparral, the district court’s ruling on this point rests on a\\n\\nflawed assumption. Specifically, Chaparral contends that in ruling a jury can answer\\n\\nthe marketability question without undertaking a well-by-well analysis, the district\\n\\ncourt relied on the fact that all the gas at issue actually underwent GCDTP services.\\n\\nAnd in so ruling, Chaparral argues, the district court made a legally erroneous\\n\\nassumption: it incorrectly assumed that any time gas undergoes GCDTP services, this\\n\\nproves, ipso facto, that the gas wasn’t marketable before it underwent those services.\\n\\n We agree with Chaparral that if the district court assumed GCDTP services\\n\\nfunction solely as a mechanism for transforming unmarketable gas into a marketable\\n\\nproduct, then the court committed a legal error. As Chaparral correctly points out,\\n\\nMittelstaedt expressly recognizes that sometimes even marketable gas undergoes\\n\\nGCDTP services—not to “create a marketable product” but to “transform[] an\\n\\nalready[-]marketable product into an enhanced” one. Mittelstaedt, 954 P.2d at 1209–\\n\\n10; see also id. at 1208 (acknowledging that it’s possible for gas to “be in a\\n\\nmarketable form at the well[head],” i.e., before any GCDTP services are\\n\\nperformed).11 But we disagree with Chaparral that the district court ever assumed\\n\\notherwise.\\n\\n\\n\\n 11\\n In asserting that gas can be marketable at the wellhead, Chaparral appears to\\nrely in part on its position that the gas at issue here was in fact marketable at the\\nwellhead—because (according to Chaparral) that is where Chaparral first “sold” the\\n 21\\n\\f That is, contrary to Chaparral’s argument, the district court neither ruled nor\\n\\nassumed “that gas must be unmarketable if it goes through a processing plant or\\n\\nreceives one or more of the GCDTP services.” Aplt. Br. 19. On the contrary, the\\n\\ndistrict court expressly recognized that the marketability question turns not on\\n\\nwhether the gas undergoes GCDTP services, but on whether the gas undergoes\\n\\nGCDTP services “to become marketable.” App. vol. 5, 1151. Indeed, the district\\n\\ncourt expressly relied on evidence indicating that all the gas at issue here “require[d]\\n\\nGCDTP services to be made marketable” in order to distinguish the facts of this case\\n\\nfrom those before this court in Wallace B. Roderick Revocable Living Trust v. XTO\\n\\nEnergy, Inc., 725 F.3d 1213 (10th Cir. 2013); in that case, the district court pointed\\n\\nout, some of the gas at issue “may [have been] marketable at the well.” App. vol. 5,\\n\\n1146 (emphases added) (quoting Roderick, 725 F.3d at 1217). Critically, in making\\n\\nthis distinction, the district court necessarily acknowledged both that (1) “gas may be\\n\\nmarketable at the well[head]” and (2) the performance of GCDTP services does not\\n\\nprove, ipso facto, that the gas at issue was not marketable before those services were\\n\\n\\ngas “to a [midstream processing company] in a good[-]faith transaction.” Aplt. Br.\\n20; see also id. at 18 (“Gas is in marketable condition once it can be marketed.”).\\n\\n As an initial matter, we question whether the OSC would adopt this good-\\nfaith-transaction test for marketability. See Pummill, 419 P.3d at 1278–79\\n(suggesting good-faith-transaction approach is inconsistent with controlling OSC\\nauthority). More importantly, as the district court noted below, accepting as true\\nChaparral’s blanket assertion that all the gas at issue was marketable at the wellhead\\nbecause that is where Chaparral could first “market[]” it to midstream processing\\ncompanies, Aplt. Br. 18, would serve only to “demonstrate[]” commonality, not\\n“negate[]” it, App. vol. 5, 1149; such a blanket rule would obviate the need for any\\nindividualized analysis of the gas from each well.\\n 22\\n\\fperformed. Id. (quoting Roderick, 725 F.3d at 1217). Accordingly, we reject\\n\\nChaparral’s assertion that the district court assumed otherwise.\\n\\n Alternatively, Chaparral argues that the district court erred in treating\\n\\nmarketability as a question of law. Instead, Chaparral asserts, marketability is a\\n\\nquestion of fact—one that turns, at least in part, on “gas quality.” Aplt. Br. 23. And it\\n\\nfurther insists that because the quality of its gas varies from well to well, a jury will\\n\\nbe unable to resolve the marketability question (and, by extension, the question of\\n\\nwhether Chaparral breached the IDM) without performing a well-by-well analysis to\\n\\ndetermine whether any of the gas at issue was marketable at the wellhead. Thus,\\n\\nChaparral insists, the district court abused its discretion in failing to recognize that\\n\\nmarketability defeats commonality and predominance.\\n\\n In evaluating this argument, we need not resolve whether the district court\\n\\ntreated marketability as a question of law or a question of fact. Nor must we resolve\\n\\nwhether, if the district court indeed treated marketability as a question of law, it erred\\n\\nin doing so.12 Even assuming Chaparral is correct on both points, that doesn’t\\n\\nnecessarily mean Chaparral is entitled to reversal. On the contrary, “we may affirm\\n\\non any basis supported by the record, even if it requires ruling on arguments not\\n\\nreached by the district court.” Richison, 634 F.3d at 1130. That is, we have a\\n\\n“preference for affirmance”—one that “follows from the deference we owe to the\\n\\n\\n\\n 12\\n We nevertheless note in passing that it appears Oklahoma indeed treats\\nmarketability as question of fact. See, e.g., Whisenant, 429 P.3d at 708 n.6; Pummill,\\n419 P.3d at 1274 n.9.\\n 23\\n\\fdistrict courts and the judgments they reach, many times only after years of involved\\n\\nand expensive proceedings.” Id. And “[b]ecause of the cost and risk involved anytime\\n\\nwe upset a court’s reasoned judgment, we are ready to affirm whenever the record\\n\\nallows it.” Id. Thus, to demonstrate it is entitled to reversal, Chaparral must\\n\\n“shoulder a heavy burden”: it “must come ready both to show” that the district court\\n\\nerred and “to explain why no other grounds” will allow us to affirm the district\\n\\ncourt’s decision. Id. For the reasons discussed below, we conclude that in light of the\\n\\nOCOCA’s persuasive reasoning in Pummill, Chaparral cannot shoulder the second\\n\\npart of this heavy burden here. See West v. Am. Tel. & Tel. Co., 311 U.S. 223, 237\\n\\n(1940) (explaining that decision of intermediate state appellate court “is a datum for\\n\\nascertaining state law [that] is not to be disregarded by a federal court unless it is\\n\\nconvinced by other persuasive data that the highest court of the state would decide\\n\\notherwise”).\\n\\n In Pummill, the OCOCA relied heavily on two factors in affirming the state\\n\\ntrial court’s ruling that the gas at issue wasn’t marketable before it underwent\\n\\nGCTDP services. As an initial matter, the OCOCA pointed out that the first “actual\\n\\nsale” of the gas occurred not when the defendants transferred the gas to a midstream\\n\\nprocessing company, but instead “at the ‘tailgate’ of the [processing] plants, where\\n\\n[the gas was] transferred into high-pressure lines.” 419 P.3d at 1277–78. And the\\n\\nOCOCA deduced from the location of this first “actual sale” that “the market in\\n\\nwhich” the defendants “chose[] to participate” was the pipeline market, not the\\n\\nwellhead market. Id. Second, the OCOCA noted that the gas had to undergo GCDTP\\n\\n 24\\n\\fservices to make it “acceptable for delivery” into the high-pressure pipelines. Id. at\\n\\n1277. Accordingly, the OCOCA concluded that the IDM precluded the defendants\\n\\nfrom “deduct[ing] from [the plaintiffs’] royalties the proportionate expenses\\n\\nassociated with preparing the gas for sale” to such pipelines. Id. at 1280.\\n\\n Here, Naylor Farms has presented evidence of these same two factors. More\\n\\nimportantly, it has presented classwide evidence of these same two factors. See Tyson\\n\\nFoods, Inc., 136 S. Ct. at 1045 (explaining that for purposes of Rule 23(b)(3), “a\\n\\ncommon question is one where ‘the same evidence will suffice for each member to\\n\\nmake a prima facie showing [or] the issue is susceptible to generalized, class[]wide\\n\\nproof’” (alteration in original) (quoting Newberg on Class Actions § 4:50)). First, the\\n\\nrecord contains classwide evidence indicating that Chaparral, like the defendants in\\n\\nPummill, elects to participate in the high-pressure-pipeline market: according to\\n\\nNaylor Farms’ expert, this is where Chaparral’s gas is actually “sold.” Aplt. Supp.\\n\\nApp. vol. 18, 5270; see also Pummill, 419 P.3d at 1278 (noting that pipeline market\\n\\nwas where first “actual sale” of gas occurred). Second, Naylor Farms’ expert opined\\n\\nthat, as a classwide matter, the gas at issue here—like the gas at issue in Pummill—\\n\\nwas required to undergo at least one GCDTP service before it could “reach” and be\\n\\n“sold into” the pipeline market.13 Aplt. Supp. App. vol. 18, 5270–71; see also\\n\\nPummill, 419 P.3d at 1277 (concluding that gas wasn’t marketable on pipeline market\\n\\n\\n 13\\n Notably, despite Chaparral’s insistence that a well-by-well analysis is\\nnecessary to determine when the gas became marketable, Chaparral fails to point to\\nany evidence in the record indicating that such an individualized analysis would yield\\na different conclusion.\\n 25\\n\\funtil it was “acceptable for delivery” into relevant pipelines); cf. Wood, 854 P.2d at\\n\\n882 (explaining that IDM imposes “a duty to get the product to the place of sale in\\n\\nmarketable form” (emphasis added)).\\n\\n In short, the district court’s ruling that marketability is subject to classwide\\n\\nproof under the specific facts of this case is entirely consistent with the OCOCA’s\\n\\ndecision in Pummill. Thus, Chaparral faces an uphill climb in attempting to show that\\n\\nthis particular ruling rests on an error of state law. See West, 311 U.S. at 237. In\\n\\nattempting to make that showing here, Chaparral relies heavily on the OCOCA’s\\n\\nrecent decision in Whisenant.\\n\\n In Whisenant, the OCOCA held that the state trial court erred in certifying a\\n\\nclass of Oklahoma royalty owners under Oklahoma’s analog to Rule 23, reasoning\\n\\nthat a “highly individualized and fact-intensive review of each [class member’s]\\n\\nclaim,” as informed by the quality of gas at each individual well, “would be\\n\\nnecessary to determine if” the defendant in that case breached the IDM. 429 P.3d at\\n\\n707–10 (quoting Strack, 405 P.3d at 140)). Citing Whisenant, Chaparral insists that\\n\\nunder Oklahoma law, marketability can never be susceptible to classwide proof\\n\\nbecause it will always require an individualized assessment of the gas produced by\\n\\neach well. And to the extent the district court failed to recognize as much here,\\n\\nChaparral contends, the court made a legal error and thereby abused its discretion.\\n\\nSee CGC Holding Co., 773 F.3d at 1085–86 (“The district court abuses its discretion\\n\\nwhen it misapplies the Rule 23 factors—either through a clearly erroneous finding of\\n\\n\\n\\n 26\\n\\ffact or an erroneous conclusion of law—in deciding whether class certification is\\n\\nappropriate.”).\\n\\n In light of Whisenant’s similar procedural posture, Chaparral’s argument isn’t\\n\\nwithout appeal. But because that argument overlooks a critical aspect of Whisenant’s\\n\\nanalysis, we ultimately reject it. That is, the Whisenant court did hold that, in that\\n\\nparticular case, “determinations of the quality of gas and other facts pertinent to each\\n\\nwell” weren’t “susceptible to generalized proof.” 429 P.3d at 710. But the Whisenant\\n\\ncourt also expressly eschewed the type of rigid, one-size-fits-all approach to\\n\\nmarketability that Chaparral asks us to endorse here. Specifically, the Whisenant\\n\\ncourt recognized that the OSC has declined to adopt a uniform test for determining\\n\\nwhen gas becomes marketable, and that the OSC has instead “left the issue open to\\n\\nresolution on a case-by-case basis.” 429 P.3d at 708. And in recognizing as much, the\\n\\nWhisenant court necessarily “left . . . open” the possibility that, in some cases, a\\n\\nfactfinder may be able to determine when gas became marketable without\\n\\nundertaking an individualized inquiry into the quality of that gas. Id.\\n\\n Critically, the facts in Pummill (and, by extension, the facts in this case) fit\\n\\ncomfortably in the space “left . . . open” by Whisenant. Id. Thus, despite any tension\\n\\nthat might exist between Pummill and Whisenant, we rely on both—and “disregard[]”\\n\\nneither—in predicting how the OSC would answer the marketability question before\\n\\nus in this appeal. West, 311 U.S. at 237. And in light of Pummill and Whisenant, we\\n\\npredict the OSC would answer that question by holding that, under the facts of this\\n\\ncase, a jury could determine when the gas at issue became marketable without\\n\\n 27\\n\\findividually assessing the quality of that gas; instead, a jury could make this\\n\\ndetermination based solely on expert testimony that all the gas at issue was required\\n\\nto undergo at least one GCDTP service before it could “reach” and be “sold into” the\\n\\npipeline market. Aplt. Supp. App. vol. 18, 5270–71. See Whisenant, 429 P.3d at 708\\n\\n(opining that OSC has intentionally and wisely “left the issue [of marketability] open\\n\\nto resolution on a case-by-case basis”); Pummill, 419 P.3d at 1273, 1278 (indicating\\n\\nthat in some cases, it may be possible to answer marketability question based on\\n\\ncharacteristics of relevant market, thus rendering individualized gas-quality\\n\\nassessment unnecessary). Accordingly, the district court didn’t abuse its discretion by\\n\\nconcluding that the marketability question in this particular case is subject to\\n\\ncommon, classwide proof for purposes of satisfying Rule 23’s commonality and\\n\\npredominance requirements. See Tyson Foods, Inc., 136 S. Ct. at 1045; CGC Holding\\n\\nCo., 773 F.3d at 1086; Richison, 634 F.3d at 1130.\\n\\nII. Lease Language\\n\\n Next, Chaparral asserts that even if gas-quality variations don’t pose a bar to\\n\\ncertification, lease-language variations do. Specifically, Chaparral asserts that “[a]t\\n\\ntrial, every one of the contracts will have to be considered individually, defeating\\n\\ncommonality and predominance.” Aplt. Br. 27–28. But the district court concluded\\n\\notherwise, ruling that its decision to limit the class to leases containing a Mittelstaedt\\n\\nClause renders such an individualized analysis unnecessary.14\\n\\n\\n 14\\n Naylor Farms asserts we should take judicial notice of certain briefing in\\nMittelstaedt because, according to Naylor Farms, that briefing sheds additional light\\n 28\\n\\f In challenging this conclusion, Chaparral first asserts the district court\\n\\nabdicated its duty to determine which leases actually contain a Mittelstaedt Clause\\n\\nand instead merely “satisfied itself with [Naylor Farms’] contentions” that this is so.\\n\\nId. at 28. We disagree. As the district court noted, Naylor Farms prepared a chart that\\n\\n“categorized” the leases at issue “by royalty[-]clause language.” App. vol. 5, 1143.\\n\\nAnd we have previously indicated that this is precisely what a plaintiff should do to\\n\\nestablish commonality under these circumstances. See Roderick, 725 F.3d at 1219.\\n\\n Like Naylor Farms, the plaintiffs in Roderick asserted that each class\\n\\nmember’s lease contained an IDM. Id. at 1218. But neither the plaintiffs nor the\\n\\ndistrict court bothered to examine all the leases to verify this assertion. Id. at 1219.\\n\\nThus, this court recommended that on remand, the plaintiffs should consider\\n\\n“creat[ing] a chart classifying lease types.” Id. And if they did so, this court opined,\\n\\n“the district court could” rely on that chart to “decide that no lease type negates the\\n\\nIDM.” Id.\\n\\n Here, Naylor Farms created such a chart. And contrary to Chaparral’s\\n\\nassertions, the district court independently “confirmed that” the chart was “generally\\n\\naccurate.” App. vol. 5, 1147. Notably, Chaparral doesn’t provide us with any\\n\\ninformation that might call into question the district court’s assessment of the chart’s\\n\\naccuracy. Instead, Chaparral merely asserts that because there exist distinctions\\n\\n\\non the lease language at issue in Mittelstaedt as well as the arguments the parties\\nmade about that language. Because we conclude we may resolve Chaparral’s lease-\\nlanguage arguments without this additional information, we deny Naylor Farms’\\nmotion to take judicial notice.\\n 29\\n\\fbetween the facts in this case and the facts in TXO, 903 P.2d 259, and Wood, 854\\n\\nP.2d 880—each of which involved a Mittelstaedt Clause—“the district court could\\n\\nnot” rely on these two cases to “determine as a matter of law whether” Chaparral\\n\\ncould “share[]” certain costs with royalty owners. Aplt. Br. 28–29. In particular,\\n\\nChaparral asserts that although the costs in TXO and Wood were incurred on the\\n\\nleased premises, “[t]he costs here were incurred off-lease.” Id. at 28.\\n\\n Perhaps these “facts” will ultimately be relevant to the merits question of\\n\\nwhether Chaparral breached the IDM. Id. Perhaps not. Either way, we fail to see how\\n\\nthey might be relevant to the question of whether, as a threshold matter, the class\\n\\nleases contain an IDM. And the chart was designed to aid the district court in\\n\\nanswering the latter question, not the former one. See Roderick, 725 F.3d at 1218\\n\\n(noting that chart could aid district court in determining whether “every class\\n\\nmember’s lease” contained IDM and, by extension, could help district court\\n\\ndetermine whether plaintiff satisfied Rule 23(a)(2)’s commonality requirement).\\n\\n Here, Chaparral offers no further explanation regarding the relevance of these\\n\\n“facts” vis-à-vis the district court’s Rule 23 inquiry. Aplt. Br. 28; see also Amgen\\n\\nInc. v. Conn. Ret. Plans & Tr. Funds, 568 U.S. 455, 466 (2013) (“Rule 23 grants\\n\\ncourts no license to engage in free-ranging merits inquiries at the certification stage.\\n\\nMerits questions may be considered to the extent—but only to the extent—that they\\n\\nare relevant to determining whether the Rule 23 prerequisites for class certification\\n\\nare satisfied.”). Further, Chaparral’s position that all “[t]he costs here were incurred\\n\\noff-lease” would tend to support the district court’s rulings on predominance and\\n\\n 30\\n\\fcommonality, not undermine them. Id. at 28; see also Tyson Foods, Inc., 136 S. Ct. at\\n\\n1045; Wal–Mart Stores, Inc., 564 U.S. at 350. Accordingly, we decline to hold that\\n\\nthe district court abused its discretion by relying on Naylor Farms’ chart after\\n\\n“confirm[ing] that” the chart was “generally accurate.” App. vol. 5, 1147.\\n\\n Chaparral’s remaining arguments about lease language rest on its assertions\\n\\nthat (1) the leases at issue contain multiple royalty provisions and (2) the interplay\\n\\nbetween these royalty provisions renders the leases ambiguous. According to\\n\\nChaparral, this ambiguity would entitle Chaparral to present individualized extrinsic\\n\\nevidence of “the intent of the parties and the meaning of the leases” at trial, including\\n\\n“exhibits [and] interlineations” to each individual lease, as well as evidence about\\n\\nindustry customs in effect “when the various leases were executed.” Aplt. Br. 33–36.\\n\\n But as Naylor Farms points out, Chaparral didn’t advance this specific\\n\\nextrinsic-evidence argument below as a basis for denying Naylor Farms’ motion to\\n\\ncertify the class. Instead, Chaparral merely asserted that, as a general matter,\\n\\n“differences in royalty obligations” and lease language defeat commonality and\\n\\npredominance.15 App. vol. 2, 411. Critically, our “rule against considering new\\n\\narguments on appeal applies equally when ‘a litigant changes to a new theory on\\n\\nappeal that falls under the same general category as an argument presented at trial.’”\\n\\n\\n 15\\n In its reply brief, Chaparral asserts for the first time that it raised an\\nextrinsic-evidence argument in its response to Naylor Farms’ motion for summary\\njudgment. We agree that Chaparral’s response to Naylor Farms’ summary-judgment\\nmotion refers to what might be classified as extrinsic evidence. But we see no\\nargument there that the need to examine such evidence precludes certification. Nor\\ndo we see any indication that the district court ever ruled on such an argument.\\n 31\\n\\fUnited States v. Nelson, 868 F.3d 885, 891 n.4 (10th Cir. 2017) (quoting Lyons v.\\n\\nJefferson Bank & Tr., 994 F.2d 716, 722 (10th Cir. 1993)). Further, Chaparral fails to\\n\\nargue for plain error on appeal. Accordingly, it has waived its extrinsic-evidence\\n\\nargument. See Richison, 634 F.3d at 1131.\\n\\n Alternatively, even assuming Chaparral preserved its extrinsic-evidence\\n\\nargument below, it fails to adequately brief this argument on appeal. This is so\\n\\nbecause Chaparral fails to identify any specific extrinsic evidence—in the form of an\\n\\nexhibit, interlineation, or industry custom—that might allow a jury to conclude that\\n\\nChaparral breached the IDM as to one lease but not another. See Fed. R. App. P.\\n\\n28(a)(8)(A) (requiring argument section of appellant’s brief to contain “appellant’s\\n\\ncontentions and the reasons for them, with citations to the authorities and parts of the\\n\\nrecord on which the appellant relies”); Bronson v. Swensen, 500 F.3d 1099, 1104\\n\\n(10th Cir. 2007) (explaining that we routinely decline to consider inadequately\\n\\nbriefed arguments). Accordingly, even assuming the district court erred, we see no\\n\\nbasis upon which to conclude the district court’s error prejudiced Chaparral. See\\n\\nShinseki v. Sanders, 556 U.S. 396, 410 (2009) (explaining that “the party seeking\\n\\nreversal normally must explain why the erroneous ruling caused harm”). Thus, we\\n\\ndecline to reverse on this basis. And for the same reasons, we likewise decline to\\n\\nreverse based on Chaparral’s assertion that even in the absence of any ambiguity in\\n\\nthe leases, a jury will be required to consider industry customs in effect “when the\\n\\nvarious leases were executed” to determine whether Chaparral breached the terms of\\n\\n\\n\\n 32\\n\\feach individual lease. Aplt. Br. 36. Again, Chaparral neither identifies any particular\\n\\ncustoms nor explains their legal relevance.\\n\\n In its final lease-language argument, Chaparral asserts that individual\\n\\nvariations in its agreements with midstream processing companies, rather than in its\\n\\nagreements with Naylor Farms and other royalty owners, defeat commonality and\\n\\npredominance. In support, Chaparral says Naylor Farms’ underlying legal theory is\\n\\nthat Chaparral committed fraud by using wellhead sales contracts to circumvent\\n\\nOklahoma law. And to evaluate this theory, Chaparral contends, a jury will have to\\n\\nconduct an individualized inquiry to determine whether Chaparral entered into each\\n\\nof those wellhead sales contracts in good faith.\\n\\n But this argument overlooks the fact that the district court declined to certify\\n\\nNaylor Farms’ fraud claim. And Chaparral cites no authority indicating that whether\\n\\nit entered into the wellhead sales contracts in good faith is dispositive of, or even\\n\\nrelevant to, the claims the district court did certify. Accordingly, we find this\\n\\nargument inadequately briefed and decline to consider it as well. See Fed. R. App. P.\\n\\n28(a)(8)(A); Bronson, 500 F.3d at 1104. And we further conclude that Chaparral\\n\\ntherefore fails to demonstrate the district court abused its discretion in certifying the\\n\\nclass despite minor variations in lease language.\\n\\nIII. Uniform Payment Methodology\\n\\n As a final matter, Chaparral asserts Naylor Farms failed to demonstrate that\\n\\nChaparral uses a uniform payment methodology to calculate royalty payments and\\n\\n\\n\\n 33\\n\\fthat this “lack of a common payment methodology defeats class certification.” Aplt.\\n\\nBr. 39.\\n\\n We have indeed explained that the existence of a uniform payment\\n\\nmethodology, standing alone, isn’t sufficient to establish predominance. See\\n\\nRoderick, 725 F.3d at 1220. But contrary to Chaparral’s assertion, we see nothing in\\n\\nRoderick that indicates the existence of such a methodology is necessary to\\n\\naccomplish this task. Accordingly, we reject this argument. And to the extent\\n\\nChaparral instead means to suggest that individual questions about damages defeat\\n\\npredominance, we do not agree. “The fact that damages may have to be ascertained\\n\\non an individual basis is not, standing alone, sufficient to defeat class certification.”\\n\\nMenocal, 882 F.3d at 922 (quoting Roderick, 725 F.3d at 1220)). Instead, “material\\n\\ndifferences in damages determinations” will only destroy predominance if those\\n\\n“individualized issues will overwhelm . . . questions common to the class.” Roderick,\\n\\n725 F.3d at 1220.\\n\\n We see no indication that will occur here. On the contrary, as the district court\\n\\npointed out, Naylor Farms “provided evidence that [its] expert can determine\\n\\ndamages on a class[]wide basis through use of a model,” thus obviating the need for\\n\\nindividualized evidence. App. vol. 5, 1155; see also Tyson Foods, Inc., 136 S. Ct. at\\n\\n1045. And Chaparral fails to explain why that model is inaccurate or unworkable.\\n\\nFurther, the district court correctly noted that if necessary, it can later divide the class\\n\\ninto subclasses for purposes of determining damages. See Fed. R. Civ. P. 23(c)(1)(C),\\n\\n(c)(5); Roderick, 725 F.3d 1213. Thus, the district court didn’t abuse its discretion in\\n\\n 34\\n\\fruling that individual questions about damages don’t defeat predominance. See\\n\\nRoderick, 725 F.3d 1213 (“[T]he district court is in the best position to evaluate the\\n\\npractical difficulties which inhere in the class action format, and is especially suited\\n\\nto tailor the proceedings accordingly.”).\\n\\n Conclusion\\n\\n For the reasons discussed above, we conclude that Chaparral fails to\\n\\ndemonstrate the district court’s decision to certify the class falls outside “the bounds\\n\\nof rationally available choices given the facts and law involved in the matter at\\n\\nhand.” CGC Holding Co., 773 F.3d at 1086 (quoting Vallario, 554 F.3d at 1264). We\\n\\ntherefore affirm the district court’s order.\\n\\n\\n\\n\\n 35\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4393855/\", \"author_raw\": \"MORITZ, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"MORITZ"},"judge2":{"kind":"string","value":"MURPHY"},"judge3":{"kind":"string","value":"EID"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4616602/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: NAYLOR FARMS, INC. ; Harrel's LLC, Plaintiffs-Appellees, v. CHAPARRAL ENERGY, LLC, Defendant-Appellant, Black Stone Minerals Company, L.P., Amicus Curiae.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 3, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\n NAYLOR FARMS, INC.; HARREL’S\n LLC,\n\n Plaintiffs - Appellees,\n\n v. No. 17-6146\n\n CHAPARRAL ENERGY, LLC,\n\n Defendant – Appellant,\n\n _____________________\n\n BLACK STONE MINERALS\n COMPANY, L.P.,\n\n Amicus Curiae.\n _________________________________\n\n Appeal from the United States District Court\n for the Western District of Oklahoma\n (D.C. No. 5:11-CV-00634-HE)\n _________________________________\n\nAnthony J. Shaheen, Holland & Hart LLP, Denver, Colorado (Christopher A. Chrisman\nand Jessica M. Schmidt, Holland & Hart LLP, Denver, Colorado; Linda J. Byford,\nChaparral Energy, LLC, Oklahoma City, Oklahoma; John J. Griffin, Jr., Harvey D. Ellis,\nJr., and Charles V. Knutter, Crowe & Dunlevy, Oklahoma City, Oklahoma, with him on\nthe briefs), for Defendant-Appellant Chaparral Energy, LLC.\n\nConner L. Helms (Gary R. Underwood and Erin M. Moore, with him on the brief), Helms\nUnderwood & Cook, Oklahoma City, Oklahoma, for Plaintiffs-Appellees Naylor Farms,\nInc. and Harrel’s LLC.\n\fDaniel H. Charest and Warren T. Burns, Burns Charest LLP, Dallas, Texas, filed an\namicus curiae brief for Black Stone Minerals Company, L.P. in support of Plaintiffs-\nAppellees Naylor Farms, Inc. and Harrel’s L.L.C.\n _________________________________\n\nBefore MORITZ, MURPHY, and EID, Circuit Judges.\n _________________________________\n\nMORITZ, Circuit Judge.\n _________________________________\n\n Defendant Chaparral Energy, L.L.C. (Chaparral) operates approximately 2,500\n\noil and gas wells in Oklahoma. Plaintiffs Naylor Farms, Inc. and Harrel’s, L.L.C.\n\n(collectively, Naylor Farms) have royalty interests in some of those wells. As a\n\nresult, Naylor Farms receives a portion of the proceeds those wells generate. But\n\naccording to Naylor Farms, Chaparral systematically underpaid Naylor Farms and\n\nother similarly situated royalty owners by improperly deducting from their royalty\n\npayments certain gas-treatment costs—costs that Naylor Farms says Chaparral was\n\nrequired to shoulder under Oklahoma law. Thus, Naylor Farms brought a putative\n\nclass-action lawsuit against Chaparral and moved to certify the class under Rule 23\n\nof the Federal Rules of Civil Procedure. The district court granted Naylor Farms’\n\nmotion to certify, and Chaparral now appeals the district court’s certification order.\n\nFor the reasons discussed below, we affirm.\n\n Background\n\n Under Oklahoma law, lessees like Chaparral are subject to an implied duty of\n\nmarketability (IDM).1 The IDM imposes upon lessees “a duty to provide a\n\n\n 1\n The parties agree that Oklahoma substantive law controls.\n 2\n\fmarketable product available to market.” Mittelstaedt v. Santa Fe Minerals, Inc., 954\n\nP.2d 1203, 1206 (Okla. 1998). Consistent with this duty, lessees are generally\n\nprecluded from passing along to royalty owners any costs the lessees incur in making\n\na product marketable. See id. at 1208. And because “raw or unprocessed gas” must\n\ntypically “undergo[] certain field processes”—such as gathering, compressing,\n\ndehydrating, transporting, and producing (GCDTP services)—to make the gas\n\nmarketable, lessees generally bear the costs associated with performing such services.\n\nId. at 1205, 1208.\n\n Citing the IDM, Naylor Farms brought a putative class-action lawsuit against\n\nChaparral, asserting claims for breach of contract, breach of fiduciary duty, fraud,\n\nunjust enrichment, and failure to produce in paying quantities. As relevant here,\n\nNaylor Farms’ complaint alleges that Chaparral breached the IDM by improperly\n\ndeducting GCDTP-service costs from the royalty payments Chaparral made to Naylor\n\nFarms and to other similarly-situated royalty owners. More specifically, Naylor\n\nFarms contends that in an attempt to circumvent the IDM, Chaparral enters into\n\nwellhead sales contracts with midstream processing companies. Under the terms of\n\nthose contracts, the midstream companies acquire title or possession of unprocessed\n\ngas at or near the wellhead.2 Yet according to Naylor Farms, the midstream\n\n\n 2\n The contracts fall into two categories: percentage-of-proceeds (POP)\ncontracts and percentage-of-liquids (POL) contracts. The vast majority of the\ncontracts at issue are POP contracts. Under a POP contract, the midstream processing\ncompany takes possession of the entire gas stream, processes the gas, sells it to a\ndownstream purchaser, and then pays Chaparral a percentage of the resulting\nproceeds. Under a POL contract, the midstream processing company obtains\n 3\n\fcompanies don’t actually pay Chaparral for the gas at this time. Instead, the\n\nmidstream companies first perform certain GCDTP services and then sell the treated\n\ngas to downstream purchasers.\n\n At that point, Naylor Farms asserts, the midstream companies (1) take the\n\ngross proceeds they receive from the downstream sales; (2) deduct from those gross\n\nproceeds the costs and fees associated with performing the GCDTP services;3 and\n\n(3) pay Chaparral for the gas they previously acquired at the wellhead by giving\n\nChaparral the resulting net proceeds. Chaparral then calculates royalty payments\n\nbased on the net proceeds it receives from the midstream companies, rather than\n\ncalculating royalty payments based on the gross proceeds the midstream companies\n\nreceive from the downstream sales. And in doing so, Naylor Farms alleges, Chaparral\n\nimpermissibly “requires royalty owners to bear the costs of transforming unprocessed\n\ngas into a marketable product,” thus violating the IDM. Id. at 13.\n\n Based on this theory of liability, Naylor Farms moved to certify a class\n\ncomprising it and other similarly situated royalty owners.4 In relevant part, Naylor\n\n\n\n(1) possession of and title to the natural gas liquids (NGLs) and (2) possession of\n(but not title to) the residue gas at the wellhead. Chaparral retains title to the residue\ngas, which the midstream processing company returns to Chaparral after performing\ncertain GCDTP services. The midstream processing company then charges Chaparral\na fee for performing the GCDTP services and also retains the NGLs.\n 3\n Under a POL contract, the midstream processing company charges a fee and\nretains the NGLs.\n 4\n After Naylor Farms moved to certify, Chaparral filed for bankruptcy. The\nbankruptcy court initially imposed an automatic stay on the underlying proceedings.\nBut it then partially lifted that stay so the district court could rule on Naylor Farms’\nmotion to certify.\n 4\n\fFarms argued that certification was appropriate under Rule 23 because (1) whether\n\nChaparral breached the IDM is a common question, see Fed. R. Civ. P. 23(a)(2); and\n\n(2) this and other common questions predominate over any individual ones, see Fed.\n\nR. Civ. P. 23(b)(3).\n\n In response, Chaparral asserted that whether it breached the IDM isn’t a\n\ncommon question because a jury won’t be able to answer it without first assessing\n\n“individualized issues, including the obligation created by each” individual lease\n\n“and the gas produced from each” individual well. App. vol. 2, 410. Further,\n\nChaparral asserted, these individual questions about lease language and gas quality,\n\nas well as individual questions about damages, predominate over any common\n\nquestions Naylor Farms might identify. Thus, Chaparral argued, Naylor Farms cannot\n\nsatisfy Rule 23’s certification requirements.\n\n The district court disagreed and concluded that certification was appropriate.\n\nAs an initial matter, the court ruled that Naylor Farms identified at least one common\n\nquestion: whether Chaparral breached the IDM. The district court then rejected\n\nChaparral’s arguments that answering this common question will require an\n\nindividualized assessment of either the language that appears in each lease or the\n\nquality of the gas that comes from each well. Next, the district court ruled that\n\ncommon questions, including whether Chaparral breached the IDM, predominate\n\nover any individual ones. Ultimately, after addressing Rule 23’s remaining\n\n\n\n\n 5\n\frequirements, the district court granted Naylor Farms’ motion to certify.5 Chaparral\n\nnow appeals the district court’s class-certification order.\n\n Analysis\n\n According to Chaparral, the district court erred in certifying the class under\n\nRule 23. In support, Chaparral advances three discrete arguments. It first asserts the\n\ndistrict court erred in failing to recognize that marketability constitutes an individual\n\nquestion—one that necessarily predominates over any common ones in this litigation.\n\nIt next contends the district court erred in rejecting Chaparral’s argument that\n\ndistinctions in lease language also give rise to individual questions, and that those\n\nindividual questions likewise predominate. Finally, it insists the district court erred in\n\nfailing to recognize that in the absence of evidence indicating Chaparral employs a\n\nuniform payment methodology, certification is inappropriate. We address each of\n\nthese arguments in turn.\n\nI. Marketability\n\n As discussed above, the cornerstone of Naylor Farms’ class-action lawsuit is\n\nits allegation that Chaparral breached the IDM by improperly saddling Naylor Farms\n\nand other similarly situated royalty owners with certain gas-treatment costs.\n\n The parties agree that the success of this allegation turns in large part on when\n\nthe gas at issue became marketable. But they disagree about whether, in assessing\n\nmarketability, a jury will need to individually analyze the quality of gas that each\n\n\n 5\n The district court excluded Naylor Farms’ fraud claim from the class-\ncertification order.\n 6\n\fwell produced. And by extension, they also disagree about whether the attendant need\n\nto conduct such an individualized assessment renders class certification\n\ninappropriate.\n\n To resolve the parties’ disagreement on this point, we begin with an overview\n\nof Oklahoma state law. We then discuss Rule 23’s certification requirements. Next,\n\nwe explain how the district court applied Rule 23 in the context of Naylor Farms’\n\nstate-law claims. Finally, we set forth the applicable standard of review and discuss\n\nwhether, considering that deferential standard, Chaparral’s marketability arguments\n\nrequire us to reverse the district court’s class-certification order.\n\n A. Oklahoma Law\n\n As discussed in more detail below, the ultimate issue before us in this appeal is\n\nwhether the district court abused its discretion in concluding that Naylor Farms\n\nsatisfied Rule 23’s certification requirements. See Vallario v. Vandehey, 554 F.3d\n\n1259, 1264 (10th Cir. 2009). And this ultimate issue presents a question of federal\n\nlaw. But that doesn’t doom Oklahoma law to irrelevancy. On the contrary, at the\n\nheart of the parties’ Rule 23 dispute lies an intermediate state-law question: When is\n\ngas marketable under Oklahoma law? Thus, we begin our discussion with an\n\noverview of that law. Cf. Wal–Mart Stores, Inc. v. Dukes, 564 U.S. 338, 351 (2011)\n\n(noting that Rule 23 analysis will often “overlap with the merits of the plaintiff’s\n\nunderlying claim”); CGC Holding Co., LLC v. Broad & Cassel, 773 F.3d 1076, 1087\n\n(10th Cir. 2014) (explaining that Rule 23 inquiry requires “consideration of how the\n\n\n\n 7\n\fclass intends to answer factual and legal questions to prove its claim” and thus “will\n\nfrequently entail some discussion of the claim itself”).\n\n To the extent we “are called upon to interpret state law” in resolving this\n\nappeal, we begin by “look[ing] to the rulings of [Oklahoma’s] highest state court.”\n\nStickley v. State Farm Mut. Auto. Ins. Co., 505 F.3d 1070, 1077 (10th Cir. 2007)\n\n(quoting Johnson v. Riddle, 305 F.3d 1107, 1118 (10th Cir. 2002)). It has been more\n\nthan two decades since the Oklahoma Supreme Court (OSC) has said anything\n\nmeaningful about marketability. See Mittelstaedt, 954 P.2d 1203. And neither party\n\nsuggests Mittelstaedt involved (or even contemplated, for that matter) the type of\n\nwellhead sales contracts that Chaparral allegedly utilized here. Thus, in the absence\n\nof any guidance from the OSC on the specific marketability questions before us in\n\nthis appeal, our task is “to predict how [the OSC] would rule” if it were to answer\n\nthose questions. Stickley, 505 F.3d at 1077 (quoting Johnson, 305 F.3d at 1118). In\n\nundertaking that task, we find certain aspects of Mittelstaedt relevant to, albeit not\n\ndispositive of, the issues before us.\n\n In Mittelstaedt, the OSC began by explaining that the IDM imparts upon\n\nlessees like Chaparral a duty “to provide a marketable product available to market.”\n\n954 P.2d at 1208. And as the OSC noted, “[i]t is common knowledge that raw or\n\nunprocessed gas” must usually undergo one or more GCDTP services to make that\n\ngas marketable.6 Id. Thus, because the costs of such GCDTP services are often\n\n\n 6\n In Mittelstaedt, the OSC discussed “separation, dehydration, compression,\nand treatment” but didn’t mention gathering or transporting. 954 P.2d at 1208.\n 8\n\f“associated with” making gas marketable, the OSC explained that the IDM typically\n\nprecludes a lessee from “deducting a proportionate share” of those costs from royalty\n\npayments. Id. at 1205. But the OSC then recognized that a lessee may sometimes be\n\nable to demonstrate that gas is “in a marketable form at the well[head].” Id. at 1208.\n\nIn that scenario, GCDTP services aren’t “necessary” to transform the already-\n\nmarketable gas into a marketable product. Id. at 1208. Yet a lessee may nevertheless\n\nopt to perform such services with an eye toward “enhancing” the value of the\n\n“already[-]marketable” gas. Id. at 1210. And when it does so, the OSC explained, the\n\ncost of performing such GCDTP services “may be allocated to the royalty interests”\n\nif the lessee can make certain additional showings. Id.\n\n We derive two controlling principles from Mittelstaedt. First, Mittelstaedt\n\nresolved that when unmarketable gas undergoes GCDTP services for the purpose of\n\ntransforming that unmarketable gas into a marketable product, the lessee must bear\n\nthe cost of the GCDTP services. Second, Mittelstaedt resolved that when marketable\n\ngas undergoes GCDTP services to enhance the value of gas that is already\n\nmarketable, the lessee may, under certain circumstances, allocate the cost of the\n\nGCDTP services to royalty holders.\n\n Yet Mittelstaedt left unresolved a whole host of other questions. The most\n\nobvious are these: What does the term “marketable” mean, and what factors\n\n\n\nNevertheless, because neither party identifies any legally significant distinctions\nbetween these services, we continue to use the term “GCDTP services” when\ndiscussing Mittelstaedt.\n 9\n\fdetermine when, where, and if gas became marketable for purposes of applying\n\nMittelstaedt’s marketable-product rule?\n\n Notably, the OSC has declined at least two recent invitations to address these\n\nquestions. See Order Denying Certiorari, Whisenant v. Strat Land Expl. Co., No.\n\n115,660 (Okla. Oct. 1, 2018); Order Denying Certiorari, Pummill v. Hancock Expl.\n\nLLC, No. 114,703 (Okla. May 21, 2018). Further, the OSC declined one of these\n\ninvitations over the dissenting voices of two of its own members. See Dissent from\n\nOrder Denying Certiorari, Pummill, No. 114,703 (May 21, 2018) (Winchester, J.)\n\n(noting that OSC “should grant certiorari to refine what constitutes a ‘marketable\n\nproduct’ as that term is used in [Mittelstaedt]”).\n\n Nevertheless, the Oklahoma Court of Civil Appeals (OCOCA) has attempted\n\nto fill the resulting legal vacuum, albeit with somewhat inconsistent outcomes. See\n\nWhisenant v. Strat Land Expl. Co., 429 P.3d 703, 707, 708–10 (Okla. Civ. App.\n\n2018) (recognizing that term “marketable product” isn’t susceptible to and has no\n\nuniform definition, but then implicitly suggesting marketability always turns, at least\n\nin part, on individual characteristics of gas at issue); Pummill v. Hancock Expl. LLC,\n\n419 P.3d 1268, 1278 (Oka. Civ. App. 2018) (indicating that in some cases, it may be\n\npossible to answer marketability question based on characteristics of relevant market,\n\nthus rendering individualized gas-quality assessment unnecessary).\n\n In Whisenant, for instance, the OCOCA held that the state trial court erred\n\nwhen, in proceeding under Okla. Stat. Ann. tit. 12, § 2023(B)(3), it certified a class\n\nof Oklahoma royalty owners who brought claims similar to those Naylor Farms\n\n 10\n\fadvances here.7 See 429 P.3d at 706–07. Specifically, those royalty owners alleged\n\nthat the defendant, who operated several Oklahoma gas wells, breached the IDM by\n\ncalculating “royalties based on what it received from” a midstream processing\n\ncompany, “rather than based on what” that midstream processing company “received\n\nfor the gas at the interstate (or intrastate) pipeline inlet.” Id. at 706.\n\n In reversing the district court’s certification order, the Whisenant court\n\ninitially expressed its view that the OSC has, “for good reasons,” declined to “define\n\nthe meaning of ‘marketable product,’” opting instead to leave the marketability\n\nquestion “open to resolution on a case-by-case basis.” Whisenant 429 P.3d at 708\n\n(quoting Mittelstaedt, 954 P.2d at 1208). Nevertheless, immediately after suggesting\n\nthat the concept of marketability isn’t susceptible to any uniform definition or test,\n\nthe Whisenant court indicated that the answer to the marketability question will\n\nalways turn, at least in part, on “the quality of [the] gas” at issue. Id. at 710–12. Thus,\n\nthe Whisenant court reasoned, a “highly individualized and fact-intensive review of\n\neach [class member’s] claim,” as informed by the quality of the gas at each\n\nindividual well, “would be necessary to determine if” the defendant in that case\n\nbreached the IDM. Id. at 707, 709–10 (quoting Strack v. Cont’l Res., Inc., 405 P.3d\n\n131, 140 (Okla. Ct. Civ. App. 2017)).\n\n In Pummill, on the other hand, a different panel of the OCOCA indicated that,\n\nin some circumstances, it may be possible to determine whether gas is marketable\n\n\n 7\n Section 2023(B)(3) is Rule 23(b)(3)’s state-law counterpart. See Whisenant,\n429 P.3d at 706.\n 11\n\fwithout undertaking such a gas-quality assessment. In that case, the state trial court\n\nruled that the gas at issue wasn’t marketable “at or near the wellhead” and that\n\ninstead the gas only became marketable once it “reache[d] the tailgate of” a\n\nmidstream processing plant—i.e., once the midstream processing company completed\n\ncertain GCDTP services. Pummill, 419 P.3d at 1271, 1276–78.\n\n In reaching that conclusion, the trial court focused not on a qualitative analysis\n\nof the gas itself, but on evidence about “the market in which” the defendants (there,\n\nthe well operator and multiple lessees) “chose[] to participate.” Id. at 1270–71, 1278.\n\nIn particular, although the gas at issue was physically transferred to the midstream\n\nprocessing company near the wellhead, the trial court concluded that the well\n\noperator was “not in the wellhead market.” Id. at 1271, 1278. Instead, the trial court\n\nreasoned, no “actual sale” occurred until the gas was “acceptable for transport in”\n\nand capable of being “transferred into” high-pressure pipelines. Id. at 1278. Thus, the\n\ntrial court deduced, the well operator was in the high-pressure pipeline market. And\n\nbecause the gas wasn’t capable of being sold on the high-pressure pipeline market\n\nuntil it was “compressed, treated, dehydrated, separated, and processed,” the trial\n\ncourt ruled the gas wasn’t marketable until it underwent those services. Id.\n\n The Pummill court affirmed. Id. at 1280. In doing so, it expressly endorsed the\n\ntrial court’s method of “focus[ing] on” when the gas at issue was first capable of\n\nbeing sold on “the market in which” the well operator “chose[] to participate”—there,\n\nthe high-pressure pipeline market. Id. at 1278. And because the gas at issue wasn’t\n\ncapable of being sold on the high-pressure pipeline market until GCDTP services\n\n 12\n\frendered the gas “acceptable for transport in high-pressure pipelines,” the OCOCA\n\nagreed the gas wasn’t marketable until that point. Id. Thus, the OCOCA held, the\n\nIDM precluded the defendants from passing on to royalty owners the costs associated\n\nwith performing those GCTDP services. Id. at 1280.\n\n Notably, en route to affirming the trial court’s ruling, the OCOCA declined to\n\nadopt Kansas’s rule that gas is marketable once it is “acceptable to a purchaser in a\n\ngood[-]faith transaction.” Id. at 1276 (quoting Fawcett v. Oil Producers, Inc., 352\n\nP.3d 1032, 1034 (Kan. Ct. App. 2015)). And the OCOCA likewise rejected the\n\ndefendants’ related argument that “raw or minimally processed gas” becomes\n\nmarketable as soon as a “limited group of potential purchasers” is willing to\n\n“purchase” that gas “for further processing and sale downstream.” Id. at 1277; see\n\nalso id. at 1278 (explaining that “[e]vidence of hypothetical sales of raw product to a\n\nlimited group of potential purchasers to whom such gas would be acceptable[] does\n\nnot readily lend itself to a conclusion that the product being sold is ‘marketable’ in a\n\nfree and competitive market”). Instead, the Pummill court reasoned, gas becomes\n\nmarketable when it’s subject to an “actual sale.” Id. at 1278 (explaining that this\n\nconclusion is “consistent with” OSC precedent describing “market value” of gas “as\n\nbeing based on what [gas] will sell for, between a willing buyer and seller, in ‘a free\n\nand open market’” (quoting Howell v. Texaco Inc., 112 P.3d 1154, 1159 (Okla.\n\n2004))).\n\n The OCOCA’s 2018 decisions in Pummill and Whisenant illustrate what has\n\nlong been clear: although “it is easy to articulate [Mittelstaedt’s] marketable-product\n\n 13\n\frule, application of it to a particular circumstance is difficult.” Foster v. Apache\n\nCorp., 285 F.R.D. 632, 638 & n.14 (W.D. Okla. 2012). And for reasons we turn to\n\nnext, “[d]oing so in the class action context”—as the district court was required to\n\ndo here—is more difficult still. Id. at 638.\n\n B. Rule 23’s Certification Requirements\n\n Rule 23 sets forth the requirements for class certification.8 See Wal–Mart\n\nStores, Inc., 564 U.S. at 345. Only two of those requirements are at issue here: Rule\n\n23(a)(2)’s commonality requirement and Rule 23(b)(3)’s predominance requirement.9\n\nA plaintiff seeking class certification satisfies Rule 23(a)(2)’s commonality\n\nrequirement by demonstrating that “there are questions of law or fact common to the\n\nclass.” Fed. R. Civ. P. 23(a)(2). A plaintiff satisfies Rule 23(b)(3)’s related\n\npredominance requirement by showing that “questions of law or fact common to\n\nclass members predominate over any questions affecting only individual members.”\n\nFed. R. Civ. P. 23(b)(3).\n\n\n 8\n Rule 23’s requirements inform our analysis of each of the three discrete\narguments Chaparral presents on appeal. See infra Sections II, III.\n 9\n Chaparral asserts that “Rule 23 includes an ‘implied requirement of\nascertainability’” and that Naylor Farms cannot satisfy this “implied requirement”\nhere. Aplt. Br. 14 (quoting Brecher v. Republic of Argentina, 806 F.3d 22, 24 (2d Cir.\n2015)). But Chaparral fails to “cite the precise references in the record where” this\nascertainability argument “was raised and ruled on” below. 10th Cir. Rule 28.1(A).\nAnd it also fails to make a case for plain error on appeal. Accordingly, we decline to\naddress this argument. See Richison v. Ernest Grp., Inc., 634 F.3d 1123, 1131 (10th\nCir. 2011); Harolds Stores, Inc. v. Dillard Dep’t Stores, Inc., 82 F.3d 1533, 1540 n.3\n(10th Cir. 1996). Likewise, although Chaparral makes passing reference to Rule\n23(a)(3)’s typicality requirement, see Aplt. Br. 23, 33, we find these “stray\nsentences” insufficient to adequately brief any argument on this point. Eizember v.\nTrammell, 803 F.3d 1129, 1141 (10th Cir. 2015).\n 14\n\f Rule 23(a)(2)’s commonality requirement “is easy to misread.” Wal–Mart\n\nStores, Inc., 564 U.S. at 349. It requires a plaintiff to do more than merely identify “a\n\ncommon contention”; instead, that “common contention . . . must be of such a nature\n\nthat it is capable of classwide resolution—which means that determination of its truth\n\nor falsity will resolve an issue that is central to the validity of each one of the claims\n\nin one stroke.” Id. at 350. In other words, the focus of Rule 23(a)(2)’s commonality\n\nrequirement is not so much on whether there exist common questions, but rather on\n\n“the capacity of a classwide proceeding to generate common answers apt to drive the\n\nresolution of the litigation.” Id. at 350 (quoting Richard A. Nagareda, Class\n\nCertification in the Age of Aggregate Proof, 84 N.Y.U. L. Rev. 97, 132 (2009)).\n\n Rule 23(b)(3)’s predominance requirement is related to, albeit “more\n\ndemanding than,” Rule 23(a)(2)’s commonality requirement. Comcast Corp. v.\n\nBehrend, 569 U.S. 27, 34 (2013). To satisfy Rule 23(b)(3), a plaintiff must “show\n\nthat common questions subject to generalized, classwide proof predominate over\n\nindividual questions.” CGC Holding Co., 773 F.3d at 1087; see also Tyson Foods,\n\nInc. v. Bouaphakeo, 136 S. Ct. 1036, 1045 (2016) (“An individual question is one\n\nwhere ‘members of a proposed class will need to present evidence that varies from\n\nmember to member,’ while a common question is one where ‘the same evidence will\n\nsuffice for each member to make a prima facie showing [or] the issue is susceptible\n\nto generalized, class[]wide proof.’” (alteration in original) (quoting 2 William B.\n\nRubenstein et al., Newberg on Class Actions § 4:50 (5th ed. 2012))).\n\n\n\n 15\n\f Notably, this doesn’t mean a plaintiff must show “that all of the elements of\n\nthe claim entail questions of fact and law that are common to the class” or “that the\n\nanswers to those common questions [are] dispositive” of the claim. CGC Holding\n\nCo., 773 F.3d at 1087. Instead, the predominance inquiry “asks whether the common,\n\naggregation-enabling[] issues in the case are more prevalent or important than the\n\nnon-common, aggregation-defeating, individual issues.” Id. (quoting Newberg on\n\nClass Actions § 4:49). Thus, to determine whether a plaintiff can satisfy Rule\n\n23(b)(3)’s predominance requirement, a court must first “characterize the issues in\n\nthe case as common or not, and then weigh which issues predominate.” Id. (quoting\n\nNewberg on Class Actions § 4:50). Critically, so long as at least one common issue\n\npredominates, a plaintiff can satisfy Rule 23(b)(3)—even if there remain individual\n\nissues, such as damages, that must be tried separately. Tyson Foods, Inc., 136 S. Ct.\n\nat 1045.\n\n Having reviewed the relevant Rule 23 requirements and examined Oklahoma’s\n\ntreatment of the marketability question, we next explain how the district court treated\n\nthe interplay between the former and the latter in ruling on Naylor Farms’ motion to\n\ncertify.\n\n C. The District Court’s Ruling\n\n The district court found that Naylor Farms successfully identified at least one\n\ncommon question: whether Chaparral breached the IDM.10 And the court then ruled\n\n\n 10\n Chaparral contends the district court erred in concluding that the threshold\nissue of whether each lease contains an IDM is “in and of itself” a common question.\n 16\n\fthat this common question predominates over any individual ones.\n\n Critically, in doing so, the district court first narrowed the class to include only\n\nthose royalty owners whose leases contain clauses that are similar to the royalty\n\nclauses (collectively, Mittelstaedt Clauses) the OSC considered in three cases:\n\n(1) Mittelstaedt, (2) TXO Production Corp. v. State ex rel. Commissioners of Land\n\nOffice, 903 P.2d 259 (Okla. 1995), and (3) Wood v. TXO Production Corp., 854 P.2d\n\n880 (Okla. 1993). Because the OSC has held that the language of these Mittelstaedt\n\nClauses “does not negate the IDM” and “is consistent with the marketable[-]product\n\nrule,” the district court reasoned that—contrary to Chaparral’s arguments—any\n\nremaining “variations in lease language” do not defeat commonality or\n\npredominance. App. vol. 5, 1148, 1153.\n\n Next, the district court rejected Chaparral’s argument that in order to\n\ndetermine whether Chaparral breached the IDM, a jury will have to engage in an\n\n\nAplt. Br. 11. As an initial matter, we disagree with the premise of this argument; at\nmost, it appears the district court treated the existence of the IDM “and its alleged\nbreach” as a compound common question. App. vol. 5, 1154 (emphasis added).\n\n In any event, even assuming the district court treated the existence of the IDM\nas a standalone common question and even assuming it erred in doing so, the error\nwas harmless; the district court correctly concluded that whether Chaparral breached\nthe IDM is a common question. See Wal–Mart Stores, Inc., 564 U.S. at 350\n(explaining that question is common for purposes of Rule 23(a)(2) if its answer “will\nresolve an issue that is central to the validity of each one of the claims in one\nstroke”); cf. Menocal v. GEO Grp., Inc., 882 F.3d 905, 916–17 (10th Cir.) (holding\nthat question of whether defendant’s policy violated federal statute constituted\ncommon question), cert. denied, 139 S. Ct. 143 (2018). Chaparral doesn’t seriously\nargue otherwise. And when it comes to satisfying Rule 23(a)(2)’s commonality\nrequirement, the existence of this single common question “will do.” Wal–Mart\nStores, Inc., 564 U.S. at 359.\n 17\n\findividualized “well-by-well analysis” to determine when the gas from each well\n\nbecame marketable. Id. at 1149. In rejecting this argument, the district court\n\nacknowledged that gas quality might vary from well to well and that, as a result,\n\nsome gas might require more or different GCTDP services to become marketable\n\nthan other gas. But the district court explained that in order to determine whether\n\nChaparral breached the IDM, an individualized gas-quality analysis is nevertheless\n\n“unnecessary” in this case because, as Naylor Farms demonstrated, all the gas at\n\nissue “require[d]” at least one GCDTP service “to become marketable.” Id. at 1149,\n\n1151, 1157.\n\n Thus, the district court appeared to recognize, differences in the precise\n\nnumber and nature of GCDTP services required to make the gas from each well\n\nmarketable are relevant only to the post-breach question of damages. And because\n\nNaylor Farms “provided evidence that [its] expert can determine damages on a\n\nclass[]wide basis through use of a model,” the district court ruled these distinctions\n\ndon’t defeat predominance. Id. at 1155. Alternatively, the district court pointed out\n\nthat if necessary, it can divide the class into subclasses at a later date for purposes of\n\ndetermining damages. See Fed. R. Civ. P. 23(c)(1)(C) (“An order that grants or\n\ndenies class certification may be altered or amended before final judgment.”), (c)(5)\n\n(“When appropriate, a class may be divided into subclasses that are each treated as a\n\nclass under this rule.”). Accordingly, the district granted Naylor Farms’ motion to\n\ncertify.\n\n\n\n 18\n\f D. Our Standard of Review\n\n Our review of the district court’s decision is highly deferential. So long as the\n\ndistrict court “applied the proper standard in deciding whether to certify [the] class,\n\nwe may reverse that decision only for abuse of discretion.” CGC Holding Co., 773\n\nF.3d at 1085 (quoting Adamson v. Bowen, 855 F.2d 668, 675 (10th Cir. 1988)); see\n\nalso Vallario, 554 F.3d at 1264 (“Because class certification decisions are necessarily\n\ncase specific, district courts possess significant latitude in deciding whether or not to\n\ncertify a class.” (citation omitted)). A “district court abuses its discretion when it\n\nmisapplies the Rule 23 factors—either through a clearly erroneous finding of fact or\n\nan erroneous conclusion of law—in deciding whether class certification is\n\nappropriate.” CGC Holding Co., 773 F.3d at 1085–86.\n\n Here, Chaparral doesn’t argue that the district court failed to apply the proper\n\nRule 23 standard. Thus, in addressing those arguments Chaparral does make, we must\n\ndefer to the district court’s ruling unless Chaparral shows the district court’s\n\ncertification decision falls outside “the bounds of rationally available choices given\n\nthe facts and law involved in the matter at hand.” Id. at 1086 (quoting Vallario, 554\n\nF.3d at 1264). For the reasons discussed below, we conclude that Chaparral fails to\n\nmake this demanding showing.\n\n E. Chaparral’s Marketability Arguments\n\n Chaparral’s primary argument on appeal is that the district court abused its\n\ndiscretion in ruling that Naylor Farms demonstrated commonality and predominance\n\nbecause such a ruling is irreconcilable with Oklahoma’s approach to determining\n\n 19\n\fmarketability. Or, as Chaparral puts it, “Certifying a class of ‘Mittelstaedt Clause\n\n[l]eases’ is contrary to Mittelstaedt.” Aplt. Br. 16.\n\n Recall that, under Mittelstaedt, two things are clear. First, when unmarketable\n\ngas undergoes GCDTP services for purposes of transforming the unmarketable gas\n\ninto a marketable product, a lessee breaches the IDM by passing on to royalty owners\n\nthe cost of performing those GCDTP services. See Mittelstaedt, 954 P.2d at 1205.\n\nSecond, when marketable gas undergoes GCDTP services to enhance the value of\n\ngas that is already marketable, a lessee may, under certain circumstance, allocate the\n\ncost of those services to royalty owners without breaching the IDM. Id. at 1210.\n\nThus, to determine whether Chaparral breached the IDM—i.e., to answer the question\n\nthe district court determined was common to the class for purposes of satisfying Rule\n\n23(a)(2)’s commonality requirement—a jury will have to determine when the gas at\n\nissue became marketable.\n\n Here, as Chaparral points out, the district court ruled that (1) the question of\n\nwhen the gas became marketable can be answered via generalized, classwide proof\n\nand (2) as a result, the marketability question doesn’t defeat predominance. See Fed.\n\nR. Civ. P. 23(b)(3) (allowing for certification if common questions predominate over\n\nindividual ones); Tyson Foods, Inc., 136 S. Ct. at 1045 (“An individual question is\n\none where ‘members of a proposed class will need to present evidence that varies\n\nfrom member to member,’ while a common question is one where ‘the same evidence\n\nwill suffice for each member to make a prima facie showing [or] the issue is\n\n\n\n 20\n\fsusceptible to generalized, class[]wide proof.’” (first alteration in original) (quoting\n\nNewberg on Class Actions § 4:50)).\n\n But according to Chaparral, the district court’s ruling on this point rests on a\n\nflawed assumption. Specifically, Chaparral contends that in ruling a jury can answer\n\nthe marketability question without undertaking a well-by-well analysis, the district\n\ncourt relied on the fact that all the gas at issue actually underwent GCDTP services.\n\nAnd in so ruling, Chaparral argues, the district court made a legally erroneous\n\nassumption: it incorrectly assumed that any time gas undergoes GCDTP services, this\n\nproves, ipso facto, that the gas wasn’t marketable before it underwent those services.\n\n We agree with Chaparral that if the district court assumed GCDTP services\n\nfunction solely as a mechanism for transforming unmarketable gas into a marketable\n\nproduct, then the court committed a legal error. As Chaparral correctly points out,\n\nMittelstaedt expressly recognizes that sometimes even marketable gas undergoes\n\nGCDTP services—not to “create a marketable product” but to “transform[] an\n\nalready[-]marketable product into an enhanced” one. Mittelstaedt, 954 P.2d at 1209–\n\n10; see also id. at 1208 (acknowledging that it’s possible for gas to “be in a\n\nmarketable form at the well[head],” i.e., before any GCDTP services are\n\nperformed).11 But we disagree with Chaparral that the district court ever assumed\n\notherwise.\n\n\n\n 11\n In asserting that gas can be marketable at the wellhead, Chaparral appears to\nrely in part on its position that the gas at issue here was in fact marketable at the\nwellhead—because (according to Chaparral) that is where Chaparral first “sold” the\n 21\n\f That is, contrary to Chaparral’s argument, the district court neither ruled nor\n\nassumed “that gas must be unmarketable if it goes through a processing plant or\n\nreceives one or more of the GCDTP services.” Aplt. Br. 19. On the contrary, the\n\ndistrict court expressly recognized that the marketability question turns not on\n\nwhether the gas undergoes GCDTP services, but on whether the gas undergoes\n\nGCDTP services “to become marketable.” App. vol. 5, 1151. Indeed, the district\n\ncourt expressly relied on evidence indicating that all the gas at issue here “require[d]\n\nGCDTP services to be made marketable” in order to distinguish the facts of this case\n\nfrom those before this court in Wallace B. Roderick Revocable Living Trust v. XTO\n\nEnergy, Inc., 725 F.3d 1213 (10th Cir. 2013); in that case, the district court pointed\n\nout, some of the gas at issue “may [have been] marketable at the well.” App. vol. 5,\n\n1146 (emphases added) (quoting Roderick, 725 F.3d at 1217). Critically, in making\n\nthis distinction, the district court necessarily acknowledged both that (1) “gas may be\n\nmarketable at the well[head]” and (2) the performance of GCDTP services does not\n\nprove, ipso facto, that the gas at issue was not marketable before those services were\n\n\ngas “to a [midstream processing company] in a good[-]faith transaction.” Aplt. Br.\n20; see also id. at 18 (“Gas is in marketable condition once it can be marketed.”).\n\n As an initial matter, we question whether the OSC would adopt this good-\nfaith-transaction test for marketability. See Pummill, 419 P.3d at 1278–79\n(suggesting good-faith-transaction approach is inconsistent with controlling OSC\nauthority). More importantly, as the district court noted below, accepting as true\nChaparral’s blanket assertion that all the gas at issue was marketable at the wellhead\nbecause that is where Chaparral could first “market[]” it to midstream processing\ncompanies, Aplt. Br. 18, would serve only to “demonstrate[]” commonality, not\n“negate[]” it, App. vol. 5, 1149; such a blanket rule would obviate the need for any\nindividualized analysis of the gas from each well.\n 22\n\fperformed. Id. (quoting Roderick, 725 F.3d at 1217). Accordingly, we reject\n\nChaparral’s assertion that the district court assumed otherwise.\n\n Alternatively, Chaparral argues that the district court erred in treating\n\nmarketability as a question of law. Instead, Chaparral asserts, marketability is a\n\nquestion of fact—one that turns, at least in part, on “gas quality.” Aplt. Br. 23. And it\n\nfurther insists that because the quality of its gas varies from well to well, a jury will\n\nbe unable to resolve the marketability question (and, by extension, the question of\n\nwhether Chaparral breached the IDM) without performing a well-by-well analysis to\n\ndetermine whether any of the gas at issue was marketable at the wellhead. Thus,\n\nChaparral insists, the district court abused its discretion in failing to recognize that\n\nmarketability defeats commonality and predominance.\n\n In evaluating this argument, we need not resolve whether the district court\n\ntreated marketability as a question of law or a question of fact. Nor must we resolve\n\nwhether, if the district court indeed treated marketability as a question of law, it erred\n\nin doing so.12 Even assuming Chaparral is correct on both points, that doesn’t\n\nnecessarily mean Chaparral is entitled to reversal. On the contrary, “we may affirm\n\non any basis supported by the record, even if it requires ruling on arguments not\n\nreached by the district court.” Richison, 634 F.3d at 1130. That is, we have a\n\n“preference for affirmance”—one that “follows from the deference we owe to the\n\n\n\n 12\n We nevertheless note in passing that it appears Oklahoma indeed treats\nmarketability as question of fact. See, e.g., Whisenant, 429 P.3d at 708 n.6; Pummill,\n419 P.3d at 1274 n.9.\n 23\n\fdistrict courts and the judgments they reach, many times only after years of involved\n\nand expensive proceedings.” Id. And “[b]ecause of the cost and risk involved anytime\n\nwe upset a court’s reasoned judgment, we are ready to affirm whenever the record\n\nallows it.” Id. Thus, to demonstrate it is entitled to reversal, Chaparral must\n\n“shoulder a heavy burden”: it “must come ready both to show” that the district court\n\nerred and “to explain why no other grounds” will allow us to affirm the district\n\ncourt’s decision. Id. For the reasons discussed below, we conclude that in light of the\n\nOCOCA’s persuasive reasoning in Pummill, Chaparral cannot shoulder the second\n\npart of this heavy burden here. See West v. Am. Tel. & Tel. Co., 311 U.S. 223, 237\n\n(1940) (explaining that decision of intermediate state appellate court “is a datum for\n\nascertaining state law [that] is not to be disregarded by a federal court unless it is\n\nconvinced by other persuasive data that the highest court of the state would decide\n\notherwise”).\n\n In Pummill, the OCOCA relied heavily on two factors in affirming the state\n\ntrial court’s ruling that the gas at issue wasn’t marketable before it underwent\n\nGCTDP services. As an initial matter, the OCOCA pointed out that the first “actual\n\nsale” of the gas occurred not when the defendants transferred the gas to a midstream\n\nprocessing company, but instead “at the ‘tailgate’ of the [processing] plants, where\n\n[the gas was] transferred into high-pressure lines.” 419 P.3d at 1277–78. And the\n\nOCOCA deduced from the location of this first “actual sale” that “the market in\n\nwhich” the defendants “chose[] to participate” was the pipeline market, not the\n\nwellhead market. Id. Second, the OCOCA noted that the gas had to undergo GCDTP\n\n 24\n\fservices to make it “acceptable for delivery” into the high-pressure pipelines. Id. at\n\n1277. Accordingly, the OCOCA concluded that the IDM precluded the defendants\n\nfrom “deduct[ing] from [the plaintiffs’] royalties the proportionate expenses\n\nassociated with preparing the gas for sale” to such pipelines. Id. at 1280.\n\n Here, Naylor Farms has presented evidence of these same two factors. More\n\nimportantly, it has presented classwide evidence of these same two factors. See Tyson\n\nFoods, Inc., 136 S. Ct. at 1045 (explaining that for purposes of Rule 23(b)(3), “a\n\ncommon question is one where ‘the same evidence will suffice for each member to\n\nmake a prima facie showing [or] the issue is susceptible to generalized, class[]wide\n\nproof’” (alteration in original) (quoting Newberg on Class Actions § 4:50)). First, the\n\nrecord contains classwide evidence indicating that Chaparral, like the defendants in\n\nPummill, elects to participate in the high-pressure-pipeline market: according to\n\nNaylor Farms’ expert, this is where Chaparral’s gas is actually “sold.” Aplt. Supp.\n\nApp. vol. 18, 5270; see also Pummill, 419 P.3d at 1278 (noting that pipeline market\n\nwas where first “actual sale” of gas occurred). Second, Naylor Farms’ expert opined\n\nthat, as a classwide matter, the gas at issue here—like the gas at issue in Pummill—\n\nwas required to undergo at least one GCDTP service before it could “reach” and be\n\n“sold into” the pipeline market.13 Aplt. Supp. App. vol. 18, 5270–71; see also\n\nPummill, 419 P.3d at 1277 (concluding that gas wasn’t marketable on pipeline market\n\n\n 13\n Notably, despite Chaparral’s insistence that a well-by-well analysis is\nnecessary to determine when the gas became marketable, Chaparral fails to point to\nany evidence in the record indicating that such an individualized analysis would yield\na different conclusion.\n 25\n\funtil it was “acceptable for delivery” into relevant pipelines); cf. Wood, 854 P.2d at\n\n882 (explaining that IDM imposes “a duty to get the product to the place of sale in\n\nmarketable form” (emphasis added)).\n\n In short, the district court’s ruling that marketability is subject to classwide\n\nproof under the specific facts of this case is entirely consistent with the OCOCA’s\n\ndecision in Pummill. Thus, Chaparral faces an uphill climb in attempting to show that\n\nthis particular ruling rests on an error of state law. See West, 311 U.S. at 237. In\n\nattempting to make that showing here, Chaparral relies heavily on the OCOCA’s\n\nrecent decision in Whisenant.\n\n In Whisenant, the OCOCA held that the state trial court erred in certifying a\n\nclass of Oklahoma royalty owners under Oklahoma’s analog to Rule 23, reasoning\n\nthat a “highly individualized and fact-intensive review of each [class member’s]\n\nclaim,” as informed by the quality of gas at each individual well, “would be\n\nnecessary to determine if” the defendant in that case breached the IDM. 429 P.3d at\n\n707–10 (quoting Strack, 405 P.3d at 140)). Citing Whisenant, Chaparral insists that\n\nunder Oklahoma law, marketability can never be susceptible to classwide proof\n\nbecause it will always require an individualized assessment of the gas produced by\n\neach well. And to the extent the district court failed to recognize as much here,\n\nChaparral contends, the court made a legal error and thereby abused its discretion.\n\nSee CGC Holding Co., 773 F.3d at 1085–86 (“The district court abuses its discretion\n\nwhen it misapplies the Rule 23 factors—either through a clearly erroneous finding of\n\n\n\n 26\n\ffact or an erroneous conclusion of law—in deciding whether class certification is\n\nappropriate.”).\n\n In light of Whisenant’s similar procedural posture, Chaparral’s argument isn’t\n\nwithout appeal. But because that argument overlooks a critical aspect of Whisenant’s\n\nanalysis, we ultimately reject it. That is, the Whisenant court did hold that, in that\n\nparticular case, “determinations of the quality of gas and other facts pertinent to each\n\nwell” weren’t “susceptible to generalized proof.” 429 P.3d at 710. But the Whisenant\n\ncourt also expressly eschewed the type of rigid, one-size-fits-all approach to\n\nmarketability that Chaparral asks us to endorse here. Specifically, the Whisenant\n\ncourt recognized that the OSC has declined to adopt a uniform test for determining\n\nwhen gas becomes marketable, and that the OSC has instead “left the issue open to\n\nresolution on a case-by-case basis.” 429 P.3d at 708. And in recognizing as much, the\n\nWhisenant court necessarily “left . . . open” the possibility that, in some cases, a\n\nfactfinder may be able to determine when gas became marketable without\n\nundertaking an individualized inquiry into the quality of that gas. Id.\n\n Critically, the facts in Pummill (and, by extension, the facts in this case) fit\n\ncomfortably in the space “left . . . open” by Whisenant. Id. Thus, despite any tension\n\nthat might exist between Pummill and Whisenant, we rely on both—and “disregard[]”\n\nneither—in predicting how the OSC would answer the marketability question before\n\nus in this appeal. West, 311 U.S. at 237. And in light of Pummill and Whisenant, we\n\npredict the OSC would answer that question by holding that, under the facts of this\n\ncase, a jury could determine when the gas at issue became marketable without\n\n 27\n\findividually assessing the quality of that gas; instead, a jury could make this\n\ndetermination based solely on expert testimony that all the gas at issue was required\n\nto undergo at least one GCDTP service before it could “reach” and be “sold into” the\n\npipeline market. Aplt. Supp. App. vol. 18, 5270–71. See Whisenant, 429 P.3d at 708\n\n(opining that OSC has intentionally and wisely “left the issue [of marketability] open\n\nto resolution on a case-by-case basis”); Pummill, 419 P.3d at 1273, 1278 (indicating\n\nthat in some cases, it may be possible to answer marketability question based on\n\ncharacteristics of relevant market, thus rendering individualized gas-quality\n\nassessment unnecessary). Accordingly, the district court didn’t abuse its discretion by\n\nconcluding that the marketability question in this particular case is subject to\n\ncommon, classwide proof for purposes of satisfying Rule 23’s commonality and\n\npredominance requirements. See Tyson Foods, Inc., 136 S. Ct. at 1045; CGC Holding\n\nCo., 773 F.3d at 1086; Richison, 634 F.3d at 1130.\n\nII. Lease Language\n\n Next, Chaparral asserts that even if gas-quality variations don’t pose a bar to\n\ncertification, lease-language variations do. Specifically, Chaparral asserts that “[a]t\n\ntrial, every one of the contracts will have to be considered individually, defeating\n\ncommonality and predominance.” Aplt. Br. 27–28. But the district court concluded\n\notherwise, ruling that its decision to limit the class to leases containing a Mittelstaedt\n\nClause renders such an individualized analysis unnecessary.14\n\n\n 14\n Naylor Farms asserts we should take judicial notice of certain briefing in\nMittelstaedt because, according to Naylor Farms, that briefing sheds additional light\n 28\n\f In challenging this conclusion, Chaparral first asserts the district court\n\nabdicated its duty to determine which leases actually contain a Mittelstaedt Clause\n\nand instead merely “satisfied itself with [Naylor Farms’] contentions” that this is so.\n\nId. at 28. We disagree. As the district court noted, Naylor Farms prepared a chart that\n\n“categorized” the leases at issue “by royalty[-]clause language.” App. vol. 5, 1143.\n\nAnd we have previously indicated that this is precisely what a plaintiff should do to\n\nestablish commonality under these circumstances. See Roderick, 725 F.3d at 1219.\n\n Like Naylor Farms, the plaintiffs in Roderick asserted that each class\n\nmember’s lease contained an IDM. Id. at 1218. But neither the plaintiffs nor the\n\ndistrict court bothered to examine all the leases to verify this assertion. Id. at 1219.\n\nThus, this court recommended that on remand, the plaintiffs should consider\n\n“creat[ing] a chart classifying lease types.” Id. And if they did so, this court opined,\n\n“the district court could” rely on that chart to “decide that no lease type negates the\n\nIDM.” Id.\n\n Here, Naylor Farms created such a chart. And contrary to Chaparral’s\n\nassertions, the district court independently “confirmed that” the chart was “generally\n\naccurate.” App. vol. 5, 1147. Notably, Chaparral doesn’t provide us with any\n\ninformation that might call into question the district court’s assessment of the chart’s\n\naccuracy. Instead, Chaparral merely asserts that because there exist distinctions\n\n\non the lease language at issue in Mittelstaedt as well as the arguments the parties\nmade about that language. Because we conclude we may resolve Chaparral’s lease-\nlanguage arguments without this additional information, we deny Naylor Farms’\nmotion to take judicial notice.\n 29\n\fbetween the facts in this case and the facts in TXO, 903 P.2d 259, and Wood, 854\n\nP.2d 880—each of which involved a Mittelstaedt Clause—“the district court could\n\nnot” rely on these two cases to “determine as a matter of law whether” Chaparral\n\ncould “share[]” certain costs with royalty owners. Aplt. Br. 28–29. In particular,\n\nChaparral asserts that although the costs in TXO and Wood were incurred on the\n\nleased premises, “[t]he costs here were incurred off-lease.” Id. at 28.\n\n Perhaps these “facts” will ultimately be relevant to the merits question of\n\nwhether Chaparral breached the IDM. Id. Perhaps not. Either way, we fail to see how\n\nthey might be relevant to the question of whether, as a threshold matter, the class\n\nleases contain an IDM. And the chart was designed to aid the district court in\n\nanswering the latter question, not the former one. See Roderick, 725 F.3d at 1218\n\n(noting that chart could aid district court in determining whether “every class\n\nmember’s lease” contained IDM and, by extension, could help district court\n\ndetermine whether plaintiff satisfied Rule 23(a)(2)’s commonality requirement).\n\n Here, Chaparral offers no further explanation regarding the relevance of these\n\n“facts” vis-à-vis the district court’s Rule 23 inquiry. Aplt. Br. 28; see also Amgen\n\nInc. v. Conn. Ret. Plans & Tr. Funds, 568 U.S. 455, 466 (2013) (“Rule 23 grants\n\ncourts no license to engage in free-ranging merits inquiries at the certification stage.\n\nMerits questions may be considered to the extent—but only to the extent—that they\n\nare relevant to determining whether the Rule 23 prerequisites for class certification\n\nare satisfied.”). Further, Chaparral’s position that all “[t]he costs here were incurred\n\noff-lease” would tend to support the district court’s rulings on predominance and\n\n 30\n\fcommonality, not undermine them. Id. at 28; see also Tyson Foods, Inc., 136 S. Ct. at\n\n1045; Wal–Mart Stores, Inc., 564 U.S. at 350. Accordingly, we decline to hold that\n\nthe district court abused its discretion by relying on Naylor Farms’ chart after\n\n“confirm[ing] that” the chart was “generally accurate.” App. vol. 5, 1147.\n\n Chaparral’s remaining arguments about lease language rest on its assertions\n\nthat (1) the leases at issue contain multiple royalty provisions and (2) the interplay\n\nbetween these royalty provisions renders the leases ambiguous. According to\n\nChaparral, this ambiguity would entitle Chaparral to present individualized extrinsic\n\nevidence of “the intent of the parties and the meaning of the leases” at trial, including\n\n“exhibits [and] interlineations” to each individual lease, as well as evidence about\n\nindustry customs in effect “when the various leases were executed.” Aplt. Br. 33–36.\n\n But as Naylor Farms points out, Chaparral didn’t advance this specific\n\nextrinsic-evidence argument below as a basis for denying Naylor Farms’ motion to\n\ncertify the class. Instead, Chaparral merely asserted that, as a general matter,\n\n“differences in royalty obligations” and lease language defeat commonality and\n\npredominance.15 App. vol. 2, 411. Critically, our “rule against considering new\n\narguments on appeal applies equally when ‘a litigant changes to a new theory on\n\nappeal that falls under the same general category as an argument presented at trial.’”\n\n\n 15\n In its reply brief, Chaparral asserts for the first time that it raised an\nextrinsic-evidence argument in its response to Naylor Farms’ motion for summary\njudgment. We agree that Chaparral’s response to Naylor Farms’ summary-judgment\nmotion refers to what might be classified as extrinsic evidence. But we see no\nargument there that the need to examine such evidence precludes certification. Nor\ndo we see any indication that the district court ever ruled on such an argument.\n 31\n\fUnited States v. Nelson, 868 F.3d 885, 891 n.4 (10th Cir. 2017) (quoting Lyons v.\n\nJefferson Bank & Tr., 994 F.2d 716, 722 (10th Cir. 1993)). Further, Chaparral fails to\n\nargue for plain error on appeal. Accordingly, it has waived its extrinsic-evidence\n\nargument. See Richison, 634 F.3d at 1131.\n\n Alternatively, even assuming Chaparral preserved its extrinsic-evidence\n\nargument below, it fails to adequately brief this argument on appeal. This is so\n\nbecause Chaparral fails to identify any specific extrinsic evidence—in the form of an\n\nexhibit, interlineation, or industry custom—that might allow a jury to conclude that\n\nChaparral breached the IDM as to one lease but not another. See Fed. R. App. P.\n\n28(a)(8)(A) (requiring argument section of appellant’s brief to contain “appellant’s\n\ncontentions and the reasons for them, with citations to the authorities and parts of the\n\nrecord on which the appellant relies”); Bronson v. Swensen, 500 F.3d 1099, 1104\n\n(10th Cir. 2007) (explaining that we routinely decline to consider inadequately\n\nbriefed arguments). Accordingly, even assuming the district court erred, we see no\n\nbasis upon which to conclude the district court’s error prejudiced Chaparral. See\n\nShinseki v. Sanders, 556 U.S. 396, 410 (2009) (explaining that “the party seeking\n\nreversal normally must explain why the erroneous ruling caused harm”). Thus, we\n\ndecline to reverse on this basis. And for the same reasons, we likewise decline to\n\nreverse based on Chaparral’s assertion that even in the absence of any ambiguity in\n\nthe leases, a jury will be required to consider industry customs in effect “when the\n\nvarious leases were executed” to determine whether Chaparral breached the terms of\n\n\n\n 32\n\feach individual lease. Aplt. Br. 36. Again, Chaparral neither identifies any particular\n\ncustoms nor explains their legal relevance.\n\n In its final lease-language argument, Chaparral asserts that individual\n\nvariations in its agreements with midstream processing companies, rather than in its\n\nagreements with Naylor Farms and other royalty owners, defeat commonality and\n\npredominance. In support, Chaparral says Naylor Farms’ underlying legal theory is\n\nthat Chaparral committed fraud by using wellhead sales contracts to circumvent\n\nOklahoma law. And to evaluate this theory, Chaparral contends, a jury will have to\n\nconduct an individualized inquiry to determine whether Chaparral entered into each\n\nof those wellhead sales contracts in good faith.\n\n But this argument overlooks the fact that the district court declined to certify\n\nNaylor Farms’ fraud claim. And Chaparral cites no authority indicating that whether\n\nit entered into the wellhead sales contracts in good faith is dispositive of, or even\n\nrelevant to, the claims the district court did certify. Accordingly, we find this\n\nargument inadequately briefed and decline to consider it as well. See Fed. R. App. P.\n\n28(a)(8)(A); Bronson, 500 F.3d at 1104. And we further conclude that Chaparral\n\ntherefore fails to demonstrate the district court abused its discretion in certifying the\n\nclass despite minor variations in lease language.\n\nIII. Uniform Payment Methodology\n\n As a final matter, Chaparral asserts Naylor Farms failed to demonstrate that\n\nChaparral uses a uniform payment methodology to calculate royalty payments and\n\n\n\n 33\n\fthat this “lack of a common payment methodology defeats class certification.” Aplt.\n\nBr. 39.\n\n We have indeed explained that the existence of a uniform payment\n\nmethodology, standing alone, isn’t sufficient to establish predominance. See\n\nRoderick, 725 F.3d at 1220. But contrary to Chaparral’s assertion, we see nothing in\n\nRoderick that indicates the existence of such a methodology is necessary to\n\naccomplish this task. Accordingly, we reject this argument. And to the extent\n\nChaparral instead means to suggest that individual questions about damages defeat\n\npredominance, we do not agree. “The fact that damages may have to be ascertained\n\non an individual basis is not, standing alone, sufficient to defeat class certification.”\n\nMenocal, 882 F.3d at 922 (quoting Roderick, 725 F.3d at 1220)). Instead, “material\n\ndifferences in damages determinations” will only destroy predominance if those\n\n“individualized issues will overwhelm . . . questions common to the class.” Roderick,\n\n725 F.3d at 1220.\n\n We see no indication that will occur here. On the contrary, as the district court\n\npointed out, Naylor Farms “provided evidence that [its] expert can determine\n\ndamages on a class[]wide basis through use of a model,” thus obviating the need for\n\nindividualized evidence. App. vol. 5, 1155; see also Tyson Foods, Inc., 136 S. Ct. at\n\n1045. And Chaparral fails to explain why that model is inaccurate or unworkable.\n\nFurther, the district court correctly noted that if necessary, it can later divide the class\n\ninto subclasses for purposes of determining damages. See Fed. R. Civ. P. 23(c)(1)(C),\n\n(c)(5); Roderick, 725 F.3d 1213. Thus, the district court didn’t abuse its discretion in\n\n 34\n\fruling that individual questions about damages don’t defeat predominance. See\n\nRoderick, 725 F.3d 1213 (“[T]he district court is in the best position to evaluate the\n\npractical difficulties which inhere in the class action format, and is especially suited\n\nto tailor the proceedings accordingly.”).\n\n Conclusion\n\n For the reasons discussed above, we conclude that Chaparral fails to\n\ndemonstrate the district court’s decision to certify the class falls outside “the bounds\n\nof rationally available choices given the facts and law involved in the matter at\n\nhand.” CGC Holding Co., 773 F.3d at 1086 (quoting Vallario, 554 F.3d at 1264). We\n\ntherefore affirm the district court’s order.\n\n\n\n\n 35\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: NAYLOR FARMS, INC. ; Harrel's LLC, Plaintiffs-Appellees, v. CHAPARRAL ENERGY, LLC, Defendant-Appellant, Black Stone Minerals Company, L.P., Amicus Curiae.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 3, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n NAYLOR FARMS, INC.; HARREL’S\\n LLC,\\n\\n Plaintiffs - Appellees,\\n\\n v. No. 17-6146\\n\\n CHAPARRAL ENERGY, LLC,\\n\\n Defendant – Appellant,\\n\\n _____________________\\n\\n BLACK STONE MINERALS\\n COMPANY, L.P.,\\n\\n Amicus Curiae.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the Western District of Oklahoma\\n (D.C. No. 5:11-CV-00634-HE)\\n _________________________________\\n\\nAnthony J. Shaheen, Holland & Hart LLP, Denver, Colorado (Christopher A. Chrisman\\nand Jessica M. Schmidt, Holland & Hart LLP, Denver, Colorado; Linda J. Byford,\\nChaparral Energy, LLC, Oklahoma City, Oklahoma; John J. Griffin, Jr., Harvey D. Ellis,\\nJr., and Charles V. Knutter, Crowe & Dunlevy, Oklahoma City, Oklahoma, with him on\\nthe briefs), for Defendant-Appellant Chaparral Energy, LLC.\\n\\nConner L. Helms (Gary R. Underwood and Erin M. Moore, with him on the brief), Helms\\nUnderwood & Cook, Oklahoma City, Oklahoma, for Plaintiffs-Appellees Naylor Farms,\\nInc. and Harrel’s LLC.\\n\\fDaniel H. Charest and Warren T. Burns, Burns Charest LLP, Dallas, Texas, filed an\\namicus curiae brief for Black Stone Minerals Company, L.P. in support of Plaintiffs-\\nAppellees Naylor Farms, Inc. and Harrel’s L.L.C.\\n _________________________________\\n\\nBefore MORITZ, MURPHY, and EID, Circuit Judges.\\n _________________________________\\n\\nMORITZ, Circuit Judge.\\n _________________________________\\n\\n Defendant Chaparral Energy, L.L.C. (Chaparral) operates approximately 2,500\\n\\noil and gas wells in Oklahoma. Plaintiffs Naylor Farms, Inc. and Harrel’s, L.L.C.\\n\\n(collectively, Naylor Farms) have royalty interests in some of those wells. As a\\n\\nresult, Naylor Farms receives a portion of the proceeds those wells generate. But\\n\\naccording to Naylor Farms, Chaparral systematically underpaid Naylor Farms and\\n\\nother similarly situated royalty owners by improperly deducting from their royalty\\n\\npayments certain gas-treatment costs—costs that Naylor Farms says Chaparral was\\n\\nrequired to shoulder under Oklahoma law. Thus, Naylor Farms brought a putative\\n\\nclass-action lawsuit against Chaparral and moved to certify the class under Rule 23\\n\\nof the Federal Rules of Civil Procedure. The district court granted Naylor Farms’\\n\\nmotion to certify, and Chaparral now appeals the district court’s certification order.\\n\\nFor the reasons discussed below, we affirm.\\n\\n Background\\n\\n Under Oklahoma law, lessees like Chaparral are subject to an implied duty of\\n\\nmarketability (IDM).1 The IDM imposes upon lessees “a duty to provide a\\n\\n\\n 1\\n The parties agree that Oklahoma substantive law controls.\\n 2\\n\\fmarketable product available to market.” Mittelstaedt v. Santa Fe Minerals, Inc., 954\\n\\nP.2d 1203, 1206 (Okla. 1998). Consistent with this duty, lessees are generally\\n\\nprecluded from passing along to royalty owners any costs the lessees incur in making\\n\\na product marketable. See id. at 1208. And because “raw or unprocessed gas” must\\n\\ntypically “undergo[] certain field processes”—such as gathering, compressing,\\n\\ndehydrating, transporting, and producing (GCDTP services)—to make the gas\\n\\nmarketable, lessees generally bear the costs associated with performing such services.\\n\\nId. at 1205, 1208.\\n\\n Citing the IDM, Naylor Farms brought a putative class-action lawsuit against\\n\\nChaparral, asserting claims for breach of contract, breach of fiduciary duty, fraud,\\n\\nunjust enrichment, and failure to produce in paying quantities. As relevant here,\\n\\nNaylor Farms’ complaint alleges that Chaparral breached the IDM by improperly\\n\\ndeducting GCDTP-service costs from the royalty payments Chaparral made to Naylor\\n\\nFarms and to other similarly-situated royalty owners. More specifically, Naylor\\n\\nFarms contends that in an attempt to circumvent the IDM, Chaparral enters into\\n\\nwellhead sales contracts with midstream processing companies. Under the terms of\\n\\nthose contracts, the midstream companies acquire title or possession of unprocessed\\n\\ngas at or near the wellhead.2 Yet according to Naylor Farms, the midstream\\n\\n\\n 2\\n The contracts fall into two categories: percentage-of-proceeds (POP)\\ncontracts and percentage-of-liquids (POL) contracts. The vast majority of the\\ncontracts at issue are POP contracts. Under a POP contract, the midstream processing\\ncompany takes possession of the entire gas stream, processes the gas, sells it to a\\ndownstream purchaser, and then pays Chaparral a percentage of the resulting\\nproceeds. Under a POL contract, the midstream processing company obtains\\n 3\\n\\fcompanies don’t actually pay Chaparral for the gas at this time. Instead, the\\n\\nmidstream companies first perform certain GCDTP services and then sell the treated\\n\\ngas to downstream purchasers.\\n\\n At that point, Naylor Farms asserts, the midstream companies (1) take the\\n\\ngross proceeds they receive from the downstream sales; (2) deduct from those gross\\n\\nproceeds the costs and fees associated with performing the GCDTP services;3 and\\n\\n(3) pay Chaparral for the gas they previously acquired at the wellhead by giving\\n\\nChaparral the resulting net proceeds. Chaparral then calculates royalty payments\\n\\nbased on the net proceeds it receives from the midstream companies, rather than\\n\\ncalculating royalty payments based on the gross proceeds the midstream companies\\n\\nreceive from the downstream sales. And in doing so, Naylor Farms alleges, Chaparral\\n\\nimpermissibly “requires royalty owners to bear the costs of transforming unprocessed\\n\\ngas into a marketable product,” thus violating the IDM. Id. at 13.\\n\\n Based on this theory of liability, Naylor Farms moved to certify a class\\n\\ncomprising it and other similarly situated royalty owners.4 In relevant part, Naylor\\n\\n\\n\\n(1) possession of and title to the natural gas liquids (NGLs) and (2) possession of\\n(but not title to) the residue gas at the wellhead. Chaparral retains title to the residue\\ngas, which the midstream processing company returns to Chaparral after performing\\ncertain GCDTP services. The midstream processing company then charges Chaparral\\na fee for performing the GCDTP services and also retains the NGLs.\\n 3\\n Under a POL contract, the midstream processing company charges a fee and\\nretains the NGLs.\\n 4\\n After Naylor Farms moved to certify, Chaparral filed for bankruptcy. The\\nbankruptcy court initially imposed an automatic stay on the underlying proceedings.\\nBut it then partially lifted that stay so the district court could rule on Naylor Farms’\\nmotion to certify.\\n 4\\n\\fFarms argued that certification was appropriate under Rule 23 because (1) whether\\n\\nChaparral breached the IDM is a common question, see Fed. R. Civ. P. 23(a)(2); and\\n\\n(2) this and other common questions predominate over any individual ones, see Fed.\\n\\nR. Civ. P. 23(b)(3).\\n\\n In response, Chaparral asserted that whether it breached the IDM isn’t a\\n\\ncommon question because a jury won’t be able to answer it without first assessing\\n\\n“individualized issues, including the obligation created by each” individual lease\\n\\n“and the gas produced from each” individual well. App. vol. 2, 410. Further,\\n\\nChaparral asserted, these individual questions about lease language and gas quality,\\n\\nas well as individual questions about damages, predominate over any common\\n\\nquestions Naylor Farms might identify. Thus, Chaparral argued, Naylor Farms cannot\\n\\nsatisfy Rule 23’s certification requirements.\\n\\n The district court disagreed and concluded that certification was appropriate.\\n\\nAs an initial matter, the court ruled that Naylor Farms identified at least one common\\n\\nquestion: whether Chaparral breached the IDM. The district court then rejected\\n\\nChaparral’s arguments that answering this common question will require an\\n\\nindividualized assessment of either the language that appears in each lease or the\\n\\nquality of the gas that comes from each well. Next, the district court ruled that\\n\\ncommon questions, including whether Chaparral breached the IDM, predominate\\n\\nover any individual ones. Ultimately, after addressing Rule 23’s remaining\\n\\n\\n\\n\\n 5\\n\\frequirements, the district court granted Naylor Farms’ motion to certify.5 Chaparral\\n\\nnow appeals the district court’s class-certification order.\\n\\n Analysis\\n\\n According to Chaparral, the district court erred in certifying the class under\\n\\nRule 23. In support, Chaparral advances three discrete arguments. It first asserts the\\n\\ndistrict court erred in failing to recognize that marketability constitutes an individual\\n\\nquestion—one that necessarily predominates over any common ones in this litigation.\\n\\nIt next contends the district court erred in rejecting Chaparral’s argument that\\n\\ndistinctions in lease language also give rise to individual questions, and that those\\n\\nindividual questions likewise predominate. Finally, it insists the district court erred in\\n\\nfailing to recognize that in the absence of evidence indicating Chaparral employs a\\n\\nuniform payment methodology, certification is inappropriate. We address each of\\n\\nthese arguments in turn.\\n\\nI. Marketability\\n\\n As discussed above, the cornerstone of Naylor Farms’ class-action lawsuit is\\n\\nits allegation that Chaparral breached the IDM by improperly saddling Naylor Farms\\n\\nand other similarly situated royalty owners with certain gas-treatment costs.\\n\\n The parties agree that the success of this allegation turns in large part on when\\n\\nthe gas at issue became marketable. But they disagree about whether, in assessing\\n\\nmarketability, a jury will need to individually analyze the quality of gas that each\\n\\n\\n 5\\n The district court excluded Naylor Farms’ fraud claim from the class-\\ncertification order.\\n 6\\n\\fwell produced. And by extension, they also disagree about whether the attendant need\\n\\nto conduct such an individualized assessment renders class certification\\n\\ninappropriate.\\n\\n To resolve the parties’ disagreement on this point, we begin with an overview\\n\\nof Oklahoma state law. We then discuss Rule 23’s certification requirements. Next,\\n\\nwe explain how the district court applied Rule 23 in the context of Naylor Farms’\\n\\nstate-law claims. Finally, we set forth the applicable standard of review and discuss\\n\\nwhether, considering that deferential standard, Chaparral’s marketability arguments\\n\\nrequire us to reverse the district court’s class-certification order.\\n\\n A. Oklahoma Law\\n\\n As discussed in more detail below, the ultimate issue before us in this appeal is\\n\\nwhether the district court abused its discretion in concluding that Naylor Farms\\n\\nsatisfied Rule 23’s certification requirements. See Vallario v. Vandehey, 554 F.3d\\n\\n1259, 1264 (10th Cir. 2009). And this ultimate issue presents a question of federal\\n\\nlaw. But that doesn’t doom Oklahoma law to irrelevancy. On the contrary, at the\\n\\nheart of the parties’ Rule 23 dispute lies an intermediate state-law question: When is\\n\\ngas marketable under Oklahoma law? Thus, we begin our discussion with an\\n\\noverview of that law. Cf. Wal–Mart Stores, Inc. v. Dukes, 564 U.S. 338, 351 (2011)\\n\\n(noting that Rule 23 analysis will often “overlap with the merits of the plaintiff’s\\n\\nunderlying claim”); CGC Holding Co., LLC v. Broad & Cassel, 773 F.3d 1076, 1087\\n\\n(10th Cir. 2014) (explaining that Rule 23 inquiry requires “consideration of how the\\n\\n\\n\\n 7\\n\\fclass intends to answer factual and legal questions to prove its claim” and thus “will\\n\\nfrequently entail some discussion of the claim itself”).\\n\\n To the extent we “are called upon to interpret state law” in resolving this\\n\\nappeal, we begin by “look[ing] to the rulings of [Oklahoma’s] highest state court.”\\n\\nStickley v. State Farm Mut. Auto. Ins. Co., 505 F.3d 1070, 1077 (10th Cir. 2007)\\n\\n(quoting Johnson v. Riddle, 305 F.3d 1107, 1118 (10th Cir. 2002)). It has been more\\n\\nthan two decades since the Oklahoma Supreme Court (OSC) has said anything\\n\\nmeaningful about marketability. See Mittelstaedt, 954 P.2d 1203. And neither party\\n\\nsuggests Mittelstaedt involved (or even contemplated, for that matter) the type of\\n\\nwellhead sales contracts that Chaparral allegedly utilized here. Thus, in the absence\\n\\nof any guidance from the OSC on the specific marketability questions before us in\\n\\nthis appeal, our task is “to predict how [the OSC] would rule” if it were to answer\\n\\nthose questions. Stickley, 505 F.3d at 1077 (quoting Johnson, 305 F.3d at 1118). In\\n\\nundertaking that task, we find certain aspects of Mittelstaedt relevant to, albeit not\\n\\ndispositive of, the issues before us.\\n\\n In Mittelstaedt, the OSC began by explaining that the IDM imparts upon\\n\\nlessees like Chaparral a duty “to provide a marketable product available to market.”\\n\\n954 P.2d at 1208. And as the OSC noted, “[i]t is common knowledge that raw or\\n\\nunprocessed gas” must usually undergo one or more GCDTP services to make that\\n\\ngas marketable.6 Id. Thus, because the costs of such GCDTP services are often\\n\\n\\n 6\\n In Mittelstaedt, the OSC discussed “separation, dehydration, compression,\\nand treatment” but didn’t mention gathering or transporting. 954 P.2d at 1208.\\n 8\\n\\f“associated with” making gas marketable, the OSC explained that the IDM typically\\n\\nprecludes a lessee from “deducting a proportionate share” of those costs from royalty\\n\\npayments. Id. at 1205. But the OSC then recognized that a lessee may sometimes be\\n\\nable to demonstrate that gas is “in a marketable form at the well[head].” Id. at 1208.\\n\\nIn that scenario, GCDTP services aren’t “necessary” to transform the already-\\n\\nmarketable gas into a marketable product. Id. at 1208. Yet a lessee may nevertheless\\n\\nopt to perform such services with an eye toward “enhancing” the value of the\\n\\n“already[-]marketable” gas. Id. at 1210. And when it does so, the OSC explained, the\\n\\ncost of performing such GCDTP services “may be allocated to the royalty interests”\\n\\nif the lessee can make certain additional showings. Id.\\n\\n We derive two controlling principles from Mittelstaedt. First, Mittelstaedt\\n\\nresolved that when unmarketable gas undergoes GCDTP services for the purpose of\\n\\ntransforming that unmarketable gas into a marketable product, the lessee must bear\\n\\nthe cost of the GCDTP services. Second, Mittelstaedt resolved that when marketable\\n\\ngas undergoes GCDTP services to enhance the value of gas that is already\\n\\nmarketable, the lessee may, under certain circumstances, allocate the cost of the\\n\\nGCDTP services to royalty holders.\\n\\n Yet Mittelstaedt left unresolved a whole host of other questions. The most\\n\\nobvious are these: What does the term “marketable” mean, and what factors\\n\\n\\n\\nNevertheless, because neither party identifies any legally significant distinctions\\nbetween these services, we continue to use the term “GCDTP services” when\\ndiscussing Mittelstaedt.\\n 9\\n\\fdetermine when, where, and if gas became marketable for purposes of applying\\n\\nMittelstaedt’s marketable-product rule?\\n\\n Notably, the OSC has declined at least two recent invitations to address these\\n\\nquestions. See Order Denying Certiorari, Whisenant v. Strat Land Expl. Co., No.\\n\\n115,660 (Okla. Oct. 1, 2018); Order Denying Certiorari, Pummill v. Hancock Expl.\\n\\nLLC, No. 114,703 (Okla. May 21, 2018). Further, the OSC declined one of these\\n\\ninvitations over the dissenting voices of two of its own members. See Dissent from\\n\\nOrder Denying Certiorari, Pummill, No. 114,703 (May 21, 2018) (Winchester, J.)\\n\\n(noting that OSC “should grant certiorari to refine what constitutes a ‘marketable\\n\\nproduct’ as that term is used in [Mittelstaedt]”).\\n\\n Nevertheless, the Oklahoma Court of Civil Appeals (OCOCA) has attempted\\n\\nto fill the resulting legal vacuum, albeit with somewhat inconsistent outcomes. See\\n\\nWhisenant v. Strat Land Expl. Co., 429 P.3d 703, 707, 708–10 (Okla. Civ. App.\\n\\n2018) (recognizing that term “marketable product” isn’t susceptible to and has no\\n\\nuniform definition, but then implicitly suggesting marketability always turns, at least\\n\\nin part, on individual characteristics of gas at issue); Pummill v. Hancock Expl. LLC,\\n\\n419 P.3d 1268, 1278 (Oka. Civ. App. 2018) (indicating that in some cases, it may be\\n\\npossible to answer marketability question based on characteristics of relevant market,\\n\\nthus rendering individualized gas-quality assessment unnecessary).\\n\\n In Whisenant, for instance, the OCOCA held that the state trial court erred\\n\\nwhen, in proceeding under Okla. Stat. Ann. tit. 12, § 2023(B)(3), it certified a class\\n\\nof Oklahoma royalty owners who brought claims similar to those Naylor Farms\\n\\n 10\\n\\fadvances here.7 See 429 P.3d at 706–07. Specifically, those royalty owners alleged\\n\\nthat the defendant, who operated several Oklahoma gas wells, breached the IDM by\\n\\ncalculating “royalties based on what it received from” a midstream processing\\n\\ncompany, “rather than based on what” that midstream processing company “received\\n\\nfor the gas at the interstate (or intrastate) pipeline inlet.” Id. at 706.\\n\\n In reversing the district court’s certification order, the Whisenant court\\n\\ninitially expressed its view that the OSC has, “for good reasons,” declined to “define\\n\\nthe meaning of ‘marketable product,’” opting instead to leave the marketability\\n\\nquestion “open to resolution on a case-by-case basis.” Whisenant 429 P.3d at 708\\n\\n(quoting Mittelstaedt, 954 P.2d at 1208). Nevertheless, immediately after suggesting\\n\\nthat the concept of marketability isn’t susceptible to any uniform definition or test,\\n\\nthe Whisenant court indicated that the answer to the marketability question will\\n\\nalways turn, at least in part, on “the quality of [the] gas” at issue. Id. at 710–12. Thus,\\n\\nthe Whisenant court reasoned, a “highly individualized and fact-intensive review of\\n\\neach [class member’s] claim,” as informed by the quality of the gas at each\\n\\nindividual well, “would be necessary to determine if” the defendant in that case\\n\\nbreached the IDM. Id. at 707, 709–10 (quoting Strack v. Cont’l Res., Inc., 405 P.3d\\n\\n131, 140 (Okla. Ct. Civ. App. 2017)).\\n\\n In Pummill, on the other hand, a different panel of the OCOCA indicated that,\\n\\nin some circumstances, it may be possible to determine whether gas is marketable\\n\\n\\n 7\\n Section 2023(B)(3) is Rule 23(b)(3)’s state-law counterpart. See Whisenant,\\n429 P.3d at 706.\\n 11\\n\\fwithout undertaking such a gas-quality assessment. In that case, the state trial court\\n\\nruled that the gas at issue wasn’t marketable “at or near the wellhead” and that\\n\\ninstead the gas only became marketable once it “reache[d] the tailgate of” a\\n\\nmidstream processing plant—i.e., once the midstream processing company completed\\n\\ncertain GCDTP services. Pummill, 419 P.3d at 1271, 1276–78.\\n\\n In reaching that conclusion, the trial court focused not on a qualitative analysis\\n\\nof the gas itself, but on evidence about “the market in which” the defendants (there,\\n\\nthe well operator and multiple lessees) “chose[] to participate.” Id. at 1270–71, 1278.\\n\\nIn particular, although the gas at issue was physically transferred to the midstream\\n\\nprocessing company near the wellhead, the trial court concluded that the well\\n\\noperator was “not in the wellhead market.” Id. at 1271, 1278. Instead, the trial court\\n\\nreasoned, no “actual sale” occurred until the gas was “acceptable for transport in”\\n\\nand capable of being “transferred into” high-pressure pipelines. Id. at 1278. Thus, the\\n\\ntrial court deduced, the well operator was in the high-pressure pipeline market. And\\n\\nbecause the gas wasn’t capable of being sold on the high-pressure pipeline market\\n\\nuntil it was “compressed, treated, dehydrated, separated, and processed,” the trial\\n\\ncourt ruled the gas wasn’t marketable until it underwent those services. Id.\\n\\n The Pummill court affirmed. Id. at 1280. In doing so, it expressly endorsed the\\n\\ntrial court’s method of “focus[ing] on” when the gas at issue was first capable of\\n\\nbeing sold on “the market in which” the well operator “chose[] to participate”—there,\\n\\nthe high-pressure pipeline market. Id. at 1278. And because the gas at issue wasn’t\\n\\ncapable of being sold on the high-pressure pipeline market until GCDTP services\\n\\n 12\\n\\frendered the gas “acceptable for transport in high-pressure pipelines,” the OCOCA\\n\\nagreed the gas wasn’t marketable until that point. Id. Thus, the OCOCA held, the\\n\\nIDM precluded the defendants from passing on to royalty owners the costs associated\\n\\nwith performing those GCTDP services. Id. at 1280.\\n\\n Notably, en route to affirming the trial court’s ruling, the OCOCA declined to\\n\\nadopt Kansas’s rule that gas is marketable once it is “acceptable to a purchaser in a\\n\\ngood[-]faith transaction.” Id. at 1276 (quoting Fawcett v. Oil Producers, Inc., 352\\n\\nP.3d 1032, 1034 (Kan. Ct. App. 2015)). And the OCOCA likewise rejected the\\n\\ndefendants’ related argument that “raw or minimally processed gas” becomes\\n\\nmarketable as soon as a “limited group of potential purchasers” is willing to\\n\\n“purchase” that gas “for further processing and sale downstream.” Id. at 1277; see\\n\\nalso id. at 1278 (explaining that “[e]vidence of hypothetical sales of raw product to a\\n\\nlimited group of potential purchasers to whom such gas would be acceptable[] does\\n\\nnot readily lend itself to a conclusion that the product being sold is ‘marketable’ in a\\n\\nfree and competitive market”). Instead, the Pummill court reasoned, gas becomes\\n\\nmarketable when it’s subject to an “actual sale.” Id. at 1278 (explaining that this\\n\\nconclusion is “consistent with” OSC precedent describing “market value” of gas “as\\n\\nbeing based on what [gas] will sell for, between a willing buyer and seller, in ‘a free\\n\\nand open market’” (quoting Howell v. Texaco Inc., 112 P.3d 1154, 1159 (Okla.\\n\\n2004))).\\n\\n The OCOCA’s 2018 decisions in Pummill and Whisenant illustrate what has\\n\\nlong been clear: although “it is easy to articulate [Mittelstaedt’s] marketable-product\\n\\n 13\\n\\frule, application of it to a particular circumstance is difficult.” Foster v. Apache\\n\\nCorp., 285 F.R.D. 632, 638 & n.14 (W.D. Okla. 2012). And for reasons we turn to\\n\\nnext, “[d]oing so in the class action context”—as the district court was required to\\n\\ndo here—is more difficult still. Id. at 638.\\n\\n B. Rule 23’s Certification Requirements\\n\\n Rule 23 sets forth the requirements for class certification.8 See Wal–Mart\\n\\nStores, Inc., 564 U.S. at 345. Only two of those requirements are at issue here: Rule\\n\\n23(a)(2)’s commonality requirement and Rule 23(b)(3)’s predominance requirement.9\\n\\nA plaintiff seeking class certification satisfies Rule 23(a)(2)’s commonality\\n\\nrequirement by demonstrating that “there are questions of law or fact common to the\\n\\nclass.” Fed. R. Civ. P. 23(a)(2). A plaintiff satisfies Rule 23(b)(3)’s related\\n\\npredominance requirement by showing that “questions of law or fact common to\\n\\nclass members predominate over any questions affecting only individual members.”\\n\\nFed. R. Civ. P. 23(b)(3).\\n\\n\\n 8\\n Rule 23’s requirements inform our analysis of each of the three discrete\\narguments Chaparral presents on appeal. See infra Sections II, III.\\n 9\\n Chaparral asserts that “Rule 23 includes an ‘implied requirement of\\nascertainability’” and that Naylor Farms cannot satisfy this “implied requirement”\\nhere. Aplt. Br. 14 (quoting Brecher v. Republic of Argentina, 806 F.3d 22, 24 (2d Cir.\\n2015)). But Chaparral fails to “cite the precise references in the record where” this\\nascertainability argument “was raised and ruled on” below. 10th Cir. Rule 28.1(A).\\nAnd it also fails to make a case for plain error on appeal. Accordingly, we decline to\\naddress this argument. See Richison v. Ernest Grp., Inc., 634 F.3d 1123, 1131 (10th\\nCir. 2011); Harolds Stores, Inc. v. Dillard Dep’t Stores, Inc., 82 F.3d 1533, 1540 n.3\\n(10th Cir. 1996). Likewise, although Chaparral makes passing reference to Rule\\n23(a)(3)’s typicality requirement, see Aplt. Br. 23, 33, we find these “stray\\nsentences” insufficient to adequately brief any argument on this point. Eizember v.\\nTrammell, 803 F.3d 1129, 1141 (10th Cir. 2015).\\n 14\\n\\f Rule 23(a)(2)’s commonality requirement “is easy to misread.” Wal–Mart\\n\\nStores, Inc., 564 U.S. at 349. It requires a plaintiff to do more than merely identify “a\\n\\ncommon contention”; instead, that “common contention . . . must be of such a nature\\n\\nthat it is capable of classwide resolution—which means that determination of its truth\\n\\nor falsity will resolve an issue that is central to the validity of each one of the claims\\n\\nin one stroke.” Id. at 350. In other words, the focus of Rule 23(a)(2)’s commonality\\n\\nrequirement is not so much on whether there exist common questions, but rather on\\n\\n“the capacity of a classwide proceeding to generate common answers apt to drive the\\n\\nresolution of the litigation.” Id. at 350 (quoting Richard A. Nagareda, Class\\n\\nCertification in the Age of Aggregate Proof, 84 N.Y.U. L. Rev. 97, 132 (2009)).\\n\\n Rule 23(b)(3)’s predominance requirement is related to, albeit “more\\n\\ndemanding than,” Rule 23(a)(2)’s commonality requirement. Comcast Corp. v.\\n\\nBehrend, 569 U.S. 27, 34 (2013). To satisfy Rule 23(b)(3), a plaintiff must “show\\n\\nthat common questions subject to generalized, classwide proof predominate over\\n\\nindividual questions.” CGC Holding Co., 773 F.3d at 1087; see also Tyson Foods,\\n\\nInc. v. Bouaphakeo, 136 S. Ct. 1036, 1045 (2016) (“An individual question is one\\n\\nwhere ‘members of a proposed class will need to present evidence that varies from\\n\\nmember to member,’ while a common question is one where ‘the same evidence will\\n\\nsuffice for each member to make a prima facie showing [or] the issue is susceptible\\n\\nto generalized, class[]wide proof.’” (alteration in original) (quoting 2 William B.\\n\\nRubenstein et al., Newberg on Class Actions § 4:50 (5th ed. 2012))).\\n\\n\\n\\n 15\\n\\f Notably, this doesn’t mean a plaintiff must show “that all of the elements of\\n\\nthe claim entail questions of fact and law that are common to the class” or “that the\\n\\nanswers to those common questions [are] dispositive” of the claim. CGC Holding\\n\\nCo., 773 F.3d at 1087. Instead, the predominance inquiry “asks whether the common,\\n\\naggregation-enabling[] issues in the case are more prevalent or important than the\\n\\nnon-common, aggregation-defeating, individual issues.” Id. (quoting Newberg on\\n\\nClass Actions § 4:49). Thus, to determine whether a plaintiff can satisfy Rule\\n\\n23(b)(3)’s predominance requirement, a court must first “characterize the issues in\\n\\nthe case as common or not, and then weigh which issues predominate.” Id. (quoting\\n\\nNewberg on Class Actions § 4:50). Critically, so long as at least one common issue\\n\\npredominates, a plaintiff can satisfy Rule 23(b)(3)—even if there remain individual\\n\\nissues, such as damages, that must be tried separately. Tyson Foods, Inc., 136 S. Ct.\\n\\nat 1045.\\n\\n Having reviewed the relevant Rule 23 requirements and examined Oklahoma’s\\n\\ntreatment of the marketability question, we next explain how the district court treated\\n\\nthe interplay between the former and the latter in ruling on Naylor Farms’ motion to\\n\\ncertify.\\n\\n C. The District Court’s Ruling\\n\\n The district court found that Naylor Farms successfully identified at least one\\n\\ncommon question: whether Chaparral breached the IDM.10 And the court then ruled\\n\\n\\n 10\\n Chaparral contends the district court erred in concluding that the threshold\\nissue of whether each lease contains an IDM is “in and of itself” a common question.\\n 16\\n\\fthat this common question predominates over any individual ones.\\n\\n Critically, in doing so, the district court first narrowed the class to include only\\n\\nthose royalty owners whose leases contain clauses that are similar to the royalty\\n\\nclauses (collectively, Mittelstaedt Clauses) the OSC considered in three cases:\\n\\n(1) Mittelstaedt, (2) TXO Production Corp. v. State ex rel. Commissioners of Land\\n\\nOffice, 903 P.2d 259 (Okla. 1995), and (3) Wood v. TXO Production Corp., 854 P.2d\\n\\n880 (Okla. 1993). Because the OSC has held that the language of these Mittelstaedt\\n\\nClauses “does not negate the IDM” and “is consistent with the marketable[-]product\\n\\nrule,” the district court reasoned that—contrary to Chaparral’s arguments—any\\n\\nremaining “variations in lease language” do not defeat commonality or\\n\\npredominance. App. vol. 5, 1148, 1153.\\n\\n Next, the district court rejected Chaparral’s argument that in order to\\n\\ndetermine whether Chaparral breached the IDM, a jury will have to engage in an\\n\\n\\nAplt. Br. 11. As an initial matter, we disagree with the premise of this argument; at\\nmost, it appears the district court treated the existence of the IDM “and its alleged\\nbreach” as a compound common question. App. vol. 5, 1154 (emphasis added).\\n\\n In any event, even assuming the district court treated the existence of the IDM\\nas a standalone common question and even assuming it erred in doing so, the error\\nwas harmless; the district court correctly concluded that whether Chaparral breached\\nthe IDM is a common question. See Wal–Mart Stores, Inc., 564 U.S. at 350\\n(explaining that question is common for purposes of Rule 23(a)(2) if its answer “will\\nresolve an issue that is central to the validity of each one of the claims in one\\nstroke”); cf. Menocal v. GEO Grp., Inc., 882 F.3d 905, 916–17 (10th Cir.) (holding\\nthat question of whether defendant’s policy violated federal statute constituted\\ncommon question), cert. denied, 139 S. Ct. 143 (2018). Chaparral doesn’t seriously\\nargue otherwise. And when it comes to satisfying Rule 23(a)(2)’s commonality\\nrequirement, the existence of this single common question “will do.” Wal–Mart\\nStores, Inc., 564 U.S. at 359.\\n 17\\n\\findividualized “well-by-well analysis” to determine when the gas from each well\\n\\nbecame marketable. Id. at 1149. In rejecting this argument, the district court\\n\\nacknowledged that gas quality might vary from well to well and that, as a result,\\n\\nsome gas might require more or different GCTDP services to become marketable\\n\\nthan other gas. But the district court explained that in order to determine whether\\n\\nChaparral breached the IDM, an individualized gas-quality analysis is nevertheless\\n\\n“unnecessary” in this case because, as Naylor Farms demonstrated, all the gas at\\n\\nissue “require[d]” at least one GCDTP service “to become marketable.” Id. at 1149,\\n\\n1151, 1157.\\n\\n Thus, the district court appeared to recognize, differences in the precise\\n\\nnumber and nature of GCDTP services required to make the gas from each well\\n\\nmarketable are relevant only to the post-breach question of damages. And because\\n\\nNaylor Farms “provided evidence that [its] expert can determine damages on a\\n\\nclass[]wide basis through use of a model,” the district court ruled these distinctions\\n\\ndon’t defeat predominance. Id. at 1155. Alternatively, the district court pointed out\\n\\nthat if necessary, it can divide the class into subclasses at a later date for purposes of\\n\\ndetermining damages. See Fed. R. Civ. P. 23(c)(1)(C) (“An order that grants or\\n\\ndenies class certification may be altered or amended before final judgment.”), (c)(5)\\n\\n(“When appropriate, a class may be divided into subclasses that are each treated as a\\n\\nclass under this rule.”). Accordingly, the district granted Naylor Farms’ motion to\\n\\ncertify.\\n\\n\\n\\n 18\\n\\f D. Our Standard of Review\\n\\n Our review of the district court’s decision is highly deferential. So long as the\\n\\ndistrict court “applied the proper standard in deciding whether to certify [the] class,\\n\\nwe may reverse that decision only for abuse of discretion.” CGC Holding Co., 773\\n\\nF.3d at 1085 (quoting Adamson v. Bowen, 855 F.2d 668, 675 (10th Cir. 1988)); see\\n\\nalso Vallario, 554 F.3d at 1264 (“Because class certification decisions are necessarily\\n\\ncase specific, district courts possess significant latitude in deciding whether or not to\\n\\ncertify a class.” (citation omitted)). A “district court abuses its discretion when it\\n\\nmisapplies the Rule 23 factors—either through a clearly erroneous finding of fact or\\n\\nan erroneous conclusion of law—in deciding whether class certification is\\n\\nappropriate.” CGC Holding Co., 773 F.3d at 1085–86.\\n\\n Here, Chaparral doesn’t argue that the district court failed to apply the proper\\n\\nRule 23 standard. Thus, in addressing those arguments Chaparral does make, we must\\n\\ndefer to the district court’s ruling unless Chaparral shows the district court’s\\n\\ncertification decision falls outside “the bounds of rationally available choices given\\n\\nthe facts and law involved in the matter at hand.” Id. at 1086 (quoting Vallario, 554\\n\\nF.3d at 1264). For the reasons discussed below, we conclude that Chaparral fails to\\n\\nmake this demanding showing.\\n\\n E. Chaparral’s Marketability Arguments\\n\\n Chaparral’s primary argument on appeal is that the district court abused its\\n\\ndiscretion in ruling that Naylor Farms demonstrated commonality and predominance\\n\\nbecause such a ruling is irreconcilable with Oklahoma’s approach to determining\\n\\n 19\\n\\fmarketability. Or, as Chaparral puts it, “Certifying a class of ‘Mittelstaedt Clause\\n\\n[l]eases’ is contrary to Mittelstaedt.” Aplt. Br. 16.\\n\\n Recall that, under Mittelstaedt, two things are clear. First, when unmarketable\\n\\ngas undergoes GCDTP services for purposes of transforming the unmarketable gas\\n\\ninto a marketable product, a lessee breaches the IDM by passing on to royalty owners\\n\\nthe cost of performing those GCDTP services. See Mittelstaedt, 954 P.2d at 1205.\\n\\nSecond, when marketable gas undergoes GCDTP services to enhance the value of\\n\\ngas that is already marketable, a lessee may, under certain circumstance, allocate the\\n\\ncost of those services to royalty owners without breaching the IDM. Id. at 1210.\\n\\nThus, to determine whether Chaparral breached the IDM—i.e., to answer the question\\n\\nthe district court determined was common to the class for purposes of satisfying Rule\\n\\n23(a)(2)’s commonality requirement—a jury will have to determine when the gas at\\n\\nissue became marketable.\\n\\n Here, as Chaparral points out, the district court ruled that (1) the question of\\n\\nwhen the gas became marketable can be answered via generalized, classwide proof\\n\\nand (2) as a result, the marketability question doesn’t defeat predominance. See Fed.\\n\\nR. Civ. P. 23(b)(3) (allowing for certification if common questions predominate over\\n\\nindividual ones); Tyson Foods, Inc., 136 S. Ct. at 1045 (“An individual question is\\n\\none where ‘members of a proposed class will need to present evidence that varies\\n\\nfrom member to member,’ while a common question is one where ‘the same evidence\\n\\nwill suffice for each member to make a prima facie showing [or] the issue is\\n\\n\\n\\n 20\\n\\fsusceptible to generalized, class[]wide proof.’” (first alteration in original) (quoting\\n\\nNewberg on Class Actions § 4:50)).\\n\\n But according to Chaparral, the district court’s ruling on this point rests on a\\n\\nflawed assumption. Specifically, Chaparral contends that in ruling a jury can answer\\n\\nthe marketability question without undertaking a well-by-well analysis, the district\\n\\ncourt relied on the fact that all the gas at issue actually underwent GCDTP services.\\n\\nAnd in so ruling, Chaparral argues, the district court made a legally erroneous\\n\\nassumption: it incorrectly assumed that any time gas undergoes GCDTP services, this\\n\\nproves, ipso facto, that the gas wasn’t marketable before it underwent those services.\\n\\n We agree with Chaparral that if the district court assumed GCDTP services\\n\\nfunction solely as a mechanism for transforming unmarketable gas into a marketable\\n\\nproduct, then the court committed a legal error. As Chaparral correctly points out,\\n\\nMittelstaedt expressly recognizes that sometimes even marketable gas undergoes\\n\\nGCDTP services—not to “create a marketable product” but to “transform[] an\\n\\nalready[-]marketable product into an enhanced” one. Mittelstaedt, 954 P.2d at 1209–\\n\\n10; see also id. at 1208 (acknowledging that it’s possible for gas to “be in a\\n\\nmarketable form at the well[head],” i.e., before any GCDTP services are\\n\\nperformed).11 But we disagree with Chaparral that the district court ever assumed\\n\\notherwise.\\n\\n\\n\\n 11\\n In asserting that gas can be marketable at the wellhead, Chaparral appears to\\nrely in part on its position that the gas at issue here was in fact marketable at the\\nwellhead—because (according to Chaparral) that is where Chaparral first “sold” the\\n 21\\n\\f That is, contrary to Chaparral’s argument, the district court neither ruled nor\\n\\nassumed “that gas must be unmarketable if it goes through a processing plant or\\n\\nreceives one or more of the GCDTP services.” Aplt. Br. 19. On the contrary, the\\n\\ndistrict court expressly recognized that the marketability question turns not on\\n\\nwhether the gas undergoes GCDTP services, but on whether the gas undergoes\\n\\nGCDTP services “to become marketable.” App. vol. 5, 1151. Indeed, the district\\n\\ncourt expressly relied on evidence indicating that all the gas at issue here “require[d]\\n\\nGCDTP services to be made marketable” in order to distinguish the facts of this case\\n\\nfrom those before this court in Wallace B. Roderick Revocable Living Trust v. XTO\\n\\nEnergy, Inc., 725 F.3d 1213 (10th Cir. 2013); in that case, the district court pointed\\n\\nout, some of the gas at issue “may [have been] marketable at the well.” App. vol. 5,\\n\\n1146 (emphases added) (quoting Roderick, 725 F.3d at 1217). Critically, in making\\n\\nthis distinction, the district court necessarily acknowledged both that (1) “gas may be\\n\\nmarketable at the well[head]” and (2) the performance of GCDTP services does not\\n\\nprove, ipso facto, that the gas at issue was not marketable before those services were\\n\\n\\ngas “to a [midstream processing company] in a good[-]faith transaction.” Aplt. Br.\\n20; see also id. at 18 (“Gas is in marketable condition once it can be marketed.”).\\n\\n As an initial matter, we question whether the OSC would adopt this good-\\nfaith-transaction test for marketability. See Pummill, 419 P.3d at 1278–79\\n(suggesting good-faith-transaction approach is inconsistent with controlling OSC\\nauthority). More importantly, as the district court noted below, accepting as true\\nChaparral’s blanket assertion that all the gas at issue was marketable at the wellhead\\nbecause that is where Chaparral could first “market[]” it to midstream processing\\ncompanies, Aplt. Br. 18, would serve only to “demonstrate[]” commonality, not\\n“negate[]” it, App. vol. 5, 1149; such a blanket rule would obviate the need for any\\nindividualized analysis of the gas from each well.\\n 22\\n\\fperformed. Id. (quoting Roderick, 725 F.3d at 1217). Accordingly, we reject\\n\\nChaparral’s assertion that the district court assumed otherwise.\\n\\n Alternatively, Chaparral argues that the district court erred in treating\\n\\nmarketability as a question of law. Instead, Chaparral asserts, marketability is a\\n\\nquestion of fact—one that turns, at least in part, on “gas quality.” Aplt. Br. 23. And it\\n\\nfurther insists that because the quality of its gas varies from well to well, a jury will\\n\\nbe unable to resolve the marketability question (and, by extension, the question of\\n\\nwhether Chaparral breached the IDM) without performing a well-by-well analysis to\\n\\ndetermine whether any of the gas at issue was marketable at the wellhead. Thus,\\n\\nChaparral insists, the district court abused its discretion in failing to recognize that\\n\\nmarketability defeats commonality and predominance.\\n\\n In evaluating this argument, we need not resolve whether the district court\\n\\ntreated marketability as a question of law or a question of fact. Nor must we resolve\\n\\nwhether, if the district court indeed treated marketability as a question of law, it erred\\n\\nin doing so.12 Even assuming Chaparral is correct on both points, that doesn’t\\n\\nnecessarily mean Chaparral is entitled to reversal. On the contrary, “we may affirm\\n\\non any basis supported by the record, even if it requires ruling on arguments not\\n\\nreached by the district court.” Richison, 634 F.3d at 1130. That is, we have a\\n\\n“preference for affirmance”—one that “follows from the deference we owe to the\\n\\n\\n\\n 12\\n We nevertheless note in passing that it appears Oklahoma indeed treats\\nmarketability as question of fact. See, e.g., Whisenant, 429 P.3d at 708 n.6; Pummill,\\n419 P.3d at 1274 n.9.\\n 23\\n\\fdistrict courts and the judgments they reach, many times only after years of involved\\n\\nand expensive proceedings.” Id. And “[b]ecause of the cost and risk involved anytime\\n\\nwe upset a court’s reasoned judgment, we are ready to affirm whenever the record\\n\\nallows it.” Id. Thus, to demonstrate it is entitled to reversal, Chaparral must\\n\\n“shoulder a heavy burden”: it “must come ready both to show” that the district court\\n\\nerred and “to explain why no other grounds” will allow us to affirm the district\\n\\ncourt’s decision. Id. For the reasons discussed below, we conclude that in light of the\\n\\nOCOCA’s persuasive reasoning in Pummill, Chaparral cannot shoulder the second\\n\\npart of this heavy burden here. See West v. Am. Tel. & Tel. Co., 311 U.S. 223, 237\\n\\n(1940) (explaining that decision of intermediate state appellate court “is a datum for\\n\\nascertaining state law [that] is not to be disregarded by a federal court unless it is\\n\\nconvinced by other persuasive data that the highest court of the state would decide\\n\\notherwise”).\\n\\n In Pummill, the OCOCA relied heavily on two factors in affirming the state\\n\\ntrial court’s ruling that the gas at issue wasn’t marketable before it underwent\\n\\nGCTDP services. As an initial matter, the OCOCA pointed out that the first “actual\\n\\nsale” of the gas occurred not when the defendants transferred the gas to a midstream\\n\\nprocessing company, but instead “at the ‘tailgate’ of the [processing] plants, where\\n\\n[the gas was] transferred into high-pressure lines.” 419 P.3d at 1277–78. And the\\n\\nOCOCA deduced from the location of this first “actual sale” that “the market in\\n\\nwhich” the defendants “chose[] to participate” was the pipeline market, not the\\n\\nwellhead market. Id. Second, the OCOCA noted that the gas had to undergo GCDTP\\n\\n 24\\n\\fservices to make it “acceptable for delivery” into the high-pressure pipelines. Id. at\\n\\n1277. Accordingly, the OCOCA concluded that the IDM precluded the defendants\\n\\nfrom “deduct[ing] from [the plaintiffs’] royalties the proportionate expenses\\n\\nassociated with preparing the gas for sale” to such pipelines. Id. at 1280.\\n\\n Here, Naylor Farms has presented evidence of these same two factors. More\\n\\nimportantly, it has presented classwide evidence of these same two factors. See Tyson\\n\\nFoods, Inc., 136 S. Ct. at 1045 (explaining that for purposes of Rule 23(b)(3), “a\\n\\ncommon question is one where ‘the same evidence will suffice for each member to\\n\\nmake a prima facie showing [or] the issue is susceptible to generalized, class[]wide\\n\\nproof’” (alteration in original) (quoting Newberg on Class Actions § 4:50)). First, the\\n\\nrecord contains classwide evidence indicating that Chaparral, like the defendants in\\n\\nPummill, elects to participate in the high-pressure-pipeline market: according to\\n\\nNaylor Farms’ expert, this is where Chaparral’s gas is actually “sold.” Aplt. Supp.\\n\\nApp. vol. 18, 5270; see also Pummill, 419 P.3d at 1278 (noting that pipeline market\\n\\nwas where first “actual sale” of gas occurred). Second, Naylor Farms’ expert opined\\n\\nthat, as a classwide matter, the gas at issue here—like the gas at issue in Pummill—\\n\\nwas required to undergo at least one GCDTP service before it could “reach” and be\\n\\n“sold into” the pipeline market.13 Aplt. Supp. App. vol. 18, 5270–71; see also\\n\\nPummill, 419 P.3d at 1277 (concluding that gas wasn’t marketable on pipeline market\\n\\n\\n 13\\n Notably, despite Chaparral’s insistence that a well-by-well analysis is\\nnecessary to determine when the gas became marketable, Chaparral fails to point to\\nany evidence in the record indicating that such an individualized analysis would yield\\na different conclusion.\\n 25\\n\\funtil it was “acceptable for delivery” into relevant pipelines); cf. Wood, 854 P.2d at\\n\\n882 (explaining that IDM imposes “a duty to get the product to the place of sale in\\n\\nmarketable form” (emphasis added)).\\n\\n In short, the district court’s ruling that marketability is subject to classwide\\n\\nproof under the specific facts of this case is entirely consistent with the OCOCA’s\\n\\ndecision in Pummill. Thus, Chaparral faces an uphill climb in attempting to show that\\n\\nthis particular ruling rests on an error of state law. See West, 311 U.S. at 237. In\\n\\nattempting to make that showing here, Chaparral relies heavily on the OCOCA’s\\n\\nrecent decision in Whisenant.\\n\\n In Whisenant, the OCOCA held that the state trial court erred in certifying a\\n\\nclass of Oklahoma royalty owners under Oklahoma’s analog to Rule 23, reasoning\\n\\nthat a “highly individualized and fact-intensive review of each [class member’s]\\n\\nclaim,” as informed by the quality of gas at each individual well, “would be\\n\\nnecessary to determine if” the defendant in that case breached the IDM. 429 P.3d at\\n\\n707–10 (quoting Strack, 405 P.3d at 140)). Citing Whisenant, Chaparral insists that\\n\\nunder Oklahoma law, marketability can never be susceptible to classwide proof\\n\\nbecause it will always require an individualized assessment of the gas produced by\\n\\neach well. And to the extent the district court failed to recognize as much here,\\n\\nChaparral contends, the court made a legal error and thereby abused its discretion.\\n\\nSee CGC Holding Co., 773 F.3d at 1085–86 (“The district court abuses its discretion\\n\\nwhen it misapplies the Rule 23 factors—either through a clearly erroneous finding of\\n\\n\\n\\n 26\\n\\ffact or an erroneous conclusion of law—in deciding whether class certification is\\n\\nappropriate.”).\\n\\n In light of Whisenant’s similar procedural posture, Chaparral’s argument isn’t\\n\\nwithout appeal. But because that argument overlooks a critical aspect of Whisenant’s\\n\\nanalysis, we ultimately reject it. That is, the Whisenant court did hold that, in that\\n\\nparticular case, “determinations of the quality of gas and other facts pertinent to each\\n\\nwell” weren’t “susceptible to generalized proof.” 429 P.3d at 710. But the Whisenant\\n\\ncourt also expressly eschewed the type of rigid, one-size-fits-all approach to\\n\\nmarketability that Chaparral asks us to endorse here. Specifically, the Whisenant\\n\\ncourt recognized that the OSC has declined to adopt a uniform test for determining\\n\\nwhen gas becomes marketable, and that the OSC has instead “left the issue open to\\n\\nresolution on a case-by-case basis.” 429 P.3d at 708. And in recognizing as much, the\\n\\nWhisenant court necessarily “left . . . open” the possibility that, in some cases, a\\n\\nfactfinder may be able to determine when gas became marketable without\\n\\nundertaking an individualized inquiry into the quality of that gas. Id.\\n\\n Critically, the facts in Pummill (and, by extension, the facts in this case) fit\\n\\ncomfortably in the space “left . . . open” by Whisenant. Id. Thus, despite any tension\\n\\nthat might exist between Pummill and Whisenant, we rely on both—and “disregard[]”\\n\\nneither—in predicting how the OSC would answer the marketability question before\\n\\nus in this appeal. West, 311 U.S. at 237. And in light of Pummill and Whisenant, we\\n\\npredict the OSC would answer that question by holding that, under the facts of this\\n\\ncase, a jury could determine when the gas at issue became marketable without\\n\\n 27\\n\\findividually assessing the quality of that gas; instead, a jury could make this\\n\\ndetermination based solely on expert testimony that all the gas at issue was required\\n\\nto undergo at least one GCDTP service before it could “reach” and be “sold into” the\\n\\npipeline market. Aplt. Supp. App. vol. 18, 5270–71. See Whisenant, 429 P.3d at 708\\n\\n(opining that OSC has intentionally and wisely “left the issue [of marketability] open\\n\\nto resolution on a case-by-case basis”); Pummill, 419 P.3d at 1273, 1278 (indicating\\n\\nthat in some cases, it may be possible to answer marketability question based on\\n\\ncharacteristics of relevant market, thus rendering individualized gas-quality\\n\\nassessment unnecessary). Accordingly, the district court didn’t abuse its discretion by\\n\\nconcluding that the marketability question in this particular case is subject to\\n\\ncommon, classwide proof for purposes of satisfying Rule 23’s commonality and\\n\\npredominance requirements. See Tyson Foods, Inc., 136 S. Ct. at 1045; CGC Holding\\n\\nCo., 773 F.3d at 1086; Richison, 634 F.3d at 1130.\\n\\nII. Lease Language\\n\\n Next, Chaparral asserts that even if gas-quality variations don’t pose a bar to\\n\\ncertification, lease-language variations do. Specifically, Chaparral asserts that “[a]t\\n\\ntrial, every one of the contracts will have to be considered individually, defeating\\n\\ncommonality and predominance.” Aplt. Br. 27–28. But the district court concluded\\n\\notherwise, ruling that its decision to limit the class to leases containing a Mittelstaedt\\n\\nClause renders such an individualized analysis unnecessary.14\\n\\n\\n 14\\n Naylor Farms asserts we should take judicial notice of certain briefing in\\nMittelstaedt because, according to Naylor Farms, that briefing sheds additional light\\n 28\\n\\f In challenging this conclusion, Chaparral first asserts the district court\\n\\nabdicated its duty to determine which leases actually contain a Mittelstaedt Clause\\n\\nand instead merely “satisfied itself with [Naylor Farms’] contentions” that this is so.\\n\\nId. at 28. We disagree. As the district court noted, Naylor Farms prepared a chart that\\n\\n“categorized” the leases at issue “by royalty[-]clause language.” App. vol. 5, 1143.\\n\\nAnd we have previously indicated that this is precisely what a plaintiff should do to\\n\\nestablish commonality under these circumstances. See Roderick, 725 F.3d at 1219.\\n\\n Like Naylor Farms, the plaintiffs in Roderick asserted that each class\\n\\nmember’s lease contained an IDM. Id. at 1218. But neither the plaintiffs nor the\\n\\ndistrict court bothered to examine all the leases to verify this assertion. Id. at 1219.\\n\\nThus, this court recommended that on remand, the plaintiffs should consider\\n\\n“creat[ing] a chart classifying lease types.” Id. And if they did so, this court opined,\\n\\n“the district court could” rely on that chart to “decide that no lease type negates the\\n\\nIDM.” Id.\\n\\n Here, Naylor Farms created such a chart. And contrary to Chaparral’s\\n\\nassertions, the district court independently “confirmed that” the chart was “generally\\n\\naccurate.” App. vol. 5, 1147. Notably, Chaparral doesn’t provide us with any\\n\\ninformation that might call into question the district court’s assessment of the chart’s\\n\\naccuracy. Instead, Chaparral merely asserts that because there exist distinctions\\n\\n\\non the lease language at issue in Mittelstaedt as well as the arguments the parties\\nmade about that language. Because we conclude we may resolve Chaparral’s lease-\\nlanguage arguments without this additional information, we deny Naylor Farms’\\nmotion to take judicial notice.\\n 29\\n\\fbetween the facts in this case and the facts in TXO, 903 P.2d 259, and Wood, 854\\n\\nP.2d 880—each of which involved a Mittelstaedt Clause—“the district court could\\n\\nnot” rely on these two cases to “determine as a matter of law whether” Chaparral\\n\\ncould “share[]” certain costs with royalty owners. Aplt. Br. 28–29. In particular,\\n\\nChaparral asserts that although the costs in TXO and Wood were incurred on the\\n\\nleased premises, “[t]he costs here were incurred off-lease.” Id. at 28.\\n\\n Perhaps these “facts” will ultimately be relevant to the merits question of\\n\\nwhether Chaparral breached the IDM. Id. Perhaps not. Either way, we fail to see how\\n\\nthey might be relevant to the question of whether, as a threshold matter, the class\\n\\nleases contain an IDM. And the chart was designed to aid the district court in\\n\\nanswering the latter question, not the former one. See Roderick, 725 F.3d at 1218\\n\\n(noting that chart could aid district court in determining whether “every class\\n\\nmember’s lease” contained IDM and, by extension, could help district court\\n\\ndetermine whether plaintiff satisfied Rule 23(a)(2)’s commonality requirement).\\n\\n Here, Chaparral offers no further explanation regarding the relevance of these\\n\\n“facts” vis-à-vis the district court’s Rule 23 inquiry. Aplt. Br. 28; see also Amgen\\n\\nInc. v. Conn. Ret. Plans & Tr. Funds, 568 U.S. 455, 466 (2013) (“Rule 23 grants\\n\\ncourts no license to engage in free-ranging merits inquiries at the certification stage.\\n\\nMerits questions may be considered to the extent—but only to the extent—that they\\n\\nare relevant to determining whether the Rule 23 prerequisites for class certification\\n\\nare satisfied.”). Further, Chaparral’s position that all “[t]he costs here were incurred\\n\\noff-lease” would tend to support the district court’s rulings on predominance and\\n\\n 30\\n\\fcommonality, not undermine them. Id. at 28; see also Tyson Foods, Inc., 136 S. Ct. at\\n\\n1045; Wal–Mart Stores, Inc., 564 U.S. at 350. Accordingly, we decline to hold that\\n\\nthe district court abused its discretion by relying on Naylor Farms’ chart after\\n\\n“confirm[ing] that” the chart was “generally accurate.” App. vol. 5, 1147.\\n\\n Chaparral’s remaining arguments about lease language rest on its assertions\\n\\nthat (1) the leases at issue contain multiple royalty provisions and (2) the interplay\\n\\nbetween these royalty provisions renders the leases ambiguous. According to\\n\\nChaparral, this ambiguity would entitle Chaparral to present individualized extrinsic\\n\\nevidence of “the intent of the parties and the meaning of the leases” at trial, including\\n\\n“exhibits [and] interlineations” to each individual lease, as well as evidence about\\n\\nindustry customs in effect “when the various leases were executed.” Aplt. Br. 33–36.\\n\\n But as Naylor Farms points out, Chaparral didn’t advance this specific\\n\\nextrinsic-evidence argument below as a basis for denying Naylor Farms’ motion to\\n\\ncertify the class. Instead, Chaparral merely asserted that, as a general matter,\\n\\n“differences in royalty obligations” and lease language defeat commonality and\\n\\npredominance.15 App. vol. 2, 411. Critically, our “rule against considering new\\n\\narguments on appeal applies equally when ‘a litigant changes to a new theory on\\n\\nappeal that falls under the same general category as an argument presented at trial.’”\\n\\n\\n 15\\n In its reply brief, Chaparral asserts for the first time that it raised an\\nextrinsic-evidence argument in its response to Naylor Farms’ motion for summary\\njudgment. We agree that Chaparral’s response to Naylor Farms’ summary-judgment\\nmotion refers to what might be classified as extrinsic evidence. But we see no\\nargument there that the need to examine such evidence precludes certification. Nor\\ndo we see any indication that the district court ever ruled on such an argument.\\n 31\\n\\fUnited States v. Nelson, 868 F.3d 885, 891 n.4 (10th Cir. 2017) (quoting Lyons v.\\n\\nJefferson Bank & Tr., 994 F.2d 716, 722 (10th Cir. 1993)). Further, Chaparral fails to\\n\\nargue for plain error on appeal. Accordingly, it has waived its extrinsic-evidence\\n\\nargument. See Richison, 634 F.3d at 1131.\\n\\n Alternatively, even assuming Chaparral preserved its extrinsic-evidence\\n\\nargument below, it fails to adequately brief this argument on appeal. This is so\\n\\nbecause Chaparral fails to identify any specific extrinsic evidence—in the form of an\\n\\nexhibit, interlineation, or industry custom—that might allow a jury to conclude that\\n\\nChaparral breached the IDM as to one lease but not another. See Fed. R. App. P.\\n\\n28(a)(8)(A) (requiring argument section of appellant’s brief to contain “appellant’s\\n\\ncontentions and the reasons for them, with citations to the authorities and parts of the\\n\\nrecord on which the appellant relies”); Bronson v. Swensen, 500 F.3d 1099, 1104\\n\\n(10th Cir. 2007) (explaining that we routinely decline to consider inadequately\\n\\nbriefed arguments). Accordingly, even assuming the district court erred, we see no\\n\\nbasis upon which to conclude the district court’s error prejudiced Chaparral. See\\n\\nShinseki v. Sanders, 556 U.S. 396, 410 (2009) (explaining that “the party seeking\\n\\nreversal normally must explain why the erroneous ruling caused harm”). Thus, we\\n\\ndecline to reverse on this basis. And for the same reasons, we likewise decline to\\n\\nreverse based on Chaparral’s assertion that even in the absence of any ambiguity in\\n\\nthe leases, a jury will be required to consider industry customs in effect “when the\\n\\nvarious leases were executed” to determine whether Chaparral breached the terms of\\n\\n\\n\\n 32\\n\\feach individual lease. Aplt. Br. 36. Again, Chaparral neither identifies any particular\\n\\ncustoms nor explains their legal relevance.\\n\\n In its final lease-language argument, Chaparral asserts that individual\\n\\nvariations in its agreements with midstream processing companies, rather than in its\\n\\nagreements with Naylor Farms and other royalty owners, defeat commonality and\\n\\npredominance. In support, Chaparral says Naylor Farms’ underlying legal theory is\\n\\nthat Chaparral committed fraud by using wellhead sales contracts to circumvent\\n\\nOklahoma law. And to evaluate this theory, Chaparral contends, a jury will have to\\n\\nconduct an individualized inquiry to determine whether Chaparral entered into each\\n\\nof those wellhead sales contracts in good faith.\\n\\n But this argument overlooks the fact that the district court declined to certify\\n\\nNaylor Farms’ fraud claim. And Chaparral cites no authority indicating that whether\\n\\nit entered into the wellhead sales contracts in good faith is dispositive of, or even\\n\\nrelevant to, the claims the district court did certify. Accordingly, we find this\\n\\nargument inadequately briefed and decline to consider it as well. See Fed. R. App. P.\\n\\n28(a)(8)(A); Bronson, 500 F.3d at 1104. And we further conclude that Chaparral\\n\\ntherefore fails to demonstrate the district court abused its discretion in certifying the\\n\\nclass despite minor variations in lease language.\\n\\nIII. Uniform Payment Methodology\\n\\n As a final matter, Chaparral asserts Naylor Farms failed to demonstrate that\\n\\nChaparral uses a uniform payment methodology to calculate royalty payments and\\n\\n\\n\\n 33\\n\\fthat this “lack of a common payment methodology defeats class certification.” Aplt.\\n\\nBr. 39.\\n\\n We have indeed explained that the existence of a uniform payment\\n\\nmethodology, standing alone, isn’t sufficient to establish predominance. See\\n\\nRoderick, 725 F.3d at 1220. But contrary to Chaparral’s assertion, we see nothing in\\n\\nRoderick that indicates the existence of such a methodology is necessary to\\n\\naccomplish this task. Accordingly, we reject this argument. And to the extent\\n\\nChaparral instead means to suggest that individual questions about damages defeat\\n\\npredominance, we do not agree. “The fact that damages may have to be ascertained\\n\\non an individual basis is not, standing alone, sufficient to defeat class certification.”\\n\\nMenocal, 882 F.3d at 922 (quoting Roderick, 725 F.3d at 1220)). Instead, “material\\n\\ndifferences in damages determinations” will only destroy predominance if those\\n\\n“individualized issues will overwhelm . . . questions common to the class.” Roderick,\\n\\n725 F.3d at 1220.\\n\\n We see no indication that will occur here. On the contrary, as the district court\\n\\npointed out, Naylor Farms “provided evidence that [its] expert can determine\\n\\ndamages on a class[]wide basis through use of a model,” thus obviating the need for\\n\\nindividualized evidence. App. vol. 5, 1155; see also Tyson Foods, Inc., 136 S. Ct. at\\n\\n1045. And Chaparral fails to explain why that model is inaccurate or unworkable.\\n\\nFurther, the district court correctly noted that if necessary, it can later divide the class\\n\\ninto subclasses for purposes of determining damages. See Fed. R. Civ. P. 23(c)(1)(C),\\n\\n(c)(5); Roderick, 725 F.3d 1213. Thus, the district court didn’t abuse its discretion in\\n\\n 34\\n\\fruling that individual questions about damages don’t defeat predominance. See\\n\\nRoderick, 725 F.3d 1213 (“[T]he district court is in the best position to evaluate the\\n\\npractical difficulties which inhere in the class action format, and is especially suited\\n\\nto tailor the proceedings accordingly.”).\\n\\n Conclusion\\n\\n For the reasons discussed above, we conclude that Chaparral fails to\\n\\ndemonstrate the district court’s decision to certify the class falls outside “the bounds\\n\\nof rationally available choices given the facts and law involved in the matter at\\n\\nhand.” CGC Holding Co., 773 F.3d at 1086 (quoting Vallario, 554 F.3d at 1264). We\\n\\ntherefore affirm the district court’s order.\\n\\n\\n\\n\\n 35\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2254,"cells":{"id":{"kind":"number","value":4616656,"string":"4,616,656"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Alexander Christian MILES, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Miles"},"decision_date":{"kind":"string","value":"2019-05-03"},"docket_number":{"kind":"string","value":"18-6119"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Hartz, Murphy, Carson\", \"parties\": \"\", \"opinions\": [{\"author\": \"HARTZ, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 3, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n UNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n No. 18-6119\\n v.\\n\\n ALEXANDER CHRISTIAN MILES,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the Western District of Oklahoma\\n (D.C. No. 5:06-CR-00096-HE-1)\\n _________________________________\\n\\nDon P. Chairez, Law Offices of Don Chairez, Las Vegas, Nevada, for Defendant-\\nAppellant.\\n\\nSteven W. Creager, Assistant United States Attorney (Robert J. Troester, First Assistant\\nUnited States Attorney, with him on the brief), Oklahoma City, Oklahoma, for Plaintiff-\\nAppellee.\\n _________________________________\\n\\nBefore HARTZ, MURPHY, and CARSON, Circuit Judges.\\n _________________________________\\n\\nHARTZ, Circuit Judge.\\n _________________________________\\n\\n Defendant Alexander Christian Miles appeals the denial of his second petition for\\n\\na writ of coram nobis. He pleaded guilty in 2009 to submitting a false affidavit in\\n\\nconnection with an application for a visa for a 14-year-old girl from Cambodia to whom\\n\\fhe was engaged. He has already unsuccessfully challenged that judgment in a direct\\n\\nappeal, a motion for relief under 28 U.S.C. § 2255, and a previous petition for a writ of\\n\\ncoram nobis. Exercising jurisdiction under 28 U.S.C. § 1291, we affirm the district\\n\\ncourt’s denial of his second petition because each of its claims for relief either had been\\n\\nraised by Defendant in earlier proceedings and rejected by this court, or could have been\\n\\nraised in those proceedings and was inexcusably neglected.\\n\\n I. BACKGROUND\\n\\n Defendant, age 43 at the time, married a 14-year-old Cambodian girl, S.K., in a\\n\\nCambodian wedding ceremony in October 2001. The previous July he had applied to the\\n\\nImmigration and Naturalization Service (INS) for a K-1 visa on S.K.’s behalf, and\\n\\nrepresented in his affidavit in support of the application that she was 18 years old. The\\n\\nvisa was granted and he and S.K. moved to New York, where they were married in\\n\\nDecember 2001. In February 2002, S.K. applied to the INS for adjustment of status, and\\n\\nDefendant again lied about her age on his affidavit in support of that application.\\n\\n In July 2002, Defendant and S.K. moved to Oklahoma. Shortly thereafter, federal\\n\\nprosecutors charged him with violating the Mann Act, 18 U.S.C. § 2423(a), which\\n\\nprohibits transporting a minor across state lines with intent to engage in sexual activity\\n\\ncontrary to state law. After a jury was empaneled and sworn, but before any evidence or\\n\\nargument had been presented to it, the district court granted Defendant’s motion to\\n\\ndismiss the indictment because it did not specify the underlying Oklahoma offense—\\n\\nleaving open the possibility that it was statutory rape, an offense to which Defendant’s\\n\\nmarriage to S.K. would have provided a complete defense.\\n\\n\\n 2\\n\\f The government re-indicted Defendant under the Mann Act, this time specifying\\n\\nthat the underlying Oklahoma offense was forcible rape. He moved to dismiss that\\n\\nindictment on double-jeopardy grounds, but the district court denied the motion and we\\n\\naffirmed after an interlocutory appeal. See United States v. Miles (Miles I), 327 F. App’x\\n\\n797, 798 (10th Cir. 2009). He then entered into a plea agreement with the government\\n\\nunder which the indictment was to be dismissed, and he pleaded guilty to an information\\n\\ncharging him with violating 18 U.S.C. § 1001(a)(3) by falsely stating S.K.’s age in the K-\\n\\n1 visa application. Unnoticed by the court or the parties, however, the information stated\\n\\nthat the K-1 application had been filed in February 2002 (the date of the application for\\n\\nadjustment of S.K.’s status) rather than the true date of July 2001. Nonetheless,\\n\\nDefendant “himself affirmed both the alleged date and document in his colloquy with the\\n\\ncourt establishing the factual basis for his plea at the plea hearing.” United States v.\\n\\nMiles (Miles III), 546 F. App’x 730, 731–32 (10th Cir. 2012).\\n\\n The plea agreement contained a clause waiving Defendant’s right to “[a]ppeal or\\n\\ncollaterally challenge his guilty plea,” and his right to “[a]ppeal, collaterally challenge, or\\n\\nmove to modify . . . his sentence as imposed by the Court and the manner in which the\\n\\nsentence is determined, provided the sentence is within or below the advisory guideline\\n\\nrange determined by the Court to apply to this case.” Aplt. App. at 42. The court\\n\\nimposed a five-year sentence and sex-offender conditions, Defendant appealed the\\n\\nimposition of the sex-offender conditions, and we affirmed the sentence. See United\\n\\nStates v. Miles (Miles II), 411 F. App’x 126, 127–28 (10th Cir. 2010).\\n\\n\\n\\n\\n 3\\n\\f In 2011, Defendant filed a pro se § 2255 motion claiming (1) that he was actually\\n\\ninnocent of making a material false statement to the INS in February 2002, because his\\n\\nwife’s age was not material to the application for adjustment of status, (2) that his\\n\\nattorney in the double-jeopardy appeal had been ineffective, and (3) that if the charge to\\n\\nwhich he pleaded had actually been making a false statement on a K-1 visa application\\n\\nfor S.K. in February 2002, his plea had no factual basis and any false statement was\\n\\nimmaterial because he had already obtained a K-1 fiancée visa by that time. The district\\n\\ncourt denied the motion, and we declined to issue a certificate of appealability. See Miles\\n\\nIII, 546 F. App’x at 736. We held that the collateral-review waiver in Defendant’s plea\\n\\nagreement barred any legal challenge to his guilty plea and, relevant to this appeal, that\\n\\nhe was not “factually innocent of making a false statement on the K–1 visa application he\\n\\nsubmitted for his fiancée.” Id. at 734.\\n\\n In 2013, after he had served his sentence, Defendant filed a pro se petition for a\\n\\nwrit of coram nobis under the All Writs Act, 28 U.S.C. § 1651(a). See United States v.\\n\\nDenedo, 556 U.S. 904, 911 (2009) (“In federal courts the authority to grant a writ of\\n\\ncoram nobis is conferred by the All Writs Act, which permits ‘courts established by Act\\n\\nof Congress’ to issue ‘all writs necessary or appropriate in aid of their respective\\n\\njurisdictions.’”). “A petition for a writ of coram nobis provides a way to collaterally\\n\\nattack a criminal conviction for a person . . . who is no longer ‘in custody’ and therefore\\n\\ncannot seek habeas relief under 28 U.S.C. § 2255 or § 2241.” Chaidez v. United States,\\n\\n568 U.S. 342, 345 n.1 (2013). But a remedy is rarely available. Federal courts are only\\n\\npermitted “to entertain coram nobis applications in extraordinary cases presenting\\n\\n\\n 4\\n\\fcircumstances compelling its use to achieve justice.” Rawlins v. Kansas, 714 F.3d 1189,\\n\\n1196 (10th Cir. 2013) (internal quotation marks omitted).\\n\\n Defendant’s petition asserted that he had thought his guilty plea was based on\\n\\nmaking a false statement on the 2002 adjustment-of-status form rather than the 2001 visa\\n\\napplication, that his trial counsel had told him that was the case, and that he discovered\\n\\nthat he had pleaded guilty to lying on the visa application only upon reading this court’s\\n\\ndecision on his § 2255 motion. The district court denied the petition, and we affirmed.\\n\\nSee United States v. Miles (Miles IV), 553 F. App’x 846, 849 (10th Cir. 2014). We held\\n\\nthat the petition was procedurally barred because Defendant had previously “had an\\n\\nadequate remedy under § 2255” for the claim he was asserting, and that he was not\\n\\nentitled to the miscarriage-of-justice exception to the bar because he had not shown his\\n\\nfactual innocence. Id. at 848–49.\\n\\n Finally, Defendant filed a second petition for a writ of coram nobis, the one at\\n\\nissue in this appeal. He claims that he is actually innocent of the false-statement offense\\n\\nto which he pleaded guilty because his false statement of S.K.’s age was not material to\\n\\neither the visa application or the application for adjustment of status. And he claims that\\n\\nhis trial counsel was ineffective in two respects: (1) for not fulfilling his duty under\\n\\nPadilla v. Kentucky, 559 U.S. 356 (2010), to adequately inform Defendant of the\\n\\nimmigration consequences of his plea, and (2) for failing to investigate the facts and law\\n\\non the materiality of Defendant’s false statement. The district court initially treated the\\n\\npetition as a successive § 2255 motion and dismissed it on that ground, but we reversed\\n\\nthat dismissal in United States v. Miles (Miles V), 697 F. App’x 601, 602 (10th Cir.\\n\\n\\n 5\\n\\f2017), on the ground that it is improper to recharacterize a petition by a person no longer\\n\\nin custody as a § 2255 motion. On remand the district court once again dismissed the\\n\\npetition, this time on the grounds that it was barred as an abuse of the writ, was barred by\\n\\nDefendant’s collateral-review waiver, and in any event did not satisfy the requirements\\n\\nfor a writ to issue. Agreeing in essence with the first ground, we need not address the\\n\\nothers.\\n\\n II. DISCUSSION\\n\\n A. General Principles Governing Collateral Attacks on Convictions\\n\\n Before filing the coram nobis petition at issue here, Defendant had appealed his\\n\\nsentence, pursued relief under § 2255, and sought relief under a prior coram nobis\\n\\npetition. The question naturally arises whether there is any limit to how many\\n\\npostconviction petitions he can file. Are there procedural barriers to such petitions, or\\n\\nmust we always address each issue he raises?\\n\\n There is a body of law limiting second or successive habeas corpus petitions\\n\\n(including applications under 28 U.S.C. §§ 2241 and 2254 and motions under § 2255),\\n\\nwhich are by far the most common avenues for challenges to convictions after direct\\n\\nappeals have been exhausted or not pursued. Although the Supreme Court has\\n\\nconsistently “rejected res judicata in a strict sense as a basis for dismissing a later habeas\\n\\naction,” it has “made clear that the prior adjudication [bears] vital relevance to the\\n\\nexercise of the court’s discretion in determining whether to consider the petition.”\\n\\nMcCleskey v. Zant, 499 U.S. 467, 482 (1991). Some of this law derives from statutory\\n\\nprovisions, particularly the Antiterrorism and Effective Death Penalty Act of 1996\\n\\n\\n 6\\n\\f(AEDPA), but several principles were developed through judicial decisions predating\\n\\nAEDPA. See id. at 489 (“[T]he doctrine of abuse of the writ refers to a complex and\\n\\nevolving body of equitable principles informed and controlled by historical usage,\\n\\nstatutory developments, and judicial decisions.”); Stanko v. Davis, 617 F.3d 1262, 1269\\n\\n(10th Cir. 2010) (“Long before AEDPA, and even before the enactment of § 2244, the\\n\\nSupreme Court developed several principles limiting the review of second or subsequent\\n\\nhabeas petitions.”).\\n\\n The successive-use-of-the-writ doctrine “authorized a federal court to decline to\\n\\nconsider a habeas petition presenting a claim that was previously raised and adjudicated\\n\\nin an earlier habeas proceeding, unless the court determined that hearing the claim would\\n\\nserve the ends of justice.” Stanko, 617 F.3d at 1269; see id. at n.7. The ends-of-justice\\n\\nexception had been described as requiring a “colorable showing of factual innocence,”\\n\\nMcCleskey, 499 U.S. at 495, although the test is now formulated to require a showing that\\n\\nthe alleged error “probably has caused the conviction of one innocent of the crime,”\\n\\nthereby “implicating a fundamental miscarriage of justice.” Id. at 494–95.\\n\\n “Another principle, abuse of the writ, authorized a court to decline to hear a\\n\\nsecond or subsequent habeas petition raising a claim that could have been presented in an\\n\\nearlier petition but was not.” Stanko, 617 F.3d at 1269. “[I]f a second or subsequent\\n\\npetition raises a claim that could have been raised in an earlier petition, the petitioner\\n\\nmust establish that the omission was not the result of inexcusable neglect in order to\\n\\nproceed on the new claim.” Id. at 1271. In other words, the petitioner must show “cause\\n\\nfor his failure to raise the claim in an earlier proceeding and resulting prejudice.” Stanko,\\n\\n\\n 7\\n\\f617 F.3d at 1271. “[T]he cause standard requires the petitioner to show that some\\n\\nobjective factor external to the defense impeded counsel’s efforts to raise the claim,” or\\n\\nthat the claim had not been raised because counsel had been “constitutionally\\n\\nineffective.” McCleskey, 499 U.S. at 493–94 (brackets and internal quotation marks\\n\\nomitted). This procedural bar also may be overcome if the petition comes within the\\n\\nmiscarriage-of-justice exception by “mak[ing] a proper showing of actual innocence.”\\n\\nMcQuiggin v. Perkins, 569 U.S. 383, 392 (2013) (internal quotation marks omitted); see\\n\\nStanko, 617 F.3d at 1271. A “proper showing” to overcome either bar requires “new\\n\\nevidence [that] shows it is more likely than not that no reasonable juror would have\\n\\nconvicted the petitioner.” McQuiggin, 569 U.S. at 395 (brackets and internal quotation\\n\\nmarks omitted). “New evidence” is “relevant evidence that was either excluded or\\n\\nunavailable at trial.” Schlup v. Delo, 513 U.S. 298, 327–28 (1995); see id. at 324 (“To be\\n\\ncredible, such a claim requires petitioner to support his allegations of constitutional error\\n\\nwith new reliable evidence—whether it be exculpatory scientific evidence, trustworthy\\n\\neyewitness accounts, or critical physical evidence—that was not presented at trial.”).\\n\\n We can think of no reason why these same restrictions should not apply to\\n\\npetitions for writs of coram nobis. The writ is not to be granted lightly. Its availability is\\n\\nlimited to “extraordinary cases presenting circumstances compelling its use to achieve\\n\\njustice.” Denedo, 556 U.S. at 911 (internal quotation marks omitted). As the First\\n\\nCircuit observed: “The further a case progresses through the remedial steps available to a\\n\\ncriminal defendant, the stiffer the requirements for vacating a final judgment. Thus,\\n\\ndirect review is more defendant-friendly than post-judgment review, and an initial habeas\\n\\n\\n 8\\n\\fpetition is easier for a criminal defendant to litigate than a successive one. The writ of\\n\\nerror coram nobis lies at the far end of this continuum.” United States v. George, 676\\n\\nF.3d 249, 258 (1st Cir. 2012) (citations omitted).\\n\\n Indeed, Tenth Circuit precedent already imposes a bar to coram nobis relief\\n\\n“unless relief under 28 U.S.C. § 2255 was unavailable or would have been inadequate.”\\n\\nUnited States v. Payne, 644 F.3d 1111, 1112 (10th Cir. 2011). In other words, a claim\\n\\npressed through a coram nobis petition is ordinarily barred if the petitioner previously\\n\\nraised the claim in a § 2255 motion but was unsuccessful or simply failed to pursue the\\n\\nclaim under § 2255 when petitioner could have. It is a small, and wholly logical, step to\\n\\nexpand this bar beyond previously available § 2255 motions to include all previously\\n\\navailable postconviction avenues for relief. We have done so in a nonprecedential\\n\\nopinion. See United States v. Tarango, 670 F. App’x 981, 981 (10th Cir. 2016) (Gorsuch,\\n\\nJ.) (“A writ of coram nobis may not be used to litigate issues that were or could have\\n\\nbeen raised on direct appeal or through collateral litigation, including a 28 U.S.C. § 2255\\n\\nmotion.”). We now adopt that proposition here. Absent those traditional grounds that\\n\\nhave excused successive or abusive habeas petitions, a petition for writ of coram nobis\\n\\nmust be rejected if the claim was raised or could have been raised on direct appeal,\\n\\nthrough a § 2255 motion, or in any other prior collateral attack on the conviction or\\n\\nsentence. Our view finds support in decisions from other circuits. See United States v.\\n\\nSwindall, 107 F.3d 831, 836 n.7 (11th Cir. 1997); United States v. Camacho-Bordes, 94\\n\\nF.3d 1168, 1172–73 (8th Cir. 1996); United States v. Bartlett, Nos. 90-6345, 90-6351,\\n\\n1990 WL 135645, at *1 n.* (4th Cir. Sept. 20, 1990). But see United States v. Darnell,\\n\\n\\n 9\\n\\f716 F.2d 479, 481 n.5 (7th Cir. 1983) (the abuse-of-the-writ doctrine does not apply to\\n\\ncoram nobis petitions, because the narrow scope of the writ “ensures that coram nobis\\n\\nwill not be utilized as a substitute for appeal”).\\n\\n B. Application to This Case\\n\\n Defendant’s petition asserts two grounds for relief: (1) that he is actually innocent\\n\\nof the false-statement offense to which he pleaded guilty, because his false statement of\\n\\nS.K’s age was not material1, and (2) that he received ineffective assistance of counsel in\\n\\nconnection with his guilty plea, because his trial counsel did not inform him of potential\\n\\nimmigration consequences of his guilty plea and did not adequately investigate the\\n\\nfactual basis of his guilty plea. Both are procedurally barred.\\n\\n Defendant’s actual-innocence claim was raised and rejected in prior collateral\\n\\nattacks. In his § 2255 proceeding we held that his falsification of S.K.’s age in the visa\\n\\napplication was a material falsehood and he was not actually innocent of the charge even\\n\\nif the date in the information was incorrect. See Miles III, 546 F. App’x at 732–34. And\\n\\nin upholding the rejection of his first coram nobis petition, we determined that Defendant\\n\\nclearly understood at the time of his plea that he was pleading guilty to a false statement\\n\\nrelated to the visa application, not the application for adjustment of status. See Miles IV,\\n\\n553 F. App’x at 849.\\n\\n\\n1\\n The Supreme Court has “not resolved whether a prisoner may be entitled to habeas\\nrelief based on a freestanding claim of actual innocence” McQuiggin, 569 U.S. at 391;\\nsee also Herrera v. Collins, 506 U.S. 390, 400 (1993) (“Claims of actual innocence based\\non newly discovered evidence have never been held to state a ground for federal habeas\\nrelief absent an independent constitutional violation occurring in the underlying state\\ncriminal proceeding.”).\\n\\n 10\\n\\f As for Defendant’s first ineffective-assistance claim, he relies on the Supreme\\n\\nCourt’s decision in Padilla, which postdated his conviction. Perhaps coram nobis is a\\n\\nproper avenue for relief if a claim is based on Supreme Court law that was declared after\\n\\nthe defendant had fully served the criminal sentence. Cf. United States v. Snyder, 871\\n\\nF.3d 1122, 1127 (10th Cir. 2017) (“Cause excusing procedural default is shown if a claim\\n\\nis so novel that its legal basis was not reasonably available to counsel at the time of the\\n\\ndirect appeal.” (brackets and internal quotation marks omitted)). But that is not the case\\n\\nhere. Padilla was decided on March 31, 2010, and Defendant filed his § 2255 motion in\\n\\n2011. Moreover, the claim could have been included in his 2013 coram nobis petition.2\\n\\n\\n2\\n There is a much more disturbing reason why Defendant’s Padilla claim fails. Although\\nhe is a citizen of Sweden, his counsel conceded at oral argument that he is also a\\nnaturalized United States citizen. Padilla concerns counsel’s obligation “to inform [a]\\nnoncitizen client that he faces a risk of deportation.” 559 U.S. at 374 (emphasis added).\\nTo pursue this claim, Defendant falsely states in his coram nobis petition and his affidavit\\nin support of the petition that he is an “alien national.” His briefs on appeal do not state\\noutright that he is not a citizen, but his opening brief states that he is a “foreign national,”\\nAplt. Br. at 34, his reply brief states that “the government has failed to provide any\\nproof . . . that [he] is a U.S. Citizen,” Reply Br. at 23, and both briefs continue to press\\nthe Padilla claim.\\n\\n The apparently knowing and material misrepresentations in Defendant’s filings are\\npotential violations of the rules of professional conduct for the United States District\\nCourt for the Western District of Oklahoma, and the rules of professional conduct in\\nCalifornia and Nevada, two states in which Defendant’s counsel, Don P. Chairez, is\\nlicensed to practice law. It appears that Defendant is currently not eligible to practice law\\nin California for administrative reasons, but these misrepresentations might justify\\nprofessional discipline against him as well. We direct the clerk to forward copies of this\\nopinion to the State Bar of California and the State Bar of Nevada so that they can assess\\nwhether counsel’s conduct and/or Miles’s conduct warrants any sanction. See In re\\nGraham, 981 F.2d 1135, 1142 (10th Cir. 1992) (“A court may . . . report misconduct by\\na[n] . . . attorney to that attorney’s bar association for the purpose of instituting\\ndisciplinary proceedings.”); Lail v. Apfel, No. 98-7079, 1999 WL 147305, at *2 (10th\\nCir. Mar. 18, 1999) (“[C]ontinued misrepresentations to this court . . . may\\n\\n 11\\n\\f It is even clearer that Defendant’s second ineffective-assistance claim could have\\n\\nbeen raised earlier. The matters that he contends his counsel should have discovered\\n\\nbefore he pleaded guilty were all presented in his § 2255 proceedings. He was aware of\\n\\neverything that he needed to raise the present ineffective-assistance claim.\\n\\n To be sure, the procedural bars to Defendant’s present claims may be overcome in\\n\\ncertain circumstances. But Defendant has not identified any legitimate ground to do so\\n\\nhere. He argues that cause for his failure to raise his ineffective-assistance-of-trial-\\n\\ncounsel claims is present because of (1) ineffectiveness of trial counsel—in the very\\n\\nrespects that he complains of in his coram nobis petition, (2) “new developments in law,”\\n\\nAplt. Br. at 41, and (3) “extrinsic fraud,” id. at 43. We are not persuaded. He does not\\n\\nexplain how ineffectiveness of trial counsel kept him from arguing his ineffectiveness\\n\\nclaims in his § 2255 proceedings or his first coram nobis petition; the cases he cites as\\n\\n“new developments” are not essential, or even material, to his present claims; and the\\n\\nevidence of asserted fraud is only the untrue allegation that the prosecution and the courts\\n\\nincorrectly characterized his guilty plea as being to his false statement on the visa\\n\\napplication.\\n\\n Nor can Defendant rely on the actual-innocence exception to procedural bar. The\\n\\nonly new evidence he puts forward in support of his argument for actual innocence is a\\n\\n\\nlead . . . to . . . a referral to the Oklahoma State Bar for possible disciplinary\\nproceedings.”). Because counsel informed this court during oral argument that Miles is\\nalso a medical doctor, we direct the clerk to forward copies of this opinion to the\\nOklahoma Medical Board, the New York Office of Professional Medical Conduct, the\\nArizona Medical Board, and the Medical Board of California, all states in which Miles\\nwas licensed to practice medicine.\\n\\n 12\\n\\f2013 Department of Homeland Security guidance document that he claims tends to prove\\n\\nthat a 14-year-old can qualify for a fiancée visa. He argues that this document establishes\\n\\nthat his false statement of S.K’s age was not material. But we doubt that this document\\n\\nwould have affected our reasoning in rejecting Defendant’s actual-innocence claim in his\\n\\n§ 2255 proceeding. See Miles III, 546 F. App’x at 734 (“[I]n assessing the ability of Mr.\\n\\nMiles and his fiancée to conclude a valid marriage within ninety days of her arrival for\\n\\npurposes of the K–1 visa, the true age of his fiancée, which would have triggered\\n\\nsignificant if not conclusive impediments, was plainly a material consideration.”). It does\\n\\nnot make it “more likely than not that no reasonable juror would have convicted him.”\\n\\nSchlup, 513 U.S. at 327.\\n\\n III. CONCLUSION\\n\\n We AFFIRM the denial of Defendant’s petition.\\n\\n\\n\\n\\n 13\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4393909/\", \"author_raw\": \"HARTZ, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"HARTZ"},"judge2":{"kind":"string","value":"MURPHY"},"judge3":{"kind":"string","value":"CARSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4616656/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Alexander Christian MILES, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 3, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\n UNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n No. 18-6119\n v.\n\n ALEXANDER CHRISTIAN MILES,\n\n Defendant - Appellant.\n _________________________________\n\n Appeal from the United States District Court\n for the Western District of Oklahoma\n (D.C. No. 5:06-CR-00096-HE-1)\n _________________________________\n\nDon P. Chairez, Law Offices of Don Chairez, Las Vegas, Nevada, for Defendant-\nAppellant.\n\nSteven W. Creager, Assistant United States Attorney (Robert J. Troester, First Assistant\nUnited States Attorney, with him on the brief), Oklahoma City, Oklahoma, for Plaintiff-\nAppellee.\n _________________________________\n\nBefore HARTZ, MURPHY, and CARSON, Circuit Judges.\n _________________________________\n\nHARTZ, Circuit Judge.\n _________________________________\n\n Defendant Alexander Christian Miles appeals the denial of his second petition for\n\na writ of coram nobis. He pleaded guilty in 2009 to submitting a false affidavit in\n\nconnection with an application for a visa for a 14-year-old girl from Cambodia to whom\n\fhe was engaged. He has already unsuccessfully challenged that judgment in a direct\n\nappeal, a motion for relief under 28 U.S.C. § 2255, and a previous petition for a writ of\n\ncoram nobis. Exercising jurisdiction under 28 U.S.C. § 1291, we affirm the district\n\ncourt’s denial of his second petition because each of its claims for relief either had been\n\nraised by Defendant in earlier proceedings and rejected by this court, or could have been\n\nraised in those proceedings and was inexcusably neglected.\n\n I. BACKGROUND\n\n Defendant, age 43 at the time, married a 14-year-old Cambodian girl, S.K., in a\n\nCambodian wedding ceremony in October 2001. The previous July he had applied to the\n\nImmigration and Naturalization Service (INS) for a K-1 visa on S.K.’s behalf, and\n\nrepresented in his affidavit in support of the application that she was 18 years old. The\n\nvisa was granted and he and S.K. moved to New York, where they were married in\n\nDecember 2001. In February 2002, S.K. applied to the INS for adjustment of status, and\n\nDefendant again lied about her age on his affidavit in support of that application.\n\n In July 2002, Defendant and S.K. moved to Oklahoma. Shortly thereafter, federal\n\nprosecutors charged him with violating the Mann Act, 18 U.S.C. § 2423(a), which\n\nprohibits transporting a minor across state lines with intent to engage in sexual activity\n\ncontrary to state law. After a jury was empaneled and sworn, but before any evidence or\n\nargument had been presented to it, the district court granted Defendant’s motion to\n\ndismiss the indictment because it did not specify the underlying Oklahoma offense—\n\nleaving open the possibility that it was statutory rape, an offense to which Defendant’s\n\nmarriage to S.K. would have provided a complete defense.\n\n\n 2\n\f The government re-indicted Defendant under the Mann Act, this time specifying\n\nthat the underlying Oklahoma offense was forcible rape. He moved to dismiss that\n\nindictment on double-jeopardy grounds, but the district court denied the motion and we\n\naffirmed after an interlocutory appeal. See United States v. Miles (Miles I), 327 F. App’x\n\n797, 798 (10th Cir. 2009). He then entered into a plea agreement with the government\n\nunder which the indictment was to be dismissed, and he pleaded guilty to an information\n\ncharging him with violating 18 U.S.C. § 1001(a)(3) by falsely stating S.K.’s age in the K-\n\n1 visa application. Unnoticed by the court or the parties, however, the information stated\n\nthat the K-1 application had been filed in February 2002 (the date of the application for\n\nadjustment of S.K.’s status) rather than the true date of July 2001. Nonetheless,\n\nDefendant “himself affirmed both the alleged date and document in his colloquy with the\n\ncourt establishing the factual basis for his plea at the plea hearing.” United States v.\n\nMiles (Miles III), 546 F. App’x 730, 731–32 (10th Cir. 2012).\n\n The plea agreement contained a clause waiving Defendant’s right to “[a]ppeal or\n\ncollaterally challenge his guilty plea,” and his right to “[a]ppeal, collaterally challenge, or\n\nmove to modify . . . his sentence as imposed by the Court and the manner in which the\n\nsentence is determined, provided the sentence is within or below the advisory guideline\n\nrange determined by the Court to apply to this case.” Aplt. App. at 42. The court\n\nimposed a five-year sentence and sex-offender conditions, Defendant appealed the\n\nimposition of the sex-offender conditions, and we affirmed the sentence. See United\n\nStates v. Miles (Miles II), 411 F. App’x 126, 127–28 (10th Cir. 2010).\n\n\n\n\n 3\n\f In 2011, Defendant filed a pro se § 2255 motion claiming (1) that he was actually\n\ninnocent of making a material false statement to the INS in February 2002, because his\n\nwife’s age was not material to the application for adjustment of status, (2) that his\n\nattorney in the double-jeopardy appeal had been ineffective, and (3) that if the charge to\n\nwhich he pleaded had actually been making a false statement on a K-1 visa application\n\nfor S.K. in February 2002, his plea had no factual basis and any false statement was\n\nimmaterial because he had already obtained a K-1 fiancée visa by that time. The district\n\ncourt denied the motion, and we declined to issue a certificate of appealability. See Miles\n\nIII, 546 F. App’x at 736. We held that the collateral-review waiver in Defendant’s plea\n\nagreement barred any legal challenge to his guilty plea and, relevant to this appeal, that\n\nhe was not “factually innocent of making a false statement on the K–1 visa application he\n\nsubmitted for his fiancée.” Id. at 734.\n\n In 2013, after he had served his sentence, Defendant filed a pro se petition for a\n\nwrit of coram nobis under the All Writs Act, 28 U.S.C. § 1651(a). See United States v.\n\nDenedo, 556 U.S. 904, 911 (2009) (“In federal courts the authority to grant a writ of\n\ncoram nobis is conferred by the All Writs Act, which permits ‘courts established by Act\n\nof Congress’ to issue ‘all writs necessary or appropriate in aid of their respective\n\njurisdictions.’”). “A petition for a writ of coram nobis provides a way to collaterally\n\nattack a criminal conviction for a person . . . who is no longer ‘in custody’ and therefore\n\ncannot seek habeas relief under 28 U.S.C. § 2255 or § 2241.” Chaidez v. United States,\n\n568 U.S. 342, 345 n.1 (2013). But a remedy is rarely available. Federal courts are only\n\npermitted “to entertain coram nobis applications in extraordinary cases presenting\n\n\n 4\n\fcircumstances compelling its use to achieve justice.” Rawlins v. Kansas, 714 F.3d 1189,\n\n1196 (10th Cir. 2013) (internal quotation marks omitted).\n\n Defendant’s petition asserted that he had thought his guilty plea was based on\n\nmaking a false statement on the 2002 adjustment-of-status form rather than the 2001 visa\n\napplication, that his trial counsel had told him that was the case, and that he discovered\n\nthat he had pleaded guilty to lying on the visa application only upon reading this court’s\n\ndecision on his § 2255 motion. The district court denied the petition, and we affirmed.\n\nSee United States v. Miles (Miles IV), 553 F. App’x 846, 849 (10th Cir. 2014). We held\n\nthat the petition was procedurally barred because Defendant had previously “had an\n\nadequate remedy under § 2255” for the claim he was asserting, and that he was not\n\nentitled to the miscarriage-of-justice exception to the bar because he had not shown his\n\nfactual innocence. Id. at 848–49.\n\n Finally, Defendant filed a second petition for a writ of coram nobis, the one at\n\nissue in this appeal. He claims that he is actually innocent of the false-statement offense\n\nto which he pleaded guilty because his false statement of S.K.’s age was not material to\n\neither the visa application or the application for adjustment of status. And he claims that\n\nhis trial counsel was ineffective in two respects: (1) for not fulfilling his duty under\n\nPadilla v. Kentucky, 559 U.S. 356 (2010), to adequately inform Defendant of the\n\nimmigration consequences of his plea, and (2) for failing to investigate the facts and law\n\non the materiality of Defendant’s false statement. The district court initially treated the\n\npetition as a successive § 2255 motion and dismissed it on that ground, but we reversed\n\nthat dismissal in United States v. Miles (Miles V), 697 F. App’x 601, 602 (10th Cir.\n\n\n 5\n\f2017), on the ground that it is improper to recharacterize a petition by a person no longer\n\nin custody as a § 2255 motion. On remand the district court once again dismissed the\n\npetition, this time on the grounds that it was barred as an abuse of the writ, was barred by\n\nDefendant’s collateral-review waiver, and in any event did not satisfy the requirements\n\nfor a writ to issue. Agreeing in essence with the first ground, we need not address the\n\nothers.\n\n II. DISCUSSION\n\n A. General Principles Governing Collateral Attacks on Convictions\n\n Before filing the coram nobis petition at issue here, Defendant had appealed his\n\nsentence, pursued relief under § 2255, and sought relief under a prior coram nobis\n\npetition. The question naturally arises whether there is any limit to how many\n\npostconviction petitions he can file. Are there procedural barriers to such petitions, or\n\nmust we always address each issue he raises?\n\n There is a body of law limiting second or successive habeas corpus petitions\n\n(including applications under 28 U.S.C. §§ 2241 and 2254 and motions under § 2255),\n\nwhich are by far the most common avenues for challenges to convictions after direct\n\nappeals have been exhausted or not pursued. Although the Supreme Court has\n\nconsistently “rejected res judicata in a strict sense as a basis for dismissing a later habeas\n\naction,” it has “made clear that the prior adjudication [bears] vital relevance to the\n\nexercise of the court’s discretion in determining whether to consider the petition.”\n\nMcCleskey v. Zant, 499 U.S. 467, 482 (1991). Some of this law derives from statutory\n\nprovisions, particularly the Antiterrorism and Effective Death Penalty Act of 1996\n\n\n 6\n\f(AEDPA), but several principles were developed through judicial decisions predating\n\nAEDPA. See id. at 489 (“[T]he doctrine of abuse of the writ refers to a complex and\n\nevolving body of equitable principles informed and controlled by historical usage,\n\nstatutory developments, and judicial decisions.”); Stanko v. Davis, 617 F.3d 1262, 1269\n\n(10th Cir. 2010) (“Long before AEDPA, and even before the enactment of § 2244, the\n\nSupreme Court developed several principles limiting the review of second or subsequent\n\nhabeas petitions.”).\n\n The successive-use-of-the-writ doctrine “authorized a federal court to decline to\n\nconsider a habeas petition presenting a claim that was previously raised and adjudicated\n\nin an earlier habeas proceeding, unless the court determined that hearing the claim would\n\nserve the ends of justice.” Stanko, 617 F.3d at 1269; see id. at n.7. The ends-of-justice\n\nexception had been described as requiring a “colorable showing of factual innocence,”\n\nMcCleskey, 499 U.S. at 495, although the test is now formulated to require a showing that\n\nthe alleged error “probably has caused the conviction of one innocent of the crime,”\n\nthereby “implicating a fundamental miscarriage of justice.” Id. at 494–95.\n\n “Another principle, abuse of the writ, authorized a court to decline to hear a\n\nsecond or subsequent habeas petition raising a claim that could have been presented in an\n\nearlier petition but was not.” Stanko, 617 F.3d at 1269. “[I]f a second or subsequent\n\npetition raises a claim that could have been raised in an earlier petition, the petitioner\n\nmust establish that the omission was not the result of inexcusable neglect in order to\n\nproceed on the new claim.” Id. at 1271. In other words, the petitioner must show “cause\n\nfor his failure to raise the claim in an earlier proceeding and resulting prejudice.” Stanko,\n\n\n 7\n\f617 F.3d at 1271. “[T]he cause standard requires the petitioner to show that some\n\nobjective factor external to the defense impeded counsel’s efforts to raise the claim,” or\n\nthat the claim had not been raised because counsel had been “constitutionally\n\nineffective.” McCleskey, 499 U.S. at 493–94 (brackets and internal quotation marks\n\nomitted). This procedural bar also may be overcome if the petition comes within the\n\nmiscarriage-of-justice exception by “mak[ing] a proper showing of actual innocence.”\n\nMcQuiggin v. Perkins, 569 U.S. 383, 392 (2013) (internal quotation marks omitted); see\n\nStanko, 617 F.3d at 1271. A “proper showing” to overcome either bar requires “new\n\nevidence [that] shows it is more likely than not that no reasonable juror would have\n\nconvicted the petitioner.” McQuiggin, 569 U.S. at 395 (brackets and internal quotation\n\nmarks omitted). “New evidence” is “relevant evidence that was either excluded or\n\nunavailable at trial.” Schlup v. Delo, 513 U.S. 298, 327–28 (1995); see id. at 324 (“To be\n\ncredible, such a claim requires petitioner to support his allegations of constitutional error\n\nwith new reliable evidence—whether it be exculpatory scientific evidence, trustworthy\n\neyewitness accounts, or critical physical evidence—that was not presented at trial.”).\n\n We can think of no reason why these same restrictions should not apply to\n\npetitions for writs of coram nobis. The writ is not to be granted lightly. Its availability is\n\nlimited to “extraordinary cases presenting circumstances compelling its use to achieve\n\njustice.” Denedo, 556 U.S. at 911 (internal quotation marks omitted). As the First\n\nCircuit observed: “The further a case progresses through the remedial steps available to a\n\ncriminal defendant, the stiffer the requirements for vacating a final judgment. Thus,\n\ndirect review is more defendant-friendly than post-judgment review, and an initial habeas\n\n\n 8\n\fpetition is easier for a criminal defendant to litigate than a successive one. The writ of\n\nerror coram nobis lies at the far end of this continuum.” United States v. George, 676\n\nF.3d 249, 258 (1st Cir. 2012) (citations omitted).\n\n Indeed, Tenth Circuit precedent already imposes a bar to coram nobis relief\n\n“unless relief under 28 U.S.C. § 2255 was unavailable or would have been inadequate.”\n\nUnited States v. Payne, 644 F.3d 1111, 1112 (10th Cir. 2011). In other words, a claim\n\npressed through a coram nobis petition is ordinarily barred if the petitioner previously\n\nraised the claim in a § 2255 motion but was unsuccessful or simply failed to pursue the\n\nclaim under § 2255 when petitioner could have. It is a small, and wholly logical, step to\n\nexpand this bar beyond previously available § 2255 motions to include all previously\n\navailable postconviction avenues for relief. We have done so in a nonprecedential\n\nopinion. See United States v. Tarango, 670 F. App’x 981, 981 (10th Cir. 2016) (Gorsuch,\n\nJ.) (“A writ of coram nobis may not be used to litigate issues that were or could have\n\nbeen raised on direct appeal or through collateral litigation, including a 28 U.S.C. § 2255\n\nmotion.”). We now adopt that proposition here. Absent those traditional grounds that\n\nhave excused successive or abusive habeas petitions, a petition for writ of coram nobis\n\nmust be rejected if the claim was raised or could have been raised on direct appeal,\n\nthrough a § 2255 motion, or in any other prior collateral attack on the conviction or\n\nsentence. Our view finds support in decisions from other circuits. See United States v.\n\nSwindall, 107 F.3d 831, 836 n.7 (11th Cir. 1997); United States v. Camacho-Bordes, 94\n\nF.3d 1168, 1172–73 (8th Cir. 1996); United States v. Bartlett, Nos. 90-6345, 90-6351,\n\n1990 WL 135645, at *1 n.* (4th Cir. Sept. 20, 1990). But see United States v. Darnell,\n\n\n 9\n\f716 F.2d 479, 481 n.5 (7th Cir. 1983) (the abuse-of-the-writ doctrine does not apply to\n\ncoram nobis petitions, because the narrow scope of the writ “ensures that coram nobis\n\nwill not be utilized as a substitute for appeal”).\n\n B. Application to This Case\n\n Defendant’s petition asserts two grounds for relief: (1) that he is actually innocent\n\nof the false-statement offense to which he pleaded guilty, because his false statement of\n\nS.K’s age was not material1, and (2) that he received ineffective assistance of counsel in\n\nconnection with his guilty plea, because his trial counsel did not inform him of potential\n\nimmigration consequences of his guilty plea and did not adequately investigate the\n\nfactual basis of his guilty plea. Both are procedurally barred.\n\n Defendant’s actual-innocence claim was raised and rejected in prior collateral\n\nattacks. In his § 2255 proceeding we held that his falsification of S.K.’s age in the visa\n\napplication was a material falsehood and he was not actually innocent of the charge even\n\nif the date in the information was incorrect. See Miles III, 546 F. App’x at 732–34. And\n\nin upholding the rejection of his first coram nobis petition, we determined that Defendant\n\nclearly understood at the time of his plea that he was pleading guilty to a false statement\n\nrelated to the visa application, not the application for adjustment of status. See Miles IV,\n\n553 F. App’x at 849.\n\n\n1\n The Supreme Court has “not resolved whether a prisoner may be entitled to habeas\nrelief based on a freestanding claim of actual innocence” McQuiggin, 569 U.S. at 391;\nsee also Herrera v. Collins, 506 U.S. 390, 400 (1993) (“Claims of actual innocence based\non newly discovered evidence have never been held to state a ground for federal habeas\nrelief absent an independent constitutional violation occurring in the underlying state\ncriminal proceeding.”).\n\n 10\n\f As for Defendant’s first ineffective-assistance claim, he relies on the Supreme\n\nCourt’s decision in Padilla, which postdated his conviction. Perhaps coram nobis is a\n\nproper avenue for relief if a claim is based on Supreme Court law that was declared after\n\nthe defendant had fully served the criminal sentence. Cf. United States v. Snyder, 871\n\nF.3d 1122, 1127 (10th Cir. 2017) (“Cause excusing procedural default is shown if a claim\n\nis so novel that its legal basis was not reasonably available to counsel at the time of the\n\ndirect appeal.” (brackets and internal quotation marks omitted)). But that is not the case\n\nhere. Padilla was decided on March 31, 2010, and Defendant filed his § 2255 motion in\n\n2011. Moreover, the claim could have been included in his 2013 coram nobis petition.2\n\n\n2\n There is a much more disturbing reason why Defendant’s Padilla claim fails. Although\nhe is a citizen of Sweden, his counsel conceded at oral argument that he is also a\nnaturalized United States citizen. Padilla concerns counsel’s obligation “to inform [a]\nnoncitizen client that he faces a risk of deportation.” 559 U.S. at 374 (emphasis added).\nTo pursue this claim, Defendant falsely states in his coram nobis petition and his affidavit\nin support of the petition that he is an “alien national.” His briefs on appeal do not state\noutright that he is not a citizen, but his opening brief states that he is a “foreign national,”\nAplt. Br. at 34, his reply brief states that “the government has failed to provide any\nproof . . . that [he] is a U.S. Citizen,” Reply Br. at 23, and both briefs continue to press\nthe Padilla claim.\n\n The apparently knowing and material misrepresentations in Defendant’s filings are\npotential violations of the rules of professional conduct for the United States District\nCourt for the Western District of Oklahoma, and the rules of professional conduct in\nCalifornia and Nevada, two states in which Defendant’s counsel, Don P. Chairez, is\nlicensed to practice law. It appears that Defendant is currently not eligible to practice law\nin California for administrative reasons, but these misrepresentations might justify\nprofessional discipline against him as well. We direct the clerk to forward copies of this\nopinion to the State Bar of California and the State Bar of Nevada so that they can assess\nwhether counsel’s conduct and/or Miles’s conduct warrants any sanction. See In re\nGraham, 981 F.2d 1135, 1142 (10th Cir. 1992) (“A court may . . . report misconduct by\na[n] . . . attorney to that attorney’s bar association for the purpose of instituting\ndisciplinary proceedings.”); Lail v. Apfel, No. 98-7079, 1999 WL 147305, at *2 (10th\nCir. Mar. 18, 1999) (“[C]ontinued misrepresentations to this court . . . may\n\n 11\n\f It is even clearer that Defendant’s second ineffective-assistance claim could have\n\nbeen raised earlier. The matters that he contends his counsel should have discovered\n\nbefore he pleaded guilty were all presented in his § 2255 proceedings. He was aware of\n\neverything that he needed to raise the present ineffective-assistance claim.\n\n To be sure, the procedural bars to Defendant’s present claims may be overcome in\n\ncertain circumstances. But Defendant has not identified any legitimate ground to do so\n\nhere. He argues that cause for his failure to raise his ineffective-assistance-of-trial-\n\ncounsel claims is present because of (1) ineffectiveness of trial counsel—in the very\n\nrespects that he complains of in his coram nobis petition, (2) “new developments in law,”\n\nAplt. Br. at 41, and (3) “extrinsic fraud,” id. at 43. We are not persuaded. He does not\n\nexplain how ineffectiveness of trial counsel kept him from arguing his ineffectiveness\n\nclaims in his § 2255 proceedings or his first coram nobis petition; the cases he cites as\n\n“new developments” are not essential, or even material, to his present claims; and the\n\nevidence of asserted fraud is only the untrue allegation that the prosecution and the courts\n\nincorrectly characterized his guilty plea as being to his false statement on the visa\n\napplication.\n\n Nor can Defendant rely on the actual-innocence exception to procedural bar. The\n\nonly new evidence he puts forward in support of his argument for actual innocence is a\n\n\nlead . . . to . . . a referral to the Oklahoma State Bar for possible disciplinary\nproceedings.”). Because counsel informed this court during oral argument that Miles is\nalso a medical doctor, we direct the clerk to forward copies of this opinion to the\nOklahoma Medical Board, the New York Office of Professional Medical Conduct, the\nArizona Medical Board, and the Medical Board of California, all states in which Miles\nwas licensed to practice medicine.\n\n 12\n\f2013 Department of Homeland Security guidance document that he claims tends to prove\n\nthat a 14-year-old can qualify for a fiancée visa. He argues that this document establishes\n\nthat his false statement of S.K’s age was not material. But we doubt that this document\n\nwould have affected our reasoning in rejecting Defendant’s actual-innocence claim in his\n\n§ 2255 proceeding. See Miles III, 546 F. App’x at 734 (“[I]n assessing the ability of Mr.\n\nMiles and his fiancée to conclude a valid marriage within ninety days of her arrival for\n\npurposes of the K–1 visa, the true age of his fiancée, which would have triggered\n\nsignificant if not conclusive impediments, was plainly a material consideration.”). It does\n\nnot make it “more likely than not that no reasonable juror would have convicted him.”\n\nSchlup, 513 U.S. at 327.\n\n III. CONCLUSION\n\n We AFFIRM the denial of Defendant’s petition.\n\n\n\n\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Alexander Christian MILES, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 3, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n UNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n No. 18-6119\\n v.\\n\\n ALEXANDER CHRISTIAN MILES,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the Western District of Oklahoma\\n (D.C. No. 5:06-CR-00096-HE-1)\\n _________________________________\\n\\nDon P. Chairez, Law Offices of Don Chairez, Las Vegas, Nevada, for Defendant-\\nAppellant.\\n\\nSteven W. Creager, Assistant United States Attorney (Robert J. Troester, First Assistant\\nUnited States Attorney, with him on the brief), Oklahoma City, Oklahoma, for Plaintiff-\\nAppellee.\\n _________________________________\\n\\nBefore HARTZ, MURPHY, and CARSON, Circuit Judges.\\n _________________________________\\n\\nHARTZ, Circuit Judge.\\n _________________________________\\n\\n Defendant Alexander Christian Miles appeals the denial of his second petition for\\n\\na writ of coram nobis. He pleaded guilty in 2009 to submitting a false affidavit in\\n\\nconnection with an application for a visa for a 14-year-old girl from Cambodia to whom\\n\\fhe was engaged. He has already unsuccessfully challenged that judgment in a direct\\n\\nappeal, a motion for relief under 28 U.S.C. § 2255, and a previous petition for a writ of\\n\\ncoram nobis. Exercising jurisdiction under 28 U.S.C. § 1291, we affirm the district\\n\\ncourt’s denial of his second petition because each of its claims for relief either had been\\n\\nraised by Defendant in earlier proceedings and rejected by this court, or could have been\\n\\nraised in those proceedings and was inexcusably neglected.\\n\\n I. BACKGROUND\\n\\n Defendant, age 43 at the time, married a 14-year-old Cambodian girl, S.K., in a\\n\\nCambodian wedding ceremony in October 2001. The previous July he had applied to the\\n\\nImmigration and Naturalization Service (INS) for a K-1 visa on S.K.’s behalf, and\\n\\nrepresented in his affidavit in support of the application that she was 18 years old. The\\n\\nvisa was granted and he and S.K. moved to New York, where they were married in\\n\\nDecember 2001. In February 2002, S.K. applied to the INS for adjustment of status, and\\n\\nDefendant again lied about her age on his affidavit in support of that application.\\n\\n In July 2002, Defendant and S.K. moved to Oklahoma. Shortly thereafter, federal\\n\\nprosecutors charged him with violating the Mann Act, 18 U.S.C. § 2423(a), which\\n\\nprohibits transporting a minor across state lines with intent to engage in sexual activity\\n\\ncontrary to state law. After a jury was empaneled and sworn, but before any evidence or\\n\\nargument had been presented to it, the district court granted Defendant’s motion to\\n\\ndismiss the indictment because it did not specify the underlying Oklahoma offense—\\n\\nleaving open the possibility that it was statutory rape, an offense to which Defendant’s\\n\\nmarriage to S.K. would have provided a complete defense.\\n\\n\\n 2\\n\\f The government re-indicted Defendant under the Mann Act, this time specifying\\n\\nthat the underlying Oklahoma offense was forcible rape. He moved to dismiss that\\n\\nindictment on double-jeopardy grounds, but the district court denied the motion and we\\n\\naffirmed after an interlocutory appeal. See United States v. Miles (Miles I), 327 F. App’x\\n\\n797, 798 (10th Cir. 2009). He then entered into a plea agreement with the government\\n\\nunder which the indictment was to be dismissed, and he pleaded guilty to an information\\n\\ncharging him with violating 18 U.S.C. § 1001(a)(3) by falsely stating S.K.’s age in the K-\\n\\n1 visa application. Unnoticed by the court or the parties, however, the information stated\\n\\nthat the K-1 application had been filed in February 2002 (the date of the application for\\n\\nadjustment of S.K.’s status) rather than the true date of July 2001. Nonetheless,\\n\\nDefendant “himself affirmed both the alleged date and document in his colloquy with the\\n\\ncourt establishing the factual basis for his plea at the plea hearing.” United States v.\\n\\nMiles (Miles III), 546 F. App’x 730, 731–32 (10th Cir. 2012).\\n\\n The plea agreement contained a clause waiving Defendant’s right to “[a]ppeal or\\n\\ncollaterally challenge his guilty plea,” and his right to “[a]ppeal, collaterally challenge, or\\n\\nmove to modify . . . his sentence as imposed by the Court and the manner in which the\\n\\nsentence is determined, provided the sentence is within or below the advisory guideline\\n\\nrange determined by the Court to apply to this case.” Aplt. App. at 42. The court\\n\\nimposed a five-year sentence and sex-offender conditions, Defendant appealed the\\n\\nimposition of the sex-offender conditions, and we affirmed the sentence. See United\\n\\nStates v. Miles (Miles II), 411 F. App’x 126, 127–28 (10th Cir. 2010).\\n\\n\\n\\n\\n 3\\n\\f In 2011, Defendant filed a pro se § 2255 motion claiming (1) that he was actually\\n\\ninnocent of making a material false statement to the INS in February 2002, because his\\n\\nwife’s age was not material to the application for adjustment of status, (2) that his\\n\\nattorney in the double-jeopardy appeal had been ineffective, and (3) that if the charge to\\n\\nwhich he pleaded had actually been making a false statement on a K-1 visa application\\n\\nfor S.K. in February 2002, his plea had no factual basis and any false statement was\\n\\nimmaterial because he had already obtained a K-1 fiancée visa by that time. The district\\n\\ncourt denied the motion, and we declined to issue a certificate of appealability. See Miles\\n\\nIII, 546 F. App’x at 736. We held that the collateral-review waiver in Defendant’s plea\\n\\nagreement barred any legal challenge to his guilty plea and, relevant to this appeal, that\\n\\nhe was not “factually innocent of making a false statement on the K–1 visa application he\\n\\nsubmitted for his fiancée.” Id. at 734.\\n\\n In 2013, after he had served his sentence, Defendant filed a pro se petition for a\\n\\nwrit of coram nobis under the All Writs Act, 28 U.S.C. § 1651(a). See United States v.\\n\\nDenedo, 556 U.S. 904, 911 (2009) (“In federal courts the authority to grant a writ of\\n\\ncoram nobis is conferred by the All Writs Act, which permits ‘courts established by Act\\n\\nof Congress’ to issue ‘all writs necessary or appropriate in aid of their respective\\n\\njurisdictions.’”). “A petition for a writ of coram nobis provides a way to collaterally\\n\\nattack a criminal conviction for a person . . . who is no longer ‘in custody’ and therefore\\n\\ncannot seek habeas relief under 28 U.S.C. § 2255 or § 2241.” Chaidez v. United States,\\n\\n568 U.S. 342, 345 n.1 (2013). But a remedy is rarely available. Federal courts are only\\n\\npermitted “to entertain coram nobis applications in extraordinary cases presenting\\n\\n\\n 4\\n\\fcircumstances compelling its use to achieve justice.” Rawlins v. Kansas, 714 F.3d 1189,\\n\\n1196 (10th Cir. 2013) (internal quotation marks omitted).\\n\\n Defendant’s petition asserted that he had thought his guilty plea was based on\\n\\nmaking a false statement on the 2002 adjustment-of-status form rather than the 2001 visa\\n\\napplication, that his trial counsel had told him that was the case, and that he discovered\\n\\nthat he had pleaded guilty to lying on the visa application only upon reading this court’s\\n\\ndecision on his § 2255 motion. The district court denied the petition, and we affirmed.\\n\\nSee United States v. Miles (Miles IV), 553 F. App’x 846, 849 (10th Cir. 2014). We held\\n\\nthat the petition was procedurally barred because Defendant had previously “had an\\n\\nadequate remedy under § 2255” for the claim he was asserting, and that he was not\\n\\nentitled to the miscarriage-of-justice exception to the bar because he had not shown his\\n\\nfactual innocence. Id. at 848–49.\\n\\n Finally, Defendant filed a second petition for a writ of coram nobis, the one at\\n\\nissue in this appeal. He claims that he is actually innocent of the false-statement offense\\n\\nto which he pleaded guilty because his false statement of S.K.’s age was not material to\\n\\neither the visa application or the application for adjustment of status. And he claims that\\n\\nhis trial counsel was ineffective in two respects: (1) for not fulfilling his duty under\\n\\nPadilla v. Kentucky, 559 U.S. 356 (2010), to adequately inform Defendant of the\\n\\nimmigration consequences of his plea, and (2) for failing to investigate the facts and law\\n\\non the materiality of Defendant’s false statement. The district court initially treated the\\n\\npetition as a successive § 2255 motion and dismissed it on that ground, but we reversed\\n\\nthat dismissal in United States v. Miles (Miles V), 697 F. App’x 601, 602 (10th Cir.\\n\\n\\n 5\\n\\f2017), on the ground that it is improper to recharacterize a petition by a person no longer\\n\\nin custody as a § 2255 motion. On remand the district court once again dismissed the\\n\\npetition, this time on the grounds that it was barred as an abuse of the writ, was barred by\\n\\nDefendant’s collateral-review waiver, and in any event did not satisfy the requirements\\n\\nfor a writ to issue. Agreeing in essence with the first ground, we need not address the\\n\\nothers.\\n\\n II. DISCUSSION\\n\\n A. General Principles Governing Collateral Attacks on Convictions\\n\\n Before filing the coram nobis petition at issue here, Defendant had appealed his\\n\\nsentence, pursued relief under § 2255, and sought relief under a prior coram nobis\\n\\npetition. The question naturally arises whether there is any limit to how many\\n\\npostconviction petitions he can file. Are there procedural barriers to such petitions, or\\n\\nmust we always address each issue he raises?\\n\\n There is a body of law limiting second or successive habeas corpus petitions\\n\\n(including applications under 28 U.S.C. §§ 2241 and 2254 and motions under § 2255),\\n\\nwhich are by far the most common avenues for challenges to convictions after direct\\n\\nappeals have been exhausted or not pursued. Although the Supreme Court has\\n\\nconsistently “rejected res judicata in a strict sense as a basis for dismissing a later habeas\\n\\naction,” it has “made clear that the prior adjudication [bears] vital relevance to the\\n\\nexercise of the court’s discretion in determining whether to consider the petition.”\\n\\nMcCleskey v. Zant, 499 U.S. 467, 482 (1991). Some of this law derives from statutory\\n\\nprovisions, particularly the Antiterrorism and Effective Death Penalty Act of 1996\\n\\n\\n 6\\n\\f(AEDPA), but several principles were developed through judicial decisions predating\\n\\nAEDPA. See id. at 489 (“[T]he doctrine of abuse of the writ refers to a complex and\\n\\nevolving body of equitable principles informed and controlled by historical usage,\\n\\nstatutory developments, and judicial decisions.”); Stanko v. Davis, 617 F.3d 1262, 1269\\n\\n(10th Cir. 2010) (“Long before AEDPA, and even before the enactment of § 2244, the\\n\\nSupreme Court developed several principles limiting the review of second or subsequent\\n\\nhabeas petitions.”).\\n\\n The successive-use-of-the-writ doctrine “authorized a federal court to decline to\\n\\nconsider a habeas petition presenting a claim that was previously raised and adjudicated\\n\\nin an earlier habeas proceeding, unless the court determined that hearing the claim would\\n\\nserve the ends of justice.” Stanko, 617 F.3d at 1269; see id. at n.7. The ends-of-justice\\n\\nexception had been described as requiring a “colorable showing of factual innocence,”\\n\\nMcCleskey, 499 U.S. at 495, although the test is now formulated to require a showing that\\n\\nthe alleged error “probably has caused the conviction of one innocent of the crime,”\\n\\nthereby “implicating a fundamental miscarriage of justice.” Id. at 494–95.\\n\\n “Another principle, abuse of the writ, authorized a court to decline to hear a\\n\\nsecond or subsequent habeas petition raising a claim that could have been presented in an\\n\\nearlier petition but was not.” Stanko, 617 F.3d at 1269. “[I]f a second or subsequent\\n\\npetition raises a claim that could have been raised in an earlier petition, the petitioner\\n\\nmust establish that the omission was not the result of inexcusable neglect in order to\\n\\nproceed on the new claim.” Id. at 1271. In other words, the petitioner must show “cause\\n\\nfor his failure to raise the claim in an earlier proceeding and resulting prejudice.” Stanko,\\n\\n\\n 7\\n\\f617 F.3d at 1271. “[T]he cause standard requires the petitioner to show that some\\n\\nobjective factor external to the defense impeded counsel’s efforts to raise the claim,” or\\n\\nthat the claim had not been raised because counsel had been “constitutionally\\n\\nineffective.” McCleskey, 499 U.S. at 493–94 (brackets and internal quotation marks\\n\\nomitted). This procedural bar also may be overcome if the petition comes within the\\n\\nmiscarriage-of-justice exception by “mak[ing] a proper showing of actual innocence.”\\n\\nMcQuiggin v. Perkins, 569 U.S. 383, 392 (2013) (internal quotation marks omitted); see\\n\\nStanko, 617 F.3d at 1271. A “proper showing” to overcome either bar requires “new\\n\\nevidence [that] shows it is more likely than not that no reasonable juror would have\\n\\nconvicted the petitioner.” McQuiggin, 569 U.S. at 395 (brackets and internal quotation\\n\\nmarks omitted). “New evidence” is “relevant evidence that was either excluded or\\n\\nunavailable at trial.” Schlup v. Delo, 513 U.S. 298, 327–28 (1995); see id. at 324 (“To be\\n\\ncredible, such a claim requires petitioner to support his allegations of constitutional error\\n\\nwith new reliable evidence—whether it be exculpatory scientific evidence, trustworthy\\n\\neyewitness accounts, or critical physical evidence—that was not presented at trial.”).\\n\\n We can think of no reason why these same restrictions should not apply to\\n\\npetitions for writs of coram nobis. The writ is not to be granted lightly. Its availability is\\n\\nlimited to “extraordinary cases presenting circumstances compelling its use to achieve\\n\\njustice.” Denedo, 556 U.S. at 911 (internal quotation marks omitted). As the First\\n\\nCircuit observed: “The further a case progresses through the remedial steps available to a\\n\\ncriminal defendant, the stiffer the requirements for vacating a final judgment. Thus,\\n\\ndirect review is more defendant-friendly than post-judgment review, and an initial habeas\\n\\n\\n 8\\n\\fpetition is easier for a criminal defendant to litigate than a successive one. The writ of\\n\\nerror coram nobis lies at the far end of this continuum.” United States v. George, 676\\n\\nF.3d 249, 258 (1st Cir. 2012) (citations omitted).\\n\\n Indeed, Tenth Circuit precedent already imposes a bar to coram nobis relief\\n\\n“unless relief under 28 U.S.C. § 2255 was unavailable or would have been inadequate.”\\n\\nUnited States v. Payne, 644 F.3d 1111, 1112 (10th Cir. 2011). In other words, a claim\\n\\npressed through a coram nobis petition is ordinarily barred if the petitioner previously\\n\\nraised the claim in a § 2255 motion but was unsuccessful or simply failed to pursue the\\n\\nclaim under § 2255 when petitioner could have. It is a small, and wholly logical, step to\\n\\nexpand this bar beyond previously available § 2255 motions to include all previously\\n\\navailable postconviction avenues for relief. We have done so in a nonprecedential\\n\\nopinion. See United States v. Tarango, 670 F. App’x 981, 981 (10th Cir. 2016) (Gorsuch,\\n\\nJ.) (“A writ of coram nobis may not be used to litigate issues that were or could have\\n\\nbeen raised on direct appeal or through collateral litigation, including a 28 U.S.C. § 2255\\n\\nmotion.”). We now adopt that proposition here. Absent those traditional grounds that\\n\\nhave excused successive or abusive habeas petitions, a petition for writ of coram nobis\\n\\nmust be rejected if the claim was raised or could have been raised on direct appeal,\\n\\nthrough a § 2255 motion, or in any other prior collateral attack on the conviction or\\n\\nsentence. Our view finds support in decisions from other circuits. See United States v.\\n\\nSwindall, 107 F.3d 831, 836 n.7 (11th Cir. 1997); United States v. Camacho-Bordes, 94\\n\\nF.3d 1168, 1172–73 (8th Cir. 1996); United States v. Bartlett, Nos. 90-6345, 90-6351,\\n\\n1990 WL 135645, at *1 n.* (4th Cir. Sept. 20, 1990). But see United States v. Darnell,\\n\\n\\n 9\\n\\f716 F.2d 479, 481 n.5 (7th Cir. 1983) (the abuse-of-the-writ doctrine does not apply to\\n\\ncoram nobis petitions, because the narrow scope of the writ “ensures that coram nobis\\n\\nwill not be utilized as a substitute for appeal”).\\n\\n B. Application to This Case\\n\\n Defendant’s petition asserts two grounds for relief: (1) that he is actually innocent\\n\\nof the false-statement offense to which he pleaded guilty, because his false statement of\\n\\nS.K’s age was not material1, and (2) that he received ineffective assistance of counsel in\\n\\nconnection with his guilty plea, because his trial counsel did not inform him of potential\\n\\nimmigration consequences of his guilty plea and did not adequately investigate the\\n\\nfactual basis of his guilty plea. Both are procedurally barred.\\n\\n Defendant’s actual-innocence claim was raised and rejected in prior collateral\\n\\nattacks. In his § 2255 proceeding we held that his falsification of S.K.’s age in the visa\\n\\napplication was a material falsehood and he was not actually innocent of the charge even\\n\\nif the date in the information was incorrect. See Miles III, 546 F. App’x at 732–34. And\\n\\nin upholding the rejection of his first coram nobis petition, we determined that Defendant\\n\\nclearly understood at the time of his plea that he was pleading guilty to a false statement\\n\\nrelated to the visa application, not the application for adjustment of status. See Miles IV,\\n\\n553 F. App’x at 849.\\n\\n\\n1\\n The Supreme Court has “not resolved whether a prisoner may be entitled to habeas\\nrelief based on a freestanding claim of actual innocence” McQuiggin, 569 U.S. at 391;\\nsee also Herrera v. Collins, 506 U.S. 390, 400 (1993) (“Claims of actual innocence based\\non newly discovered evidence have never been held to state a ground for federal habeas\\nrelief absent an independent constitutional violation occurring in the underlying state\\ncriminal proceeding.”).\\n\\n 10\\n\\f As for Defendant’s first ineffective-assistance claim, he relies on the Supreme\\n\\nCourt’s decision in Padilla, which postdated his conviction. Perhaps coram nobis is a\\n\\nproper avenue for relief if a claim is based on Supreme Court law that was declared after\\n\\nthe defendant had fully served the criminal sentence. Cf. United States v. Snyder, 871\\n\\nF.3d 1122, 1127 (10th Cir. 2017) (“Cause excusing procedural default is shown if a claim\\n\\nis so novel that its legal basis was not reasonably available to counsel at the time of the\\n\\ndirect appeal.” (brackets and internal quotation marks omitted)). But that is not the case\\n\\nhere. Padilla was decided on March 31, 2010, and Defendant filed his § 2255 motion in\\n\\n2011. Moreover, the claim could have been included in his 2013 coram nobis petition.2\\n\\n\\n2\\n There is a much more disturbing reason why Defendant’s Padilla claim fails. Although\\nhe is a citizen of Sweden, his counsel conceded at oral argument that he is also a\\nnaturalized United States citizen. Padilla concerns counsel’s obligation “to inform [a]\\nnoncitizen client that he faces a risk of deportation.” 559 U.S. at 374 (emphasis added).\\nTo pursue this claim, Defendant falsely states in his coram nobis petition and his affidavit\\nin support of the petition that he is an “alien national.” His briefs on appeal do not state\\noutright that he is not a citizen, but his opening brief states that he is a “foreign national,”\\nAplt. Br. at 34, his reply brief states that “the government has failed to provide any\\nproof . . . that [he] is a U.S. Citizen,” Reply Br. at 23, and both briefs continue to press\\nthe Padilla claim.\\n\\n The apparently knowing and material misrepresentations in Defendant’s filings are\\npotential violations of the rules of professional conduct for the United States District\\nCourt for the Western District of Oklahoma, and the rules of professional conduct in\\nCalifornia and Nevada, two states in which Defendant’s counsel, Don P. Chairez, is\\nlicensed to practice law. It appears that Defendant is currently not eligible to practice law\\nin California for administrative reasons, but these misrepresentations might justify\\nprofessional discipline against him as well. We direct the clerk to forward copies of this\\nopinion to the State Bar of California and the State Bar of Nevada so that they can assess\\nwhether counsel’s conduct and/or Miles’s conduct warrants any sanction. See In re\\nGraham, 981 F.2d 1135, 1142 (10th Cir. 1992) (“A court may . . . report misconduct by\\na[n] . . . attorney to that attorney’s bar association for the purpose of instituting\\ndisciplinary proceedings.”); Lail v. Apfel, No. 98-7079, 1999 WL 147305, at *2 (10th\\nCir. Mar. 18, 1999) (“[C]ontinued misrepresentations to this court . . . may\\n\\n 11\\n\\f It is even clearer that Defendant’s second ineffective-assistance claim could have\\n\\nbeen raised earlier. The matters that he contends his counsel should have discovered\\n\\nbefore he pleaded guilty were all presented in his § 2255 proceedings. He was aware of\\n\\neverything that he needed to raise the present ineffective-assistance claim.\\n\\n To be sure, the procedural bars to Defendant’s present claims may be overcome in\\n\\ncertain circumstances. But Defendant has not identified any legitimate ground to do so\\n\\nhere. He argues that cause for his failure to raise his ineffective-assistance-of-trial-\\n\\ncounsel claims is present because of (1) ineffectiveness of trial counsel—in the very\\n\\nrespects that he complains of in his coram nobis petition, (2) “new developments in law,”\\n\\nAplt. Br. at 41, and (3) “extrinsic fraud,” id. at 43. We are not persuaded. He does not\\n\\nexplain how ineffectiveness of trial counsel kept him from arguing his ineffectiveness\\n\\nclaims in his § 2255 proceedings or his first coram nobis petition; the cases he cites as\\n\\n“new developments” are not essential, or even material, to his present claims; and the\\n\\nevidence of asserted fraud is only the untrue allegation that the prosecution and the courts\\n\\nincorrectly characterized his guilty plea as being to his false statement on the visa\\n\\napplication.\\n\\n Nor can Defendant rely on the actual-innocence exception to procedural bar. The\\n\\nonly new evidence he puts forward in support of his argument for actual innocence is a\\n\\n\\nlead . . . to . . . a referral to the Oklahoma State Bar for possible disciplinary\\nproceedings.”). Because counsel informed this court during oral argument that Miles is\\nalso a medical doctor, we direct the clerk to forward copies of this opinion to the\\nOklahoma Medical Board, the New York Office of Professional Medical Conduct, the\\nArizona Medical Board, and the Medical Board of California, all states in which Miles\\nwas licensed to practice medicine.\\n\\n 12\\n\\f2013 Department of Homeland Security guidance document that he claims tends to prove\\n\\nthat a 14-year-old can qualify for a fiancée visa. He argues that this document establishes\\n\\nthat his false statement of S.K’s age was not material. But we doubt that this document\\n\\nwould have affected our reasoning in rejecting Defendant’s actual-innocence claim in his\\n\\n§ 2255 proceeding. See Miles III, 546 F. App’x at 734 (“[I]n assessing the ability of Mr.\\n\\nMiles and his fiancée to conclude a valid marriage within ninety days of her arrival for\\n\\npurposes of the K–1 visa, the true age of his fiancée, which would have triggered\\n\\nsignificant if not conclusive impediments, was plainly a material consideration.”). It does\\n\\nnot make it “more likely than not that no reasonable juror would have convicted him.”\\n\\nSchlup, 513 U.S. at 327.\\n\\n III. CONCLUSION\\n\\n We AFFIRM the denial of Defendant’s petition.\\n\\n\\n\\n\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2255,"cells":{"id":{"kind":"number","value":8443990,"string":"8,443,990"},"name":{"kind":"string","value":"UNITED STATES of America v. Allari GUZMAN"},"name_abbreviation":{"kind":"string","value":"United States v. Guzman"},"decision_date":{"kind":"string","value":"2019-05-03"},"docket_number":{"kind":"string","value":"No. 18-3135"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415424/\"}]}"},"judge1":{"kind":"string","value":""},"judge2":{"kind":"string","value":""},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443990/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America v. Allari GUZMAN\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America v. Allari GUZMAN\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2256,"cells":{"id":{"kind":"number","value":4616959,"string":"4,616,959"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Christopher Lee MARTINEZ, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Martinez"},"decision_date":{"kind":"string","value":"2019-05-06"},"docket_number":{"kind":"string","value":"18-8007"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Hartz, Matheson, Eid\", \"parties\": \"\", \"opinions\": [{\"author\": \"HARTZ, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 6, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n UNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v. No. 18-8007\\n\\n CHRISTOPHER LEE MARTINEZ,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Wyoming\\n (D.C. No. 2:17-CR-00213-NDF-1)\\n _________________________________\\n\\nNeil D. Van Dalsem, Office of the Federal Public Defender, Muskogee, Oklahoma, for\\nDefendant-Appellant.\\n\\nTimothy J. Forwood, Assistant United States Attorney (Mark A. Klaassen, United States\\nAttorney, District of Wyoming, with him on the brief), Cheyenne, Wyoming, for\\nPlaintiff-Appellee.\\n _________________________________\\n\\nBefore HARTZ, MATHESON, and EID, Circuit Judges.\\n _________________________________\\n\\nHARTZ, Circuit Judge.\\n _________________________________\\n\\n A jury in the United States District Court for the District of Wyoming convicted\\n\\nDefendant Christopher Lee Martinez on one count of attempting to entice a minor to\\n\\nengage in illegal sexual activity. See 18 U.S.C. § 2422(b). On appeal Defendant argues\\n\\fthat the district court (1) should have authorized funds for a forensic psychologist, (2)\\n\\nimproperly excluded evidence of his history of mental illness, and (3) should have\\n\\nallowed him to present evidence of his character for truthfulness. Exercising jurisdiction\\n\\nunder 28 U.S.C. § 1291, we affirm.\\n\\n I. BACKGROUND\\n\\n A. Defendant’s Arrest\\n\\n On July 22, 2017, Special Agent Brent Metcalfe of the Wyoming Division of\\n\\nCriminal Investigation (DCI) posted a personal advertisement on the “Casual\\n\\nEncounters” section listed on the Craigslist website at that time. The purpose of the\\n\\nposting was to ferret out those who used the Internet to arrange sexual encounters with\\n\\nminors. Metcalfe chose the date because of the expected influx of tourists for Cheyenne\\n\\nFrontier Days. The advertisement was entitled “Fresh CFD Taboo” and read: “In town\\n\\nwith my dau. She is very eager. She wants to experience what Cheyenne has to offer.\\n\\nWho wants to have some ‘fresh fun.’” R., Vol. 3 at 247–49. Metcalfe explained that he\\n\\nused the terms fresh and eager to communicate to the reader that the subject of the\\n\\nadvertisement was young and sexually inexperienced.\\n\\n Defendant, 27 years old at the time, was one of the first to respond, sending a\\n\\nmessage shortly before 4:00 p.m. The email messages were relayed by Craigslist\\n\\nbetween the correspondents. Metcalfe posed as the father, telling Defendant that he\\n\\nhoped to “find a guy for my daughter, but she’s younger.” Id. at 256. When Defendant\\n\\nasked how old the girl was, Metcalfe answered that she was 12. Defendant said: “Okay.\\n\\nWhen you thinking? I’ll think about it. You ain’t a cop or law enforcement?” Id. at 257.\\n\\n\\n 2\\n\\fMetcalfe assured him that he was not a cop and the conversation continued. It centered\\n\\non whether Defendant wanted to have sexual relations with the daughter. Defendant\\n\\nasked Metcalfe what sexual acts he could engage in with the girl, whether he could take\\n\\nher virginity, and whether Metcalfe had condoms. Defendant repeatedly sought\\n\\nassurances that Metcalfe was not a “cop,” explaining that he was nervous because the\\n\\npolice had “popped a lot of people” during Frontier Days the previous year. Id. at 287.\\n\\n With Defendant’s interest established, Metcalfe requested that they move their\\n\\nconversation to “Kik,” an instant-messaging application that better allowed investigators\\n\\nto obtain Defendant’s identity. Defendant agreed. After he asked Metcalfe to send him a\\n\\npicture of the daughter, the two agreed to exchange pictures. Metcalfe sent Defendant a\\n\\npicture of part of the chest of a life-like mannequin. Defendant asked for another picture\\n\\nof the child’s full body with no face. Metcalfe refused to send additional pictures but\\n\\nagreed that Defendant could come to his motel to take his daughter’s “V card” (referring\\n\\nto her virginity). Id. at 302. Defendant eventually asked to message with the daughter\\n\\ndirectly, and Metcalfe assumed the girl’s identity. Defendant asked if she wanted to “lose\\n\\n[her] V card?” When Metcalfe asked what that meant, Defendant said “Virginity.” Id. at\\n\\n310. After exchanging about 100 messages over almost five hours, Defendant agreed to\\n\\nmeet at a motel and said that he would bring a condom.\\n\\n At 8:48 p.m., Defendant arrived at the motel parking lot and messaged Metcalfe,\\n\\nasking him to come out. Metcalfe and several other officers exited their vehicles and\\n\\narrested Defendant in his truck. He was in possession of a phone and a condom.\\n\\nForensic analysis confirmed that the phone was the one used to communicate with\\n\\n\\n 3\\n\\fMetcalfe on the Kik application. When interviewed by officers at the scene, Defendant\\n\\nadmitted to sending the messages but stated that he was getting ready to call the police\\n\\nbefore he was arrested. When asked why he had a condom, he said something like, “You\\n\\nhave to be real.” Id. at 321.\\n\\n B. Pretrial Motions\\n\\n Defense counsel filed a pretrial motion under 18 U.S.C. § 3006A requesting a\\n\\nforensic psychologist at the government’s expense. The motion stated the charge against\\n\\nDefendant, the trial date, the cost of a forensic evaluation and polygraph by Dr. Charles\\n\\nW. Dennison CP, Defendant’s minimal employment history, and his lack of funds to pay\\n\\nDr. Dennison. Other than stating that Defendant was on Social Security disability with a\\n\\nmental-health diagnosis, the motion said nothing regarding his mental health and the need\\n\\nfor an evaluation except as follows:\\n\\n Defendant was diagnosed with bipolar disorder, attention deficit disorder\\n (ADD), schizophrenia and depression when he was 18 years old. The\\n diagnosis was at Peak Wellness, Cheyenne, Wyoming. Defendant has a\\n Mental Health history of attempted suicide at 18 years of age,\\n hallucinations with the last occurrence taking place about 4-5 years ago.\\n Defendant was prescribed Trazadone, Invega, Amitriptyline, Abilify and\\n Fluoxetine. He is currently off medication.\\n\\n ...\\n\\n Due to the nature of the charges in this matter, a forensic evaluation is\\n necessary.\\n\\nR., Vol. 1 at 29. The district court denied the motion, saying:\\n\\n Defendant failed to provide the Court with information regarding the\\n necessity for a forensic evaluation by Dr. Dennison at Government\\n expense. The Court routinely grants forensic evaluations in cases involving\\n receipt of child porn, for purposes of sentencing mitigation. However, this\\n\\n\\n 4\\n\\f case involves attempted enticement of a minor. . . . Given the mandatory\\n minimum sentence in this case, it is not clear the purpose of a forensic\\n evaluation. Defendant has failed to provide the Court with any explanation\\n of the necessity for an evaluation, either for trial or sentencing purposes. IT\\n IS ORDERED that Defendant’s Motion for Forensic Psychologist at\\n Government Expense is DENIED at this time based on the Court’s finding\\n that Defendant has not established the necessity for this evaluation.\\n\\nR., Vol. 2 at 12 (italics added). Defense counsel did not renew the motion or later\\n\\nprovide further justification for a forensic psychologist.\\n\\n The government then filed a motion in limine to prevent Defendant from\\n\\npresenting evidence of his character for truthfulness and honesty and to exclude any\\n\\nevidence of his mental illness. On the first issue, it argued that because the charged\\n\\noffense of enticement of a minor is not a crimen falsi (that is, an offense in which a lie by\\n\\nthe defendant is one of the elements of the crime), testimony regarding Defendant’s\\n\\ncharacter for truthfulness was not relevant. Accordingly, it requested that Defendant’s\\n\\nuse of character evidence be limited to evidence that he is law abiding. The court agreed\\n\\nthat Defendant had not shown a basis for offering evidence of his character for\\n\\ntruthfulness, but said that it would later rule on specific issues related to character\\n\\nevidence that might arise during trial.\\n\\n On the second issue, the government contended that absent an insanity defense,\\n\\nevidence of Defendant’s mental defects or lack of volitional control was not an allowable\\n\\ndefense. Although the government acknowledged that evidence of mental health could\\n\\nbe admitted to negate specific intent, it pointed out that Defendant bore the burden of\\n\\nshowing that the proffered evidence was being offered for that purpose. This issue was\\n\\naddressed at the final pretrial conference, where the court gave defense counsel the\\n\\n\\n 5\\n\\fopportunity to explain the purpose of introducing evidence of Defendant’s mental health.\\n\\nDefense counsel stated:\\n\\n So my plan was to introduce a very limited number of medical records that\\n I’ve provided to the Government, and they basically just state that Mr.\\n Martinez was diagnosed with bipolar, I think back in 2010; that he was\\n prescribed medication. He’s also got ADD, I believe. And the only\\n purpose of those records is because I would have him testify and his family\\n testify that he has these mental issues and that his mental state of mind is\\n important because one of the elements in this case is that he obviously\\n knowingly had to complete this act, and that goes to that element of\\n whether or not he knowingly completed this act.\\n\\n And the medical records themselves are really just to – there to corroborate\\n what he would testify to about his own character and state of mind.\\n\\nR., Vol. 3 at 34 (emphasis added). Defense counsel acknowledged that Defendant “did\\n\\nnot plead guilty by reason of mental illness” but argued that the jury should decide\\n\\n“whether or not [his mental illness] affected his decision to do the things he did or not.”\\n\\nId. at 35. And responding to the arguments by the government, he said:\\n\\n We’re offering it to show his potential state of mind in general and who he\\n is. And this is a person – and like I said, I don’t know how you can – the\\n Court or any court could preclude an individual from getting on the stand\\n and testifying that, “Yes, I’m – you know, this is my background. I have\\n these issues that I’ve dealt with. I was on medication, but I wasn’t taking\\n the medication at the time,” and to describe his general makeup, I suppose.\\n\\nId. at 38.\\n\\n The court granted the motion in limine. It expressed concern that the proffered\\n\\nmental-illness testimony would “create[] the potential for confusion by the jury and\\n\\nseek[ ] to suggest a justification as opposed to a defense to any of the elements that the\\n\\nGovernment is required to prove by proof beyond a reasonable doubt.” Id. at 39. It noted\\n\\nthat this court had held “that psychological and psychiatric evidence that negates the\\n\\n\\n 6\\n\\fessential element of specific intent can be admissible” but that the admission of such\\n\\nevidence required clear demonstration of “how such evidence would negate intent rather\\n\\nthan merely present a dangerously confusing theory of defense more akin to justification\\n\\nand excuse.” R., Vol. 1 at 72 (internal quotation marks omitted). The court concluded\\n\\nthat without an expert or current medical records, Defendant lacked mental-health\\n\\nevidence showing “some cognitive defect precluding him from forming the specific\\n\\nintent for the charged offense” and thus the proffered evidence was irrelevant. Id. at 73.\\n\\n C. Trial\\n\\n The prosecution called only three witnesses at trial: Special Agent Robert\\n\\nLeazenby of the Wyoming DCI testified in general about the conduct of child-\\n\\nexploitation investigations; Agent Metcalfe testified about his communications with\\n\\nDefendant; and Mark Timmons of the Wyoming DCI testified about his search of\\n\\nDefendant’s car after the arrest.\\n\\n Before calling any witnesses, Defendant renewed his request to be permitted to\\n\\noffer mental-health evidence. He pointed to testimony by Agent Leazenby that\\n\\ninvestigators like to talk to arrestees in such cases to determine their states of mind. The\\n\\nprosecutor pointed out, however, that the state of mind Leazenby was referring to was\\n\\nwhether or not the arrestee wanted to have sex with the child. When the court asked\\n\\ndefense counsel how the mental-health evidence would relate to the instruction on the\\n\\nknowingly element of the offense, counsel responded that he wanted to put on the\\n\\nevidence simply as background evidence:\\n\\n\\n\\n\\n 7\\n\\f But that’s who he is and that’s kind of his general makeup, just as if a\\n person was employed and is – you know, as an officer and they’ve been\\n doing that for ten years. Well, in the last ten years he’s been doing really\\n nothing. Why has he been doing nothing? Because he’s on [Social\\n Security benefits], and the jury is going to know why he’s on [Social\\n Security benefits]. Well, that’s why.\\n\\nR., Vol. 3 at 377. The court was not persuaded. It held that while information\\n\\nconcerning Defendant’s background may be relevant for sentencing purposes, it was not\\n\\nrelevant at the trial.\\n\\n Defendant’s evidence consisted of (1) his own testimony, explaining that he was\\n\\nnot engaged in criminal activity but, rather, was attempting to identify someone engaged\\n\\nin child exploitation, whom he would report to law-enforcement authorities, and (2) six\\n\\nwitnesses who testified to his character as a law-abiding citizen.\\n\\n Defendant also unsuccessfully attempted to put on evidence of his character for\\n\\ntruthfulness, which he claimed had been attacked during his cross-examination by the\\n\\nprosecution. He argued that such evidence would assist the jury in determining whether\\n\\nto believe his statement that he did not intend to engage in sex with a minor. The court\\n\\nrejected the argument, reaffirming its earlier ruling that such evidence was not relevant\\n\\nbecause the charged offense did not include an element that concerned truthfulness. It\\n\\nfurther observed that because the bulk of the evidence in the case involved contradictory\\n\\nstatements made by Defendant before and after his arrest, testimony regarding his\\n\\ncharacter for truthfulness would not be probative in helping the jury decide which if any\\n\\nof his statements to believe.\\n\\n\\n\\n\\n 8\\n\\f II. DISCUSSION\\n\\n A. Denial of Motion to Hire Forensic Psychologist\\n\\n The Criminal Justice Act (CJA) permits a court to authorize funding for an expert\\n\\nwitness at the government’s expense:\\n\\n Counsel for a person who is financially unable to obtain investigative,\\n expert, or other services necessary for adequate representation may request\\n them in an ex parte application. Upon finding, after appropriate inquiry in\\n an ex parte proceeding, that the services are necessary and that the person is\\n financially unable to obtain them, the court . . . shall authorize counsel to\\n obtain the services.\\n\\n18 U.S.C. § 3006A(e)(1). The defendant bears the burden of persuasion. See United\\n\\nStates v. Greschner, 802 F.2d 373, 376 (10th Cir. 1986). The necessity of services must\\n\\nbe established with specificity. In the present context, “[g]eneral allegations supporting a\\n\\nrequest for court appointment of a psychiatric expert, without substantive supporting\\n\\nfacts, and undeveloped assertions that psychiatric assistance would be beneficial to the\\n\\ndefendant will not suffice to require the appointment of a psychiatrist to aid in the\\n\\npreparation of a criminal defense.” Liles v. Saffle, 945 F.2d 333, 336 (10th Cir. 1991).\\n\\nWe review the denial of a CJA funding request for an abuse of discretion. See United\\n\\nStates v. Solon, 596 F.3d 1206, 1210 (10th. Cir. 2010).\\n\\n On appeal Defendant argues that psychiatric testimony could have supported his\\n\\ndefense that he was merely trying to catch sexual predators, not trying to be one himself.\\n\\nHe states:\\n\\n [Defendant’s] case provides a classic example of how psychological\\n evidence can be relevant in evaluating a defendant’s specific intent.\\n\\n\\n\\n\\n 9\\n\\f [Defendant] was charged with an attempt crime, a specific intent crime.[1]\\n What he was actually thinking is of critical importance. [Defendant’s]\\n entire defense to this case was that he did not really intend to break the law\\n by enticing a minor to have sex. He defended this case on the ground that\\n he intended to identify a person who was offering up a minor for sex.\\n\\n For the jurors to evaluate that assertion, they certainly needed to know\\n about [Defendant’s] mental illness. The government’s case was based on\\n an argument that it would be completely bizarre for a person to have taken\\n steps [Defendant] took without first calling law enforcement. [Defendant]\\n should have been allowed to prepare a defense that informed the jury, that,\\n in fact, he is a person who suffers from mental illness, and he legitimately\\n may not proceed as a rational person would.\\n\\n Even though his conduct may seem strange, he was not trying to commit a\\n crime. To the contrary, from the moment of his arrest, he explained that he\\n was trying to catch a criminal. A casual observer might find his\\n explanation, provided by a “normal” person, to not make a great deal of\\n sense or be persuasive. However, in evaluating [Defendant’s] explanation,\\n the jurors needed to know that, in fact, [Defendant] is mentally ill. While a\\n mentally healthy person may not have tried to catch the Craigslist poster, a\\n person with bipolar disorder may well have done so.\\n\\nAplt. Br. at 25–26.\\n\\n This is an interesting argument, but we need not address it because it was not\\n\\nraised below and Defendant does not argue for plain-error review on appeal. See United\\n\\n\\n\\n1\\n To establish a violation of § 2422(b), the government must prove that the defendant\\n“(1) [used] a facility of interstate commerce; (2) to knowingly persuade, induce, entice, or\\ncoerce; (3) any individual who is younger than 18; (4) to engage in any sexual activity for\\nwhich any person can be charged with a criminal offense or attempting to do so.” United\\nStates v. Faust, 795 F.3d 1243, 1248 (10th Cir. 2015) (internal quotation marks omitted).\\n“To prove an attempt crime, the government must prove (1) an intent to commit the\\nsubstantive offense; and (2) the commission of an act which constitutes a substantial step\\ntowards commission of the substantive offense, . . . [which] must be something more than\\nmere preparation.” United States v. Vigil, 523 F.3d 1258, 1267 (10th Cir. 2008)\\n(typographical errors corrected and internal quotation marks omitted). Thus, in this case\\nthe government had to show that Defendant intended to entice a girl under 18 years old to\\nengage in criminal sexual activity.\\n\\n 10\\n\\fStates v. McGlothin, 705 F.3d 1254, 1267 (10th Cir. 2013) (if appellant forfeits an\\n\\nargument before the district court and then fails to explain in appellate briefing how the\\n\\nargument survives appellate review under the plain-error standard, then the appellant has\\n\\nwaived the argument on appeal). In his pretrial motion he stated that he suffered from\\n\\nvarious mental illnesses. But he did not even attempt to explain how these disorders\\n\\ncould negate any element of the charged crime. He wrongly assumes that simply putting\\n\\nthe court on notice that he suffered from mental-health disorders was somehow enough to\\n\\nsatisfy his burden. It is not the job of the court, however, to come up with arguments\\n\\nwhy a defendant’s mental illness must have influenced his conduct in committing a\\n\\ncrime.\\n\\n Further, the court’s order said that Defendant’s motion was merely denied “at this\\n\\ntime” for lack of the requisite showing. It left open the opportunity for Defendant to\\n\\nproperly explain why the forensic psychologist was needed. If the need for such an\\n\\nexpert should have been obvious to the court, Defendant could have easily explained the\\n\\npoint. Yet Defendant never pursued the issue again. We cannot fault the district court\\n\\nfor denying Defendant’s motion in light of the remarkably sparse argument he proffered.\\n\\nWe see no abuse of discretion here. (To the extent that Defendant attempts to raise for\\n\\nthe first time on appeal a due-process challenge to the denial of an expert, we also decline\\n\\nto address that argument. See id.)\\n\\n B. Exclusion of Evidence of Defendant’s Mental-Health History\\n\\n At trial Defendant unsuccessfully requested that the district court permit him to\\n\\noffer evidence of his history of mental illness, including medical records from more than\\n\\n\\n 11\\n\\ffive years past, his testimony, and his wife’s testimony. The court ruled that it was\\n\\nirrelevant. “We review a district court’s evidentiary rulings for abuse of discretion,\\n\\nconsidering the record as a whole.” United States v. Trujillo, 136 F.3d 1388, 1395 (10th\\n\\nCir. 1998). An evidentiary decision will not be reversed if it “falls within the bounds of\\n\\npermissible choice in the circumstances and is not arbitrary, capricious or whimsical.”\\n\\nUnited States v. Wills, 826 F.3d 1265, 1270 (10th Cir. 2016) (internal quotation marks\\n\\nomitted).\\n\\n On appeal Defendant argues, as he did with respect to the denial of funds for a\\n\\npsychiatric expert, that this mental-illness evidence could support his defense that he was\\n\\nnot seeking a sexual partner but was trying to catch a sexual predator. He contends that\\n\\nthe evidence would “explain[] that his arguably irrational behavior was the product of his\\n\\nmental illness.” Aplt. Br. at 34. Again, however, he did not raise this argument in\\n\\ndistrict court, so we will not address it. See McGlothin, 705 F.3d at 1267.\\n\\n What Defendant did argue in district court was that evidence of his mental illness\\n\\nwas relevant to communicating his overall background to the jury. To establish that\\n\\nDefendant offered no relevant purpose for the mental-health evidence, we set forth\\n\\nextended excerpts of defense counsel’s colloquy with the court when he renewed his\\n\\nmotion to admit the evidence. During the colloquy, counsel made clear that the purpose\\n\\nof the evidence was simply to tell the jury what kind of person Defendant is:\\n\\n DEFENSE COUNSEL: [A]s I understand the Court’s order, I’m not\\n allowed to introduce any evidence concerning his mental-health.\\n\\n However, in talking with him and providing the background for the jury of\\n what he’s – who he is and what he’s doing, I think it is necessary to state at\\n\\n\\n 12\\n\\fleast to a certain extent that, number one, that he’s on – he’s been on SSI\\n[Social Security] since he was 17 for ADD, bipolar and depression, and\\nthat’s what he’s been doing for the last 10 years. He doesn’t work.\\n\\nSo we at least need to explain that to the jury, that I think he should be\\nallowed to say, “Hey, this is what I’ve been doing for the last 10 years. I\\nwas on medication. I was off medication because I didn’t like it,” whatever\\nreason.\\n....\\n[A]nd if you look at the instructions, the knowingly instruction also talks\\nabout a person’s state of mind. And so the jury is going to consider his\\nstate of mind, and we’re telling them to.\\n...\\nTHE COURT [after also hearing from the prosecution]: How does the\\nstated diagnosis speak to the considerations in Instruction 24 which is that\\nhe was conscious and aware of his actions, realized what he was doing or\\nwhat was happening around him and did not act because of ignorance,\\nmistake or accident? Even assuming that the diagnosis is – would be the\\ndiagnosis today by a qualified healthcare professional, how does that\\ndiagnosis relate to the instruction on knowingly?\\n\\nDEFENSE COUNSEL: Well, Your Honor, I think we’re talking about two\\ndifferent things here. And, number one, I am not trying to introduce this\\nevidence as evidence that he had a mental defect at the time and did not act\\nin accordance with the statute because of that mental defect.\\n\\nWhat I am trying to introduce, simply, is that we have an individual that has\\nmental issues or a mental diagnosis and he’s been on SSI and it is part of\\nhis background. Now, there’s a reason for that and the jury, I think, is\\ngoing to want to know what he’s – who this person is.\\n\\nSo, number one, I don’t think anything is prohibitive of talking about an\\nindividual’s background, what he’s been doing. So I think that is fair game.\\n...\\nSo I don’t – like I said, I’m not going to use it. I don’t think – I wasn’t\\nplanning on bringing an expert to come in and testify that he suffers from\\ndepression, ADD and bipolar, and therefore, that’s what – why he\\ncommitted this act. . . .\\n\\nAnd that’s not what our intent is here. The only reason I want to introduce\\nthe records is to show that when he says, “yeah, I’ve been on SSI,” that’s\\ndocumented and the jury doesn’t think that he is faking it or just some\\nperson out there not – by choice not working in kind of a low-life situation\\nby choice.\\n\\n 13\\n\\f So we are not offering as mental health defense that information, but\\n merely as background information and that’s who this person is and what\\n he’s been doing. The jury can do whatever they want with it, I suspect.\\n\\nR., Vol. 3 at 372–78.\\n\\n “Evidence is relevant if: (a) it has any tendency to make a fact more or less\\n\\nprobable than it would be without the evidence; and (b) the fact is of consequence in\\n\\ndetermining the action.” Fed. R. Evid. 401. To be sure, “[t]he bar for admission under\\n\\nRule 401 is very low”; the evidence need “only provide a fact-finder with a basis for\\n\\nmaking some inference, or chain of inferences.” United States v. Jordan, 485 F.3d 1214,\\n\\n1218 (10th Cir. 2007) (internal quotation marks omitted). But Defendant’s proffered\\n\\nground for admitting this evidence did not meet even this low bar. Defense counsel\\n\\nnever suggested a chain of inference from this evidence to an element of the crime or a\\n\\ndefense.\\n\\n We recognize that it is generally appropriate to humanize a witness by letting the\\n\\nwitness tell the jury a few things about himself or herself. But even if such background\\n\\ninformation can be admissible, Federal Rule of Evidence 403 permits exclusion of even\\n\\nrelevant evidence “if its probative value is substantially outweighed by the danger of . . .\\n\\nunfair prejudice, confusing the issues, [or] misleading the jury.” Courts must be cautious\\n\\nabout admitting marginally relevant mental-health evidence because the jury may think\\n\\nthat it provides an “excuse” for misconduct or it may otherwise generate sympathy for the\\n\\ndefendant. See United States v. Cameron, 907 F.2d 1051, 1067 (11th Cir. 1990)\\n\\n(“[P]sychiatric evidence . . . presents an inherent danger that it will distract the jury[ ]\\n\\nfrom focusing on the actual presence or absence of mens rea, and . . . may easily slide\\n\\n\\n 14\\n\\finto wider usage that opens up the jury to theories of defense more akin to justification.”\\n\\n(internal quotation marks omitted)). Here, the district court permitted some humanizing\\n\\nevidence, such as Defendant’s testimony that he was unemployed and on social-security\\n\\nbenefits, because it saw no danger of improper prejudice or confusing the jury. But it\\n\\nexcluded the mental-health evidence, which it viewed as “just an effort to elicit\\n\\nsympathy.” R., Vol. 3 at 378. This ruling was not an abuse of discretion.\\n\\n C. Exclusion of Character Evidence\\n\\n Defendant argues that the district court abused its discretion in excluding evidence\\n\\nof his character for truthfulness after his credibility was allegedly attacked on cross-\\n\\nexamination. He contends that the court’s decision to exclude evidence of his character\\n\\nfor truthfulness was based on a misapplication of Rule 608 of the Federal Rules of\\n\\nEvidence. “We review a trial court’s exclusion of character evidence for abuse of\\n\\ndiscretion.” Tanberg v. Sholtis, 401 F.3d 1151, 1167 (10th Cir. 2005). But we review de\\n\\nnovo the district court’s legal interpretation of the Federal Rules of Evidence. See United\\n\\nStates v. Torrez-Ortega, 184 F.3d 1128, 1132 (10th Cir. 1999).\\n\\n Under Rule 608 a witness’s credibility ordinarily may be attacked by presenting\\n\\nevidence of the witness’s character for untruthfulness, but positive evidence of a truthful\\n\\ncharacter is permitted only in response to an attack on such character:\\n\\n Reputation or Opinion Evidence. A witness’s credibility may be attacked\\n or supported by testimony about the witness’s reputation for having a\\n character for truthfulness or untruthfulness, or by testimony in the form of\\n an opinion about that character. But evidence of truthful character is\\n admissible only after the witness’s character for truthfulness has been\\n attacked.\\n\\n\\n\\n 15\\n\\fFed. R. Evid. 608(a). An advisory committee note clarifies what constitutes an attack on\\n\\ncharacter for truthfulness:\\n\\n Opinion or reputation that the witness is untruthful specifically qualifies as\\n an attack under the rule, and evidence of misconduct, including conviction\\n of crime, and of corruption also fall within this category. Evidence of bias\\n or interest does not. Whether evidence in the form of contradiction is an\\n attack upon the character of the witness must depend upon the\\n circumstances.\\n\\nFed. R. Evid. 608(a) Advisory Committee Notes to 1972 proposed rules.\\n\\n No firm line can be drawn regarding whether cross-examination of a witness\\n\\namounts to an attack on the witness’s character for truthfulness. But a useful test\\n\\nemployed by the courts is whether the questioning attacks the veracity of the witness’s\\n\\naccount of the facts in the specific case before the court or attacks the witness’s veracity\\n\\nin general. The Ninth Circuit expressed the point as follows:\\n\\n The purpose of Rule [608(a)] is to encourage direct attacks on a witness’s\\n veracity in the instant case and to discourage peripheral attacks on a\\n witness’s general character for truthfulness. To this end, the Rule prohibits\\n rehabilitation by character evidence of truthfulness after direct attacks on a\\n witness’s veracity in the instant case. However, the Rule permits\\n rehabilitation after indirect attacks on a witness’s general character for\\n truthfulness.\\n\\nUnited States v. Dring, 930 F.2d 687, 690–91 (9th Cir. 1991); see Renda v. King, 347\\n\\nF.3d 550, 554 (3d Cir. 2003) (“Direct attacks on a witness’s veracity in the particular\\n\\ncase do not open the door for evidence of the witness’s good character.” (emphasis\\n\\nadded)).\\n\\n Some circumstances are easy to characterize. For example, impeachment of the\\n\\nwitness through evidence of a prior felony conviction or prior fraudulent activity is not\\n\\n\\n\\n 16\\n\\fspecific to the case being tried and amounts to an attack on character. See Dring, 930\\n\\nF.2d. at 691 (“[I]ndirect attacks on truthfulness include opinion evidence, reputation\\n\\nevidence, and evidence of corruption, which require the jury to infer that the witness is\\n\\nlying at present simply because he has lied often in the past.”); Weinstein’s Federal\\n\\nEvidence § 608.12[1]; Roger Park & Tom Lininger, The New Wigmore: A Treatise on\\n\\nEvidence: Impeachment and Rehabilitation § 9.2 (2012). In contrast, a cross-\\n\\nexamination that focuses on the witness’s memory or perception does not implicate\\n\\ncharacter. Also, evidence of bias generally is not an attack on character. The fact that the\\n\\nwitness is a party’s mother may lessen her credibility in this case, but it does not mean\\n\\nthat she is usually an untruthful person. See Wigmore § 9.2 at 332. But cf. id. (if the\\n\\nproof of bias is that a party bribed the witness, the fact that the witness took a bribe is a\\n\\nreflection on character). And “most courts do not view contradiction of one witness’s\\n\\ntestimony by other witnesses as an attack on character.” Weinstein § 608.12[4][ a]; see\\n\\nUnited States v. Drury, 396 F.3d 1303, 1315 (11th Cir. 2005) (“An attack that consists\\n\\nonly of Government counsel pointing out inconsistencies in testimony and arguing that\\n\\nthe accused’s testimony is not credible does not constitute an attack on the accused’s\\n\\nreputation for truthfulness within the meaning of Rule 608.” (internal quotation marks\\n\\nomitted)); Kauz v. United States, 188 F.2d 9, 10 (5th Cir. 1951) (“The mere fact that a\\n\\nwitness is contradicted by other evidence in the case does not constitute an attack upon\\n\\nhis reputation for truth and veracity.”).\\n\\n Perhaps the most difficult questions arise when a witness has been vigorously\\n\\ncross-examined. “[A] slashing cross-examination can carry strong accusations of\\n\\n\\n 17\\n\\fmisconduct and bad character, which even the witness’s forceful denial will not remove\\n\\nfrom the jury’s mind.” 1 McCormick on Evidence § 47 at 309 (7th ed. 2013) (footnote\\n\\nomitted). Those are situations in which our standard of review properly affords\\n\\nsubstantial discretion to the trial judge.\\n\\n In this case there was nothing resembling an abuse of discretion in the district\\n\\ncourt’s exclusion of Defendant’s character-for-truthfulness evidence. The clear purpose\\n\\nof the prosecutor’s cross-examination of Defendant was to obtain admissions for much of\\n\\nthe government’s case. Defendant not only admitted to what he did or did not do but also\\n\\nto the unreasonableness of his actions. The following excerpt gives a flavor of the cross-\\n\\nexamination:\\n\\n Q: So despite your plan to try to protect this young child, you don’t tell anyone\\n over the course of five hours what you’re doing?\\n\\n A: Yes.\\n\\n Q: Or where you’re headed?\\n\\n A: Yes.\\n\\n Q: Doesn’t that seem dangerous?\\n\\n A: Yes.\\n\\n Q: For you?\\n\\n A: Yes.\\n\\n Q: For the girl?\\n\\n A: Yes.\\n\\n Q: You brought up condoms in these conversations, correct?\\n\\n A: Yes.\\n\\n\\n\\n 18\\n\\fQ: You actually proposed having oral sex with a 12-year-old correct?\\n\\nA: Yes.\\n\\nQ: You repeatedly brought up all kinds of different sex acts that you and this 12-\\nyear-old girl could engage in, correct?\\n\\nA: Yes.\\n\\nQ: You have testified that you were concerned about the welfare of this girl; is that\\nright?\\n\\nA: Yes.\\n\\nQ: And that you wanted to save her?\\n\\nA: Yes.\\n\\nQ: And I’m assuming you didn’t want to cause her any trauma or pain?\\n\\nA: No.\\n\\nQ: But you didn’t care enough to not ask for a photo, did you?\\n\\nA: No.\\n\\nQ: Don’t you think that it would be traumatic, for this girl’s photo to be shared?\\n\\nA: Yeah.\\n\\nQ: You specifically asked for more photos, didn’t you?\\n\\nA: Yes.\\n\\nQ: And you specifically requested full-body photos with no face?\\n\\nA: Yes.\\n\\nQ: Would you not agree that not having the face in those photos would actually\\nmake it more difficult to hold this person accountable?\\n\\nA: Yes.\\n\\nQ: You were wanting to actually hold this person accountable. Wouldn’t you\\nwant to see who the girl actually is?\\n\\nA: Yes.\\n\\n\\n 19\\n\\f Q: But instead, you specifically request no face photos, correct?\\n\\n A: Yes.\\n\\n Q: And you sent a photo of yourself and block all identifiers, don’t you?\\n\\n A: Yes.\\n\\n Q: You also don’t care enough about the safety of this child to not speak to her,\\n correct?\\n\\n A: Yes.\\n\\nR., Vol. 3 at 412–14. On two occasions Defendant initially disagreed with the\\n\\nprosecutor, but then the matter was clarified and the prosecutor did not challenge his\\n\\nanswer. See id. at 4112; id. at 4163. The only occasion when the prosecutor was clearly\\n\\nchallenging the veracity of Defendant’s testimony was the final exchange: “Q: You\\n\\nshowed up to take her V card, didn’t you? A: No.” Id. at 418.\\n\\n\\n\\n\\n2\\n Q: And I believe you indicated before that you don’t feel like you’re very Internet\\n [savvy]? Is that how you said that?\\n A: No.\\n Q: Yet you specifically informed the purported father in this case how to share a\\n picture with you on Kik, correct?\\n A: That’s totally different than –\\n Q: So you’re Internet [savvy] when it comes to Kik, but not Internet [savvy] on\\n Craigslist where you’re specifically going to a certain section on there?\\n A: Yes.\\n3\\n Q: So you showed up ready to meet the girl, correct?\\n A: No.\\n Q: Is that a yes or a no?\\n A: No.\\n Q: You showed up to meet her father, is that what you’re indicating?\\n A: Yes.\\n\\n\\n 20\\n\\f As the district court observed, “The defendant’s response to virtually every\\n\\nquestion by the Government was yes.” Id. at 431. Rather than challenging Defendant’s\\n\\nveracity, the prosecutor generally wanted the jury to believe all his answers except the\\n\\nlast. Indeed, the frankness of Defendant’s admissions on cross-examination likely led the\\n\\njury to conclude that Defendant was basically a truthful person. But given all those\\n\\nadmissions, it would be impossible to believe that he was really intending to act as an\\n\\nagent of law enforcement rather than as a sexual predator. The prosecution was\\n\\nchallenging Defendant’s veracity with respect to a specific issue in the present case (his\\n\\nintent), not his general truthfulness. See Renda, 347 F.3d at 554; Dring, 930 F.2d at 690–\\n\\n91. And the basis for the challenge was merely the unbelievability of his statement of his\\n\\nintent in light of the undisputed facts. See Kauz, 188 F.2d at 10 (“The mere fact that a\\n\\nwitness is contradicted by other evidence in the case does not constitute an attack upon\\n\\nhis reputation for truth and veracity.”) If this be an attack on Defendant’s character for\\n\\ntruthfulness, then such an attack occurs whenever the prosecution puts on evidence\\n\\ncontrary to a witness’s account. We decline to interpret Rule 608(a) as permitting\\n\\nevidence of a witness’s character for truthfulness whenever the witness’s testimony is\\n\\nchallenged.\\n\\n III. CONCLUSION\\n\\n We AFFIRM Defendant’s conviction.\\n\\n\\n\\n\\n 21\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4394212/\", \"author_raw\": \"HARTZ, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"HARTZ"},"judge2":{"kind":"string","value":"MATHESON"},"judge3":{"kind":"string","value":"EID"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4616959/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Christopher Lee MARTINEZ, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-06\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 6, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\n UNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v. No. 18-8007\n\n CHRISTOPHER LEE MARTINEZ,\n\n Defendant - Appellant.\n _________________________________\n\n Appeal from the United States District Court\n for the District of Wyoming\n (D.C. No. 2:17-CR-00213-NDF-1)\n _________________________________\n\nNeil D. Van Dalsem, Office of the Federal Public Defender, Muskogee, Oklahoma, for\nDefendant-Appellant.\n\nTimothy J. Forwood, Assistant United States Attorney (Mark A. Klaassen, United States\nAttorney, District of Wyoming, with him on the brief), Cheyenne, Wyoming, for\nPlaintiff-Appellee.\n _________________________________\n\nBefore HARTZ, MATHESON, and EID, Circuit Judges.\n _________________________________\n\nHARTZ, Circuit Judge.\n _________________________________\n\n A jury in the United States District Court for the District of Wyoming convicted\n\nDefendant Christopher Lee Martinez on one count of attempting to entice a minor to\n\nengage in illegal sexual activity. See 18 U.S.C. § 2422(b). On appeal Defendant argues\n\fthat the district court (1) should have authorized funds for a forensic psychologist, (2)\n\nimproperly excluded evidence of his history of mental illness, and (3) should have\n\nallowed him to present evidence of his character for truthfulness. Exercising jurisdiction\n\nunder 28 U.S.C. § 1291, we affirm.\n\n I. BACKGROUND\n\n A. Defendant’s Arrest\n\n On July 22, 2017, Special Agent Brent Metcalfe of the Wyoming Division of\n\nCriminal Investigation (DCI) posted a personal advertisement on the “Casual\n\nEncounters” section listed on the Craigslist website at that time. The purpose of the\n\nposting was to ferret out those who used the Internet to arrange sexual encounters with\n\nminors. Metcalfe chose the date because of the expected influx of tourists for Cheyenne\n\nFrontier Days. The advertisement was entitled “Fresh CFD Taboo” and read: “In town\n\nwith my dau. She is very eager. She wants to experience what Cheyenne has to offer.\n\nWho wants to have some ‘fresh fun.’” R., Vol. 3 at 247–49. Metcalfe explained that he\n\nused the terms fresh and eager to communicate to the reader that the subject of the\n\nadvertisement was young and sexually inexperienced.\n\n Defendant, 27 years old at the time, was one of the first to respond, sending a\n\nmessage shortly before 4:00 p.m. The email messages were relayed by Craigslist\n\nbetween the correspondents. Metcalfe posed as the father, telling Defendant that he\n\nhoped to “find a guy for my daughter, but she’s younger.” Id. at 256. When Defendant\n\nasked how old the girl was, Metcalfe answered that she was 12. Defendant said: “Okay.\n\nWhen you thinking? I’ll think about it. You ain’t a cop or law enforcement?” Id. at 257.\n\n\n 2\n\fMetcalfe assured him that he was not a cop and the conversation continued. It centered\n\non whether Defendant wanted to have sexual relations with the daughter. Defendant\n\nasked Metcalfe what sexual acts he could engage in with the girl, whether he could take\n\nher virginity, and whether Metcalfe had condoms. Defendant repeatedly sought\n\nassurances that Metcalfe was not a “cop,” explaining that he was nervous because the\n\npolice had “popped a lot of people” during Frontier Days the previous year. Id. at 287.\n\n With Defendant’s interest established, Metcalfe requested that they move their\n\nconversation to “Kik,” an instant-messaging application that better allowed investigators\n\nto obtain Defendant’s identity. Defendant agreed. After he asked Metcalfe to send him a\n\npicture of the daughter, the two agreed to exchange pictures. Metcalfe sent Defendant a\n\npicture of part of the chest of a life-like mannequin. Defendant asked for another picture\n\nof the child’s full body with no face. Metcalfe refused to send additional pictures but\n\nagreed that Defendant could come to his motel to take his daughter’s “V card” (referring\n\nto her virginity). Id. at 302. Defendant eventually asked to message with the daughter\n\ndirectly, and Metcalfe assumed the girl’s identity. Defendant asked if she wanted to “lose\n\n[her] V card?” When Metcalfe asked what that meant, Defendant said “Virginity.” Id. at\n\n310. After exchanging about 100 messages over almost five hours, Defendant agreed to\n\nmeet at a motel and said that he would bring a condom.\n\n At 8:48 p.m., Defendant arrived at the motel parking lot and messaged Metcalfe,\n\nasking him to come out. Metcalfe and several other officers exited their vehicles and\n\narrested Defendant in his truck. He was in possession of a phone and a condom.\n\nForensic analysis confirmed that the phone was the one used to communicate with\n\n\n 3\n\fMetcalfe on the Kik application. When interviewed by officers at the scene, Defendant\n\nadmitted to sending the messages but stated that he was getting ready to call the police\n\nbefore he was arrested. When asked why he had a condom, he said something like, “You\n\nhave to be real.” Id. at 321.\n\n B. Pretrial Motions\n\n Defense counsel filed a pretrial motion under 18 U.S.C. § 3006A requesting a\n\nforensic psychologist at the government’s expense. The motion stated the charge against\n\nDefendant, the trial date, the cost of a forensic evaluation and polygraph by Dr. Charles\n\nW. Dennison CP, Defendant’s minimal employment history, and his lack of funds to pay\n\nDr. Dennison. Other than stating that Defendant was on Social Security disability with a\n\nmental-health diagnosis, the motion said nothing regarding his mental health and the need\n\nfor an evaluation except as follows:\n\n Defendant was diagnosed with bipolar disorder, attention deficit disorder\n (ADD), schizophrenia and depression when he was 18 years old. The\n diagnosis was at Peak Wellness, Cheyenne, Wyoming. Defendant has a\n Mental Health history of attempted suicide at 18 years of age,\n hallucinations with the last occurrence taking place about 4-5 years ago.\n Defendant was prescribed Trazadone, Invega, Amitriptyline, Abilify and\n Fluoxetine. He is currently off medication.\n\n ...\n\n Due to the nature of the charges in this matter, a forensic evaluation is\n necessary.\n\nR., Vol. 1 at 29. The district court denied the motion, saying:\n\n Defendant failed to provide the Court with information regarding the\n necessity for a forensic evaluation by Dr. Dennison at Government\n expense. The Court routinely grants forensic evaluations in cases involving\n receipt of child porn, for purposes of sentencing mitigation. However, this\n\n\n 4\n\f case involves attempted enticement of a minor. . . . Given the mandatory\n minimum sentence in this case, it is not clear the purpose of a forensic\n evaluation. Defendant has failed to provide the Court with any explanation\n of the necessity for an evaluation, either for trial or sentencing purposes. IT\n IS ORDERED that Defendant’s Motion for Forensic Psychologist at\n Government Expense is DENIED at this time based on the Court’s finding\n that Defendant has not established the necessity for this evaluation.\n\nR., Vol. 2 at 12 (italics added). Defense counsel did not renew the motion or later\n\nprovide further justification for a forensic psychologist.\n\n The government then filed a motion in limine to prevent Defendant from\n\npresenting evidence of his character for truthfulness and honesty and to exclude any\n\nevidence of his mental illness. On the first issue, it argued that because the charged\n\noffense of enticement of a minor is not a crimen falsi (that is, an offense in which a lie by\n\nthe defendant is one of the elements of the crime), testimony regarding Defendant’s\n\ncharacter for truthfulness was not relevant. Accordingly, it requested that Defendant’s\n\nuse of character evidence be limited to evidence that he is law abiding. The court agreed\n\nthat Defendant had not shown a basis for offering evidence of his character for\n\ntruthfulness, but said that it would later rule on specific issues related to character\n\nevidence that might arise during trial.\n\n On the second issue, the government contended that absent an insanity defense,\n\nevidence of Defendant’s mental defects or lack of volitional control was not an allowable\n\ndefense. Although the government acknowledged that evidence of mental health could\n\nbe admitted to negate specific intent, it pointed out that Defendant bore the burden of\n\nshowing that the proffered evidence was being offered for that purpose. This issue was\n\naddressed at the final pretrial conference, where the court gave defense counsel the\n\n\n 5\n\fopportunity to explain the purpose of introducing evidence of Defendant’s mental health.\n\nDefense counsel stated:\n\n So my plan was to introduce a very limited number of medical records that\n I’ve provided to the Government, and they basically just state that Mr.\n Martinez was diagnosed with bipolar, I think back in 2010; that he was\n prescribed medication. He’s also got ADD, I believe. And the only\n purpose of those records is because I would have him testify and his family\n testify that he has these mental issues and that his mental state of mind is\n important because one of the elements in this case is that he obviously\n knowingly had to complete this act, and that goes to that element of\n whether or not he knowingly completed this act.\n\n And the medical records themselves are really just to – there to corroborate\n what he would testify to about his own character and state of mind.\n\nR., Vol. 3 at 34 (emphasis added). Defense counsel acknowledged that Defendant “did\n\nnot plead guilty by reason of mental illness” but argued that the jury should decide\n\n“whether or not [his mental illness] affected his decision to do the things he did or not.”\n\nId. at 35. And responding to the arguments by the government, he said:\n\n We’re offering it to show his potential state of mind in general and who he\n is. And this is a person – and like I said, I don’t know how you can – the\n Court or any court could preclude an individual from getting on the stand\n and testifying that, “Yes, I’m – you know, this is my background. I have\n these issues that I’ve dealt with. I was on medication, but I wasn’t taking\n the medication at the time,” and to describe his general makeup, I suppose.\n\nId. at 38.\n\n The court granted the motion in limine. It expressed concern that the proffered\n\nmental-illness testimony would “create[] the potential for confusion by the jury and\n\nseek[ ] to suggest a justification as opposed to a defense to any of the elements that the\n\nGovernment is required to prove by proof beyond a reasonable doubt.” Id. at 39. It noted\n\nthat this court had held “that psychological and psychiatric evidence that negates the\n\n\n 6\n\fessential element of specific intent can be admissible” but that the admission of such\n\nevidence required clear demonstration of “how such evidence would negate intent rather\n\nthan merely present a dangerously confusing theory of defense more akin to justification\n\nand excuse.” R., Vol. 1 at 72 (internal quotation marks omitted). The court concluded\n\nthat without an expert or current medical records, Defendant lacked mental-health\n\nevidence showing “some cognitive defect precluding him from forming the specific\n\nintent for the charged offense” and thus the proffered evidence was irrelevant. Id. at 73.\n\n C. Trial\n\n The prosecution called only three witnesses at trial: Special Agent Robert\n\nLeazenby of the Wyoming DCI testified in general about the conduct of child-\n\nexploitation investigations; Agent Metcalfe testified about his communications with\n\nDefendant; and Mark Timmons of the Wyoming DCI testified about his search of\n\nDefendant’s car after the arrest.\n\n Before calling any witnesses, Defendant renewed his request to be permitted to\n\noffer mental-health evidence. He pointed to testimony by Agent Leazenby that\n\ninvestigators like to talk to arrestees in such cases to determine their states of mind. The\n\nprosecutor pointed out, however, that the state of mind Leazenby was referring to was\n\nwhether or not the arrestee wanted to have sex with the child. When the court asked\n\ndefense counsel how the mental-health evidence would relate to the instruction on the\n\nknowingly element of the offense, counsel responded that he wanted to put on the\n\nevidence simply as background evidence:\n\n\n\n\n 7\n\f But that’s who he is and that’s kind of his general makeup, just as if a\n person was employed and is – you know, as an officer and they’ve been\n doing that for ten years. Well, in the last ten years he’s been doing really\n nothing. Why has he been doing nothing? Because he’s on [Social\n Security benefits], and the jury is going to know why he’s on [Social\n Security benefits]. Well, that’s why.\n\nR., Vol. 3 at 377. The court was not persuaded. It held that while information\n\nconcerning Defendant’s background may be relevant for sentencing purposes, it was not\n\nrelevant at the trial.\n\n Defendant’s evidence consisted of (1) his own testimony, explaining that he was\n\nnot engaged in criminal activity but, rather, was attempting to identify someone engaged\n\nin child exploitation, whom he would report to law-enforcement authorities, and (2) six\n\nwitnesses who testified to his character as a law-abiding citizen.\n\n Defendant also unsuccessfully attempted to put on evidence of his character for\n\ntruthfulness, which he claimed had been attacked during his cross-examination by the\n\nprosecution. He argued that such evidence would assist the jury in determining whether\n\nto believe his statement that he did not intend to engage in sex with a minor. The court\n\nrejected the argument, reaffirming its earlier ruling that such evidence was not relevant\n\nbecause the charged offense did not include an element that concerned truthfulness. It\n\nfurther observed that because the bulk of the evidence in the case involved contradictory\n\nstatements made by Defendant before and after his arrest, testimony regarding his\n\ncharacter for truthfulness would not be probative in helping the jury decide which if any\n\nof his statements to believe.\n\n\n\n\n 8\n\f II. DISCUSSION\n\n A. Denial of Motion to Hire Forensic Psychologist\n\n The Criminal Justice Act (CJA) permits a court to authorize funding for an expert\n\nwitness at the government’s expense:\n\n Counsel for a person who is financially unable to obtain investigative,\n expert, or other services necessary for adequate representation may request\n them in an ex parte application. Upon finding, after appropriate inquiry in\n an ex parte proceeding, that the services are necessary and that the person is\n financially unable to obtain them, the court . . . shall authorize counsel to\n obtain the services.\n\n18 U.S.C. § 3006A(e)(1). The defendant bears the burden of persuasion. See United\n\nStates v. Greschner, 802 F.2d 373, 376 (10th Cir. 1986). The necessity of services must\n\nbe established with specificity. In the present context, “[g]eneral allegations supporting a\n\nrequest for court appointment of a psychiatric expert, without substantive supporting\n\nfacts, and undeveloped assertions that psychiatric assistance would be beneficial to the\n\ndefendant will not suffice to require the appointment of a psychiatrist to aid in the\n\npreparation of a criminal defense.” Liles v. Saffle, 945 F.2d 333, 336 (10th Cir. 1991).\n\nWe review the denial of a CJA funding request for an abuse of discretion. See United\n\nStates v. Solon, 596 F.3d 1206, 1210 (10th. Cir. 2010).\n\n On appeal Defendant argues that psychiatric testimony could have supported his\n\ndefense that he was merely trying to catch sexual predators, not trying to be one himself.\n\nHe states:\n\n [Defendant’s] case provides a classic example of how psychological\n evidence can be relevant in evaluating a defendant’s specific intent.\n\n\n\n\n 9\n\f [Defendant] was charged with an attempt crime, a specific intent crime.[1]\n What he was actually thinking is of critical importance. [Defendant’s]\n entire defense to this case was that he did not really intend to break the law\n by enticing a minor to have sex. He defended this case on the ground that\n he intended to identify a person who was offering up a minor for sex.\n\n For the jurors to evaluate that assertion, they certainly needed to know\n about [Defendant’s] mental illness. The government’s case was based on\n an argument that it would be completely bizarre for a person to have taken\n steps [Defendant] took without first calling law enforcement. [Defendant]\n should have been allowed to prepare a defense that informed the jury, that,\n in fact, he is a person who suffers from mental illness, and he legitimately\n may not proceed as a rational person would.\n\n Even though his conduct may seem strange, he was not trying to commit a\n crime. To the contrary, from the moment of his arrest, he explained that he\n was trying to catch a criminal. A casual observer might find his\n explanation, provided by a “normal” person, to not make a great deal of\n sense or be persuasive. However, in evaluating [Defendant’s] explanation,\n the jurors needed to know that, in fact, [Defendant] is mentally ill. While a\n mentally healthy person may not have tried to catch the Craigslist poster, a\n person with bipolar disorder may well have done so.\n\nAplt. Br. at 25–26.\n\n This is an interesting argument, but we need not address it because it was not\n\nraised below and Defendant does not argue for plain-error review on appeal. See United\n\n\n\n1\n To establish a violation of § 2422(b), the government must prove that the defendant\n“(1) [used] a facility of interstate commerce; (2) to knowingly persuade, induce, entice, or\ncoerce; (3) any individual who is younger than 18; (4) to engage in any sexual activity for\nwhich any person can be charged with a criminal offense or attempting to do so.” United\nStates v. Faust, 795 F.3d 1243, 1248 (10th Cir. 2015) (internal quotation marks omitted).\n“To prove an attempt crime, the government must prove (1) an intent to commit the\nsubstantive offense; and (2) the commission of an act which constitutes a substantial step\ntowards commission of the substantive offense, . . . [which] must be something more than\nmere preparation.” United States v. Vigil, 523 F.3d 1258, 1267 (10th Cir. 2008)\n(typographical errors corrected and internal quotation marks omitted). Thus, in this case\nthe government had to show that Defendant intended to entice a girl under 18 years old to\nengage in criminal sexual activity.\n\n 10\n\fStates v. McGlothin, 705 F.3d 1254, 1267 (10th Cir. 2013) (if appellant forfeits an\n\nargument before the district court and then fails to explain in appellate briefing how the\n\nargument survives appellate review under the plain-error standard, then the appellant has\n\nwaived the argument on appeal). In his pretrial motion he stated that he suffered from\n\nvarious mental illnesses. But he did not even attempt to explain how these disorders\n\ncould negate any element of the charged crime. He wrongly assumes that simply putting\n\nthe court on notice that he suffered from mental-health disorders was somehow enough to\n\nsatisfy his burden. It is not the job of the court, however, to come up with arguments\n\nwhy a defendant’s mental illness must have influenced his conduct in committing a\n\ncrime.\n\n Further, the court’s order said that Defendant’s motion was merely denied “at this\n\ntime” for lack of the requisite showing. It left open the opportunity for Defendant to\n\nproperly explain why the forensic psychologist was needed. If the need for such an\n\nexpert should have been obvious to the court, Defendant could have easily explained the\n\npoint. Yet Defendant never pursued the issue again. We cannot fault the district court\n\nfor denying Defendant’s motion in light of the remarkably sparse argument he proffered.\n\nWe see no abuse of discretion here. (To the extent that Defendant attempts to raise for\n\nthe first time on appeal a due-process challenge to the denial of an expert, we also decline\n\nto address that argument. See id.)\n\n B. Exclusion of Evidence of Defendant’s Mental-Health History\n\n At trial Defendant unsuccessfully requested that the district court permit him to\n\noffer evidence of his history of mental illness, including medical records from more than\n\n\n 11\n\ffive years past, his testimony, and his wife’s testimony. The court ruled that it was\n\nirrelevant. “We review a district court’s evidentiary rulings for abuse of discretion,\n\nconsidering the record as a whole.” United States v. Trujillo, 136 F.3d 1388, 1395 (10th\n\nCir. 1998). An evidentiary decision will not be reversed if it “falls within the bounds of\n\npermissible choice in the circumstances and is not arbitrary, capricious or whimsical.”\n\nUnited States v. Wills, 826 F.3d 1265, 1270 (10th Cir. 2016) (internal quotation marks\n\nomitted).\n\n On appeal Defendant argues, as he did with respect to the denial of funds for a\n\npsychiatric expert, that this mental-illness evidence could support his defense that he was\n\nnot seeking a sexual partner but was trying to catch a sexual predator. He contends that\n\nthe evidence would “explain[] that his arguably irrational behavior was the product of his\n\nmental illness.” Aplt. Br. at 34. Again, however, he did not raise this argument in\n\ndistrict court, so we will not address it. See McGlothin, 705 F.3d at 1267.\n\n What Defendant did argue in district court was that evidence of his mental illness\n\nwas relevant to communicating his overall background to the jury. To establish that\n\nDefendant offered no relevant purpose for the mental-health evidence, we set forth\n\nextended excerpts of defense counsel’s colloquy with the court when he renewed his\n\nmotion to admit the evidence. During the colloquy, counsel made clear that the purpose\n\nof the evidence was simply to tell the jury what kind of person Defendant is:\n\n DEFENSE COUNSEL: [A]s I understand the Court’s order, I’m not\n allowed to introduce any evidence concerning his mental-health.\n\n However, in talking with him and providing the background for the jury of\n what he’s – who he is and what he’s doing, I think it is necessary to state at\n\n\n 12\n\fleast to a certain extent that, number one, that he’s on – he’s been on SSI\n[Social Security] since he was 17 for ADD, bipolar and depression, and\nthat’s what he’s been doing for the last 10 years. He doesn’t work.\n\nSo we at least need to explain that to the jury, that I think he should be\nallowed to say, “Hey, this is what I’ve been doing for the last 10 years. I\nwas on medication. I was off medication because I didn’t like it,” whatever\nreason.\n....\n[A]nd if you look at the instructions, the knowingly instruction also talks\nabout a person’s state of mind. And so the jury is going to consider his\nstate of mind, and we’re telling them to.\n...\nTHE COURT [after also hearing from the prosecution]: How does the\nstated diagnosis speak to the considerations in Instruction 24 which is that\nhe was conscious and aware of his actions, realized what he was doing or\nwhat was happening around him and did not act because of ignorance,\nmistake or accident? Even assuming that the diagnosis is – would be the\ndiagnosis today by a qualified healthcare professional, how does that\ndiagnosis relate to the instruction on knowingly?\n\nDEFENSE COUNSEL: Well, Your Honor, I think we’re talking about two\ndifferent things here. And, number one, I am not trying to introduce this\nevidence as evidence that he had a mental defect at the time and did not act\nin accordance with the statute because of that mental defect.\n\nWhat I am trying to introduce, simply, is that we have an individual that has\nmental issues or a mental diagnosis and he’s been on SSI and it is part of\nhis background. Now, there’s a reason for that and the jury, I think, is\ngoing to want to know what he’s – who this person is.\n\nSo, number one, I don’t think anything is prohibitive of talking about an\nindividual’s background, what he’s been doing. So I think that is fair game.\n...\nSo I don’t – like I said, I’m not going to use it. I don’t think – I wasn’t\nplanning on bringing an expert to come in and testify that he suffers from\ndepression, ADD and bipolar, and therefore, that’s what – why he\ncommitted this act. . . .\n\nAnd that’s not what our intent is here. The only reason I want to introduce\nthe records is to show that when he says, “yeah, I’ve been on SSI,” that’s\ndocumented and the jury doesn’t think that he is faking it or just some\nperson out there not – by choice not working in kind of a low-life situation\nby choice.\n\n 13\n\f So we are not offering as mental health defense that information, but\n merely as background information and that’s who this person is and what\n he’s been doing. The jury can do whatever they want with it, I suspect.\n\nR., Vol. 3 at 372–78.\n\n “Evidence is relevant if: (a) it has any tendency to make a fact more or less\n\nprobable than it would be without the evidence; and (b) the fact is of consequence in\n\ndetermining the action.” Fed. R. Evid. 401. To be sure, “[t]he bar for admission under\n\nRule 401 is very low”; the evidence need “only provide a fact-finder with a basis for\n\nmaking some inference, or chain of inferences.” United States v. Jordan, 485 F.3d 1214,\n\n1218 (10th Cir. 2007) (internal quotation marks omitted). But Defendant’s proffered\n\nground for admitting this evidence did not meet even this low bar. Defense counsel\n\nnever suggested a chain of inference from this evidence to an element of the crime or a\n\ndefense.\n\n We recognize that it is generally appropriate to humanize a witness by letting the\n\nwitness tell the jury a few things about himself or herself. But even if such background\n\ninformation can be admissible, Federal Rule of Evidence 403 permits exclusion of even\n\nrelevant evidence “if its probative value is substantially outweighed by the danger of . . .\n\nunfair prejudice, confusing the issues, [or] misleading the jury.” Courts must be cautious\n\nabout admitting marginally relevant mental-health evidence because the jury may think\n\nthat it provides an “excuse” for misconduct or it may otherwise generate sympathy for the\n\ndefendant. See United States v. Cameron, 907 F.2d 1051, 1067 (11th Cir. 1990)\n\n(“[P]sychiatric evidence . . . presents an inherent danger that it will distract the jury[ ]\n\nfrom focusing on the actual presence or absence of mens rea, and . . . may easily slide\n\n\n 14\n\finto wider usage that opens up the jury to theories of defense more akin to justification.”\n\n(internal quotation marks omitted)). Here, the district court permitted some humanizing\n\nevidence, such as Defendant’s testimony that he was unemployed and on social-security\n\nbenefits, because it saw no danger of improper prejudice or confusing the jury. But it\n\nexcluded the mental-health evidence, which it viewed as “just an effort to elicit\n\nsympathy.” R., Vol. 3 at 378. This ruling was not an abuse of discretion.\n\n C. Exclusion of Character Evidence\n\n Defendant argues that the district court abused its discretion in excluding evidence\n\nof his character for truthfulness after his credibility was allegedly attacked on cross-\n\nexamination. He contends that the court’s decision to exclude evidence of his character\n\nfor truthfulness was based on a misapplication of Rule 608 of the Federal Rules of\n\nEvidence. “We review a trial court’s exclusion of character evidence for abuse of\n\ndiscretion.” Tanberg v. Sholtis, 401 F.3d 1151, 1167 (10th Cir. 2005). But we review de\n\nnovo the district court’s legal interpretation of the Federal Rules of Evidence. See United\n\nStates v. Torrez-Ortega, 184 F.3d 1128, 1132 (10th Cir. 1999).\n\n Under Rule 608 a witness’s credibility ordinarily may be attacked by presenting\n\nevidence of the witness’s character for untruthfulness, but positive evidence of a truthful\n\ncharacter is permitted only in response to an attack on such character:\n\n Reputation or Opinion Evidence. A witness’s credibility may be attacked\n or supported by testimony about the witness’s reputation for having a\n character for truthfulness or untruthfulness, or by testimony in the form of\n an opinion about that character. But evidence of truthful character is\n admissible only after the witness’s character for truthfulness has been\n attacked.\n\n\n\n 15\n\fFed. R. Evid. 608(a). An advisory committee note clarifies what constitutes an attack on\n\ncharacter for truthfulness:\n\n Opinion or reputation that the witness is untruthful specifically qualifies as\n an attack under the rule, and evidence of misconduct, including conviction\n of crime, and of corruption also fall within this category. Evidence of bias\n or interest does not. Whether evidence in the form of contradiction is an\n attack upon the character of the witness must depend upon the\n circumstances.\n\nFed. R. Evid. 608(a) Advisory Committee Notes to 1972 proposed rules.\n\n No firm line can be drawn regarding whether cross-examination of a witness\n\namounts to an attack on the witness’s character for truthfulness. But a useful test\n\nemployed by the courts is whether the questioning attacks the veracity of the witness’s\n\naccount of the facts in the specific case before the court or attacks the witness’s veracity\n\nin general. The Ninth Circuit expressed the point as follows:\n\n The purpose of Rule [608(a)] is to encourage direct attacks on a witness’s\n veracity in the instant case and to discourage peripheral attacks on a\n witness’s general character for truthfulness. To this end, the Rule prohibits\n rehabilitation by character evidence of truthfulness after direct attacks on a\n witness’s veracity in the instant case. However, the Rule permits\n rehabilitation after indirect attacks on a witness’s general character for\n truthfulness.\n\nUnited States v. Dring, 930 F.2d 687, 690–91 (9th Cir. 1991); see Renda v. King, 347\n\nF.3d 550, 554 (3d Cir. 2003) (“Direct attacks on a witness’s veracity in the particular\n\ncase do not open the door for evidence of the witness’s good character.” (emphasis\n\nadded)).\n\n Some circumstances are easy to characterize. For example, impeachment of the\n\nwitness through evidence of a prior felony conviction or prior fraudulent activity is not\n\n\n\n 16\n\fspecific to the case being tried and amounts to an attack on character. See Dring, 930\n\nF.2d. at 691 (“[I]ndirect attacks on truthfulness include opinion evidence, reputation\n\nevidence, and evidence of corruption, which require the jury to infer that the witness is\n\nlying at present simply because he has lied often in the past.”); Weinstein’s Federal\n\nEvidence § 608.12[1]; Roger Park & Tom Lininger, The New Wigmore: A Treatise on\n\nEvidence: Impeachment and Rehabilitation § 9.2 (2012). In contrast, a cross-\n\nexamination that focuses on the witness’s memory or perception does not implicate\n\ncharacter. Also, evidence of bias generally is not an attack on character. The fact that the\n\nwitness is a party’s mother may lessen her credibility in this case, but it does not mean\n\nthat she is usually an untruthful person. See Wigmore § 9.2 at 332. But cf. id. (if the\n\nproof of bias is that a party bribed the witness, the fact that the witness took a bribe is a\n\nreflection on character). And “most courts do not view contradiction of one witness’s\n\ntestimony by other witnesses as an attack on character.” Weinstein § 608.12[4][ a]; see\n\nUnited States v. Drury, 396 F.3d 1303, 1315 (11th Cir. 2005) (“An attack that consists\n\nonly of Government counsel pointing out inconsistencies in testimony and arguing that\n\nthe accused’s testimony is not credible does not constitute an attack on the accused’s\n\nreputation for truthfulness within the meaning of Rule 608.” (internal quotation marks\n\nomitted)); Kauz v. United States, 188 F.2d 9, 10 (5th Cir. 1951) (“The mere fact that a\n\nwitness is contradicted by other evidence in the case does not constitute an attack upon\n\nhis reputation for truth and veracity.”).\n\n Perhaps the most difficult questions arise when a witness has been vigorously\n\ncross-examined. “[A] slashing cross-examination can carry strong accusations of\n\n\n 17\n\fmisconduct and bad character, which even the witness’s forceful denial will not remove\n\nfrom the jury’s mind.” 1 McCormick on Evidence § 47 at 309 (7th ed. 2013) (footnote\n\nomitted). Those are situations in which our standard of review properly affords\n\nsubstantial discretion to the trial judge.\n\n In this case there was nothing resembling an abuse of discretion in the district\n\ncourt’s exclusion of Defendant’s character-for-truthfulness evidence. The clear purpose\n\nof the prosecutor’s cross-examination of Defendant was to obtain admissions for much of\n\nthe government’s case. Defendant not only admitted to what he did or did not do but also\n\nto the unreasonableness of his actions. The following excerpt gives a flavor of the cross-\n\nexamination:\n\n Q: So despite your plan to try to protect this young child, you don’t tell anyone\n over the course of five hours what you’re doing?\n\n A: Yes.\n\n Q: Or where you’re headed?\n\n A: Yes.\n\n Q: Doesn’t that seem dangerous?\n\n A: Yes.\n\n Q: For you?\n\n A: Yes.\n\n Q: For the girl?\n\n A: Yes.\n\n Q: You brought up condoms in these conversations, correct?\n\n A: Yes.\n\n\n\n 18\n\fQ: You actually proposed having oral sex with a 12-year-old correct?\n\nA: Yes.\n\nQ: You repeatedly brought up all kinds of different sex acts that you and this 12-\nyear-old girl could engage in, correct?\n\nA: Yes.\n\nQ: You have testified that you were concerned about the welfare of this girl; is that\nright?\n\nA: Yes.\n\nQ: And that you wanted to save her?\n\nA: Yes.\n\nQ: And I’m assuming you didn’t want to cause her any trauma or pain?\n\nA: No.\n\nQ: But you didn’t care enough to not ask for a photo, did you?\n\nA: No.\n\nQ: Don’t you think that it would be traumatic, for this girl’s photo to be shared?\n\nA: Yeah.\n\nQ: You specifically asked for more photos, didn’t you?\n\nA: Yes.\n\nQ: And you specifically requested full-body photos with no face?\n\nA: Yes.\n\nQ: Would you not agree that not having the face in those photos would actually\nmake it more difficult to hold this person accountable?\n\nA: Yes.\n\nQ: You were wanting to actually hold this person accountable. Wouldn’t you\nwant to see who the girl actually is?\n\nA: Yes.\n\n\n 19\n\f Q: But instead, you specifically request no face photos, correct?\n\n A: Yes.\n\n Q: And you sent a photo of yourself and block all identifiers, don’t you?\n\n A: Yes.\n\n Q: You also don’t care enough about the safety of this child to not speak to her,\n correct?\n\n A: Yes.\n\nR., Vol. 3 at 412–14. On two occasions Defendant initially disagreed with the\n\nprosecutor, but then the matter was clarified and the prosecutor did not challenge his\n\nanswer. See id. at 4112; id. at 4163. The only occasion when the prosecutor was clearly\n\nchallenging the veracity of Defendant’s testimony was the final exchange: “Q: You\n\nshowed up to take her V card, didn’t you? A: No.” Id. at 418.\n\n\n\n\n2\n Q: And I believe you indicated before that you don’t feel like you’re very Internet\n [savvy]? Is that how you said that?\n A: No.\n Q: Yet you specifically informed the purported father in this case how to share a\n picture with you on Kik, correct?\n A: That’s totally different than –\n Q: So you’re Internet [savvy] when it comes to Kik, but not Internet [savvy] on\n Craigslist where you’re specifically going to a certain section on there?\n A: Yes.\n3\n Q: So you showed up ready to meet the girl, correct?\n A: No.\n Q: Is that a yes or a no?\n A: No.\n Q: You showed up to meet her father, is that what you’re indicating?\n A: Yes.\n\n\n 20\n\f As the district court observed, “The defendant’s response to virtually every\n\nquestion by the Government was yes.” Id. at 431. Rather than challenging Defendant’s\n\nveracity, the prosecutor generally wanted the jury to believe all his answers except the\n\nlast. Indeed, the frankness of Defendant’s admissions on cross-examination likely led the\n\njury to conclude that Defendant was basically a truthful person. But given all those\n\nadmissions, it would be impossible to believe that he was really intending to act as an\n\nagent of law enforcement rather than as a sexual predator. The prosecution was\n\nchallenging Defendant’s veracity with respect to a specific issue in the present case (his\n\nintent), not his general truthfulness. See Renda, 347 F.3d at 554; Dring, 930 F.2d at 690–\n\n91. And the basis for the challenge was merely the unbelievability of his statement of his\n\nintent in light of the undisputed facts. See Kauz, 188 F.2d at 10 (“The mere fact that a\n\nwitness is contradicted by other evidence in the case does not constitute an attack upon\n\nhis reputation for truth and veracity.”) If this be an attack on Defendant’s character for\n\ntruthfulness, then such an attack occurs whenever the prosecution puts on evidence\n\ncontrary to a witness’s account. We decline to interpret Rule 608(a) as permitting\n\nevidence of a witness’s character for truthfulness whenever the witness’s testimony is\n\nchallenged.\n\n III. CONCLUSION\n\n We AFFIRM Defendant’s conviction.\n\n\n\n\n 21\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Christopher Lee MARTINEZ, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-06\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 6, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n UNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v. No. 18-8007\\n\\n CHRISTOPHER LEE MARTINEZ,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Wyoming\\n (D.C. No. 2:17-CR-00213-NDF-1)\\n _________________________________\\n\\nNeil D. Van Dalsem, Office of the Federal Public Defender, Muskogee, Oklahoma, for\\nDefendant-Appellant.\\n\\nTimothy J. Forwood, Assistant United States Attorney (Mark A. Klaassen, United States\\nAttorney, District of Wyoming, with him on the brief), Cheyenne, Wyoming, for\\nPlaintiff-Appellee.\\n _________________________________\\n\\nBefore HARTZ, MATHESON, and EID, Circuit Judges.\\n _________________________________\\n\\nHARTZ, Circuit Judge.\\n _________________________________\\n\\n A jury in the United States District Court for the District of Wyoming convicted\\n\\nDefendant Christopher Lee Martinez on one count of attempting to entice a minor to\\n\\nengage in illegal sexual activity. See 18 U.S.C. § 2422(b). On appeal Defendant argues\\n\\fthat the district court (1) should have authorized funds for a forensic psychologist, (2)\\n\\nimproperly excluded evidence of his history of mental illness, and (3) should have\\n\\nallowed him to present evidence of his character for truthfulness. Exercising jurisdiction\\n\\nunder 28 U.S.C. § 1291, we affirm.\\n\\n I. BACKGROUND\\n\\n A. Defendant’s Arrest\\n\\n On July 22, 2017, Special Agent Brent Metcalfe of the Wyoming Division of\\n\\nCriminal Investigation (DCI) posted a personal advertisement on the “Casual\\n\\nEncounters” section listed on the Craigslist website at that time. The purpose of the\\n\\nposting was to ferret out those who used the Internet to arrange sexual encounters with\\n\\nminors. Metcalfe chose the date because of the expected influx of tourists for Cheyenne\\n\\nFrontier Days. The advertisement was entitled “Fresh CFD Taboo” and read: “In town\\n\\nwith my dau. She is very eager. She wants to experience what Cheyenne has to offer.\\n\\nWho wants to have some ‘fresh fun.’” R., Vol. 3 at 247–49. Metcalfe explained that he\\n\\nused the terms fresh and eager to communicate to the reader that the subject of the\\n\\nadvertisement was young and sexually inexperienced.\\n\\n Defendant, 27 years old at the time, was one of the first to respond, sending a\\n\\nmessage shortly before 4:00 p.m. The email messages were relayed by Craigslist\\n\\nbetween the correspondents. Metcalfe posed as the father, telling Defendant that he\\n\\nhoped to “find a guy for my daughter, but she’s younger.” Id. at 256. When Defendant\\n\\nasked how old the girl was, Metcalfe answered that she was 12. Defendant said: “Okay.\\n\\nWhen you thinking? I’ll think about it. You ain’t a cop or law enforcement?” Id. at 257.\\n\\n\\n 2\\n\\fMetcalfe assured him that he was not a cop and the conversation continued. It centered\\n\\non whether Defendant wanted to have sexual relations with the daughter. Defendant\\n\\nasked Metcalfe what sexual acts he could engage in with the girl, whether he could take\\n\\nher virginity, and whether Metcalfe had condoms. Defendant repeatedly sought\\n\\nassurances that Metcalfe was not a “cop,” explaining that he was nervous because the\\n\\npolice had “popped a lot of people” during Frontier Days the previous year. Id. at 287.\\n\\n With Defendant’s interest established, Metcalfe requested that they move their\\n\\nconversation to “Kik,” an instant-messaging application that better allowed investigators\\n\\nto obtain Defendant’s identity. Defendant agreed. After he asked Metcalfe to send him a\\n\\npicture of the daughter, the two agreed to exchange pictures. Metcalfe sent Defendant a\\n\\npicture of part of the chest of a life-like mannequin. Defendant asked for another picture\\n\\nof the child’s full body with no face. Metcalfe refused to send additional pictures but\\n\\nagreed that Defendant could come to his motel to take his daughter’s “V card” (referring\\n\\nto her virginity). Id. at 302. Defendant eventually asked to message with the daughter\\n\\ndirectly, and Metcalfe assumed the girl’s identity. Defendant asked if she wanted to “lose\\n\\n[her] V card?” When Metcalfe asked what that meant, Defendant said “Virginity.” Id. at\\n\\n310. After exchanging about 100 messages over almost five hours, Defendant agreed to\\n\\nmeet at a motel and said that he would bring a condom.\\n\\n At 8:48 p.m., Defendant arrived at the motel parking lot and messaged Metcalfe,\\n\\nasking him to come out. Metcalfe and several other officers exited their vehicles and\\n\\narrested Defendant in his truck. He was in possession of a phone and a condom.\\n\\nForensic analysis confirmed that the phone was the one used to communicate with\\n\\n\\n 3\\n\\fMetcalfe on the Kik application. When interviewed by officers at the scene, Defendant\\n\\nadmitted to sending the messages but stated that he was getting ready to call the police\\n\\nbefore he was arrested. When asked why he had a condom, he said something like, “You\\n\\nhave to be real.” Id. at 321.\\n\\n B. Pretrial Motions\\n\\n Defense counsel filed a pretrial motion under 18 U.S.C. § 3006A requesting a\\n\\nforensic psychologist at the government’s expense. The motion stated the charge against\\n\\nDefendant, the trial date, the cost of a forensic evaluation and polygraph by Dr. Charles\\n\\nW. Dennison CP, Defendant’s minimal employment history, and his lack of funds to pay\\n\\nDr. Dennison. Other than stating that Defendant was on Social Security disability with a\\n\\nmental-health diagnosis, the motion said nothing regarding his mental health and the need\\n\\nfor an evaluation except as follows:\\n\\n Defendant was diagnosed with bipolar disorder, attention deficit disorder\\n (ADD), schizophrenia and depression when he was 18 years old. The\\n diagnosis was at Peak Wellness, Cheyenne, Wyoming. Defendant has a\\n Mental Health history of attempted suicide at 18 years of age,\\n hallucinations with the last occurrence taking place about 4-5 years ago.\\n Defendant was prescribed Trazadone, Invega, Amitriptyline, Abilify and\\n Fluoxetine. He is currently off medication.\\n\\n ...\\n\\n Due to the nature of the charges in this matter, a forensic evaluation is\\n necessary.\\n\\nR., Vol. 1 at 29. The district court denied the motion, saying:\\n\\n Defendant failed to provide the Court with information regarding the\\n necessity for a forensic evaluation by Dr. Dennison at Government\\n expense. The Court routinely grants forensic evaluations in cases involving\\n receipt of child porn, for purposes of sentencing mitigation. However, this\\n\\n\\n 4\\n\\f case involves attempted enticement of a minor. . . . Given the mandatory\\n minimum sentence in this case, it is not clear the purpose of a forensic\\n evaluation. Defendant has failed to provide the Court with any explanation\\n of the necessity for an evaluation, either for trial or sentencing purposes. IT\\n IS ORDERED that Defendant’s Motion for Forensic Psychologist at\\n Government Expense is DENIED at this time based on the Court’s finding\\n that Defendant has not established the necessity for this evaluation.\\n\\nR., Vol. 2 at 12 (italics added). Defense counsel did not renew the motion or later\\n\\nprovide further justification for a forensic psychologist.\\n\\n The government then filed a motion in limine to prevent Defendant from\\n\\npresenting evidence of his character for truthfulness and honesty and to exclude any\\n\\nevidence of his mental illness. On the first issue, it argued that because the charged\\n\\noffense of enticement of a minor is not a crimen falsi (that is, an offense in which a lie by\\n\\nthe defendant is one of the elements of the crime), testimony regarding Defendant’s\\n\\ncharacter for truthfulness was not relevant. Accordingly, it requested that Defendant’s\\n\\nuse of character evidence be limited to evidence that he is law abiding. The court agreed\\n\\nthat Defendant had not shown a basis for offering evidence of his character for\\n\\ntruthfulness, but said that it would later rule on specific issues related to character\\n\\nevidence that might arise during trial.\\n\\n On the second issue, the government contended that absent an insanity defense,\\n\\nevidence of Defendant’s mental defects or lack of volitional control was not an allowable\\n\\ndefense. Although the government acknowledged that evidence of mental health could\\n\\nbe admitted to negate specific intent, it pointed out that Defendant bore the burden of\\n\\nshowing that the proffered evidence was being offered for that purpose. This issue was\\n\\naddressed at the final pretrial conference, where the court gave defense counsel the\\n\\n\\n 5\\n\\fopportunity to explain the purpose of introducing evidence of Defendant’s mental health.\\n\\nDefense counsel stated:\\n\\n So my plan was to introduce a very limited number of medical records that\\n I’ve provided to the Government, and they basically just state that Mr.\\n Martinez was diagnosed with bipolar, I think back in 2010; that he was\\n prescribed medication. He’s also got ADD, I believe. And the only\\n purpose of those records is because I would have him testify and his family\\n testify that he has these mental issues and that his mental state of mind is\\n important because one of the elements in this case is that he obviously\\n knowingly had to complete this act, and that goes to that element of\\n whether or not he knowingly completed this act.\\n\\n And the medical records themselves are really just to – there to corroborate\\n what he would testify to about his own character and state of mind.\\n\\nR., Vol. 3 at 34 (emphasis added). Defense counsel acknowledged that Defendant “did\\n\\nnot plead guilty by reason of mental illness” but argued that the jury should decide\\n\\n“whether or not [his mental illness] affected his decision to do the things he did or not.”\\n\\nId. at 35. And responding to the arguments by the government, he said:\\n\\n We’re offering it to show his potential state of mind in general and who he\\n is. And this is a person – and like I said, I don’t know how you can – the\\n Court or any court could preclude an individual from getting on the stand\\n and testifying that, “Yes, I’m – you know, this is my background. I have\\n these issues that I’ve dealt with. I was on medication, but I wasn’t taking\\n the medication at the time,” and to describe his general makeup, I suppose.\\n\\nId. at 38.\\n\\n The court granted the motion in limine. It expressed concern that the proffered\\n\\nmental-illness testimony would “create[] the potential for confusion by the jury and\\n\\nseek[ ] to suggest a justification as opposed to a defense to any of the elements that the\\n\\nGovernment is required to prove by proof beyond a reasonable doubt.” Id. at 39. It noted\\n\\nthat this court had held “that psychological and psychiatric evidence that negates the\\n\\n\\n 6\\n\\fessential element of specific intent can be admissible” but that the admission of such\\n\\nevidence required clear demonstration of “how such evidence would negate intent rather\\n\\nthan merely present a dangerously confusing theory of defense more akin to justification\\n\\nand excuse.” R., Vol. 1 at 72 (internal quotation marks omitted). The court concluded\\n\\nthat without an expert or current medical records, Defendant lacked mental-health\\n\\nevidence showing “some cognitive defect precluding him from forming the specific\\n\\nintent for the charged offense” and thus the proffered evidence was irrelevant. Id. at 73.\\n\\n C. Trial\\n\\n The prosecution called only three witnesses at trial: Special Agent Robert\\n\\nLeazenby of the Wyoming DCI testified in general about the conduct of child-\\n\\nexploitation investigations; Agent Metcalfe testified about his communications with\\n\\nDefendant; and Mark Timmons of the Wyoming DCI testified about his search of\\n\\nDefendant’s car after the arrest.\\n\\n Before calling any witnesses, Defendant renewed his request to be permitted to\\n\\noffer mental-health evidence. He pointed to testimony by Agent Leazenby that\\n\\ninvestigators like to talk to arrestees in such cases to determine their states of mind. The\\n\\nprosecutor pointed out, however, that the state of mind Leazenby was referring to was\\n\\nwhether or not the arrestee wanted to have sex with the child. When the court asked\\n\\ndefense counsel how the mental-health evidence would relate to the instruction on the\\n\\nknowingly element of the offense, counsel responded that he wanted to put on the\\n\\nevidence simply as background evidence:\\n\\n\\n\\n\\n 7\\n\\f But that’s who he is and that’s kind of his general makeup, just as if a\\n person was employed and is – you know, as an officer and they’ve been\\n doing that for ten years. Well, in the last ten years he’s been doing really\\n nothing. Why has he been doing nothing? Because he’s on [Social\\n Security benefits], and the jury is going to know why he’s on [Social\\n Security benefits]. Well, that’s why.\\n\\nR., Vol. 3 at 377. The court was not persuaded. It held that while information\\n\\nconcerning Defendant’s background may be relevant for sentencing purposes, it was not\\n\\nrelevant at the trial.\\n\\n Defendant’s evidence consisted of (1) his own testimony, explaining that he was\\n\\nnot engaged in criminal activity but, rather, was attempting to identify someone engaged\\n\\nin child exploitation, whom he would report to law-enforcement authorities, and (2) six\\n\\nwitnesses who testified to his character as a law-abiding citizen.\\n\\n Defendant also unsuccessfully attempted to put on evidence of his character for\\n\\ntruthfulness, which he claimed had been attacked during his cross-examination by the\\n\\nprosecution. He argued that such evidence would assist the jury in determining whether\\n\\nto believe his statement that he did not intend to engage in sex with a minor. The court\\n\\nrejected the argument, reaffirming its earlier ruling that such evidence was not relevant\\n\\nbecause the charged offense did not include an element that concerned truthfulness. It\\n\\nfurther observed that because the bulk of the evidence in the case involved contradictory\\n\\nstatements made by Defendant before and after his arrest, testimony regarding his\\n\\ncharacter for truthfulness would not be probative in helping the jury decide which if any\\n\\nof his statements to believe.\\n\\n\\n\\n\\n 8\\n\\f II. DISCUSSION\\n\\n A. Denial of Motion to Hire Forensic Psychologist\\n\\n The Criminal Justice Act (CJA) permits a court to authorize funding for an expert\\n\\nwitness at the government’s expense:\\n\\n Counsel for a person who is financially unable to obtain investigative,\\n expert, or other services necessary for adequate representation may request\\n them in an ex parte application. Upon finding, after appropriate inquiry in\\n an ex parte proceeding, that the services are necessary and that the person is\\n financially unable to obtain them, the court . . . shall authorize counsel to\\n obtain the services.\\n\\n18 U.S.C. § 3006A(e)(1). The defendant bears the burden of persuasion. See United\\n\\nStates v. Greschner, 802 F.2d 373, 376 (10th Cir. 1986). The necessity of services must\\n\\nbe established with specificity. In the present context, “[g]eneral allegations supporting a\\n\\nrequest for court appointment of a psychiatric expert, without substantive supporting\\n\\nfacts, and undeveloped assertions that psychiatric assistance would be beneficial to the\\n\\ndefendant will not suffice to require the appointment of a psychiatrist to aid in the\\n\\npreparation of a criminal defense.” Liles v. Saffle, 945 F.2d 333, 336 (10th Cir. 1991).\\n\\nWe review the denial of a CJA funding request for an abuse of discretion. See United\\n\\nStates v. Solon, 596 F.3d 1206, 1210 (10th. Cir. 2010).\\n\\n On appeal Defendant argues that psychiatric testimony could have supported his\\n\\ndefense that he was merely trying to catch sexual predators, not trying to be one himself.\\n\\nHe states:\\n\\n [Defendant’s] case provides a classic example of how psychological\\n evidence can be relevant in evaluating a defendant’s specific intent.\\n\\n\\n\\n\\n 9\\n\\f [Defendant] was charged with an attempt crime, a specific intent crime.[1]\\n What he was actually thinking is of critical importance. [Defendant’s]\\n entire defense to this case was that he did not really intend to break the law\\n by enticing a minor to have sex. He defended this case on the ground that\\n he intended to identify a person who was offering up a minor for sex.\\n\\n For the jurors to evaluate that assertion, they certainly needed to know\\n about [Defendant’s] mental illness. The government’s case was based on\\n an argument that it would be completely bizarre for a person to have taken\\n steps [Defendant] took without first calling law enforcement. [Defendant]\\n should have been allowed to prepare a defense that informed the jury, that,\\n in fact, he is a person who suffers from mental illness, and he legitimately\\n may not proceed as a rational person would.\\n\\n Even though his conduct may seem strange, he was not trying to commit a\\n crime. To the contrary, from the moment of his arrest, he explained that he\\n was trying to catch a criminal. A casual observer might find his\\n explanation, provided by a “normal” person, to not make a great deal of\\n sense or be persuasive. However, in evaluating [Defendant’s] explanation,\\n the jurors needed to know that, in fact, [Defendant] is mentally ill. While a\\n mentally healthy person may not have tried to catch the Craigslist poster, a\\n person with bipolar disorder may well have done so.\\n\\nAplt. Br. at 25–26.\\n\\n This is an interesting argument, but we need not address it because it was not\\n\\nraised below and Defendant does not argue for plain-error review on appeal. See United\\n\\n\\n\\n1\\n To establish a violation of § 2422(b), the government must prove that the defendant\\n“(1) [used] a facility of interstate commerce; (2) to knowingly persuade, induce, entice, or\\ncoerce; (3) any individual who is younger than 18; (4) to engage in any sexual activity for\\nwhich any person can be charged with a criminal offense or attempting to do so.” United\\nStates v. Faust, 795 F.3d 1243, 1248 (10th Cir. 2015) (internal quotation marks omitted).\\n“To prove an attempt crime, the government must prove (1) an intent to commit the\\nsubstantive offense; and (2) the commission of an act which constitutes a substantial step\\ntowards commission of the substantive offense, . . . [which] must be something more than\\nmere preparation.” United States v. Vigil, 523 F.3d 1258, 1267 (10th Cir. 2008)\\n(typographical errors corrected and internal quotation marks omitted). Thus, in this case\\nthe government had to show that Defendant intended to entice a girl under 18 years old to\\nengage in criminal sexual activity.\\n\\n 10\\n\\fStates v. McGlothin, 705 F.3d 1254, 1267 (10th Cir. 2013) (if appellant forfeits an\\n\\nargument before the district court and then fails to explain in appellate briefing how the\\n\\nargument survives appellate review under the plain-error standard, then the appellant has\\n\\nwaived the argument on appeal). In his pretrial motion he stated that he suffered from\\n\\nvarious mental illnesses. But he did not even attempt to explain how these disorders\\n\\ncould negate any element of the charged crime. He wrongly assumes that simply putting\\n\\nthe court on notice that he suffered from mental-health disorders was somehow enough to\\n\\nsatisfy his burden. It is not the job of the court, however, to come up with arguments\\n\\nwhy a defendant’s mental illness must have influenced his conduct in committing a\\n\\ncrime.\\n\\n Further, the court’s order said that Defendant’s motion was merely denied “at this\\n\\ntime” for lack of the requisite showing. It left open the opportunity for Defendant to\\n\\nproperly explain why the forensic psychologist was needed. If the need for such an\\n\\nexpert should have been obvious to the court, Defendant could have easily explained the\\n\\npoint. Yet Defendant never pursued the issue again. We cannot fault the district court\\n\\nfor denying Defendant’s motion in light of the remarkably sparse argument he proffered.\\n\\nWe see no abuse of discretion here. (To the extent that Defendant attempts to raise for\\n\\nthe first time on appeal a due-process challenge to the denial of an expert, we also decline\\n\\nto address that argument. See id.)\\n\\n B. Exclusion of Evidence of Defendant’s Mental-Health History\\n\\n At trial Defendant unsuccessfully requested that the district court permit him to\\n\\noffer evidence of his history of mental illness, including medical records from more than\\n\\n\\n 11\\n\\ffive years past, his testimony, and his wife’s testimony. The court ruled that it was\\n\\nirrelevant. “We review a district court’s evidentiary rulings for abuse of discretion,\\n\\nconsidering the record as a whole.” United States v. Trujillo, 136 F.3d 1388, 1395 (10th\\n\\nCir. 1998). An evidentiary decision will not be reversed if it “falls within the bounds of\\n\\npermissible choice in the circumstances and is not arbitrary, capricious or whimsical.”\\n\\nUnited States v. Wills, 826 F.3d 1265, 1270 (10th Cir. 2016) (internal quotation marks\\n\\nomitted).\\n\\n On appeal Defendant argues, as he did with respect to the denial of funds for a\\n\\npsychiatric expert, that this mental-illness evidence could support his defense that he was\\n\\nnot seeking a sexual partner but was trying to catch a sexual predator. He contends that\\n\\nthe evidence would “explain[] that his arguably irrational behavior was the product of his\\n\\nmental illness.” Aplt. Br. at 34. Again, however, he did not raise this argument in\\n\\ndistrict court, so we will not address it. See McGlothin, 705 F.3d at 1267.\\n\\n What Defendant did argue in district court was that evidence of his mental illness\\n\\nwas relevant to communicating his overall background to the jury. To establish that\\n\\nDefendant offered no relevant purpose for the mental-health evidence, we set forth\\n\\nextended excerpts of defense counsel’s colloquy with the court when he renewed his\\n\\nmotion to admit the evidence. During the colloquy, counsel made clear that the purpose\\n\\nof the evidence was simply to tell the jury what kind of person Defendant is:\\n\\n DEFENSE COUNSEL: [A]s I understand the Court’s order, I’m not\\n allowed to introduce any evidence concerning his mental-health.\\n\\n However, in talking with him and providing the background for the jury of\\n what he’s – who he is and what he’s doing, I think it is necessary to state at\\n\\n\\n 12\\n\\fleast to a certain extent that, number one, that he’s on – he’s been on SSI\\n[Social Security] since he was 17 for ADD, bipolar and depression, and\\nthat’s what he’s been doing for the last 10 years. He doesn’t work.\\n\\nSo we at least need to explain that to the jury, that I think he should be\\nallowed to say, “Hey, this is what I’ve been doing for the last 10 years. I\\nwas on medication. I was off medication because I didn’t like it,” whatever\\nreason.\\n....\\n[A]nd if you look at the instructions, the knowingly instruction also talks\\nabout a person’s state of mind. And so the jury is going to consider his\\nstate of mind, and we’re telling them to.\\n...\\nTHE COURT [after also hearing from the prosecution]: How does the\\nstated diagnosis speak to the considerations in Instruction 24 which is that\\nhe was conscious and aware of his actions, realized what he was doing or\\nwhat was happening around him and did not act because of ignorance,\\nmistake or accident? Even assuming that the diagnosis is – would be the\\ndiagnosis today by a qualified healthcare professional, how does that\\ndiagnosis relate to the instruction on knowingly?\\n\\nDEFENSE COUNSEL: Well, Your Honor, I think we’re talking about two\\ndifferent things here. And, number one, I am not trying to introduce this\\nevidence as evidence that he had a mental defect at the time and did not act\\nin accordance with the statute because of that mental defect.\\n\\nWhat I am trying to introduce, simply, is that we have an individual that has\\nmental issues or a mental diagnosis and he’s been on SSI and it is part of\\nhis background. Now, there’s a reason for that and the jury, I think, is\\ngoing to want to know what he’s – who this person is.\\n\\nSo, number one, I don’t think anything is prohibitive of talking about an\\nindividual’s background, what he’s been doing. So I think that is fair game.\\n...\\nSo I don’t – like I said, I’m not going to use it. I don’t think – I wasn’t\\nplanning on bringing an expert to come in and testify that he suffers from\\ndepression, ADD and bipolar, and therefore, that’s what – why he\\ncommitted this act. . . .\\n\\nAnd that’s not what our intent is here. The only reason I want to introduce\\nthe records is to show that when he says, “yeah, I’ve been on SSI,” that’s\\ndocumented and the jury doesn’t think that he is faking it or just some\\nperson out there not – by choice not working in kind of a low-life situation\\nby choice.\\n\\n 13\\n\\f So we are not offering as mental health defense that information, but\\n merely as background information and that’s who this person is and what\\n he’s been doing. The jury can do whatever they want with it, I suspect.\\n\\nR., Vol. 3 at 372–78.\\n\\n “Evidence is relevant if: (a) it has any tendency to make a fact more or less\\n\\nprobable than it would be without the evidence; and (b) the fact is of consequence in\\n\\ndetermining the action.” Fed. R. Evid. 401. To be sure, “[t]he bar for admission under\\n\\nRule 401 is very low”; the evidence need “only provide a fact-finder with a basis for\\n\\nmaking some inference, or chain of inferences.” United States v. Jordan, 485 F.3d 1214,\\n\\n1218 (10th Cir. 2007) (internal quotation marks omitted). But Defendant’s proffered\\n\\nground for admitting this evidence did not meet even this low bar. Defense counsel\\n\\nnever suggested a chain of inference from this evidence to an element of the crime or a\\n\\ndefense.\\n\\n We recognize that it is generally appropriate to humanize a witness by letting the\\n\\nwitness tell the jury a few things about himself or herself. But even if such background\\n\\ninformation can be admissible, Federal Rule of Evidence 403 permits exclusion of even\\n\\nrelevant evidence “if its probative value is substantially outweighed by the danger of . . .\\n\\nunfair prejudice, confusing the issues, [or] misleading the jury.” Courts must be cautious\\n\\nabout admitting marginally relevant mental-health evidence because the jury may think\\n\\nthat it provides an “excuse” for misconduct or it may otherwise generate sympathy for the\\n\\ndefendant. See United States v. Cameron, 907 F.2d 1051, 1067 (11th Cir. 1990)\\n\\n(“[P]sychiatric evidence . . . presents an inherent danger that it will distract the jury[ ]\\n\\nfrom focusing on the actual presence or absence of mens rea, and . . . may easily slide\\n\\n\\n 14\\n\\finto wider usage that opens up the jury to theories of defense more akin to justification.”\\n\\n(internal quotation marks omitted)). Here, the district court permitted some humanizing\\n\\nevidence, such as Defendant’s testimony that he was unemployed and on social-security\\n\\nbenefits, because it saw no danger of improper prejudice or confusing the jury. But it\\n\\nexcluded the mental-health evidence, which it viewed as “just an effort to elicit\\n\\nsympathy.” R., Vol. 3 at 378. This ruling was not an abuse of discretion.\\n\\n C. Exclusion of Character Evidence\\n\\n Defendant argues that the district court abused its discretion in excluding evidence\\n\\nof his character for truthfulness after his credibility was allegedly attacked on cross-\\n\\nexamination. He contends that the court’s decision to exclude evidence of his character\\n\\nfor truthfulness was based on a misapplication of Rule 608 of the Federal Rules of\\n\\nEvidence. “We review a trial court’s exclusion of character evidence for abuse of\\n\\ndiscretion.” Tanberg v. Sholtis, 401 F.3d 1151, 1167 (10th Cir. 2005). But we review de\\n\\nnovo the district court’s legal interpretation of the Federal Rules of Evidence. See United\\n\\nStates v. Torrez-Ortega, 184 F.3d 1128, 1132 (10th Cir. 1999).\\n\\n Under Rule 608 a witness’s credibility ordinarily may be attacked by presenting\\n\\nevidence of the witness’s character for untruthfulness, but positive evidence of a truthful\\n\\ncharacter is permitted only in response to an attack on such character:\\n\\n Reputation or Opinion Evidence. A witness’s credibility may be attacked\\n or supported by testimony about the witness’s reputation for having a\\n character for truthfulness or untruthfulness, or by testimony in the form of\\n an opinion about that character. But evidence of truthful character is\\n admissible only after the witness’s character for truthfulness has been\\n attacked.\\n\\n\\n\\n 15\\n\\fFed. R. Evid. 608(a). An advisory committee note clarifies what constitutes an attack on\\n\\ncharacter for truthfulness:\\n\\n Opinion or reputation that the witness is untruthful specifically qualifies as\\n an attack under the rule, and evidence of misconduct, including conviction\\n of crime, and of corruption also fall within this category. Evidence of bias\\n or interest does not. Whether evidence in the form of contradiction is an\\n attack upon the character of the witness must depend upon the\\n circumstances.\\n\\nFed. R. Evid. 608(a) Advisory Committee Notes to 1972 proposed rules.\\n\\n No firm line can be drawn regarding whether cross-examination of a witness\\n\\namounts to an attack on the witness’s character for truthfulness. But a useful test\\n\\nemployed by the courts is whether the questioning attacks the veracity of the witness’s\\n\\naccount of the facts in the specific case before the court or attacks the witness’s veracity\\n\\nin general. The Ninth Circuit expressed the point as follows:\\n\\n The purpose of Rule [608(a)] is to encourage direct attacks on a witness’s\\n veracity in the instant case and to discourage peripheral attacks on a\\n witness’s general character for truthfulness. To this end, the Rule prohibits\\n rehabilitation by character evidence of truthfulness after direct attacks on a\\n witness’s veracity in the instant case. However, the Rule permits\\n rehabilitation after indirect attacks on a witness’s general character for\\n truthfulness.\\n\\nUnited States v. Dring, 930 F.2d 687, 690–91 (9th Cir. 1991); see Renda v. King, 347\\n\\nF.3d 550, 554 (3d Cir. 2003) (“Direct attacks on a witness’s veracity in the particular\\n\\ncase do not open the door for evidence of the witness’s good character.” (emphasis\\n\\nadded)).\\n\\n Some circumstances are easy to characterize. For example, impeachment of the\\n\\nwitness through evidence of a prior felony conviction or prior fraudulent activity is not\\n\\n\\n\\n 16\\n\\fspecific to the case being tried and amounts to an attack on character. See Dring, 930\\n\\nF.2d. at 691 (“[I]ndirect attacks on truthfulness include opinion evidence, reputation\\n\\nevidence, and evidence of corruption, which require the jury to infer that the witness is\\n\\nlying at present simply because he has lied often in the past.”); Weinstein’s Federal\\n\\nEvidence § 608.12[1]; Roger Park & Tom Lininger, The New Wigmore: A Treatise on\\n\\nEvidence: Impeachment and Rehabilitation § 9.2 (2012). In contrast, a cross-\\n\\nexamination that focuses on the witness’s memory or perception does not implicate\\n\\ncharacter. Also, evidence of bias generally is not an attack on character. The fact that the\\n\\nwitness is a party’s mother may lessen her credibility in this case, but it does not mean\\n\\nthat she is usually an untruthful person. See Wigmore § 9.2 at 332. But cf. id. (if the\\n\\nproof of bias is that a party bribed the witness, the fact that the witness took a bribe is a\\n\\nreflection on character). And “most courts do not view contradiction of one witness’s\\n\\ntestimony by other witnesses as an attack on character.” Weinstein § 608.12[4][ a]; see\\n\\nUnited States v. Drury, 396 F.3d 1303, 1315 (11th Cir. 2005) (“An attack that consists\\n\\nonly of Government counsel pointing out inconsistencies in testimony and arguing that\\n\\nthe accused’s testimony is not credible does not constitute an attack on the accused’s\\n\\nreputation for truthfulness within the meaning of Rule 608.” (internal quotation marks\\n\\nomitted)); Kauz v. United States, 188 F.2d 9, 10 (5th Cir. 1951) (“The mere fact that a\\n\\nwitness is contradicted by other evidence in the case does not constitute an attack upon\\n\\nhis reputation for truth and veracity.”).\\n\\n Perhaps the most difficult questions arise when a witness has been vigorously\\n\\ncross-examined. “[A] slashing cross-examination can carry strong accusations of\\n\\n\\n 17\\n\\fmisconduct and bad character, which even the witness’s forceful denial will not remove\\n\\nfrom the jury’s mind.” 1 McCormick on Evidence § 47 at 309 (7th ed. 2013) (footnote\\n\\nomitted). Those are situations in which our standard of review properly affords\\n\\nsubstantial discretion to the trial judge.\\n\\n In this case there was nothing resembling an abuse of discretion in the district\\n\\ncourt’s exclusion of Defendant’s character-for-truthfulness evidence. The clear purpose\\n\\nof the prosecutor’s cross-examination of Defendant was to obtain admissions for much of\\n\\nthe government’s case. Defendant not only admitted to what he did or did not do but also\\n\\nto the unreasonableness of his actions. The following excerpt gives a flavor of the cross-\\n\\nexamination:\\n\\n Q: So despite your plan to try to protect this young child, you don’t tell anyone\\n over the course of five hours what you’re doing?\\n\\n A: Yes.\\n\\n Q: Or where you’re headed?\\n\\n A: Yes.\\n\\n Q: Doesn’t that seem dangerous?\\n\\n A: Yes.\\n\\n Q: For you?\\n\\n A: Yes.\\n\\n Q: For the girl?\\n\\n A: Yes.\\n\\n Q: You brought up condoms in these conversations, correct?\\n\\n A: Yes.\\n\\n\\n\\n 18\\n\\fQ: You actually proposed having oral sex with a 12-year-old correct?\\n\\nA: Yes.\\n\\nQ: You repeatedly brought up all kinds of different sex acts that you and this 12-\\nyear-old girl could engage in, correct?\\n\\nA: Yes.\\n\\nQ: You have testified that you were concerned about the welfare of this girl; is that\\nright?\\n\\nA: Yes.\\n\\nQ: And that you wanted to save her?\\n\\nA: Yes.\\n\\nQ: And I’m assuming you didn’t want to cause her any trauma or pain?\\n\\nA: No.\\n\\nQ: But you didn’t care enough to not ask for a photo, did you?\\n\\nA: No.\\n\\nQ: Don’t you think that it would be traumatic, for this girl’s photo to be shared?\\n\\nA: Yeah.\\n\\nQ: You specifically asked for more photos, didn’t you?\\n\\nA: Yes.\\n\\nQ: And you specifically requested full-body photos with no face?\\n\\nA: Yes.\\n\\nQ: Would you not agree that not having the face in those photos would actually\\nmake it more difficult to hold this person accountable?\\n\\nA: Yes.\\n\\nQ: You were wanting to actually hold this person accountable. Wouldn’t you\\nwant to see who the girl actually is?\\n\\nA: Yes.\\n\\n\\n 19\\n\\f Q: But instead, you specifically request no face photos, correct?\\n\\n A: Yes.\\n\\n Q: And you sent a photo of yourself and block all identifiers, don’t you?\\n\\n A: Yes.\\n\\n Q: You also don’t care enough about the safety of this child to not speak to her,\\n correct?\\n\\n A: Yes.\\n\\nR., Vol. 3 at 412–14. On two occasions Defendant initially disagreed with the\\n\\nprosecutor, but then the matter was clarified and the prosecutor did not challenge his\\n\\nanswer. See id. at 4112; id. at 4163. The only occasion when the prosecutor was clearly\\n\\nchallenging the veracity of Defendant’s testimony was the final exchange: “Q: You\\n\\nshowed up to take her V card, didn’t you? A: No.” Id. at 418.\\n\\n\\n\\n\\n2\\n Q: And I believe you indicated before that you don’t feel like you’re very Internet\\n [savvy]? Is that how you said that?\\n A: No.\\n Q: Yet you specifically informed the purported father in this case how to share a\\n picture with you on Kik, correct?\\n A: That’s totally different than –\\n Q: So you’re Internet [savvy] when it comes to Kik, but not Internet [savvy] on\\n Craigslist where you’re specifically going to a certain section on there?\\n A: Yes.\\n3\\n Q: So you showed up ready to meet the girl, correct?\\n A: No.\\n Q: Is that a yes or a no?\\n A: No.\\n Q: You showed up to meet her father, is that what you’re indicating?\\n A: Yes.\\n\\n\\n 20\\n\\f As the district court observed, “The defendant’s response to virtually every\\n\\nquestion by the Government was yes.” Id. at 431. Rather than challenging Defendant’s\\n\\nveracity, the prosecutor generally wanted the jury to believe all his answers except the\\n\\nlast. Indeed, the frankness of Defendant’s admissions on cross-examination likely led the\\n\\njury to conclude that Defendant was basically a truthful person. But given all those\\n\\nadmissions, it would be impossible to believe that he was really intending to act as an\\n\\nagent of law enforcement rather than as a sexual predator. The prosecution was\\n\\nchallenging Defendant’s veracity with respect to a specific issue in the present case (his\\n\\nintent), not his general truthfulness. See Renda, 347 F.3d at 554; Dring, 930 F.2d at 690–\\n\\n91. And the basis for the challenge was merely the unbelievability of his statement of his\\n\\nintent in light of the undisputed facts. See Kauz, 188 F.2d at 10 (“The mere fact that a\\n\\nwitness is contradicted by other evidence in the case does not constitute an attack upon\\n\\nhis reputation for truth and veracity.”) If this be an attack on Defendant’s character for\\n\\ntruthfulness, then such an attack occurs whenever the prosecution puts on evidence\\n\\ncontrary to a witness’s account. We decline to interpret Rule 608(a) as permitting\\n\\nevidence of a witness’s character for truthfulness whenever the witness’s testimony is\\n\\nchallenged.\\n\\n III. CONCLUSION\\n\\n We AFFIRM Defendant’s conviction.\\n\\n\\n\\n\\n 21\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2257,"cells":{"id":{"kind":"number","value":4617295,"string":"4,617,295"},"name":{"kind":"string","value":"ADVANCED RECOVERY SYSTEMS, a Utah Limited Liability Company, Plaintiff Counterclaim Defendant, v. AMERICAN AGENCIES, a Pennsylvania Limited Liability Company, Defendant Counterclaimant Third-Party Plaintiff-Appellee, NRA Group, a Pennsylvania Limited Liability Company, A/K/A National Recovery Agency; Steven C. Kusic, CEO/managing Member of American Agencies, LLC and/or NRA Group, LLC, and Individually, Defendants, Brent Sloan, Third-Party Defendant-Appellant, Kinum, Inc.; Scott Mitchell; Blake Reynolds, Third-Party Defendants, and Sajax Software, Third-Party Defendant Counterclaimant."},"name_abbreviation":{"kind":"string","value":"Advanced Recovery Sys. v. Am. Agencies, Ltd."},"decision_date":{"kind":"string","value":"2019-05-07"},"docket_number":{"kind":"string","value":"17-4202"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Bacharach, Baldock, Phillips\", \"parties\": \"\", \"opinions\": [{\"author\": \"BACHARACH, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 7, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\nADVANCED RECOVERY\\nSYSTEMS, a Utah limited liability\\ncompany,\\n\\n Plaintiff Counterclaim\\n Defendant,\\n\\nv. No. 17-4202\\n\\nAMERICAN AGENCIES, a\\nPennsylvania limited liability\\ncompany,\\n\\n Defendant Counterclaimant\\n Third-Party Plaintiff -\\n Appellee,\\n\\nNRA GROUP, a Pennsylvania\\nlimited liability company, a/k/a\\nNational Recovery Agency;\\nSTEVEN C. KUSIC, CEO/managing\\nmember of American Agencies, LLC\\nand/or NRA Group, LLC, and\\nindividually,\\n\\n Defendants,\\n\\nBRENT SLOAN,\\n\\n Third-Party Defendant -\\n Appellant,\\n\\nKINUM, INC.; SCOTT MITCHELL;\\nBLAKE REYNOLDS,\\n\\n Third-Party Defendants,\\n\\f and\\n\\n SAJAX SOFTWARE,\\n\\n Third-Party Defendant\\n Counterclaimant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Utah\\n (D.C. No. 2:13-CV-00283-DAK-BCW)\\n _________________________________\\n\\nRichard D. Salgado, Dentons US LLP, Dallas, Texas (Kelley C. Cox,\\nDentons US, Dallas, Texas, and Wade P. K. Carr, Dentons US, Kansas\\nCity, Missouri, with him on the briefs), for Third-Party Defendant-\\nAppellant.\\n\\nMichael K. Erickson (Carol A. Funk, with him on the brief), Ray Quinney\\n& Nebeker P.C., Salt Lake City, Utah, for Third-Party Plaintiff-Appellee.\\n _________________________________\\n\\nBefore BACHARACH, BALDOCK, and PHILLIPS, Circuit Judges.\\n _________________________________\\n\\nBACHARACH, Circuit Judge.\\n _________________________________\\n\\n This appeal grew out of Mr. Brent Sloan’s participation in two\\n\\ntransactions. The first transaction entailed a merger between Advanced\\n\\nRecovery Systems, LLC and Kinum, Inc.; 1 the second transaction consisted\\n\\nof a sale of software from Kinum to Sajax Software, LLC.\\n\\n\\n\\n\\n1\\n At the time of the merger, Kinum was known as “Fidelis Asset\\nManagement, Inc.” In the interest of simplicity, however, we refer to the\\nentity (before and after the merger) as “Kinum.”\\n\\n\\n 2\\n\\f American Agencies, LLC alleged harm from these transactions and\\n\\nsued Mr. Sloan for damages and restitution. 2 After the close of evidence,\\n\\nMr. Sloan filed a motion for judgment as a matter of law. Following the\\n\\ndenial of this motion, a jury found Mr. Sloan liable on American Agencies’\\n\\nclaims of tortious interference with business relations, conspiracy to\\n\\ninterfere with business relations, tortious interference with contract,\\n\\ncopyright infringement, unjust enrichment, and misappropriation of trade\\n\\nsecrets. 3 Mr. Sloan unsuccessfully renewed his motion for judgment as a\\n\\nmatter of law. After the district court denied this motion, Mr. Sloan\\n\\nappealed. We affirm in part and reverse in part based on four conclusions:\\n\\n 1. On the claims of tortious interference with business relations\\n and conspiracy to interfere with business relations, Mr. Sloan\\n contends that (1) one of American Agencies’ theories of\\n improper means is preempted by a Utah statute and (2)\\n American Agencies did not present sufficient evidence of\\n improper means. We disagree because Mr. Sloan did not\\n preserve his preemption argument and the jury could have\\n reasonably found improper means based on deceit. We thus\\n conclude that the district court properly denied Mr. Sloan’s\\n motion for judgment as a matter of law on these claims.\\n\\n 2. On the claim of tortious interference with contract, Mr. Sloan\\n argues that the jury instructions erroneously and prejudicially\\n\\n\\n\\n2\\n Federal jurisdiction existed under 28 U.S.C. §§ 1331(a)(1), 1332, and\\n1367(a).\\n3\\n The finding of liability for misappropriation of trade secrets is not\\ninvolved in this appeal.\\n\\n\\n 3\\n\\f excluded improper means as an element. We agree with Mr.\\n Sloan and reverse the judgment on this claim. 4\\n\\n 3. On the claim of copyright infringement, Mr. Sloan contends\\n that the jury could not have reasonably found commercial use\\n or regarded the pertinent documents as original. We disagree,\\n concluding that (1) Mr. Sloan did not preserve his commercial-\\n use argument and (2) American Agencies’ evidence on\\n originality was sufficient.\\n\\n 4. On the claim of unjust enrichment, Mr. Sloan contends that the\\n jury could not have reasonably inferred the value of a benefit\\n to Mr. Sloan. 5 We agree, so we reverse the denial of Mr.\\n Sloan’s motion for judgment as a matter of law on this claim.\\n\\n Background\\n\\n1. Advanced Recovery Systems enters into a licensing agreement\\n with American Agencies.\\n\\n American Agencies is a debt-collection agency that entered into a\\n\\nlicensing agreement with Advanced Recovery Systems. Under the licensing\\n\\nagreement, American Agencies enjoyed\\n\\n the exclusive right to use certain debt-collection software\\n developed by Advanced Recovery Systems and\\n\\n the right of first refusal with respect to any future sale of\\n Advanced Recovery Systems.\\n\\n\\n\\n\\n4\\n On appeal, Mr. Sloan also challenges the district court’s award of\\nattorney’s fees to American Agencies. This part of the award was based on\\nthe claim of tortious interference with contract. Our reversal on this claim\\nencompasses the award of attorney’s fees.\\n5\\n Mr. Sloan also contends that other legal remedies were adequate to\\ncompensate American Agencies. We need not address this contention.\\n 4\\n\\fThe debt-collection software contained American Agencies’ customer data,\\n\\nincluding a client list, client history, fee structure, and rate of success.\\n\\n2. Advanced Recovery Systems merges into Kinum, and Kinum sells\\n the software to Sajax.\\n\\n Without American Agencies’ knowledge, Advanced Recovery\\n\\nSystems merged into Kinum. See p. 3 n.1, above. Mr. Sloan helped to\\n\\nfacilitate the merger and became Kinum’s chief executive officer after the\\n\\nmerger. As the chief executive officer, Mr. Sloan oversaw Kinum’s sale of\\n\\nthe debt-collection software to Sajax. With the software came American\\n\\nAgencies’ customer data.\\n\\n\\n\\n\\n 5\\n\\f6\\n\\f The Individual Claims and Mr. Sloan’s Appellate Arguments\\n1. Liability for tortious interference with business relations and\\n conspiracy to interfere with business relations: The evidence\\n adequately supported the jury’s findings of liability.\\n\\n On the claims of tortious interference with business relations and\\n\\nconspiracy to commit this tort, American Agencies had to prove improper\\n\\nmeans. Overstock.com, Inc. v. SmartBargains, Inc., 192 P.3d 858, 864\\n\\n(Utah 2008); see also Puttuck v. Gendron, 199 P.3d 971, 978 (Utah App.\\n\\n2008) (stating that a claim of civil conspiracy under Utah law requires an\\n\\nunderlying tort). 6 American Agencies alleged that Mr. Sloan had used\\n\\nimproper means in two ways:\\n\\n 1. using deceit to conceal transfers of the debt-collection software\\n and American Agencies’ customer data\\n\\n 2. initiating unfounded litigation against American Agencies. 7\\n\\nMr. Sloan responds to these allegations by arguing that\\n\\n the theory of improper means through deceit is preempted by a\\n Utah statute and\\n\\n the evidence did not indicate that the litigation had been\\n unfounded.\\n\\nWe reject these arguments.\\n\\n\\n6\\n The district court and the parties treat Utah law as the applicable\\nlaw, so we also apply Utah law. See Strickland Tower Maint., Inc. v. AT&T\\nCommc’ns, Inc., 128 F.3d 1422, 1426 (10th Cir. 1997).\\n7\\n The parties agree that a third theory presented by American Agencies\\n(altering American Agencies’ license agreements with sales agents) did not\\napply to Mr. Sloan.\\n\\n 7\\n\\f A. Mr. Sloan did not preserve his preemption argument.\\n\\n On appeal, Mr. Sloan urges preemption of American Agencies’\\n\\ntheory of deceit based on a Utah statute. But Mr. Sloan failed to preserve\\n\\nhis preemption argument.\\n\\n To preserve the argument, Mr. Sloan needed to comply with Rule 50\\n\\nof the Federal Rules of Civil Procedure, which governs motions for\\n\\njudgment as a matter of law. Unitherm Food Sys., Inc. v. Swift-Eckrich,\\n\\nInc., 546 U.S. 394, 399 (2006). Under subsection (a) of this rule, a litigant\\n\\ncan move for judgment before the jury renders its verdict. Fed. R. Civ. P.\\n\\n50(a). If a litigant moves for a pre-verdict judgment under subsection (a)\\n\\nand the court denies the motion, the litigant can renew the motion after the\\n\\nverdict under subsection (b) of the rule. Fed. R. Civ. P. 50(b); see\\n\\nMarshall v. Columbia Lea Reg’l Hosp., 474 F.3d 733, 738–39 (10th Cir.\\n\\n2007). If a ground is omitted from a pre-verdict motion, however, the\\n\\nground cannot be asserted in a post-verdict motion or in an appeal. See\\n\\nMarshall, 474 F.3d at 738–39 (cannot be asserted in the post-verdict\\n\\nmotion); Unitherm Food Sys., Inc., 546 U.S. at 399 (cannot be asserted in\\n\\nthe appeal).\\n\\n Before the jury returned a verdict, Mr. Sloan moved for judgment as\\n\\na matter of law under Rule 50(a), contending that American Agencies\\n\\nhadn’t presented evidence of (1) intentional interference by improper\\n\\nmeans or (2) injury caused by the interference. But Mr. Sloan’s motion did\\n\\n 8\\n\\fnot include his current argument involving preemption. As a result, this\\n\\nargument was not preserved for appeal.\\n\\n B. Mr. Sloan doesn’t contest the sufficiency of the evidence on\\n deceit, so we reject his challenge to the claims of tortious\\n interference with business relations and conspiracy to\\n commit this tort.\\n\\n On appeal, Mr. Sloan does not challenge the sufficiency of the\\n\\nevidence supporting American Agencies’ theory of deceit; he challenges\\n\\nonly the sufficiency of the evidence supporting the theory of unfounded\\n\\nlitigation. Given the limited scope of this challenge, we treat the deceit\\n\\ntheory as sufficient for liability. 8\\n\\n The district court’s special-verdict form didn’t distinguish between\\n\\nAmerican Agencies’ two theories of improper means, so we don’t know\\n\\n\\n\\n\\n8\\n Even if Mr. Sloan had challenged the sufficiency of the evidence on\\ndeceit, we would have rejected the challenge. In our view, the trial\\nevidence permitted a reasonable jury to find that Mr. Sloan had deceitfully\\nconcealed transfers involving the software and American Agencies’\\ncustomer data. See Bartee v. Michelin N. Am., Inc., 374 F.3d 906, 914\\n(10th Cir. 2004) (sufficient evidence exists if there is evidence on which a\\njury could properly return a verdict for the non-movant). This evidence\\nincluded support for three findings:\\n First, Mr. Sloan knew before the merger with Kinum that American\\nAgencies had an exclusive license to use the software and a right of first\\nrefusal on a sale of Advanced Recovery Systems.\\n Second, with knowledge of these rights, Mr. Sloan helped to merge\\nAdvanced Recovery Systems into Kinum without telling American\\nAgencies of the merger or the transfer of software to Kinum.\\n\\n\\n 9\\n\\fwhich theory the jury credited. Given this uncertainty, we must affirm if\\n\\nsufficient evidence existed on either of American Agencies’ factual\\n\\ntheories. Kirkbride v. Terex USA, LLC, 798 F.3d 1343, 1349 (10th Cir.\\n\\n2015). So in the absence of a challenge to the sufficiency of the evidence\\n\\non deceit, we need not decide whether the evidence would have supported\\n\\nAmerican Agencies’ theory of unfounded litigation.\\n\\n Mr. Sloan points to a line of cases suggesting that “reversal is . . .\\n\\nnecessary if either basis [for a verdict] was improper.” Appellant’s Reply\\n\\nBr. at 18 (emphasis in original); see id. at 18–19. But this line of cases\\n\\napplies only when the defendant challenges the validity of a legal theory.\\n\\nPratt v. Petelin, 733 F.3d 1006, 1009 (10th Cir. 2013). These cases do not\\n\\napply when the defendant challenges the sufficiency of the evidence on\\n\\nsome (but not all) of the plaintiff’s factual theories:\\n\\n [T]hese cases address the situation where the jury may have\\n based its verdict on an incorrect or entirely unsupported legal\\n theory. They are thus distinguishable from the case at hand,\\n where [the defendant] claims that some, but not all, of the\\n factual bases presented to the jury for one legal theory—\\n negligence—were unsupported by sufficient evidence.\\n\\n\\n\\n\\n Third, without telling American Agencies, Mr. Sloan directed Kinum\\nto sell the software to Sajax even though the software contained American\\nAgencies’ customer data.\\n\\n 10\\n\\fId. (emphasis in original). Here we are addressing the sufficiency of\\n\\nevidence on factual theories, not the validity of a legal theory. Mr. Sloan’s\\n\\ncited authority is thus inapplicable.\\n\\n2. Liability for tortious interference with contract: The district\\n court erroneously and prejudicially failed to include improper\\n means as an element of the claim.\\n\\n American Agencies claimed tortious interference with contract,\\n\\nalleging that Mr. Sloan had induced Advanced Recovery Systems to breach\\n\\nits licensing agreement. The district court instructed the jury on the\\n\\nelements of the claim but did not include improper means as an element.\\n\\nThe omission constituted an error that prejudiced Mr. Sloan.\\n\\n We apply the abuse-of-discretion standard. Lederman v. Frontier\\n\\nFire Protection, Inc., 685 F.3d 1151, 1154 (10th Cir. 2012). But in\\n\\napplying this standard, we conduct de novo review of the instructions as a\\n\\nwhole to assess their accuracy under Utah law. Royal Maccabees Life Ins.\\n\\nCo. v. Choren, 393 F.3d 1175, 1179 (10th Cir. 2005).\\n\\n Reviewing the instructions de novo, we conclude that the district\\n\\ncourt erred because the Utah Supreme Court treats improper means as an\\n\\nelement of tortious interference with contract. See C.R. England v. Swift\\n\\nTransp. Co., 2019 UT 8, ¶ 39 (Feb. 27, 2019) (“Because the weight of\\n\\nauthority supports St. Benedict’s adoption of the ‘improper means’ element\\n\\nfor the tort of intentional interference with contract, and because this\\n\\nelement has become firmly embedded in Utah law, we reaffirm it.”); see\\n 11\\n\\falso St. Benedict’s Devel. Co. v. St. Benedict’s Hosp., 811 P.2d 194, 201\\n\\n(Utah 1991) (stating that one incurs liability for intentional interference\\n\\nwith contract by “intentionally and improperly” causing a party not to\\n\\nperform the contract). By failing to correctly tell the jury what’s needed\\n\\nfor liability, the district court misled the jury. See Wankier v. Crown\\n\\nEquip. Corp., 353 F.3d 862, 868 (10th Cir. 2003) (“A district court’s\\n\\nfailure to inform the jury of all the elements essential to a plaintiff’s claim\\n\\nnecessarily misleads the jury.”).\\n\\n American Agencies argues that the error didn’t prejudice Mr. Sloan.\\n\\nWe disagree. An error in jury instructions requires reversal if the error was\\n\\nprejudicial. Heggy v. Heggy, 944 F.2d 1537, 1542 (10th Cir. 1991). An\\n\\nerror is prejudicial if “the jury might have based its verdict on the\\n\\nerroneously given instruction.” Level 3 Commc’ns, LLC v. Liebert Corp.,\\n\\n535 F.3d 1146, 1158 (10th Cir. 2008) (emphasis in original) (quoting\\n\\nWankier, 353 F.3d at 867). We thus must reverse based on an erroneous\\n\\ninstruction if there is even a slight possibility of an effect on the verdict.\\n\\nId.\\n\\n Such a possibility doesn’t always exist. For example, omission of an\\n\\nelement may be harmless if the verdict on another claim would have\\n\\nrequired the jury to find the omitted element. See United States v.\\n\\nMcDonald, 150 F.3d 1301, 1304–05 (10th Cir. 1998) (concluding that the\\n\\nomission of elements of a criminal offense in the jury instructions was\\n\\n 12\\n\\fharmless because the verdict of guilty on a separate criminal offense\\n\\n“necessarily embraced the missing elements”).\\n\\n American Agencies contends that the jury necessarily found that Mr.\\n\\nSloan had used improper means to interfere with American Agencies’\\n\\nlicensing agreement with Advanced Recovery Systems because\\n\\n the jury instructions included improper means as an element of\\n tortious interference with business relations and\\n\\n the jury found tortious interference with American Agencies’\\n business relations.\\n\\nThis contention assumes that American Agencies’ theories of improper\\n\\nmeans for tortious interference with business relations would also support\\n\\nliability for tortious interference with contract. 9 If even one theory of\\n\\nimproper means supported liability for tortious interference with business\\n\\nrelations but not for tortious interference with contract, the instructional\\n\\nerror would be prejudicial. See p. 12, above.\\n\\n As noted above, American Agencies presented two theories of\\n\\nimproper means on the claim against Mr. Sloan for tortious interference\\n\\nwith business relations:\\n\\n 1. the use of deceit to conceal the transfers of the debt-collection\\n software and American Agencies’ customer data\\n\\n\\n9\\n American Agencies assumes that Utah uses the same definition of\\nimproper means for both tortious interference with contract and tortious\\ninterference with business relations. For the sake of argument, we can\\nmake the same assumption.\\n\\n 13\\n\\f 2. the initiation of unfounded litigation against American\\n Agencies.\\n\\nAmerican Agencies based the deceit theory on two transactions:\\n\\n 1. Advanced Recovery Systems’ merger with Kinum\\n\\n 2. Kinum’s sale of the debt-collection software to Sajax.\\n\\nThe jury might have found liability for tortious interference with business\\n\\nrelations based on Kinum’s sale of the debt-collection software. For\\n\\ntortious interference with contract, however, the jury might have rejected\\n\\nliability on this basis by viewing Mr. Sloan as the principal of one of the\\n\\ncontracting parties (Kinum).\\n\\n Under Utah law, a corporation cannot incur liability for interfering\\n\\nwith its own contract. See Leigh Furniture & Carpet Co. v. Isom, 657 P.2d\\n\\n293, 301 (Utah 1982) (“[O]ne party to a contract cannot be liable for the\\n\\ntort of interference with contract for inducing a breach by himself or the\\n\\nother contracting party.”), overruled on other grounds by Eldridge v.\\n\\nJohndrow, 345 P.3d 553 (Utah 2015). And after Advanced Recovery\\n\\nSystems merged with Kinum, Kinum became a party to the licensing\\n\\nagreement. See Utah Stat. § 48-3a-1026(1)(d) (explaining that when a\\n\\nlimited liability company merges with another entity, “all debts,\\n\\nobligations, and other liabilities” of the limited liability company become\\n\\n“debts, obligations, and other liabilities of the surviving entity”). So when\\n\\n\\n\\n\\n 14\\n\\fKinum sold the debt-collection software, it was a party to the licensing\\n\\nagreement and Mr. Sloan was Kinum’s chief executive officer.\\n\\n To find that Mr. Sloan’s participation in this sale constituted\\n\\nimproper means for tortious interference with contract, the jury would have\\n\\nneeded to find that Kinum’s chief executive officer had tortiously\\n\\ninterfered with his own company’s contract. As noted above, Utah law\\n\\ndoesn’t authorize liability for tortiously interfering with one’s own\\n\\ncontract. And under Utah law, corporations can act only through their\\n\\nagents. Stratton v. W. States Constr., 440 P.2d 117, 118 (Utah 1968).\\n\\n In similar circumstances, courts throughout the country have held\\n\\nthat a corporate officer cannot incur liability for tortiously interfering with\\n\\nthe corporation’s own contract. 10 Here, however, we need not decide\\n\\n\\n10 See Boulevard Assocs. v. Sovereign Hotels, Inc., 72 F.3d 1029, 1036\\n(2d Cir. 1995) (noting that Connecticut courts have held that “[a]n agent\\nacting legitimately within the scope of his authority cannot be held liable\\nfor interfering with or inducing his principal to breach a contract between\\nhis principal and a third party, because to hold him liable would be, in\\neffect, to hold the corporation liable in tort for breaching its contract”\\n(quoting Murray v. Bridgeport Hosp., 480 A.2d 610, 613 (Conn. Super. Ct.\\n1984))); Emerson Radio Corp. v. Orion Sales, Inc., 253 F.3d 159, 173 (3d\\nCir. 2001) (stating that under New Jersey law, a corporate agent acting\\nwithin the scope of the agency relationship cannot incur liability for\\ntortiously interfering with the corporation’s own contract with a third\\nparty); Kuhn v. Washtenaw Cty., 709 F.3d 612, 630 – 31 (6th Cir. 2013)\\n(“[W]ell-established Michigan law holds that ‘corporate agents are not\\nliable for tortious interference with the corporation’s contracts unless they\\nacted solely for their own benefit with no benefit to the corporation.’”\\n(quoting Reed v. Mich. Metro Girl Scout Council, 506 N.W.2d 231, 233\\n(Mich. App. 1993))); Palmer v. Ark. Council on Econ. Educ., 40 S.W.3d\\n\\n 15\\n\\fwhether Utah law would always bar liability for a corporate agent’s\\n\\ninterference with the corporation’s own contract. Even if Utah law would\\n\\nnot go that far, the jury could reasonably have determined that Mr. Sloan,\\n\\nas Kinum’s chief executive officer, had not acted as a stranger to Kinum’s\\n\\ncontract with a third party. Such a determination would have allowed a\\n\\nfinding that Mr. Sloan had not used improper means to tortiously interfere\\n\\nwith American Agencies’ contract (even if he had used improper means to\\n\\ntortiously interfere with American Agencies’ business relations). The\\n\\ndistrict court’s error thus could have affected the verdict, which requires\\n\\nus to treat the error as prejudicial and to reverse the judgment on this\\n\\nclaim. See p. 12, above.\\n\\n\\n\\n\\n784, 791 (Ark. 2001) (“It is well settled that a party to a contract, and its\\nagents acting in the scope of their authority, cannot be liable for\\ninterfering with the party’s own contract.”); Trail v. Boys & Girls Clubs of\\nNw. Ind., 845 N.E.2d 130, 138 (Ind. 2006) (holding that when officers act\\nin their official capacity as corporate agents, they cannot incur personal\\nliability for tortiously interfering with the corporation’s own contracts);\\nVoiles v. Santa Fe Minerals, Inc., 911 P.2d 1205, 1210 (Okla. 1996)\\n(holding that a person “acting in a representative capacity for a party” to a\\ncontract cannot incur liability for wrongfully interfering with that\\ncontract); Morgan Stanley & Co. v. Tex. Oil Co., 958 S.W.2d 178, 179\\n(Tex. 1997) (“[A] contracting party’s agent or employee acting in the\\nparty’s interests cannot interfere with the party’s contract.”); see also W.\\nPage Keeton et al., Prosser & Keeton on The Law of Torts 990 (5th ed.\\n1984) (“[T]he defendant’s employees acting within the scope of their\\nemployment are identified with the defendant himself so that they may\\nordinarily advise the defendant to breach his own contract without\\nthemselves incurring liability in tort.”).\\n 16\\n\\f3. Liability for copyright infringement: The district court did not\\n err in denying Mr. Sloan’s argument for judgment as a matter of\\n law.\\n\\n The debt-collection software contained American Agencies’ standard\\n\\ncollection letter and service agreement. After obtaining the software,\\n\\nKinum began using a collection letter and a service agreement like the ones\\n\\nused by American Agencies. Kinum’s use of these documents led American\\n\\nAgencies to include a claim for copyright infringement against Mr. Sloan.\\n\\n Mr. Sloan contends that on the copyright-infringement claim, the\\n\\nevidence was insufficient regarding commercial use or originality. We\\n\\nreject these contentions, concluding that (1) Mr. Sloan failed to preserve\\n\\nhis challenge involving commercial use and (2) the evidence on originality\\n\\nwas sufficient for a jury to find liability.\\n\\n To preserve the challenge on commercial use, Mr. Sloan needed to\\n\\nraise this issue in his pre-verdict motion for judgment as a matter of law.\\n\\nSee p. 8, above. In that motion, Mr. Sloan did not question the sufficiency\\n\\nof evidence involving commercial use. By omitting this challenge from the\\n\\npre-verdict motion, Mr. Sloan failed to preserve the issue for appeal. See\\n\\np. 8, above.\\n\\n On appeal, however, Mr. Sloan also challenges the evidence of\\n\\noriginality. To consider this challenge, we review the issue de novo and\\n\\naffirm if there is evidence on which the jury could properly return a verdict\\n\\n\\n\\n 17\\n\\ffor American Agencies. Bartee v. Michelin N. Am., Inc., 374 F.3d 906, 914\\n\\n(10th Cir. 2004).\\n\\n To establish Mr. Sloan’s liability on the claim of copyright\\n\\ninfringement, American Agencies had to prove the originality of its\\n\\ncollection letter and service agreement. Feist Pubs., Inc. v. Rural Tel. Serv.\\n\\nCo., 499 U.S. 340, 345 (1991). These documents would be considered\\n\\n“original” only if\\n\\n American Agencies independently created the work and\\n\\n the work entailed “some minimal degree of creativity.”\\n\\nId.\\n\\n Mr. Sloan contends that American Agencies’ collection letter and\\n\\nservice agreement lacked a minimal degree of creativity. But the required\\n\\ncreativity “is extremely low,” and most works satisfy this requirement even\\n\\nwhen they are “‘crude, humble or obvious.’” Id. (quoting 1 Melville B.\\n\\nNimmer & David Nimmer, Copyright § 1.08[C][1] (1990)).\\n\\n Given this low standard, the jury could have reasonably inferred that\\n\\nthe collection letter and service agreement had entailed the required degree\\n\\nof creativity. An executive for American Agencies testified that (1) she\\n\\nhad contributed to the format and content of the collection letter and (2)\\n\\nthe service agreement contained terms unique to American Agencies,\\n\\nincluding\\n\\n references to American Agencies’ services to creditors,\\n 18\\n\\f information in the “payment authorization” section,\\n\\n information about a “phase one guarantee,”\\n\\n language allowing a client to authorize American Agencies to\\n review accounts for referral to an attorney for legal action, and\\n\\n language allowing clients to authorize American Agencies to\\n offer settlements.\\n\\nGiven this testimony, the jury could reasonably find at least some\\n\\ncreativity, rendering the evidence of originality sufficient for liability.\\n\\n4. Liability for unjust enrichment: The district court should have\\n granted judgment as a matter of law to Mr. Sloan based on the\\n insufficiency of evidence regarding the value of his benefit.\\n\\n Mr. Sloan contends that the district court should have granted him\\n\\njudgment as a matter of law on American Agencies’ claim of unjust\\n\\nenrichment because insufficient evidence existed on the value of Mr.\\n\\nSloan’s benefit. We agree.\\n\\n On the claim of unjust enrichment, American Agencies had to prove\\n\\nthe amount of Mr. Sloan’s benefit stemming from his wrongful conduct.\\n\\nSee Emergency Physicians Integrated Care v. Salt Lake Cty., 167 P.3d\\n\\n1080, 1086 (Utah 2007) (“The first element of [unjust enrichment] requires\\n\\nthe court to measure the benefit conferred on the defendant by the\\n\\nplaintiff.”); Richards v. Brown, 222 P.3d 69, 81 (Utah Ct. App. 2009)\\n\\n(requiring the plaintiff to prove that a wrongdoer “has been unjustly\\n\\n\\n\\n\\n 19\\n\\fenriched in some calculable amount”), aff’d on other grounds, 274 P.3d\\n\\n911 (Utah 2012).\\n\\n At trial, American Agencies relied on expert testimony to prove the\\n\\nvalue of the benefit received by Mr. Sloan’s corporation (Kinum) rather\\n\\nthan the value of the benefit received by Mr. Sloan. American Agencies\\n\\nargues that as a stockholder, Mr. Sloan benefited from an increase in the\\n\\nvalue of his Kinum stock. But American Agencies didn’t present evidence\\n\\non the amount of the alleged increase in the stock price. Given the absence\\n\\nof such evidence, American Agencies’ claim of unjust enrichment failed as\\n\\na matter of law. The district court should thus have granted Mr. Sloan’s\\n\\nmotion for judgment as a matter of law on this claim.\\n\\n Disposition\\n\\n On the claim against Mr. Sloan for tortious interference with\\n\\ncontract, we reverse and remand for a new trial. And on the claim of unjust\\n\\nenrichment, we reverse and remand with instructions to grant Mr. Sloan’s\\n\\nmotion for judgment as a matter of law. We otherwise affirm. 11\\n\\n\\n11\\n The district court’s judgment found that Mr. Sloan was jointly and\\nseverally liable for damages of $3,104,208.11. Given our opinion, Mr.\\nSloan would remain jointly and severally liable for $280,519 of that\\namount.\\n\\n The district court also found Mr. Sloan individually liable for\\ndamages of $315,325. Our opinion leaves Mr. Sloan liable for an amount\\nbetween $53,831 and $153,831. (The uncertainty arises because the\\nassessment of the punitive damages award was based on both tortious\\n\\n 20\\n\\finterference with contract and tortious interference with business relations,\\nand we are reversing the judgment for tortious interference with contract.)\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4394548/\", \"author_raw\": \"BACHARACH, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"BACHARACH"},"judge2":{"kind":"string","value":"BALDOCK"},"judge3":{"kind":"string","value":"PHILLIPS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4617295/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: ADVANCED RECOVERY SYSTEMS, a Utah Limited Liability Company, Plaintiff Counterclaim Defendant, v. AMERICAN AGENCIES, a Pennsylvania Limited Liability Company, Defendant Counterclaimant Third-Party Plaintiff-Appellee, NRA Group, a Pennsylvania Limited Liability Company, A/K/A National Recovery Agency; Steven C. Kusic, CEO/managing Member of American Agencies, LLC and/or NRA Group, LLC, and Individually, Defendants, Brent Sloan, Third-Party Defendant-Appellant, Kinum, Inc.; Scott Mitchell; Blake Reynolds, Third-Party Defendants, and Sajax Software, Third-Party Defendant Counterclaimant.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-07\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 7, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\nADVANCED RECOVERY\nSYSTEMS, a Utah limited liability\ncompany,\n\n Plaintiff Counterclaim\n Defendant,\n\nv. No. 17-4202\n\nAMERICAN AGENCIES, a\nPennsylvania limited liability\ncompany,\n\n Defendant Counterclaimant\n Third-Party Plaintiff -\n Appellee,\n\nNRA GROUP, a Pennsylvania\nlimited liability company, a/k/a\nNational Recovery Agency;\nSTEVEN C. KUSIC, CEO/managing\nmember of American Agencies, LLC\nand/or NRA Group, LLC, and\nindividually,\n\n Defendants,\n\nBRENT SLOAN,\n\n Third-Party Defendant -\n Appellant,\n\nKINUM, INC.; SCOTT MITCHELL;\nBLAKE REYNOLDS,\n\n Third-Party Defendants,\n\f and\n\n SAJAX SOFTWARE,\n\n Third-Party Defendant\n Counterclaimant.\n _________________________________\n\n Appeal from the United States District Court\n for the District of Utah\n (D.C. No. 2:13-CV-00283-DAK-BCW)\n _________________________________\n\nRichard D. Salgado, Dentons US LLP, Dallas, Texas (Kelley C. Cox,\nDentons US, Dallas, Texas, and Wade P. K. Carr, Dentons US, Kansas\nCity, Missouri, with him on the briefs), for Third-Party Defendant-\nAppellant.\n\nMichael K. Erickson (Carol A. Funk, with him on the brief), Ray Quinney\n& Nebeker P.C., Salt Lake City, Utah, for Third-Party Plaintiff-Appellee.\n _________________________________\n\nBefore BACHARACH, BALDOCK, and PHILLIPS, Circuit Judges.\n _________________________________\n\nBACHARACH, Circuit Judge.\n _________________________________\n\n This appeal grew out of Mr. Brent Sloan’s participation in two\n\ntransactions. The first transaction entailed a merger between Advanced\n\nRecovery Systems, LLC and Kinum, Inc.; 1 the second transaction consisted\n\nof a sale of software from Kinum to Sajax Software, LLC.\n\n\n\n\n1\n At the time of the merger, Kinum was known as “Fidelis Asset\nManagement, Inc.” In the interest of simplicity, however, we refer to the\nentity (before and after the merger) as “Kinum.”\n\n\n 2\n\f American Agencies, LLC alleged harm from these transactions and\n\nsued Mr. Sloan for damages and restitution. 2 After the close of evidence,\n\nMr. Sloan filed a motion for judgment as a matter of law. Following the\n\ndenial of this motion, a jury found Mr. Sloan liable on American Agencies’\n\nclaims of tortious interference with business relations, conspiracy to\n\ninterfere with business relations, tortious interference with contract,\n\ncopyright infringement, unjust enrichment, and misappropriation of trade\n\nsecrets. 3 Mr. Sloan unsuccessfully renewed his motion for judgment as a\n\nmatter of law. After the district court denied this motion, Mr. Sloan\n\nappealed. We affirm in part and reverse in part based on four conclusions:\n\n 1. On the claims of tortious interference with business relations\n and conspiracy to interfere with business relations, Mr. Sloan\n contends that (1) one of American Agencies’ theories of\n improper means is preempted by a Utah statute and (2)\n American Agencies did not present sufficient evidence of\n improper means. We disagree because Mr. Sloan did not\n preserve his preemption argument and the jury could have\n reasonably found improper means based on deceit. We thus\n conclude that the district court properly denied Mr. Sloan’s\n motion for judgment as a matter of law on these claims.\n\n 2. On the claim of tortious interference with contract, Mr. Sloan\n argues that the jury instructions erroneously and prejudicially\n\n\n\n2\n Federal jurisdiction existed under 28 U.S.C. §§ 1331(a)(1), 1332, and\n1367(a).\n3\n The finding of liability for misappropriation of trade secrets is not\ninvolved in this appeal.\n\n\n 3\n\f excluded improper means as an element. We agree with Mr.\n Sloan and reverse the judgment on this claim. 4\n\n 3. On the claim of copyright infringement, Mr. Sloan contends\n that the jury could not have reasonably found commercial use\n or regarded the pertinent documents as original. We disagree,\n concluding that (1) Mr. Sloan did not preserve his commercial-\n use argument and (2) American Agencies’ evidence on\n originality was sufficient.\n\n 4. On the claim of unjust enrichment, Mr. Sloan contends that the\n jury could not have reasonably inferred the value of a benefit\n to Mr. Sloan. 5 We agree, so we reverse the denial of Mr.\n Sloan’s motion for judgment as a matter of law on this claim.\n\n Background\n\n1. Advanced Recovery Systems enters into a licensing agreement\n with American Agencies.\n\n American Agencies is a debt-collection agency that entered into a\n\nlicensing agreement with Advanced Recovery Systems. Under the licensing\n\nagreement, American Agencies enjoyed\n\n the exclusive right to use certain debt-collection software\n developed by Advanced Recovery Systems and\n\n the right of first refusal with respect to any future sale of\n Advanced Recovery Systems.\n\n\n\n\n4\n On appeal, Mr. Sloan also challenges the district court’s award of\nattorney’s fees to American Agencies. This part of the award was based on\nthe claim of tortious interference with contract. Our reversal on this claim\nencompasses the award of attorney’s fees.\n5\n Mr. Sloan also contends that other legal remedies were adequate to\ncompensate American Agencies. We need not address this contention.\n 4\n\fThe debt-collection software contained American Agencies’ customer data,\n\nincluding a client list, client history, fee structure, and rate of success.\n\n2. Advanced Recovery Systems merges into Kinum, and Kinum sells\n the software to Sajax.\n\n Without American Agencies’ knowledge, Advanced Recovery\n\nSystems merged into Kinum. See p. 3 n.1, above. Mr. Sloan helped to\n\nfacilitate the merger and became Kinum’s chief executive officer after the\n\nmerger. As the chief executive officer, Mr. Sloan oversaw Kinum’s sale of\n\nthe debt-collection software to Sajax. With the software came American\n\nAgencies’ customer data.\n\n\n\n\n 5\n\f6\n\f The Individual Claims and Mr. Sloan’s Appellate Arguments\n1. Liability for tortious interference with business relations and\n conspiracy to interfere with business relations: The evidence\n adequately supported the jury’s findings of liability.\n\n On the claims of tortious interference with business relations and\n\nconspiracy to commit this tort, American Agencies had to prove improper\n\nmeans. Overstock.com, Inc. v. SmartBargains, Inc., 192 P.3d 858, 864\n\n(Utah 2008); see also Puttuck v. Gendron, 199 P.3d 971, 978 (Utah App.\n\n2008) (stating that a claim of civil conspiracy under Utah law requires an\n\nunderlying tort). 6 American Agencies alleged that Mr. Sloan had used\n\nimproper means in two ways:\n\n 1. using deceit to conceal transfers of the debt-collection software\n and American Agencies’ customer data\n\n 2. initiating unfounded litigation against American Agencies. 7\n\nMr. Sloan responds to these allegations by arguing that\n\n the theory of improper means through deceit is preempted by a\n Utah statute and\n\n the evidence did not indicate that the litigation had been\n unfounded.\n\nWe reject these arguments.\n\n\n6\n The district court and the parties treat Utah law as the applicable\nlaw, so we also apply Utah law. See Strickland Tower Maint., Inc. v. AT&T\nCommc’ns, Inc., 128 F.3d 1422, 1426 (10th Cir. 1997).\n7\n The parties agree that a third theory presented by American Agencies\n(altering American Agencies’ license agreements with sales agents) did not\napply to Mr. Sloan.\n\n 7\n\f A. Mr. Sloan did not preserve his preemption argument.\n\n On appeal, Mr. Sloan urges preemption of American Agencies’\n\ntheory of deceit based on a Utah statute. But Mr. Sloan failed to preserve\n\nhis preemption argument.\n\n To preserve the argument, Mr. Sloan needed to comply with Rule 50\n\nof the Federal Rules of Civil Procedure, which governs motions for\n\njudgment as a matter of law. Unitherm Food Sys., Inc. v. Swift-Eckrich,\n\nInc., 546 U.S. 394, 399 (2006). Under subsection (a) of this rule, a litigant\n\ncan move for judgment before the jury renders its verdict. Fed. R. Civ. P.\n\n50(a). If a litigant moves for a pre-verdict judgment under subsection (a)\n\nand the court denies the motion, the litigant can renew the motion after the\n\nverdict under subsection (b) of the rule. Fed. R. Civ. P. 50(b); see\n\nMarshall v. Columbia Lea Reg’l Hosp., 474 F.3d 733, 738–39 (10th Cir.\n\n2007). If a ground is omitted from a pre-verdict motion, however, the\n\nground cannot be asserted in a post-verdict motion or in an appeal. See\n\nMarshall, 474 F.3d at 738–39 (cannot be asserted in the post-verdict\n\nmotion); Unitherm Food Sys., Inc., 546 U.S. at 399 (cannot be asserted in\n\nthe appeal).\n\n Before the jury returned a verdict, Mr. Sloan moved for judgment as\n\na matter of law under Rule 50(a), contending that American Agencies\n\nhadn’t presented evidence of (1) intentional interference by improper\n\nmeans or (2) injury caused by the interference. But Mr. Sloan’s motion did\n\n 8\n\fnot include his current argument involving preemption. As a result, this\n\nargument was not preserved for appeal.\n\n B. Mr. Sloan doesn’t contest the sufficiency of the evidence on\n deceit, so we reject his challenge to the claims of tortious\n interference with business relations and conspiracy to\n commit this tort.\n\n On appeal, Mr. Sloan does not challenge the sufficiency of the\n\nevidence supporting American Agencies’ theory of deceit; he challenges\n\nonly the sufficiency of the evidence supporting the theory of unfounded\n\nlitigation. Given the limited scope of this challenge, we treat the deceit\n\ntheory as sufficient for liability. 8\n\n The district court’s special-verdict form didn’t distinguish between\n\nAmerican Agencies’ two theories of improper means, so we don’t know\n\n\n\n\n8\n Even if Mr. Sloan had challenged the sufficiency of the evidence on\ndeceit, we would have rejected the challenge. In our view, the trial\nevidence permitted a reasonable jury to find that Mr. Sloan had deceitfully\nconcealed transfers involving the software and American Agencies’\ncustomer data. See Bartee v. Michelin N. Am., Inc., 374 F.3d 906, 914\n(10th Cir. 2004) (sufficient evidence exists if there is evidence on which a\njury could properly return a verdict for the non-movant). This evidence\nincluded support for three findings:\n First, Mr. Sloan knew before the merger with Kinum that American\nAgencies had an exclusive license to use the software and a right of first\nrefusal on a sale of Advanced Recovery Systems.\n Second, with knowledge of these rights, Mr. Sloan helped to merge\nAdvanced Recovery Systems into Kinum without telling American\nAgencies of the merger or the transfer of software to Kinum.\n\n\n 9\n\fwhich theory the jury credited. Given this uncertainty, we must affirm if\n\nsufficient evidence existed on either of American Agencies’ factual\n\ntheories. Kirkbride v. Terex USA, LLC, 798 F.3d 1343, 1349 (10th Cir.\n\n2015). So in the absence of a challenge to the sufficiency of the evidence\n\non deceit, we need not decide whether the evidence would have supported\n\nAmerican Agencies’ theory of unfounded litigation.\n\n Mr. Sloan points to a line of cases suggesting that “reversal is . . .\n\nnecessary if either basis [for a verdict] was improper.” Appellant’s Reply\n\nBr. at 18 (emphasis in original); see id. at 18–19. But this line of cases\n\napplies only when the defendant challenges the validity of a legal theory.\n\nPratt v. Petelin, 733 F.3d 1006, 1009 (10th Cir. 2013). These cases do not\n\napply when the defendant challenges the sufficiency of the evidence on\n\nsome (but not all) of the plaintiff’s factual theories:\n\n [T]hese cases address the situation where the jury may have\n based its verdict on an incorrect or entirely unsupported legal\n theory. They are thus distinguishable from the case at hand,\n where [the defendant] claims that some, but not all, of the\n factual bases presented to the jury for one legal theory—\n negligence—were unsupported by sufficient evidence.\n\n\n\n\n Third, without telling American Agencies, Mr. Sloan directed Kinum\nto sell the software to Sajax even though the software contained American\nAgencies’ customer data.\n\n 10\n\fId. (emphasis in original). Here we are addressing the sufficiency of\n\nevidence on factual theories, not the validity of a legal theory. Mr. Sloan’s\n\ncited authority is thus inapplicable.\n\n2. Liability for tortious interference with contract: The district\n court erroneously and prejudicially failed to include improper\n means as an element of the claim.\n\n American Agencies claimed tortious interference with contract,\n\nalleging that Mr. Sloan had induced Advanced Recovery Systems to breach\n\nits licensing agreement. The district court instructed the jury on the\n\nelements of the claim but did not include improper means as an element.\n\nThe omission constituted an error that prejudiced Mr. Sloan.\n\n We apply the abuse-of-discretion standard. Lederman v. Frontier\n\nFire Protection, Inc., 685 F.3d 1151, 1154 (10th Cir. 2012). But in\n\napplying this standard, we conduct de novo review of the instructions as a\n\nwhole to assess their accuracy under Utah law. Royal Maccabees Life Ins.\n\nCo. v. Choren, 393 F.3d 1175, 1179 (10th Cir. 2005).\n\n Reviewing the instructions de novo, we conclude that the district\n\ncourt erred because the Utah Supreme Court treats improper means as an\n\nelement of tortious interference with contract. See C.R. England v. Swift\n\nTransp. Co., 2019 UT 8, ¶ 39 (Feb. 27, 2019) (“Because the weight of\n\nauthority supports St. Benedict’s adoption of the ‘improper means’ element\n\nfor the tort of intentional interference with contract, and because this\n\nelement has become firmly embedded in Utah law, we reaffirm it.”); see\n 11\n\falso St. Benedict’s Devel. Co. v. St. Benedict’s Hosp., 811 P.2d 194, 201\n\n(Utah 1991) (stating that one incurs liability for intentional interference\n\nwith contract by “intentionally and improperly” causing a party not to\n\nperform the contract). By failing to correctly tell the jury what’s needed\n\nfor liability, the district court misled the jury. See Wankier v. Crown\n\nEquip. Corp., 353 F.3d 862, 868 (10th Cir. 2003) (“A district court’s\n\nfailure to inform the jury of all the elements essential to a plaintiff’s claim\n\nnecessarily misleads the jury.”).\n\n American Agencies argues that the error didn’t prejudice Mr. Sloan.\n\nWe disagree. An error in jury instructions requires reversal if the error was\n\nprejudicial. Heggy v. Heggy, 944 F.2d 1537, 1542 (10th Cir. 1991). An\n\nerror is prejudicial if “the jury might have based its verdict on the\n\nerroneously given instruction.” Level 3 Commc’ns, LLC v. Liebert Corp.,\n\n535 F.3d 1146, 1158 (10th Cir. 2008) (emphasis in original) (quoting\n\nWankier, 353 F.3d at 867). We thus must reverse based on an erroneous\n\ninstruction if there is even a slight possibility of an effect on the verdict.\n\nId.\n\n Such a possibility doesn’t always exist. For example, omission of an\n\nelement may be harmless if the verdict on another claim would have\n\nrequired the jury to find the omitted element. See United States v.\n\nMcDonald, 150 F.3d 1301, 1304–05 (10th Cir. 1998) (concluding that the\n\nomission of elements of a criminal offense in the jury instructions was\n\n 12\n\fharmless because the verdict of guilty on a separate criminal offense\n\n“necessarily embraced the missing elements”).\n\n American Agencies contends that the jury necessarily found that Mr.\n\nSloan had used improper means to interfere with American Agencies’\n\nlicensing agreement with Advanced Recovery Systems because\n\n the jury instructions included improper means as an element of\n tortious interference with business relations and\n\n the jury found tortious interference with American Agencies’\n business relations.\n\nThis contention assumes that American Agencies’ theories of improper\n\nmeans for tortious interference with business relations would also support\n\nliability for tortious interference with contract. 9 If even one theory of\n\nimproper means supported liability for tortious interference with business\n\nrelations but not for tortious interference with contract, the instructional\n\nerror would be prejudicial. See p. 12, above.\n\n As noted above, American Agencies presented two theories of\n\nimproper means on the claim against Mr. Sloan for tortious interference\n\nwith business relations:\n\n 1. the use of deceit to conceal the transfers of the debt-collection\n software and American Agencies’ customer data\n\n\n9\n American Agencies assumes that Utah uses the same definition of\nimproper means for both tortious interference with contract and tortious\ninterference with business relations. For the sake of argument, we can\nmake the same assumption.\n\n 13\n\f 2. the initiation of unfounded litigation against American\n Agencies.\n\nAmerican Agencies based the deceit theory on two transactions:\n\n 1. Advanced Recovery Systems’ merger with Kinum\n\n 2. Kinum’s sale of the debt-collection software to Sajax.\n\nThe jury might have found liability for tortious interference with business\n\nrelations based on Kinum’s sale of the debt-collection software. For\n\ntortious interference with contract, however, the jury might have rejected\n\nliability on this basis by viewing Mr. Sloan as the principal of one of the\n\ncontracting parties (Kinum).\n\n Under Utah law, a corporation cannot incur liability for interfering\n\nwith its own contract. See Leigh Furniture & Carpet Co. v. Isom, 657 P.2d\n\n293, 301 (Utah 1982) (“[O]ne party to a contract cannot be liable for the\n\ntort of interference with contract for inducing a breach by himself or the\n\nother contracting party.”), overruled on other grounds by Eldridge v.\n\nJohndrow, 345 P.3d 553 (Utah 2015). And after Advanced Recovery\n\nSystems merged with Kinum, Kinum became a party to the licensing\n\nagreement. See Utah Stat. § 48-3a-1026(1)(d) (explaining that when a\n\nlimited liability company merges with another entity, “all debts,\n\nobligations, and other liabilities” of the limited liability company become\n\n“debts, obligations, and other liabilities of the surviving entity”). So when\n\n\n\n\n 14\n\fKinum sold the debt-collection software, it was a party to the licensing\n\nagreement and Mr. Sloan was Kinum’s chief executive officer.\n\n To find that Mr. Sloan’s participation in this sale constituted\n\nimproper means for tortious interference with contract, the jury would have\n\nneeded to find that Kinum’s chief executive officer had tortiously\n\ninterfered with his own company’s contract. As noted above, Utah law\n\ndoesn’t authorize liability for tortiously interfering with one’s own\n\ncontract. And under Utah law, corporations can act only through their\n\nagents. Stratton v. W. States Constr., 440 P.2d 117, 118 (Utah 1968).\n\n In similar circumstances, courts throughout the country have held\n\nthat a corporate officer cannot incur liability for tortiously interfering with\n\nthe corporation’s own contract. 10 Here, however, we need not decide\n\n\n10 See Boulevard Assocs. v. Sovereign Hotels, Inc., 72 F.3d 1029, 1036\n(2d Cir. 1995) (noting that Connecticut courts have held that “[a]n agent\nacting legitimately within the scope of his authority cannot be held liable\nfor interfering with or inducing his principal to breach a contract between\nhis principal and a third party, because to hold him liable would be, in\neffect, to hold the corporation liable in tort for breaching its contract”\n(quoting Murray v. Bridgeport Hosp., 480 A.2d 610, 613 (Conn. Super. Ct.\n1984))); Emerson Radio Corp. v. Orion Sales, Inc., 253 F.3d 159, 173 (3d\nCir. 2001) (stating that under New Jersey law, a corporate agent acting\nwithin the scope of the agency relationship cannot incur liability for\ntortiously interfering with the corporation’s own contract with a third\nparty); Kuhn v. Washtenaw Cty., 709 F.3d 612, 630 – 31 (6th Cir. 2013)\n(“[W]ell-established Michigan law holds that ‘corporate agents are not\nliable for tortious interference with the corporation’s contracts unless they\nacted solely for their own benefit with no benefit to the corporation.’”\n(quoting Reed v. Mich. Metro Girl Scout Council, 506 N.W.2d 231, 233\n(Mich. App. 1993))); Palmer v. Ark. Council on Econ. Educ., 40 S.W.3d\n\n 15\n\fwhether Utah law would always bar liability for a corporate agent’s\n\ninterference with the corporation’s own contract. Even if Utah law would\n\nnot go that far, the jury could reasonably have determined that Mr. Sloan,\n\nas Kinum’s chief executive officer, had not acted as a stranger to Kinum’s\n\ncontract with a third party. Such a determination would have allowed a\n\nfinding that Mr. Sloan had not used improper means to tortiously interfere\n\nwith American Agencies’ contract (even if he had used improper means to\n\ntortiously interfere with American Agencies’ business relations). The\n\ndistrict court’s error thus could have affected the verdict, which requires\n\nus to treat the error as prejudicial and to reverse the judgment on this\n\nclaim. See p. 12, above.\n\n\n\n\n784, 791 (Ark. 2001) (“It is well settled that a party to a contract, and its\nagents acting in the scope of their authority, cannot be liable for\ninterfering with the party’s own contract.”); Trail v. Boys & Girls Clubs of\nNw. Ind., 845 N.E.2d 130, 138 (Ind. 2006) (holding that when officers act\nin their official capacity as corporate agents, they cannot incur personal\nliability for tortiously interfering with the corporation’s own contracts);\nVoiles v. Santa Fe Minerals, Inc., 911 P.2d 1205, 1210 (Okla. 1996)\n(holding that a person “acting in a representative capacity for a party” to a\ncontract cannot incur liability for wrongfully interfering with that\ncontract); Morgan Stanley & Co. v. Tex. Oil Co., 958 S.W.2d 178, 179\n(Tex. 1997) (“[A] contracting party’s agent or employee acting in the\nparty’s interests cannot interfere with the party’s contract.”); see also W.\nPage Keeton et al., Prosser & Keeton on The Law of Torts 990 (5th ed.\n1984) (“[T]he defendant’s employees acting within the scope of their\nemployment are identified with the defendant himself so that they may\nordinarily advise the defendant to breach his own contract without\nthemselves incurring liability in tort.”).\n 16\n\f3. Liability for copyright infringement: The district court did not\n err in denying Mr. Sloan’s argument for judgment as a matter of\n law.\n\n The debt-collection software contained American Agencies’ standard\n\ncollection letter and service agreement. After obtaining the software,\n\nKinum began using a collection letter and a service agreement like the ones\n\nused by American Agencies. Kinum’s use of these documents led American\n\nAgencies to include a claim for copyright infringement against Mr. Sloan.\n\n Mr. Sloan contends that on the copyright-infringement claim, the\n\nevidence was insufficient regarding commercial use or originality. We\n\nreject these contentions, concluding that (1) Mr. Sloan failed to preserve\n\nhis challenge involving commercial use and (2) the evidence on originality\n\nwas sufficient for a jury to find liability.\n\n To preserve the challenge on commercial use, Mr. Sloan needed to\n\nraise this issue in his pre-verdict motion for judgment as a matter of law.\n\nSee p. 8, above. In that motion, Mr. Sloan did not question the sufficiency\n\nof evidence involving commercial use. By omitting this challenge from the\n\npre-verdict motion, Mr. Sloan failed to preserve the issue for appeal. See\n\np. 8, above.\n\n On appeal, however, Mr. Sloan also challenges the evidence of\n\noriginality. To consider this challenge, we review the issue de novo and\n\naffirm if there is evidence on which the jury could properly return a verdict\n\n\n\n 17\n\ffor American Agencies. Bartee v. Michelin N. Am., Inc., 374 F.3d 906, 914\n\n(10th Cir. 2004).\n\n To establish Mr. Sloan’s liability on the claim of copyright\n\ninfringement, American Agencies had to prove the originality of its\n\ncollection letter and service agreement. Feist Pubs., Inc. v. Rural Tel. Serv.\n\nCo., 499 U.S. 340, 345 (1991). These documents would be considered\n\n“original” only if\n\n American Agencies independently created the work and\n\n the work entailed “some minimal degree of creativity.”\n\nId.\n\n Mr. Sloan contends that American Agencies’ collection letter and\n\nservice agreement lacked a minimal degree of creativity. But the required\n\ncreativity “is extremely low,” and most works satisfy this requirement even\n\nwhen they are “‘crude, humble or obvious.’” Id. (quoting 1 Melville B.\n\nNimmer & David Nimmer, Copyright § 1.08[C][1] (1990)).\n\n Given this low standard, the jury could have reasonably inferred that\n\nthe collection letter and service agreement had entailed the required degree\n\nof creativity. An executive for American Agencies testified that (1) she\n\nhad contributed to the format and content of the collection letter and (2)\n\nthe service agreement contained terms unique to American Agencies,\n\nincluding\n\n references to American Agencies’ services to creditors,\n 18\n\f information in the “payment authorization” section,\n\n information about a “phase one guarantee,”\n\n language allowing a client to authorize American Agencies to\n review accounts for referral to an attorney for legal action, and\n\n language allowing clients to authorize American Agencies to\n offer settlements.\n\nGiven this testimony, the jury could reasonably find at least some\n\ncreativity, rendering the evidence of originality sufficient for liability.\n\n4. Liability for unjust enrichment: The district court should have\n granted judgment as a matter of law to Mr. Sloan based on the\n insufficiency of evidence regarding the value of his benefit.\n\n Mr. Sloan contends that the district court should have granted him\n\njudgment as a matter of law on American Agencies’ claim of unjust\n\nenrichment because insufficient evidence existed on the value of Mr.\n\nSloan’s benefit. We agree.\n\n On the claim of unjust enrichment, American Agencies had to prove\n\nthe amount of Mr. Sloan’s benefit stemming from his wrongful conduct.\n\nSee Emergency Physicians Integrated Care v. Salt Lake Cty., 167 P.3d\n\n1080, 1086 (Utah 2007) (“The first element of [unjust enrichment] requires\n\nthe court to measure the benefit conferred on the defendant by the\n\nplaintiff.”); Richards v. Brown, 222 P.3d 69, 81 (Utah Ct. App. 2009)\n\n(requiring the plaintiff to prove that a wrongdoer “has been unjustly\n\n\n\n\n 19\n\fenriched in some calculable amount”), aff’d on other grounds, 274 P.3d\n\n911 (Utah 2012).\n\n At trial, American Agencies relied on expert testimony to prove the\n\nvalue of the benefit received by Mr. Sloan’s corporation (Kinum) rather\n\nthan the value of the benefit received by Mr. Sloan. American Agencies\n\nargues that as a stockholder, Mr. Sloan benefited from an increase in the\n\nvalue of his Kinum stock. But American Agencies didn’t present evidence\n\non the amount of the alleged increase in the stock price. Given the absence\n\nof such evidence, American Agencies’ claim of unjust enrichment failed as\n\na matter of law. The district court should thus have granted Mr. Sloan’s\n\nmotion for judgment as a matter of law on this claim.\n\n Disposition\n\n On the claim against Mr. Sloan for tortious interference with\n\ncontract, we reverse and remand for a new trial. And on the claim of unjust\n\nenrichment, we reverse and remand with instructions to grant Mr. Sloan’s\n\nmotion for judgment as a matter of law. We otherwise affirm. 11\n\n\n11\n The district court’s judgment found that Mr. Sloan was jointly and\nseverally liable for damages of $3,104,208.11. Given our opinion, Mr.\nSloan would remain jointly and severally liable for $280,519 of that\namount.\n\n The district court also found Mr. Sloan individually liable for\ndamages of $315,325. Our opinion leaves Mr. Sloan liable for an amount\nbetween $53,831 and $153,831. (The uncertainty arises because the\nassessment of the punitive damages award was based on both tortious\n\n 20\n\finterference with contract and tortious interference with business relations,\nand we are reversing the judgment for tortious interference with contract.)\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: ADVANCED RECOVERY SYSTEMS, a Utah Limited Liability Company, Plaintiff Counterclaim Defendant, v. AMERICAN AGENCIES, a Pennsylvania Limited Liability Company, Defendant Counterclaimant Third-Party Plaintiff-Appellee, NRA Group, a Pennsylvania Limited Liability Company, A/K/A National Recovery Agency; Steven C. Kusic, CEO/managing Member of American Agencies, LLC and/or NRA Group, LLC, and Individually, Defendants, Brent Sloan, Third-Party Defendant-Appellant, Kinum, Inc.; Scott Mitchell; Blake Reynolds, Third-Party Defendants, and Sajax Software, Third-Party Defendant Counterclaimant.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-07\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 7, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\nADVANCED RECOVERY\\nSYSTEMS, a Utah limited liability\\ncompany,\\n\\n Plaintiff Counterclaim\\n Defendant,\\n\\nv. No. 17-4202\\n\\nAMERICAN AGENCIES, a\\nPennsylvania limited liability\\ncompany,\\n\\n Defendant Counterclaimant\\n Third-Party Plaintiff -\\n Appellee,\\n\\nNRA GROUP, a Pennsylvania\\nlimited liability company, a/k/a\\nNational Recovery Agency;\\nSTEVEN C. KUSIC, CEO/managing\\nmember of American Agencies, LLC\\nand/or NRA Group, LLC, and\\nindividually,\\n\\n Defendants,\\n\\nBRENT SLOAN,\\n\\n Third-Party Defendant -\\n Appellant,\\n\\nKINUM, INC.; SCOTT MITCHELL;\\nBLAKE REYNOLDS,\\n\\n Third-Party Defendants,\\n\\f and\\n\\n SAJAX SOFTWARE,\\n\\n Third-Party Defendant\\n Counterclaimant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Utah\\n (D.C. No. 2:13-CV-00283-DAK-BCW)\\n _________________________________\\n\\nRichard D. Salgado, Dentons US LLP, Dallas, Texas (Kelley C. Cox,\\nDentons US, Dallas, Texas, and Wade P. K. Carr, Dentons US, Kansas\\nCity, Missouri, with him on the briefs), for Third-Party Defendant-\\nAppellant.\\n\\nMichael K. Erickson (Carol A. Funk, with him on the brief), Ray Quinney\\n& Nebeker P.C., Salt Lake City, Utah, for Third-Party Plaintiff-Appellee.\\n _________________________________\\n\\nBefore BACHARACH, BALDOCK, and PHILLIPS, Circuit Judges.\\n _________________________________\\n\\nBACHARACH, Circuit Judge.\\n _________________________________\\n\\n This appeal grew out of Mr. Brent Sloan’s participation in two\\n\\ntransactions. The first transaction entailed a merger between Advanced\\n\\nRecovery Systems, LLC and Kinum, Inc.; 1 the second transaction consisted\\n\\nof a sale of software from Kinum to Sajax Software, LLC.\\n\\n\\n\\n\\n1\\n At the time of the merger, Kinum was known as “Fidelis Asset\\nManagement, Inc.” In the interest of simplicity, however, we refer to the\\nentity (before and after the merger) as “Kinum.”\\n\\n\\n 2\\n\\f American Agencies, LLC alleged harm from these transactions and\\n\\nsued Mr. Sloan for damages and restitution. 2 After the close of evidence,\\n\\nMr. Sloan filed a motion for judgment as a matter of law. Following the\\n\\ndenial of this motion, a jury found Mr. Sloan liable on American Agencies’\\n\\nclaims of tortious interference with business relations, conspiracy to\\n\\ninterfere with business relations, tortious interference with contract,\\n\\ncopyright infringement, unjust enrichment, and misappropriation of trade\\n\\nsecrets. 3 Mr. Sloan unsuccessfully renewed his motion for judgment as a\\n\\nmatter of law. After the district court denied this motion, Mr. Sloan\\n\\nappealed. We affirm in part and reverse in part based on four conclusions:\\n\\n 1. On the claims of tortious interference with business relations\\n and conspiracy to interfere with business relations, Mr. Sloan\\n contends that (1) one of American Agencies’ theories of\\n improper means is preempted by a Utah statute and (2)\\n American Agencies did not present sufficient evidence of\\n improper means. We disagree because Mr. Sloan did not\\n preserve his preemption argument and the jury could have\\n reasonably found improper means based on deceit. We thus\\n conclude that the district court properly denied Mr. Sloan’s\\n motion for judgment as a matter of law on these claims.\\n\\n 2. On the claim of tortious interference with contract, Mr. Sloan\\n argues that the jury instructions erroneously and prejudicially\\n\\n\\n\\n2\\n Federal jurisdiction existed under 28 U.S.C. §§ 1331(a)(1), 1332, and\\n1367(a).\\n3\\n The finding of liability for misappropriation of trade secrets is not\\ninvolved in this appeal.\\n\\n\\n 3\\n\\f excluded improper means as an element. We agree with Mr.\\n Sloan and reverse the judgment on this claim. 4\\n\\n 3. On the claim of copyright infringement, Mr. Sloan contends\\n that the jury could not have reasonably found commercial use\\n or regarded the pertinent documents as original. We disagree,\\n concluding that (1) Mr. Sloan did not preserve his commercial-\\n use argument and (2) American Agencies’ evidence on\\n originality was sufficient.\\n\\n 4. On the claim of unjust enrichment, Mr. Sloan contends that the\\n jury could not have reasonably inferred the value of a benefit\\n to Mr. Sloan. 5 We agree, so we reverse the denial of Mr.\\n Sloan’s motion for judgment as a matter of law on this claim.\\n\\n Background\\n\\n1. Advanced Recovery Systems enters into a licensing agreement\\n with American Agencies.\\n\\n American Agencies is a debt-collection agency that entered into a\\n\\nlicensing agreement with Advanced Recovery Systems. Under the licensing\\n\\nagreement, American Agencies enjoyed\\n\\n the exclusive right to use certain debt-collection software\\n developed by Advanced Recovery Systems and\\n\\n the right of first refusal with respect to any future sale of\\n Advanced Recovery Systems.\\n\\n\\n\\n\\n4\\n On appeal, Mr. Sloan also challenges the district court’s award of\\nattorney’s fees to American Agencies. This part of the award was based on\\nthe claim of tortious interference with contract. Our reversal on this claim\\nencompasses the award of attorney’s fees.\\n5\\n Mr. Sloan also contends that other legal remedies were adequate to\\ncompensate American Agencies. We need not address this contention.\\n 4\\n\\fThe debt-collection software contained American Agencies’ customer data,\\n\\nincluding a client list, client history, fee structure, and rate of success.\\n\\n2. Advanced Recovery Systems merges into Kinum, and Kinum sells\\n the software to Sajax.\\n\\n Without American Agencies’ knowledge, Advanced Recovery\\n\\nSystems merged into Kinum. See p. 3 n.1, above. Mr. Sloan helped to\\n\\nfacilitate the merger and became Kinum’s chief executive officer after the\\n\\nmerger. As the chief executive officer, Mr. Sloan oversaw Kinum’s sale of\\n\\nthe debt-collection software to Sajax. With the software came American\\n\\nAgencies’ customer data.\\n\\n\\n\\n\\n 5\\n\\f6\\n\\f The Individual Claims and Mr. Sloan’s Appellate Arguments\\n1. Liability for tortious interference with business relations and\\n conspiracy to interfere with business relations: The evidence\\n adequately supported the jury’s findings of liability.\\n\\n On the claims of tortious interference with business relations and\\n\\nconspiracy to commit this tort, American Agencies had to prove improper\\n\\nmeans. Overstock.com, Inc. v. SmartBargains, Inc., 192 P.3d 858, 864\\n\\n(Utah 2008); see also Puttuck v. Gendron, 199 P.3d 971, 978 (Utah App.\\n\\n2008) (stating that a claim of civil conspiracy under Utah law requires an\\n\\nunderlying tort). 6 American Agencies alleged that Mr. Sloan had used\\n\\nimproper means in two ways:\\n\\n 1. using deceit to conceal transfers of the debt-collection software\\n and American Agencies’ customer data\\n\\n 2. initiating unfounded litigation against American Agencies. 7\\n\\nMr. Sloan responds to these allegations by arguing that\\n\\n the theory of improper means through deceit is preempted by a\\n Utah statute and\\n\\n the evidence did not indicate that the litigation had been\\n unfounded.\\n\\nWe reject these arguments.\\n\\n\\n6\\n The district court and the parties treat Utah law as the applicable\\nlaw, so we also apply Utah law. See Strickland Tower Maint., Inc. v. AT&T\\nCommc’ns, Inc., 128 F.3d 1422, 1426 (10th Cir. 1997).\\n7\\n The parties agree that a third theory presented by American Agencies\\n(altering American Agencies’ license agreements with sales agents) did not\\napply to Mr. Sloan.\\n\\n 7\\n\\f A. Mr. Sloan did not preserve his preemption argument.\\n\\n On appeal, Mr. Sloan urges preemption of American Agencies’\\n\\ntheory of deceit based on a Utah statute. But Mr. Sloan failed to preserve\\n\\nhis preemption argument.\\n\\n To preserve the argument, Mr. Sloan needed to comply with Rule 50\\n\\nof the Federal Rules of Civil Procedure, which governs motions for\\n\\njudgment as a matter of law. Unitherm Food Sys., Inc. v. Swift-Eckrich,\\n\\nInc., 546 U.S. 394, 399 (2006). Under subsection (a) of this rule, a litigant\\n\\ncan move for judgment before the jury renders its verdict. Fed. R. Civ. P.\\n\\n50(a). If a litigant moves for a pre-verdict judgment under subsection (a)\\n\\nand the court denies the motion, the litigant can renew the motion after the\\n\\nverdict under subsection (b) of the rule. Fed. R. Civ. P. 50(b); see\\n\\nMarshall v. Columbia Lea Reg’l Hosp., 474 F.3d 733, 738–39 (10th Cir.\\n\\n2007). If a ground is omitted from a pre-verdict motion, however, the\\n\\nground cannot be asserted in a post-verdict motion or in an appeal. See\\n\\nMarshall, 474 F.3d at 738–39 (cannot be asserted in the post-verdict\\n\\nmotion); Unitherm Food Sys., Inc., 546 U.S. at 399 (cannot be asserted in\\n\\nthe appeal).\\n\\n Before the jury returned a verdict, Mr. Sloan moved for judgment as\\n\\na matter of law under Rule 50(a), contending that American Agencies\\n\\nhadn’t presented evidence of (1) intentional interference by improper\\n\\nmeans or (2) injury caused by the interference. But Mr. Sloan’s motion did\\n\\n 8\\n\\fnot include his current argument involving preemption. As a result, this\\n\\nargument was not preserved for appeal.\\n\\n B. Mr. Sloan doesn’t contest the sufficiency of the evidence on\\n deceit, so we reject his challenge to the claims of tortious\\n interference with business relations and conspiracy to\\n commit this tort.\\n\\n On appeal, Mr. Sloan does not challenge the sufficiency of the\\n\\nevidence supporting American Agencies’ theory of deceit; he challenges\\n\\nonly the sufficiency of the evidence supporting the theory of unfounded\\n\\nlitigation. Given the limited scope of this challenge, we treat the deceit\\n\\ntheory as sufficient for liability. 8\\n\\n The district court’s special-verdict form didn’t distinguish between\\n\\nAmerican Agencies’ two theories of improper means, so we don’t know\\n\\n\\n\\n\\n8\\n Even if Mr. Sloan had challenged the sufficiency of the evidence on\\ndeceit, we would have rejected the challenge. In our view, the trial\\nevidence permitted a reasonable jury to find that Mr. Sloan had deceitfully\\nconcealed transfers involving the software and American Agencies’\\ncustomer data. See Bartee v. Michelin N. Am., Inc., 374 F.3d 906, 914\\n(10th Cir. 2004) (sufficient evidence exists if there is evidence on which a\\njury could properly return a verdict for the non-movant). This evidence\\nincluded support for three findings:\\n First, Mr. Sloan knew before the merger with Kinum that American\\nAgencies had an exclusive license to use the software and a right of first\\nrefusal on a sale of Advanced Recovery Systems.\\n Second, with knowledge of these rights, Mr. Sloan helped to merge\\nAdvanced Recovery Systems into Kinum without telling American\\nAgencies of the merger or the transfer of software to Kinum.\\n\\n\\n 9\\n\\fwhich theory the jury credited. Given this uncertainty, we must affirm if\\n\\nsufficient evidence existed on either of American Agencies’ factual\\n\\ntheories. Kirkbride v. Terex USA, LLC, 798 F.3d 1343, 1349 (10th Cir.\\n\\n2015). So in the absence of a challenge to the sufficiency of the evidence\\n\\non deceit, we need not decide whether the evidence would have supported\\n\\nAmerican Agencies’ theory of unfounded litigation.\\n\\n Mr. Sloan points to a line of cases suggesting that “reversal is . . .\\n\\nnecessary if either basis [for a verdict] was improper.” Appellant’s Reply\\n\\nBr. at 18 (emphasis in original); see id. at 18–19. But this line of cases\\n\\napplies only when the defendant challenges the validity of a legal theory.\\n\\nPratt v. Petelin, 733 F.3d 1006, 1009 (10th Cir. 2013). These cases do not\\n\\napply when the defendant challenges the sufficiency of the evidence on\\n\\nsome (but not all) of the plaintiff’s factual theories:\\n\\n [T]hese cases address the situation where the jury may have\\n based its verdict on an incorrect or entirely unsupported legal\\n theory. They are thus distinguishable from the case at hand,\\n where [the defendant] claims that some, but not all, of the\\n factual bases presented to the jury for one legal theory—\\n negligence—were unsupported by sufficient evidence.\\n\\n\\n\\n\\n Third, without telling American Agencies, Mr. Sloan directed Kinum\\nto sell the software to Sajax even though the software contained American\\nAgencies’ customer data.\\n\\n 10\\n\\fId. (emphasis in original). Here we are addressing the sufficiency of\\n\\nevidence on factual theories, not the validity of a legal theory. Mr. Sloan’s\\n\\ncited authority is thus inapplicable.\\n\\n2. Liability for tortious interference with contract: The district\\n court erroneously and prejudicially failed to include improper\\n means as an element of the claim.\\n\\n American Agencies claimed tortious interference with contract,\\n\\nalleging that Mr. Sloan had induced Advanced Recovery Systems to breach\\n\\nits licensing agreement. The district court instructed the jury on the\\n\\nelements of the claim but did not include improper means as an element.\\n\\nThe omission constituted an error that prejudiced Mr. Sloan.\\n\\n We apply the abuse-of-discretion standard. Lederman v. Frontier\\n\\nFire Protection, Inc., 685 F.3d 1151, 1154 (10th Cir. 2012). But in\\n\\napplying this standard, we conduct de novo review of the instructions as a\\n\\nwhole to assess their accuracy under Utah law. Royal Maccabees Life Ins.\\n\\nCo. v. Choren, 393 F.3d 1175, 1179 (10th Cir. 2005).\\n\\n Reviewing the instructions de novo, we conclude that the district\\n\\ncourt erred because the Utah Supreme Court treats improper means as an\\n\\nelement of tortious interference with contract. See C.R. England v. Swift\\n\\nTransp. Co., 2019 UT 8, ¶ 39 (Feb. 27, 2019) (“Because the weight of\\n\\nauthority supports St. Benedict’s adoption of the ‘improper means’ element\\n\\nfor the tort of intentional interference with contract, and because this\\n\\nelement has become firmly embedded in Utah law, we reaffirm it.”); see\\n 11\\n\\falso St. Benedict’s Devel. Co. v. St. Benedict’s Hosp., 811 P.2d 194, 201\\n\\n(Utah 1991) (stating that one incurs liability for intentional interference\\n\\nwith contract by “intentionally and improperly” causing a party not to\\n\\nperform the contract). By failing to correctly tell the jury what’s needed\\n\\nfor liability, the district court misled the jury. See Wankier v. Crown\\n\\nEquip. Corp., 353 F.3d 862, 868 (10th Cir. 2003) (“A district court’s\\n\\nfailure to inform the jury of all the elements essential to a plaintiff’s claim\\n\\nnecessarily misleads the jury.”).\\n\\n American Agencies argues that the error didn’t prejudice Mr. Sloan.\\n\\nWe disagree. An error in jury instructions requires reversal if the error was\\n\\nprejudicial. Heggy v. Heggy, 944 F.2d 1537, 1542 (10th Cir. 1991). An\\n\\nerror is prejudicial if “the jury might have based its verdict on the\\n\\nerroneously given instruction.” Level 3 Commc’ns, LLC v. Liebert Corp.,\\n\\n535 F.3d 1146, 1158 (10th Cir. 2008) (emphasis in original) (quoting\\n\\nWankier, 353 F.3d at 867). We thus must reverse based on an erroneous\\n\\ninstruction if there is even a slight possibility of an effect on the verdict.\\n\\nId.\\n\\n Such a possibility doesn’t always exist. For example, omission of an\\n\\nelement may be harmless if the verdict on another claim would have\\n\\nrequired the jury to find the omitted element. See United States v.\\n\\nMcDonald, 150 F.3d 1301, 1304–05 (10th Cir. 1998) (concluding that the\\n\\nomission of elements of a criminal offense in the jury instructions was\\n\\n 12\\n\\fharmless because the verdict of guilty on a separate criminal offense\\n\\n“necessarily embraced the missing elements”).\\n\\n American Agencies contends that the jury necessarily found that Mr.\\n\\nSloan had used improper means to interfere with American Agencies’\\n\\nlicensing agreement with Advanced Recovery Systems because\\n\\n the jury instructions included improper means as an element of\\n tortious interference with business relations and\\n\\n the jury found tortious interference with American Agencies’\\n business relations.\\n\\nThis contention assumes that American Agencies’ theories of improper\\n\\nmeans for tortious interference with business relations would also support\\n\\nliability for tortious interference with contract. 9 If even one theory of\\n\\nimproper means supported liability for tortious interference with business\\n\\nrelations but not for tortious interference with contract, the instructional\\n\\nerror would be prejudicial. See p. 12, above.\\n\\n As noted above, American Agencies presented two theories of\\n\\nimproper means on the claim against Mr. Sloan for tortious interference\\n\\nwith business relations:\\n\\n 1. the use of deceit to conceal the transfers of the debt-collection\\n software and American Agencies’ customer data\\n\\n\\n9\\n American Agencies assumes that Utah uses the same definition of\\nimproper means for both tortious interference with contract and tortious\\ninterference with business relations. For the sake of argument, we can\\nmake the same assumption.\\n\\n 13\\n\\f 2. the initiation of unfounded litigation against American\\n Agencies.\\n\\nAmerican Agencies based the deceit theory on two transactions:\\n\\n 1. Advanced Recovery Systems’ merger with Kinum\\n\\n 2. Kinum’s sale of the debt-collection software to Sajax.\\n\\nThe jury might have found liability for tortious interference with business\\n\\nrelations based on Kinum’s sale of the debt-collection software. For\\n\\ntortious interference with contract, however, the jury might have rejected\\n\\nliability on this basis by viewing Mr. Sloan as the principal of one of the\\n\\ncontracting parties (Kinum).\\n\\n Under Utah law, a corporation cannot incur liability for interfering\\n\\nwith its own contract. See Leigh Furniture & Carpet Co. v. Isom, 657 P.2d\\n\\n293, 301 (Utah 1982) (“[O]ne party to a contract cannot be liable for the\\n\\ntort of interference with contract for inducing a breach by himself or the\\n\\nother contracting party.”), overruled on other grounds by Eldridge v.\\n\\nJohndrow, 345 P.3d 553 (Utah 2015). And after Advanced Recovery\\n\\nSystems merged with Kinum, Kinum became a party to the licensing\\n\\nagreement. See Utah Stat. § 48-3a-1026(1)(d) (explaining that when a\\n\\nlimited liability company merges with another entity, “all debts,\\n\\nobligations, and other liabilities” of the limited liability company become\\n\\n“debts, obligations, and other liabilities of the surviving entity”). So when\\n\\n\\n\\n\\n 14\\n\\fKinum sold the debt-collection software, it was a party to the licensing\\n\\nagreement and Mr. Sloan was Kinum’s chief executive officer.\\n\\n To find that Mr. Sloan’s participation in this sale constituted\\n\\nimproper means for tortious interference with contract, the jury would have\\n\\nneeded to find that Kinum’s chief executive officer had tortiously\\n\\ninterfered with his own company’s contract. As noted above, Utah law\\n\\ndoesn’t authorize liability for tortiously interfering with one’s own\\n\\ncontract. And under Utah law, corporations can act only through their\\n\\nagents. Stratton v. W. States Constr., 440 P.2d 117, 118 (Utah 1968).\\n\\n In similar circumstances, courts throughout the country have held\\n\\nthat a corporate officer cannot incur liability for tortiously interfering with\\n\\nthe corporation’s own contract. 10 Here, however, we need not decide\\n\\n\\n10 See Boulevard Assocs. v. Sovereign Hotels, Inc., 72 F.3d 1029, 1036\\n(2d Cir. 1995) (noting that Connecticut courts have held that “[a]n agent\\nacting legitimately within the scope of his authority cannot be held liable\\nfor interfering with or inducing his principal to breach a contract between\\nhis principal and a third party, because to hold him liable would be, in\\neffect, to hold the corporation liable in tort for breaching its contract”\\n(quoting Murray v. Bridgeport Hosp., 480 A.2d 610, 613 (Conn. Super. Ct.\\n1984))); Emerson Radio Corp. v. Orion Sales, Inc., 253 F.3d 159, 173 (3d\\nCir. 2001) (stating that under New Jersey law, a corporate agent acting\\nwithin the scope of the agency relationship cannot incur liability for\\ntortiously interfering with the corporation’s own contract with a third\\nparty); Kuhn v. Washtenaw Cty., 709 F.3d 612, 630 – 31 (6th Cir. 2013)\\n(“[W]ell-established Michigan law holds that ‘corporate agents are not\\nliable for tortious interference with the corporation’s contracts unless they\\nacted solely for their own benefit with no benefit to the corporation.’”\\n(quoting Reed v. Mich. Metro Girl Scout Council, 506 N.W.2d 231, 233\\n(Mich. App. 1993))); Palmer v. Ark. Council on Econ. Educ., 40 S.W.3d\\n\\n 15\\n\\fwhether Utah law would always bar liability for a corporate agent’s\\n\\ninterference with the corporation’s own contract. Even if Utah law would\\n\\nnot go that far, the jury could reasonably have determined that Mr. Sloan,\\n\\nas Kinum’s chief executive officer, had not acted as a stranger to Kinum’s\\n\\ncontract with a third party. Such a determination would have allowed a\\n\\nfinding that Mr. Sloan had not used improper means to tortiously interfere\\n\\nwith American Agencies’ contract (even if he had used improper means to\\n\\ntortiously interfere with American Agencies’ business relations). The\\n\\ndistrict court’s error thus could have affected the verdict, which requires\\n\\nus to treat the error as prejudicial and to reverse the judgment on this\\n\\nclaim. See p. 12, above.\\n\\n\\n\\n\\n784, 791 (Ark. 2001) (“It is well settled that a party to a contract, and its\\nagents acting in the scope of their authority, cannot be liable for\\ninterfering with the party’s own contract.”); Trail v. Boys & Girls Clubs of\\nNw. Ind., 845 N.E.2d 130, 138 (Ind. 2006) (holding that when officers act\\nin their official capacity as corporate agents, they cannot incur personal\\nliability for tortiously interfering with the corporation’s own contracts);\\nVoiles v. Santa Fe Minerals, Inc., 911 P.2d 1205, 1210 (Okla. 1996)\\n(holding that a person “acting in a representative capacity for a party” to a\\ncontract cannot incur liability for wrongfully interfering with that\\ncontract); Morgan Stanley & Co. v. Tex. Oil Co., 958 S.W.2d 178, 179\\n(Tex. 1997) (“[A] contracting party’s agent or employee acting in the\\nparty’s interests cannot interfere with the party’s contract.”); see also W.\\nPage Keeton et al., Prosser & Keeton on The Law of Torts 990 (5th ed.\\n1984) (“[T]he defendant’s employees acting within the scope of their\\nemployment are identified with the defendant himself so that they may\\nordinarily advise the defendant to breach his own contract without\\nthemselves incurring liability in tort.”).\\n 16\\n\\f3. Liability for copyright infringement: The district court did not\\n err in denying Mr. Sloan’s argument for judgment as a matter of\\n law.\\n\\n The debt-collection software contained American Agencies’ standard\\n\\ncollection letter and service agreement. After obtaining the software,\\n\\nKinum began using a collection letter and a service agreement like the ones\\n\\nused by American Agencies. Kinum’s use of these documents led American\\n\\nAgencies to include a claim for copyright infringement against Mr. Sloan.\\n\\n Mr. Sloan contends that on the copyright-infringement claim, the\\n\\nevidence was insufficient regarding commercial use or originality. We\\n\\nreject these contentions, concluding that (1) Mr. Sloan failed to preserve\\n\\nhis challenge involving commercial use and (2) the evidence on originality\\n\\nwas sufficient for a jury to find liability.\\n\\n To preserve the challenge on commercial use, Mr. Sloan needed to\\n\\nraise this issue in his pre-verdict motion for judgment as a matter of law.\\n\\nSee p. 8, above. In that motion, Mr. Sloan did not question the sufficiency\\n\\nof evidence involving commercial use. By omitting this challenge from the\\n\\npre-verdict motion, Mr. Sloan failed to preserve the issue for appeal. See\\n\\np. 8, above.\\n\\n On appeal, however, Mr. Sloan also challenges the evidence of\\n\\noriginality. To consider this challenge, we review the issue de novo and\\n\\naffirm if there is evidence on which the jury could properly return a verdict\\n\\n\\n\\n 17\\n\\ffor American Agencies. Bartee v. Michelin N. Am., Inc., 374 F.3d 906, 914\\n\\n(10th Cir. 2004).\\n\\n To establish Mr. Sloan’s liability on the claim of copyright\\n\\ninfringement, American Agencies had to prove the originality of its\\n\\ncollection letter and service agreement. Feist Pubs., Inc. v. Rural Tel. Serv.\\n\\nCo., 499 U.S. 340, 345 (1991). These documents would be considered\\n\\n“original” only if\\n\\n American Agencies independently created the work and\\n\\n the work entailed “some minimal degree of creativity.”\\n\\nId.\\n\\n Mr. Sloan contends that American Agencies’ collection letter and\\n\\nservice agreement lacked a minimal degree of creativity. But the required\\n\\ncreativity “is extremely low,” and most works satisfy this requirement even\\n\\nwhen they are “‘crude, humble or obvious.’” Id. (quoting 1 Melville B.\\n\\nNimmer & David Nimmer, Copyright § 1.08[C][1] (1990)).\\n\\n Given this low standard, the jury could have reasonably inferred that\\n\\nthe collection letter and service agreement had entailed the required degree\\n\\nof creativity. An executive for American Agencies testified that (1) she\\n\\nhad contributed to the format and content of the collection letter and (2)\\n\\nthe service agreement contained terms unique to American Agencies,\\n\\nincluding\\n\\n references to American Agencies’ services to creditors,\\n 18\\n\\f information in the “payment authorization” section,\\n\\n information about a “phase one guarantee,”\\n\\n language allowing a client to authorize American Agencies to\\n review accounts for referral to an attorney for legal action, and\\n\\n language allowing clients to authorize American Agencies to\\n offer settlements.\\n\\nGiven this testimony, the jury could reasonably find at least some\\n\\ncreativity, rendering the evidence of originality sufficient for liability.\\n\\n4. Liability for unjust enrichment: The district court should have\\n granted judgment as a matter of law to Mr. Sloan based on the\\n insufficiency of evidence regarding the value of his benefit.\\n\\n Mr. Sloan contends that the district court should have granted him\\n\\njudgment as a matter of law on American Agencies’ claim of unjust\\n\\nenrichment because insufficient evidence existed on the value of Mr.\\n\\nSloan’s benefit. We agree.\\n\\n On the claim of unjust enrichment, American Agencies had to prove\\n\\nthe amount of Mr. Sloan’s benefit stemming from his wrongful conduct.\\n\\nSee Emergency Physicians Integrated Care v. Salt Lake Cty., 167 P.3d\\n\\n1080, 1086 (Utah 2007) (“The first element of [unjust enrichment] requires\\n\\nthe court to measure the benefit conferred on the defendant by the\\n\\nplaintiff.”); Richards v. Brown, 222 P.3d 69, 81 (Utah Ct. App. 2009)\\n\\n(requiring the plaintiff to prove that a wrongdoer “has been unjustly\\n\\n\\n\\n\\n 19\\n\\fenriched in some calculable amount”), aff’d on other grounds, 274 P.3d\\n\\n911 (Utah 2012).\\n\\n At trial, American Agencies relied on expert testimony to prove the\\n\\nvalue of the benefit received by Mr. Sloan’s corporation (Kinum) rather\\n\\nthan the value of the benefit received by Mr. Sloan. American Agencies\\n\\nargues that as a stockholder, Mr. Sloan benefited from an increase in the\\n\\nvalue of his Kinum stock. But American Agencies didn’t present evidence\\n\\non the amount of the alleged increase in the stock price. Given the absence\\n\\nof such evidence, American Agencies’ claim of unjust enrichment failed as\\n\\na matter of law. The district court should thus have granted Mr. Sloan’s\\n\\nmotion for judgment as a matter of law on this claim.\\n\\n Disposition\\n\\n On the claim against Mr. Sloan for tortious interference with\\n\\ncontract, we reverse and remand for a new trial. And on the claim of unjust\\n\\nenrichment, we reverse and remand with instructions to grant Mr. Sloan’s\\n\\nmotion for judgment as a matter of law. We otherwise affirm. 11\\n\\n\\n11\\n The district court’s judgment found that Mr. Sloan was jointly and\\nseverally liable for damages of $3,104,208.11. Given our opinion, Mr.\\nSloan would remain jointly and severally liable for $280,519 of that\\namount.\\n\\n The district court also found Mr. Sloan individually liable for\\ndamages of $315,325. Our opinion leaves Mr. Sloan liable for an amount\\nbetween $53,831 and $153,831. (The uncertainty arises because the\\nassessment of the punitive damages award was based on both tortious\\n\\n 20\\n\\finterference with contract and tortious interference with business relations,\\nand we are reversing the judgment for tortious interference with contract.)\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2258,"cells":{"id":{"kind":"number","value":4617344,"string":"4,617,344"},"name":{"kind":"string","value":"DINE CITIZENS AGAINST RUINING OUR ENVIRONMENT; San Juan Citizens Alliance; WildEarth Guardians; Natural Resources Defense Council, Plaintiffs-Appellants, v. David BERNHARDT, in His Official Capacity as Acting Secretary of the United States Department of the Interior; United States Bureau of Land Management, an Agency Within the United States Department of the Interior; Neil Kornze, in His Official Capacity as Director of the United States Bureau of Land Management, Defendants-Appellees, and DJR Energy Holdings, LLC; BP America Production Company; American Petroleum Institute; Anschutz Exploration Corporation; Enduring Resources IV, LLC, Intervenor Defendants-Appellees, and ConocoPhillips Company; Burlington Resources Oil & Gas Company LP, Intervenor Defendants. All Pueblo Council of Governors; National Trust for Historic Preservation; Navajo Allottees; Alice Benally; Lilly Comanche; Virginia Harrison ; Samuel Harrison; Dolora Hesuse; Verna Martinez; Loyce Phoenix, Amici Curiae."},"name_abbreviation":{"kind":"string","value":"Dine Citizens Against Ruining Our Env't v. Bernhardt"},"decision_date":{"kind":"string","value":"2019-05-07"},"docket_number":{"kind":"string","value":"18-2089"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Briscoe, McKay, Holmes\", \"parties\": \"\", \"opinions\": [{\"author\": \"BRISCOE, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 7, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\nDINE CITIZENS AGAINST RUINING\\nOUR ENVIRONMENT; SAN JUAN\\nCITIZENS ALLIANCE; WILDEARTH\\nGUARDIANS; NATURAL RESOURCES\\nDEFENSE COUNCIL,\\n\\n Plaintiffs - Appellants,\\n No. 18-2089\\nv.\\n\\nDAVID BERNHARDT, in his official\\ncapacity as Acting Secretary of the United\\nStates Department of the Interior; UNITED\\nSTATES BUREAU OF LAND\\nMANAGEMENT, an agency within the\\nUnited States Department of the Interior;\\nNEIL KORNZE, in his official capacity as\\nDirector of the United States Bureau of\\nLand Management,\\n\\n Defendants - Appellees,\\n\\nand\\n\\nDJR ENERGY HOLDINGS, LLC; BP\\nAMERICA PRODUCTION COMPANY;\\nAMERICAN PETROLEUM INSTITUTE;\\nANSCHUTZ EXPLORATION\\nCORPORATION; ENDURING\\nRESOURCES IV, LLC,\\n\\n Intervenor Defendants - Appellees,\\n\\nand\\n\\nCONOCOPHILLIPS COMPANY;\\n\\f BURLINGTON RESOURCES OIL &\\n GAS COMPANY LP,\\n\\n Intervenor Defendants.\\n\\n ------------------------------\\n\\n ALL PUEBLO COUNCIL OF\\n GOVERNORS; NATIONAL TRUST FOR\\n HISTORIC PRESERVATION; NAVAJO\\n ALLOTTEES; ALICE BENALLY; LILLY\\n COMANCHE; VIRGINIA HARRISON;\\n SAMUEL HARRISON; DOLORA\\n HESUSE; VERNA MARTINEZ; LOYCE\\n PHOENIX,\\n\\n Amici Curiae.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of New Mexico\\n (D.C. No. 1:15-CV-00209-JB-LF)\\n _________________________________\\n\\nSamantha Ruscavage-Barz, WildEarth Guardians, Santa Fe, New Mexico (Kyle J. Tisdel,\\nWestern Environmental Law Center, Taos, New Mexico, with her on the briefs),\\nappearing for Appellants.\\n\\nAvi Kupfer, U.S. Department of Justice, Environment & Natural Resources Division,\\nWashington, D.C. (Michael C. Williams, Of Counsel, Attorney-Advisor, Office of the\\nSolicitor, U.S. Department of the Interior, Clare M. Boronow, and Mark R. Haag, U.S.\\nDepartment of Justice, Environment & Natural Resources Division, Washington, D.C.,\\non the brief), for the Defendants-Appellees.\\n\\nHadassah M. Reimer, Holland & Hart LLP, Jackson, Wyoming (Stephen G. Masciocchi,\\nand John F. Shepherd, Holland & Hart LLP, Denver, Colorado, Bradford Berge, Holland\\n& Hart LLP, Santa Fe, New Mexico, Rebecca W. Watson, Welborn Sullivan Meck &\\nTooley, P.C., Denver, Colorado, Stephen Rosenbaum, Covington & Burling, LLP,\\nWashington, D.C., and Jon J. Indall, Comeau Maldegen Templeman & Indall LLP, Santa\\nFe, New Mexico, with her on the brief), appearing for Intervenors-Appellees.\\n _________________________________\\n\\nBefore BRISCOE, McKAY, and HOLMES, Circuit Judges.\\n\\n 2\\n\\f _________________________________\\n\\nBRISCOE, Circuit Judge.\\n _________________________________\\n\\n In this case, we are asked to decide whether the Bureau of Land Management\\n\\nviolated the National Historic Preservation Act (NHPA) and the National\\n\\nEnvironmental Policy Act (NEPA) in granting more than 300 applications for permits\\n\\nto drill horizontal, multi-stage hydraulically fracked wells in the Mancos Shale area\\n\\nof the San Juan Basin in northeastern New Mexico. Appellants1 sued the Secretary of\\n\\nthe Department of the Interior, the Bureau of Land Management, and the Secretary of\\n\\nthe BLM, alleging that the BLM authorized the drilling without fully considering its\\n\\nindirect and cumulative impacts on the environment or on historic properties. The\\n\\ndistrict court denied Appellants a preliminary injunction, and we affirmed that\\n\\ndecision in 2016. After merits briefing, the district court concluded that the BLM\\n\\nhad not violated either NHPA or NEPA and dismissed Appellants’ claims with\\n\\nprejudice. Appellants now appeal.\\n\\n We have jurisdiction under 28 U.S.C. § 1291 and affirm in part, reverse in\\n\\npart, and remand with instructions.\\n\\n\\n\\n 1\\n Appellants are four environmental advocacy groups: (1) Diné Citizens\\nAgainst Ruining Our Environment, comprised of Navajo community activists from\\nthe Four Corners region, (2) San Juan Citizens Alliance, concerned with social,\\neconomic, and environmental justice in the San Juan Basin, (3) WildEarth Guardians,\\nbased in Santa Fe, New Mexico and with members and offices throughout the\\nwestern United States, and (4) Natural Resources Defense Council, with members\\nthroughout the United States, many of whom reside in New Mexico.\\n\\n 3\\n\\f I\\n\\nWe summarized the underlying facts in the prior appeal.\\n\\n The San Juan Basin is a large geographic region in the southwestern\\nUnited States, including part of New Mexico. Drilling for oil and gas has\\noccurred in the Basin for more than sixty years, and the Basin is currently\\none of the most prolific sources of natural gas in the country. The Basin\\nincludes both public and private lands. Many of the public lands and\\nresources fall under the jurisdiction of the Bureau of Land Management’s\\nFarmington Field Office in New Mexico, which manages these lands and\\nresources under its published Resource Management Plan.\\n\\n In 2000, the BLM initiated the process of revising its existing RMP,\\nwhich had been published in 1988. As part of this process, the BLM\\ncontracted with the New Mexico Institute of Mining and Geology to\\ndevelop a “reasonably foreseeable development scenario,” or RFDS, to\\npredict the foreseeable oil and gas development likely to occur over the\\nnext twenty years. Based on historic production data and available\\ngeologic and engineering evidence, the RFDS estimated that 9,970 new oil\\nand gas wells would be drilled on federally managed lands in the New\\nMexico portion of the San Juan Basin during this time period. Of these\\nwells, the RFDS estimated that more than forty percent would be “Dakota,\\nMancos” gas wells—wells that could produce gas from both the Mancos\\ngeologic horizon and the Dakota geologic horizon that lies below it. The\\nRFDS estimated that only 180 new oil wells would be drilled in the Mancos\\nShale, due to the fact that most reservoirs in the Mancos Shale were\\napproaching depletion under then-current technologies, but it noted that\\nthere is excellent potential for the Mancos to be further evaluated.\\n\\n In 2003, the BLM issued its Proposed Resource Management Plan\\nand Final Environmental Impact Statement ([2003 EIS]). In this document,\\nthe BLM referred to the predictions and analysis contained in the RFDS in\\norder to assess four proposed alternatives for managing federal lands in the\\nSan Juan Basin, including the “balanced approach” the agency ultimately\\ndecided to adopt. Under this balanced approach, the BLM analyzed the\\ncumulative impacts of an estimated 9,942 new wells in the San Juan\\nBasin—approximately the same number predicted in the 2001 RFDS—by\\nlooking at, for instance, the likely air quality impacts from the drilling and\\noperation of this many new wells in the region. The [2003 EIS] did not\\ndiscuss specific sites or approve any individual wells, although it assumed\\nthe majority of new wells would be drilled in the high development area in\\nthe northern part of the managed area. The BLM issued its final RMP,\\n\\n 4\\n\\f adopting the Alternative D balanced approach, in December 2003.\\n\\nDiné Citizens Against Ruining Our Env’t v. Jewell (Diné II), 839 F.3d 1276, 1279–80\\n\\n(10th Cir. 2016) (citations omitted).\\n\\n Although the 2003 EIS analyzed oil and gas drilling in the San Juan Basin\\n\\ngenerally, operators wanting to drill new wells in the area must seek and receive approval\\n\\nfor specific drilling via an application for a permit to drill (APD) submitted to the BLM.\\n\\nWhen the BLM receives an APD, it prepares an environmental assessment (EA)\\n\\nexamining the environmental impacts of the proposed drilling. The EA must include an\\n\\nanalysis of the direct, indirect, and cumulative effects of the proposed drilling. See 40\\n\\nC.F.R. §§ 1508.7, 1508.8. The EA process results in one of three outcomes: (1) a\\n\\nconclusion that the proposed action would result in a significant environmental impact,\\n\\nnecessitating an EIS, (2) a conclusion that the proposed action would not result in a\\n\\nsignificant environmental impact—a “finding of no significant impact” (FONSI), or (3) a\\n\\nconclusion that the proposed action will not go forward. 43 C.F.R. § 46.325. Even if a\\n\\nproposed action will have significant effects, the EA may still result in a FONSI if it is\\n\\ntiered to a broader environmental analysis that fully analyzed those significant effects.\\n\\nId. § 46.140(c).\\n\\n Beginning in 2010, the BLM began receiving APDs for drilling in the Mancos\\n\\nShale. Development interest in the area increased quickly, and between early 2012 and\\n\\nApril 2014, seventy new wells were completed in the Mancos Shale area. In 2014,\\n\\nrecognizing the potential for additional Mancos Shale development, the BLM had a new\\n\\nRFDS prepared to evaluate the Mancos Shale’s potential for oil and gas development.\\n\\n 5\\n\\fThe 2014 RFDS estimates that full development of the Mancos Shale would result in\\n\\n3,960 new wells.\\n\\n The 2014 RFDS predicts that new drilling in the Mancos Shale will be done\\n\\nlargely, if not entirely, by horizontal drilling and multi-stage hydraulic fracturing. “A\\n\\nhorizontally drilled well starts as a vertical or directional well, but then curves and\\n\\nbecomes horizontal, or nearly so, allowing the wellbore [i.e., drilled hole] to follow\\n\\nwithin a rock stratum for significant distances and thus greatly increase the volume of a\\n\\nreservoir opened by the wellbore.” Wyoming v. Zinke, 871 F.3d 1133, 1137 (10th Cir.\\n\\n2017) (alteration in original) (quotations omitted). Hydraulic fracturing is a process\\n\\ndesigned to “maximize the extraction” of oil and gas resources. JA1912. Fluids, usually\\n\\nwater with chemical additives, “are pumped into a geologic formation at high pressure.”\\n\\nId. When the pressure “exceeds the rock strength,” it creates or enlarges fractures from\\n\\nwhich oil and gas can flow more freely. Id. After the fractures are created, a “propping\\n\\nagent (usually sand) is pumped into the fractures to keep them from closing.” Id.\\n\\n As we noted previously,\\n\\n These new drilling techniques have greatly increased access to oil and gas\\n reserves that were not previously targeted for development and have given\\n rise to much higher levels of development in the Mancos Shale than the\\n BLM previously estimated and accounted for. Moreover, horizontal\\n drilling and multi-stage fracturing may have greater environmental impacts\\n than vertical drilling and older fracturing techniques.\\n\\nDiné II, 839 F.3d at 1283.\\n\\n Hydraulic fracturing is common in the San Juan Basin and has been used there in\\n\\nsome form since the 1950s. Horizontal drilling, however, is relatively new. At the time\\n\\n\\n 6\\n\\fthe 2003 EIS issued, “[h]orizontal drilling [wa]s possible but not [then] applied in the San\\n\\nJuan Basin due to poor cost[-]to[-]benefit ratio.” JA746. The environmental impacts\\n\\nconsidered in the 2003 EIS were therefore based on the impacts associated with vertical\\n\\ndrilling, not horizontal drilling. But the 2003 EIS noted that “[i]f horizontal drilling\\n\\nshould prove economically and technically feasible in the future, the next advancement in\\n\\nhorizontal well technology could be drilling multi-laterals or hydraulic fracturing\\n\\nhorizontal wells.” Id.\\n\\n Since the 2003 EIS issued, 3,945 of the 9,942 contemplated vertical wells have\\n\\nbeen drilled in the San Juan Basin. The BLM continues to receive and approve APDs for\\n\\nhorizontal Mancos Shale wells. Appellants’ initial petition in the district court\\n\\nchallenged “at least 130” Mancos Shale APDs approved by the BLM. JA2449. Over the\\n\\ncourse of this litigation, Appellants amended their petition three times to account for\\n\\nadditional granted APDs. Their final petition challenged “at least 351” APDs.2 JA2701.\\n\\n In 2015, Appellants filed their first Petition for Review of Agency Action\\n\\n(Petition) in district court, challenging the BLM’s issuance of APDs as violative of\\n\\nNEPA and NHPA. Appellants named as defendants the Secretary of the United\\n\\nStates Department of the Interior, BLM, and the Director of BLM (collectively,\\n\\n\\n\\n 2\\n The number of wells at issue on appeal is unclear. Although the district court\\nruled that twenty-eight challenged APDs are not final agency action and four others\\nare moot—a ruling Appellants do not appeal—Appellants continue to assert that 362\\nAPDs (the same number they argued throughout briefing in the district court) are at\\nissue. Federal Appellees, for their part, assert that the challenged wells “number[]\\n337 as of October 17, 2018,” but cite only to the district court’s opinion in support.\\nFed. Aples. Br. at 18.\\n 7\\n\\fFederal Appellees). A group of oil companies (DJR Energy Holdings, LLC, BP\\n\\nAmerica Production Company, American Petroleum Institute, Anschutz Exploration\\n\\nCorporation, and Enduring Resources IV, LLC), each of which owns leases or\\n\\ndrilling permits in the Mancos Shale intervened as defendants (collectively,\\n\\nIntervenor Appellees).\\n\\n Appellants moved for a preliminary injunction, which the district court denied.\\n\\nSee Diné Citizens Against Ruining Our Env’t v. Jewell (Diné I), No. CIV 15-0209,\\n\\n2015 WL 6393843 (D.N.M. Sept. 16, 2015). This court upheld the denial on appeal.\\n\\nDiné II, 839 F.3d 1276. In district court, Appellants amended their Petition three\\n\\ntimes to add additional challenged APDs. Appellants’ operative Third Supplemented\\n\\nPetition alleges, as relevant on appeal: (1) a NEPA violation for improperly tiering\\n\\nthe EAs to the 2003 EIS; (2) a NEPA violation for failing to prepare an EIS or\\n\\nsupplement an existing EIS; and (3) a NHPA violation for failing to complete Section\\n\\n106 consultation. Appellants sought vacatur of all the challenged APDs and an\\n\\ninjunction against all “future horizontal drilling or hydraulic fracturing in the Mancos\\n\\nShale” until the BLM complied with NHPA and NEPA. JA2743.\\n\\n In April 2017, Appellants sought judgment in the district court. On April 23,\\n\\n2018, the district court ruled against Appellants and dismissed their claims with\\n\\nprejudice. The district court made the following relevant rulings: (1) Appellants have\\n\\nstanding to pursue their claims; (2) Appellants do not establish a NEPA violation;\\n\\nand (3) Appellants do not establish a NHPA violation.\\n\\n Appellants timely appealed, raising two issues. First, they contend that the\\n\\n 8\\n\\fBLM violated NHPA because it “failed to analyze the indirect and cumulative\\n\\nimpacts of the challenged Mancos Shale drilling permits on cultural sites in the\\n\\nGreater Chaco Landscape.” Aplts. Br. at 1 (footnote omitted). Second, they argue\\n\\nthat the BLM violated NEPA because it “failed to analyze the cumulative impacts of\\n\\nthe challenged Mancos Shale drilling permits on environmental resources in the\\n\\nGreater Chaco Landscape.” Id. at 2. Appellants seek vacatur of the challenged\\n\\nAPDs and a permanent injunction against “any further ground-disturbing activities on\\n\\nthe challenged APDs until BLM complies with the NHPA and NEPA.” Id. at 51.\\n\\n Federal Appellees assert, as they did in the district court, that Appellants lack\\n\\nstanding to challenge the relevant agency actions.\\n\\n II\\n\\n The BLM is subject to two statutes relevant on appeal: the National Historic\\n\\nPreservation Act and the National Environmental Policy Act. “NHPA[] . . . is a\\n\\nprocedural statute requiring government agencies to stop, look, and listen before\\n\\nproceeding when their action will affect national historical assets.” Coal. of Concerned\\n\\nCitizens to Make Art Smart v. Fed. Transit Admin. of U.S. Dep’t of Transp. (Concerned\\n\\nCitizens), 843 F.3d 886, 905 (10th Cir. 2016) (quoting Presidio Historical Ass’n v.\\n\\nPresidio Trust, 811 F.3d 1154, 1169 (9th Cir. 2016)). NHPA was enacted “to foster\\n\\nconditions under which our modern society and our historic property can exist in\\n\\nproductive harmony and fulfill the social, economic, and other requirements of present\\n\\nand future generations.” 54 U.S.C. § 300101(1).\\n\\n NEPA is also a procedural statute. It requires agencies to “pause before\\n\\n 9\\n\\fcommitting resources to a project and consider the likely environmental impacts of the\\n\\npreferred course of action as well as reasonable alternatives.” N.M. ex rel. Richardson\\n\\nv. Bureau of Land Mgmt., 565 F.3d 683, 703 (10th Cir. 2008). NEPA has twin aims:\\n\\n First, it places upon an agency the obligation to consider every significant\\n aspect of the environmental impact of a proposed action. Second, it ensures\\n that the agency will inform the public that it has indeed considered\\n environmental concerns in its decisionmaking process.\\n\\nForest Guardians v. U.S. Fish & Wildlife Serv., 611 F.3d 692, 711 (10th Cir. 2010)\\n\\n(quoting Balt. Gas & Elec. Co. v. Nat. Res. Def. Council, Inc., 462 U.S 87, 97 (1983)).\\n\\n Neither NEPA nor NHPA “provide a private right of action,” so we review the\\n\\ntwo decisions as “final agency action[s] under the” APA. Utah Envtl. Cong. v.\\n\\nRussell, 518 F.3d 817, 823 (10th Cir. 2008). We apply the same standard of review as\\n\\nthe district court: the familiar “arbitrary and capricious” standard. Richardson, 565 F.3d\\n\\nat 704–05; 5 U.S.C. § 706(2)(A). An agency’s decision is arbitrary and capricious if the\\n\\nagency:\\n\\n (1) entirely failed to consider an important aspect of the problem, (2)\\n offered an explanation for its decision that runs counter to the evidence\\n before the agency, or is so implausible that it could not be ascribed to a\\n difference in view or the product of agency expertise, (3) failed to base\\n its decision on consideration of the relevant factors, or (4) made a clear\\n error of judgment.\\n\\nRichardson, 565 F.3d at 704 (citations and quotations omitted). “A presumption of\\n\\nvalidity attaches to the agency action and the burden of proof rests with [the parties]\\n\\nwho challenge such action.” Citizens’ Comm. to Save Our Canyons v. Krueger, 513\\n\\nF.3d 1169, 1176 (10th Cir. 2008) (quoting Colo. Health Care Ass’n v. Colo. Dep’t of\\n\\nSoc. Servs., 842 F.2d 1158, 1164 (10th Cir. 1988)). Our deference to the agency is\\n\\n 10\\n\\f“especially strong where the challenged decisions involve technical or scientific\\n\\nmatters within the agency’s area of expertise.” Morris v. U.S. Nuclear Reg.\\n\\nComm’n, 598 F.3d 677, 691 (10th Cir. 2010) (quoting Russell, 518 F.3d at 824).\\n\\n III\\n\\n Because standing is jurisdictional, we must first determine whether Appellants\\n\\nhave standing to bring their claims. The district court concluded that Appellants have\\n\\nstanding, and we review that determination de novo. S. Utah Wilderness All. v. Palma,\\n\\n707 F.3d 1143, 1152 (10th Cir. 2013).\\n\\n When, as here, an organization sues on behalf of its members, the organization has\\n\\nstanding if:\\n\\n (a) its members would otherwise have standing to sue in their own right; (b)\\n the interests it seeks to protect are germane to the organization’s purpose;\\n and (c) neither the claim asserted nor the relief requested requires the\\n participation of individual members in the lawsuit.\\n\\nHunt v. Wash. State Apple Advert. Comm’n, 432 U.S. 333, 343 (1977). Federal\\n\\nAppelles do not argue that the interests Appellants seek to protect are not germane to the\\n\\norganizations’ purposes, nor do they argue that the participation of individual members is\\n\\nrequired.3 Our standing inquiry is therefore limited to whether any of Appellants’\\n\\nmembers “have standing to sue in their own right.” Id. We conclude that they do.\\n\\n To establish standing, a plaintiff must show:\\n\\n (1) it has suffered an “injury in fact” that is (a) concrete and particularized\\n\\n 3\\n Regardless, both of these requirements are met. Each organization has the\\ngoal of protecting the environment in some way. And nothing indicates that\\nindividual members would need to participate for the court to grant the relief\\nAppellants request.\\n 11\\n\\f and (b) actual or imminent, not conjectural or hypothetical; (2) the injury is\\n fairly traceable to the challenged action of the defendant; and (3) it is likely,\\n as opposed to merely speculative, that the injury will be redressed by a\\n favorable decision.\\n\\nFriends of the Earth v. Laidlaw Envtl. Servs. (TOC), Inc., 528 U.S. 167, 180–81 (2013).\\n\\nAt the summary judgment stage, Appellants must “set forth by affidavit or other evidence\\n\\nspecific facts, which for purposes of the summary judgment motion will be taken to be\\n\\ntrue.” Lujan v. Defs. of Wildlife, 504 U.S. 555, 561 (1992) (citations and quotations\\n\\nomitted).\\n\\n A\\n\\n The injury-in-fact prong of our standing analysis “breaks down into two parts.”\\n\\nComm. to Save the Rio Hondo v. Lucero, 102 F.3d 445, 449 (10th Cir. 1996).\\n\\nAppellants must show that (1) “in making its decision without following [NEPA’s]\\n\\nprocedures, the agency created an increased risk of actual, threatened, or imminent\\n\\nenvironmental harm,” and (2) “the increased risk of environmental harm injures [the\\n\\nlitigant’s] concrete interests by demonstrating either its geographical nexus to, or actual\\n\\nuse of the site of the agency action.” Id. Appellants have satisfied both requirements.\\n\\n 1\\n\\n Under NEPA, “an injury of alleged increased environmental risks due to an\\n\\nagency’s uninformed decisionmaking may be the foundation for injury in fact under\\n\\nArticle III.” Id. Here, the allegedly uninformed decisions Appellants challenge are the\\n\\nBLM’s approval of hundreds of APDs in the Mancos Shale without considering the\\n\\nindirect and cumulative impacts to cultural sites and environmental resources. Aplts. Br.\\n\\n\\n 12\\n\\fat 1–2. Appellants have sufficiently tied the BLM’s challenged decisions to increased\\n\\nenvironmental risks.\\n\\n Eisenfeld, a member of San Juan Citizens and WildEarth, asserts that the “Mancos\\n\\nShale APD authorizations . . . impact[] the visual landscape, night sky, solitude and quiet,\\n\\n[and] public health and safety.” JA343. Nichols, a member of WildEarth, states that\\n\\n“[w]ith the increase in oil and gas development has come light pollution, more truck\\n\\ntraffic, drilling rigs sticking up from the land, smells, dust, and more industrialization.”\\n\\nJA615. He asserts that recently,\\n\\n the impacts of Mancos shale oil development have become more visible,\\n offensive, and degrading of [his] recreational enjoyment of public lands in\\n the area. The new development has brought more drilling rigs, flaring,\\n truck traffic, road building, pipeline construction, the construction and\\n operation of more tanks and production facilities, and just overall more oil\\n and gas industry presence in the area.\\n\\nJA607–08. These facts are sufficient to establish “an increased risk of environmental\\n\\nharm due to [the BLM’s] alleged uninformed decisionmaking,” and they satisfy the first\\n\\nprong of our injury-in-fact analysis. Lucero, 102 F.3d at 451.\\n\\n Federal Appellees argue that Appellants fail on this prong of the standing analysis\\n\\nbecause the 2003 EIS examined the effects of “drilling 9,942 wells using conventional\\n\\ntechniques,” and Appellants have not shown that the challenged Mancos Shale APDs\\n\\n“will increase the risk of environmental harm in a manner or to a degree not already\\n\\nconsidered.” Fed. Aples. Br. at 26. This argument conflates the standing analysis with\\n\\nthe merits analysis.\\n\\n As discussed, Appellants have submitted affidavits that show an increase in\\n\\n\\n 13\\n\\fenvironmental harm from drilling activities in the Mancos Shale area; this satisfies the\\n\\nfirst prong of our injury-in-fact analysis. Whether that environmental harm is of a\\n\\nmanner or to a degree not already considered in the 2003 EIS is a question that goes to\\n\\nthe merits of Appellants’ NEPA claim. Appellants, of course, need not prove the merits\\n\\nof their claim in order to establish standing. See, e.g., Steel Co. v. Citizens for a Better\\n\\nEnv’t, 523 U.S. 83, 89 (“It is firmly established in our cases that the absence of a valid\\n\\n(as opposed to arguable) cause of action does not implicate subject-matter jurisdiction . . .\\n\\n.”).\\n\\n 2\\n\\n Standing “also requires a plaintiff be among the injured.” Lucero, 102 F.3d at\\n\\n449. Therefore, Appellants “must be able to show that a separate injury to [their]\\n\\nconcrete, particularized interests flows from the agency’s procedural failure.” Id. (citing\\n\\nLujan, 504 U.S. at 572). To demonstrate harm to a plaintiff’s concrete interests, the\\n\\nplaintiff must “establish either its geographic nexus to, or actual use of the site where the\\n\\nagency will take or has taken action such that it may be expected to suffer the\\n\\nenvironmental consequences of the [challenged] action.” Id. (quotations omitted).\\n\\n Appellants’ members’ affidavits show a geographic nexus to the affected areas\\n\\nsufficient to satisfy the second prong of our injury-in-fact analysis. Eisenfeld states that\\n\\nhe “regularly visit[s] the greater Chaco region, including areas in and around Counselor,\\n\\nLybrook, and Nageezi,” and that he “intend[s] to go back [to Nageezi] in May and June\\n\\n\\n\\n\\n 14\\n\\fof 2017.”4 JA338. He also states that he has “visited hundreds of well sites in the\\n\\n[Greater Chaco] area, and ha[s] frequented lands where many other Mancos Shale wells\\n\\nare in view.” JA342.\\n\\n Nichols regularly visits the Greater Chaco region “for recreational enjoyment.”\\n\\nJA348. He describes visiting Pueblo Pintado, Chaco Culture National Historical Park\\n\\n(Chaco Park), Nageezi, and Pueblo Alto. Nichols “intend[s] to continue visiting the\\n\\nGreater Chaco region, including [Chaco Park] and its outliers, as well as public lands in\\n\\nthe region, at least once a year for the foreseeable future,” and had a trip planned for “late\\n\\nJune 2017.” JA351.\\n\\n Kendra Pinto, a member of Diné, lives in Twin Pines, New Mexico, which is\\n\\n“located along Highway 550, at the county line of San Juan and Rio Arriba.” JA617.\\n\\nBeginning in 2013, she noticed a “major increase in Halliburton trucks along 550, and at\\n\\nthe intersection of 7900 and 7950, trucks are staging right off the highway and even on\\n\\nthe county road blocking traffic.” JA618. She “pass[es] through areas that are very\\n\\npotent in natural gas odors,” and has “seen the giant pillars of fire for the flaring the sites\\n\\ndo.” JA619. She states that “[t]he lights staged at well sites can be as bright as stadium\\n\\nlights.” Id.\\n\\n Deborah Green, a member of NRDC, visits the Chaco Canyon area and Chaco\\n\\nPark at least once a year. She states that “[o]il and gas leasing and development in the\\n\\n\\n\\n 4\\n Because “standing is determined at the time the action is brought,” Mink v.\\nSuthers, 482 F.3d 1244, 1253 (10th Cir. 2007), it does not affect our standing\\nanalysis that these dates are now past.\\n 15\\n\\fChaco Canyon area/region and [Chaco Park] adversely affect[] the quality of [her] visitor\\n\\nexperience in the area, and if expanded, would do so even more.” JA630. Along\\n\\nHighway 550, on the way to Chaco Park, Green has experienced\\n\\n air pollution from gas flares at wells and large amounts of exhaust from the\\n oil and gas company trucks and heavy equipment; noise pollution from\\n heavy truck traffic; and light pollution when drilling goes on around the\\n clock and from gas flares, which are visible from the road for a long\\n distance at night.\\n\\nId.\\n\\n These affidavits establish that the BLM’s challenged actions impair these\\n\\nindividuals’ actual, concrete interests because the affiants have a geographical nexus to\\n\\nand actually use the land in the allegedly affected area.\\n\\n Federal Appellees argue that the affidavits are insufficient for two reasons. First,\\n\\nthey contend that Appellants have “challenged 337 individual agency actions,” each of\\n\\nwhich “gives rise to a distinct claim,” and that Appellants “must establish standing . . . for\\n\\neach challenged APD approval.” Fed. Aples. Br. at 23. Second, they argue that\\n\\nAppellants “fail to establish a geographical nexus to the challenged agency actions”\\n\\nbecause Appellants’ affidavits all refer generally to the “greater Chaco region” or the\\n\\n“Mancos Shale formation.” Id. at 26–27. Both arguments fail.\\n\\n As Appellants point out, we have previously rejected similar arguments. In\\n\\nPalma, the district court held that the plaintiffs did not establish an injury in fact because\\n\\nthey submitted affidavits that “did not identify specific visits to each of the thirty-nine\\n\\nleases at issue.” 707 F.3d at 1155. This holding, we concluded, misapplied the law. Id.\\n\\n“Neither our court nor the Supreme Court has ever required an environmental plaintiff to\\n\\n 16\\n\\fshow that it has traversed each bit of land that will be affected by a challenged agency\\n\\naction.” Id. Rather, “[a] plaintiff who has repeatedly visited a particular site, has\\n\\nimminent plans to do so again, and whose interest are harmed by a defendant’s conduct\\n\\nhas suffered injury in fact that is concrete and particularized.” Id. at 1156. In Palma, an\\n\\norganization’s member’s affidavit was “sufficient” when “[h]e specified areas which he\\n\\nhas visited, averred that these specific areas will be affected by oil and gas drilling, and\\n\\nstated his interests will be harmed by such activity.” Id. The affidavits Appellants\\n\\nsubmitted in this case meet this standard.5\\n\\n Further, maps in the record indicate the geographic proximity of challenged APD\\n\\nsites to specific areas referenced in Appellants’ affidavits. Nichols attached to his\\n\\ndeclaration a map of the area around Chaco Park that shows the proximity of existing and\\n\\nnew wells to Chaco Park and other locations affiants describe. This and other maps in\\n\\nthe record indicate that challenged well sites are within twenty miles or less of Chaco\\n\\nPark, where Nichols and Green recreate; along Highway 550, the road to enter Chaco\\n\\nPark; and within several miles of Twin Pines, where Pinto lives, and Nageezi, where\\n\\nEisenfeld and Nichols both recreate.\\n\\n Furthermore, Appellants in this case challenge the BLM’s alleged failure to\\n\\n\\n 5\\n Although we dismissed the appeal in Palma for lack of ripeness, Palma still\\ninforms our injury-in-fact determination. Because we concluded that the Palma\\nplaintiffs had established a concrete and particularized injury, we went on to consider\\n“not whether SUWA is a proper party to challenge BLM’s decision, but when it can\\ndo so.” 707 F.3d at 1157. But our determination that the Palma plaintiffs’ harm was\\nnot ripe does not render obsolete our conclusion that their harm was sufficiently\\nconcrete and imminent. Palma therefore appropriately informs our injury-in-fact\\nanalysis here.\\n 17\\n\\fevaluate the indirect and cumulative impacts of the APDs, not merely the direct impacts\\n\\nof drilling to the area immediately surrounding the wellpads. Although Appellants’\\n\\nNEPA claim is in the form of challenges to numerous individual APDs, the allegedly\\n\\naffected area extends beyond the boundaries of the well sites and into the greater Chaco\\n\\nlandscape. Affiants’ descriptions of environmental harms including “air pollution from\\n\\ngas flares at wells,” “exhaust from the oil and gas company trucks and heavy equipment,”\\n\\n“noise pollution from heavy truck traffic,” and “light pollution” from drilling and “gas\\n\\nflares,” JA630, which they experience as they live and recreate in the affected area, are\\n\\nsufficient to place Appellants “among the injured.” Lucero, 102 F.3d at 449.\\n\\n Appellants have shown through their members’ affidavits that some of their\\n\\nmembers have a geographical nexus to, and actually use, land the BLM has exposed to an\\n\\nincreased risk of environmental harm due to its alleged uninformed decisionmaking.\\n\\nAppellants have established an injury in fact for purposes of Article III.\\n\\n B\\n\\n To establish causation, an environmental plaintiff “need only trace the risk of\\n\\nharm to the agency’s alleged failure to follow [NEPA]’s procedures.” Lucero, 102 F.3d\\n\\nat 452. A NEPA injury “results not from the agency’s decision, but from the agency’s\\n\\nuninformed decisionmaking.” Id. (first emphasis added).\\n\\n Federal Appellees argue that Appellants have not shown that “the relief sought—\\n\\nthe vacatur of BLM’s decisions approving these 337 APDs—will remedy their alleged\\n\\ninjuries.” Fed. Aples. Br. at 29. They assert that Appellants have not established that\\n\\ntheir environmental harms were caused by “the 337 challenged permits rather than . . . the\\n\\n 18\\n\\fapproximately 23,000 active oil and gas wells in the San Juan Basin that are not the\\n\\nsubject of this action.” Id. This argument fails.\\n\\n “In the context of a [NEPA] claim, the injury is the increased risk of\\n\\nenvironmental harm to concrete interests . . . .” Lucero, 102 F.3d at 451 (emphasis\\n\\nadded). In this case, Appellants’ asserted injury is the increased risk of environmental\\n\\nharm from the additional wells, and it is undisputed that BLM has authorized more than\\n\\n300 additional wells in the Mancos Shale. Appellants have alleged that the BLM did not\\n\\ncomply with NEPA in granting the challenged APDs, and that its alleged failure resulted\\n\\nin “the agency’s uninformed decisionmaking” as to these additional wells. Id. at 452.\\n\\nThis is sufficient to establish causation.\\n\\n C\\n\\n Appellants must also establish that it is “likely, as opposed to merely speculative,\\n\\nthat the injury will be redressed by a favorable decision.” Lujan, 504 U.S. at 561\\n\\n(quotations omitted). Under NEPA, “a plaintiff need not establish that the ultimate\\n\\nagency decision would change upon [NEPA] compliance. Rather, the [Plaintiff must\\n\\nonly show] that its injury would be redressed by a favorable decision requiring”\\n\\ncompliance with NEPA procedures. Lucero, 102 F.2d at 452 (quotations and citations\\n\\nomitted). Here, Appellants challenge the BLM’s decision to grant APDs without\\n\\nconducting the requisite NEPA analysis. A favorable decision ordering compliance with\\n\\nNEPA’s procedures would “avert the possibility that the [BLM] may have overlooked\\n\\nsignificant environmental consequences of its actions,” thereby redressing Appellants’\\n\\nalleged harms. Id. Appellants have established redressability.\\n\\n 19\\n\\f Because individual members of Appellants’ organizations have suffered a concrete\\n\\nand particularized injury in fact that is fairly traceable to the BLM’s alleged failure to\\n\\ncomply with NEPA and could be redressed by a favorable decision, we conclude that\\n\\nAppellants have standing.6\\n\\n IV\\n\\n Before analyzing the merits of Appellants’ arguments, we first note the dramatic\\n\\ninsufficiency of the record. Although Appellants challenge more than 300 individual\\n\\nagency actions, they have provided us with the complete record of the BLM’s\\n\\ndecisionmaking process for only a few of the challenged actions. We are therefore\\n\\nunable to evaluate the sufficiency of the BLM’s NHPA and NEPA analyses for the vast\\n\\nmajority of the challenged actions. See 10th Cir. R. 10.4(A) (“Counsel must designate a\\n\\nrecord on appeal . . . that is sufficient for considering and deciding the appellate issues.”);\\n\\nid. at 10.4(B) (“When the party asserting an issue fails to provide a record or appendix\\n\\nsufficient for considering that issue, the court may decline to consider it.”).\\n\\n As to NHPA, the record indicates that the BLM considered impacts on historic\\n\\nproperties in at least three documents for each APD: (1) a Cultural Resource Survey\\n\\n(CRS), (2) a Record of Review, and (3) a site-specific EA. Therefore, in order to\\n\\n\\n\\n 6\\n The harms Appellants allege are the same for their NHPA claims (an\\nincreased risk of harm to Chaco Park and the surrounding area), and NHPA is also a\\nprocedural statute, so the standing analysis for NHPA is the same as for NEPA in this\\ncase. Appellants have established standing under NHPA because they allege a\\nconcrete and particularized injury in fact that is fairly traceable to the BLM’s alleged\\nfailure to comply with NHPA and could be redressed by a favorable decision.\\n\\n 20\\n\\fevaluate the sufficiency of the BLM’s NHPA analysis, we would need the complete EA,\\n\\ncomplete CRS, and complete Record of Review for each challenged APD. The record,\\n\\nhowever, contains portions of the BLM’s NHPA analysis for only seventeen different\\n\\nsets of APDs.7 Further, the vast majority of the NHPA analyses in the record are only\\n\\nseveral-page excerpts, not the entire analysis. The record contains the complete EA,\\n\\nCRS, and Record of Review for only one set of challenged APDs: Kimbeto Wash Unit\\n\\nWells 787H, 789H, and 791H.\\n\\n As to NEPA, the record indicates that the BLM’s NEPA analysis was included in\\n\\nat least each site-specific EA and the 2003 EIS (to which each of the site-specific EAs\\n\\ntiered). Therefore, in order to evaluate the sufficiency of the BLM’s NEPA analyses, we\\n\\nwould need the complete 2003 EIS and the complete EA for each challenged APD. The\\n\\nrecord, however, only includes portions of twenty-seven EAs. And, as with the NHPA\\n\\nanalyses, the vast majority of the EAs in the record are several-page excerpts, not the\\n\\ncomplete EA. From our count, the record contains only six complete EAs: EA 2012-\\n\\n0268, EA 2014-0272, EA 2015-0036, EA 2015-0066, EA 2016-0029, and EA 2016-\\n\\n0200/2016-0076. We are therefore able to analyze whether the BLM violated NEPA\\n\\nonly as to those six EAs.\\n\\n “[O]ur cases addressing deficiencies in the appendix submitted by an appellant\\n\\ndefine a guiding principle . . . .” Lincoln v. BNSF Ry. Co., 900 F.3d 1166, 1190 (10th\\n\\n\\n 7\\n It appears that many CRSs and Records of Review analyze the impacts on\\nhistoric properties for more than one APD. And it appears that most, if not all, EAs\\nanalyze the impacts of more than one APD. Regardless, the record on appeal\\ncontains far fewer than all of the documents containing the BLM’s NHPA analyses.\\n 21\\n\\fCir. 2018). Even when an appendix is deficient, if “the materials provided by the\\n\\nappellant permit us to reach a firm and definite conclusion regarding the merits of an\\n\\nindividual argument or claim within the appeal,” we often will address the argument or\\n\\nclaim, although our rules do not require us to do so. Id. But if “we are forced to venture\\n\\na guess as to the merits of an argument or claim, even ‘an informed guess,’ we will\\n\\nsummarily affirm the district court’s judgment.” Id. (collecting cases).\\n\\n Applying these principles, we conduct our NHPA and NEPA reviews only as to\\n\\nthose challenged actions for which we have the BLM’s complete analysis. For NHPA,\\n\\nwe evaluate the sufficiency of the BLM’s analysis for Kimbeto Wash Unit Wells 787H,\\n\\n789H, and 791H. For NEPA, we evaluate the sufficiency of the BLM’s analysis for: (1)\\n\\nEA 2012-0268, (2) EA 2014-0272, (3) EA 2015-0036, (4) EA 2015-0066, (5) EA 2016-\\n\\n0029, and (6) EA 2016-0200/2016-0076.8 As to all other challenged agency actions, the\\n\\nrecord “is insufficient to permit assessment of [Appellants’] claim of error,” and we\\n\\naffirm the district court. Tilton v. Capital Cities/ABC, Inc., 115 F.3d 1471, 1474 (10th\\n\\nCir. 1997).\\n\\n\\n\\n\\n 8\\n We note that even as to these EAs, it is possible that the record does not\\ncontain the BLM’s entire NEPA analysis. See, e.g., JA2143 (stating “Appendix D.\\nSurface Reclamation Plan,” but not containing any surface reclamation plan).\\nHowever, because we do not identify—and the parties do not point to—any missing\\nportion of these EAs relevant to the challenges Appellants raise on appeal, we\\nconclude that the record is sufficient for us to evaluate Appellants’ NEPA claims as\\nto these EAs.\\n 22\\n\\f V\\n\\n Appellants contend that the BLM violated NHPA in three ways. First, they assert\\n\\nthat the BLM arbitrarily defined an area of potential effects (APE) for each APD in a way\\n\\nthat excluded cultural sites that might be indirectly affected by Mancos Shale\\n\\ndevelopment. This argument is premised on Appellants’ assertion that the 2014 Protocol\\n\\nrequired the BLM to set a separate APE for indirect effects, which the BLM did not do.\\n\\nSecond, Appellants argue that the BLM did not consider the cumulative effects of\\n\\nMancos Shale development on relevant cultural and historic properties. Finally,\\n\\nAppellants contend that the BLM failed to consult with the State Historic Preservation\\n\\nOffice (SHPO) as required by the 2014 Protocol. Each of these arguments fail.\\n\\n A\\n\\n Section 106 of NHPA sets forth specific processes federal agencies must perform\\n\\nto comply with NHPA. See 36 C.F.R. § 800.1(a). In general, the Section 106 process\\n\\ninvolves four steps. First, the agency defines the APE. 36 C.F.R. § 800.4(a). The APE\\n\\nis “the geographic area or areas within which an undertaking may directly or indirectly\\n\\ncause alterations in the character or use of historic properties, if any such properties\\n\\nexist.” Id. § 800.16(d). “Establishing an [APE] requires a high level of agency expertise,\\n\\nand as such, the agency’s determination is due a substantial amount of discretion.”\\n\\nValley Cmty. Pres. Comm’n v. Mineta, 373 F.3d 1078, 1092 (10th Cir. 2004).\\n\\n After defining the APE, the agency identifies historic properties within the APE.\\n\\n36 C.F.R. § 800.4(b). A historic property is “any prehistoric or historic district, site,\\n\\nbuilding, structure, or object included on, or eligible for inclusion on” the National\\n\\n 23\\n\\fRegister of Historic Places (NRHP). 54 U.S.C. § 300308. If the agency determines that\\n\\nno historic properties are present within the APE, it reports that finding and the NHPA\\n\\nprocess ends. 36 C.F.R. § 800.4(d)(1).\\n\\n If historic properties are present within the APE, the agency determines whether\\n\\nthe proposed undertaking will adversely affect those properties. Id. § 800.5. An adverse\\n\\neffect exists “when an undertaking may alter, directly or indirectly, any of the\\n\\ncharacteristics of a historic property that qualify the property for inclusion in the [NRHP]\\n\\nin a manner that would diminish the integrity of the property’s location, design, setting,\\n\\nmaterials, workmanship, feeling, or association.” Id. § 800.5(a)(1). Adverse effects\\n\\ninclude “reasonably foreseeable effects caused by the undertaking that may occur later in\\n\\ntime, be farther removed in distance or be cumulative.” Id. They also include the\\n\\n“[i]ntroduction of visual, atmospheric[,] or audible elements that diminish the integrity of\\n\\nthe property’s significant historic features.” Id. § 800.5(a)(2)(v).\\n\\n If the agency determines that the undertaking may cause an adverse effect on the\\n\\nhistoric properties within the APE, it must “develop and evaluate alternatives or\\n\\nmodifications to the undertaking that could avoid, minimize, or mitigate adverse effects\\n\\non historic properties.” Id. § 800.6(a). The Section 106 process does not demand a\\n\\nparticular result, however, because “Section 106 is essentially a procedural statute and\\n\\ndoes not impose a substantive mandate” on the agencies governed by it. Valley Cmty.,\\n\\n373 F.3d at 1085.\\n\\n Section 106 authorizes agencies to enter into a “programmatic agreement to\\n\\ngovern the implementation of a particular program or the resolution of adverse effects\\n\\n 24\\n\\ffrom certain complex project situations or multiple undertakings.” 36 C.F.R.\\n\\n§ 800.14(b). When a governing programmatic agreement is in place, compliance with the\\n\\nprocedures in that agreement satisfies the agency’s NHPA Section 106 responsibilities\\n\\nfor all covered undertakings. Id. § 800.14(b)(2)(iii).\\n\\n The parties agree that two programmatic agreements governed the BLM’s NHPA\\n\\nanalyses of the APDs in this case: one agreement that went into effect in 2004 (the 2004\\n\\nProtocol), and one that went into effect in 2014 (the 2014 Protocol). Therefore, we must\\n\\nresolve whether Appellants have shown that the BLM violated the requirements of the\\n\\n2014 Protocol9 as to the single challenged APD properly before us. Although the\\n\\ncompliance requirements for the 2014 Protocol are somewhat different than Section\\n\\n106’s requirements, the basic NHPA process is the same.\\n\\n The 2014 Protocol states generally that, “[i]n defining the APE, the BLM will\\n\\nconsider potential direct, indirect, and cumulative effects to historic properties and their\\n\\nassociated settings when setting is an important aspect of integrity, as applicable.”\\n\\nJA1562. Relevant here, the 2014 Protocol states that “[t]he BLM will follow the\\n\\nestablished guidance on standard direct APEs for certain types of projects in Appendix\\n\\n\\n\\n 9\\n Although Appellants acknowledge the existence and applicability of the 2004\\nProtocol, they make no NHPA arguments under the 2004 Protocol. Federal\\nAppellees assert (without citation) that “[a]pproximately 221 of the challenged\\ndrilling permits were approved at the time the 2004 Protocol was operative, and\\napproximately 163 permits fell under the 2014 Protocol.” Fed. Aples. Br. at 12. All\\nof Appellants’ NHPA arguments, however, rely on the 2014 Protocol. Because we\\nconclude that Appellants’ NHPA challenge fails for other reasons, we need not\\naddress the effect Appellants’ failure to argue that the BLM violated the 2004\\nProtocol might otherwise have on Appellants’ NHPA challenges.\\n 25\\n\\fB.” Id. (italics omitted). Appendix B sets a “standard APE” for well pads of “the well\\n\\npad and construction zone plus 100[] [feet] on each side from the edge of the construction\\n\\nzone.” JA1594. The 2014 Protocol acknowledges that “[i]n certain circumstances, even\\n\\nthough an undertaking may have a standard APE . . . , the Field Manager, at the\\n\\nrecommendation of the cultural resource specialist, may have justification to require a\\n\\nlarger APE.” Id.\\n\\n B\\n\\n Appellants argue that the BLM “failed to account for indirect impacts to cultural\\n\\nsites, as required by the NHPA and the Protocol.” Aplts. Br. at 30. According to\\n\\nAppellants, “the Protocol requires BLM to consider a separate APE for indirect effects\\n\\nwhere ‘[t]he introduction of physical, visual, or audible elements has the potential to\\n\\naffect the historic setting or use’ of cultural sites ‘where setting is an important aspect of\\n\\nintegrity.’” Id. at 31 (quoting JA1562). Appellants’ argument fails because the 2014\\n\\nProtocol merely allows for, it does not require, a separate indirect-effects APE.\\n\\n The 2014 Protocol acknowledges that “[t]he introduction of physical, visual,\\n\\naudible, or atmospheric elements has the potential to affect the historic setting or use of\\n\\nhistoric properties,” and requires the BLM to “take this into account in defining the limits\\n\\nof an APE for indirect effects.” JA1562 (emphasis added). Under the 2014 Protocol,\\n\\n“[t]he indirect APE shall include known or suspected historic properties and their\\n\\nassociated settings where setting is an important aspect of integrity.” Id. The 2014\\n\\nProtocol continues: “Identification efforts outside of the APE for direct effects shall be at\\n\\nthe approval of the BLM field manager, taking into account the recommendations of the\\n\\n 26\\n\\fBLM cultural resource specialist and the SHPO.” Id. (emphasis added). In other words,\\n\\nthe BLM need not set—or even consider—a separate indirect-effects APE when\\n\\n“physical, visual, audible, or atmospheric elements ha[ve] the potential to affect the\\n\\nhistoric setting or use of historic properties,” as Appellants argue. JA1562. Rather, the\\n\\n2014 Protocol only requires that the BLM take indirect effects into account as it exercises\\n\\nits substantial discretion in setting the APE. The 2014 Protocol therefore contains a\\n\\ndefault presumption that the direct and indirect APE will be the same and, to the extent\\n\\nthe BLM will attempt to identify historic properties outside the direct-effects APE, those\\n\\nidentification efforts will be at the approval of the BLM field manager.\\n\\n Moreover, the CRS, the Record of Review, and the EA for the Kimbeto Wash\\n\\nUnit wells indicate that the BLM looked to areas far outside the standard direct-effects\\n\\nAPE to identify cultural properties. The EA includes a fulsome discussion of the\\n\\npotential for indirect impacts from the proposed project, including an analysis of visual\\n\\nresources. The EA notes that the proposed action is at least 8.5 miles “from the boundary\\n\\nof [Chaco Park].” Id. It acknowledges that “small portions of the pipeline fall within”\\n\\ntwo National Park Service designated Key Observation Points, but concludes that\\n\\n“[g]iven [the] distance ([over] 11.5 miles) and low profile[,] the pipeline will not be\\n\\nvisible.” JA1949. The EA notes that the project’s “well pad is within a mile of a few\\n\\nscattered residences,” but concludes that it is “unlikely that the well pad will be visible\\n\\nfrom these residences due to area topography.” JA1950. It also states that the “well pad\\n\\nwill not visible from any designated recreation areas.” Id.\\n\\n The EA also addresses the project’s potential impact on night skies, noting that\\n\\n 27\\n\\f“[l]ight sources associated with drilling an oil and gas well include a light plant or\\n\\ngenerator, a light on top of the rig, vehicle traffic, and flaring.” JA1951.\\n\\n The necessity for flaring and the duration of flaring varies widely from well\\n to well and is difficult to predict. With the exception of a few yearly\\n events, visitors are not allowed access to the canyon rim where the\\n proposed action may be seen after sunset, minimizing the chance that\\n visitors would see the direct light. While these lights could reduce the\\n general darkness of the night sky as seen from [Chaco Park], it is likely the\\n impact would be imperceptible.\\n\\nId. Further, the EA notes that any potential light impacts “would be short-term.” Id.\\n\\n The CRS and Record of Review also indicate that the BLM looked for historic\\n\\nsites in an area that extended far beyond the direct-effects APE. The CRS notes that a\\n\\nrecord search was conducted and “[n]o sites listed on the State Register of Cultural\\n\\nProperties or the [NRHP we]re located within a 1 mile [sic] of the project area.” JA2173\\n\\n(emphasis added). The BLM also conducted pedestrian surveys of a 108.01-acre area,\\n\\nalthough the CRS indicates only 25.76 acres in the APE. [Id.] During the pedestrian\\n\\nsurveys, “[w]hen cultural material was encountered, it was pin flagged and the\\n\\narchaeologists began an intensive search of the area to locate other material.” JA2175.\\n\\nAfter eight “Fieldwork Dates,” forty-six “Survey Person Hours” and thirty-nine\\n\\n“Recording Person Hours,” the BLM’s NHPA review identified four newly recorded\\n\\ncultural sites, one previously recorded site, and twelve isolated occurrences of cultural\\n\\nmaterial. Id. The BLM ultimately determined that three of the five sites were ineligible\\n\\nfor listing on the NRHP, and two were eligible but avoided. The BLM therefore\\n\\nrecommended that the project go forward with mitigation requirements, including\\n\\nemployee education, temporary barriers, and archaeological site monitoring.\\n\\n 28\\n\\f The CRS, Record of Review, and EA for the Kimbeto Wash Unit wells indicate\\n\\nthat the BLM attempted to identify historic properties in an area far outside the standard\\n\\ndirect-effects APE for well pads, and that the BLM considered the proposed drilling’s\\n\\npossible visual impacts, including its impact on night skies. Given this analysis,\\n\\nespecially considering that it far exceeded the analysis required by the 2014 Protocol,\\n\\nAppellants have failed to establish that the BLM violated NHPA by not adequately\\n\\nconsidering the indirect effects of the Kimbeto Wash Unit wells.10\\n\\n C\\n\\n Appellants also argue that the BLM violated NHPA because it “failed to analyze\\n\\nthe cumulative effects of developing hundreds of new APDs across this culturally\\n\\nsignificant landscape.” Aplts. Br. at 38. Appellants’ cumulative-effects argument fails\\n\\nbecause Appellants identify no historic properties within the APE the BLM set.\\n\\n In support of their cumulative-effects argument, Appellants cite to 36 C.F.R.\\n\\n\\n\\n 10\\n Despite the BLM’s extensive NHPA analysis for the Kimbeto Wash Unit\\nwells, parts of the record indicate that the BLM may not have considered the\\ncumulative and indirect impacts of other challenged APDs so thoroughly. For\\nexample, in discussing possible cumulative impacts, some EAs state simply that\\n“[t]here would be no negative cumulative impact on cultural resources, as significant\\ncultural sites would be avoided.” JA1154; accord JA1267 (same); JA1333 (same).\\nDepending on the circumstances—and whether this were indeed the only cumulative\\nimpacts analysis the BLM completed—this cursory analysis could be insufficient.\\n However, other parts of the record contain more thorough indirect- and\\ncumulative-effects analyses. Indeed, the apparent difference in the substance of the\\nBLM’s NHPA analyses for different APDs highlights the need to examine each of the\\nBLM’s challenged actions individually and with reference to a complete record of the\\nBLM’s NHPA analysis. And, of course, we cannot determine that the BLM’s\\nanalysis was insufficient for one APD by examining the analysis the BLM conducted\\nfor a different APD.\\n 29\\n\\f§ 800.5(a)(1), which states that “[a]dverse effects may include reasonably foreseeable\\n\\neffects caused by the undertaking that may occur later in time, be farther removed in\\n\\ndistance or be cumulative.” This regulation, however, addresses the BLM’s application\\n\\nof “the criteria of adverse effect to historic properties within the [APE].” 36 C.F.R.\\n\\n§ 800.5(a) (emphasis added). In other words, the cited language simply means that an\\n\\nundertaking can have adverse effects on historical properties within the APE, even if the\\n\\nundertaking only adversely affects the properties through “reasonably foreseeable effects\\n\\ncaused by the undertaking that may . . . be cumulative.” Id. § 800.5(a)(1).\\n\\n Appellants, however, argue that the BLM abused its discretion by failing to\\n\\nanalyze the cumulative adverse effects horizontal Mancos Shale wells might have “on the\\n\\nintegrity of the historic setting for any number of cultural sites, [Chaco] Park, and the\\n\\nGreater Chaco Landscape.” Aplts. Br. at 37. This argument ignores that § 800.5(a)(1)\\n\\napplies to the BLM’s assessment of adverse effects on “historic properties within the\\n\\n[APE].” 36 C.F.R. § 800.5(a) (emphasis added). And the record indicates that the APE\\n\\nfor the Kimbeto Wash Unit wells did not encompass the “cultural sites, [Chaco] Park, and\\n\\nthe Greater Chaco Landscape,” Aplts. Br. at 37, which Appellants argue would be\\n\\nnegatively impacted by these cumulative effects.11\\n\\n In sum, Appellants’ cumulative-effects argument is premised on an APE different\\n\\n\\n\\n 11\\n Indeed, Appellants criticize this aspect of the BLM’s NHPA process,\\narguing that the BLM’s APE definition “resulted in the agency excluding from its\\nanalysis all cultural sites likely to be adversely affected by noise, light, and air\\npollution.” Aplts. Br. at 30.\\n\\n 30\\n\\ffrom the one the BLM defined. Appellants’ argument therefore fails.\\n\\n D\\n\\n Appellants also argue that the BLM was required to consult with the SHPO12\\n\\nbecause defining APEs for the challenged APDs was “complicated or controversial.”\\n\\nAplts. Br. at 35. In support, Appellants cite the 2014 Protocol’s examples of\\n\\n“complicated or controversial” projects, contending that the APDs at issue qualify\\n\\nbecause “‘multiple applicants’ [and] ‘multiple Indian tribes’ are involved.” Id. (quoting\\n\\nJA1562). Appellants’ SHPO consultation argument fails.\\n\\n The 2014 Protocol “specifies the manner in which the BLM works with SHPO,”\\n\\nand “establishes a streamlined consultation process for most BLM undertakings.”\\n\\nJA1552. It provides that “[t]he BLM will consult with SHPO on undertakings for which\\n\\na standard APE . . . has not been developed.” JA1562. Appendix B indicates that if the\\n\\nBLM utilizes a standard APE for an undertaking, the “BLM and SHPO have consulted”\\n\\nas to that APE. JA1594 (emphasis added). The 2014 Protocol also states that the BLM\\n\\nwill consult with the SHPO “where the APE is complicated or controversial,” and gives\\n\\nexamples of situations in which defining the APE may be complicated or controversial:\\n\\n\\n\\n\\n 12\\n Amici All Pueblo Council of Governors and the National Trust for Historic\\nPreservation in the United States argue that the BLM did not adequately consult with\\nNative American tribes before approving the APDs. Appellants did not make this\\nargument in district court, and we decline to consider it for the first time on appeal.\\nMcDonald v. Kinder-Morgan, Inc., 287 F.3d 992, 999 (10th Cir. 2002) (“[A]bsent\\nextraordinary circumstances, we will not consider arguments raised for the first time\\non appeal.”).\\n 31\\n\\f“undertakings involving multiple agencies, multiple states, multiple applicants, and/or\\n\\nmultiple Indian tribes.” JA1562.\\n\\n The 2014 Protocol therefore establishes a default presumption that the BLM need\\n\\nnot consult with the SHPO “on undertakings for which a standard APE” exists, such as\\n\\nthe undertakings at issue in this case. JA1562. And in this case, the applicability of a\\n\\nstandard APE also undermines a conclusion that the APE is complicated or controversial.\\n\\nRather, the existence of a standard APE indicates that the BLM and the SHPO anticipated\\n\\nthat the BLM would often have to define an APE for activities related to oil and gas\\n\\ndrilling, such as well pads, pipelines, and roads. And, seeking to “streamline the\\n\\nconsultation process” for these common undertakings, the BLM and the SHPO\\n\\ndetermined that a standard APE for these activities would suffice in most circumstances,\\n\\nand BLM-SHPO consultation in defining the specific APE would be unnecessary.\\n\\nJA1552; accord JA1562. We therefore reject Appellants’ argument that the BLM abused\\n\\nits discretion by not consulting with the SHPO.\\n\\n Appellants fail to carry their burden of establishing that the BLM violated NHPA.\\n\\nThe BLM’s decision is entitled to a presumption of regularity, and it finds support in the\\n\\nrecord. Accordingly, we affirm the district court’s dismissal of Appellants’ NHPA claim.\\n\\n VI\\n\\n Appellants’ NEPA argument is as follows: the environmental impacts of the\\n\\nhorizontal Mancos Shale wells are both (1) different in kind from and (2) greater in\\n\\nmagnitude than those considered in the 2003 EIS. Because of this, the 2003 EIS did not\\n\\nfully analyze the environmental impacts associated with horizontal Mancos Shale wells,\\n\\n 32\\n\\fso the BLM was not authorized to tier the EAs to the 2003 EIS, and the FONSIs the BLM\\n\\nissued were arbitrary and capricious. We conclude that, as to five EAs, Appellants have\\n\\ndemonstrated that the BLM needed to—but did not—consider the cumulative impacts of\\n\\nwater resources associated with the 3,960 reasonably foreseeable horizontal Mancos\\n\\nShale wells. The BLM’s issuance of FONSIs and approval of APDs associated with\\n\\nthese EAs was therefore arbitrary and capricious and violated NEPA.\\n\\n A\\n\\n NEPA “requires federal agencies . . . to analyze environmental consequences\\n\\nbefore initiating actions that potentially affect the environment.” Utah Env’t Cong. v.\\n\\nBosworth, 443 F.3d 732, 735–36 (10th Cir. 2006). To comply with NEPA, agencies\\n\\nmust prepare a detailed statement of the environmental impact of any “major Federal\\n\\naction[] significantly affecting the quality of the human environment.” 42 U.S.C.\\n\\n§ 4332(2)(C).\\n\\n In conducting its NEPA analysis, a federal agency must prepare, as relevant here,\\n\\neither “(1) an environmental impact statement [(EIS)], [or] (2) an environmental\\n\\nassessment [(EA)].” Bosworth, 443 F.3d at 736. An EIS “is required if a proposed\\n\\naction will ‘significantly affect[] the quality of the human environment.’” Id. (alteration\\n\\nin original) (quoting 42 U.S.C. § 4332(C)). “If an agency is uncertain whether the\\n\\nproposed action will significantly affect the environment, it may prepare a considerably\\n\\nless detailed [EA].” Id.\\n\\n Although less detailed than an EIS, the EA must still “include brief discussions of\\n\\nthe need for the proposal, of alternatives . . . , [and] of the environmental impacts of the\\n\\n 33\\n\\fproposed action and alternatives.” 40 C.F.R. § 1508.9(b). Among the environmental\\n\\nimpacts the EA must evaluate are “the cumulative impacts of a project.” WildEarth\\n\\nGuardians v. U.S. Fish & Wildlife Serv., 784 F.3d 677, 690 (10th Cir. 2015) (quoting\\n\\nDavis v. Mineta, 302 F.3d 1104, 1125 (10th Cir. 2002) abrogated on other grounds by\\n\\nDiné Citizens Against Ruining Our Env’t v. Jewell, 839 F.3d 1276 (10th Cir. 2016)).\\n\\nCumulative impacts are “the impact on the environment which results from the\\n\\nincremental impact of the action when added to other past, present, and reasonably\\n\\nforeseeable future actions.” 40 C.F.R. § 1508.7. Cumulative impacts can result from\\n\\n“individually minor but collectively significant actions taking place over a long period of\\n\\ntime.” Id.\\n\\n If, after considering the necessary factors, the agency concludes the action is\\n\\nunlikely to have a significant environmental impact, it may issue a finding of no\\n\\nsignificant impact (FONSI) and proceed with the action. 40 C.F.R. § 1508.13. If the\\n\\nagency reaches the opposite conclusion, before proceeding with the action, it must\\n\\nprepare an environmental impact statement to thoroughly analyze the action’s predicted\\n\\nenvironmental impacts, including its direct, indirect, and cumulative impacts. 42 U.S.C.\\n\\n§ 4332(2)(C); 40 C.F.R. §§ 1508.11, 1508.25. However, even when a proposed action\\n\\nhas “significant effects,” the BLM may tier13 an EA to an existing EIS—and thereby\\n\\n\\n\\n 13\\n “Tiering refers to the coverage of general matters in broader environmental\\nimpact statements . . . with subsequent narrower statements or environmental\\nanalyses . . . incorporating by reference the general discussions and concentrating\\nsolely on the issues specific to the statement subsequently prepared.” 40 C.F.R.\\n§ 1508.28.\\n 34\\n\\freach a FONSI—if the EIS to which it tiers “fully analyzed those significant effects.” 43\\n\\nC.F.R. § 46.140(c). But if the “relevant analysis in the [EIS] is not sufficiently\\n\\ncomprehensive or adequate to support further decisions, the [EA] must explain this and\\n\\nprovide any necessary analysis.” Id. § 46.140(b).\\n\\n “The role of a federal court under NEPA is to review the EIS, [or] EA, . . . as the\\n\\ncase may be, and ‘simply . . . ensure that the agency has adequately considered and\\n\\ndisclosed the environmental impact of its actions.” Concerned Citizens, 843 F.3d at 902\\n\\n(third alteration in original) (quoting Wyoming v. U.S. Dep’t of Agric., 661 F.3d 1209,\\n\\n1256–57 (10th Cir. 2011)). In conducting this review, we apply a “rule of reason\\n\\nstandard” to determine whether claimed NEPA violations “are merely flyspecks, or are\\n\\nsignificant enough to defeat the goals of informed decision making and informed public\\n\\ncomment.” Utahns for Better Transp. v. U.S. Dep’t of Transp., 305 F.3d 1152, 1163\\n\\n(10th Cir. 2002).\\n\\n B\\n\\n Appellants first argue that the challenged APDs cause environmental impacts\\n\\nqualitatively different from those considered in the 2003 EIS because the APDs authorize\\n\\ndrilling in the southern portion of the Mancos Shale, while the 2003 EIS “only evaluated\\n\\ndevelopment in the northern portion.” Aplts. Br. at 42. Appellants’ argument fails\\n\\nbecause the 2003 EIS evaluated the effects of drilling throughout the entire San Juan\\n\\nBasin—an area that includes the location of the challenged APDs.\\n\\n The 2003 EIS was developed to “analyze[] the environmental impacts of oil and\\n\\ngas leasing and development in the San Juan Basin in New Mexico.” JA767. The\\n\\n 35\\n\\f“planning area” addressed in the 2003 EIS “includes all of San Juan County, most of\\n\\nMcKinley County, western Rio Arriba County, and northwestern Sandoval County.”\\n\\nJA768. All challenged APDs are within this area.\\n\\n The 2003 EIS denoted the northeastern portion of the planning area as a “high\\n\\ndevelopment area” for oil and gas production, but that area was so identified because\\n\\n“more than 99 percent of the federal oil and gas resources [we]re currently leased” in that\\n\\narea. JA778. Nothing in the 2003 EIS indicates that the BLM analyzed the\\n\\nenvironmental impacts of drilling on only the high development area. Indeed, the 2003\\n\\nEIS’s chapter on the affected environment contains a lengthy discussion of the cultural\\n\\nresources present in the Chaco Canyon. The record, therefore, does not support\\n\\nAppellants’ assertion that the challenged APDs are in a geographic area not considered\\n\\nby the 2003 EIS.\\n\\n C\\n\\n Appellants also argue that the BLM has never fully analyzed the cumulative\\n\\nenvironmental impacts of drilling 3,960 horizontal wells in the Mancos Shale because\\n\\nthose impacts exceed the environmental impacts evaluated in the 2003 EIS in two\\n\\nspecific ways: air pollution and water use. As to air pollution, we conclude that\\n\\nAppellants have not provided us with a record from which we can assess the BLM’s\\n\\nNEPA analysis. As to water use, we conclude that Appellants have shown that the BLM\\n\\nnever considered the cumulative impact of the water use associated with the 3,960\\n\\nreasonably foreseeable horizontal Mancos Shale wells for five specific EAs. We\\n\\ntherefore reverse the district court’s dismissal of Appellants’ NEPA claims as to EAs\\n\\n 36\\n\\f2014-0272, 2015-0036, 2015-0066, 2016-0029, and 2016-0200/2016-0076.14\\n\\n 1\\n\\n Appellants’ cumulative-impacts argument relies on one assumption the parties\\n\\ndispute: that the BLM’s NEPA analysis must consider the impacts associated with all\\n\\n3,960 wells the 2014 RFDS identified as possible if full-field Mancos Shale\\n\\ndevelopment occurs. We conclude that the 2014 RFDS made it reasonably\\n\\nforeseeable that 3,960 horizontal Mancos Shale wells would be drilled, and NEPA\\n\\ntherefore required the BLM to consider the cumulative impacts of those wells in the\\n\\nEAs it conducted for subsequent horizontal Mancos Shale well APDs.\\n\\n The 2014 RFDS “collect[ed] and analyze[d] geological and engineering\\n\\nevidence[] . . . to determine the potential subsurface development of the Gallup/Mancos\\n\\nplay.” JA1665. Based on this analysis, it estimated that full development of the Mancos\\n\\nShale would result in 3,960 new wells. And, although it predicted “a five[-]year delay in\\n\\nsignificant activity” in the Mancos Shale area “due to unfavorable economics,” it also\\n\\npredicted that well activity would “rapidly increase” once the economics became more\\n\\nfavorable. JA1662.\\n\\n The BLM itself has relied on RFDSs to define the scope of “reasonably\\n\\n\\n\\n 14\\n EA 2012-0268 was completed in June 2012, more than two years before the\\n2014 RFDS issued. Appellants’ cumulative-impacts argument relies entirely on the\\n2014 RFDS’s prediction of 3,960 horizontal Mancos Shale wells. Because\\nAppellants provide no reason other than the 2014 RFDS that the BLM’s NEPA\\nanalysis should have included the environmental impacts from 3,960 horizontal\\nMancos Shale wells, Appellants do not establish that the BLM violated NEPA as to\\nEA 2012-0268.\\n 37\\n\\fforeseeable” actions for the purposes of its cumulative-impacts analyses. For example,\\n\\ntwo of the EAs before us cite to the 2014 RFDS in their discussions of cumulative\\n\\nimpacts. In describing the methodology used to analyze cumulative impacts, EA 2016-\\n\\n0029 and EA 2016-0200/2016-0076 discuss oil and gas development predicted in the\\n\\n2014 RFDS, noting that the 2014 RFDS\\n\\n identified high, moderate, and low potential regions for oil development of\\n the Mancos-Gallup Formation. Within the high potential region, full\\n development would include 5 wells per section, resulting in 1,600\\n completions. Within the moderate potential region, full development\\n would include one well per section, resulting in 330 completions. Within\\n the low potential region, full development would include one well per\\n township, resulting in 30 well completions. Additionally, the [2014 RFDS]\\n predicted 2,000 gas wells could be development [sic] in the northeastern\\n corner of the [BLM’s Farmington Field Office].\\n\\nJA1926; JA2096. The BLM also relied on the 2001 RFDS for projected drilling amounts\\n\\nin the 2003 EIS. The 2003 EIS states that the 2001 RFDS “form[ed] the basis for\\n\\nprojected oil and gas development in the planning area over the next 20 years.” JA769–\\n\\n70. Especially in light of the BLM’s past reliance on the drilling projected in RFDSs, we\\n\\nconclude that once the 2014 RFDS issued, the 3,960 horizontal Mancos Shale wells\\n\\npredicted in that document were “reasonably foreseeable future actions.” 40 C.F.R.\\n\\n§ 1508.7; accord Sierra Club v. Marsh, 976 F.2d 763, 767 (1st Cir. 1992) (“[A]s in other\\n\\nlegal contexts, the terms ‘likely’ and ‘foreseeable,’ as applied to a type of environmental\\n\\nimpact, are properly interpreted as meaning that the impact is sufficiently likely to occur\\n\\nthat a person of ordinary prudence would take it into account in reaching a decision.”).\\n\\nThe BLM therefore needed to consider the cumulative environmental impacts associated\\n\\nwith the reasonably foreseeable 3,960 horizontal Mancos Shale wells when it conducted\\n\\n 38\\n\\fEAs for the challenged APDs.\\n\\n Intervenor Appellees’ arguments do not persuade us otherwise. First, we of\\n\\ncourse acknowledge that “full-field [Mancos Shale] development is not at issue in\\n\\nthis case.” Int. Aples. Br. at 38. But that does not excuse the BLM from NEPA’s\\n\\nrequirement that it “take a ‘hard look’ at the environmental consequences before”\\n\\napproving the challenged APDs. Balt. Gas & Elec. Co., 462 U.S. at 97. And, in this\\n\\ncase, that involved considering the cumulative impacts of the 3,960 reasonably\\n\\nforeseeable horizontal Mancos Shale wells. See 40 C.F.R. §§ 1508.9(b), 1508.7.\\n\\n Second, we reject Intervenor Appellees’ argument that the BLM did not need\\n\\nto consider the cumulative impact of the predicted 3,960 wells because “no operator\\n\\nhas proposed to drill” all of those wells. Int. Aples. Br. at 40. Once the 2014 RFDS\\n\\nissued, it became reasonably foreseeable to the BLM that the projected wells would\\n\\nbe drilled, so the BLM needed to consider the cumulative impact of all those wells,\\n\\neven if the wells were not going to be drilled imminently. 40 C.F.R. § 1508.7\\n\\n(“Cumulative impacts can result from individually minor but collectively significant\\n\\nactions taking place over a period of time.” (emphasis added)).\\n\\n Finally, we reject Intervenor Appellees’ argument that our conclusion here would\\n\\n“automatically foreclose authorization of all individual activities in the [planning] area”\\n\\nonce the BLM initiates an RMP amendment process. Int. Aples. Br. at 42. Rather, our\\n\\ndecision forecloses only those activities with environmental impacts—direct, indirect, or\\n\\ncumulative—that have not been considered in either a site-specific EA or a broader\\n\\nNEPA document to which the EA tiers. But that is the purpose of NEPA: to “require[]\\n\\n 39\\n\\ffederal agencies . . . to analyze environmental consequences before initiating actions that\\n\\npotentially affect the environment.” Bosworth, 443 F.3d at 735–36.\\n\\n We conclude that the 3,960 horizontal Mancos Shale wells predicted in the 2014\\n\\nRFDS were reasonably foreseeable after the 2014 RFDS issued. The BLM therefore had\\n\\nto consider the cumulative impacts of all 3,960 wells when it conducted its site-specific\\n\\nEAs.\\n\\n 2\\n\\n Appellants argue that the air pollution caused by the horizontal Mancos Shale\\n\\nwells will exceed the air pollution amounts considered in the 2003 EIS. In support,\\n\\nAppellants point to a table that purports to “illustrate the total combined impacts of past,\\n\\npresent, and reasonably foreseeable future development.” Aplts. Br. at 43. Although the\\n\\nnumbers in Appellants’ table indicate that horizontal wells have a much greater\\n\\nenvironmental impact than do vertical wells, the numbers Appellants provide for the\\n\\nenvironmental impacts of vertical wells are not supported by the record. More\\n\\nimportantly, the record does not contain the BLM’s complete air pollution analysis, so we\\n\\nare unable to fully evaluate the air pollution argument Appellants make.\\n\\n Appellants’ air pollution argument relies on the following assumptions:15\\n\\n Well Type Construction Time Nox CO VOC PM10\\n (tpy) (tpy) (tpy) (tpy)\\n Vertical 9 days 2.30 0.63 0.20 0.92\\n\\n\\n\\n 15\\n NOx is nitrous oxide; CO is carbon monoxide; VOC is volatile organic\\ncompound; and PM10 is particulate matter at 10 microns. Each is a form of air\\npollution.\\n 40\\n\\f Horizontal 25 days 6.13 1.64 0.55 2.54\\n\\n\\nId. at 44. Although these numbers support the conclusion that horizontal wells have a\\n\\ngreater environmental impact than do vertical wells, these numbers are not supported\\n\\neither by the part of the record to which Appellants cite or by any other part of the record\\n\\nwe could identify.\\n\\n First, Appellants cite to “JA2331–32 ([pages 4-61–4-62 of the] 2003 EIS\\n\\nproviding qualitative assessment of air quality impairment and violations of air\\n\\nstandards)” and “JA2328–29 (emissions estimates based on developing 663 wells per\\n\\nyear)” in support of the numbers they list for air pollution associated with vertical wells.\\n\\nAplts. Br. at 44 n.22. The first cited portion of the 2003 EIS, however, analyzes the\\n\\noverall potential effect of contemplated drilling operations on air quality in the project\\n\\narea. Those pages do not analyze the air pollution contemplated by construction of\\n\\nvertical wells, as Appellants indicate they do. Moreover, there is no discernible\\n\\nconnection between any of the numbers in this cited portion of the 2003 EIS and the\\n\\nnumbers in Appellants’ chart.\\n\\n The same is true of the other portion of the record Appellants cite: JA2328–29\\n\\n(pages 4-58 and 4-59 of the 2003 EIS). That portion of the 2003 EIS provides an\\n\\n“estimation of emissions for each year” under Alternative B.16 JA2328. A table on the\\n\\n\\n 16\\n This portion of the 2003 EIS analyzes emissions associated with Alternative\\nB—which the BLM did not select. Elsewhere, the 2003 EIS notes that air emissions\\nunder Alternative D, the selected alternative, would be “99.7% of that under\\nAlternative B.” JA782. Air emission estimates for Alternative B therefore could\\ninform estimates for Alternative D.\\n 41\\n\\fsecond cited page contains categories that match the categories in Appellants’ chart—\\n\\nVOC, CO, Nox, and PM10. However, the table indicates that it depicts “Project Year 1\\n\\nand Project Year 20 Annual Air Emissions Associated with Gas Production” under\\n\\nAlternative B. JA2329 (emphasis added). The numbers, therefore, do not represent air\\n\\npollution associated with vertical well construction. And, once again, there is no\\n\\ndiscernible connection between any air pollution numbers in these pages and the vertical-\\n\\nwell numbers in Appellants’ table.\\n\\n Finally, Appellants indicate that the well construction time for a vertical well is\\n\\nnine days. Again, nothing in the part of the record to which Appellants cite supports that\\n\\nassertion. However, the 2003 EIS notes elsewhere that “the time to complete individual\\n\\nwells is generally between one and two months.” JA2287 (emphasis added). This\\n\\nindicates that Appellants’ cited nine days is incorrect.\\n\\n More fundamentally, the record does not contain crucial aspects of the BLM’s\\n\\nNEPA analysis. Specifically, the record does not include the BLM’s complete air\\n\\npollution analysis. The 2003 EIS notes that “Appendix J includes the emissions estimates\\n\\nfor Alternative D.” JA2378. Appendix J also “presents data used to estimate annual air\\n\\nemissions” for each alternative. JA834. But Appendix J is not in the record.\\n\\n Further, from our review, no other part of the record includes data that would\\n\\nfacilitate the comparison on which Appellants rely: the gross amount of NOx, CO, VOC,\\n\\nand PM10 created in the construction of a single vertical well. Those numbers might be in\\n\\nAppendix J—and they might even be the numbers Appellants include in their chart—but\\n\\nwe have no way of determining that because Appendix J is not in the record. We\\n\\n 42\\n\\ftherefore cannot evaluate whether, as Appellants argue, “the 3,945 existing vertically\\n\\ndrilled and the reasonably foreseeable 3,960 horizontally drilled Mancos Shale wells\\n\\nexceed the total impacts predicted in the 2003 EIS.” Aplts. Br. at 45.\\n\\n Appellants do not include the BLM’s complete analysis of air pollution in the\\n\\n2003 EIS, and therefore offer no way to compare the impacts contemplated by the 2003\\n\\nEIS with the impacts that could result from 3,960 horizontal Mancos Shale wells. The\\n\\nBLM’s NEPA analysis “is entitled to the presumption of regularity,” Stiles, 654 F.3d at\\n\\n1045, and Appellants have not carried their burden of demonstrating that the BLM acted\\n\\narbitrarily or capriciously.\\n\\n 3\\n\\n Appellants also argue that the total water used for drilling 3,960 horizontal\\n\\nMancos Shale wells will exceed the water use contemplated in the 2003 EIS, and the\\n\\nBLM therefore abused its discretion in tiering the EAs to the 2003 EIS, issuing FONSIs,\\n\\nand approving APDs. We agree with Appellants that, as to five challenged EAs, the\\n\\nBLM did not consider the cumulative water use associated with the 3,960 reasonably\\n\\nforeseeable horizontal Mancos Shale wells. Therefore, as to these five EAs, the BLM’s\\n\\nissuance of FONSIs and approval of APDs was arbitrary and capricious.\\n\\n Appellants’ water-resources argument, like their air-pollution argument, is based\\n\\nlargely on calculations in their comparison table. First, Appellants state that drilling a\\n\\nsingle horizontal well will use 1,020,000 gallons of water. In contrast, Appellants assert\\n\\nthe 2003 EIS predicted that drilling a single vertical well would use 283,500 gallons of\\n\\nwater. Appellants then multiply each of these numbers by the total number of wells\\n\\n 43\\n\\f(3,960 reasonably foreseeable horizontal wells; 3,945 already drilled vertical wells) and\\n\\narrive at a total water consumption amount of over 5 billion gallons of water. According\\n\\nto Appellants, the 2003 EIS contemplated total water use of just over 2.8 billion gallons.\\n\\nTherefore, argue Appellants, when the 3,960 reasonably foreseeable horizontal Mancos\\n\\nShale wells are taken into account, the projected water use increases by 82% over what\\n\\nthe 2003 EIS considered.\\n\\n Although we note some discrepancies between Appellants’ cited numbers and\\n\\nthe numbers in the record,17 we reject Federal Appellees’ argument that Appellants’\\n\\nwater-resources calculations “do not withstand scrutiny.” Fed. Aples. Br. at 33. Federal\\n\\nAppellees argue generally that water use could be decreased through “new strategies and\\n\\ntechnologies,” Fed. Aples. Br. at 35 (quotations omitted), but they do not point us to any\\n\\npart of the record that contradicts Appellants’ assertions that the cumulative water use\\n\\nassociated with the reasonably foreseeable 3,960 wells dramatically exceeds the total\\n\\n\\n 17\\n First, the average of 6,750 barrels of water per well on which Appellants\\nbase their vertical well calculations is the figure contemplated under Alternative A,\\nwhich the BLM did not select. For Alternative D, the BLM’s chosen alternative, the\\n2003 EIS predicted total water use of 7,000 acre-feet or an average of 0.70 acre-feet\\n(228,095 gallons) of water for each well.\\n And although the 2014 RFDS noted an average water use of 3.13 acre-feet\\n(1.02 million gallons) for the 55 horizontal wells that had reported water use\\nnumbers, other figures to which Appellants cite in their water use comparison are not\\nsupported by the record. Specifically, Appellants indicate that three EAs “calculat[e]\\n966,000 gallons per horizontal well.” Aplts. Br. at 44 n.21. Each of these three EAs,\\nhowever, estimate that “23,000 barrels of useable water would be required to drill\\neach well,” but “approximately 10,000 to 11,000 barrels would be recovered for\\nreuse,” resulting in a net water use for these wells of 12,000 to 13,000 barrels, or\\n504,000 to 546,000 gallons. JA1071, JA1075, JA1083. 966,000 gallons is the\\namount of water in 23,000 barrels, indicating that Appellants ignored the EAs’\\nprediction that water would be recovered for reuse.\\n 44\\n\\fwater use contemplated in the 2003 EIS. We conclude that, regardless of the minor\\n\\ninaccuracies in their calculations, Appellants have established that the difference between\\n\\nthe water use contemplated in the 2003 EIS and the water use associated with drilling the\\n\\nreasonably foreseeable horizontal Mancos Shale wells is more than a “mere[] flyspeck.”\\n\\nUtahns for Better Transp., 305 F.3d at 1163.\\n\\n None of the five EAs before us considered the cumulative impacts of the water use\\n\\nassociated with all 3,960 reasonably foreseeable horizontal Mancos Shale wells. The\\n\\nonly discussion of water resources in EA 2015-0036 is as follows:\\n\\n [T]he operator would follow ‘Pit Rule’ guidelines and Onshore Order\\n No. 1. Drilling operations would utilize a closed-loop system. Drilling\\n of the horizontal lateral would be accomplished with water-based mud.\\n All cuttings would be hauled to a commercial disposal facility or land\\n farm.\\n\\nJA1241. Three other EAs (EA 2015-0066, EA 2016-0029, and EA 2016-0200/2016-\\n\\n0076) all list “Groundwater Resources” as an “issue considered but not analyzed.”\\n\\nJA1305; JA1911–12; JA2082–83. Each of these EAs discusses the general process\\n\\nfor hydraulic fracturing, then concludes that “[n]o impacts to surface water or\\n\\nfreshwater-bearing groundwater aquifers are expected to occur from hydraulic\\n\\nfracturing of these proposed wells.” JA1912; JA2083; accord JA1306 (containing the\\n\\nsame substantive analysis with slightly different wording). EAs 2015-0036, 2015-\\n\\n0066, 2016-0029, and 2016-0200/2016-0076 contain no discussion of the cumulative\\n\\nimpacts related to water resources.\\n\\n EA 2014-0272 is the only EA that contains any discussion of the cumulative\\n\\nimpacts on water resources. Its cumulative-impact analysis states:\\n\\n 45\\n\\f Reasonably foreseeable development within the Largo sub-\\n watershed may include an estimated additional 1,811 oil and gas wells and\\n related facilities. Surface-disturbing activities that would be associated\\n with these actions may affect an estimated 6,756 acres ([2003 EIS], page 4-\\n 7). The [2003 EIS] determined that the primary cumulative impacts on\\n water quality would result from surface disturbance, which would generate\\n increased sediment yields ([2003 EIS] pages 4-123 and 4-124). Cumulative\\n effects to water resources from the proposed action would be maximized\\n shortly after construction begins and would decrease over time as\\n reclamation efforts progress.\\n\\n The proposed action would cumulatively contribute approximately\\n 20.0 acres of long-term disturbance in the watershed. Cumulative impacts\\n to surface waters would be related to short-term sedimentation or flow\\n changes. Surface-disturbing activities other than the proposed action that\\n may cause accelerated erosion include—but are not limited to—\\n construction of roads, other facilities, and installation of trenches for\\n utilities; road maintenance such as grading or ditch cleaning; public\\n recreational activities; vegetation manipulation and management activities;\\n prescribed and natural fires; and livestock grazing.\\n\\nJA1141. This analysis of the cumulative impacts on water resources does not address the\\n\\nwater consumption associated with the 3,960 reasonably foreseeable Mancos Shale wells.\\n\\n As to these five EAs, the BLM was required to, but did not, consider the\\n\\ncumulative impacts on water resources associated with drilling the 3,960 reasonably\\n\\nforeseeable horizontal Mancos Shale wells.18 The BLM therefore acted arbitrarily and\\n\\ncapriciously in issuing FONSIs and approving APDs associated with these EAs.\\n\\n Federal Appellees make two additional arguments in support of the BLM’s NEPA\\n\\nanalysis, both of which we reject.\\n\\n\\n\\n\\n 18\\n All five EAs referenced the 2003 EIS in their analysis of the cumulative\\nimpacts associated with air pollution, but not water use.\\n 46\\n\\f Federal Appellees first argue that Appellants advocate “too narrow a definition of\\n\\ncumulative impact—one that would require specific, quantitative measurements of all\\n\\npotential effects.” Fed. Aples. Br. at 33. Instead, argue Federal Appellees, the 2003 EIS\\n\\nanalyzed cumulative impacts via a “broad, qualitative approach . . . consistent with the\\n\\npurpose of [a] programmatic EIS.” Id. This argument fails because the record indicates\\n\\nthat (1) the BLM did quantify the cumulative water-resources impacts of proposed\\n\\ndrilling in the 2003 EIS, (2) the BLM could have quantified the cumulative water-\\n\\nresources impacts of the horizontal Mancos Shale wells, and (3) water use is an important\\n\\naspect of the environmental impacts associated with well drilling.\\n\\n First, the 2003 EIS quantified the total amount of water required for drilling\\n\\noperations in each considered alternative. Second, four of the five EAs we consider also\\n\\nincluded a quantitative measure of the amount of water the drilling operations for the\\n\\nproposed APDs would use. Finally, the 2003 EIS acknowledged that “[t]he primary\\n\\nissues and concerns regarding water resource problems caused by oil and gas\\n\\ndevelopment involve . . . water consumption and use.” JA2283. Likewise, the 2014\\n\\nRFDS noted that “[t]he development of the Mancos play will require additional fresh\\n\\nwater for stimulation purposes,” and acknowledged that “horizontal completions . . .\\n\\nrequire large volumes of water for hydraulic fracturing.” JA1686.\\n\\n We therefore reject Federal Appellees’ argument that the BLM could conduct an\\n\\nadequate cumulative-impacts analysis without quantifying the amount of reasonably\\n\\nforeseeable water use. The BLM had non-speculative figures that it could use to quantify\\n\\nthe cumulative impact of the drilling, and the water-resources impacts were important.\\n\\n 47\\n\\fThe BLM was therefore required to consider those impacts to comply with NEPA. See\\n\\nWyoming v. USDA, 661 F.3d at 1253 (rejecting the argument that an EIS failed to\\n\\nadequately consider cumulative impacts because “cumulative impacts that are too\\n\\nspeculative or hypothetical to meaningfully contribute to NEPA’s goals of public\\n\\ndisclosure and informed decisionmaking need not be considered”); Utah Envtl. Congress\\n\\nv. Troyer, 479 F.3d 1269, 1280 (10th Cir. 2007) (“An agency’s decision will be deemed\\n\\narbitrary and capricious if the agency entirely failed to consider an important aspect of\\n\\nthe problem[] . . . . [or] failed to base its decision on consideration of the relevant factors .\\n\\n. . .” (internal quotations and alterations omitted)).\\n\\n We also reject Federal Appellees argument that “the site-specific APD EAs\\n\\naddressed cumulative drilling effects that differ in type and magnitude from those\\n\\nexamined in the” 2003 EIS. Fed. Aples. Br. at 37. As discussed, the record indicates\\n\\notherwise. None of the five EAs we consider contain any analysis of the cumulative\\n\\nimpact to water resources from the 3,960 reasonably foreseeable horizontal Mancos Shale\\n\\nwells. And the record supports the conclusion that the water use associated with those\\n\\n3,960 wells far exceeds the water use considered in the 2003 EIS. The 2003 EIS’s water-\\n\\nresources analysis was therefore not “sufficiently comprehensive or adequate” to support\\n\\nthe proposed drilling, and the EAs were required to “provide any necessary analysis.” 43\\n\\nC.F.R. § 46.140(b). Because they did not, the BLM violated NEPA.\\n\\n Appellants have established that the water use associated with drilling the 3,960\\n\\nreasonably foreseeable horizontal Mancos Shale wells exceeded the water use\\n\\ncontemplated in the 2003 EIS in a way that made the BLM’s failure to consider the\\n\\n 48\\n\\fcumulative water impacts “significant enough to defeat the goals of informed\\n\\ndecisionmaking and informed public comment.” Utahns for Better Transp, 305 F.3d at\\n\\n1163. We conclude that the BLM acted arbitrarily and capriciously in issuing FONSIs\\n\\nand approving APDs associated with EAs 2014-0272, 2015-0036, 2015-0066, 2016-\\n\\n0029, and 2016-0200/2016-0076.\\n\\n VII\\n\\n Because we conclude that the BLM violated NEPA, we remand to the district\\n\\ncourt with instructions to vacate the FONSIs and APDs associated with EAs 2014-0272,\\n\\n2015-0036, 2015-0066, 2016-0029, and 2016-0200/2016-0076, and to remand those EAs\\n\\nto the BLM to conduct a proper NEPA analysis.\\n\\n “Under the APA, courts ‘shall’ ‘hold unlawful and set aside agency action’\\n\\nthat is found to be arbitrary or capricious.” WildEarth Guardians v. U.S. Bureau of\\n\\nLand Mgmt., 870 F.3d 1222, 1239 (10th Cir. 2017) (quoting 5 U.S.C. § 706(2)(A)).\\n\\n“Vacatur of agency action is a common, and often appropriate form of injunctive\\n\\nrelief granted by district courts.” Id. “In the past, we have done all of the following\\n\\nwhen placed in a similar posture: (1) reversed and remanded without instructions, (2)\\n\\nreversed and remanded with instructions to vacate, and (3) vacated agency\\n\\ndecisions.” Id. (collecting cases). And remand to the agency is usually the\\n\\nappropriate decision in this situation. See Middle Rio Grande Conservancy Dist. v.\\n\\nNorton, 294 F.3d 1220, 1225–26 (10th Cir. 2002) (“[A] reviewing court normally\\n\\nremands when it finds an agency’s decision not to conduct an EIS arbitrary or\\n\\ncapricious.”).\\n\\n 49\\n\\f Given our remand instructions to vacate, however, there is no need to also\\n\\n“enjoin any further ground-disturbing activities on the APDs” as Appellants request.\\n\\nAplts. Br. at 51. Once the APDs are vacated, drilling operations will have to stop\\n\\nbecause “[n]o drilling operations, nor surface disturbance preliminary thereto, may be\\n\\ncommenced prior to” APD approval. 43 C.F.R. § 3162.3-1(c). Because vacatur is\\n\\n“sufficient to redress [Appellants’] injury, no recourse to the additional and\\n\\nextraordinary relief of an injunction [is] warranted.” Monsanto Co. v. Geertson Seed\\n\\nFarms, 561 U.S. 139, 166 (2010).\\n\\n VIII\\n\\n For the foregoing reasons, we affirm in part and reverse in part the judgment of the\\n\\ndistrict court.19 We remand to the district court with instructions to vacate the FONSIs\\n\\nand APDs associated with EAs 2014-0272, 2015-0036, 2015-0066, 2016-0029, and\\n\\n2016-0200/2016-0076, and to remand those EAs to the BLM to conduct a proper NEPA\\n\\nanalysis.\\n\\n\\n\\n\\n 19\\n We deny Navajo Allottees Alice Benally, Lilly Comanche, Virginia\\nHarrison, Samuel Harrison, Dolora Hesuse, Verna Martinez, and Lois Phoenix’s\\nmotion to file an amicus brief because “the matters asserted in [Navajo Allottees’\\namicus brief] are [not] relevant to the disposition of the case,” Fed. R. App. P.\\n29(a)(3)(B).\\n 50\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4394597/\", \"author_raw\": \"BRISCOE, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"BRISCOE"},"judge2":{"kind":"string","value":"MCKAY"},"judge3":{"kind":"string","value":"HOLMES"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4617344/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: DINE CITIZENS AGAINST RUINING OUR ENVIRONMENT; San Juan Citizens Alliance; WildEarth Guardians; Natural Resources Defense Council, Plaintiffs-Appellants, v. David BERNHARDT, in His Official Capacity as Acting Secretary of the United States Department of the Interior; United States Bureau of Land Management, an Agency Within the United States Department of the Interior; Neil Kornze, in His Official Capacity as Director of the United States Bureau of Land Management, Defendants-Appellees, and DJR Energy Holdings, LLC; BP America Production Company; American Petroleum Institute; Anschutz Exploration Corporation; Enduring Resources IV, LLC, Intervenor Defendants-Appellees, and ConocoPhillips Company; Burlington Resources Oil & Gas Company LP, Intervenor Defendants. All Pueblo Council of Governors; National Trust for Historic Preservation; Navajo Allottees; Alice Benally; Lilly Comanche; Virginia Harrison ; Samuel Harrison; Dolora Hesuse; Verna Martinez; Loyce Phoenix, Amici Curiae.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-07\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 7, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\nDINE CITIZENS AGAINST RUINING\nOUR ENVIRONMENT; SAN JUAN\nCITIZENS ALLIANCE; WILDEARTH\nGUARDIANS; NATURAL RESOURCES\nDEFENSE COUNCIL,\n\n Plaintiffs - Appellants,\n No. 18-2089\nv.\n\nDAVID BERNHARDT, in his official\ncapacity as Acting Secretary of the United\nStates Department of the Interior; UNITED\nSTATES BUREAU OF LAND\nMANAGEMENT, an agency within the\nUnited States Department of the Interior;\nNEIL KORNZE, in his official capacity as\nDirector of the United States Bureau of\nLand Management,\n\n Defendants - Appellees,\n\nand\n\nDJR ENERGY HOLDINGS, LLC; BP\nAMERICA PRODUCTION COMPANY;\nAMERICAN PETROLEUM INSTITUTE;\nANSCHUTZ EXPLORATION\nCORPORATION; ENDURING\nRESOURCES IV, LLC,\n\n Intervenor Defendants - Appellees,\n\nand\n\nCONOCOPHILLIPS COMPANY;\n\f BURLINGTON RESOURCES OIL &\n GAS COMPANY LP,\n\n Intervenor Defendants.\n\n ------------------------------\n\n ALL PUEBLO COUNCIL OF\n GOVERNORS; NATIONAL TRUST FOR\n HISTORIC PRESERVATION; NAVAJO\n ALLOTTEES; ALICE BENALLY; LILLY\n COMANCHE; VIRGINIA HARRISON;\n SAMUEL HARRISON; DOLORA\n HESUSE; VERNA MARTINEZ; LOYCE\n PHOENIX,\n\n Amici Curiae.\n _________________________________\n\n Appeal from the United States District Court\n for the District of New Mexico\n (D.C. No. 1:15-CV-00209-JB-LF)\n _________________________________\n\nSamantha Ruscavage-Barz, WildEarth Guardians, Santa Fe, New Mexico (Kyle J. Tisdel,\nWestern Environmental Law Center, Taos, New Mexico, with her on the briefs),\nappearing for Appellants.\n\nAvi Kupfer, U.S. Department of Justice, Environment & Natural Resources Division,\nWashington, D.C. (Michael C. Williams, Of Counsel, Attorney-Advisor, Office of the\nSolicitor, U.S. Department of the Interior, Clare M. Boronow, and Mark R. Haag, U.S.\nDepartment of Justice, Environment & Natural Resources Division, Washington, D.C.,\non the brief), for the Defendants-Appellees.\n\nHadassah M. Reimer, Holland & Hart LLP, Jackson, Wyoming (Stephen G. Masciocchi,\nand John F. Shepherd, Holland & Hart LLP, Denver, Colorado, Bradford Berge, Holland\n& Hart LLP, Santa Fe, New Mexico, Rebecca W. Watson, Welborn Sullivan Meck &\nTooley, P.C., Denver, Colorado, Stephen Rosenbaum, Covington & Burling, LLP,\nWashington, D.C., and Jon J. Indall, Comeau Maldegen Templeman & Indall LLP, Santa\nFe, New Mexico, with her on the brief), appearing for Intervenors-Appellees.\n _________________________________\n\nBefore BRISCOE, McKAY, and HOLMES, Circuit Judges.\n\n 2\n\f _________________________________\n\nBRISCOE, Circuit Judge.\n _________________________________\n\n In this case, we are asked to decide whether the Bureau of Land Management\n\nviolated the National Historic Preservation Act (NHPA) and the National\n\nEnvironmental Policy Act (NEPA) in granting more than 300 applications for permits\n\nto drill horizontal, multi-stage hydraulically fracked wells in the Mancos Shale area\n\nof the San Juan Basin in northeastern New Mexico. Appellants1 sued the Secretary of\n\nthe Department of the Interior, the Bureau of Land Management, and the Secretary of\n\nthe BLM, alleging that the BLM authorized the drilling without fully considering its\n\nindirect and cumulative impacts on the environment or on historic properties. The\n\ndistrict court denied Appellants a preliminary injunction, and we affirmed that\n\ndecision in 2016. After merits briefing, the district court concluded that the BLM\n\nhad not violated either NHPA or NEPA and dismissed Appellants’ claims with\n\nprejudice. Appellants now appeal.\n\n We have jurisdiction under 28 U.S.C. § 1291 and affirm in part, reverse in\n\npart, and remand with instructions.\n\n\n\n 1\n Appellants are four environmental advocacy groups: (1) Diné Citizens\nAgainst Ruining Our Environment, comprised of Navajo community activists from\nthe Four Corners region, (2) San Juan Citizens Alliance, concerned with social,\neconomic, and environmental justice in the San Juan Basin, (3) WildEarth Guardians,\nbased in Santa Fe, New Mexico and with members and offices throughout the\nwestern United States, and (4) Natural Resources Defense Council, with members\nthroughout the United States, many of whom reside in New Mexico.\n\n 3\n\f I\n\nWe summarized the underlying facts in the prior appeal.\n\n The San Juan Basin is a large geographic region in the southwestern\nUnited States, including part of New Mexico. Drilling for oil and gas has\noccurred in the Basin for more than sixty years, and the Basin is currently\none of the most prolific sources of natural gas in the country. The Basin\nincludes both public and private lands. Many of the public lands and\nresources fall under the jurisdiction of the Bureau of Land Management’s\nFarmington Field Office in New Mexico, which manages these lands and\nresources under its published Resource Management Plan.\n\n In 2000, the BLM initiated the process of revising its existing RMP,\nwhich had been published in 1988. As part of this process, the BLM\ncontracted with the New Mexico Institute of Mining and Geology to\ndevelop a “reasonably foreseeable development scenario,” or RFDS, to\npredict the foreseeable oil and gas development likely to occur over the\nnext twenty years. Based on historic production data and available\ngeologic and engineering evidence, the RFDS estimated that 9,970 new oil\nand gas wells would be drilled on federally managed lands in the New\nMexico portion of the San Juan Basin during this time period. Of these\nwells, the RFDS estimated that more than forty percent would be “Dakota,\nMancos” gas wells—wells that could produce gas from both the Mancos\ngeologic horizon and the Dakota geologic horizon that lies below it. The\nRFDS estimated that only 180 new oil wells would be drilled in the Mancos\nShale, due to the fact that most reservoirs in the Mancos Shale were\napproaching depletion under then-current technologies, but it noted that\nthere is excellent potential for the Mancos to be further evaluated.\n\n In 2003, the BLM issued its Proposed Resource Management Plan\nand Final Environmental Impact Statement ([2003 EIS]). In this document,\nthe BLM referred to the predictions and analysis contained in the RFDS in\norder to assess four proposed alternatives for managing federal lands in the\nSan Juan Basin, including the “balanced approach” the agency ultimately\ndecided to adopt. Under this balanced approach, the BLM analyzed the\ncumulative impacts of an estimated 9,942 new wells in the San Juan\nBasin—approximately the same number predicted in the 2001 RFDS—by\nlooking at, for instance, the likely air quality impacts from the drilling and\noperation of this many new wells in the region. The [2003 EIS] did not\ndiscuss specific sites or approve any individual wells, although it assumed\nthe majority of new wells would be drilled in the high development area in\nthe northern part of the managed area. The BLM issued its final RMP,\n\n 4\n\f adopting the Alternative D balanced approach, in December 2003.\n\nDiné Citizens Against Ruining Our Env’t v. Jewell (Diné II), 839 F.3d 1276, 1279–80\n\n(10th Cir. 2016) (citations omitted).\n\n Although the 2003 EIS analyzed oil and gas drilling in the San Juan Basin\n\ngenerally, operators wanting to drill new wells in the area must seek and receive approval\n\nfor specific drilling via an application for a permit to drill (APD) submitted to the BLM.\n\nWhen the BLM receives an APD, it prepares an environmental assessment (EA)\n\nexamining the environmental impacts of the proposed drilling. The EA must include an\n\nanalysis of the direct, indirect, and cumulative effects of the proposed drilling. See 40\n\nC.F.R. §§ 1508.7, 1508.8. The EA process results in one of three outcomes: (1) a\n\nconclusion that the proposed action would result in a significant environmental impact,\n\nnecessitating an EIS, (2) a conclusion that the proposed action would not result in a\n\nsignificant environmental impact—a “finding of no significant impact” (FONSI), or (3) a\n\nconclusion that the proposed action will not go forward. 43 C.F.R. § 46.325. Even if a\n\nproposed action will have significant effects, the EA may still result in a FONSI if it is\n\ntiered to a broader environmental analysis that fully analyzed those significant effects.\n\nId. § 46.140(c).\n\n Beginning in 2010, the BLM began receiving APDs for drilling in the Mancos\n\nShale. Development interest in the area increased quickly, and between early 2012 and\n\nApril 2014, seventy new wells were completed in the Mancos Shale area. In 2014,\n\nrecognizing the potential for additional Mancos Shale development, the BLM had a new\n\nRFDS prepared to evaluate the Mancos Shale’s potential for oil and gas development.\n\n 5\n\fThe 2014 RFDS estimates that full development of the Mancos Shale would result in\n\n3,960 new wells.\n\n The 2014 RFDS predicts that new drilling in the Mancos Shale will be done\n\nlargely, if not entirely, by horizontal drilling and multi-stage hydraulic fracturing. “A\n\nhorizontally drilled well starts as a vertical or directional well, but then curves and\n\nbecomes horizontal, or nearly so, allowing the wellbore [i.e., drilled hole] to follow\n\nwithin a rock stratum for significant distances and thus greatly increase the volume of a\n\nreservoir opened by the wellbore.” Wyoming v. Zinke, 871 F.3d 1133, 1137 (10th Cir.\n\n2017) (alteration in original) (quotations omitted). Hydraulic fracturing is a process\n\ndesigned to “maximize the extraction” of oil and gas resources. JA1912. Fluids, usually\n\nwater with chemical additives, “are pumped into a geologic formation at high pressure.”\n\nId. When the pressure “exceeds the rock strength,” it creates or enlarges fractures from\n\nwhich oil and gas can flow more freely. Id. After the fractures are created, a “propping\n\nagent (usually sand) is pumped into the fractures to keep them from closing.” Id.\n\n As we noted previously,\n\n These new drilling techniques have greatly increased access to oil and gas\n reserves that were not previously targeted for development and have given\n rise to much higher levels of development in the Mancos Shale than the\n BLM previously estimated and accounted for. Moreover, horizontal\n drilling and multi-stage fracturing may have greater environmental impacts\n than vertical drilling and older fracturing techniques.\n\nDiné II, 839 F.3d at 1283.\n\n Hydraulic fracturing is common in the San Juan Basin and has been used there in\n\nsome form since the 1950s. Horizontal drilling, however, is relatively new. At the time\n\n\n 6\n\fthe 2003 EIS issued, “[h]orizontal drilling [wa]s possible but not [then] applied in the San\n\nJuan Basin due to poor cost[-]to[-]benefit ratio.” JA746. The environmental impacts\n\nconsidered in the 2003 EIS were therefore based on the impacts associated with vertical\n\ndrilling, not horizontal drilling. But the 2003 EIS noted that “[i]f horizontal drilling\n\nshould prove economically and technically feasible in the future, the next advancement in\n\nhorizontal well technology could be drilling multi-laterals or hydraulic fracturing\n\nhorizontal wells.” Id.\n\n Since the 2003 EIS issued, 3,945 of the 9,942 contemplated vertical wells have\n\nbeen drilled in the San Juan Basin. The BLM continues to receive and approve APDs for\n\nhorizontal Mancos Shale wells. Appellants’ initial petition in the district court\n\nchallenged “at least 130” Mancos Shale APDs approved by the BLM. JA2449. Over the\n\ncourse of this litigation, Appellants amended their petition three times to account for\n\nadditional granted APDs. Their final petition challenged “at least 351” APDs.2 JA2701.\n\n In 2015, Appellants filed their first Petition for Review of Agency Action\n\n(Petition) in district court, challenging the BLM’s issuance of APDs as violative of\n\nNEPA and NHPA. Appellants named as defendants the Secretary of the United\n\nStates Department of the Interior, BLM, and the Director of BLM (collectively,\n\n\n\n 2\n The number of wells at issue on appeal is unclear. Although the district court\nruled that twenty-eight challenged APDs are not final agency action and four others\nare moot—a ruling Appellants do not appeal—Appellants continue to assert that 362\nAPDs (the same number they argued throughout briefing in the district court) are at\nissue. Federal Appellees, for their part, assert that the challenged wells “number[]\n337 as of October 17, 2018,” but cite only to the district court’s opinion in support.\nFed. Aples. Br. at 18.\n 7\n\fFederal Appellees). A group of oil companies (DJR Energy Holdings, LLC, BP\n\nAmerica Production Company, American Petroleum Institute, Anschutz Exploration\n\nCorporation, and Enduring Resources IV, LLC), each of which owns leases or\n\ndrilling permits in the Mancos Shale intervened as defendants (collectively,\n\nIntervenor Appellees).\n\n Appellants moved for a preliminary injunction, which the district court denied.\n\nSee Diné Citizens Against Ruining Our Env’t v. Jewell (Diné I), No. CIV 15-0209,\n\n2015 WL 6393843 (D.N.M. Sept. 16, 2015). This court upheld the denial on appeal.\n\nDiné II, 839 F.3d 1276. In district court, Appellants amended their Petition three\n\ntimes to add additional challenged APDs. Appellants’ operative Third Supplemented\n\nPetition alleges, as relevant on appeal: (1) a NEPA violation for improperly tiering\n\nthe EAs to the 2003 EIS; (2) a NEPA violation for failing to prepare an EIS or\n\nsupplement an existing EIS; and (3) a NHPA violation for failing to complete Section\n\n106 consultation. Appellants sought vacatur of all the challenged APDs and an\n\ninjunction against all “future horizontal drilling or hydraulic fracturing in the Mancos\n\nShale” until the BLM complied with NHPA and NEPA. JA2743.\n\n In April 2017, Appellants sought judgment in the district court. On April 23,\n\n2018, the district court ruled against Appellants and dismissed their claims with\n\nprejudice. The district court made the following relevant rulings: (1) Appellants have\n\nstanding to pursue their claims; (2) Appellants do not establish a NEPA violation;\n\nand (3) Appellants do not establish a NHPA violation.\n\n Appellants timely appealed, raising two issues. First, they contend that the\n\n 8\n\fBLM violated NHPA because it “failed to analyze the indirect and cumulative\n\nimpacts of the challenged Mancos Shale drilling permits on cultural sites in the\n\nGreater Chaco Landscape.” Aplts. Br. at 1 (footnote omitted). Second, they argue\n\nthat the BLM violated NEPA because it “failed to analyze the cumulative impacts of\n\nthe challenged Mancos Shale drilling permits on environmental resources in the\n\nGreater Chaco Landscape.” Id. at 2. Appellants seek vacatur of the challenged\n\nAPDs and a permanent injunction against “any further ground-disturbing activities on\n\nthe challenged APDs until BLM complies with the NHPA and NEPA.” Id. at 51.\n\n Federal Appellees assert, as they did in the district court, that Appellants lack\n\nstanding to challenge the relevant agency actions.\n\n II\n\n The BLM is subject to two statutes relevant on appeal: the National Historic\n\nPreservation Act and the National Environmental Policy Act. “NHPA[] . . . is a\n\nprocedural statute requiring government agencies to stop, look, and listen before\n\nproceeding when their action will affect national historical assets.” Coal. of Concerned\n\nCitizens to Make Art Smart v. Fed. Transit Admin. of U.S. Dep’t of Transp. (Concerned\n\nCitizens), 843 F.3d 886, 905 (10th Cir. 2016) (quoting Presidio Historical Ass’n v.\n\nPresidio Trust, 811 F.3d 1154, 1169 (9th Cir. 2016)). NHPA was enacted “to foster\n\nconditions under which our modern society and our historic property can exist in\n\nproductive harmony and fulfill the social, economic, and other requirements of present\n\nand future generations.” 54 U.S.C. § 300101(1).\n\n NEPA is also a procedural statute. It requires agencies to “pause before\n\n 9\n\fcommitting resources to a project and consider the likely environmental impacts of the\n\npreferred course of action as well as reasonable alternatives.” N.M. ex rel. Richardson\n\nv. Bureau of Land Mgmt., 565 F.3d 683, 703 (10th Cir. 2008). NEPA has twin aims:\n\n First, it places upon an agency the obligation to consider every significant\n aspect of the environmental impact of a proposed action. Second, it ensures\n that the agency will inform the public that it has indeed considered\n environmental concerns in its decisionmaking process.\n\nForest Guardians v. U.S. Fish & Wildlife Serv., 611 F.3d 692, 711 (10th Cir. 2010)\n\n(quoting Balt. Gas & Elec. Co. v. Nat. Res. Def. Council, Inc., 462 U.S 87, 97 (1983)).\n\n Neither NEPA nor NHPA “provide a private right of action,” so we review the\n\ntwo decisions as “final agency action[s] under the” APA. Utah Envtl. Cong. v.\n\nRussell, 518 F.3d 817, 823 (10th Cir. 2008). We apply the same standard of review as\n\nthe district court: the familiar “arbitrary and capricious” standard. Richardson, 565 F.3d\n\nat 704–05; 5 U.S.C. § 706(2)(A). An agency’s decision is arbitrary and capricious if the\n\nagency:\n\n (1) entirely failed to consider an important aspect of the problem, (2)\n offered an explanation for its decision that runs counter to the evidence\n before the agency, or is so implausible that it could not be ascribed to a\n difference in view or the product of agency expertise, (3) failed to base\n its decision on consideration of the relevant factors, or (4) made a clear\n error of judgment.\n\nRichardson, 565 F.3d at 704 (citations and quotations omitted). “A presumption of\n\nvalidity attaches to the agency action and the burden of proof rests with [the parties]\n\nwho challenge such action.” Citizens’ Comm. to Save Our Canyons v. Krueger, 513\n\nF.3d 1169, 1176 (10th Cir. 2008) (quoting Colo. Health Care Ass’n v. Colo. Dep’t of\n\nSoc. Servs., 842 F.2d 1158, 1164 (10th Cir. 1988)). Our deference to the agency is\n\n 10\n\f“especially strong where the challenged decisions involve technical or scientific\n\nmatters within the agency’s area of expertise.” Morris v. U.S. Nuclear Reg.\n\nComm’n, 598 F.3d 677, 691 (10th Cir. 2010) (quoting Russell, 518 F.3d at 824).\n\n III\n\n Because standing is jurisdictional, we must first determine whether Appellants\n\nhave standing to bring their claims. The district court concluded that Appellants have\n\nstanding, and we review that determination de novo. S. Utah Wilderness All. v. Palma,\n\n707 F.3d 1143, 1152 (10th Cir. 2013).\n\n When, as here, an organization sues on behalf of its members, the organization has\n\nstanding if:\n\n (a) its members would otherwise have standing to sue in their own right; (b)\n the interests it seeks to protect are germane to the organization’s purpose;\n and (c) neither the claim asserted nor the relief requested requires the\n participation of individual members in the lawsuit.\n\nHunt v. Wash. State Apple Advert. Comm’n, 432 U.S. 333, 343 (1977). Federal\n\nAppelles do not argue that the interests Appellants seek to protect are not germane to the\n\norganizations’ purposes, nor do they argue that the participation of individual members is\n\nrequired.3 Our standing inquiry is therefore limited to whether any of Appellants’\n\nmembers “have standing to sue in their own right.” Id. We conclude that they do.\n\n To establish standing, a plaintiff must show:\n\n (1) it has suffered an “injury in fact” that is (a) concrete and particularized\n\n 3\n Regardless, both of these requirements are met. Each organization has the\ngoal of protecting the environment in some way. And nothing indicates that\nindividual members would need to participate for the court to grant the relief\nAppellants request.\n 11\n\f and (b) actual or imminent, not conjectural or hypothetical; (2) the injury is\n fairly traceable to the challenged action of the defendant; and (3) it is likely,\n as opposed to merely speculative, that the injury will be redressed by a\n favorable decision.\n\nFriends of the Earth v. Laidlaw Envtl. Servs. (TOC), Inc., 528 U.S. 167, 180–81 (2013).\n\nAt the summary judgment stage, Appellants must “set forth by affidavit or other evidence\n\nspecific facts, which for purposes of the summary judgment motion will be taken to be\n\ntrue.” Lujan v. Defs. of Wildlife, 504 U.S. 555, 561 (1992) (citations and quotations\n\nomitted).\n\n A\n\n The injury-in-fact prong of our standing analysis “breaks down into two parts.”\n\nComm. to Save the Rio Hondo v. Lucero, 102 F.3d 445, 449 (10th Cir. 1996).\n\nAppellants must show that (1) “in making its decision without following [NEPA’s]\n\nprocedures, the agency created an increased risk of actual, threatened, or imminent\n\nenvironmental harm,” and (2) “the increased risk of environmental harm injures [the\n\nlitigant’s] concrete interests by demonstrating either its geographical nexus to, or actual\n\nuse of the site of the agency action.” Id. Appellants have satisfied both requirements.\n\n 1\n\n Under NEPA, “an injury of alleged increased environmental risks due to an\n\nagency’s uninformed decisionmaking may be the foundation for injury in fact under\n\nArticle III.” Id. Here, the allegedly uninformed decisions Appellants challenge are the\n\nBLM’s approval of hundreds of APDs in the Mancos Shale without considering the\n\nindirect and cumulative impacts to cultural sites and environmental resources. Aplts. Br.\n\n\n 12\n\fat 1–2. Appellants have sufficiently tied the BLM’s challenged decisions to increased\n\nenvironmental risks.\n\n Eisenfeld, a member of San Juan Citizens and WildEarth, asserts that the “Mancos\n\nShale APD authorizations . . . impact[] the visual landscape, night sky, solitude and quiet,\n\n[and] public health and safety.” JA343. Nichols, a member of WildEarth, states that\n\n“[w]ith the increase in oil and gas development has come light pollution, more truck\n\ntraffic, drilling rigs sticking up from the land, smells, dust, and more industrialization.”\n\nJA615. He asserts that recently,\n\n the impacts of Mancos shale oil development have become more visible,\n offensive, and degrading of [his] recreational enjoyment of public lands in\n the area. The new development has brought more drilling rigs, flaring,\n truck traffic, road building, pipeline construction, the construction and\n operation of more tanks and production facilities, and just overall more oil\n and gas industry presence in the area.\n\nJA607–08. These facts are sufficient to establish “an increased risk of environmental\n\nharm due to [the BLM’s] alleged uninformed decisionmaking,” and they satisfy the first\n\nprong of our injury-in-fact analysis. Lucero, 102 F.3d at 451.\n\n Federal Appellees argue that Appellants fail on this prong of the standing analysis\n\nbecause the 2003 EIS examined the effects of “drilling 9,942 wells using conventional\n\ntechniques,” and Appellants have not shown that the challenged Mancos Shale APDs\n\n“will increase the risk of environmental harm in a manner or to a degree not already\n\nconsidered.” Fed. Aples. Br. at 26. This argument conflates the standing analysis with\n\nthe merits analysis.\n\n As discussed, Appellants have submitted affidavits that show an increase in\n\n\n 13\n\fenvironmental harm from drilling activities in the Mancos Shale area; this satisfies the\n\nfirst prong of our injury-in-fact analysis. Whether that environmental harm is of a\n\nmanner or to a degree not already considered in the 2003 EIS is a question that goes to\n\nthe merits of Appellants’ NEPA claim. Appellants, of course, need not prove the merits\n\nof their claim in order to establish standing. See, e.g., Steel Co. v. Citizens for a Better\n\nEnv’t, 523 U.S. 83, 89 (“It is firmly established in our cases that the absence of a valid\n\n(as opposed to arguable) cause of action does not implicate subject-matter jurisdiction . . .\n\n.”).\n\n 2\n\n Standing “also requires a plaintiff be among the injured.” Lucero, 102 F.3d at\n\n449. Therefore, Appellants “must be able to show that a separate injury to [their]\n\nconcrete, particularized interests flows from the agency’s procedural failure.” Id. (citing\n\nLujan, 504 U.S. at 572). To demonstrate harm to a plaintiff’s concrete interests, the\n\nplaintiff must “establish either its geographic nexus to, or actual use of the site where the\n\nagency will take or has taken action such that it may be expected to suffer the\n\nenvironmental consequences of the [challenged] action.” Id. (quotations omitted).\n\n Appellants’ members’ affidavits show a geographic nexus to the affected areas\n\nsufficient to satisfy the second prong of our injury-in-fact analysis. Eisenfeld states that\n\nhe “regularly visit[s] the greater Chaco region, including areas in and around Counselor,\n\nLybrook, and Nageezi,” and that he “intend[s] to go back [to Nageezi] in May and June\n\n\n\n\n 14\n\fof 2017.”4 JA338. He also states that he has “visited hundreds of well sites in the\n\n[Greater Chaco] area, and ha[s] frequented lands where many other Mancos Shale wells\n\nare in view.” JA342.\n\n Nichols regularly visits the Greater Chaco region “for recreational enjoyment.”\n\nJA348. He describes visiting Pueblo Pintado, Chaco Culture National Historical Park\n\n(Chaco Park), Nageezi, and Pueblo Alto. Nichols “intend[s] to continue visiting the\n\nGreater Chaco region, including [Chaco Park] and its outliers, as well as public lands in\n\nthe region, at least once a year for the foreseeable future,” and had a trip planned for “late\n\nJune 2017.” JA351.\n\n Kendra Pinto, a member of Diné, lives in Twin Pines, New Mexico, which is\n\n“located along Highway 550, at the county line of San Juan and Rio Arriba.” JA617.\n\nBeginning in 2013, she noticed a “major increase in Halliburton trucks along 550, and at\n\nthe intersection of 7900 and 7950, trucks are staging right off the highway and even on\n\nthe county road blocking traffic.” JA618. She “pass[es] through areas that are very\n\npotent in natural gas odors,” and has “seen the giant pillars of fire for the flaring the sites\n\ndo.” JA619. She states that “[t]he lights staged at well sites can be as bright as stadium\n\nlights.” Id.\n\n Deborah Green, a member of NRDC, visits the Chaco Canyon area and Chaco\n\nPark at least once a year. She states that “[o]il and gas leasing and development in the\n\n\n\n 4\n Because “standing is determined at the time the action is brought,” Mink v.\nSuthers, 482 F.3d 1244, 1253 (10th Cir. 2007), it does not affect our standing\nanalysis that these dates are now past.\n 15\n\fChaco Canyon area/region and [Chaco Park] adversely affect[] the quality of [her] visitor\n\nexperience in the area, and if expanded, would do so even more.” JA630. Along\n\nHighway 550, on the way to Chaco Park, Green has experienced\n\n air pollution from gas flares at wells and large amounts of exhaust from the\n oil and gas company trucks and heavy equipment; noise pollution from\n heavy truck traffic; and light pollution when drilling goes on around the\n clock and from gas flares, which are visible from the road for a long\n distance at night.\n\nId.\n\n These affidavits establish that the BLM’s challenged actions impair these\n\nindividuals’ actual, concrete interests because the affiants have a geographical nexus to\n\nand actually use the land in the allegedly affected area.\n\n Federal Appellees argue that the affidavits are insufficient for two reasons. First,\n\nthey contend that Appellants have “challenged 337 individual agency actions,” each of\n\nwhich “gives rise to a distinct claim,” and that Appellants “must establish standing . . . for\n\neach challenged APD approval.” Fed. Aples. Br. at 23. Second, they argue that\n\nAppellants “fail to establish a geographical nexus to the challenged agency actions”\n\nbecause Appellants’ affidavits all refer generally to the “greater Chaco region” or the\n\n“Mancos Shale formation.” Id. at 26–27. Both arguments fail.\n\n As Appellants point out, we have previously rejected similar arguments. In\n\nPalma, the district court held that the plaintiffs did not establish an injury in fact because\n\nthey submitted affidavits that “did not identify specific visits to each of the thirty-nine\n\nleases at issue.” 707 F.3d at 1155. This holding, we concluded, misapplied the law. Id.\n\n“Neither our court nor the Supreme Court has ever required an environmental plaintiff to\n\n 16\n\fshow that it has traversed each bit of land that will be affected by a challenged agency\n\naction.” Id. Rather, “[a] plaintiff who has repeatedly visited a particular site, has\n\nimminent plans to do so again, and whose interest are harmed by a defendant’s conduct\n\nhas suffered injury in fact that is concrete and particularized.” Id. at 1156. In Palma, an\n\norganization’s member’s affidavit was “sufficient” when “[h]e specified areas which he\n\nhas visited, averred that these specific areas will be affected by oil and gas drilling, and\n\nstated his interests will be harmed by such activity.” Id. The affidavits Appellants\n\nsubmitted in this case meet this standard.5\n\n Further, maps in the record indicate the geographic proximity of challenged APD\n\nsites to specific areas referenced in Appellants’ affidavits. Nichols attached to his\n\ndeclaration a map of the area around Chaco Park that shows the proximity of existing and\n\nnew wells to Chaco Park and other locations affiants describe. This and other maps in\n\nthe record indicate that challenged well sites are within twenty miles or less of Chaco\n\nPark, where Nichols and Green recreate; along Highway 550, the road to enter Chaco\n\nPark; and within several miles of Twin Pines, where Pinto lives, and Nageezi, where\n\nEisenfeld and Nichols both recreate.\n\n Furthermore, Appellants in this case challenge the BLM’s alleged failure to\n\n\n 5\n Although we dismissed the appeal in Palma for lack of ripeness, Palma still\ninforms our injury-in-fact determination. Because we concluded that the Palma\nplaintiffs had established a concrete and particularized injury, we went on to consider\n“not whether SUWA is a proper party to challenge BLM’s decision, but when it can\ndo so.” 707 F.3d at 1157. But our determination that the Palma plaintiffs’ harm was\nnot ripe does not render obsolete our conclusion that their harm was sufficiently\nconcrete and imminent. Palma therefore appropriately informs our injury-in-fact\nanalysis here.\n 17\n\fevaluate the indirect and cumulative impacts of the APDs, not merely the direct impacts\n\nof drilling to the area immediately surrounding the wellpads. Although Appellants’\n\nNEPA claim is in the form of challenges to numerous individual APDs, the allegedly\n\naffected area extends beyond the boundaries of the well sites and into the greater Chaco\n\nlandscape. Affiants’ descriptions of environmental harms including “air pollution from\n\ngas flares at wells,” “exhaust from the oil and gas company trucks and heavy equipment,”\n\n“noise pollution from heavy truck traffic,” and “light pollution” from drilling and “gas\n\nflares,” JA630, which they experience as they live and recreate in the affected area, are\n\nsufficient to place Appellants “among the injured.” Lucero, 102 F.3d at 449.\n\n Appellants have shown through their members’ affidavits that some of their\n\nmembers have a geographical nexus to, and actually use, land the BLM has exposed to an\n\nincreased risk of environmental harm due to its alleged uninformed decisionmaking.\n\nAppellants have established an injury in fact for purposes of Article III.\n\n B\n\n To establish causation, an environmental plaintiff “need only trace the risk of\n\nharm to the agency’s alleged failure to follow [NEPA]’s procedures.” Lucero, 102 F.3d\n\nat 452. A NEPA injury “results not from the agency’s decision, but from the agency’s\n\nuninformed decisionmaking.” Id. (first emphasis added).\n\n Federal Appellees argue that Appellants have not shown that “the relief sought—\n\nthe vacatur of BLM’s decisions approving these 337 APDs—will remedy their alleged\n\ninjuries.” Fed. Aples. Br. at 29. They assert that Appellants have not established that\n\ntheir environmental harms were caused by “the 337 challenged permits rather than . . . the\n\n 18\n\fapproximately 23,000 active oil and gas wells in the San Juan Basin that are not the\n\nsubject of this action.” Id. This argument fails.\n\n “In the context of a [NEPA] claim, the injury is the increased risk of\n\nenvironmental harm to concrete interests . . . .” Lucero, 102 F.3d at 451 (emphasis\n\nadded). In this case, Appellants’ asserted injury is the increased risk of environmental\n\nharm from the additional wells, and it is undisputed that BLM has authorized more than\n\n300 additional wells in the Mancos Shale. Appellants have alleged that the BLM did not\n\ncomply with NEPA in granting the challenged APDs, and that its alleged failure resulted\n\nin “the agency’s uninformed decisionmaking” as to these additional wells. Id. at 452.\n\nThis is sufficient to establish causation.\n\n C\n\n Appellants must also establish that it is “likely, as opposed to merely speculative,\n\nthat the injury will be redressed by a favorable decision.” Lujan, 504 U.S. at 561\n\n(quotations omitted). Under NEPA, “a plaintiff need not establish that the ultimate\n\nagency decision would change upon [NEPA] compliance. Rather, the [Plaintiff must\n\nonly show] that its injury would be redressed by a favorable decision requiring”\n\ncompliance with NEPA procedures. Lucero, 102 F.2d at 452 (quotations and citations\n\nomitted). Here, Appellants challenge the BLM’s decision to grant APDs without\n\nconducting the requisite NEPA analysis. A favorable decision ordering compliance with\n\nNEPA’s procedures would “avert the possibility that the [BLM] may have overlooked\n\nsignificant environmental consequences of its actions,” thereby redressing Appellants’\n\nalleged harms. Id. Appellants have established redressability.\n\n 19\n\f Because individual members of Appellants’ organizations have suffered a concrete\n\nand particularized injury in fact that is fairly traceable to the BLM’s alleged failure to\n\ncomply with NEPA and could be redressed by a favorable decision, we conclude that\n\nAppellants have standing.6\n\n IV\n\n Before analyzing the merits of Appellants’ arguments, we first note the dramatic\n\ninsufficiency of the record. Although Appellants challenge more than 300 individual\n\nagency actions, they have provided us with the complete record of the BLM’s\n\ndecisionmaking process for only a few of the challenged actions. We are therefore\n\nunable to evaluate the sufficiency of the BLM’s NHPA and NEPA analyses for the vast\n\nmajority of the challenged actions. See 10th Cir. R. 10.4(A) (“Counsel must designate a\n\nrecord on appeal . . . that is sufficient for considering and deciding the appellate issues.”);\n\nid. at 10.4(B) (“When the party asserting an issue fails to provide a record or appendix\n\nsufficient for considering that issue, the court may decline to consider it.”).\n\n As to NHPA, the record indicates that the BLM considered impacts on historic\n\nproperties in at least three documents for each APD: (1) a Cultural Resource Survey\n\n(CRS), (2) a Record of Review, and (3) a site-specific EA. Therefore, in order to\n\n\n\n 6\n The harms Appellants allege are the same for their NHPA claims (an\nincreased risk of harm to Chaco Park and the surrounding area), and NHPA is also a\nprocedural statute, so the standing analysis for NHPA is the same as for NEPA in this\ncase. Appellants have established standing under NHPA because they allege a\nconcrete and particularized injury in fact that is fairly traceable to the BLM’s alleged\nfailure to comply with NHPA and could be redressed by a favorable decision.\n\n 20\n\fevaluate the sufficiency of the BLM’s NHPA analysis, we would need the complete EA,\n\ncomplete CRS, and complete Record of Review for each challenged APD. The record,\n\nhowever, contains portions of the BLM’s NHPA analysis for only seventeen different\n\nsets of APDs.7 Further, the vast majority of the NHPA analyses in the record are only\n\nseveral-page excerpts, not the entire analysis. The record contains the complete EA,\n\nCRS, and Record of Review for only one set of challenged APDs: Kimbeto Wash Unit\n\nWells 787H, 789H, and 791H.\n\n As to NEPA, the record indicates that the BLM’s NEPA analysis was included in\n\nat least each site-specific EA and the 2003 EIS (to which each of the site-specific EAs\n\ntiered). Therefore, in order to evaluate the sufficiency of the BLM’s NEPA analyses, we\n\nwould need the complete 2003 EIS and the complete EA for each challenged APD. The\n\nrecord, however, only includes portions of twenty-seven EAs. And, as with the NHPA\n\nanalyses, the vast majority of the EAs in the record are several-page excerpts, not the\n\ncomplete EA. From our count, the record contains only six complete EAs: EA 2012-\n\n0268, EA 2014-0272, EA 2015-0036, EA 2015-0066, EA 2016-0029, and EA 2016-\n\n0200/2016-0076. We are therefore able to analyze whether the BLM violated NEPA\n\nonly as to those six EAs.\n\n “[O]ur cases addressing deficiencies in the appendix submitted by an appellant\n\ndefine a guiding principle . . . .” Lincoln v. BNSF Ry. Co., 900 F.3d 1166, 1190 (10th\n\n\n 7\n It appears that many CRSs and Records of Review analyze the impacts on\nhistoric properties for more than one APD. And it appears that most, if not all, EAs\nanalyze the impacts of more than one APD. Regardless, the record on appeal\ncontains far fewer than all of the documents containing the BLM’s NHPA analyses.\n 21\n\fCir. 2018). Even when an appendix is deficient, if “the materials provided by the\n\nappellant permit us to reach a firm and definite conclusion regarding the merits of an\n\nindividual argument or claim within the appeal,” we often will address the argument or\n\nclaim, although our rules do not require us to do so. Id. But if “we are forced to venture\n\na guess as to the merits of an argument or claim, even ‘an informed guess,’ we will\n\nsummarily affirm the district court’s judgment.” Id. (collecting cases).\n\n Applying these principles, we conduct our NHPA and NEPA reviews only as to\n\nthose challenged actions for which we have the BLM’s complete analysis. For NHPA,\n\nwe evaluate the sufficiency of the BLM’s analysis for Kimbeto Wash Unit Wells 787H,\n\n789H, and 791H. For NEPA, we evaluate the sufficiency of the BLM’s analysis for: (1)\n\nEA 2012-0268, (2) EA 2014-0272, (3) EA 2015-0036, (4) EA 2015-0066, (5) EA 2016-\n\n0029, and (6) EA 2016-0200/2016-0076.8 As to all other challenged agency actions, the\n\nrecord “is insufficient to permit assessment of [Appellants’] claim of error,” and we\n\naffirm the district court. Tilton v. Capital Cities/ABC, Inc., 115 F.3d 1471, 1474 (10th\n\nCir. 1997).\n\n\n\n\n 8\n We note that even as to these EAs, it is possible that the record does not\ncontain the BLM’s entire NEPA analysis. See, e.g., JA2143 (stating “Appendix D.\nSurface Reclamation Plan,” but not containing any surface reclamation plan).\nHowever, because we do not identify—and the parties do not point to—any missing\nportion of these EAs relevant to the challenges Appellants raise on appeal, we\nconclude that the record is sufficient for us to evaluate Appellants’ NEPA claims as\nto these EAs.\n 22\n\f V\n\n Appellants contend that the BLM violated NHPA in three ways. First, they assert\n\nthat the BLM arbitrarily defined an area of potential effects (APE) for each APD in a way\n\nthat excluded cultural sites that might be indirectly affected by Mancos Shale\n\ndevelopment. This argument is premised on Appellants’ assertion that the 2014 Protocol\n\nrequired the BLM to set a separate APE for indirect effects, which the BLM did not do.\n\nSecond, Appellants argue that the BLM did not consider the cumulative effects of\n\nMancos Shale development on relevant cultural and historic properties. Finally,\n\nAppellants contend that the BLM failed to consult with the State Historic Preservation\n\nOffice (SHPO) as required by the 2014 Protocol. Each of these arguments fail.\n\n A\n\n Section 106 of NHPA sets forth specific processes federal agencies must perform\n\nto comply with NHPA. See 36 C.F.R. § 800.1(a). In general, the Section 106 process\n\ninvolves four steps. First, the agency defines the APE. 36 C.F.R. § 800.4(a). The APE\n\nis “the geographic area or areas within which an undertaking may directly or indirectly\n\ncause alterations in the character or use of historic properties, if any such properties\n\nexist.” Id. § 800.16(d). “Establishing an [APE] requires a high level of agency expertise,\n\nand as such, the agency’s determination is due a substantial amount of discretion.”\n\nValley Cmty. Pres. Comm’n v. Mineta, 373 F.3d 1078, 1092 (10th Cir. 2004).\n\n After defining the APE, the agency identifies historic properties within the APE.\n\n36 C.F.R. § 800.4(b). A historic property is “any prehistoric or historic district, site,\n\nbuilding, structure, or object included on, or eligible for inclusion on” the National\n\n 23\n\fRegister of Historic Places (NRHP). 54 U.S.C. § 300308. If the agency determines that\n\nno historic properties are present within the APE, it reports that finding and the NHPA\n\nprocess ends. 36 C.F.R. § 800.4(d)(1).\n\n If historic properties are present within the APE, the agency determines whether\n\nthe proposed undertaking will adversely affect those properties. Id. § 800.5. An adverse\n\neffect exists “when an undertaking may alter, directly or indirectly, any of the\n\ncharacteristics of a historic property that qualify the property for inclusion in the [NRHP]\n\nin a manner that would diminish the integrity of the property’s location, design, setting,\n\nmaterials, workmanship, feeling, or association.” Id. § 800.5(a)(1). Adverse effects\n\ninclude “reasonably foreseeable effects caused by the undertaking that may occur later in\n\ntime, be farther removed in distance or be cumulative.” Id. They also include the\n\n“[i]ntroduction of visual, atmospheric[,] or audible elements that diminish the integrity of\n\nthe property’s significant historic features.” Id. § 800.5(a)(2)(v).\n\n If the agency determines that the undertaking may cause an adverse effect on the\n\nhistoric properties within the APE, it must “develop and evaluate alternatives or\n\nmodifications to the undertaking that could avoid, minimize, or mitigate adverse effects\n\non historic properties.” Id. § 800.6(a). The Section 106 process does not demand a\n\nparticular result, however, because “Section 106 is essentially a procedural statute and\n\ndoes not impose a substantive mandate” on the agencies governed by it. Valley Cmty.,\n\n373 F.3d at 1085.\n\n Section 106 authorizes agencies to enter into a “programmatic agreement to\n\ngovern the implementation of a particular program or the resolution of adverse effects\n\n 24\n\ffrom certain complex project situations or multiple undertakings.” 36 C.F.R.\n\n§ 800.14(b). When a governing programmatic agreement is in place, compliance with the\n\nprocedures in that agreement satisfies the agency’s NHPA Section 106 responsibilities\n\nfor all covered undertakings. Id. § 800.14(b)(2)(iii).\n\n The parties agree that two programmatic agreements governed the BLM’s NHPA\n\nanalyses of the APDs in this case: one agreement that went into effect in 2004 (the 2004\n\nProtocol), and one that went into effect in 2014 (the 2014 Protocol). Therefore, we must\n\nresolve whether Appellants have shown that the BLM violated the requirements of the\n\n2014 Protocol9 as to the single challenged APD properly before us. Although the\n\ncompliance requirements for the 2014 Protocol are somewhat different than Section\n\n106’s requirements, the basic NHPA process is the same.\n\n The 2014 Protocol states generally that, “[i]n defining the APE, the BLM will\n\nconsider potential direct, indirect, and cumulative effects to historic properties and their\n\nassociated settings when setting is an important aspect of integrity, as applicable.”\n\nJA1562. Relevant here, the 2014 Protocol states that “[t]he BLM will follow the\n\nestablished guidance on standard direct APEs for certain types of projects in Appendix\n\n\n\n 9\n Although Appellants acknowledge the existence and applicability of the 2004\nProtocol, they make no NHPA arguments under the 2004 Protocol. Federal\nAppellees assert (without citation) that “[a]pproximately 221 of the challenged\ndrilling permits were approved at the time the 2004 Protocol was operative, and\napproximately 163 permits fell under the 2014 Protocol.” Fed. Aples. Br. at 12. All\nof Appellants’ NHPA arguments, however, rely on the 2014 Protocol. Because we\nconclude that Appellants’ NHPA challenge fails for other reasons, we need not\naddress the effect Appellants’ failure to argue that the BLM violated the 2004\nProtocol might otherwise have on Appellants’ NHPA challenges.\n 25\n\fB.” Id. (italics omitted). Appendix B sets a “standard APE” for well pads of “the well\n\npad and construction zone plus 100[] [feet] on each side from the edge of the construction\n\nzone.” JA1594. The 2014 Protocol acknowledges that “[i]n certain circumstances, even\n\nthough an undertaking may have a standard APE . . . , the Field Manager, at the\n\nrecommendation of the cultural resource specialist, may have justification to require a\n\nlarger APE.” Id.\n\n B\n\n Appellants argue that the BLM “failed to account for indirect impacts to cultural\n\nsites, as required by the NHPA and the Protocol.” Aplts. Br. at 30. According to\n\nAppellants, “the Protocol requires BLM to consider a separate APE for indirect effects\n\nwhere ‘[t]he introduction of physical, visual, or audible elements has the potential to\n\naffect the historic setting or use’ of cultural sites ‘where setting is an important aspect of\n\nintegrity.’” Id. at 31 (quoting JA1562). Appellants’ argument fails because the 2014\n\nProtocol merely allows for, it does not require, a separate indirect-effects APE.\n\n The 2014 Protocol acknowledges that “[t]he introduction of physical, visual,\n\naudible, or atmospheric elements has the potential to affect the historic setting or use of\n\nhistoric properties,” and requires the BLM to “take this into account in defining the limits\n\nof an APE for indirect effects.” JA1562 (emphasis added). Under the 2014 Protocol,\n\n“[t]he indirect APE shall include known or suspected historic properties and their\n\nassociated settings where setting is an important aspect of integrity.” Id. The 2014\n\nProtocol continues: “Identification efforts outside of the APE for direct effects shall be at\n\nthe approval of the BLM field manager, taking into account the recommendations of the\n\n 26\n\fBLM cultural resource specialist and the SHPO.” Id. (emphasis added). In other words,\n\nthe BLM need not set—or even consider—a separate indirect-effects APE when\n\n“physical, visual, audible, or atmospheric elements ha[ve] the potential to affect the\n\nhistoric setting or use of historic properties,” as Appellants argue. JA1562. Rather, the\n\n2014 Protocol only requires that the BLM take indirect effects into account as it exercises\n\nits substantial discretion in setting the APE. The 2014 Protocol therefore contains a\n\ndefault presumption that the direct and indirect APE will be the same and, to the extent\n\nthe BLM will attempt to identify historic properties outside the direct-effects APE, those\n\nidentification efforts will be at the approval of the BLM field manager.\n\n Moreover, the CRS, the Record of Review, and the EA for the Kimbeto Wash\n\nUnit wells indicate that the BLM looked to areas far outside the standard direct-effects\n\nAPE to identify cultural properties. The EA includes a fulsome discussion of the\n\npotential for indirect impacts from the proposed project, including an analysis of visual\n\nresources. The EA notes that the proposed action is at least 8.5 miles “from the boundary\n\nof [Chaco Park].” Id. It acknowledges that “small portions of the pipeline fall within”\n\ntwo National Park Service designated Key Observation Points, but concludes that\n\n“[g]iven [the] distance ([over] 11.5 miles) and low profile[,] the pipeline will not be\n\nvisible.” JA1949. The EA notes that the project’s “well pad is within a mile of a few\n\nscattered residences,” but concludes that it is “unlikely that the well pad will be visible\n\nfrom these residences due to area topography.” JA1950. It also states that the “well pad\n\nwill not visible from any designated recreation areas.” Id.\n\n The EA also addresses the project’s potential impact on night skies, noting that\n\n 27\n\f“[l]ight sources associated with drilling an oil and gas well include a light plant or\n\ngenerator, a light on top of the rig, vehicle traffic, and flaring.” JA1951.\n\n The necessity for flaring and the duration of flaring varies widely from well\n to well and is difficult to predict. With the exception of a few yearly\n events, visitors are not allowed access to the canyon rim where the\n proposed action may be seen after sunset, minimizing the chance that\n visitors would see the direct light. While these lights could reduce the\n general darkness of the night sky as seen from [Chaco Park], it is likely the\n impact would be imperceptible.\n\nId. Further, the EA notes that any potential light impacts “would be short-term.” Id.\n\n The CRS and Record of Review also indicate that the BLM looked for historic\n\nsites in an area that extended far beyond the direct-effects APE. The CRS notes that a\n\nrecord search was conducted and “[n]o sites listed on the State Register of Cultural\n\nProperties or the [NRHP we]re located within a 1 mile [sic] of the project area.” JA2173\n\n(emphasis added). The BLM also conducted pedestrian surveys of a 108.01-acre area,\n\nalthough the CRS indicates only 25.76 acres in the APE. [Id.] During the pedestrian\n\nsurveys, “[w]hen cultural material was encountered, it was pin flagged and the\n\narchaeologists began an intensive search of the area to locate other material.” JA2175.\n\nAfter eight “Fieldwork Dates,” forty-six “Survey Person Hours” and thirty-nine\n\n“Recording Person Hours,” the BLM’s NHPA review identified four newly recorded\n\ncultural sites, one previously recorded site, and twelve isolated occurrences of cultural\n\nmaterial. Id. The BLM ultimately determined that three of the five sites were ineligible\n\nfor listing on the NRHP, and two were eligible but avoided. The BLM therefore\n\nrecommended that the project go forward with mitigation requirements, including\n\nemployee education, temporary barriers, and archaeological site monitoring.\n\n 28\n\f The CRS, Record of Review, and EA for the Kimbeto Wash Unit wells indicate\n\nthat the BLM attempted to identify historic properties in an area far outside the standard\n\ndirect-effects APE for well pads, and that the BLM considered the proposed drilling’s\n\npossible visual impacts, including its impact on night skies. Given this analysis,\n\nespecially considering that it far exceeded the analysis required by the 2014 Protocol,\n\nAppellants have failed to establish that the BLM violated NHPA by not adequately\n\nconsidering the indirect effects of the Kimbeto Wash Unit wells.10\n\n C\n\n Appellants also argue that the BLM violated NHPA because it “failed to analyze\n\nthe cumulative effects of developing hundreds of new APDs across this culturally\n\nsignificant landscape.” Aplts. Br. at 38. Appellants’ cumulative-effects argument fails\n\nbecause Appellants identify no historic properties within the APE the BLM set.\n\n In support of their cumulative-effects argument, Appellants cite to 36 C.F.R.\n\n\n\n 10\n Despite the BLM’s extensive NHPA analysis for the Kimbeto Wash Unit\nwells, parts of the record indicate that the BLM may not have considered the\ncumulative and indirect impacts of other challenged APDs so thoroughly. For\nexample, in discussing possible cumulative impacts, some EAs state simply that\n“[t]here would be no negative cumulative impact on cultural resources, as significant\ncultural sites would be avoided.” JA1154; accord JA1267 (same); JA1333 (same).\nDepending on the circumstances—and whether this were indeed the only cumulative\nimpacts analysis the BLM completed—this cursory analysis could be insufficient.\n However, other parts of the record contain more thorough indirect- and\ncumulative-effects analyses. Indeed, the apparent difference in the substance of the\nBLM’s NHPA analyses for different APDs highlights the need to examine each of the\nBLM’s challenged actions individually and with reference to a complete record of the\nBLM’s NHPA analysis. And, of course, we cannot determine that the BLM’s\nanalysis was insufficient for one APD by examining the analysis the BLM conducted\nfor a different APD.\n 29\n\f§ 800.5(a)(1), which states that “[a]dverse effects may include reasonably foreseeable\n\neffects caused by the undertaking that may occur later in time, be farther removed in\n\ndistance or be cumulative.” This regulation, however, addresses the BLM’s application\n\nof “the criteria of adverse effect to historic properties within the [APE].” 36 C.F.R.\n\n§ 800.5(a) (emphasis added). In other words, the cited language simply means that an\n\nundertaking can have adverse effects on historical properties within the APE, even if the\n\nundertaking only adversely affects the properties through “reasonably foreseeable effects\n\ncaused by the undertaking that may . . . be cumulative.” Id. § 800.5(a)(1).\n\n Appellants, however, argue that the BLM abused its discretion by failing to\n\nanalyze the cumulative adverse effects horizontal Mancos Shale wells might have “on the\n\nintegrity of the historic setting for any number of cultural sites, [Chaco] Park, and the\n\nGreater Chaco Landscape.” Aplts. Br. at 37. This argument ignores that § 800.5(a)(1)\n\napplies to the BLM’s assessment of adverse effects on “historic properties within the\n\n[APE].” 36 C.F.R. § 800.5(a) (emphasis added). And the record indicates that the APE\n\nfor the Kimbeto Wash Unit wells did not encompass the “cultural sites, [Chaco] Park, and\n\nthe Greater Chaco Landscape,” Aplts. Br. at 37, which Appellants argue would be\n\nnegatively impacted by these cumulative effects.11\n\n In sum, Appellants’ cumulative-effects argument is premised on an APE different\n\n\n\n 11\n Indeed, Appellants criticize this aspect of the BLM’s NHPA process,\narguing that the BLM’s APE definition “resulted in the agency excluding from its\nanalysis all cultural sites likely to be adversely affected by noise, light, and air\npollution.” Aplts. Br. at 30.\n\n 30\n\ffrom the one the BLM defined. Appellants’ argument therefore fails.\n\n D\n\n Appellants also argue that the BLM was required to consult with the SHPO12\n\nbecause defining APEs for the challenged APDs was “complicated or controversial.”\n\nAplts. Br. at 35. In support, Appellants cite the 2014 Protocol’s examples of\n\n“complicated or controversial” projects, contending that the APDs at issue qualify\n\nbecause “‘multiple applicants’ [and] ‘multiple Indian tribes’ are involved.” Id. (quoting\n\nJA1562). Appellants’ SHPO consultation argument fails.\n\n The 2014 Protocol “specifies the manner in which the BLM works with SHPO,”\n\nand “establishes a streamlined consultation process for most BLM undertakings.”\n\nJA1552. It provides that “[t]he BLM will consult with SHPO on undertakings for which\n\na standard APE . . . has not been developed.” JA1562. Appendix B indicates that if the\n\nBLM utilizes a standard APE for an undertaking, the “BLM and SHPO have consulted”\n\nas to that APE. JA1594 (emphasis added). The 2014 Protocol also states that the BLM\n\nwill consult with the SHPO “where the APE is complicated or controversial,” and gives\n\nexamples of situations in which defining the APE may be complicated or controversial:\n\n\n\n\n 12\n Amici All Pueblo Council of Governors and the National Trust for Historic\nPreservation in the United States argue that the BLM did not adequately consult with\nNative American tribes before approving the APDs. Appellants did not make this\nargument in district court, and we decline to consider it for the first time on appeal.\nMcDonald v. Kinder-Morgan, Inc., 287 F.3d 992, 999 (10th Cir. 2002) (“[A]bsent\nextraordinary circumstances, we will not consider arguments raised for the first time\non appeal.”).\n 31\n\f“undertakings involving multiple agencies, multiple states, multiple applicants, and/or\n\nmultiple Indian tribes.” JA1562.\n\n The 2014 Protocol therefore establishes a default presumption that the BLM need\n\nnot consult with the SHPO “on undertakings for which a standard APE” exists, such as\n\nthe undertakings at issue in this case. JA1562. And in this case, the applicability of a\n\nstandard APE also undermines a conclusion that the APE is complicated or controversial.\n\nRather, the existence of a standard APE indicates that the BLM and the SHPO anticipated\n\nthat the BLM would often have to define an APE for activities related to oil and gas\n\ndrilling, such as well pads, pipelines, and roads. And, seeking to “streamline the\n\nconsultation process” for these common undertakings, the BLM and the SHPO\n\ndetermined that a standard APE for these activities would suffice in most circumstances,\n\nand BLM-SHPO consultation in defining the specific APE would be unnecessary.\n\nJA1552; accord JA1562. We therefore reject Appellants’ argument that the BLM abused\n\nits discretion by not consulting with the SHPO.\n\n Appellants fail to carry their burden of establishing that the BLM violated NHPA.\n\nThe BLM’s decision is entitled to a presumption of regularity, and it finds support in the\n\nrecord. Accordingly, we affirm the district court’s dismissal of Appellants’ NHPA claim.\n\n VI\n\n Appellants’ NEPA argument is as follows: the environmental impacts of the\n\nhorizontal Mancos Shale wells are both (1) different in kind from and (2) greater in\n\nmagnitude than those considered in the 2003 EIS. Because of this, the 2003 EIS did not\n\nfully analyze the environmental impacts associated with horizontal Mancos Shale wells,\n\n 32\n\fso the BLM was not authorized to tier the EAs to the 2003 EIS, and the FONSIs the BLM\n\nissued were arbitrary and capricious. We conclude that, as to five EAs, Appellants have\n\ndemonstrated that the BLM needed to—but did not—consider the cumulative impacts of\n\nwater resources associated with the 3,960 reasonably foreseeable horizontal Mancos\n\nShale wells. The BLM’s issuance of FONSIs and approval of APDs associated with\n\nthese EAs was therefore arbitrary and capricious and violated NEPA.\n\n A\n\n NEPA “requires federal agencies . . . to analyze environmental consequences\n\nbefore initiating actions that potentially affect the environment.” Utah Env’t Cong. v.\n\nBosworth, 443 F.3d 732, 735–36 (10th Cir. 2006). To comply with NEPA, agencies\n\nmust prepare a detailed statement of the environmental impact of any “major Federal\n\naction[] significantly affecting the quality of the human environment.” 42 U.S.C.\n\n§ 4332(2)(C).\n\n In conducting its NEPA analysis, a federal agency must prepare, as relevant here,\n\neither “(1) an environmental impact statement [(EIS)], [or] (2) an environmental\n\nassessment [(EA)].” Bosworth, 443 F.3d at 736. An EIS “is required if a proposed\n\naction will ‘significantly affect[] the quality of the human environment.’” Id. (alteration\n\nin original) (quoting 42 U.S.C. § 4332(C)). “If an agency is uncertain whether the\n\nproposed action will significantly affect the environment, it may prepare a considerably\n\nless detailed [EA].” Id.\n\n Although less detailed than an EIS, the EA must still “include brief discussions of\n\nthe need for the proposal, of alternatives . . . , [and] of the environmental impacts of the\n\n 33\n\fproposed action and alternatives.” 40 C.F.R. § 1508.9(b). Among the environmental\n\nimpacts the EA must evaluate are “the cumulative impacts of a project.” WildEarth\n\nGuardians v. U.S. Fish & Wildlife Serv., 784 F.3d 677, 690 (10th Cir. 2015) (quoting\n\nDavis v. Mineta, 302 F.3d 1104, 1125 (10th Cir. 2002) abrogated on other grounds by\n\nDiné Citizens Against Ruining Our Env’t v. Jewell, 839 F.3d 1276 (10th Cir. 2016)).\n\nCumulative impacts are “the impact on the environment which results from the\n\nincremental impact of the action when added to other past, present, and reasonably\n\nforeseeable future actions.” 40 C.F.R. § 1508.7. Cumulative impacts can result from\n\n“individually minor but collectively significant actions taking place over a long period of\n\ntime.” Id.\n\n If, after considering the necessary factors, the agency concludes the action is\n\nunlikely to have a significant environmental impact, it may issue a finding of no\n\nsignificant impact (FONSI) and proceed with the action. 40 C.F.R. § 1508.13. If the\n\nagency reaches the opposite conclusion, before proceeding with the action, it must\n\nprepare an environmental impact statement to thoroughly analyze the action’s predicted\n\nenvironmental impacts, including its direct, indirect, and cumulative impacts. 42 U.S.C.\n\n§ 4332(2)(C); 40 C.F.R. §§ 1508.11, 1508.25. However, even when a proposed action\n\nhas “significant effects,” the BLM may tier13 an EA to an existing EIS—and thereby\n\n\n\n 13\n “Tiering refers to the coverage of general matters in broader environmental\nimpact statements . . . with subsequent narrower statements or environmental\nanalyses . . . incorporating by reference the general discussions and concentrating\nsolely on the issues specific to the statement subsequently prepared.” 40 C.F.R.\n§ 1508.28.\n 34\n\freach a FONSI—if the EIS to which it tiers “fully analyzed those significant effects.” 43\n\nC.F.R. § 46.140(c). But if the “relevant analysis in the [EIS] is not sufficiently\n\ncomprehensive or adequate to support further decisions, the [EA] must explain this and\n\nprovide any necessary analysis.” Id. § 46.140(b).\n\n “The role of a federal court under NEPA is to review the EIS, [or] EA, . . . as the\n\ncase may be, and ‘simply . . . ensure that the agency has adequately considered and\n\ndisclosed the environmental impact of its actions.” Concerned Citizens, 843 F.3d at 902\n\n(third alteration in original) (quoting Wyoming v. U.S. Dep’t of Agric., 661 F.3d 1209,\n\n1256–57 (10th Cir. 2011)). In conducting this review, we apply a “rule of reason\n\nstandard” to determine whether claimed NEPA violations “are merely flyspecks, or are\n\nsignificant enough to defeat the goals of informed decision making and informed public\n\ncomment.” Utahns for Better Transp. v. U.S. Dep’t of Transp., 305 F.3d 1152, 1163\n\n(10th Cir. 2002).\n\n B\n\n Appellants first argue that the challenged APDs cause environmental impacts\n\nqualitatively different from those considered in the 2003 EIS because the APDs authorize\n\ndrilling in the southern portion of the Mancos Shale, while the 2003 EIS “only evaluated\n\ndevelopment in the northern portion.” Aplts. Br. at 42. Appellants’ argument fails\n\nbecause the 2003 EIS evaluated the effects of drilling throughout the entire San Juan\n\nBasin—an area that includes the location of the challenged APDs.\n\n The 2003 EIS was developed to “analyze[] the environmental impacts of oil and\n\ngas leasing and development in the San Juan Basin in New Mexico.” JA767. The\n\n 35\n\f“planning area” addressed in the 2003 EIS “includes all of San Juan County, most of\n\nMcKinley County, western Rio Arriba County, and northwestern Sandoval County.”\n\nJA768. All challenged APDs are within this area.\n\n The 2003 EIS denoted the northeastern portion of the planning area as a “high\n\ndevelopment area” for oil and gas production, but that area was so identified because\n\n“more than 99 percent of the federal oil and gas resources [we]re currently leased” in that\n\narea. JA778. Nothing in the 2003 EIS indicates that the BLM analyzed the\n\nenvironmental impacts of drilling on only the high development area. Indeed, the 2003\n\nEIS’s chapter on the affected environment contains a lengthy discussion of the cultural\n\nresources present in the Chaco Canyon. The record, therefore, does not support\n\nAppellants’ assertion that the challenged APDs are in a geographic area not considered\n\nby the 2003 EIS.\n\n C\n\n Appellants also argue that the BLM has never fully analyzed the cumulative\n\nenvironmental impacts of drilling 3,960 horizontal wells in the Mancos Shale because\n\nthose impacts exceed the environmental impacts evaluated in the 2003 EIS in two\n\nspecific ways: air pollution and water use. As to air pollution, we conclude that\n\nAppellants have not provided us with a record from which we can assess the BLM’s\n\nNEPA analysis. As to water use, we conclude that Appellants have shown that the BLM\n\nnever considered the cumulative impact of the water use associated with the 3,960\n\nreasonably foreseeable horizontal Mancos Shale wells for five specific EAs. We\n\ntherefore reverse the district court’s dismissal of Appellants’ NEPA claims as to EAs\n\n 36\n\f2014-0272, 2015-0036, 2015-0066, 2016-0029, and 2016-0200/2016-0076.14\n\n 1\n\n Appellants’ cumulative-impacts argument relies on one assumption the parties\n\ndispute: that the BLM’s NEPA analysis must consider the impacts associated with all\n\n3,960 wells the 2014 RFDS identified as possible if full-field Mancos Shale\n\ndevelopment occurs. We conclude that the 2014 RFDS made it reasonably\n\nforeseeable that 3,960 horizontal Mancos Shale wells would be drilled, and NEPA\n\ntherefore required the BLM to consider the cumulative impacts of those wells in the\n\nEAs it conducted for subsequent horizontal Mancos Shale well APDs.\n\n The 2014 RFDS “collect[ed] and analyze[d] geological and engineering\n\nevidence[] . . . to determine the potential subsurface development of the Gallup/Mancos\n\nplay.” JA1665. Based on this analysis, it estimated that full development of the Mancos\n\nShale would result in 3,960 new wells. And, although it predicted “a five[-]year delay in\n\nsignificant activity” in the Mancos Shale area “due to unfavorable economics,” it also\n\npredicted that well activity would “rapidly increase” once the economics became more\n\nfavorable. JA1662.\n\n The BLM itself has relied on RFDSs to define the scope of “reasonably\n\n\n\n 14\n EA 2012-0268 was completed in June 2012, more than two years before the\n2014 RFDS issued. Appellants’ cumulative-impacts argument relies entirely on the\n2014 RFDS’s prediction of 3,960 horizontal Mancos Shale wells. Because\nAppellants provide no reason other than the 2014 RFDS that the BLM’s NEPA\nanalysis should have included the environmental impacts from 3,960 horizontal\nMancos Shale wells, Appellants do not establish that the BLM violated NEPA as to\nEA 2012-0268.\n 37\n\fforeseeable” actions for the purposes of its cumulative-impacts analyses. For example,\n\ntwo of the EAs before us cite to the 2014 RFDS in their discussions of cumulative\n\nimpacts. In describing the methodology used to analyze cumulative impacts, EA 2016-\n\n0029 and EA 2016-0200/2016-0076 discuss oil and gas development predicted in the\n\n2014 RFDS, noting that the 2014 RFDS\n\n identified high, moderate, and low potential regions for oil development of\n the Mancos-Gallup Formation. Within the high potential region, full\n development would include 5 wells per section, resulting in 1,600\n completions. Within the moderate potential region, full development\n would include one well per section, resulting in 330 completions. Within\n the low potential region, full development would include one well per\n township, resulting in 30 well completions. Additionally, the [2014 RFDS]\n predicted 2,000 gas wells could be development [sic] in the northeastern\n corner of the [BLM’s Farmington Field Office].\n\nJA1926; JA2096. The BLM also relied on the 2001 RFDS for projected drilling amounts\n\nin the 2003 EIS. The 2003 EIS states that the 2001 RFDS “form[ed] the basis for\n\nprojected oil and gas development in the planning area over the next 20 years.” JA769–\n\n70. Especially in light of the BLM’s past reliance on the drilling projected in RFDSs, we\n\nconclude that once the 2014 RFDS issued, the 3,960 horizontal Mancos Shale wells\n\npredicted in that document were “reasonably foreseeable future actions.” 40 C.F.R.\n\n§ 1508.7; accord Sierra Club v. Marsh, 976 F.2d 763, 767 (1st Cir. 1992) (“[A]s in other\n\nlegal contexts, the terms ‘likely’ and ‘foreseeable,’ as applied to a type of environmental\n\nimpact, are properly interpreted as meaning that the impact is sufficiently likely to occur\n\nthat a person of ordinary prudence would take it into account in reaching a decision.”).\n\nThe BLM therefore needed to consider the cumulative environmental impacts associated\n\nwith the reasonably foreseeable 3,960 horizontal Mancos Shale wells when it conducted\n\n 38\n\fEAs for the challenged APDs.\n\n Intervenor Appellees’ arguments do not persuade us otherwise. First, we of\n\ncourse acknowledge that “full-field [Mancos Shale] development is not at issue in\n\nthis case.” Int. Aples. Br. at 38. But that does not excuse the BLM from NEPA’s\n\nrequirement that it “take a ‘hard look’ at the environmental consequences before”\n\napproving the challenged APDs. Balt. Gas & Elec. Co., 462 U.S. at 97. And, in this\n\ncase, that involved considering the cumulative impacts of the 3,960 reasonably\n\nforeseeable horizontal Mancos Shale wells. See 40 C.F.R. §§ 1508.9(b), 1508.7.\n\n Second, we reject Intervenor Appellees’ argument that the BLM did not need\n\nto consider the cumulative impact of the predicted 3,960 wells because “no operator\n\nhas proposed to drill” all of those wells. Int. Aples. Br. at 40. Once the 2014 RFDS\n\nissued, it became reasonably foreseeable to the BLM that the projected wells would\n\nbe drilled, so the BLM needed to consider the cumulative impact of all those wells,\n\neven if the wells were not going to be drilled imminently. 40 C.F.R. § 1508.7\n\n(“Cumulative impacts can result from individually minor but collectively significant\n\nactions taking place over a period of time.” (emphasis added)).\n\n Finally, we reject Intervenor Appellees’ argument that our conclusion here would\n\n“automatically foreclose authorization of all individual activities in the [planning] area”\n\nonce the BLM initiates an RMP amendment process. Int. Aples. Br. at 42. Rather, our\n\ndecision forecloses only those activities with environmental impacts—direct, indirect, or\n\ncumulative—that have not been considered in either a site-specific EA or a broader\n\nNEPA document to which the EA tiers. But that is the purpose of NEPA: to “require[]\n\n 39\n\ffederal agencies . . . to analyze environmental consequences before initiating actions that\n\npotentially affect the environment.” Bosworth, 443 F.3d at 735–36.\n\n We conclude that the 3,960 horizontal Mancos Shale wells predicted in the 2014\n\nRFDS were reasonably foreseeable after the 2014 RFDS issued. The BLM therefore had\n\nto consider the cumulative impacts of all 3,960 wells when it conducted its site-specific\n\nEAs.\n\n 2\n\n Appellants argue that the air pollution caused by the horizontal Mancos Shale\n\nwells will exceed the air pollution amounts considered in the 2003 EIS. In support,\n\nAppellants point to a table that purports to “illustrate the total combined impacts of past,\n\npresent, and reasonably foreseeable future development.” Aplts. Br. at 43. Although the\n\nnumbers in Appellants’ table indicate that horizontal wells have a much greater\n\nenvironmental impact than do vertical wells, the numbers Appellants provide for the\n\nenvironmental impacts of vertical wells are not supported by the record. More\n\nimportantly, the record does not contain the BLM’s complete air pollution analysis, so we\n\nare unable to fully evaluate the air pollution argument Appellants make.\n\n Appellants’ air pollution argument relies on the following assumptions:15\n\n Well Type Construction Time Nox CO VOC PM10\n (tpy) (tpy) (tpy) (tpy)\n Vertical 9 days 2.30 0.63 0.20 0.92\n\n\n\n 15\n NOx is nitrous oxide; CO is carbon monoxide; VOC is volatile organic\ncompound; and PM10 is particulate matter at 10 microns. Each is a form of air\npollution.\n 40\n\f Horizontal 25 days 6.13 1.64 0.55 2.54\n\n\nId. at 44. Although these numbers support the conclusion that horizontal wells have a\n\ngreater environmental impact than do vertical wells, these numbers are not supported\n\neither by the part of the record to which Appellants cite or by any other part of the record\n\nwe could identify.\n\n First, Appellants cite to “JA2331–32 ([pages 4-61–4-62 of the] 2003 EIS\n\nproviding qualitative assessment of air quality impairment and violations of air\n\nstandards)” and “JA2328–29 (emissions estimates based on developing 663 wells per\n\nyear)” in support of the numbers they list for air pollution associated with vertical wells.\n\nAplts. Br. at 44 n.22. The first cited portion of the 2003 EIS, however, analyzes the\n\noverall potential effect of contemplated drilling operations on air quality in the project\n\narea. Those pages do not analyze the air pollution contemplated by construction of\n\nvertical wells, as Appellants indicate they do. Moreover, there is no discernible\n\nconnection between any of the numbers in this cited portion of the 2003 EIS and the\n\nnumbers in Appellants’ chart.\n\n The same is true of the other portion of the record Appellants cite: JA2328–29\n\n(pages 4-58 and 4-59 of the 2003 EIS). That portion of the 2003 EIS provides an\n\n“estimation of emissions for each year” under Alternative B.16 JA2328. A table on the\n\n\n 16\n This portion of the 2003 EIS analyzes emissions associated with Alternative\nB—which the BLM did not select. Elsewhere, the 2003 EIS notes that air emissions\nunder Alternative D, the selected alternative, would be “99.7% of that under\nAlternative B.” JA782. Air emission estimates for Alternative B therefore could\ninform estimates for Alternative D.\n 41\n\fsecond cited page contains categories that match the categories in Appellants’ chart—\n\nVOC, CO, Nox, and PM10. However, the table indicates that it depicts “Project Year 1\n\nand Project Year 20 Annual Air Emissions Associated with Gas Production” under\n\nAlternative B. JA2329 (emphasis added). The numbers, therefore, do not represent air\n\npollution associated with vertical well construction. And, once again, there is no\n\ndiscernible connection between any air pollution numbers in these pages and the vertical-\n\nwell numbers in Appellants’ table.\n\n Finally, Appellants indicate that the well construction time for a vertical well is\n\nnine days. Again, nothing in the part of the record to which Appellants cite supports that\n\nassertion. However, the 2003 EIS notes elsewhere that “the time to complete individual\n\nwells is generally between one and two months.” JA2287 (emphasis added). This\n\nindicates that Appellants’ cited nine days is incorrect.\n\n More fundamentally, the record does not contain crucial aspects of the BLM’s\n\nNEPA analysis. Specifically, the record does not include the BLM’s complete air\n\npollution analysis. The 2003 EIS notes that “Appendix J includes the emissions estimates\n\nfor Alternative D.” JA2378. Appendix J also “presents data used to estimate annual air\n\nemissions” for each alternative. JA834. But Appendix J is not in the record.\n\n Further, from our review, no other part of the record includes data that would\n\nfacilitate the comparison on which Appellants rely: the gross amount of NOx, CO, VOC,\n\nand PM10 created in the construction of a single vertical well. Those numbers might be in\n\nAppendix J—and they might even be the numbers Appellants include in their chart—but\n\nwe have no way of determining that because Appendix J is not in the record. We\n\n 42\n\ftherefore cannot evaluate whether, as Appellants argue, “the 3,945 existing vertically\n\ndrilled and the reasonably foreseeable 3,960 horizontally drilled Mancos Shale wells\n\nexceed the total impacts predicted in the 2003 EIS.” Aplts. Br. at 45.\n\n Appellants do not include the BLM’s complete analysis of air pollution in the\n\n2003 EIS, and therefore offer no way to compare the impacts contemplated by the 2003\n\nEIS with the impacts that could result from 3,960 horizontal Mancos Shale wells. The\n\nBLM’s NEPA analysis “is entitled to the presumption of regularity,” Stiles, 654 F.3d at\n\n1045, and Appellants have not carried their burden of demonstrating that the BLM acted\n\narbitrarily or capriciously.\n\n 3\n\n Appellants also argue that the total water used for drilling 3,960 horizontal\n\nMancos Shale wells will exceed the water use contemplated in the 2003 EIS, and the\n\nBLM therefore abused its discretion in tiering the EAs to the 2003 EIS, issuing FONSIs,\n\nand approving APDs. We agree with Appellants that, as to five challenged EAs, the\n\nBLM did not consider the cumulative water use associated with the 3,960 reasonably\n\nforeseeable horizontal Mancos Shale wells. Therefore, as to these five EAs, the BLM’s\n\nissuance of FONSIs and approval of APDs was arbitrary and capricious.\n\n Appellants’ water-resources argument, like their air-pollution argument, is based\n\nlargely on calculations in their comparison table. First, Appellants state that drilling a\n\nsingle horizontal well will use 1,020,000 gallons of water. In contrast, Appellants assert\n\nthe 2003 EIS predicted that drilling a single vertical well would use 283,500 gallons of\n\nwater. Appellants then multiply each of these numbers by the total number of wells\n\n 43\n\f(3,960 reasonably foreseeable horizontal wells; 3,945 already drilled vertical wells) and\n\narrive at a total water consumption amount of over 5 billion gallons of water. According\n\nto Appellants, the 2003 EIS contemplated total water use of just over 2.8 billion gallons.\n\nTherefore, argue Appellants, when the 3,960 reasonably foreseeable horizontal Mancos\n\nShale wells are taken into account, the projected water use increases by 82% over what\n\nthe 2003 EIS considered.\n\n Although we note some discrepancies between Appellants’ cited numbers and\n\nthe numbers in the record,17 we reject Federal Appellees’ argument that Appellants’\n\nwater-resources calculations “do not withstand scrutiny.” Fed. Aples. Br. at 33. Federal\n\nAppellees argue generally that water use could be decreased through “new strategies and\n\ntechnologies,” Fed. Aples. Br. at 35 (quotations omitted), but they do not point us to any\n\npart of the record that contradicts Appellants’ assertions that the cumulative water use\n\nassociated with the reasonably foreseeable 3,960 wells dramatically exceeds the total\n\n\n 17\n First, the average of 6,750 barrels of water per well on which Appellants\nbase their vertical well calculations is the figure contemplated under Alternative A,\nwhich the BLM did not select. For Alternative D, the BLM’s chosen alternative, the\n2003 EIS predicted total water use of 7,000 acre-feet or an average of 0.70 acre-feet\n(228,095 gallons) of water for each well.\n And although the 2014 RFDS noted an average water use of 3.13 acre-feet\n(1.02 million gallons) for the 55 horizontal wells that had reported water use\nnumbers, other figures to which Appellants cite in their water use comparison are not\nsupported by the record. Specifically, Appellants indicate that three EAs “calculat[e]\n966,000 gallons per horizontal well.” Aplts. Br. at 44 n.21. Each of these three EAs,\nhowever, estimate that “23,000 barrels of useable water would be required to drill\neach well,” but “approximately 10,000 to 11,000 barrels would be recovered for\nreuse,” resulting in a net water use for these wells of 12,000 to 13,000 barrels, or\n504,000 to 546,000 gallons. JA1071, JA1075, JA1083. 966,000 gallons is the\namount of water in 23,000 barrels, indicating that Appellants ignored the EAs’\nprediction that water would be recovered for reuse.\n 44\n\fwater use contemplated in the 2003 EIS. We conclude that, regardless of the minor\n\ninaccuracies in their calculations, Appellants have established that the difference between\n\nthe water use contemplated in the 2003 EIS and the water use associated with drilling the\n\nreasonably foreseeable horizontal Mancos Shale wells is more than a “mere[] flyspeck.”\n\nUtahns for Better Transp., 305 F.3d at 1163.\n\n None of the five EAs before us considered the cumulative impacts of the water use\n\nassociated with all 3,960 reasonably foreseeable horizontal Mancos Shale wells. The\n\nonly discussion of water resources in EA 2015-0036 is as follows:\n\n [T]he operator would follow ‘Pit Rule’ guidelines and Onshore Order\n No. 1. Drilling operations would utilize a closed-loop system. Drilling\n of the horizontal lateral would be accomplished with water-based mud.\n All cuttings would be hauled to a commercial disposal facility or land\n farm.\n\nJA1241. Three other EAs (EA 2015-0066, EA 2016-0029, and EA 2016-0200/2016-\n\n0076) all list “Groundwater Resources” as an “issue considered but not analyzed.”\n\nJA1305; JA1911–12; JA2082–83. Each of these EAs discusses the general process\n\nfor hydraulic fracturing, then concludes that “[n]o impacts to surface water or\n\nfreshwater-bearing groundwater aquifers are expected to occur from hydraulic\n\nfracturing of these proposed wells.” JA1912; JA2083; accord JA1306 (containing the\n\nsame substantive analysis with slightly different wording). EAs 2015-0036, 2015-\n\n0066, 2016-0029, and 2016-0200/2016-0076 contain no discussion of the cumulative\n\nimpacts related to water resources.\n\n EA 2014-0272 is the only EA that contains any discussion of the cumulative\n\nimpacts on water resources. Its cumulative-impact analysis states:\n\n 45\n\f Reasonably foreseeable development within the Largo sub-\n watershed may include an estimated additional 1,811 oil and gas wells and\n related facilities. Surface-disturbing activities that would be associated\n with these actions may affect an estimated 6,756 acres ([2003 EIS], page 4-\n 7). The [2003 EIS] determined that the primary cumulative impacts on\n water quality would result from surface disturbance, which would generate\n increased sediment yields ([2003 EIS] pages 4-123 and 4-124). Cumulative\n effects to water resources from the proposed action would be maximized\n shortly after construction begins and would decrease over time as\n reclamation efforts progress.\n\n The proposed action would cumulatively contribute approximately\n 20.0 acres of long-term disturbance in the watershed. Cumulative impacts\n to surface waters would be related to short-term sedimentation or flow\n changes. Surface-disturbing activities other than the proposed action that\n may cause accelerated erosion include—but are not limited to—\n construction of roads, other facilities, and installation of trenches for\n utilities; road maintenance such as grading or ditch cleaning; public\n recreational activities; vegetation manipulation and management activities;\n prescribed and natural fires; and livestock grazing.\n\nJA1141. This analysis of the cumulative impacts on water resources does not address the\n\nwater consumption associated with the 3,960 reasonably foreseeable Mancos Shale wells.\n\n As to these five EAs, the BLM was required to, but did not, consider the\n\ncumulative impacts on water resources associated with drilling the 3,960 reasonably\n\nforeseeable horizontal Mancos Shale wells.18 The BLM therefore acted arbitrarily and\n\ncapriciously in issuing FONSIs and approving APDs associated with these EAs.\n\n Federal Appellees make two additional arguments in support of the BLM’s NEPA\n\nanalysis, both of which we reject.\n\n\n\n\n 18\n All five EAs referenced the 2003 EIS in their analysis of the cumulative\nimpacts associated with air pollution, but not water use.\n 46\n\f Federal Appellees first argue that Appellants advocate “too narrow a definition of\n\ncumulative impact—one that would require specific, quantitative measurements of all\n\npotential effects.” Fed. Aples. Br. at 33. Instead, argue Federal Appellees, the 2003 EIS\n\nanalyzed cumulative impacts via a “broad, qualitative approach . . . consistent with the\n\npurpose of [a] programmatic EIS.” Id. This argument fails because the record indicates\n\nthat (1) the BLM did quantify the cumulative water-resources impacts of proposed\n\ndrilling in the 2003 EIS, (2) the BLM could have quantified the cumulative water-\n\nresources impacts of the horizontal Mancos Shale wells, and (3) water use is an important\n\naspect of the environmental impacts associated with well drilling.\n\n First, the 2003 EIS quantified the total amount of water required for drilling\n\noperations in each considered alternative. Second, four of the five EAs we consider also\n\nincluded a quantitative measure of the amount of water the drilling operations for the\n\nproposed APDs would use. Finally, the 2003 EIS acknowledged that “[t]he primary\n\nissues and concerns regarding water resource problems caused by oil and gas\n\ndevelopment involve . . . water consumption and use.” JA2283. Likewise, the 2014\n\nRFDS noted that “[t]he development of the Mancos play will require additional fresh\n\nwater for stimulation purposes,” and acknowledged that “horizontal completions . . .\n\nrequire large volumes of water for hydraulic fracturing.” JA1686.\n\n We therefore reject Federal Appellees’ argument that the BLM could conduct an\n\nadequate cumulative-impacts analysis without quantifying the amount of reasonably\n\nforeseeable water use. The BLM had non-speculative figures that it could use to quantify\n\nthe cumulative impact of the drilling, and the water-resources impacts were important.\n\n 47\n\fThe BLM was therefore required to consider those impacts to comply with NEPA. See\n\nWyoming v. USDA, 661 F.3d at 1253 (rejecting the argument that an EIS failed to\n\nadequately consider cumulative impacts because “cumulative impacts that are too\n\nspeculative or hypothetical to meaningfully contribute to NEPA’s goals of public\n\ndisclosure and informed decisionmaking need not be considered”); Utah Envtl. Congress\n\nv. Troyer, 479 F.3d 1269, 1280 (10th Cir. 2007) (“An agency’s decision will be deemed\n\narbitrary and capricious if the agency entirely failed to consider an important aspect of\n\nthe problem[] . . . . [or] failed to base its decision on consideration of the relevant factors .\n\n. . .” (internal quotations and alterations omitted)).\n\n We also reject Federal Appellees argument that “the site-specific APD EAs\n\naddressed cumulative drilling effects that differ in type and magnitude from those\n\nexamined in the” 2003 EIS. Fed. Aples. Br. at 37. As discussed, the record indicates\n\notherwise. None of the five EAs we consider contain any analysis of the cumulative\n\nimpact to water resources from the 3,960 reasonably foreseeable horizontal Mancos Shale\n\nwells. And the record supports the conclusion that the water use associated with those\n\n3,960 wells far exceeds the water use considered in the 2003 EIS. The 2003 EIS’s water-\n\nresources analysis was therefore not “sufficiently comprehensive or adequate” to support\n\nthe proposed drilling, and the EAs were required to “provide any necessary analysis.” 43\n\nC.F.R. § 46.140(b). Because they did not, the BLM violated NEPA.\n\n Appellants have established that the water use associated with drilling the 3,960\n\nreasonably foreseeable horizontal Mancos Shale wells exceeded the water use\n\ncontemplated in the 2003 EIS in a way that made the BLM’s failure to consider the\n\n 48\n\fcumulative water impacts “significant enough to defeat the goals of informed\n\ndecisionmaking and informed public comment.” Utahns for Better Transp, 305 F.3d at\n\n1163. We conclude that the BLM acted arbitrarily and capriciously in issuing FONSIs\n\nand approving APDs associated with EAs 2014-0272, 2015-0036, 2015-0066, 2016-\n\n0029, and 2016-0200/2016-0076.\n\n VII\n\n Because we conclude that the BLM violated NEPA, we remand to the district\n\ncourt with instructions to vacate the FONSIs and APDs associated with EAs 2014-0272,\n\n2015-0036, 2015-0066, 2016-0029, and 2016-0200/2016-0076, and to remand those EAs\n\nto the BLM to conduct a proper NEPA analysis.\n\n “Under the APA, courts ‘shall’ ‘hold unlawful and set aside agency action’\n\nthat is found to be arbitrary or capricious.” WildEarth Guardians v. U.S. Bureau of\n\nLand Mgmt., 870 F.3d 1222, 1239 (10th Cir. 2017) (quoting 5 U.S.C. § 706(2)(A)).\n\n“Vacatur of agency action is a common, and often appropriate form of injunctive\n\nrelief granted by district courts.” Id. “In the past, we have done all of the following\n\nwhen placed in a similar posture: (1) reversed and remanded without instructions, (2)\n\nreversed and remanded with instructions to vacate, and (3) vacated agency\n\ndecisions.” Id. (collecting cases). And remand to the agency is usually the\n\nappropriate decision in this situation. See Middle Rio Grande Conservancy Dist. v.\n\nNorton, 294 F.3d 1220, 1225–26 (10th Cir. 2002) (“[A] reviewing court normally\n\nremands when it finds an agency’s decision not to conduct an EIS arbitrary or\n\ncapricious.”).\n\n 49\n\f Given our remand instructions to vacate, however, there is no need to also\n\n“enjoin any further ground-disturbing activities on the APDs” as Appellants request.\n\nAplts. Br. at 51. Once the APDs are vacated, drilling operations will have to stop\n\nbecause “[n]o drilling operations, nor surface disturbance preliminary thereto, may be\n\ncommenced prior to” APD approval. 43 C.F.R. § 3162.3-1(c). Because vacatur is\n\n“sufficient to redress [Appellants’] injury, no recourse to the additional and\n\nextraordinary relief of an injunction [is] warranted.” Monsanto Co. v. Geertson Seed\n\nFarms, 561 U.S. 139, 166 (2010).\n\n VIII\n\n For the foregoing reasons, we affirm in part and reverse in part the judgment of the\n\ndistrict court.19 We remand to the district court with instructions to vacate the FONSIs\n\nand APDs associated with EAs 2014-0272, 2015-0036, 2015-0066, 2016-0029, and\n\n2016-0200/2016-0076, and to remand those EAs to the BLM to conduct a proper NEPA\n\nanalysis.\n\n\n\n\n 19\n We deny Navajo Allottees Alice Benally, Lilly Comanche, Virginia\nHarrison, Samuel Harrison, Dolora Hesuse, Verna Martinez, and Lois Phoenix’s\nmotion to file an amicus brief because “the matters asserted in [Navajo Allottees’\namicus brief] are [not] relevant to the disposition of the case,” Fed. R. App. P.\n29(a)(3)(B).\n 50\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: DINE CITIZENS AGAINST RUINING OUR ENVIRONMENT; San Juan Citizens Alliance; WildEarth Guardians; Natural Resources Defense Council, Plaintiffs-Appellants, v. David BERNHARDT, in His Official Capacity as Acting Secretary of the United States Department of the Interior; United States Bureau of Land Management, an Agency Within the United States Department of the Interior; Neil Kornze, in His Official Capacity as Director of the United States Bureau of Land Management, Defendants-Appellees, and DJR Energy Holdings, LLC; BP America Production Company; American Petroleum Institute; Anschutz Exploration Corporation; Enduring Resources IV, LLC, Intervenor Defendants-Appellees, and ConocoPhillips Company; Burlington Resources Oil & Gas Company LP, Intervenor Defendants. All Pueblo Council of Governors; National Trust for Historic Preservation; Navajo Allottees; Alice Benally; Lilly Comanche; Virginia Harrison ; Samuel Harrison; Dolora Hesuse; Verna Martinez; Loyce Phoenix, Amici Curiae.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-07\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 7, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\nDINE CITIZENS AGAINST RUINING\\nOUR ENVIRONMENT; SAN JUAN\\nCITIZENS ALLIANCE; WILDEARTH\\nGUARDIANS; NATURAL RESOURCES\\nDEFENSE COUNCIL,\\n\\n Plaintiffs - Appellants,\\n No. 18-2089\\nv.\\n\\nDAVID BERNHARDT, in his official\\ncapacity as Acting Secretary of the United\\nStates Department of the Interior; UNITED\\nSTATES BUREAU OF LAND\\nMANAGEMENT, an agency within the\\nUnited States Department of the Interior;\\nNEIL KORNZE, in his official capacity as\\nDirector of the United States Bureau of\\nLand Management,\\n\\n Defendants - Appellees,\\n\\nand\\n\\nDJR ENERGY HOLDINGS, LLC; BP\\nAMERICA PRODUCTION COMPANY;\\nAMERICAN PETROLEUM INSTITUTE;\\nANSCHUTZ EXPLORATION\\nCORPORATION; ENDURING\\nRESOURCES IV, LLC,\\n\\n Intervenor Defendants - Appellees,\\n\\nand\\n\\nCONOCOPHILLIPS COMPANY;\\n\\f BURLINGTON RESOURCES OIL &\\n GAS COMPANY LP,\\n\\n Intervenor Defendants.\\n\\n ------------------------------\\n\\n ALL PUEBLO COUNCIL OF\\n GOVERNORS; NATIONAL TRUST FOR\\n HISTORIC PRESERVATION; NAVAJO\\n ALLOTTEES; ALICE BENALLY; LILLY\\n COMANCHE; VIRGINIA HARRISON;\\n SAMUEL HARRISON; DOLORA\\n HESUSE; VERNA MARTINEZ; LOYCE\\n PHOENIX,\\n\\n Amici Curiae.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of New Mexico\\n (D.C. No. 1:15-CV-00209-JB-LF)\\n _________________________________\\n\\nSamantha Ruscavage-Barz, WildEarth Guardians, Santa Fe, New Mexico (Kyle J. Tisdel,\\nWestern Environmental Law Center, Taos, New Mexico, with her on the briefs),\\nappearing for Appellants.\\n\\nAvi Kupfer, U.S. Department of Justice, Environment & Natural Resources Division,\\nWashington, D.C. (Michael C. Williams, Of Counsel, Attorney-Advisor, Office of the\\nSolicitor, U.S. Department of the Interior, Clare M. Boronow, and Mark R. Haag, U.S.\\nDepartment of Justice, Environment & Natural Resources Division, Washington, D.C.,\\non the brief), for the Defendants-Appellees.\\n\\nHadassah M. Reimer, Holland & Hart LLP, Jackson, Wyoming (Stephen G. Masciocchi,\\nand John F. Shepherd, Holland & Hart LLP, Denver, Colorado, Bradford Berge, Holland\\n& Hart LLP, Santa Fe, New Mexico, Rebecca W. Watson, Welborn Sullivan Meck &\\nTooley, P.C., Denver, Colorado, Stephen Rosenbaum, Covington & Burling, LLP,\\nWashington, D.C., and Jon J. Indall, Comeau Maldegen Templeman & Indall LLP, Santa\\nFe, New Mexico, with her on the brief), appearing for Intervenors-Appellees.\\n _________________________________\\n\\nBefore BRISCOE, McKAY, and HOLMES, Circuit Judges.\\n\\n 2\\n\\f _________________________________\\n\\nBRISCOE, Circuit Judge.\\n _________________________________\\n\\n In this case, we are asked to decide whether the Bureau of Land Management\\n\\nviolated the National Historic Preservation Act (NHPA) and the National\\n\\nEnvironmental Policy Act (NEPA) in granting more than 300 applications for permits\\n\\nto drill horizontal, multi-stage hydraulically fracked wells in the Mancos Shale area\\n\\nof the San Juan Basin in northeastern New Mexico. Appellants1 sued the Secretary of\\n\\nthe Department of the Interior, the Bureau of Land Management, and the Secretary of\\n\\nthe BLM, alleging that the BLM authorized the drilling without fully considering its\\n\\nindirect and cumulative impacts on the environment or on historic properties. The\\n\\ndistrict court denied Appellants a preliminary injunction, and we affirmed that\\n\\ndecision in 2016. After merits briefing, the district court concluded that the BLM\\n\\nhad not violated either NHPA or NEPA and dismissed Appellants’ claims with\\n\\nprejudice. Appellants now appeal.\\n\\n We have jurisdiction under 28 U.S.C. § 1291 and affirm in part, reverse in\\n\\npart, and remand with instructions.\\n\\n\\n\\n 1\\n Appellants are four environmental advocacy groups: (1) Diné Citizens\\nAgainst Ruining Our Environment, comprised of Navajo community activists from\\nthe Four Corners region, (2) San Juan Citizens Alliance, concerned with social,\\neconomic, and environmental justice in the San Juan Basin, (3) WildEarth Guardians,\\nbased in Santa Fe, New Mexico and with members and offices throughout the\\nwestern United States, and (4) Natural Resources Defense Council, with members\\nthroughout the United States, many of whom reside in New Mexico.\\n\\n 3\\n\\f I\\n\\nWe summarized the underlying facts in the prior appeal.\\n\\n The San Juan Basin is a large geographic region in the southwestern\\nUnited States, including part of New Mexico. Drilling for oil and gas has\\noccurred in the Basin for more than sixty years, and the Basin is currently\\none of the most prolific sources of natural gas in the country. The Basin\\nincludes both public and private lands. Many of the public lands and\\nresources fall under the jurisdiction of the Bureau of Land Management’s\\nFarmington Field Office in New Mexico, which manages these lands and\\nresources under its published Resource Management Plan.\\n\\n In 2000, the BLM initiated the process of revising its existing RMP,\\nwhich had been published in 1988. As part of this process, the BLM\\ncontracted with the New Mexico Institute of Mining and Geology to\\ndevelop a “reasonably foreseeable development scenario,” or RFDS, to\\npredict the foreseeable oil and gas development likely to occur over the\\nnext twenty years. Based on historic production data and available\\ngeologic and engineering evidence, the RFDS estimated that 9,970 new oil\\nand gas wells would be drilled on federally managed lands in the New\\nMexico portion of the San Juan Basin during this time period. Of these\\nwells, the RFDS estimated that more than forty percent would be “Dakota,\\nMancos” gas wells—wells that could produce gas from both the Mancos\\ngeologic horizon and the Dakota geologic horizon that lies below it. The\\nRFDS estimated that only 180 new oil wells would be drilled in the Mancos\\nShale, due to the fact that most reservoirs in the Mancos Shale were\\napproaching depletion under then-current technologies, but it noted that\\nthere is excellent potential for the Mancos to be further evaluated.\\n\\n In 2003, the BLM issued its Proposed Resource Management Plan\\nand Final Environmental Impact Statement ([2003 EIS]). In this document,\\nthe BLM referred to the predictions and analysis contained in the RFDS in\\norder to assess four proposed alternatives for managing federal lands in the\\nSan Juan Basin, including the “balanced approach” the agency ultimately\\ndecided to adopt. Under this balanced approach, the BLM analyzed the\\ncumulative impacts of an estimated 9,942 new wells in the San Juan\\nBasin—approximately the same number predicted in the 2001 RFDS—by\\nlooking at, for instance, the likely air quality impacts from the drilling and\\noperation of this many new wells in the region. The [2003 EIS] did not\\ndiscuss specific sites or approve any individual wells, although it assumed\\nthe majority of new wells would be drilled in the high development area in\\nthe northern part of the managed area. The BLM issued its final RMP,\\n\\n 4\\n\\f adopting the Alternative D balanced approach, in December 2003.\\n\\nDiné Citizens Against Ruining Our Env’t v. Jewell (Diné II), 839 F.3d 1276, 1279–80\\n\\n(10th Cir. 2016) (citations omitted).\\n\\n Although the 2003 EIS analyzed oil and gas drilling in the San Juan Basin\\n\\ngenerally, operators wanting to drill new wells in the area must seek and receive approval\\n\\nfor specific drilling via an application for a permit to drill (APD) submitted to the BLM.\\n\\nWhen the BLM receives an APD, it prepares an environmental assessment (EA)\\n\\nexamining the environmental impacts of the proposed drilling. The EA must include an\\n\\nanalysis of the direct, indirect, and cumulative effects of the proposed drilling. See 40\\n\\nC.F.R. §§ 1508.7, 1508.8. The EA process results in one of three outcomes: (1) a\\n\\nconclusion that the proposed action would result in a significant environmental impact,\\n\\nnecessitating an EIS, (2) a conclusion that the proposed action would not result in a\\n\\nsignificant environmental impact—a “finding of no significant impact” (FONSI), or (3) a\\n\\nconclusion that the proposed action will not go forward. 43 C.F.R. § 46.325. Even if a\\n\\nproposed action will have significant effects, the EA may still result in a FONSI if it is\\n\\ntiered to a broader environmental analysis that fully analyzed those significant effects.\\n\\nId. § 46.140(c).\\n\\n Beginning in 2010, the BLM began receiving APDs for drilling in the Mancos\\n\\nShale. Development interest in the area increased quickly, and between early 2012 and\\n\\nApril 2014, seventy new wells were completed in the Mancos Shale area. In 2014,\\n\\nrecognizing the potential for additional Mancos Shale development, the BLM had a new\\n\\nRFDS prepared to evaluate the Mancos Shale’s potential for oil and gas development.\\n\\n 5\\n\\fThe 2014 RFDS estimates that full development of the Mancos Shale would result in\\n\\n3,960 new wells.\\n\\n The 2014 RFDS predicts that new drilling in the Mancos Shale will be done\\n\\nlargely, if not entirely, by horizontal drilling and multi-stage hydraulic fracturing. “A\\n\\nhorizontally drilled well starts as a vertical or directional well, but then curves and\\n\\nbecomes horizontal, or nearly so, allowing the wellbore [i.e., drilled hole] to follow\\n\\nwithin a rock stratum for significant distances and thus greatly increase the volume of a\\n\\nreservoir opened by the wellbore.” Wyoming v. Zinke, 871 F.3d 1133, 1137 (10th Cir.\\n\\n2017) (alteration in original) (quotations omitted). Hydraulic fracturing is a process\\n\\ndesigned to “maximize the extraction” of oil and gas resources. JA1912. Fluids, usually\\n\\nwater with chemical additives, “are pumped into a geologic formation at high pressure.”\\n\\nId. When the pressure “exceeds the rock strength,” it creates or enlarges fractures from\\n\\nwhich oil and gas can flow more freely. Id. After the fractures are created, a “propping\\n\\nagent (usually sand) is pumped into the fractures to keep them from closing.” Id.\\n\\n As we noted previously,\\n\\n These new drilling techniques have greatly increased access to oil and gas\\n reserves that were not previously targeted for development and have given\\n rise to much higher levels of development in the Mancos Shale than the\\n BLM previously estimated and accounted for. Moreover, horizontal\\n drilling and multi-stage fracturing may have greater environmental impacts\\n than vertical drilling and older fracturing techniques.\\n\\nDiné II, 839 F.3d at 1283.\\n\\n Hydraulic fracturing is common in the San Juan Basin and has been used there in\\n\\nsome form since the 1950s. Horizontal drilling, however, is relatively new. At the time\\n\\n\\n 6\\n\\fthe 2003 EIS issued, “[h]orizontal drilling [wa]s possible but not [then] applied in the San\\n\\nJuan Basin due to poor cost[-]to[-]benefit ratio.” JA746. The environmental impacts\\n\\nconsidered in the 2003 EIS were therefore based on the impacts associated with vertical\\n\\ndrilling, not horizontal drilling. But the 2003 EIS noted that “[i]f horizontal drilling\\n\\nshould prove economically and technically feasible in the future, the next advancement in\\n\\nhorizontal well technology could be drilling multi-laterals or hydraulic fracturing\\n\\nhorizontal wells.” Id.\\n\\n Since the 2003 EIS issued, 3,945 of the 9,942 contemplated vertical wells have\\n\\nbeen drilled in the San Juan Basin. The BLM continues to receive and approve APDs for\\n\\nhorizontal Mancos Shale wells. Appellants’ initial petition in the district court\\n\\nchallenged “at least 130” Mancos Shale APDs approved by the BLM. JA2449. Over the\\n\\ncourse of this litigation, Appellants amended their petition three times to account for\\n\\nadditional granted APDs. Their final petition challenged “at least 351” APDs.2 JA2701.\\n\\n In 2015, Appellants filed their first Petition for Review of Agency Action\\n\\n(Petition) in district court, challenging the BLM’s issuance of APDs as violative of\\n\\nNEPA and NHPA. Appellants named as defendants the Secretary of the United\\n\\nStates Department of the Interior, BLM, and the Director of BLM (collectively,\\n\\n\\n\\n 2\\n The number of wells at issue on appeal is unclear. Although the district court\\nruled that twenty-eight challenged APDs are not final agency action and four others\\nare moot—a ruling Appellants do not appeal—Appellants continue to assert that 362\\nAPDs (the same number they argued throughout briefing in the district court) are at\\nissue. Federal Appellees, for their part, assert that the challenged wells “number[]\\n337 as of October 17, 2018,” but cite only to the district court’s opinion in support.\\nFed. Aples. Br. at 18.\\n 7\\n\\fFederal Appellees). A group of oil companies (DJR Energy Holdings, LLC, BP\\n\\nAmerica Production Company, American Petroleum Institute, Anschutz Exploration\\n\\nCorporation, and Enduring Resources IV, LLC), each of which owns leases or\\n\\ndrilling permits in the Mancos Shale intervened as defendants (collectively,\\n\\nIntervenor Appellees).\\n\\n Appellants moved for a preliminary injunction, which the district court denied.\\n\\nSee Diné Citizens Against Ruining Our Env’t v. Jewell (Diné I), No. CIV 15-0209,\\n\\n2015 WL 6393843 (D.N.M. Sept. 16, 2015). This court upheld the denial on appeal.\\n\\nDiné II, 839 F.3d 1276. In district court, Appellants amended their Petition three\\n\\ntimes to add additional challenged APDs. Appellants’ operative Third Supplemented\\n\\nPetition alleges, as relevant on appeal: (1) a NEPA violation for improperly tiering\\n\\nthe EAs to the 2003 EIS; (2) a NEPA violation for failing to prepare an EIS or\\n\\nsupplement an existing EIS; and (3) a NHPA violation for failing to complete Section\\n\\n106 consultation. Appellants sought vacatur of all the challenged APDs and an\\n\\ninjunction against all “future horizontal drilling or hydraulic fracturing in the Mancos\\n\\nShale” until the BLM complied with NHPA and NEPA. JA2743.\\n\\n In April 2017, Appellants sought judgment in the district court. On April 23,\\n\\n2018, the district court ruled against Appellants and dismissed their claims with\\n\\nprejudice. The district court made the following relevant rulings: (1) Appellants have\\n\\nstanding to pursue their claims; (2) Appellants do not establish a NEPA violation;\\n\\nand (3) Appellants do not establish a NHPA violation.\\n\\n Appellants timely appealed, raising two issues. First, they contend that the\\n\\n 8\\n\\fBLM violated NHPA because it “failed to analyze the indirect and cumulative\\n\\nimpacts of the challenged Mancos Shale drilling permits on cultural sites in the\\n\\nGreater Chaco Landscape.” Aplts. Br. at 1 (footnote omitted). Second, they argue\\n\\nthat the BLM violated NEPA because it “failed to analyze the cumulative impacts of\\n\\nthe challenged Mancos Shale drilling permits on environmental resources in the\\n\\nGreater Chaco Landscape.” Id. at 2. Appellants seek vacatur of the challenged\\n\\nAPDs and a permanent injunction against “any further ground-disturbing activities on\\n\\nthe challenged APDs until BLM complies with the NHPA and NEPA.” Id. at 51.\\n\\n Federal Appellees assert, as they did in the district court, that Appellants lack\\n\\nstanding to challenge the relevant agency actions.\\n\\n II\\n\\n The BLM is subject to two statutes relevant on appeal: the National Historic\\n\\nPreservation Act and the National Environmental Policy Act. “NHPA[] . . . is a\\n\\nprocedural statute requiring government agencies to stop, look, and listen before\\n\\nproceeding when their action will affect national historical assets.” Coal. of Concerned\\n\\nCitizens to Make Art Smart v. Fed. Transit Admin. of U.S. Dep’t of Transp. (Concerned\\n\\nCitizens), 843 F.3d 886, 905 (10th Cir. 2016) (quoting Presidio Historical Ass’n v.\\n\\nPresidio Trust, 811 F.3d 1154, 1169 (9th Cir. 2016)). NHPA was enacted “to foster\\n\\nconditions under which our modern society and our historic property can exist in\\n\\nproductive harmony and fulfill the social, economic, and other requirements of present\\n\\nand future generations.” 54 U.S.C. § 300101(1).\\n\\n NEPA is also a procedural statute. It requires agencies to “pause before\\n\\n 9\\n\\fcommitting resources to a project and consider the likely environmental impacts of the\\n\\npreferred course of action as well as reasonable alternatives.” N.M. ex rel. Richardson\\n\\nv. Bureau of Land Mgmt., 565 F.3d 683, 703 (10th Cir. 2008). NEPA has twin aims:\\n\\n First, it places upon an agency the obligation to consider every significant\\n aspect of the environmental impact of a proposed action. Second, it ensures\\n that the agency will inform the public that it has indeed considered\\n environmental concerns in its decisionmaking process.\\n\\nForest Guardians v. U.S. Fish & Wildlife Serv., 611 F.3d 692, 711 (10th Cir. 2010)\\n\\n(quoting Balt. Gas & Elec. Co. v. Nat. Res. Def. Council, Inc., 462 U.S 87, 97 (1983)).\\n\\n Neither NEPA nor NHPA “provide a private right of action,” so we review the\\n\\ntwo decisions as “final agency action[s] under the” APA. Utah Envtl. Cong. v.\\n\\nRussell, 518 F.3d 817, 823 (10th Cir. 2008). We apply the same standard of review as\\n\\nthe district court: the familiar “arbitrary and capricious” standard. Richardson, 565 F.3d\\n\\nat 704–05; 5 U.S.C. § 706(2)(A). An agency’s decision is arbitrary and capricious if the\\n\\nagency:\\n\\n (1) entirely failed to consider an important aspect of the problem, (2)\\n offered an explanation for its decision that runs counter to the evidence\\n before the agency, or is so implausible that it could not be ascribed to a\\n difference in view or the product of agency expertise, (3) failed to base\\n its decision on consideration of the relevant factors, or (4) made a clear\\n error of judgment.\\n\\nRichardson, 565 F.3d at 704 (citations and quotations omitted). “A presumption of\\n\\nvalidity attaches to the agency action and the burden of proof rests with [the parties]\\n\\nwho challenge such action.” Citizens’ Comm. to Save Our Canyons v. Krueger, 513\\n\\nF.3d 1169, 1176 (10th Cir. 2008) (quoting Colo. Health Care Ass’n v. Colo. Dep’t of\\n\\nSoc. Servs., 842 F.2d 1158, 1164 (10th Cir. 1988)). Our deference to the agency is\\n\\n 10\\n\\f“especially strong where the challenged decisions involve technical or scientific\\n\\nmatters within the agency’s area of expertise.” Morris v. U.S. Nuclear Reg.\\n\\nComm’n, 598 F.3d 677, 691 (10th Cir. 2010) (quoting Russell, 518 F.3d at 824).\\n\\n III\\n\\n Because standing is jurisdictional, we must first determine whether Appellants\\n\\nhave standing to bring their claims. The district court concluded that Appellants have\\n\\nstanding, and we review that determination de novo. S. Utah Wilderness All. v. Palma,\\n\\n707 F.3d 1143, 1152 (10th Cir. 2013).\\n\\n When, as here, an organization sues on behalf of its members, the organization has\\n\\nstanding if:\\n\\n (a) its members would otherwise have standing to sue in their own right; (b)\\n the interests it seeks to protect are germane to the organization’s purpose;\\n and (c) neither the claim asserted nor the relief requested requires the\\n participation of individual members in the lawsuit.\\n\\nHunt v. Wash. State Apple Advert. Comm’n, 432 U.S. 333, 343 (1977). Federal\\n\\nAppelles do not argue that the interests Appellants seek to protect are not germane to the\\n\\norganizations’ purposes, nor do they argue that the participation of individual members is\\n\\nrequired.3 Our standing inquiry is therefore limited to whether any of Appellants’\\n\\nmembers “have standing to sue in their own right.” Id. We conclude that they do.\\n\\n To establish standing, a plaintiff must show:\\n\\n (1) it has suffered an “injury in fact” that is (a) concrete and particularized\\n\\n 3\\n Regardless, both of these requirements are met. Each organization has the\\ngoal of protecting the environment in some way. And nothing indicates that\\nindividual members would need to participate for the court to grant the relief\\nAppellants request.\\n 11\\n\\f and (b) actual or imminent, not conjectural or hypothetical; (2) the injury is\\n fairly traceable to the challenged action of the defendant; and (3) it is likely,\\n as opposed to merely speculative, that the injury will be redressed by a\\n favorable decision.\\n\\nFriends of the Earth v. Laidlaw Envtl. Servs. (TOC), Inc., 528 U.S. 167, 180–81 (2013).\\n\\nAt the summary judgment stage, Appellants must “set forth by affidavit or other evidence\\n\\nspecific facts, which for purposes of the summary judgment motion will be taken to be\\n\\ntrue.” Lujan v. Defs. of Wildlife, 504 U.S. 555, 561 (1992) (citations and quotations\\n\\nomitted).\\n\\n A\\n\\n The injury-in-fact prong of our standing analysis “breaks down into two parts.”\\n\\nComm. to Save the Rio Hondo v. Lucero, 102 F.3d 445, 449 (10th Cir. 1996).\\n\\nAppellants must show that (1) “in making its decision without following [NEPA’s]\\n\\nprocedures, the agency created an increased risk of actual, threatened, or imminent\\n\\nenvironmental harm,” and (2) “the increased risk of environmental harm injures [the\\n\\nlitigant’s] concrete interests by demonstrating either its geographical nexus to, or actual\\n\\nuse of the site of the agency action.” Id. Appellants have satisfied both requirements.\\n\\n 1\\n\\n Under NEPA, “an injury of alleged increased environmental risks due to an\\n\\nagency’s uninformed decisionmaking may be the foundation for injury in fact under\\n\\nArticle III.” Id. Here, the allegedly uninformed decisions Appellants challenge are the\\n\\nBLM’s approval of hundreds of APDs in the Mancos Shale without considering the\\n\\nindirect and cumulative impacts to cultural sites and environmental resources. Aplts. Br.\\n\\n\\n 12\\n\\fat 1–2. Appellants have sufficiently tied the BLM’s challenged decisions to increased\\n\\nenvironmental risks.\\n\\n Eisenfeld, a member of San Juan Citizens and WildEarth, asserts that the “Mancos\\n\\nShale APD authorizations . . . impact[] the visual landscape, night sky, solitude and quiet,\\n\\n[and] public health and safety.” JA343. Nichols, a member of WildEarth, states that\\n\\n“[w]ith the increase in oil and gas development has come light pollution, more truck\\n\\ntraffic, drilling rigs sticking up from the land, smells, dust, and more industrialization.”\\n\\nJA615. He asserts that recently,\\n\\n the impacts of Mancos shale oil development have become more visible,\\n offensive, and degrading of [his] recreational enjoyment of public lands in\\n the area. The new development has brought more drilling rigs, flaring,\\n truck traffic, road building, pipeline construction, the construction and\\n operation of more tanks and production facilities, and just overall more oil\\n and gas industry presence in the area.\\n\\nJA607–08. These facts are sufficient to establish “an increased risk of environmental\\n\\nharm due to [the BLM’s] alleged uninformed decisionmaking,” and they satisfy the first\\n\\nprong of our injury-in-fact analysis. Lucero, 102 F.3d at 451.\\n\\n Federal Appellees argue that Appellants fail on this prong of the standing analysis\\n\\nbecause the 2003 EIS examined the effects of “drilling 9,942 wells using conventional\\n\\ntechniques,” and Appellants have not shown that the challenged Mancos Shale APDs\\n\\n“will increase the risk of environmental harm in a manner or to a degree not already\\n\\nconsidered.” Fed. Aples. Br. at 26. This argument conflates the standing analysis with\\n\\nthe merits analysis.\\n\\n As discussed, Appellants have submitted affidavits that show an increase in\\n\\n\\n 13\\n\\fenvironmental harm from drilling activities in the Mancos Shale area; this satisfies the\\n\\nfirst prong of our injury-in-fact analysis. Whether that environmental harm is of a\\n\\nmanner or to a degree not already considered in the 2003 EIS is a question that goes to\\n\\nthe merits of Appellants’ NEPA claim. Appellants, of course, need not prove the merits\\n\\nof their claim in order to establish standing. See, e.g., Steel Co. v. Citizens for a Better\\n\\nEnv’t, 523 U.S. 83, 89 (“It is firmly established in our cases that the absence of a valid\\n\\n(as opposed to arguable) cause of action does not implicate subject-matter jurisdiction . . .\\n\\n.”).\\n\\n 2\\n\\n Standing “also requires a plaintiff be among the injured.” Lucero, 102 F.3d at\\n\\n449. Therefore, Appellants “must be able to show that a separate injury to [their]\\n\\nconcrete, particularized interests flows from the agency’s procedural failure.” Id. (citing\\n\\nLujan, 504 U.S. at 572). To demonstrate harm to a plaintiff’s concrete interests, the\\n\\nplaintiff must “establish either its geographic nexus to, or actual use of the site where the\\n\\nagency will take or has taken action such that it may be expected to suffer the\\n\\nenvironmental consequences of the [challenged] action.” Id. (quotations omitted).\\n\\n Appellants’ members’ affidavits show a geographic nexus to the affected areas\\n\\nsufficient to satisfy the second prong of our injury-in-fact analysis. Eisenfeld states that\\n\\nhe “regularly visit[s] the greater Chaco region, including areas in and around Counselor,\\n\\nLybrook, and Nageezi,” and that he “intend[s] to go back [to Nageezi] in May and June\\n\\n\\n\\n\\n 14\\n\\fof 2017.”4 JA338. He also states that he has “visited hundreds of well sites in the\\n\\n[Greater Chaco] area, and ha[s] frequented lands where many other Mancos Shale wells\\n\\nare in view.” JA342.\\n\\n Nichols regularly visits the Greater Chaco region “for recreational enjoyment.”\\n\\nJA348. He describes visiting Pueblo Pintado, Chaco Culture National Historical Park\\n\\n(Chaco Park), Nageezi, and Pueblo Alto. Nichols “intend[s] to continue visiting the\\n\\nGreater Chaco region, including [Chaco Park] and its outliers, as well as public lands in\\n\\nthe region, at least once a year for the foreseeable future,” and had a trip planned for “late\\n\\nJune 2017.” JA351.\\n\\n Kendra Pinto, a member of Diné, lives in Twin Pines, New Mexico, which is\\n\\n“located along Highway 550, at the county line of San Juan and Rio Arriba.” JA617.\\n\\nBeginning in 2013, she noticed a “major increase in Halliburton trucks along 550, and at\\n\\nthe intersection of 7900 and 7950, trucks are staging right off the highway and even on\\n\\nthe county road blocking traffic.” JA618. She “pass[es] through areas that are very\\n\\npotent in natural gas odors,” and has “seen the giant pillars of fire for the flaring the sites\\n\\ndo.” JA619. She states that “[t]he lights staged at well sites can be as bright as stadium\\n\\nlights.” Id.\\n\\n Deborah Green, a member of NRDC, visits the Chaco Canyon area and Chaco\\n\\nPark at least once a year. She states that “[o]il and gas leasing and development in the\\n\\n\\n\\n 4\\n Because “standing is determined at the time the action is brought,” Mink v.\\nSuthers, 482 F.3d 1244, 1253 (10th Cir. 2007), it does not affect our standing\\nanalysis that these dates are now past.\\n 15\\n\\fChaco Canyon area/region and [Chaco Park] adversely affect[] the quality of [her] visitor\\n\\nexperience in the area, and if expanded, would do so even more.” JA630. Along\\n\\nHighway 550, on the way to Chaco Park, Green has experienced\\n\\n air pollution from gas flares at wells and large amounts of exhaust from the\\n oil and gas company trucks and heavy equipment; noise pollution from\\n heavy truck traffic; and light pollution when drilling goes on around the\\n clock and from gas flares, which are visible from the road for a long\\n distance at night.\\n\\nId.\\n\\n These affidavits establish that the BLM’s challenged actions impair these\\n\\nindividuals’ actual, concrete interests because the affiants have a geographical nexus to\\n\\nand actually use the land in the allegedly affected area.\\n\\n Federal Appellees argue that the affidavits are insufficient for two reasons. First,\\n\\nthey contend that Appellants have “challenged 337 individual agency actions,” each of\\n\\nwhich “gives rise to a distinct claim,” and that Appellants “must establish standing . . . for\\n\\neach challenged APD approval.” Fed. Aples. Br. at 23. Second, they argue that\\n\\nAppellants “fail to establish a geographical nexus to the challenged agency actions”\\n\\nbecause Appellants’ affidavits all refer generally to the “greater Chaco region” or the\\n\\n“Mancos Shale formation.” Id. at 26–27. Both arguments fail.\\n\\n As Appellants point out, we have previously rejected similar arguments. In\\n\\nPalma, the district court held that the plaintiffs did not establish an injury in fact because\\n\\nthey submitted affidavits that “did not identify specific visits to each of the thirty-nine\\n\\nleases at issue.” 707 F.3d at 1155. This holding, we concluded, misapplied the law. Id.\\n\\n“Neither our court nor the Supreme Court has ever required an environmental plaintiff to\\n\\n 16\\n\\fshow that it has traversed each bit of land that will be affected by a challenged agency\\n\\naction.” Id. Rather, “[a] plaintiff who has repeatedly visited a particular site, has\\n\\nimminent plans to do so again, and whose interest are harmed by a defendant’s conduct\\n\\nhas suffered injury in fact that is concrete and particularized.” Id. at 1156. In Palma, an\\n\\norganization’s member’s affidavit was “sufficient” when “[h]e specified areas which he\\n\\nhas visited, averred that these specific areas will be affected by oil and gas drilling, and\\n\\nstated his interests will be harmed by such activity.” Id. The affidavits Appellants\\n\\nsubmitted in this case meet this standard.5\\n\\n Further, maps in the record indicate the geographic proximity of challenged APD\\n\\nsites to specific areas referenced in Appellants’ affidavits. Nichols attached to his\\n\\ndeclaration a map of the area around Chaco Park that shows the proximity of existing and\\n\\nnew wells to Chaco Park and other locations affiants describe. This and other maps in\\n\\nthe record indicate that challenged well sites are within twenty miles or less of Chaco\\n\\nPark, where Nichols and Green recreate; along Highway 550, the road to enter Chaco\\n\\nPark; and within several miles of Twin Pines, where Pinto lives, and Nageezi, where\\n\\nEisenfeld and Nichols both recreate.\\n\\n Furthermore, Appellants in this case challenge the BLM’s alleged failure to\\n\\n\\n 5\\n Although we dismissed the appeal in Palma for lack of ripeness, Palma still\\ninforms our injury-in-fact determination. Because we concluded that the Palma\\nplaintiffs had established a concrete and particularized injury, we went on to consider\\n“not whether SUWA is a proper party to challenge BLM’s decision, but when it can\\ndo so.” 707 F.3d at 1157. But our determination that the Palma plaintiffs’ harm was\\nnot ripe does not render obsolete our conclusion that their harm was sufficiently\\nconcrete and imminent. Palma therefore appropriately informs our injury-in-fact\\nanalysis here.\\n 17\\n\\fevaluate the indirect and cumulative impacts of the APDs, not merely the direct impacts\\n\\nof drilling to the area immediately surrounding the wellpads. Although Appellants’\\n\\nNEPA claim is in the form of challenges to numerous individual APDs, the allegedly\\n\\naffected area extends beyond the boundaries of the well sites and into the greater Chaco\\n\\nlandscape. Affiants’ descriptions of environmental harms including “air pollution from\\n\\ngas flares at wells,” “exhaust from the oil and gas company trucks and heavy equipment,”\\n\\n“noise pollution from heavy truck traffic,” and “light pollution” from drilling and “gas\\n\\nflares,” JA630, which they experience as they live and recreate in the affected area, are\\n\\nsufficient to place Appellants “among the injured.” Lucero, 102 F.3d at 449.\\n\\n Appellants have shown through their members’ affidavits that some of their\\n\\nmembers have a geographical nexus to, and actually use, land the BLM has exposed to an\\n\\nincreased risk of environmental harm due to its alleged uninformed decisionmaking.\\n\\nAppellants have established an injury in fact for purposes of Article III.\\n\\n B\\n\\n To establish causation, an environmental plaintiff “need only trace the risk of\\n\\nharm to the agency’s alleged failure to follow [NEPA]’s procedures.” Lucero, 102 F.3d\\n\\nat 452. A NEPA injury “results not from the agency’s decision, but from the agency’s\\n\\nuninformed decisionmaking.” Id. (first emphasis added).\\n\\n Federal Appellees argue that Appellants have not shown that “the relief sought—\\n\\nthe vacatur of BLM’s decisions approving these 337 APDs—will remedy their alleged\\n\\ninjuries.” Fed. Aples. Br. at 29. They assert that Appellants have not established that\\n\\ntheir environmental harms were caused by “the 337 challenged permits rather than . . . the\\n\\n 18\\n\\fapproximately 23,000 active oil and gas wells in the San Juan Basin that are not the\\n\\nsubject of this action.” Id. This argument fails.\\n\\n “In the context of a [NEPA] claim, the injury is the increased risk of\\n\\nenvironmental harm to concrete interests . . . .” Lucero, 102 F.3d at 451 (emphasis\\n\\nadded). In this case, Appellants’ asserted injury is the increased risk of environmental\\n\\nharm from the additional wells, and it is undisputed that BLM has authorized more than\\n\\n300 additional wells in the Mancos Shale. Appellants have alleged that the BLM did not\\n\\ncomply with NEPA in granting the challenged APDs, and that its alleged failure resulted\\n\\nin “the agency’s uninformed decisionmaking” as to these additional wells. Id. at 452.\\n\\nThis is sufficient to establish causation.\\n\\n C\\n\\n Appellants must also establish that it is “likely, as opposed to merely speculative,\\n\\nthat the injury will be redressed by a favorable decision.” Lujan, 504 U.S. at 561\\n\\n(quotations omitted). Under NEPA, “a plaintiff need not establish that the ultimate\\n\\nagency decision would change upon [NEPA] compliance. Rather, the [Plaintiff must\\n\\nonly show] that its injury would be redressed by a favorable decision requiring”\\n\\ncompliance with NEPA procedures. Lucero, 102 F.2d at 452 (quotations and citations\\n\\nomitted). Here, Appellants challenge the BLM’s decision to grant APDs without\\n\\nconducting the requisite NEPA analysis. A favorable decision ordering compliance with\\n\\nNEPA’s procedures would “avert the possibility that the [BLM] may have overlooked\\n\\nsignificant environmental consequences of its actions,” thereby redressing Appellants’\\n\\nalleged harms. Id. Appellants have established redressability.\\n\\n 19\\n\\f Because individual members of Appellants’ organizations have suffered a concrete\\n\\nand particularized injury in fact that is fairly traceable to the BLM’s alleged failure to\\n\\ncomply with NEPA and could be redressed by a favorable decision, we conclude that\\n\\nAppellants have standing.6\\n\\n IV\\n\\n Before analyzing the merits of Appellants’ arguments, we first note the dramatic\\n\\ninsufficiency of the record. Although Appellants challenge more than 300 individual\\n\\nagency actions, they have provided us with the complete record of the BLM’s\\n\\ndecisionmaking process for only a few of the challenged actions. We are therefore\\n\\nunable to evaluate the sufficiency of the BLM’s NHPA and NEPA analyses for the vast\\n\\nmajority of the challenged actions. See 10th Cir. R. 10.4(A) (“Counsel must designate a\\n\\nrecord on appeal . . . that is sufficient for considering and deciding the appellate issues.”);\\n\\nid. at 10.4(B) (“When the party asserting an issue fails to provide a record or appendix\\n\\nsufficient for considering that issue, the court may decline to consider it.”).\\n\\n As to NHPA, the record indicates that the BLM considered impacts on historic\\n\\nproperties in at least three documents for each APD: (1) a Cultural Resource Survey\\n\\n(CRS), (2) a Record of Review, and (3) a site-specific EA. Therefore, in order to\\n\\n\\n\\n 6\\n The harms Appellants allege are the same for their NHPA claims (an\\nincreased risk of harm to Chaco Park and the surrounding area), and NHPA is also a\\nprocedural statute, so the standing analysis for NHPA is the same as for NEPA in this\\ncase. Appellants have established standing under NHPA because they allege a\\nconcrete and particularized injury in fact that is fairly traceable to the BLM’s alleged\\nfailure to comply with NHPA and could be redressed by a favorable decision.\\n\\n 20\\n\\fevaluate the sufficiency of the BLM’s NHPA analysis, we would need the complete EA,\\n\\ncomplete CRS, and complete Record of Review for each challenged APD. The record,\\n\\nhowever, contains portions of the BLM’s NHPA analysis for only seventeen different\\n\\nsets of APDs.7 Further, the vast majority of the NHPA analyses in the record are only\\n\\nseveral-page excerpts, not the entire analysis. The record contains the complete EA,\\n\\nCRS, and Record of Review for only one set of challenged APDs: Kimbeto Wash Unit\\n\\nWells 787H, 789H, and 791H.\\n\\n As to NEPA, the record indicates that the BLM’s NEPA analysis was included in\\n\\nat least each site-specific EA and the 2003 EIS (to which each of the site-specific EAs\\n\\ntiered). Therefore, in order to evaluate the sufficiency of the BLM’s NEPA analyses, we\\n\\nwould need the complete 2003 EIS and the complete EA for each challenged APD. The\\n\\nrecord, however, only includes portions of twenty-seven EAs. And, as with the NHPA\\n\\nanalyses, the vast majority of the EAs in the record are several-page excerpts, not the\\n\\ncomplete EA. From our count, the record contains only six complete EAs: EA 2012-\\n\\n0268, EA 2014-0272, EA 2015-0036, EA 2015-0066, EA 2016-0029, and EA 2016-\\n\\n0200/2016-0076. We are therefore able to analyze whether the BLM violated NEPA\\n\\nonly as to those six EAs.\\n\\n “[O]ur cases addressing deficiencies in the appendix submitted by an appellant\\n\\ndefine a guiding principle . . . .” Lincoln v. BNSF Ry. Co., 900 F.3d 1166, 1190 (10th\\n\\n\\n 7\\n It appears that many CRSs and Records of Review analyze the impacts on\\nhistoric properties for more than one APD. And it appears that most, if not all, EAs\\nanalyze the impacts of more than one APD. Regardless, the record on appeal\\ncontains far fewer than all of the documents containing the BLM’s NHPA analyses.\\n 21\\n\\fCir. 2018). Even when an appendix is deficient, if “the materials provided by the\\n\\nappellant permit us to reach a firm and definite conclusion regarding the merits of an\\n\\nindividual argument or claim within the appeal,” we often will address the argument or\\n\\nclaim, although our rules do not require us to do so. Id. But if “we are forced to venture\\n\\na guess as to the merits of an argument or claim, even ‘an informed guess,’ we will\\n\\nsummarily affirm the district court’s judgment.” Id. (collecting cases).\\n\\n Applying these principles, we conduct our NHPA and NEPA reviews only as to\\n\\nthose challenged actions for which we have the BLM’s complete analysis. For NHPA,\\n\\nwe evaluate the sufficiency of the BLM’s analysis for Kimbeto Wash Unit Wells 787H,\\n\\n789H, and 791H. For NEPA, we evaluate the sufficiency of the BLM’s analysis for: (1)\\n\\nEA 2012-0268, (2) EA 2014-0272, (3) EA 2015-0036, (4) EA 2015-0066, (5) EA 2016-\\n\\n0029, and (6) EA 2016-0200/2016-0076.8 As to all other challenged agency actions, the\\n\\nrecord “is insufficient to permit assessment of [Appellants’] claim of error,” and we\\n\\naffirm the district court. Tilton v. Capital Cities/ABC, Inc., 115 F.3d 1471, 1474 (10th\\n\\nCir. 1997).\\n\\n\\n\\n\\n 8\\n We note that even as to these EAs, it is possible that the record does not\\ncontain the BLM’s entire NEPA analysis. See, e.g., JA2143 (stating “Appendix D.\\nSurface Reclamation Plan,” but not containing any surface reclamation plan).\\nHowever, because we do not identify—and the parties do not point to—any missing\\nportion of these EAs relevant to the challenges Appellants raise on appeal, we\\nconclude that the record is sufficient for us to evaluate Appellants’ NEPA claims as\\nto these EAs.\\n 22\\n\\f V\\n\\n Appellants contend that the BLM violated NHPA in three ways. First, they assert\\n\\nthat the BLM arbitrarily defined an area of potential effects (APE) for each APD in a way\\n\\nthat excluded cultural sites that might be indirectly affected by Mancos Shale\\n\\ndevelopment. This argument is premised on Appellants’ assertion that the 2014 Protocol\\n\\nrequired the BLM to set a separate APE for indirect effects, which the BLM did not do.\\n\\nSecond, Appellants argue that the BLM did not consider the cumulative effects of\\n\\nMancos Shale development on relevant cultural and historic properties. Finally,\\n\\nAppellants contend that the BLM failed to consult with the State Historic Preservation\\n\\nOffice (SHPO) as required by the 2014 Protocol. Each of these arguments fail.\\n\\n A\\n\\n Section 106 of NHPA sets forth specific processes federal agencies must perform\\n\\nto comply with NHPA. See 36 C.F.R. § 800.1(a). In general, the Section 106 process\\n\\ninvolves four steps. First, the agency defines the APE. 36 C.F.R. § 800.4(a). The APE\\n\\nis “the geographic area or areas within which an undertaking may directly or indirectly\\n\\ncause alterations in the character or use of historic properties, if any such properties\\n\\nexist.” Id. § 800.16(d). “Establishing an [APE] requires a high level of agency expertise,\\n\\nand as such, the agency’s determination is due a substantial amount of discretion.”\\n\\nValley Cmty. Pres. Comm’n v. Mineta, 373 F.3d 1078, 1092 (10th Cir. 2004).\\n\\n After defining the APE, the agency identifies historic properties within the APE.\\n\\n36 C.F.R. § 800.4(b). A historic property is “any prehistoric or historic district, site,\\n\\nbuilding, structure, or object included on, or eligible for inclusion on” the National\\n\\n 23\\n\\fRegister of Historic Places (NRHP). 54 U.S.C. § 300308. If the agency determines that\\n\\nno historic properties are present within the APE, it reports that finding and the NHPA\\n\\nprocess ends. 36 C.F.R. § 800.4(d)(1).\\n\\n If historic properties are present within the APE, the agency determines whether\\n\\nthe proposed undertaking will adversely affect those properties. Id. § 800.5. An adverse\\n\\neffect exists “when an undertaking may alter, directly or indirectly, any of the\\n\\ncharacteristics of a historic property that qualify the property for inclusion in the [NRHP]\\n\\nin a manner that would diminish the integrity of the property’s location, design, setting,\\n\\nmaterials, workmanship, feeling, or association.” Id. § 800.5(a)(1). Adverse effects\\n\\ninclude “reasonably foreseeable effects caused by the undertaking that may occur later in\\n\\ntime, be farther removed in distance or be cumulative.” Id. They also include the\\n\\n“[i]ntroduction of visual, atmospheric[,] or audible elements that diminish the integrity of\\n\\nthe property’s significant historic features.” Id. § 800.5(a)(2)(v).\\n\\n If the agency determines that the undertaking may cause an adverse effect on the\\n\\nhistoric properties within the APE, it must “develop and evaluate alternatives or\\n\\nmodifications to the undertaking that could avoid, minimize, or mitigate adverse effects\\n\\non historic properties.” Id. § 800.6(a). The Section 106 process does not demand a\\n\\nparticular result, however, because “Section 106 is essentially a procedural statute and\\n\\ndoes not impose a substantive mandate” on the agencies governed by it. Valley Cmty.,\\n\\n373 F.3d at 1085.\\n\\n Section 106 authorizes agencies to enter into a “programmatic agreement to\\n\\ngovern the implementation of a particular program or the resolution of adverse effects\\n\\n 24\\n\\ffrom certain complex project situations or multiple undertakings.” 36 C.F.R.\\n\\n§ 800.14(b). When a governing programmatic agreement is in place, compliance with the\\n\\nprocedures in that agreement satisfies the agency’s NHPA Section 106 responsibilities\\n\\nfor all covered undertakings. Id. § 800.14(b)(2)(iii).\\n\\n The parties agree that two programmatic agreements governed the BLM’s NHPA\\n\\nanalyses of the APDs in this case: one agreement that went into effect in 2004 (the 2004\\n\\nProtocol), and one that went into effect in 2014 (the 2014 Protocol). Therefore, we must\\n\\nresolve whether Appellants have shown that the BLM violated the requirements of the\\n\\n2014 Protocol9 as to the single challenged APD properly before us. Although the\\n\\ncompliance requirements for the 2014 Protocol are somewhat different than Section\\n\\n106’s requirements, the basic NHPA process is the same.\\n\\n The 2014 Protocol states generally that, “[i]n defining the APE, the BLM will\\n\\nconsider potential direct, indirect, and cumulative effects to historic properties and their\\n\\nassociated settings when setting is an important aspect of integrity, as applicable.”\\n\\nJA1562. Relevant here, the 2014 Protocol states that “[t]he BLM will follow the\\n\\nestablished guidance on standard direct APEs for certain types of projects in Appendix\\n\\n\\n\\n 9\\n Although Appellants acknowledge the existence and applicability of the 2004\\nProtocol, they make no NHPA arguments under the 2004 Protocol. Federal\\nAppellees assert (without citation) that “[a]pproximately 221 of the challenged\\ndrilling permits were approved at the time the 2004 Protocol was operative, and\\napproximately 163 permits fell under the 2014 Protocol.” Fed. Aples. Br. at 12. All\\nof Appellants’ NHPA arguments, however, rely on the 2014 Protocol. Because we\\nconclude that Appellants’ NHPA challenge fails for other reasons, we need not\\naddress the effect Appellants’ failure to argue that the BLM violated the 2004\\nProtocol might otherwise have on Appellants’ NHPA challenges.\\n 25\\n\\fB.” Id. (italics omitted). Appendix B sets a “standard APE” for well pads of “the well\\n\\npad and construction zone plus 100[] [feet] on each side from the edge of the construction\\n\\nzone.” JA1594. The 2014 Protocol acknowledges that “[i]n certain circumstances, even\\n\\nthough an undertaking may have a standard APE . . . , the Field Manager, at the\\n\\nrecommendation of the cultural resource specialist, may have justification to require a\\n\\nlarger APE.” Id.\\n\\n B\\n\\n Appellants argue that the BLM “failed to account for indirect impacts to cultural\\n\\nsites, as required by the NHPA and the Protocol.” Aplts. Br. at 30. According to\\n\\nAppellants, “the Protocol requires BLM to consider a separate APE for indirect effects\\n\\nwhere ‘[t]he introduction of physical, visual, or audible elements has the potential to\\n\\naffect the historic setting or use’ of cultural sites ‘where setting is an important aspect of\\n\\nintegrity.’” Id. at 31 (quoting JA1562). Appellants’ argument fails because the 2014\\n\\nProtocol merely allows for, it does not require, a separate indirect-effects APE.\\n\\n The 2014 Protocol acknowledges that “[t]he introduction of physical, visual,\\n\\naudible, or atmospheric elements has the potential to affect the historic setting or use of\\n\\nhistoric properties,” and requires the BLM to “take this into account in defining the limits\\n\\nof an APE for indirect effects.” JA1562 (emphasis added). Under the 2014 Protocol,\\n\\n“[t]he indirect APE shall include known or suspected historic properties and their\\n\\nassociated settings where setting is an important aspect of integrity.” Id. The 2014\\n\\nProtocol continues: “Identification efforts outside of the APE for direct effects shall be at\\n\\nthe approval of the BLM field manager, taking into account the recommendations of the\\n\\n 26\\n\\fBLM cultural resource specialist and the SHPO.” Id. (emphasis added). In other words,\\n\\nthe BLM need not set—or even consider—a separate indirect-effects APE when\\n\\n“physical, visual, audible, or atmospheric elements ha[ve] the potential to affect the\\n\\nhistoric setting or use of historic properties,” as Appellants argue. JA1562. Rather, the\\n\\n2014 Protocol only requires that the BLM take indirect effects into account as it exercises\\n\\nits substantial discretion in setting the APE. The 2014 Protocol therefore contains a\\n\\ndefault presumption that the direct and indirect APE will be the same and, to the extent\\n\\nthe BLM will attempt to identify historic properties outside the direct-effects APE, those\\n\\nidentification efforts will be at the approval of the BLM field manager.\\n\\n Moreover, the CRS, the Record of Review, and the EA for the Kimbeto Wash\\n\\nUnit wells indicate that the BLM looked to areas far outside the standard direct-effects\\n\\nAPE to identify cultural properties. The EA includes a fulsome discussion of the\\n\\npotential for indirect impacts from the proposed project, including an analysis of visual\\n\\nresources. The EA notes that the proposed action is at least 8.5 miles “from the boundary\\n\\nof [Chaco Park].” Id. It acknowledges that “small portions of the pipeline fall within”\\n\\ntwo National Park Service designated Key Observation Points, but concludes that\\n\\n“[g]iven [the] distance ([over] 11.5 miles) and low profile[,] the pipeline will not be\\n\\nvisible.” JA1949. The EA notes that the project’s “well pad is within a mile of a few\\n\\nscattered residences,” but concludes that it is “unlikely that the well pad will be visible\\n\\nfrom these residences due to area topography.” JA1950. It also states that the “well pad\\n\\nwill not visible from any designated recreation areas.” Id.\\n\\n The EA also addresses the project’s potential impact on night skies, noting that\\n\\n 27\\n\\f“[l]ight sources associated with drilling an oil and gas well include a light plant or\\n\\ngenerator, a light on top of the rig, vehicle traffic, and flaring.” JA1951.\\n\\n The necessity for flaring and the duration of flaring varies widely from well\\n to well and is difficult to predict. With the exception of a few yearly\\n events, visitors are not allowed access to the canyon rim where the\\n proposed action may be seen after sunset, minimizing the chance that\\n visitors would see the direct light. While these lights could reduce the\\n general darkness of the night sky as seen from [Chaco Park], it is likely the\\n impact would be imperceptible.\\n\\nId. Further, the EA notes that any potential light impacts “would be short-term.” Id.\\n\\n The CRS and Record of Review also indicate that the BLM looked for historic\\n\\nsites in an area that extended far beyond the direct-effects APE. The CRS notes that a\\n\\nrecord search was conducted and “[n]o sites listed on the State Register of Cultural\\n\\nProperties or the [NRHP we]re located within a 1 mile [sic] of the project area.” JA2173\\n\\n(emphasis added). The BLM also conducted pedestrian surveys of a 108.01-acre area,\\n\\nalthough the CRS indicates only 25.76 acres in the APE. [Id.] During the pedestrian\\n\\nsurveys, “[w]hen cultural material was encountered, it was pin flagged and the\\n\\narchaeologists began an intensive search of the area to locate other material.” JA2175.\\n\\nAfter eight “Fieldwork Dates,” forty-six “Survey Person Hours” and thirty-nine\\n\\n“Recording Person Hours,” the BLM’s NHPA review identified four newly recorded\\n\\ncultural sites, one previously recorded site, and twelve isolated occurrences of cultural\\n\\nmaterial. Id. The BLM ultimately determined that three of the five sites were ineligible\\n\\nfor listing on the NRHP, and two were eligible but avoided. The BLM therefore\\n\\nrecommended that the project go forward with mitigation requirements, including\\n\\nemployee education, temporary barriers, and archaeological site monitoring.\\n\\n 28\\n\\f The CRS, Record of Review, and EA for the Kimbeto Wash Unit wells indicate\\n\\nthat the BLM attempted to identify historic properties in an area far outside the standard\\n\\ndirect-effects APE for well pads, and that the BLM considered the proposed drilling’s\\n\\npossible visual impacts, including its impact on night skies. Given this analysis,\\n\\nespecially considering that it far exceeded the analysis required by the 2014 Protocol,\\n\\nAppellants have failed to establish that the BLM violated NHPA by not adequately\\n\\nconsidering the indirect effects of the Kimbeto Wash Unit wells.10\\n\\n C\\n\\n Appellants also argue that the BLM violated NHPA because it “failed to analyze\\n\\nthe cumulative effects of developing hundreds of new APDs across this culturally\\n\\nsignificant landscape.” Aplts. Br. at 38. Appellants’ cumulative-effects argument fails\\n\\nbecause Appellants identify no historic properties within the APE the BLM set.\\n\\n In support of their cumulative-effects argument, Appellants cite to 36 C.F.R.\\n\\n\\n\\n 10\\n Despite the BLM’s extensive NHPA analysis for the Kimbeto Wash Unit\\nwells, parts of the record indicate that the BLM may not have considered the\\ncumulative and indirect impacts of other challenged APDs so thoroughly. For\\nexample, in discussing possible cumulative impacts, some EAs state simply that\\n“[t]here would be no negative cumulative impact on cultural resources, as significant\\ncultural sites would be avoided.” JA1154; accord JA1267 (same); JA1333 (same).\\nDepending on the circumstances—and whether this were indeed the only cumulative\\nimpacts analysis the BLM completed—this cursory analysis could be insufficient.\\n However, other parts of the record contain more thorough indirect- and\\ncumulative-effects analyses. Indeed, the apparent difference in the substance of the\\nBLM’s NHPA analyses for different APDs highlights the need to examine each of the\\nBLM’s challenged actions individually and with reference to a complete record of the\\nBLM’s NHPA analysis. And, of course, we cannot determine that the BLM’s\\nanalysis was insufficient for one APD by examining the analysis the BLM conducted\\nfor a different APD.\\n 29\\n\\f§ 800.5(a)(1), which states that “[a]dverse effects may include reasonably foreseeable\\n\\neffects caused by the undertaking that may occur later in time, be farther removed in\\n\\ndistance or be cumulative.” This regulation, however, addresses the BLM’s application\\n\\nof “the criteria of adverse effect to historic properties within the [APE].” 36 C.F.R.\\n\\n§ 800.5(a) (emphasis added). In other words, the cited language simply means that an\\n\\nundertaking can have adverse effects on historical properties within the APE, even if the\\n\\nundertaking only adversely affects the properties through “reasonably foreseeable effects\\n\\ncaused by the undertaking that may . . . be cumulative.” Id. § 800.5(a)(1).\\n\\n Appellants, however, argue that the BLM abused its discretion by failing to\\n\\nanalyze the cumulative adverse effects horizontal Mancos Shale wells might have “on the\\n\\nintegrity of the historic setting for any number of cultural sites, [Chaco] Park, and the\\n\\nGreater Chaco Landscape.” Aplts. Br. at 37. This argument ignores that § 800.5(a)(1)\\n\\napplies to the BLM’s assessment of adverse effects on “historic properties within the\\n\\n[APE].” 36 C.F.R. § 800.5(a) (emphasis added). And the record indicates that the APE\\n\\nfor the Kimbeto Wash Unit wells did not encompass the “cultural sites, [Chaco] Park, and\\n\\nthe Greater Chaco Landscape,” Aplts. Br. at 37, which Appellants argue would be\\n\\nnegatively impacted by these cumulative effects.11\\n\\n In sum, Appellants’ cumulative-effects argument is premised on an APE different\\n\\n\\n\\n 11\\n Indeed, Appellants criticize this aspect of the BLM’s NHPA process,\\narguing that the BLM’s APE definition “resulted in the agency excluding from its\\nanalysis all cultural sites likely to be adversely affected by noise, light, and air\\npollution.” Aplts. Br. at 30.\\n\\n 30\\n\\ffrom the one the BLM defined. Appellants’ argument therefore fails.\\n\\n D\\n\\n Appellants also argue that the BLM was required to consult with the SHPO12\\n\\nbecause defining APEs for the challenged APDs was “complicated or controversial.”\\n\\nAplts. Br. at 35. In support, Appellants cite the 2014 Protocol’s examples of\\n\\n“complicated or controversial” projects, contending that the APDs at issue qualify\\n\\nbecause “‘multiple applicants’ [and] ‘multiple Indian tribes’ are involved.” Id. (quoting\\n\\nJA1562). Appellants’ SHPO consultation argument fails.\\n\\n The 2014 Protocol “specifies the manner in which the BLM works with SHPO,”\\n\\nand “establishes a streamlined consultation process for most BLM undertakings.”\\n\\nJA1552. It provides that “[t]he BLM will consult with SHPO on undertakings for which\\n\\na standard APE . . . has not been developed.” JA1562. Appendix B indicates that if the\\n\\nBLM utilizes a standard APE for an undertaking, the “BLM and SHPO have consulted”\\n\\nas to that APE. JA1594 (emphasis added). The 2014 Protocol also states that the BLM\\n\\nwill consult with the SHPO “where the APE is complicated or controversial,” and gives\\n\\nexamples of situations in which defining the APE may be complicated or controversial:\\n\\n\\n\\n\\n 12\\n Amici All Pueblo Council of Governors and the National Trust for Historic\\nPreservation in the United States argue that the BLM did not adequately consult with\\nNative American tribes before approving the APDs. Appellants did not make this\\nargument in district court, and we decline to consider it for the first time on appeal.\\nMcDonald v. Kinder-Morgan, Inc., 287 F.3d 992, 999 (10th Cir. 2002) (“[A]bsent\\nextraordinary circumstances, we will not consider arguments raised for the first time\\non appeal.”).\\n 31\\n\\f“undertakings involving multiple agencies, multiple states, multiple applicants, and/or\\n\\nmultiple Indian tribes.” JA1562.\\n\\n The 2014 Protocol therefore establishes a default presumption that the BLM need\\n\\nnot consult with the SHPO “on undertakings for which a standard APE” exists, such as\\n\\nthe undertakings at issue in this case. JA1562. And in this case, the applicability of a\\n\\nstandard APE also undermines a conclusion that the APE is complicated or controversial.\\n\\nRather, the existence of a standard APE indicates that the BLM and the SHPO anticipated\\n\\nthat the BLM would often have to define an APE for activities related to oil and gas\\n\\ndrilling, such as well pads, pipelines, and roads. And, seeking to “streamline the\\n\\nconsultation process” for these common undertakings, the BLM and the SHPO\\n\\ndetermined that a standard APE for these activities would suffice in most circumstances,\\n\\nand BLM-SHPO consultation in defining the specific APE would be unnecessary.\\n\\nJA1552; accord JA1562. We therefore reject Appellants’ argument that the BLM abused\\n\\nits discretion by not consulting with the SHPO.\\n\\n Appellants fail to carry their burden of establishing that the BLM violated NHPA.\\n\\nThe BLM’s decision is entitled to a presumption of regularity, and it finds support in the\\n\\nrecord. Accordingly, we affirm the district court’s dismissal of Appellants’ NHPA claim.\\n\\n VI\\n\\n Appellants’ NEPA argument is as follows: the environmental impacts of the\\n\\nhorizontal Mancos Shale wells are both (1) different in kind from and (2) greater in\\n\\nmagnitude than those considered in the 2003 EIS. Because of this, the 2003 EIS did not\\n\\nfully analyze the environmental impacts associated with horizontal Mancos Shale wells,\\n\\n 32\\n\\fso the BLM was not authorized to tier the EAs to the 2003 EIS, and the FONSIs the BLM\\n\\nissued were arbitrary and capricious. We conclude that, as to five EAs, Appellants have\\n\\ndemonstrated that the BLM needed to—but did not—consider the cumulative impacts of\\n\\nwater resources associated with the 3,960 reasonably foreseeable horizontal Mancos\\n\\nShale wells. The BLM’s issuance of FONSIs and approval of APDs associated with\\n\\nthese EAs was therefore arbitrary and capricious and violated NEPA.\\n\\n A\\n\\n NEPA “requires federal agencies . . . to analyze environmental consequences\\n\\nbefore initiating actions that potentially affect the environment.” Utah Env’t Cong. v.\\n\\nBosworth, 443 F.3d 732, 735–36 (10th Cir. 2006). To comply with NEPA, agencies\\n\\nmust prepare a detailed statement of the environmental impact of any “major Federal\\n\\naction[] significantly affecting the quality of the human environment.” 42 U.S.C.\\n\\n§ 4332(2)(C).\\n\\n In conducting its NEPA analysis, a federal agency must prepare, as relevant here,\\n\\neither “(1) an environmental impact statement [(EIS)], [or] (2) an environmental\\n\\nassessment [(EA)].” Bosworth, 443 F.3d at 736. An EIS “is required if a proposed\\n\\naction will ‘significantly affect[] the quality of the human environment.’” Id. (alteration\\n\\nin original) (quoting 42 U.S.C. § 4332(C)). “If an agency is uncertain whether the\\n\\nproposed action will significantly affect the environment, it may prepare a considerably\\n\\nless detailed [EA].” Id.\\n\\n Although less detailed than an EIS, the EA must still “include brief discussions of\\n\\nthe need for the proposal, of alternatives . . . , [and] of the environmental impacts of the\\n\\n 33\\n\\fproposed action and alternatives.” 40 C.F.R. § 1508.9(b). Among the environmental\\n\\nimpacts the EA must evaluate are “the cumulative impacts of a project.” WildEarth\\n\\nGuardians v. U.S. Fish & Wildlife Serv., 784 F.3d 677, 690 (10th Cir. 2015) (quoting\\n\\nDavis v. Mineta, 302 F.3d 1104, 1125 (10th Cir. 2002) abrogated on other grounds by\\n\\nDiné Citizens Against Ruining Our Env’t v. Jewell, 839 F.3d 1276 (10th Cir. 2016)).\\n\\nCumulative impacts are “the impact on the environment which results from the\\n\\nincremental impact of the action when added to other past, present, and reasonably\\n\\nforeseeable future actions.” 40 C.F.R. § 1508.7. Cumulative impacts can result from\\n\\n“individually minor but collectively significant actions taking place over a long period of\\n\\ntime.” Id.\\n\\n If, after considering the necessary factors, the agency concludes the action is\\n\\nunlikely to have a significant environmental impact, it may issue a finding of no\\n\\nsignificant impact (FONSI) and proceed with the action. 40 C.F.R. § 1508.13. If the\\n\\nagency reaches the opposite conclusion, before proceeding with the action, it must\\n\\nprepare an environmental impact statement to thoroughly analyze the action’s predicted\\n\\nenvironmental impacts, including its direct, indirect, and cumulative impacts. 42 U.S.C.\\n\\n§ 4332(2)(C); 40 C.F.R. §§ 1508.11, 1508.25. However, even when a proposed action\\n\\nhas “significant effects,” the BLM may tier13 an EA to an existing EIS—and thereby\\n\\n\\n\\n 13\\n “Tiering refers to the coverage of general matters in broader environmental\\nimpact statements . . . with subsequent narrower statements or environmental\\nanalyses . . . incorporating by reference the general discussions and concentrating\\nsolely on the issues specific to the statement subsequently prepared.” 40 C.F.R.\\n§ 1508.28.\\n 34\\n\\freach a FONSI—if the EIS to which it tiers “fully analyzed those significant effects.” 43\\n\\nC.F.R. § 46.140(c). But if the “relevant analysis in the [EIS] is not sufficiently\\n\\ncomprehensive or adequate to support further decisions, the [EA] must explain this and\\n\\nprovide any necessary analysis.” Id. § 46.140(b).\\n\\n “The role of a federal court under NEPA is to review the EIS, [or] EA, . . . as the\\n\\ncase may be, and ‘simply . . . ensure that the agency has adequately considered and\\n\\ndisclosed the environmental impact of its actions.” Concerned Citizens, 843 F.3d at 902\\n\\n(third alteration in original) (quoting Wyoming v. U.S. Dep’t of Agric., 661 F.3d 1209,\\n\\n1256–57 (10th Cir. 2011)). In conducting this review, we apply a “rule of reason\\n\\nstandard” to determine whether claimed NEPA violations “are merely flyspecks, or are\\n\\nsignificant enough to defeat the goals of informed decision making and informed public\\n\\ncomment.” Utahns for Better Transp. v. U.S. Dep’t of Transp., 305 F.3d 1152, 1163\\n\\n(10th Cir. 2002).\\n\\n B\\n\\n Appellants first argue that the challenged APDs cause environmental impacts\\n\\nqualitatively different from those considered in the 2003 EIS because the APDs authorize\\n\\ndrilling in the southern portion of the Mancos Shale, while the 2003 EIS “only evaluated\\n\\ndevelopment in the northern portion.” Aplts. Br. at 42. Appellants’ argument fails\\n\\nbecause the 2003 EIS evaluated the effects of drilling throughout the entire San Juan\\n\\nBasin—an area that includes the location of the challenged APDs.\\n\\n The 2003 EIS was developed to “analyze[] the environmental impacts of oil and\\n\\ngas leasing and development in the San Juan Basin in New Mexico.” JA767. The\\n\\n 35\\n\\f“planning area” addressed in the 2003 EIS “includes all of San Juan County, most of\\n\\nMcKinley County, western Rio Arriba County, and northwestern Sandoval County.”\\n\\nJA768. All challenged APDs are within this area.\\n\\n The 2003 EIS denoted the northeastern portion of the planning area as a “high\\n\\ndevelopment area” for oil and gas production, but that area was so identified because\\n\\n“more than 99 percent of the federal oil and gas resources [we]re currently leased” in that\\n\\narea. JA778. Nothing in the 2003 EIS indicates that the BLM analyzed the\\n\\nenvironmental impacts of drilling on only the high development area. Indeed, the 2003\\n\\nEIS’s chapter on the affected environment contains a lengthy discussion of the cultural\\n\\nresources present in the Chaco Canyon. The record, therefore, does not support\\n\\nAppellants’ assertion that the challenged APDs are in a geographic area not considered\\n\\nby the 2003 EIS.\\n\\n C\\n\\n Appellants also argue that the BLM has never fully analyzed the cumulative\\n\\nenvironmental impacts of drilling 3,960 horizontal wells in the Mancos Shale because\\n\\nthose impacts exceed the environmental impacts evaluated in the 2003 EIS in two\\n\\nspecific ways: air pollution and water use. As to air pollution, we conclude that\\n\\nAppellants have not provided us with a record from which we can assess the BLM’s\\n\\nNEPA analysis. As to water use, we conclude that Appellants have shown that the BLM\\n\\nnever considered the cumulative impact of the water use associated with the 3,960\\n\\nreasonably foreseeable horizontal Mancos Shale wells for five specific EAs. We\\n\\ntherefore reverse the district court’s dismissal of Appellants’ NEPA claims as to EAs\\n\\n 36\\n\\f2014-0272, 2015-0036, 2015-0066, 2016-0029, and 2016-0200/2016-0076.14\\n\\n 1\\n\\n Appellants’ cumulative-impacts argument relies on one assumption the parties\\n\\ndispute: that the BLM’s NEPA analysis must consider the impacts associated with all\\n\\n3,960 wells the 2014 RFDS identified as possible if full-field Mancos Shale\\n\\ndevelopment occurs. We conclude that the 2014 RFDS made it reasonably\\n\\nforeseeable that 3,960 horizontal Mancos Shale wells would be drilled, and NEPA\\n\\ntherefore required the BLM to consider the cumulative impacts of those wells in the\\n\\nEAs it conducted for subsequent horizontal Mancos Shale well APDs.\\n\\n The 2014 RFDS “collect[ed] and analyze[d] geological and engineering\\n\\nevidence[] . . . to determine the potential subsurface development of the Gallup/Mancos\\n\\nplay.” JA1665. Based on this analysis, it estimated that full development of the Mancos\\n\\nShale would result in 3,960 new wells. And, although it predicted “a five[-]year delay in\\n\\nsignificant activity” in the Mancos Shale area “due to unfavorable economics,” it also\\n\\npredicted that well activity would “rapidly increase” once the economics became more\\n\\nfavorable. JA1662.\\n\\n The BLM itself has relied on RFDSs to define the scope of “reasonably\\n\\n\\n\\n 14\\n EA 2012-0268 was completed in June 2012, more than two years before the\\n2014 RFDS issued. Appellants’ cumulative-impacts argument relies entirely on the\\n2014 RFDS’s prediction of 3,960 horizontal Mancos Shale wells. Because\\nAppellants provide no reason other than the 2014 RFDS that the BLM’s NEPA\\nanalysis should have included the environmental impacts from 3,960 horizontal\\nMancos Shale wells, Appellants do not establish that the BLM violated NEPA as to\\nEA 2012-0268.\\n 37\\n\\fforeseeable” actions for the purposes of its cumulative-impacts analyses. For example,\\n\\ntwo of the EAs before us cite to the 2014 RFDS in their discussions of cumulative\\n\\nimpacts. In describing the methodology used to analyze cumulative impacts, EA 2016-\\n\\n0029 and EA 2016-0200/2016-0076 discuss oil and gas development predicted in the\\n\\n2014 RFDS, noting that the 2014 RFDS\\n\\n identified high, moderate, and low potential regions for oil development of\\n the Mancos-Gallup Formation. Within the high potential region, full\\n development would include 5 wells per section, resulting in 1,600\\n completions. Within the moderate potential region, full development\\n would include one well per section, resulting in 330 completions. Within\\n the low potential region, full development would include one well per\\n township, resulting in 30 well completions. Additionally, the [2014 RFDS]\\n predicted 2,000 gas wells could be development [sic] in the northeastern\\n corner of the [BLM’s Farmington Field Office].\\n\\nJA1926; JA2096. The BLM also relied on the 2001 RFDS for projected drilling amounts\\n\\nin the 2003 EIS. The 2003 EIS states that the 2001 RFDS “form[ed] the basis for\\n\\nprojected oil and gas development in the planning area over the next 20 years.” JA769–\\n\\n70. Especially in light of the BLM’s past reliance on the drilling projected in RFDSs, we\\n\\nconclude that once the 2014 RFDS issued, the 3,960 horizontal Mancos Shale wells\\n\\npredicted in that document were “reasonably foreseeable future actions.” 40 C.F.R.\\n\\n§ 1508.7; accord Sierra Club v. Marsh, 976 F.2d 763, 767 (1st Cir. 1992) (“[A]s in other\\n\\nlegal contexts, the terms ‘likely’ and ‘foreseeable,’ as applied to a type of environmental\\n\\nimpact, are properly interpreted as meaning that the impact is sufficiently likely to occur\\n\\nthat a person of ordinary prudence would take it into account in reaching a decision.”).\\n\\nThe BLM therefore needed to consider the cumulative environmental impacts associated\\n\\nwith the reasonably foreseeable 3,960 horizontal Mancos Shale wells when it conducted\\n\\n 38\\n\\fEAs for the challenged APDs.\\n\\n Intervenor Appellees’ arguments do not persuade us otherwise. First, we of\\n\\ncourse acknowledge that “full-field [Mancos Shale] development is not at issue in\\n\\nthis case.” Int. Aples. Br. at 38. But that does not excuse the BLM from NEPA’s\\n\\nrequirement that it “take a ‘hard look’ at the environmental consequences before”\\n\\napproving the challenged APDs. Balt. Gas & Elec. Co., 462 U.S. at 97. And, in this\\n\\ncase, that involved considering the cumulative impacts of the 3,960 reasonably\\n\\nforeseeable horizontal Mancos Shale wells. See 40 C.F.R. §§ 1508.9(b), 1508.7.\\n\\n Second, we reject Intervenor Appellees’ argument that the BLM did not need\\n\\nto consider the cumulative impact of the predicted 3,960 wells because “no operator\\n\\nhas proposed to drill” all of those wells. Int. Aples. Br. at 40. Once the 2014 RFDS\\n\\nissued, it became reasonably foreseeable to the BLM that the projected wells would\\n\\nbe drilled, so the BLM needed to consider the cumulative impact of all those wells,\\n\\neven if the wells were not going to be drilled imminently. 40 C.F.R. § 1508.7\\n\\n(“Cumulative impacts can result from individually minor but collectively significant\\n\\nactions taking place over a period of time.” (emphasis added)).\\n\\n Finally, we reject Intervenor Appellees’ argument that our conclusion here would\\n\\n“automatically foreclose authorization of all individual activities in the [planning] area”\\n\\nonce the BLM initiates an RMP amendment process. Int. Aples. Br. at 42. Rather, our\\n\\ndecision forecloses only those activities with environmental impacts—direct, indirect, or\\n\\ncumulative—that have not been considered in either a site-specific EA or a broader\\n\\nNEPA document to which the EA tiers. But that is the purpose of NEPA: to “require[]\\n\\n 39\\n\\ffederal agencies . . . to analyze environmental consequences before initiating actions that\\n\\npotentially affect the environment.” Bosworth, 443 F.3d at 735–36.\\n\\n We conclude that the 3,960 horizontal Mancos Shale wells predicted in the 2014\\n\\nRFDS were reasonably foreseeable after the 2014 RFDS issued. The BLM therefore had\\n\\nto consider the cumulative impacts of all 3,960 wells when it conducted its site-specific\\n\\nEAs.\\n\\n 2\\n\\n Appellants argue that the air pollution caused by the horizontal Mancos Shale\\n\\nwells will exceed the air pollution amounts considered in the 2003 EIS. In support,\\n\\nAppellants point to a table that purports to “illustrate the total combined impacts of past,\\n\\npresent, and reasonably foreseeable future development.” Aplts. Br. at 43. Although the\\n\\nnumbers in Appellants’ table indicate that horizontal wells have a much greater\\n\\nenvironmental impact than do vertical wells, the numbers Appellants provide for the\\n\\nenvironmental impacts of vertical wells are not supported by the record. More\\n\\nimportantly, the record does not contain the BLM’s complete air pollution analysis, so we\\n\\nare unable to fully evaluate the air pollution argument Appellants make.\\n\\n Appellants’ air pollution argument relies on the following assumptions:15\\n\\n Well Type Construction Time Nox CO VOC PM10\\n (tpy) (tpy) (tpy) (tpy)\\n Vertical 9 days 2.30 0.63 0.20 0.92\\n\\n\\n\\n 15\\n NOx is nitrous oxide; CO is carbon monoxide; VOC is volatile organic\\ncompound; and PM10 is particulate matter at 10 microns. Each is a form of air\\npollution.\\n 40\\n\\f Horizontal 25 days 6.13 1.64 0.55 2.54\\n\\n\\nId. at 44. Although these numbers support the conclusion that horizontal wells have a\\n\\ngreater environmental impact than do vertical wells, these numbers are not supported\\n\\neither by the part of the record to which Appellants cite or by any other part of the record\\n\\nwe could identify.\\n\\n First, Appellants cite to “JA2331–32 ([pages 4-61–4-62 of the] 2003 EIS\\n\\nproviding qualitative assessment of air quality impairment and violations of air\\n\\nstandards)” and “JA2328–29 (emissions estimates based on developing 663 wells per\\n\\nyear)” in support of the numbers they list for air pollution associated with vertical wells.\\n\\nAplts. Br. at 44 n.22. The first cited portion of the 2003 EIS, however, analyzes the\\n\\noverall potential effect of contemplated drilling operations on air quality in the project\\n\\narea. Those pages do not analyze the air pollution contemplated by construction of\\n\\nvertical wells, as Appellants indicate they do. Moreover, there is no discernible\\n\\nconnection between any of the numbers in this cited portion of the 2003 EIS and the\\n\\nnumbers in Appellants’ chart.\\n\\n The same is true of the other portion of the record Appellants cite: JA2328–29\\n\\n(pages 4-58 and 4-59 of the 2003 EIS). That portion of the 2003 EIS provides an\\n\\n“estimation of emissions for each year” under Alternative B.16 JA2328. A table on the\\n\\n\\n 16\\n This portion of the 2003 EIS analyzes emissions associated with Alternative\\nB—which the BLM did not select. Elsewhere, the 2003 EIS notes that air emissions\\nunder Alternative D, the selected alternative, would be “99.7% of that under\\nAlternative B.” JA782. Air emission estimates for Alternative B therefore could\\ninform estimates for Alternative D.\\n 41\\n\\fsecond cited page contains categories that match the categories in Appellants’ chart—\\n\\nVOC, CO, Nox, and PM10. However, the table indicates that it depicts “Project Year 1\\n\\nand Project Year 20 Annual Air Emissions Associated with Gas Production” under\\n\\nAlternative B. JA2329 (emphasis added). The numbers, therefore, do not represent air\\n\\npollution associated with vertical well construction. And, once again, there is no\\n\\ndiscernible connection between any air pollution numbers in these pages and the vertical-\\n\\nwell numbers in Appellants’ table.\\n\\n Finally, Appellants indicate that the well construction time for a vertical well is\\n\\nnine days. Again, nothing in the part of the record to which Appellants cite supports that\\n\\nassertion. However, the 2003 EIS notes elsewhere that “the time to complete individual\\n\\nwells is generally between one and two months.” JA2287 (emphasis added). This\\n\\nindicates that Appellants’ cited nine days is incorrect.\\n\\n More fundamentally, the record does not contain crucial aspects of the BLM’s\\n\\nNEPA analysis. Specifically, the record does not include the BLM’s complete air\\n\\npollution analysis. The 2003 EIS notes that “Appendix J includes the emissions estimates\\n\\nfor Alternative D.” JA2378. Appendix J also “presents data used to estimate annual air\\n\\nemissions” for each alternative. JA834. But Appendix J is not in the record.\\n\\n Further, from our review, no other part of the record includes data that would\\n\\nfacilitate the comparison on which Appellants rely: the gross amount of NOx, CO, VOC,\\n\\nand PM10 created in the construction of a single vertical well. Those numbers might be in\\n\\nAppendix J—and they might even be the numbers Appellants include in their chart—but\\n\\nwe have no way of determining that because Appendix J is not in the record. We\\n\\n 42\\n\\ftherefore cannot evaluate whether, as Appellants argue, “the 3,945 existing vertically\\n\\ndrilled and the reasonably foreseeable 3,960 horizontally drilled Mancos Shale wells\\n\\nexceed the total impacts predicted in the 2003 EIS.” Aplts. Br. at 45.\\n\\n Appellants do not include the BLM’s complete analysis of air pollution in the\\n\\n2003 EIS, and therefore offer no way to compare the impacts contemplated by the 2003\\n\\nEIS with the impacts that could result from 3,960 horizontal Mancos Shale wells. The\\n\\nBLM’s NEPA analysis “is entitled to the presumption of regularity,” Stiles, 654 F.3d at\\n\\n1045, and Appellants have not carried their burden of demonstrating that the BLM acted\\n\\narbitrarily or capriciously.\\n\\n 3\\n\\n Appellants also argue that the total water used for drilling 3,960 horizontal\\n\\nMancos Shale wells will exceed the water use contemplated in the 2003 EIS, and the\\n\\nBLM therefore abused its discretion in tiering the EAs to the 2003 EIS, issuing FONSIs,\\n\\nand approving APDs. We agree with Appellants that, as to five challenged EAs, the\\n\\nBLM did not consider the cumulative water use associated with the 3,960 reasonably\\n\\nforeseeable horizontal Mancos Shale wells. Therefore, as to these five EAs, the BLM’s\\n\\nissuance of FONSIs and approval of APDs was arbitrary and capricious.\\n\\n Appellants’ water-resources argument, like their air-pollution argument, is based\\n\\nlargely on calculations in their comparison table. First, Appellants state that drilling a\\n\\nsingle horizontal well will use 1,020,000 gallons of water. In contrast, Appellants assert\\n\\nthe 2003 EIS predicted that drilling a single vertical well would use 283,500 gallons of\\n\\nwater. Appellants then multiply each of these numbers by the total number of wells\\n\\n 43\\n\\f(3,960 reasonably foreseeable horizontal wells; 3,945 already drilled vertical wells) and\\n\\narrive at a total water consumption amount of over 5 billion gallons of water. According\\n\\nto Appellants, the 2003 EIS contemplated total water use of just over 2.8 billion gallons.\\n\\nTherefore, argue Appellants, when the 3,960 reasonably foreseeable horizontal Mancos\\n\\nShale wells are taken into account, the projected water use increases by 82% over what\\n\\nthe 2003 EIS considered.\\n\\n Although we note some discrepancies between Appellants’ cited numbers and\\n\\nthe numbers in the record,17 we reject Federal Appellees’ argument that Appellants’\\n\\nwater-resources calculations “do not withstand scrutiny.” Fed. Aples. Br. at 33. Federal\\n\\nAppellees argue generally that water use could be decreased through “new strategies and\\n\\ntechnologies,” Fed. Aples. Br. at 35 (quotations omitted), but they do not point us to any\\n\\npart of the record that contradicts Appellants’ assertions that the cumulative water use\\n\\nassociated with the reasonably foreseeable 3,960 wells dramatically exceeds the total\\n\\n\\n 17\\n First, the average of 6,750 barrels of water per well on which Appellants\\nbase their vertical well calculations is the figure contemplated under Alternative A,\\nwhich the BLM did not select. For Alternative D, the BLM’s chosen alternative, the\\n2003 EIS predicted total water use of 7,000 acre-feet or an average of 0.70 acre-feet\\n(228,095 gallons) of water for each well.\\n And although the 2014 RFDS noted an average water use of 3.13 acre-feet\\n(1.02 million gallons) for the 55 horizontal wells that had reported water use\\nnumbers, other figures to which Appellants cite in their water use comparison are not\\nsupported by the record. Specifically, Appellants indicate that three EAs “calculat[e]\\n966,000 gallons per horizontal well.” Aplts. Br. at 44 n.21. Each of these three EAs,\\nhowever, estimate that “23,000 barrels of useable water would be required to drill\\neach well,” but “approximately 10,000 to 11,000 barrels would be recovered for\\nreuse,” resulting in a net water use for these wells of 12,000 to 13,000 barrels, or\\n504,000 to 546,000 gallons. JA1071, JA1075, JA1083. 966,000 gallons is the\\namount of water in 23,000 barrels, indicating that Appellants ignored the EAs’\\nprediction that water would be recovered for reuse.\\n 44\\n\\fwater use contemplated in the 2003 EIS. We conclude that, regardless of the minor\\n\\ninaccuracies in their calculations, Appellants have established that the difference between\\n\\nthe water use contemplated in the 2003 EIS and the water use associated with drilling the\\n\\nreasonably foreseeable horizontal Mancos Shale wells is more than a “mere[] flyspeck.”\\n\\nUtahns for Better Transp., 305 F.3d at 1163.\\n\\n None of the five EAs before us considered the cumulative impacts of the water use\\n\\nassociated with all 3,960 reasonably foreseeable horizontal Mancos Shale wells. The\\n\\nonly discussion of water resources in EA 2015-0036 is as follows:\\n\\n [T]he operator would follow ‘Pit Rule’ guidelines and Onshore Order\\n No. 1. Drilling operations would utilize a closed-loop system. Drilling\\n of the horizontal lateral would be accomplished with water-based mud.\\n All cuttings would be hauled to a commercial disposal facility or land\\n farm.\\n\\nJA1241. Three other EAs (EA 2015-0066, EA 2016-0029, and EA 2016-0200/2016-\\n\\n0076) all list “Groundwater Resources” as an “issue considered but not analyzed.”\\n\\nJA1305; JA1911–12; JA2082–83. Each of these EAs discusses the general process\\n\\nfor hydraulic fracturing, then concludes that “[n]o impacts to surface water or\\n\\nfreshwater-bearing groundwater aquifers are expected to occur from hydraulic\\n\\nfracturing of these proposed wells.” JA1912; JA2083; accord JA1306 (containing the\\n\\nsame substantive analysis with slightly different wording). EAs 2015-0036, 2015-\\n\\n0066, 2016-0029, and 2016-0200/2016-0076 contain no discussion of the cumulative\\n\\nimpacts related to water resources.\\n\\n EA 2014-0272 is the only EA that contains any discussion of the cumulative\\n\\nimpacts on water resources. Its cumulative-impact analysis states:\\n\\n 45\\n\\f Reasonably foreseeable development within the Largo sub-\\n watershed may include an estimated additional 1,811 oil and gas wells and\\n related facilities. Surface-disturbing activities that would be associated\\n with these actions may affect an estimated 6,756 acres ([2003 EIS], page 4-\\n 7). The [2003 EIS] determined that the primary cumulative impacts on\\n water quality would result from surface disturbance, which would generate\\n increased sediment yields ([2003 EIS] pages 4-123 and 4-124). Cumulative\\n effects to water resources from the proposed action would be maximized\\n shortly after construction begins and would decrease over time as\\n reclamation efforts progress.\\n\\n The proposed action would cumulatively contribute approximately\\n 20.0 acres of long-term disturbance in the watershed. Cumulative impacts\\n to surface waters would be related to short-term sedimentation or flow\\n changes. Surface-disturbing activities other than the proposed action that\\n may cause accelerated erosion include—but are not limited to—\\n construction of roads, other facilities, and installation of trenches for\\n utilities; road maintenance such as grading or ditch cleaning; public\\n recreational activities; vegetation manipulation and management activities;\\n prescribed and natural fires; and livestock grazing.\\n\\nJA1141. This analysis of the cumulative impacts on water resources does not address the\\n\\nwater consumption associated with the 3,960 reasonably foreseeable Mancos Shale wells.\\n\\n As to these five EAs, the BLM was required to, but did not, consider the\\n\\ncumulative impacts on water resources associated with drilling the 3,960 reasonably\\n\\nforeseeable horizontal Mancos Shale wells.18 The BLM therefore acted arbitrarily and\\n\\ncapriciously in issuing FONSIs and approving APDs associated with these EAs.\\n\\n Federal Appellees make two additional arguments in support of the BLM’s NEPA\\n\\nanalysis, both of which we reject.\\n\\n\\n\\n\\n 18\\n All five EAs referenced the 2003 EIS in their analysis of the cumulative\\nimpacts associated with air pollution, but not water use.\\n 46\\n\\f Federal Appellees first argue that Appellants advocate “too narrow a definition of\\n\\ncumulative impact—one that would require specific, quantitative measurements of all\\n\\npotential effects.” Fed. Aples. Br. at 33. Instead, argue Federal Appellees, the 2003 EIS\\n\\nanalyzed cumulative impacts via a “broad, qualitative approach . . . consistent with the\\n\\npurpose of [a] programmatic EIS.” Id. This argument fails because the record indicates\\n\\nthat (1) the BLM did quantify the cumulative water-resources impacts of proposed\\n\\ndrilling in the 2003 EIS, (2) the BLM could have quantified the cumulative water-\\n\\nresources impacts of the horizontal Mancos Shale wells, and (3) water use is an important\\n\\naspect of the environmental impacts associated with well drilling.\\n\\n First, the 2003 EIS quantified the total amount of water required for drilling\\n\\noperations in each considered alternative. Second, four of the five EAs we consider also\\n\\nincluded a quantitative measure of the amount of water the drilling operations for the\\n\\nproposed APDs would use. Finally, the 2003 EIS acknowledged that “[t]he primary\\n\\nissues and concerns regarding water resource problems caused by oil and gas\\n\\ndevelopment involve . . . water consumption and use.” JA2283. Likewise, the 2014\\n\\nRFDS noted that “[t]he development of the Mancos play will require additional fresh\\n\\nwater for stimulation purposes,” and acknowledged that “horizontal completions . . .\\n\\nrequire large volumes of water for hydraulic fracturing.” JA1686.\\n\\n We therefore reject Federal Appellees’ argument that the BLM could conduct an\\n\\nadequate cumulative-impacts analysis without quantifying the amount of reasonably\\n\\nforeseeable water use. The BLM had non-speculative figures that it could use to quantify\\n\\nthe cumulative impact of the drilling, and the water-resources impacts were important.\\n\\n 47\\n\\fThe BLM was therefore required to consider those impacts to comply with NEPA. See\\n\\nWyoming v. USDA, 661 F.3d at 1253 (rejecting the argument that an EIS failed to\\n\\nadequately consider cumulative impacts because “cumulative impacts that are too\\n\\nspeculative or hypothetical to meaningfully contribute to NEPA’s goals of public\\n\\ndisclosure and informed decisionmaking need not be considered”); Utah Envtl. Congress\\n\\nv. Troyer, 479 F.3d 1269, 1280 (10th Cir. 2007) (“An agency’s decision will be deemed\\n\\narbitrary and capricious if the agency entirely failed to consider an important aspect of\\n\\nthe problem[] . . . . [or] failed to base its decision on consideration of the relevant factors .\\n\\n. . .” (internal quotations and alterations omitted)).\\n\\n We also reject Federal Appellees argument that “the site-specific APD EAs\\n\\naddressed cumulative drilling effects that differ in type and magnitude from those\\n\\nexamined in the” 2003 EIS. Fed. Aples. Br. at 37. As discussed, the record indicates\\n\\notherwise. None of the five EAs we consider contain any analysis of the cumulative\\n\\nimpact to water resources from the 3,960 reasonably foreseeable horizontal Mancos Shale\\n\\nwells. And the record supports the conclusion that the water use associated with those\\n\\n3,960 wells far exceeds the water use considered in the 2003 EIS. The 2003 EIS’s water-\\n\\nresources analysis was therefore not “sufficiently comprehensive or adequate” to support\\n\\nthe proposed drilling, and the EAs were required to “provide any necessary analysis.” 43\\n\\nC.F.R. § 46.140(b). Because they did not, the BLM violated NEPA.\\n\\n Appellants have established that the water use associated with drilling the 3,960\\n\\nreasonably foreseeable horizontal Mancos Shale wells exceeded the water use\\n\\ncontemplated in the 2003 EIS in a way that made the BLM’s failure to consider the\\n\\n 48\\n\\fcumulative water impacts “significant enough to defeat the goals of informed\\n\\ndecisionmaking and informed public comment.” Utahns for Better Transp, 305 F.3d at\\n\\n1163. We conclude that the BLM acted arbitrarily and capriciously in issuing FONSIs\\n\\nand approving APDs associated with EAs 2014-0272, 2015-0036, 2015-0066, 2016-\\n\\n0029, and 2016-0200/2016-0076.\\n\\n VII\\n\\n Because we conclude that the BLM violated NEPA, we remand to the district\\n\\ncourt with instructions to vacate the FONSIs and APDs associated with EAs 2014-0272,\\n\\n2015-0036, 2015-0066, 2016-0029, and 2016-0200/2016-0076, and to remand those EAs\\n\\nto the BLM to conduct a proper NEPA analysis.\\n\\n “Under the APA, courts ‘shall’ ‘hold unlawful and set aside agency action’\\n\\nthat is found to be arbitrary or capricious.” WildEarth Guardians v. U.S. Bureau of\\n\\nLand Mgmt., 870 F.3d 1222, 1239 (10th Cir. 2017) (quoting 5 U.S.C. § 706(2)(A)).\\n\\n“Vacatur of agency action is a common, and often appropriate form of injunctive\\n\\nrelief granted by district courts.” Id. “In the past, we have done all of the following\\n\\nwhen placed in a similar posture: (1) reversed and remanded without instructions, (2)\\n\\nreversed and remanded with instructions to vacate, and (3) vacated agency\\n\\ndecisions.” Id. (collecting cases). And remand to the agency is usually the\\n\\nappropriate decision in this situation. See Middle Rio Grande Conservancy Dist. v.\\n\\nNorton, 294 F.3d 1220, 1225–26 (10th Cir. 2002) (“[A] reviewing court normally\\n\\nremands when it finds an agency’s decision not to conduct an EIS arbitrary or\\n\\ncapricious.”).\\n\\n 49\\n\\f Given our remand instructions to vacate, however, there is no need to also\\n\\n“enjoin any further ground-disturbing activities on the APDs” as Appellants request.\\n\\nAplts. Br. at 51. Once the APDs are vacated, drilling operations will have to stop\\n\\nbecause “[n]o drilling operations, nor surface disturbance preliminary thereto, may be\\n\\ncommenced prior to” APD approval. 43 C.F.R. § 3162.3-1(c). Because vacatur is\\n\\n“sufficient to redress [Appellants’] injury, no recourse to the additional and\\n\\nextraordinary relief of an injunction [is] warranted.” Monsanto Co. v. Geertson Seed\\n\\nFarms, 561 U.S. 139, 166 (2010).\\n\\n VIII\\n\\n For the foregoing reasons, we affirm in part and reverse in part the judgment of the\\n\\ndistrict court.19 We remand to the district court with instructions to vacate the FONSIs\\n\\nand APDs associated with EAs 2014-0272, 2015-0036, 2015-0066, 2016-0029, and\\n\\n2016-0200/2016-0076, and to remand those EAs to the BLM to conduct a proper NEPA\\n\\nanalysis.\\n\\n\\n\\n\\n 19\\n We deny Navajo Allottees Alice Benally, Lilly Comanche, Virginia\\nHarrison, Samuel Harrison, Dolora Hesuse, Verna Martinez, and Lois Phoenix’s\\nmotion to file an amicus brief because “the matters asserted in [Navajo Allottees’\\namicus brief] are [not] relevant to the disposition of the case,” Fed. R. App. P.\\n29(a)(3)(B).\\n 50\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2259,"cells":{"id":{"kind":"number","value":4617407,"string":"4,617,407"},"name":{"kind":"string","value":"UTAH NATIVE PLANT SOCIETY; Grand Canyon Trust, Plaintiffs-Appellants, v. UNITED STATES FOREST SERVICE; Tom Tidwell, in His Official Capacity as Chief of the U.S. Forest Service, Defendants-Appellees. State of Utah; State of Alaska; State of Colorado; State of Idaho; State of Kansas; State of Nebraska; State of Wyoming; New Mexico Department of Game and Fish; Association of Fish and Wildlife Agencies, Amici Curiae."},"name_abbreviation":{"kind":"string","value":"Utah Native Plant Society v. U.S. Forest Service"},"decision_date":{"kind":"string","value":"2019-05-07"},"docket_number":{"kind":"string","value":"17-4074"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Briscoe, Baldock, Eid\", \"parties\": \"\", \"opinions\": [{\"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n Tenth Circuit\\n\\n PUBLISH May 7, 2019\\n Elisabeth A. Shumaker\\n UNITED STATES COURT OF APPEALS Clerk of Court\\n\\n TENTH CIRCUIT\\n\\n\\nUTAH NATIVE PLANT SOCIETY;\\nGRAND CANYON TRUST,\\n\\n Plaintiffs - Appellants,\\nv. No. 17-4074\\nUNITED STATES FOREST\\nSERVICE; TOM TIDWELL, in his\\nofficial capacity as Chief of the U.S.\\nForest Service,\\n\\n Defendants - Appellees.\\n----------------------------------------------\\n\\nSTATE OF UTAH; STATE OF\\nALASKA; STATE OF COLORADO;\\nSTATE OF IDAHO; STATE OF\\nKANSAS; STATE OF NEBRASKA;\\nSTATE OF WYOMING; NEW\\nMEXICO DEPARTMENT OF GAME\\nAND FISH; ASSOCIATION OF FISH\\nAND WILDLIFE AGENCIES,\\n\\n Amici Curiae.\\n\\n\\n\\n APPEAL FROM THE UNITED STATES DISTRICT COURT\\n FOR THE DISTRICT OF UTAH\\n (D.C. No. 2:16-CV-00056-PMW)\\n\\fAaron Paul (Neil Levine with him on the briefs), Grand Canyon Trust, Denver,\\nColorado, for Plaintiffs-Appellants.\\n\\nJared C. Bennett, Assistant United States Attorney (John W. Huber, United States\\nAttorney, with him on the brief), Salt Lake City, Utah, for Defendants-Appellees.\\n\\nSean D. Reyes, Utah Attorney General, Tyler R. Green, Utah Solicitor General, and\\nMartin B. Bushman and Gregory Hansen, Assistant Utah Attorneys General, Salt\\nLake City, Utah, filed an Amicus Curiae Brief for the States of Utah, Alaska,\\nColorado, Idaho, Kansas, Nebraska, and Wyoming, and the New Mexico Department\\nof Game and Fish in support of Defendants-Appellees.\\n\\nCarol Frampton and Lane Kisonak, Association of Fish and Wildlife Agencies,\\nWashington, D.C., filed an Amicus Curiae Brief for the Association of Fish and\\nWildlife Agencies in support of Defendants-Appellees.\\n\\n\\nBefore BRISCOE, BALDOCK, and EID, Circuit Judges.\\n\\n\\nBALDOCK, Circuit Judge.\\n\\n\\n The La Sal Mountain Range, located in southeastern Utah on the Colorado\\n\\nPlateau, encompasses the vast acreage of the Manti-La Sal National Forest. The\\n\\nhighest elevations of the national forest support one of the rare alpine communities\\n\\nin the region. At these elevations, sensitive tundra vegetation grows among talus\\n\\nrock and rare plants find their home. To preserve this particular community,\\n\\nDefendant United States Forest Service (FS) in 1988 designated a 2,380 acre portion\\n\\nof the Manti-La Sal National Forest’s highest elevations, namely the summits and\\n\\nridges of Mt. Peale, Mt. Mellenthin, and Mt. Tukuhnikivatz, as the Mt. Peale\\n\\n\\n\\n 2\\n\\fResearch Natural Area (RNA). 1 According to an FS regulation, an RNA should\\n\\n“illustrate adequately or typify for research or educational purposes, the important\\n\\nforest and range types in each forest region, as well as other plant communities that\\n\\nhave special or unique characteristics of scientific interest and importance.” 36\\n\\nC.F.R. § 251.23. The applicable regulation further provides an RNA “will be\\n\\nretained in a virgin or unmodified condition except where measures are required to\\n\\nmaintain a plant community which the area is intended to represent.” Id. According\\n\\nto the instant suit, “until 2013, the Forest Service adhered to its rules and preserved\\n\\nthe [Mt. Peale RNA] in an unmodified natural state.”\\n\\n Now enter the State of Utah’s Division of Wildlife Resources (UDWR), the\\n\\n“wildlife authority for Utah . . . [s]ubject to the broad policymaking authority of the\\n\\nWildlife Board.” Utah Code Ann. § 23-14-1(1)(b), (2)(a). In June 2013, the Utah\\n\\nWildlife Board approved UDWR’s “Utah Mountain Goat Statewide Management\\n\\nPlan.” Among other things, UDWR’s plan anticipated the release of a target\\n\\npopulation of 200 mountain goats into the La Sal Mountains adjacent to the Manti-\\n\\n\\n\\n 1\\n The boundary of the Mt. Peale RNA runs roughly along the treeline\\nsurrounding these three major peaks but in some areas the boundary follows\\nidentifiable topographic features such as cliff bands and ridge spurs. We are told the\\nManti-La Sal National Forest is home to ten plant species found nowhere else in\\nUtah and one found nowhere else in the world. The FS has listed four of these plant\\nspecies, all found within the Mt. Peale RNA, as sensitive. According to the Forest\\nService Manual, “sensitive species” are those for which “population viability is a\\nconcern.”\\n\\n 3\\n\\fLa Sal National Forest for the express purposes of hunting and viewing. The FS,\\n\\nrightly concerned the goats might adversely affect the habitat of the higher alpine\\n\\nregions of the national forest, responded by asking UDWR to delay implementation\\n\\nof its plan while the FS in coordination with UDWR studied the plan’s expected\\n\\nimpact on the national forest and the RNA. Unfortunately, UDWR rejected the\\n\\nFS’s request for an outright delay. UDWR indicated it would begin implementing\\n\\nits plan by transplanting a small number of goats into the mountains, but would work\\n\\ncooperatively with the FS to assess impacts and develop a strategy to prevent\\n\\noverutilization of the habitat. In September 2013, UDWR released twenty mountain\\n\\ngoats on State lands adjacent to the Manti-La Sal National Forest. A year later,\\n\\nUDWR released an additional fifteen mountain goats on the same State lands.\\n\\n At this point, Plaintiff Grand Canyon Trust (GCT) said enough. 2 The goats,\\n\\nto no one’s surprise, had moved into the La Sal Mountains’ higher elevations. There,\\n\\naccording to GCT, the goats were wallowing and foraging within the national forest\\n\\nand more particularly within the Mt. Peale RNA. Noting ongoing harm to the Mt.\\n\\nPeale RNA and citing 36 C.F.R. § 251.23, GCT demanded the FS (1) prohibit\\n\\nUDWR from introducing additional mountain goats onto State lands adjacent to the\\n\\n\\n 2\\n GCT’s mission is to protect and restore the national forests and canyon\\ncountry of the Colorado Plateau. GCT’s Co-Plaintiff, Utah Native Plant Society, has\\nthe arguably narrower but overlapping mission of preserving native plant ecosystems\\nwithin Utah and the Intermountain West. Hereinafter we refer to the two Plaintiffs\\ncollectively as GCT.\\n\\n 4\\n\\fnational forest, (2) regulate UDWR’s occupancy and use of the national forest by\\n\\nrequiring it to obtain special use authorization before releasing additional mountain\\n\\ngoats on State lands, and (3) immediately remove the mountain goats already in the\\n\\nnational forest.\\n\\n The FS denied GCT any relief, at least for the time being. In a letter to GCT,\\n\\nthe Chief of the FS explained “[t]he Forest Service does not regulate or control\\n\\nUDWR’s activities that do not occur on NFS [National Forest Service] land, and your\\n\\nrequest that the Forest Service prevent UDWR from transplanting goats anywhere in\\n\\nthe La Sal Mountains is beyond the control of the Forest Service.” The Chief further\\n\\nexplained UDWR was not required to seek a special use permit to use the national\\n\\nforest before releasing the mountain goats on State lands: “[T]he UDWR did not\\n\\nrelease the mountain goats on NFS land, and therefore was not using or occupying\\n\\nNFS land at the time of the mountain goats release. The mountain goats have strayed\\n\\nonto adjacent NFS land, including the land within the Mount Peale RNA, after they\\n\\nwere released on non-Federal land by UDWR.” Lastly, the FS Chief took a “wait\\n\\nand see” attitude with regard to GCT’s request that the FS remove or destroy any\\n\\nmountain goats not only in the Mt. Peale RNA but throughout the national forest:\\n\\n [T]he Forest Service is working cooperatively with UDWR to evaluate\\n any resource impacts and to determine an appropriate action, including\\n consideration of removal of the mountain goats from the RNA or\\n reduction in herd numbers.\\n ***\\n\\n\\n 5\\n\\f Before initiating any such action, the Forest Service will work with\\n UDWR to gather and evaluate data sufficient to determine whether that\\n action is warranted, and then will work cooperatively with UDWR to\\n determine and implement the appropriate course of action.\\n\\nGCT’s lawsuit for declaratory and injunctive relief followed.\\n\\n I.\\n\\n GCT’s muddled complaint alleged five “claims for relief” against the FS\\n\\narising under federal law, all pursuant to the judicial review provisions of the\\n\\nAdministrative Procedures Act (APA), 5 U.S.C. §§ 701–706. GCT represents that\\n\\nonly two of its claims are before us on appeal. GCT’s first claim seeks relief under\\n\\nAPA § 706(2) and alleges the FS —knowing full well UDWR’s mountain goat plan\\n\\nwould result in goats migrating into the Manti-La Sal National Forest and the Mt.\\n\\nPeale RNA—acted arbitrarily, capriciously, and unlawfully by denying GCT’s three\\n\\ndemands for relief. Meanwhile, GCT’s second claim seeks relief under APA\\n\\n§ 706(1) and alleges the FS unlawfully failed to act by refusing to comply with the\\n\\nFS regulation mandating RNA’s “will be retained in a virgin or unmodified\\n\\ncondition.” 36 C.F.R. § 251.23.\\n\\n The FS moved to dismiss GCT’s complaint in its entirety under Fed. R. Civ.\\n\\nP. 12(b)(1) for failure to allege final agency action as required by APA § 704, and\\n\\nthus subject matter jurisdiction over the Government, which enjoys sovereign\\n\\nimmunity absent congressional waiver. The district court granted the motion:\\n\\n\\n\\n 6\\n\\f Plaintiffs have cleverly amalgamated federal law in an attempt to find\\n some pathway to judicial review. Pulling apart Plaintiffs’ contortions,\\n the court [concludes] that it has no jurisdiction to review the Forest\\n Service’s action or inaction with respect to the mountain goats’\\n occupation of the Manti-La Sal National Forest. . . . The Forest Service\\n has not determined whether the goats’ presence in the Manti-La Sal\\n National Forest violates federal law or the existing Forest Plan. Nor\\n has the Forest Service decided that it will never act on Plaintiffs’\\n requests. The State acted and now the Forest Service is in the\\n reactionary position attempting to determine what agency action, if any,\\n is warranted. Accepting Plaintiffs’ allegations as true, the court [holds]\\n that Plaintiffs have failed to provide the court any action or inaction on\\n behalf of the Forest Service that is reviewable under the APA.\\n\\nUtah Native Plant Soc’y v. United States Forest Serv., 2017 WL 822098, at\\n\\n*5 (D. Utah 2017) (unpublished). GCT appeals. Our jurisdiction arises under 28\\n\\nU.S.C. § 1291. Our review of the complaint’s sufficiency is de novo. See Jones v.\\n\\nNeedham, 856 F.3d 1284, 1289 (10th Cir. 2017).\\n\\n Because we consider the FS to make a facial attack on GCT’s complaint, we\\n\\n“apply a standard patterned on Rule 12(b)(6) and assume the truthfulness of the facts\\n\\nalleged.” Garling v. Envtl. Prot. Agency, 849 F.3d 1289, 1293 n. 3 (10th Cir. 2017).\\n\\nWe may supplement the complaint’s well-pleaded facts, however, with the contents\\n\\nof documents referred to therein “if the documents are central to [GTC’s] claim[s]\\n\\nand the parties do not dispute the documents’ authenticity.” Hampton v. Root9B\\n\\nTech., 897 F.3d 1291, 1297 (10th Cir. 2018). While we uphold dismissal of GCT’s\\n\\ncomplaint under the foregoing standards, we believe the district court missed the\\n\\nmark when it concluded that because the FS is currently in the process of deciding\\n\\n\\n 7\\n\\fwhat to do, if anything, about the goats’ presence in the national forest and RNA, it\\n\\nlacked jurisdiction to review the FS’s “action or inaction” in its entirety.\\n\\n II.\\n\\n We begin by analyzing GCT’s first claim which, as we have described, alleges\\n\\nthree instances of unlawful agency action. APA § 702 generally authorizes suit by\\n\\n“[a] person suffering legal wrong because of agency action.” “‘[A]gency action’\\n\\nincludes the whole or a part of an agency rule, order, license, sanction, relief, or the\\n\\nequivalent or denial thereof, or failure to act[.]” APA §551(13) (emphasis added).\\n\\nAPA § 704 requires the challenged “action”—or, more accurately in this case, the\\n\\nFS’s respective denials of GCT’s three demands—constitute “final agency action.”\\n\\nIn Bennett v. Spear, 520 U.S. 154, 177–78 (1997), the Supreme Court decided that\\n\\nbefore agency action becomes final, such action must meet two conditions: “First,\\n\\nthe action must mark the ‘consummation’ of the agency’s decisionmaking process—it\\n\\nmust not be of a merely tentative or interlocutory nature. And second, the action\\n\\nmust be one by which ‘rights or obligations have been determined,’ or from which\\n\\n‘legal consequences will flow[.]’” (citations omitted). APA § 704’s requirement of\\n\\nfinal agency action readily applies to GCT’s first claim for relief under APA\\n\\n§ 706(2) because subsection (2) directs a reviewing court to “hold unlawful and set\\n\\naside agency action . . . found to be . . . arbitrary, capricious, an abuse of discretion,\\n\\nor otherwise not in accordance with law[.]” (emphasis added).\\n\\n\\n 8\\n\\f A.\\n\\n The first instance of FS action about which GCT complains is the former’s\\n\\ndenial of any authority to prohibit UDWR from releasing mountain goats on Utah\\n\\nState lands adjacent to the Manti-La Sal National Forest. Such denial surely\\n\\nconstitutes final agency action. The FS explained that because it “does not regulate\\n\\nor control UDWR’s activities that do not occur on NFS land,” it cannot “prevent\\n\\nUDWR from transplanting goats anywhere in the La Sal Mountains.” GCT’s first\\n\\ndemand, in other words, was “beyond the control of the Forest Service.” This\\n\\ndetermination was not “merely tentative or interlocutory in nature”; it was\\n\\nconclusive. Bennett, 520 U.S. at 178. The FS told GCT that it did not have\\n\\nthe legal authority to prevent the State of Utah from releasing mountain goats\\n\\non State lands—first demand denied; end of discussion. The FS’s denial of\\n\\nGCT first demand was based on a “final and binding” decision that “mark[ed] the\\n\\n‘consummation’ of the agency’s decisionmaking process” and from which “‘rights\\n\\nand obligations have been determined.’” Id.\\n\\n Yet while the FS’s denial of GCT’s first demand constitutes final agency\\n\\naction, this demand still plainly fails as a matter of law. See Aguilera v. Kirkpatrick,\\n\\n241 F.3d 1286, 1290 (10th Cir. 2001) (recognizing that where a district court\\n\\ndismisses a complaint for lack of subject matter jurisdiction, we may affirm dismissal\\n\\nof the complaint for failure to state a claim under the same standards). GCT\\n\\n\\n 9\\n\\facknowledges, as it must, that Utah has broad trustee and police powers over wildlife\\n\\nwithin its borders. See Kleppe v. New Mexico, 426 U.S. 529, 545 (1976). But these\\n\\npowers, GCT tells us, are constrained by federal preemption principles derived from\\n\\nthe Constitution’s Supremacy Clause. See U.S. Const. art. VI, cl. 2. With this much\\n\\nwe agree. GCT next turns to the Constitution’s Property Clause, which provides:\\n\\n“Congress shall have Power to dispose of and make all needful Rules and\\n\\nRegulations respecting the Territory or other Property belonging to the United\\n\\nStates.” Id. art. IV, § 3, cl. 2. GCT tells us the Property Clause extends to activities\\n\\nthat endanger federal lands but are initiated on non-federal lands. 3 But as a mere\\n\\ngrant of power “to make all needful Rules and Regulations,” the Property Clause’s\\n\\nplain language is not self-executing and does not itself grant the FS authority over\\n\\nUtah State lands adjacent to the Manti-La Sal National Forest.\\n\\n Assuming the Property Clause reaches thus far, Congress, with the aim of\\n\\npreserving federal lands, might rely on it to enact legislation altering the State of\\n\\nUtah’s authority to manage wildlife on its own lands. Federal legislation, however,\\n\\ndoes not supercede the historic police powers of the States “unless that was the clear\\n\\n\\n\\n 3\\n Congress unquestionably has the authority to regulate conduct on private\\nlands that is injurious to the public domain. See United States v. Alford, 274 U.S.\\n264, 267 (1927) (“Congress may prohibit the doing of acts upon privately owned\\nlands that imperil the publicly owned forests.”); Camfield v. United States, 167 U.S.\\n518, 528 (1897) (Congress has the “constitutional right of protecting the public lands\\nfrom nuisances erected upon adjoining [private] property.”).\\n\\n 10\\n\\fand manifest purpose of Congress” in enacting such legislation. Puerto Rico Dept.\\n\\nof Consumer Affairs v. Isla Petrol. Corp., 485 U.S. 495, 500 (1988). While Congress\\n\\nmight enact legislation respecting national forests, the “clear and manifest purpose”\\n\\nof which is to preempt Utah’s traditional trustee and police powers as a sovereign to\\n\\nmanage wildlife within its borders, it has not done so. GCT points us to the Organic\\n\\nAdministration Act of 1897 (Organic Act), which provides: “The Secretary of\\n\\nAgriculture shall make provisions for the protection against destruction by fire and\\n\\ndepredations upon the . . . national forests . . . and he may make such rules and\\n\\nregulations and establish such service as will insure the objects of such reservations,\\n\\nnamely, to regulate their occupancy and use and to preserve the forests thereon from\\n\\ndestruction.” 16 U.S.C. § 551. But the Organic Act’s broad directive that the\\n\\nSecretary “make provisions for the protection against destruction by . . . depredations\\n\\nupon the . . . national forests,” hardly evidences a “clear and manifest” purpose to\\n\\nencroach upon State sovereignty and override Utah’s traditional management of\\n\\nwildlife within its borders outside the Manti-La Sal National Forest.\\n\\n Nor can we say Utah’s placement of mountain goats on State lands “stands as\\n\\nan obstacle to the accomplishment of the full purposes and objectives of Congress”\\n\\nin the management of the national forest. California Coastal Comm’n v. Granite\\n\\nRock Co., 480 U.S. 572, 581 (1987) (quoting Silkwood v. Kerr-McGee Corp., 464\\n\\nU.S. 238, 248 (1984)). Legislation supplemental to the Organic Act calling for\\n\\n\\n 11\\n\\f“cooperative federalism” between federal and state authorities in the area of wildlife\\n\\nmanagement illustrates the point. 4 The Multiple-Use Sustained-Yield Act of 1960\\n\\n(MUSYA), identifies a range of purposes national forests should serve. But the\\n\\nMUSYA also provides “[n]othing herein shall be construed as affecting the\\n\\njurisdiction and responsibilities of the several States with respect to wildlife and fish\\n\\non the national forests.” 16 U.S.C. § 528. If “nothing” in the MUSYA affects the\\n\\njurisdiction of the States with respect to wildlife on the national forests, surely\\n\\n“nothing” therein affects the jurisdiction of the States with respect to wildlife off the\\n\\nnational forests. The Federal Land Policy and Management Act of 1976 (FLPMA),\\n\\ndirects “the public lands be managed in a manner . . . that, where appropriate, will\\n\\npreserve and protect certain lands in their natural condition[.]” The FLPMA further\\n\\n\\n 4\\n Because most federal public land legislation calls for “cooperative\\nfederalism,” express preemption of state laws and regulations is rare in public land\\nlaw. But see, e.g., 16 U.S.C. § 1535(f) (stating state endangered species laws and\\nregulations cannot be less restrictive than federal laws and regulations). Absent\\nexpress preemption, state laws and regulations still may be preempted in either of\\ntwo ways:\\n\\n If Congress evidences an intent to occupy a given field [i.e., field\\n preemption], any state law falling within that field is pre-empted. If\\n Congress has not entirely displaced state regulation over the matter in\\n question, state law is still pre-empted to the extent it actually conflicts\\n with federal law [i.e., conflict preemption], that is, when it is\\n impossible to comply with both state and federal law, or where the state\\n law stands as an obstacle to the accomplishment of the full purposes\\n and objective of Congress.\\n\\nGranite Rock Co., 480 U.S. at 581 (citations omitted).\\n\\n 12\\n\\fprovides, however, that “nothing” in the FLPMA “shall be construed as . . . enlarging\\n\\nor diminishing the responsibility and authority of the States for management of fish\\n\\nand resident wildlife.” 43 U.S.C. §§ 1701(a)(8), 1732(b). And the National Forest\\n\\nManagement Act of 1976 directs the Secretary of Agriculture to develop, maintain,\\n\\nand revise land and resource management plans for the national forests “coordinated\\n\\nwith the land and resource management planning processes of State and local\\n\\ngovernments[.]” 16 U.S.C. § 1604(a). In short, the clarity and manifestness of\\n\\npurpose necessary in the federal statutory scheme GCT relies on to demand the FS\\n\\nprohibit the State of Utah from releasing mountain goats on State lands adjacent to\\n\\nthe Manti-La Sal National Forest is wholly lacking.\\n\\n Like Congress, a federal agency by way of congressional delegation of\\n\\nauthority also may preempt state laws and regulations. Fidelity Fed. Sav. & Loan\\n\\nAss’n v. De La Cuesta, 458 U.S. 141, 153–54 (1982). For example, after providing\\n\\nnotice and opportunity for comment, the FS might issue preemptive regulations\\n\\nimplementing the Organic Act’s directive that the Secretary of Agriculture make\\n\\nprovisions to protect the national forests from depredations. 16 U.S.C. § 551. Such\\n\\nfederal regulations preempt state law to the extent compliance with both is\\n\\nimpossible, or “where the scheme of federal regulation is sufficiently comprehensive\\n\\nto make reasonable the inference that Congress ‘left no room’ for supplementary\\n\\nstate regulation.” Hillsborough Cty. v. Automated Med. Laboratories, Inc., 471 U.S.\\n\\n\\n 13\\n\\f707, 713 (1985); see supra n.4. This assumes, of course, such regulations are\\n\\nconsistent with a reasonable interpretation of the Organic Act and the Secretary\\n\\nreasonably exercised Congress’s delegation of authority. See State of Kansas ex rel.\\n\\nTodd v. United States, 995 F.2d 1505, 1509 (10th Cir. 1993) (citing De La Cuesta,\\n\\n458 U.S. at 153–54 and Chevron, Inc. v. Nat. Res. Def. Counsel, 467 U.S. 837, 844\\n\\n(1984)). But to say the FS may issue preemptive regulations is not to say it may do\\n\\nso subtly. 5 See Isla Petrol. Corp., 485 U.S. at 500. Like our review of the Organic\\n\\nAct and related legislation, where the States have traditionally exercised trustee and\\n\\npolice powers over a field, we assume federal regulations do not preempt the States’\\n\\nexercise of these historic powers unless their intent to do so is “clear and manifest.”\\n\\nHillsborough Cty., 471 U.S. at 715–16.\\n\\n Notably, nothing in 36 C.F.R. § 251.23, the sole FS regulation on which all of\\n\\nGCT’s demands rest, expresses an intent to preempt the State of Utah’s management\\n\\nof wildlife on State lands. Recall § 251.23 is the FS regulation which provides that\\n\\nan RNA within a national forest “will be retained in a virgin or unmodified\\n\\n\\n\\n 5\\n To the degree GCT relies on the Forest Service Manual, the Manti-La-Sal\\nNational Forest Plan, and the Mt. Peale RNA Establishment Record to support its\\nvarious demands—and it does so extensively throughout its complaint—we note such\\ndocuments do not carry the force of law. See Christensen v. Harris Cty., 529 U.S.\\n576, 587 (2000) (distinguishing agency adjudications and notice-and-comment\\nrulemaking, both of which have the force of law, from opinion letters, policy\\nstatements, agency manuals, enforcement guidelines, and the like, all of which lack\\nthe force of law).\\n\\n 14\\n\\fcondition.” But the FS has never proposed the sweeping interpretation of § 251.23\\n\\nthat GCT now endorses, perhaps because in most instances means exist to prevent\\n\\ndepredations of the national forests and RNAs short of wholly disrespecting State\\n\\nsovereignty over State lands, e.g., removing destructive wildlife from the forest.\\n\\nBecause a federal agency may address problems in detail and speak through a number\\n\\nof means, we expect an agency will clearly tell us if it intends for its regulations to\\n\\npreempt the historic police powers of the States. Hillsborough Cty., 471 U.S. at 718;\\n\\nsee also Granite Rock Co., 480 U.S. at 583 (“[I]t is appropriate to expect an\\n\\nadministrative regulation to declare any intention to pre-empt state law with some\\n\\nspecificity.”); Integrity Mgmt. Int’l, Inc. v. Tombs & Sons, Inc., 836 F.2d 485,\\n\\n492–93 (10th Cir. 1987) (“[U]nless an agency has explicitly stated an intent to\\n\\npreempt state law, there is a presumption that no such intent exists.”).\\n\\n Here, the FS has never expressed an intent—let alone a clear and manifest\\n\\none—to preempt the power of the State of Utah in its sovereign capacity to manage\\n\\nwildlife on its own public lands, regardless of where such wildlife wanders off.\\n\\nWhether the FS has the authority to do so by way of congressional delegation\\n\\npursuant to the Organic Act is beside the point. We need do no more than apply the\\n\\napplicable law to the well-pleaded factual allegations of GCT’s complaint (sans the\\n\\nmyriad of legal arguments and conclusions contained therein) to sustain the FS’s\\n\\ndetermination that it lacked the legal authority to prohibit the State of Utah, or more\\n\\n\\n 15\\n\\fparticularly UDWR, from releasing mountain goats on State lands adjacent to the\\n\\nManti-La Sal National Forest. The FS’s legal conclusion that under federal law it\\n\\ncould not prohibit the State of Utah from releasing mountain goats on State lands\\n\\nwas neither “arbitrary, capricious, an abuse of discretion, [n]or otherwise not in\\n\\naccordance with law.” 5 U.S.C. § 706(2)(A).\\n\\n B.\\n\\n The second agency action about which GCT complains is the FS’s denial of\\n\\nthe authority to regulate the State of Utah’s “occupancy” and “use” of the Manti-La\\n\\nSal National Forest by requiring UDWR to obtain a special use permit before\\n\\nreleasing mountain goats on State lands. Like the FS’s denial of GCT’s first\\n\\ndemand, its denial of GCT’s second demand also constitutes final agency action\\n\\nunder the APA. The FS informed GCT that because UDWR released the mountain\\n\\ngoats on State lands, UDWR “was not using or occupying NFS land at the time of\\n\\n[their] release,” and therefore special use authorization from the FS was not required\\n\\nunder FS regulations—second demand denied; end of discussion. This second denial\\n\\nof relief, like the first, was not “tentative or interlocutory,” but was “final and\\n\\nbinding.” Bennett, 520 U.S. at 178. Once the FS decided UDWR was not required\\n\\nto obtain a special use permit before releasing the mountain goats on State lands\\n\\nnothing else was left to decide and legal rights had been determined.\\n\\n\\n\\n\\n 16\\n\\f Still, GCT’s second demand—as novel and far-reaching as its first—also\\n\\nplainly fails as a matter of law. Absent “special use authorization,” Forest Service\\n\\nregulations generally prohibit “uses [except those otherwise enumerated] of National\\n\\nForest System lands . . . and resources.” 36 C.F.R. §251.50. In particular, § 251.23\\n\\nprohibits “occupancy [of an RNA] under a special use permit . . . unless authorized\\n\\nby the Chief of the FS.” GCT says the mountain goats’ release point on State lands\\n\\nis irrelevant to its argument regarding UDWS’s occupancy and use of the national\\n\\nforest. According to GCT, the FS is authorized “to regulate and prohibit the goat\\n\\nintroductions because the State airlifted them to the La Sal Mountains knowing the\\n\\ngoats would use and harm the Manti-La Sal National Forest and Mt. Peale RNA.”\\n\\nTwo pertinent points demonstrate the fallacy of GCT’s argument —based entirely on\\n\\nUDWR’s scienter—that the mountain goats are, in effect, instrumentalities of the\\n\\nState whose presence in the national forest and RNA constitute the State’s occupancy\\n\\nand use of the forest.\\n\\n Federal ownership of lands within a State does not in itself withdraw those\\n\\nlands from the jurisdiction of the State. Kleppe, 426 U.S. 544. “Absent consent or\\n\\ncession a State undoubtedly retains jurisdiction over federal lands within its\\n\\nterritory,” subject to Congress’s “power to enact legislation respecting those lands\\n\\npursuant to the Property Clause.” Id. at 543–44. We have already observed that\\n\\nUtah, not as a private property owner but in its sovereign capacity, has historically\\n\\n\\n 17\\n\\fpossessed broad trustee and police powers over wildlife within its borders. See id.\\n\\nat 545. Just as we did in our preceding analysis regarding the State’s authority to\\n\\nrelease wildlife on its own lands, we assume neither Congress nor the FS intended\\n\\nits enactments to alter the State of Utah’s “historic police powers to manage wildlife\\n\\non federal lands within its borders” unless such intent is “clear and manifest.”\\n\\nWyoming v. United States, 279 F.3d 1214, 1231 (10th Cir. 2002) (emphasis added).\\n\\nAnd again, at the same time, we remain mindful that we “must give full effect to\\n\\nevidence that Congress considered, and sought to preserve, [Utah’s] coordinate\\n\\nregulatory role in our federal scheme.” Id. (emphasis added) (quoting California v.\\n\\nFERC, 495 U.S. 490, 497 (1990)); see supra at 11–13.\\n\\n Where the FS has never asserted exclusive jurisdiction over the management\\n\\nof wildlife in the Manti-La Sal National Forest, GCT’s argument that the State of\\n\\nUtah needs a special use permit before releasing wildlife on State lands—regardless\\n\\nof whether everyone knew such wildlife would end up in the national forest and\\n\\nRNA—runs counter to Congress’s determination, and the FS’s obvious recognition\\n\\nin this case, that the State retains a measure of sovereignty over wildlife management\\n\\nwithin the national forest. See Defenders of Wildlife v. Andrus, 627 F.2d 1238, 1248\\n\\n(D.C. Cir. 1980) (“Despite its ability to take control into its own hands, Congress\\n\\nhas traditionally allotted the authority to manage wildlife to the States.”); 36\\n\\nC.F.R. § 241.2 (FS regulation calling for cooperation with state officials in the\\n\\n\\n 18\\n\\fmanagement of wildlife within the national forests). That the State’s wildlife\\n\\nmanagement responsibilities within the national forest are not exclusive and may be\\n\\noverridden under appropriate circumstances does not mean those management\\n\\nresponsibilities are meaningless absent federal law to the contrary. See Baldwin v.\\n\\nFish and Game Comm’n, 436 U.S. 371, 386 (1978).\\n\\n The next and perhaps more salient point concerning GCT’s second demand is\\n\\nthe mountain goats are ferae naturae or wild animals. See generally Pierson v. Post,\\n\\n3 Cai. 175 (N.Y. Sup. Ct. 1805). As a means of reducing goat populations in other\\n\\nmountainous areas of the State, UDWR captured the goats and then released them\\n\\nonto State lands adjacent to the Manti-La Sal National Forest. Because wild animals\\n\\nare not the private property of those whose lands they occupy, the State of Utah, at\\n\\nleast once it released the goats back into the wild, did not own the goats in the sense\\n\\nthat UDWS’s failure to control their expected movement constituted a sort of\\n\\ntrespass onto national forest lands requiring special use authorization from the FS.\\n\\nOur en banc decision in Mountain States Legal Found. v. Hodel, 799 F.2d 1423 (10th\\n\\nCir. 1986) (en banc) settles the score. In that case, we rejected a private\\n\\nassociation’s argument under the Wild Free-Roaming Horses and Burros Act, 16\\n\\nU.S.C. §§ 1331–37, that “wild horses are . . . instrumentalities of the federal\\n\\ngovernment whose presence on the association’s property constitutes a permanent\\n\\ngovernmental occupation.” Id. at 1428. We explained:\\n\\n\\n 19\\n\\f Neither state nor federal authority over wildlife is premised on any\\n technical “ownership” of wildlife by the government. Although older\\n decisions sometimes referred to government “ownership” of wildlife,\\n that language has been deemed “a fiction expressive in legal shorthand\\n of the importance to its people that a State have power to preserve and\\n regulate the exploitation of an important resource.” Toomer v. Witsell,\\n 334 U.S. 385, 402 (1948). As the Supreme Court declared, “[I]t is pure\\n fantasy to talk of ‘owning’ wild fish, birds, or animals. Neither the\\n States nor the Federal Government . . . has title to these creatures until\\n they are reduced to possession by skillful capture. Douglas v. Seacoast\\n Prod., Inc., 431 U.S. 265, 284 (1977) . . . .\\n\\nMountain States Legal Found., 799 F.2d at 1426. 6\\n\\n The FS’s conclusion regarding GCT’s second demand, namely that it could not\\n\\nrequire the State of Utah to seek special use authorization to occupy and use the\\n\\nManti-La Sal National Forest and Mt. Peale RNA before releasing mountain goats\\n\\non State lands adjacent to the forest, was neither arbitrary, capricious, nor an abuse\\n\\nof discretion, but was entirely consistent with applicable law. Under a proper\\n\\nassessment of this case, GCT’s second demand simply proves too much. The answer\\n\\n\\n 6\\n GCT’s reliance on Light v. United States, 220 U.S. 523 (1911) to support its\\nsecond demand is misplaced. In Light, a private property owner permitted his\\ndomestic cattle, a herd in the range of 500, to move from his property to a Forest\\nReserve and graze thereon in violation of federal regulations establishing grazing\\ndistricts on which only a limited number of cattle were allowed. The Supreme Court\\nupheld an injunction prohibiting the landowner “from pasturing his cattle on the . . .\\nForest Reserve, because he had refused to comply with the regulations adopted by\\nthe Secretary of Agriculture, under the authority conferred by [the Organic Act], to\\nmake rules and regulations as to the use, occupancy, and preservation of forests.”\\nId. at 534. One of among other reasons this case is unlike Light is because once the\\nState released the mountain goats onto State lands and into the wild, any arguable\\nownership interest the State temporarily had in the goats upon their capture\\ncomparable to that of a chattel owner was no more.\\n\\n 20\\n\\fto the legal question of whether federal law required the State of Utah as sovereign\\n\\nto obtain special use authorization to occupy and use the national forest before\\n\\nreleasing mountain goats on State lands is a resounding no.\\n\\n C.\\n\\n Our conclusions thus far—that the State of Utah presently has the authority to\\n\\nrelease mountain goats on State lands adjacent to the Manti-La Sal National Forest\\n\\nand may do so absent special use authorization from the FS—say nothing about the\\n\\nFS’s ability to manage the mountain goats consistent with federal policies and\\n\\nobjectives once the goats enter the national forest and more specifically the Mt. Peale\\n\\nRNA. “The governmental trust responsibility for wildlife is lodged initially in the\\n\\nStates, but only in so far as its exercise may not be incompatible with, or restrained\\n\\nby [federal law].” Mountain States Legal Found., 799 F.2d at 1426 (quotations\\n\\nomitted). And this brings us to the third demand of GTC’s first claim which posits\\n\\nthe FS remove the goats from the national forest and RNA instanter.\\n\\n Lest it become too comfortable with our analysis thus far, we remind the State\\n\\nof Utah, who appears herein as amicus together with seven other States in support\\n\\nof the FS, that the Supreme Court has “repeatedly observed that the power over the\\n\\npublic lands . . . entrusted to Congress is without limitations.” Granite Rock Co.,\\n\\n480 U.S. at 580 (quotations omitted). And the power of the FS under the Organic\\n\\nAct to protect the habitat of national forests “does not admit of doubt.” Hunt v.\\n\\n\\n 21\\n\\fUnited States, 278 U.S. 96, 100 (1928). In Hunt, deer had “greatly injured” the lands\\n\\nof a national game preserve inside a national forest “by overbrowsing upon and\\n\\nkilling valuable young trees, shrubs, bushes, and forage plants.” Id. at 99. The\\n\\nSupreme Court upheld the power of the Secretary of Agriculture under the Organic\\n\\nAct to order the destruction of the deer where necessary to protect the game preserve\\n\\nand national forest. Several years later, in New Mexico State Game Comm’n v.\\n\\nUdall, 410 F.2d 1197 (1969), we held the supervisory powers granted the Secretary\\n\\nof Interior over the management of national parks authorized the Secretary, without\\n\\nthe State’s approval, to direct the killing of a number of deer within a national park\\n\\nfor an ecological study prior to any serious deterioration of habitat. Opining that\\n\\n“[i]n protecting the park property it is immaterial that the United States does not\\n\\nhave exclusive jurisdiction over the land within [the park],” we rejected the State’s\\n\\nargument that “the deer-killing program could be undertaken only after a showing\\n\\nor a finding that there was existing depredation caused by the deer.” Id. at 1199,\\n\\n1201. Given these controlling precedents, we do not question the authority of the FS\\n\\nunder the Organic Act and related legislation—if exercised as a valid preventative\\n\\nor restorative measure—to remove the mountain goats from, or reduce the size of the\\n\\nherd now residing in, the Manti-La Sal National Forest and Mt. Peale RNA.\\n\\n As the reader understands by now, however, the preliminary inquiry is whether\\n\\nGCT’s first claim alleges “final agency action” by asserting the FS did not meet its\\n\\n\\n 22\\n\\fdemand to remove the goats from the national forest and RNA. GCT’s complaint\\n\\nstates that in May 2015, the Regional Forester responded to GCT’s demand to\\n\\nremove the goats: “The Forest Service reiterated that it was developing, with the\\n\\nState’s assistance, a five-year monitoring plan for four rare alpine plants where\\n\\nmonitoring results would be evaluated annually.” The Forester’s letter explained:\\n\\n The Forest Service received your Survey Report on the impacts of\\n mountain goats on plants with special status in November of 2014.\\n While the report suggests negative impacts to plants from mountain\\n goat foraging, it also indicates a need for more refined data collection.\\n In regard to your monitoring documenting trampling evidence within\\n the Mount Peale RNA, evidence similar to that observed by GCT was\\n documented in the area prior to goat introductions, and your trampling\\n evidence was not clearly demonstrated to be the result of mountain goat\\n use. In addition, your observations were not within a fixed area plot,\\n so the density of trampling occurrences cannot be calculated, or\\n compared to future data to establish a trend.\\n\\nAfter the Regional Forester rejected GCT’s demand to remove the goats from the\\n\\nnational forest immediately, GCT unsuccessfully petitioned the Chief of the FS to\\n\\norder the goats removed. GCT’s complaint represents the Chief denied its third\\n\\ndemand and informed GCT the FS “would gather and evaluate the goats’ impact and\\n\\nwork with the State to determine whether additional actions were warranted.”\\n\\nReferring to the Regional Forester’s prior letter to GCT, the Chief reiterated, “there\\n\\nis no compelling evidence to show that the mountain goats introduced by UDWR are\\n\\ncausing immediate damage to NFS land or resources.”\\n\\n\\n\\n\\n 23\\n\\f We do not deny that reasonable minds presently may differ about the impact\\n\\nthe mountain goats are having on the Mt. Peale RNA. In fact, some disagreement\\n\\nappears within the FS itself. As we have observed on multiple occasions, “habitat\\n\\nmanagement is a delicate venture.” Wyoming, 279 F.3d at 1239 (brackets omitted)\\n\\n(quoting Sierra Club-Black Hills Grp. v. United States Forest Serv., 259 F.3d 1281,\\n\\n1286 (10th Cir. 2001)). But the present disagreement over whether the FS must send\\n\\nthe goats packing far away from the Manti-La Sal National Forest, no matter how\\n\\npressing GCT believes the situation to be, does not alone imbue with finality the\\n\\nFS’s decision to study the matter further, such that relief upon proper proof is\\n\\ncurrently available to GCT under APA § 706(2). The FS has acknowledged the\\n\\nsituation and informed GCT that it needs a reasonable period of time to decide\\n\\nhow to proceed. 7 See Oil, Chemical and Atomic Workers Int’l Union v. Zegeer, 768\\n\\n\\n 7\\n The Regional Forester outlined the FS’s intentions in her May 2015 letter:\\n\\n The [FS] is continuing to work with UDWR to evaluate [habitat]\\n impacts. We have developed a rigorous five year monitoring plan to\\n evaluate population trends of four rare alpine plant species and track\\n shifts in species composition and ground cover in the alpine zone,\\n including the Mount Peale [RNA]. The monitoring protocol includes\\n recording direct impacts by grazing animals and uses motion sensing\\n camera[s] to determine the animal species involved. Monitoring data\\n will be analyzed and evaluated annually relative to Forest Plan direction\\n for rare plant species and Federal standards for protection of [RNAs].\\n Based on the results of each annual evaluation, the [FS] will work\\n cooperatively with UDWR to determine an appropriate course of action\\n concerning management of the mountain goats, including whether or not\\n removal or reduction in population objectives is warranted.\\n\\n 24\\n\\fF.2d 1480, 1485 (D.C. Cir. 1985) (concluding the APA indicates a congressional\\n\\nview that federal agencies should act within reasonable time frames). This is the\\n\\nbureaucratic process—like it or not. To suggest the refusal of the FS to remove the\\n\\ngoats from the national forest and RNA this very moment is a sort of agency action\\n\\n“mark[ing] the ‘consummation’ of the agency’s decisionmaking process,” rather than\\n\\na “tentative or interlocutory” action, is simply inconsistent with the complaint’s\\n\\nfactual allegations and the underlying documents on which those allegations rely.\\n\\nBennett, 520 U.S. at 178. The district court was correct in holding it lacked subject\\n\\nmatter jurisdiction to review the FS’s denial of GCT’s third demand for want of final\\n\\nagency action.\\n\\n III.\\n\\n While the FS’s “wait and see” response to GCT’s demand that it remove the\\n\\nmountain goats from the Manti-La Sal National Forests does not constitute “final\\n\\nagency action” under the APA, GCT’s second claim is that such response does\\n\\nconstitute a “failure to act”, redresssable under APA § 706(1) as agency action\\n\\n“unlawfully withheld.” According to GCT, 36 C.F.R. § 251.23 contains a categorical\\n\\nimperative the FS refuses to heed: “Research Natural Areas will be retained in a\\n\\nvirgin or unmodified condition except where measures are required to maintain a\\n\\nplant community which the area is intended to represent.”\\n\\n\\n\\n\\n 25\\n\\f APA § 704’s requirement of final agency action does not square well with a\\n\\ndefinition of “agency action” that includes a “failure to act.” 5 U.S.C. § 551(13).\\n\\nAnd obviously, the test the Supreme Court has set forth to determine whether agency\\n\\naction is final does not readily accommodate an agency’s failure to act. Bennett, 520\\n\\nU.S. at 177–78. “If an agency has failed to act with respect to a matter that a\\n\\ncomplaining party seeks to compel under § 706(1), it is hard to comprehend the\\n\\ncontested inaction as ‘final action’ as that term is defined in Bennett v. Spear.”\\n\\nWestern Org. of Resource Councils v. Zinke, 892 F.3d 1234, 1247 (D.C. Cir. 2018)\\n\\n(Edwards, J., concurring). Indeed, we have noted the problem and observed that\\n\\nsome courts have “implicitly recognized that unlawfully withheld actions are\\n\\nconsidered final under § 704.” Southern Utah Wilderness Alliance v. Norton, 301\\n\\nF.3d 1217, 1229 n.9 (10th Cir. 2002), rev’d 542 U.S. 55 (2004) (hereinafter SUWA).\\n\\n Fortunately, in SUWA the Supreme Court considered “what limits the APA\\n\\nplaces upon judicial review of agency inaction.” SUWA, 542 U.S. at 61. To “protect\\n\\nagencies from undue judicial interference with their lawful discretion,” among other\\n\\nreasons, the Court held “a claim under § 706(1) can proceed only where a plaintiff\\n\\nasserts that an agency failed to take a discrete agency action that it is required to\\n\\ntake.” Id. at 64, 66; see Wyoming v. United States Dept. of Interior, 839 F.3d 938,\\n\\n942 (10th Cir. 2016). The Supreme Court explained APA § 706(1) carries forward\\n\\ncourts’ traditional practice of reviewing a governmental entity’s failure to act by way\\n\\n\\n 26\\n\\fof writ of mandamus. “The mandamus remedy was normally limited to enforcement\\n\\nof ‘a specific, unequivocal command,’ the ordering of a ‘precise act about which an\\n\\nofficial had no discretion whatever.’” SUWA, 542 U.S. at 63 (brackets, citations\\n\\nand ellipses omitted). Consistent with such practice, the Court reasoned “§706(1)\\n\\nempowers a court only to compel an agency to perform a ministerial or non-\\n\\ndiscretionary act or to take action upon a matter, without directing how it shall act.”\\n\\nId. at 64 (quotations omitted).\\n\\n The language of the FS regulation at issue in this case, § 251.23, certainly is\\n\\nmandatory as to the ultimate objective. The regulation plainly states RNA’s “will\\n\\nbe retained in a virgin or unmodified condition[.]” The regulation, however, leaves\\n\\nentirely to the FS the decision of how best to achieve this objective. Indeed, GCT’s\\n\\ncomplaint recites provisions of the Forest Service Manual (FSM) which suggest as\\n\\nmuch. The complaint states FSM 4063.30(4) advises the FS to “‘[r]emove exotic\\n\\nplants or animals [from an RNA] to the extent practicable.’” (emphasis added).\\n\\nMeanwhile, FSM 4063.32 advises: “If exotic plants or animals have been introduced\\n\\ninto an established [RNA], the Station Director and the Regional Forester exercise\\n\\ncontrol measures that are in keeping with established management principles and\\n\\nstandards to eradicate them, when practical.” (emphasis added).\\n\\n So assuming the mountain goats presence within the Manti-La Sal National\\n\\nForest and Mt. Peale RNA is inconsistent with § 251.23’s objective, how shall the\\n\\n\\n 27\\n\\fFS proceed? FSM 4062.30(4) tells us removing the mountain goats from the national\\n\\nforest and RNA is one option. FSM 4063.32 tells us eradicating or destroying the\\n\\ngoats is another option. Or perhaps a reduction in the size of the herd would suffice.\\n\\nMaybe a fence or other barrier to surround the goats, the habitat, or both would be\\n\\nfeasible. Maybe a spray or other similar mean exists that would not harm the foliage\\n\\nwithin the RNA but make it less desirable to a mountain goat’s palate. Section\\n\\n251.23 does not foreclose any of these options. In other words, the FS regulation\\n\\nprovides us with no discernible rules under which we may direct the FS to act in\\n\\nexercising its enforcement powers. Section 251.23 simply does not call for a discrete\\n\\naction that will assure us the RNA “will be retained in a virgin or unmodified\\n\\ncondition[.]” See Black’s Law Dictionary 565 (10th ed. 2014) (defining “discrete”\\n\\nas “[i]individual; separate; distinct”). We are not experts in the field of habitat\\n\\nmanagement and preservation and surely have no business attempting to instruct the\\n\\nFS how best to achieve § 251.23’s objective. See SUWA, 542 U.S. at 66–67. The\\n\\ncrux of the matter is GTC’s complaint does not allege the FS has failed to take a\\n\\ndiscrete agency action that FS regulations require it take. See SUWA, 542 U.S. at\\n\\n66. Therefore GCT’s second claim based on the FS’s failure to act is not cognizable.\\n\\n ***\\n\\n As modified, the judgment of the district court dismissing GCT’s complaint\\n\\nis AFFIRMED.\\n\\n\\n 28\\n\\fNo. 17-4074, tah Native Plant Society, et al. v. United States Forest Service, et al.\", \"author\": \"BALDOCK, Circuit Judge.\"}, {\"type\": \"concurrence\", \"author\": \"EID\", \"text\": \"EID, J., concurring in part and concurring in the judgment in part.\\n\\n\\n I agree with the majority that the U.S. Forest Service’s (USFS) refusal to remove\\n\\nthe mountain goats does not constitute final agency action because the USFS’s letter\\n\\ndeferred agency action pending future research and data collection regarding the goats’\\n\\nimpact. Maj. Op. at 21-25. I would conclude, however, that the USFS’s “wait and see”\\n\\napproach also applies to the request to subject the goats to the special use permit process\\n\\nand to prevent future releases by the state. Contra id. at 9-21. Accordingly, I would\\n\\naffirm the district court’s decision that final agency action is lacking in its entirety in this\\n\\ncase, and thus would not reach the merits.\\n\\n Assessing whether there is final agency action in this case rests upon how we\\n\\ninterpret the August 7, 2015 letter sent by the Chief of the USFS, Thomas L. Tidwell, to\\n\\nthe plaintiffs. In the letter, Tidwell states that “the Forest Service is working\\n\\ncooperatively with [the state] to evaluate any resource impacts and to determine an\\n\\nappropriate action, including consideration of removal of the mountain goats from the\\n\\nRNA1 or reduction in herd numbers.” App 78 (emphasis added). In other words, the\\n\\nUSFS is performing further evaluation of goat impact before it takes “an appropriate\\n\\naction.” I read “appropriate action” to leave all three possible actions—removal,\\n\\n\\n\\n 1\\n “RNA” refers to the Mount Peale Research Natural Area. Forest Service\\nregulations provide that an RNA “will be retained in a virgin or unmodified condition\\nexcept where measures are required to maintain a plant community which the area is\\nintended to represent.” 36 C.F.R. § 251.23\\n\\fregulation, and prevention—on the table. In my view, simply because the sentence\\n\\nspecifically states that an “appropriate action” might include the possibility of removal\\n\\ndoes not exclude regulation and prevention as “appropriate action[s].”\\n\\n This interpretation is reinforced by the May 12, 2015 letter from Nora B. Rasure,\\n\\nRegional Forester, to the plaintiffs, from which they appealed to Tidwell. In that letter,\\n\\nRasure expressly lays out the plaintiffs’ three requests—namely, “your letter asserts that\\n\\nthe [USFS] has authority [1] to remove the mountain goats that have been transplanted,\\n\\n[2] prevent transplant of more mountain goats, and [3] require [the state] to obtain\\n\\n‘special use authorizations’ in order to transplant any more mountain goats, or maintain\\n\\nexisting goats, that may be located on [Forest Service land].” App 75. Rasure ends the\\n\\nletter, in a statement echoed by Tidwell, with the following: “Based on the results [of the\\n\\nfurther research and data collection], the Forest Service will work cooperatively with [the\\n\\nstate] to determine an appropriate course of action concerning management of the\\n\\nmountain goats, including whether or not removal or reduction in population objectives is\\n\\nwarranted.” App 76 (emphasis added). Again, based on the language that defers a\\n\\ndecision on an appropriate action, the USFS is adopting a “wait and see” approach as to\\n\\nall options—including removal, regulation, and prevention—regarding the mountain\\n\\ngoats.\\n\\n The district court2 concluded that the Tidwell letter indicated “that before the\\n\\nagency could initiate any action,” the USFS had to gather additional data “sufficient to\\n\\n\\n 2\\n The parties consented to having a magistrate judge adjudicate this case pursuant\\nto 28 U.S.C. § 636(c).\\n 2\\n\\fdemonstrate agency action was warranted.” Dist. Ct. Op. at 6. I agree, and would find\\n\\nthat there is no final agency action for us to review in this case. See McKeen v. United\\n\\nStates Forest Service, 615 F.3d 1244, 1253 (10th Cir. 2010) (“Pursuant to the APA, we\\n\\nhave jurisdiction to review only ‘final agency actions’”).\\n\\n In concluding that there is final action regarding permitting, the majority focuses\\n\\non the second paragraph of the Tidwell letter, which states that:\\n\\n In our response dated May 12, 2015, [Rasure] stated the Forest Service did not\\n allow or in any way sanction the introduction of mountain goats by the [state]. In\\n fact, the [state] did not release the mountain goats on [USFS] land, and therefore\\n was not using or occupying [USFS] land at the time for the mountain goat release.\\n The mountain goats have strayed onto adjacent [Forest Service] land . . . after they\\n were released on non-Federal land by [the state].\\nApp 77. The majority takes from this that the plaintiffs’ “demand [to use the permitting\\n\\nprocess was] denied; end of discussion.” Maj. Op. at 16. But I would not take this as a\\n\\nrejection of using the permitting process, as the majority does. The above-quoted\\n\\nstatement follows Tidwell’s description of the plaintiffs’ concerns, namely, that “the\\n\\n[USFS] is violating Federal law by ‘allowing goats in the National Forest and Mount\\n\\nPeale RNA.’” App 77 (emphasis added). Tidwell’s response was to deny that the USFS\\n\\nwas “allowing goats” on Forest Service land. Granted, Tidwell did point out that goats\\n\\nwere not released onto Forest Service land, but instead “strayed” there after their release.\\n\\nBut again, this statement is in direct response to the plaintiffs’ allegation that the USFS\\n\\n“allowed” goats on Forest Service land. Indeed, the next paragraph of the letter goes on\\n\\n\\n\\n\\n 3\\n\\fat length to detail the various efforts the USFS made to object to the introduction of\\n\\nmountain goats by the state. Id.3\\n\\n More importantly, nowhere does the Tidwell letter refer to the permitting process.4\\n\\nThis silence is perhaps explained by the fact that the plaintiffs’ June 13, 2015 letter to\\n\\nTidwell does not ask for action on permitting. Instead, it requests that the USFS “(1)\\n\\n\\n\\n 3\\n The paragraph states:\\n\\n As explained in [Rasure’s] letter, before the release of the mountain goats,\\n the Forest Service coordinated with [the state], and objected to the\\n transplant. In July 2013, the Forest Supervisor Expressed concerns about\\n the proposed transplant. In a letter dated August 21, 2013, the Forest\\n Service urged the [state] Wildlife Division Board to delay its decision on\\n the mountain goat transplant to provide additional time to coordinate on the\\n potential impacts the mountain goats may have on the RNA, and indicated\\n that the Forest Service did not support the transplant at that time because of\\n the uncertainty about the potential impacts to the RNA and sensitive alpine\\n plant species. When the Wildlife Division Board decided to move forward\\n with the transplant, the Forest Service contacted the [state] with a letter\\n dated August 27, 2013, to request a delay in the transplant to allow data\\n gathering to assess the impacts of any transplant. [The state’s] August 30,\\n 2013 response stated that it intended to move forward with the transplant of\\n a small number of mountain goats, but would work cooperatively with the\\n Forest Service to assess impacts, and develop a strategy to prevent\\n overutilization of the habitat.\\n\\nApp 77.\\n 4\\n The Rasure letter does refer to permitting process, as well as to the fact that the\\nmountain goats were released on state land, but it does so “[a]s noted in your letter,”\\nmeaning Rasure is repeating what the plaintiffs stated in their December 24, 2014 letter\\nto her regarding the location of the goats at the time of release. Rasure concludes the\\nparagraph by stating that “We do acknowledge that is was reasonably foreseeable that the\\ngoats might wander onto [USFS] land from where they were released.” App 75. Again,\\nhowever, this a description of the challenges of releasing goats near Forest Service land,\\nnot a denial of a particular remedy to address that challenge.\\n\\n\\n 4\\n\\fimmediately remove . . . all mountain goats from the La Sal Mountains; and (2) prohibit\\n\\nthe [state] from introducing additional goats to the La Sal Mountains.” App 325. It then\\n\\nrequests a “formal written response . . . indicating that the requested actions will occur”\\n\\nor be denied. Id. Before this court, the USFS does not argue that the permitting claim is\\n\\nunexhausted or waived, but instead suggests it is subsumed in the request for removal—a\\n\\nrequest on which there is no final action. See USFS Brief at 19 (arguing that the USFS\\n\\nhas “deferred ruling on whether the remove or destroy mountain goats or how to regulate\\n\\nthem”). To me, this reading best comports with the Tidwell letter. I therefore would\\n\\nhold that the USFS has adopted a “wait and see” approach as to the goats currently on\\n\\nForest Service land, studying options for action that might include removal or regulation.\\n\\nPermitting is simply one regulatory alternative. See Maj. Op. at 27-28 (listing others).\\n\\n Whether final agency action exists regarding future releases is a closer call, but I\\n\\nwould find it is similarly lacking. The majority finds final agency action in the last\\n\\nparagraph of the Tidwell letter, which states that “your request that the Forest Service\\n\\nprevent [the state] from transplanting goats anywhere in the La Sal Mountains is beyond\\n\\nthe control of the Forest Service.” App 78. From this statement, the majority concludes\\n\\nthat the plaintiffs’ “demand [to prevent future releases was] denied; end of discussion.”\\n\\nMaj. Op. at 9. But the majority does not consider the sentences that follow, which state\\n\\nthat the USFS “has not authorized, and has no plans to authorize, the release of mountain\\n\\ngoats on [Forest Service] land in the La Sal Mountains. The [state] has not informed the\\n\\n[USFS] of any additional planned releases.” App 78. When read in context, the Tidwell\\n\\nletter suggests that while the USFS believes it has no authority to broadly forbid the state\\n\\n 5\\n\\ffrom taking action “anywhere” in the La Sal Mountains, it is keeping its options open for\\n\\nthe future. Contrary to the majority’s interpretation, then, the letter does not suggest an\\n\\nend of discussion, but rather indicates that such action is not necessary at this time\\n\\nbecause USFS is not aware of any planned releases.\\n\\n At the very least, the USFS’s response—that the agency has no authority to\\n\\nprevent goat transplantation “anywhere” in the La Sal Mountains, but there is no\\n\\nimmediate need for such prevention given that the state has not indicated it will be\\n\\nintroducing goats in the near future—is unclear. The plaintiffs bear the burden of\\n\\nshowing finality. Col. Farm Bur. Fed’n v. U.S. Forest Service, 220 F.3d 1171, 1173\\n\\n(10th Cir. 2000) (“Plaintiffs have the burden of identifying specific federal conduct and\\n\\nexplaining how it is ‘final agency action’ within the meaning of [the APA].”). Given the\\n\\nlack of clarity regarding the USFS’s response, I would find that the plaintiffs have not\\n\\nmet their burden to show final agency action regarding future releases.\\n\\n In sum, the USFS informed the plaintiffs that it would have to further evaluate the\\n\\nimpact that the goats were having before deciding to take “an appropriate action,”\\n\\nwhatever that may be. As the district court put it, the USFS “has [not] decided that it will\\n\\nnever act on Plaintiffs’ requests. The State acted and now the [USFS] is in the\\n\\nreactionary position attempting to determine what agency action, if any, is warranted.”\\n\\nDist. Ct. Op. at 10. Under the circumstances, the USFS’s decision to further study the\\n\\nimpact that the mountain goats are having on the RNA before taking any action is\\n\\n“tentative [and] interlocutory [in] nature,” and therefore not a final agency decision. U.S.\\n\\nArmy Corps of Eng’rs v. Hawkes Co., 136 S. Ct. 1807, 1813 (2016). Accordingly, I\\n\\n 6\\n\\fwould affirm the dismissal of the case in its entirety, and not reach the merits of the\\n\\nplaintiffs’ claims.5\\n\\n\\n\\n\\n 5\\n I agree with the majority with regard to the second issue presented in this case,\\nnamely, that the “wait and see” approach does not constitute an actionable “failure to\\nact.” Maj. Op. at 25-28.\\n 7\"}]}"},"judge1":{"kind":"string","value":"BRISCOE"},"judge2":{"kind":"string","value":"BALDOCK"},"judge3":{"kind":"string","value":"EID"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":2,"string":"2"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4617407/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UTAH NATIVE PLANT SOCIETY; Grand Canyon Trust, Plaintiffs-Appellants, v. UNITED STATES FOREST SERVICE; Tom Tidwell, in His Official Capacity as Chief of the U.S. Forest Service, Defendants-Appellees. State of Utah; State of Alaska; State of Colorado; State of Idaho; State of Kansas; State of Nebraska; State of Wyoming; New Mexico Department of Game and Fish; Association of Fish and Wildlife Agencies, Amici Curiae.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-07\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n Tenth Circuit\n\n PUBLISH May 7, 2019\n Elisabeth A. Shumaker\n UNITED STATES COURT OF APPEALS Clerk of Court\n\n TENTH CIRCUIT\n\n\nUTAH NATIVE PLANT SOCIETY;\nGRAND CANYON TRUST,\n\n Plaintiffs - Appellants,\nv. No. 17-4074\nUNITED STATES FOREST\nSERVICE; TOM TIDWELL, in his\nofficial capacity as Chief of the U.S.\nForest Service,\n\n Defendants - Appellees.\n----------------------------------------------\n\nSTATE OF UTAH; STATE OF\nALASKA; STATE OF COLORADO;\nSTATE OF IDAHO; STATE OF\nKANSAS; STATE OF NEBRASKA;\nSTATE OF WYOMING; NEW\nMEXICO DEPARTMENT OF GAME\nAND FISH; ASSOCIATION OF FISH\nAND WILDLIFE AGENCIES,\n\n Amici Curiae.\n\n\n\n APPEAL FROM THE UNITED STATES DISTRICT COURT\n FOR THE DISTRICT OF UTAH\n (D.C. No. 2:16-CV-00056-PMW)\n\fAaron Paul (Neil Levine with him on the briefs), Grand Canyon Trust, Denver,\nColorado, for Plaintiffs-Appellants.\n\nJared C. Bennett, Assistant United States Attorney (John W. Huber, United States\nAttorney, with him on the brief), Salt Lake City, Utah, for Defendants-Appellees.\n\nSean D. Reyes, Utah Attorney General, Tyler R. Green, Utah Solicitor General, and\nMartin B. Bushman and Gregory Hansen, Assistant Utah Attorneys General, Salt\nLake City, Utah, filed an Amicus Curiae Brief for the States of Utah, Alaska,\nColorado, Idaho, Kansas, Nebraska, and Wyoming, and the New Mexico Department\nof Game and Fish in support of Defendants-Appellees.\n\nCarol Frampton and Lane Kisonak, Association of Fish and Wildlife Agencies,\nWashington, D.C., filed an Amicus Curiae Brief for the Association of Fish and\nWildlife Agencies in support of Defendants-Appellees.\n\n\nBefore BRISCOE, BALDOCK, and EID, Circuit Judges.\n\n\nBALDOCK, Circuit Judge.\n\n\n The La Sal Mountain Range, located in southeastern Utah on the Colorado\n\nPlateau, encompasses the vast acreage of the Manti-La Sal National Forest. The\n\nhighest elevations of the national forest support one of the rare alpine communities\n\nin the region. At these elevations, sensitive tundra vegetation grows among talus\n\nrock and rare plants find their home. To preserve this particular community,\n\nDefendant United States Forest Service (FS) in 1988 designated a 2,380 acre portion\n\nof the Manti-La Sal National Forest’s highest elevations, namely the summits and\n\nridges of Mt. Peale, Mt. Mellenthin, and Mt. Tukuhnikivatz, as the Mt. Peale\n\n\n\n 2\n\fResearch Natural Area (RNA). 1 According to an FS regulation, an RNA should\n\n“illustrate adequately or typify for research or educational purposes, the important\n\nforest and range types in each forest region, as well as other plant communities that\n\nhave special or unique characteristics of scientific interest and importance.” 36\n\nC.F.R. § 251.23. The applicable regulation further provides an RNA “will be\n\nretained in a virgin or unmodified condition except where measures are required to\n\nmaintain a plant community which the area is intended to represent.” Id. According\n\nto the instant suit, “until 2013, the Forest Service adhered to its rules and preserved\n\nthe [Mt. Peale RNA] in an unmodified natural state.”\n\n Now enter the State of Utah’s Division of Wildlife Resources (UDWR), the\n\n“wildlife authority for Utah . . . [s]ubject to the broad policymaking authority of the\n\nWildlife Board.” Utah Code Ann. § 23-14-1(1)(b), (2)(a). In June 2013, the Utah\n\nWildlife Board approved UDWR’s “Utah Mountain Goat Statewide Management\n\nPlan.” Among other things, UDWR’s plan anticipated the release of a target\n\npopulation of 200 mountain goats into the La Sal Mountains adjacent to the Manti-\n\n\n\n 1\n The boundary of the Mt. Peale RNA runs roughly along the treeline\nsurrounding these three major peaks but in some areas the boundary follows\nidentifiable topographic features such as cliff bands and ridge spurs. We are told the\nManti-La Sal National Forest is home to ten plant species found nowhere else in\nUtah and one found nowhere else in the world. The FS has listed four of these plant\nspecies, all found within the Mt. Peale RNA, as sensitive. According to the Forest\nService Manual, “sensitive species” are those for which “population viability is a\nconcern.”\n\n 3\n\fLa Sal National Forest for the express purposes of hunting and viewing. The FS,\n\nrightly concerned the goats might adversely affect the habitat of the higher alpine\n\nregions of the national forest, responded by asking UDWR to delay implementation\n\nof its plan while the FS in coordination with UDWR studied the plan’s expected\n\nimpact on the national forest and the RNA. Unfortunately, UDWR rejected the\n\nFS’s request for an outright delay. UDWR indicated it would begin implementing\n\nits plan by transplanting a small number of goats into the mountains, but would work\n\ncooperatively with the FS to assess impacts and develop a strategy to prevent\n\noverutilization of the habitat. In September 2013, UDWR released twenty mountain\n\ngoats on State lands adjacent to the Manti-La Sal National Forest. A year later,\n\nUDWR released an additional fifteen mountain goats on the same State lands.\n\n At this point, Plaintiff Grand Canyon Trust (GCT) said enough. 2 The goats,\n\nto no one’s surprise, had moved into the La Sal Mountains’ higher elevations. There,\n\naccording to GCT, the goats were wallowing and foraging within the national forest\n\nand more particularly within the Mt. Peale RNA. Noting ongoing harm to the Mt.\n\nPeale RNA and citing 36 C.F.R. § 251.23, GCT demanded the FS (1) prohibit\n\nUDWR from introducing additional mountain goats onto State lands adjacent to the\n\n\n 2\n GCT’s mission is to protect and restore the national forests and canyon\ncountry of the Colorado Plateau. GCT’s Co-Plaintiff, Utah Native Plant Society, has\nthe arguably narrower but overlapping mission of preserving native plant ecosystems\nwithin Utah and the Intermountain West. Hereinafter we refer to the two Plaintiffs\ncollectively as GCT.\n\n 4\n\fnational forest, (2) regulate UDWR’s occupancy and use of the national forest by\n\nrequiring it to obtain special use authorization before releasing additional mountain\n\ngoats on State lands, and (3) immediately remove the mountain goats already in the\n\nnational forest.\n\n The FS denied GCT any relief, at least for the time being. In a letter to GCT,\n\nthe Chief of the FS explained “[t]he Forest Service does not regulate or control\n\nUDWR’s activities that do not occur on NFS [National Forest Service] land, and your\n\nrequest that the Forest Service prevent UDWR from transplanting goats anywhere in\n\nthe La Sal Mountains is beyond the control of the Forest Service.” The Chief further\n\nexplained UDWR was not required to seek a special use permit to use the national\n\nforest before releasing the mountain goats on State lands: “[T]he UDWR did not\n\nrelease the mountain goats on NFS land, and therefore was not using or occupying\n\nNFS land at the time of the mountain goats release. The mountain goats have strayed\n\nonto adjacent NFS land, including the land within the Mount Peale RNA, after they\n\nwere released on non-Federal land by UDWR.” Lastly, the FS Chief took a “wait\n\nand see” attitude with regard to GCT’s request that the FS remove or destroy any\n\nmountain goats not only in the Mt. Peale RNA but throughout the national forest:\n\n [T]he Forest Service is working cooperatively with UDWR to evaluate\n any resource impacts and to determine an appropriate action, including\n consideration of removal of the mountain goats from the RNA or\n reduction in herd numbers.\n ***\n\n\n 5\n\f Before initiating any such action, the Forest Service will work with\n UDWR to gather and evaluate data sufficient to determine whether that\n action is warranted, and then will work cooperatively with UDWR to\n determine and implement the appropriate course of action.\n\nGCT’s lawsuit for declaratory and injunctive relief followed.\n\n I.\n\n GCT’s muddled complaint alleged five “claims for relief” against the FS\n\narising under federal law, all pursuant to the judicial review provisions of the\n\nAdministrative Procedures Act (APA), 5 U.S.C. §§ 701–706. GCT represents that\n\nonly two of its claims are before us on appeal. GCT’s first claim seeks relief under\n\nAPA § 706(2) and alleges the FS —knowing full well UDWR’s mountain goat plan\n\nwould result in goats migrating into the Manti-La Sal National Forest and the Mt.\n\nPeale RNA—acted arbitrarily, capriciously, and unlawfully by denying GCT’s three\n\ndemands for relief. Meanwhile, GCT’s second claim seeks relief under APA\n\n§ 706(1) and alleges the FS unlawfully failed to act by refusing to comply with the\n\nFS regulation mandating RNA’s “will be retained in a virgin or unmodified\n\ncondition.” 36 C.F.R. § 251.23.\n\n The FS moved to dismiss GCT’s complaint in its entirety under Fed. R. Civ.\n\nP. 12(b)(1) for failure to allege final agency action as required by APA § 704, and\n\nthus subject matter jurisdiction over the Government, which enjoys sovereign\n\nimmunity absent congressional waiver. The district court granted the motion:\n\n\n\n 6\n\f Plaintiffs have cleverly amalgamated federal law in an attempt to find\n some pathway to judicial review. Pulling apart Plaintiffs’ contortions,\n the court [concludes] that it has no jurisdiction to review the Forest\n Service’s action or inaction with respect to the mountain goats’\n occupation of the Manti-La Sal National Forest. . . . The Forest Service\n has not determined whether the goats’ presence in the Manti-La Sal\n National Forest violates federal law or the existing Forest Plan. Nor\n has the Forest Service decided that it will never act on Plaintiffs’\n requests. The State acted and now the Forest Service is in the\n reactionary position attempting to determine what agency action, if any,\n is warranted. Accepting Plaintiffs’ allegations as true, the court [holds]\n that Plaintiffs have failed to provide the court any action or inaction on\n behalf of the Forest Service that is reviewable under the APA.\n\nUtah Native Plant Soc’y v. United States Forest Serv., 2017 WL 822098, at\n\n*5 (D. Utah 2017) (unpublished). GCT appeals. Our jurisdiction arises under 28\n\nU.S.C. § 1291. Our review of the complaint’s sufficiency is de novo. See Jones v.\n\nNeedham, 856 F.3d 1284, 1289 (10th Cir. 2017).\n\n Because we consider the FS to make a facial attack on GCT’s complaint, we\n\n“apply a standard patterned on Rule 12(b)(6) and assume the truthfulness of the facts\n\nalleged.” Garling v. Envtl. Prot. Agency, 849 F.3d 1289, 1293 n. 3 (10th Cir. 2017).\n\nWe may supplement the complaint’s well-pleaded facts, however, with the contents\n\nof documents referred to therein “if the documents are central to [GTC’s] claim[s]\n\nand the parties do not dispute the documents’ authenticity.” Hampton v. Root9B\n\nTech., 897 F.3d 1291, 1297 (10th Cir. 2018). While we uphold dismissal of GCT’s\n\ncomplaint under the foregoing standards, we believe the district court missed the\n\nmark when it concluded that because the FS is currently in the process of deciding\n\n\n 7\n\fwhat to do, if anything, about the goats’ presence in the national forest and RNA, it\n\nlacked jurisdiction to review the FS’s “action or inaction” in its entirety.\n\n II.\n\n We begin by analyzing GCT’s first claim which, as we have described, alleges\n\nthree instances of unlawful agency action. APA § 702 generally authorizes suit by\n\n“[a] person suffering legal wrong because of agency action.” “‘[A]gency action’\n\nincludes the whole or a part of an agency rule, order, license, sanction, relief, or the\n\nequivalent or denial thereof, or failure to act[.]” APA §551(13) (emphasis added).\n\nAPA § 704 requires the challenged “action”—or, more accurately in this case, the\n\nFS’s respective denials of GCT’s three demands—constitute “final agency action.”\n\nIn Bennett v. Spear, 520 U.S. 154, 177–78 (1997), the Supreme Court decided that\n\nbefore agency action becomes final, such action must meet two conditions: “First,\n\nthe action must mark the ‘consummation’ of the agency’s decisionmaking process—it\n\nmust not be of a merely tentative or interlocutory nature. And second, the action\n\nmust be one by which ‘rights or obligations have been determined,’ or from which\n\n‘legal consequences will flow[.]’” (citations omitted). APA § 704’s requirement of\n\nfinal agency action readily applies to GCT’s first claim for relief under APA\n\n§ 706(2) because subsection (2) directs a reviewing court to “hold unlawful and set\n\naside agency action . . . found to be . . . arbitrary, capricious, an abuse of discretion,\n\nor otherwise not in accordance with law[.]” (emphasis added).\n\n\n 8\n\f A.\n\n The first instance of FS action about which GCT complains is the former’s\n\ndenial of any authority to prohibit UDWR from releasing mountain goats on Utah\n\nState lands adjacent to the Manti-La Sal National Forest. Such denial surely\n\nconstitutes final agency action. The FS explained that because it “does not regulate\n\nor control UDWR’s activities that do not occur on NFS land,” it cannot “prevent\n\nUDWR from transplanting goats anywhere in the La Sal Mountains.” GCT’s first\n\ndemand, in other words, was “beyond the control of the Forest Service.” This\n\ndetermination was not “merely tentative or interlocutory in nature”; it was\n\nconclusive. Bennett, 520 U.S. at 178. The FS told GCT that it did not have\n\nthe legal authority to prevent the State of Utah from releasing mountain goats\n\non State lands—first demand denied; end of discussion. The FS’s denial of\n\nGCT first demand was based on a “final and binding” decision that “mark[ed] the\n\n‘consummation’ of the agency’s decisionmaking process” and from which “‘rights\n\nand obligations have been determined.’” Id.\n\n Yet while the FS’s denial of GCT’s first demand constitutes final agency\n\naction, this demand still plainly fails as a matter of law. See Aguilera v. Kirkpatrick,\n\n241 F.3d 1286, 1290 (10th Cir. 2001) (recognizing that where a district court\n\ndismisses a complaint for lack of subject matter jurisdiction, we may affirm dismissal\n\nof the complaint for failure to state a claim under the same standards). GCT\n\n\n 9\n\facknowledges, as it must, that Utah has broad trustee and police powers over wildlife\n\nwithin its borders. See Kleppe v. New Mexico, 426 U.S. 529, 545 (1976). But these\n\npowers, GCT tells us, are constrained by federal preemption principles derived from\n\nthe Constitution’s Supremacy Clause. See U.S. Const. art. VI, cl. 2. With this much\n\nwe agree. GCT next turns to the Constitution’s Property Clause, which provides:\n\n“Congress shall have Power to dispose of and make all needful Rules and\n\nRegulations respecting the Territory or other Property belonging to the United\n\nStates.” Id. art. IV, § 3, cl. 2. GCT tells us the Property Clause extends to activities\n\nthat endanger federal lands but are initiated on non-federal lands. 3 But as a mere\n\ngrant of power “to make all needful Rules and Regulations,” the Property Clause’s\n\nplain language is not self-executing and does not itself grant the FS authority over\n\nUtah State lands adjacent to the Manti-La Sal National Forest.\n\n Assuming the Property Clause reaches thus far, Congress, with the aim of\n\npreserving federal lands, might rely on it to enact legislation altering the State of\n\nUtah’s authority to manage wildlife on its own lands. Federal legislation, however,\n\ndoes not supercede the historic police powers of the States “unless that was the clear\n\n\n\n 3\n Congress unquestionably has the authority to regulate conduct on private\nlands that is injurious to the public domain. See United States v. Alford, 274 U.S.\n264, 267 (1927) (“Congress may prohibit the doing of acts upon privately owned\nlands that imperil the publicly owned forests.”); Camfield v. United States, 167 U.S.\n518, 528 (1897) (Congress has the “constitutional right of protecting the public lands\nfrom nuisances erected upon adjoining [private] property.”).\n\n 10\n\fand manifest purpose of Congress” in enacting such legislation. Puerto Rico Dept.\n\nof Consumer Affairs v. Isla Petrol. Corp., 485 U.S. 495, 500 (1988). While Congress\n\nmight enact legislation respecting national forests, the “clear and manifest purpose”\n\nof which is to preempt Utah’s traditional trustee and police powers as a sovereign to\n\nmanage wildlife within its borders, it has not done so. GCT points us to the Organic\n\nAdministration Act of 1897 (Organic Act), which provides: “The Secretary of\n\nAgriculture shall make provisions for the protection against destruction by fire and\n\ndepredations upon the . . . national forests . . . and he may make such rules and\n\nregulations and establish such service as will insure the objects of such reservations,\n\nnamely, to regulate their occupancy and use and to preserve the forests thereon from\n\ndestruction.” 16 U.S.C. § 551. But the Organic Act’s broad directive that the\n\nSecretary “make provisions for the protection against destruction by . . . depredations\n\nupon the . . . national forests,” hardly evidences a “clear and manifest” purpose to\n\nencroach upon State sovereignty and override Utah’s traditional management of\n\nwildlife within its borders outside the Manti-La Sal National Forest.\n\n Nor can we say Utah’s placement of mountain goats on State lands “stands as\n\nan obstacle to the accomplishment of the full purposes and objectives of Congress”\n\nin the management of the national forest. California Coastal Comm’n v. Granite\n\nRock Co., 480 U.S. 572, 581 (1987) (quoting Silkwood v. Kerr-McGee Corp., 464\n\nU.S. 238, 248 (1984)). Legislation supplemental to the Organic Act calling for\n\n\n 11\n\f“cooperative federalism” between federal and state authorities in the area of wildlife\n\nmanagement illustrates the point. 4 The Multiple-Use Sustained-Yield Act of 1960\n\n(MUSYA), identifies a range of purposes national forests should serve. But the\n\nMUSYA also provides “[n]othing herein shall be construed as affecting the\n\njurisdiction and responsibilities of the several States with respect to wildlife and fish\n\non the national forests.” 16 U.S.C. § 528. If “nothing” in the MUSYA affects the\n\njurisdiction of the States with respect to wildlife on the national forests, surely\n\n“nothing” therein affects the jurisdiction of the States with respect to wildlife off the\n\nnational forests. The Federal Land Policy and Management Act of 1976 (FLPMA),\n\ndirects “the public lands be managed in a manner . . . that, where appropriate, will\n\npreserve and protect certain lands in their natural condition[.]” The FLPMA further\n\n\n 4\n Because most federal public land legislation calls for “cooperative\nfederalism,” express preemption of state laws and regulations is rare in public land\nlaw. But see, e.g., 16 U.S.C. § 1535(f) (stating state endangered species laws and\nregulations cannot be less restrictive than federal laws and regulations). Absent\nexpress preemption, state laws and regulations still may be preempted in either of\ntwo ways:\n\n If Congress evidences an intent to occupy a given field [i.e., field\n preemption], any state law falling within that field is pre-empted. If\n Congress has not entirely displaced state regulation over the matter in\n question, state law is still pre-empted to the extent it actually conflicts\n with federal law [i.e., conflict preemption], that is, when it is\n impossible to comply with both state and federal law, or where the state\n law stands as an obstacle to the accomplishment of the full purposes\n and objective of Congress.\n\nGranite Rock Co., 480 U.S. at 581 (citations omitted).\n\n 12\n\fprovides, however, that “nothing” in the FLPMA “shall be construed as . . . enlarging\n\nor diminishing the responsibility and authority of the States for management of fish\n\nand resident wildlife.” 43 U.S.C. §§ 1701(a)(8), 1732(b). And the National Forest\n\nManagement Act of 1976 directs the Secretary of Agriculture to develop, maintain,\n\nand revise land and resource management plans for the national forests “coordinated\n\nwith the land and resource management planning processes of State and local\n\ngovernments[.]” 16 U.S.C. § 1604(a). In short, the clarity and manifestness of\n\npurpose necessary in the federal statutory scheme GCT relies on to demand the FS\n\nprohibit the State of Utah from releasing mountain goats on State lands adjacent to\n\nthe Manti-La Sal National Forest is wholly lacking.\n\n Like Congress, a federal agency by way of congressional delegation of\n\nauthority also may preempt state laws and regulations. Fidelity Fed. Sav. & Loan\n\nAss’n v. De La Cuesta, 458 U.S. 141, 153–54 (1982). For example, after providing\n\nnotice and opportunity for comment, the FS might issue preemptive regulations\n\nimplementing the Organic Act’s directive that the Secretary of Agriculture make\n\nprovisions to protect the national forests from depredations. 16 U.S.C. § 551. Such\n\nfederal regulations preempt state law to the extent compliance with both is\n\nimpossible, or “where the scheme of federal regulation is sufficiently comprehensive\n\nto make reasonable the inference that Congress ‘left no room’ for supplementary\n\nstate regulation.” Hillsborough Cty. v. Automated Med. Laboratories, Inc., 471 U.S.\n\n\n 13\n\f707, 713 (1985); see supra n.4. This assumes, of course, such regulations are\n\nconsistent with a reasonable interpretation of the Organic Act and the Secretary\n\nreasonably exercised Congress’s delegation of authority. See State of Kansas ex rel.\n\nTodd v. United States, 995 F.2d 1505, 1509 (10th Cir. 1993) (citing De La Cuesta,\n\n458 U.S. at 153–54 and Chevron, Inc. v. Nat. Res. Def. Counsel, 467 U.S. 837, 844\n\n(1984)). But to say the FS may issue preemptive regulations is not to say it may do\n\nso subtly. 5 See Isla Petrol. Corp., 485 U.S. at 500. Like our review of the Organic\n\nAct and related legislation, where the States have traditionally exercised trustee and\n\npolice powers over a field, we assume federal regulations do not preempt the States’\n\nexercise of these historic powers unless their intent to do so is “clear and manifest.”\n\nHillsborough Cty., 471 U.S. at 715–16.\n\n Notably, nothing in 36 C.F.R. § 251.23, the sole FS regulation on which all of\n\nGCT’s demands rest, expresses an intent to preempt the State of Utah’s management\n\nof wildlife on State lands. Recall § 251.23 is the FS regulation which provides that\n\nan RNA within a national forest “will be retained in a virgin or unmodified\n\n\n\n 5\n To the degree GCT relies on the Forest Service Manual, the Manti-La-Sal\nNational Forest Plan, and the Mt. Peale RNA Establishment Record to support its\nvarious demands—and it does so extensively throughout its complaint—we note such\ndocuments do not carry the force of law. See Christensen v. Harris Cty., 529 U.S.\n576, 587 (2000) (distinguishing agency adjudications and notice-and-comment\nrulemaking, both of which have the force of law, from opinion letters, policy\nstatements, agency manuals, enforcement guidelines, and the like, all of which lack\nthe force of law).\n\n 14\n\fcondition.” But the FS has never proposed the sweeping interpretation of § 251.23\n\nthat GCT now endorses, perhaps because in most instances means exist to prevent\n\ndepredations of the national forests and RNAs short of wholly disrespecting State\n\nsovereignty over State lands, e.g., removing destructive wildlife from the forest.\n\nBecause a federal agency may address problems in detail and speak through a number\n\nof means, we expect an agency will clearly tell us if it intends for its regulations to\n\npreempt the historic police powers of the States. Hillsborough Cty., 471 U.S. at 718;\n\nsee also Granite Rock Co., 480 U.S. at 583 (“[I]t is appropriate to expect an\n\nadministrative regulation to declare any intention to pre-empt state law with some\n\nspecificity.”); Integrity Mgmt. Int’l, Inc. v. Tombs & Sons, Inc., 836 F.2d 485,\n\n492–93 (10th Cir. 1987) (“[U]nless an agency has explicitly stated an intent to\n\npreempt state law, there is a presumption that no such intent exists.”).\n\n Here, the FS has never expressed an intent—let alone a clear and manifest\n\none—to preempt the power of the State of Utah in its sovereign capacity to manage\n\nwildlife on its own public lands, regardless of where such wildlife wanders off.\n\nWhether the FS has the authority to do so by way of congressional delegation\n\npursuant to the Organic Act is beside the point. We need do no more than apply the\n\napplicable law to the well-pleaded factual allegations of GCT’s complaint (sans the\n\nmyriad of legal arguments and conclusions contained therein) to sustain the FS’s\n\ndetermination that it lacked the legal authority to prohibit the State of Utah, or more\n\n\n 15\n\fparticularly UDWR, from releasing mountain goats on State lands adjacent to the\n\nManti-La Sal National Forest. The FS’s legal conclusion that under federal law it\n\ncould not prohibit the State of Utah from releasing mountain goats on State lands\n\nwas neither “arbitrary, capricious, an abuse of discretion, [n]or otherwise not in\n\naccordance with law.” 5 U.S.C. § 706(2)(A).\n\n B.\n\n The second agency action about which GCT complains is the FS’s denial of\n\nthe authority to regulate the State of Utah’s “occupancy” and “use” of the Manti-La\n\nSal National Forest by requiring UDWR to obtain a special use permit before\n\nreleasing mountain goats on State lands. Like the FS’s denial of GCT’s first\n\ndemand, its denial of GCT’s second demand also constitutes final agency action\n\nunder the APA. The FS informed GCT that because UDWR released the mountain\n\ngoats on State lands, UDWR “was not using or occupying NFS land at the time of\n\n[their] release,” and therefore special use authorization from the FS was not required\n\nunder FS regulations—second demand denied; end of discussion. This second denial\n\nof relief, like the first, was not “tentative or interlocutory,” but was “final and\n\nbinding.” Bennett, 520 U.S. at 178. Once the FS decided UDWR was not required\n\nto obtain a special use permit before releasing the mountain goats on State lands\n\nnothing else was left to decide and legal rights had been determined.\n\n\n\n\n 16\n\f Still, GCT’s second demand—as novel and far-reaching as its first—also\n\nplainly fails as a matter of law. Absent “special use authorization,” Forest Service\n\nregulations generally prohibit “uses [except those otherwise enumerated] of National\n\nForest System lands . . . and resources.” 36 C.F.R. §251.50. In particular, § 251.23\n\nprohibits “occupancy [of an RNA] under a special use permit . . . unless authorized\n\nby the Chief of the FS.” GCT says the mountain goats’ release point on State lands\n\nis irrelevant to its argument regarding UDWS’s occupancy and use of the national\n\nforest. According to GCT, the FS is authorized “to regulate and prohibit the goat\n\nintroductions because the State airlifted them to the La Sal Mountains knowing the\n\ngoats would use and harm the Manti-La Sal National Forest and Mt. Peale RNA.”\n\nTwo pertinent points demonstrate the fallacy of GCT’s argument —based entirely on\n\nUDWR’s scienter—that the mountain goats are, in effect, instrumentalities of the\n\nState whose presence in the national forest and RNA constitute the State’s occupancy\n\nand use of the forest.\n\n Federal ownership of lands within a State does not in itself withdraw those\n\nlands from the jurisdiction of the State. Kleppe, 426 U.S. 544. “Absent consent or\n\ncession a State undoubtedly retains jurisdiction over federal lands within its\n\nterritory,” subject to Congress’s “power to enact legislation respecting those lands\n\npursuant to the Property Clause.” Id. at 543–44. We have already observed that\n\nUtah, not as a private property owner but in its sovereign capacity, has historically\n\n\n 17\n\fpossessed broad trustee and police powers over wildlife within its borders. See id.\n\nat 545. Just as we did in our preceding analysis regarding the State’s authority to\n\nrelease wildlife on its own lands, we assume neither Congress nor the FS intended\n\nits enactments to alter the State of Utah’s “historic police powers to manage wildlife\n\non federal lands within its borders” unless such intent is “clear and manifest.”\n\nWyoming v. United States, 279 F.3d 1214, 1231 (10th Cir. 2002) (emphasis added).\n\nAnd again, at the same time, we remain mindful that we “must give full effect to\n\nevidence that Congress considered, and sought to preserve, [Utah’s] coordinate\n\nregulatory role in our federal scheme.” Id. (emphasis added) (quoting California v.\n\nFERC, 495 U.S. 490, 497 (1990)); see supra at 11–13.\n\n Where the FS has never asserted exclusive jurisdiction over the management\n\nof wildlife in the Manti-La Sal National Forest, GCT’s argument that the State of\n\nUtah needs a special use permit before releasing wildlife on State lands—regardless\n\nof whether everyone knew such wildlife would end up in the national forest and\n\nRNA—runs counter to Congress’s determination, and the FS’s obvious recognition\n\nin this case, that the State retains a measure of sovereignty over wildlife management\n\nwithin the national forest. See Defenders of Wildlife v. Andrus, 627 F.2d 1238, 1248\n\n(D.C. Cir. 1980) (“Despite its ability to take control into its own hands, Congress\n\nhas traditionally allotted the authority to manage wildlife to the States.”); 36\n\nC.F.R. § 241.2 (FS regulation calling for cooperation with state officials in the\n\n\n 18\n\fmanagement of wildlife within the national forests). That the State’s wildlife\n\nmanagement responsibilities within the national forest are not exclusive and may be\n\noverridden under appropriate circumstances does not mean those management\n\nresponsibilities are meaningless absent federal law to the contrary. See Baldwin v.\n\nFish and Game Comm’n, 436 U.S. 371, 386 (1978).\n\n The next and perhaps more salient point concerning GCT’s second demand is\n\nthe mountain goats are ferae naturae or wild animals. See generally Pierson v. Post,\n\n3 Cai. 175 (N.Y. Sup. Ct. 1805). As a means of reducing goat populations in other\n\nmountainous areas of the State, UDWR captured the goats and then released them\n\nonto State lands adjacent to the Manti-La Sal National Forest. Because wild animals\n\nare not the private property of those whose lands they occupy, the State of Utah, at\n\nleast once it released the goats back into the wild, did not own the goats in the sense\n\nthat UDWS’s failure to control their expected movement constituted a sort of\n\ntrespass onto national forest lands requiring special use authorization from the FS.\n\nOur en banc decision in Mountain States Legal Found. v. Hodel, 799 F.2d 1423 (10th\n\nCir. 1986) (en banc) settles the score. In that case, we rejected a private\n\nassociation’s argument under the Wild Free-Roaming Horses and Burros Act, 16\n\nU.S.C. §§ 1331–37, that “wild horses are . . . instrumentalities of the federal\n\ngovernment whose presence on the association’s property constitutes a permanent\n\ngovernmental occupation.” Id. at 1428. We explained:\n\n\n 19\n\f Neither state nor federal authority over wildlife is premised on any\n technical “ownership” of wildlife by the government. Although older\n decisions sometimes referred to government “ownership” of wildlife,\n that language has been deemed “a fiction expressive in legal shorthand\n of the importance to its people that a State have power to preserve and\n regulate the exploitation of an important resource.” Toomer v. Witsell,\n 334 U.S. 385, 402 (1948). As the Supreme Court declared, “[I]t is pure\n fantasy to talk of ‘owning’ wild fish, birds, or animals. Neither the\n States nor the Federal Government . . . has title to these creatures until\n they are reduced to possession by skillful capture. Douglas v. Seacoast\n Prod., Inc., 431 U.S. 265, 284 (1977) . . . .\n\nMountain States Legal Found., 799 F.2d at 1426. 6\n\n The FS’s conclusion regarding GCT’s second demand, namely that it could not\n\nrequire the State of Utah to seek special use authorization to occupy and use the\n\nManti-La Sal National Forest and Mt. Peale RNA before releasing mountain goats\n\non State lands adjacent to the forest, was neither arbitrary, capricious, nor an abuse\n\nof discretion, but was entirely consistent with applicable law. Under a proper\n\nassessment of this case, GCT’s second demand simply proves too much. The answer\n\n\n 6\n GCT’s reliance on Light v. United States, 220 U.S. 523 (1911) to support its\nsecond demand is misplaced. In Light, a private property owner permitted his\ndomestic cattle, a herd in the range of 500, to move from his property to a Forest\nReserve and graze thereon in violation of federal regulations establishing grazing\ndistricts on which only a limited number of cattle were allowed. The Supreme Court\nupheld an injunction prohibiting the landowner “from pasturing his cattle on the . . .\nForest Reserve, because he had refused to comply with the regulations adopted by\nthe Secretary of Agriculture, under the authority conferred by [the Organic Act], to\nmake rules and regulations as to the use, occupancy, and preservation of forests.”\nId. at 534. One of among other reasons this case is unlike Light is because once the\nState released the mountain goats onto State lands and into the wild, any arguable\nownership interest the State temporarily had in the goats upon their capture\ncomparable to that of a chattel owner was no more.\n\n 20\n\fto the legal question of whether federal law required the State of Utah as sovereign\n\nto obtain special use authorization to occupy and use the national forest before\n\nreleasing mountain goats on State lands is a resounding no.\n\n C.\n\n Our conclusions thus far—that the State of Utah presently has the authority to\n\nrelease mountain goats on State lands adjacent to the Manti-La Sal National Forest\n\nand may do so absent special use authorization from the FS—say nothing about the\n\nFS’s ability to manage the mountain goats consistent with federal policies and\n\nobjectives once the goats enter the national forest and more specifically the Mt. Peale\n\nRNA. “The governmental trust responsibility for wildlife is lodged initially in the\n\nStates, but only in so far as its exercise may not be incompatible with, or restrained\n\nby [federal law].” Mountain States Legal Found., 799 F.2d at 1426 (quotations\n\nomitted). And this brings us to the third demand of GTC’s first claim which posits\n\nthe FS remove the goats from the national forest and RNA instanter.\n\n Lest it become too comfortable with our analysis thus far, we remind the State\n\nof Utah, who appears herein as amicus together with seven other States in support\n\nof the FS, that the Supreme Court has “repeatedly observed that the power over the\n\npublic lands . . . entrusted to Congress is without limitations.” Granite Rock Co.,\n\n480 U.S. at 580 (quotations omitted). And the power of the FS under the Organic\n\nAct to protect the habitat of national forests “does not admit of doubt.” Hunt v.\n\n\n 21\n\fUnited States, 278 U.S. 96, 100 (1928). In Hunt, deer had “greatly injured” the lands\n\nof a national game preserve inside a national forest “by overbrowsing upon and\n\nkilling valuable young trees, shrubs, bushes, and forage plants.” Id. at 99. The\n\nSupreme Court upheld the power of the Secretary of Agriculture under the Organic\n\nAct to order the destruction of the deer where necessary to protect the game preserve\n\nand national forest. Several years later, in New Mexico State Game Comm’n v.\n\nUdall, 410 F.2d 1197 (1969), we held the supervisory powers granted the Secretary\n\nof Interior over the management of national parks authorized the Secretary, without\n\nthe State’s approval, to direct the killing of a number of deer within a national park\n\nfor an ecological study prior to any serious deterioration of habitat. Opining that\n\n“[i]n protecting the park property it is immaterial that the United States does not\n\nhave exclusive jurisdiction over the land within [the park],” we rejected the State’s\n\nargument that “the deer-killing program could be undertaken only after a showing\n\nor a finding that there was existing depredation caused by the deer.” Id. at 1199,\n\n1201. Given these controlling precedents, we do not question the authority of the FS\n\nunder the Organic Act and related legislation—if exercised as a valid preventative\n\nor restorative measure—to remove the mountain goats from, or reduce the size of the\n\nherd now residing in, the Manti-La Sal National Forest and Mt. Peale RNA.\n\n As the reader understands by now, however, the preliminary inquiry is whether\n\nGCT’s first claim alleges “final agency action” by asserting the FS did not meet its\n\n\n 22\n\fdemand to remove the goats from the national forest and RNA. GCT’s complaint\n\nstates that in May 2015, the Regional Forester responded to GCT’s demand to\n\nremove the goats: “The Forest Service reiterated that it was developing, with the\n\nState’s assistance, a five-year monitoring plan for four rare alpine plants where\n\nmonitoring results would be evaluated annually.” The Forester’s letter explained:\n\n The Forest Service received your Survey Report on the impacts of\n mountain goats on plants with special status in November of 2014.\n While the report suggests negative impacts to plants from mountain\n goat foraging, it also indicates a need for more refined data collection.\n In regard to your monitoring documenting trampling evidence within\n the Mount Peale RNA, evidence similar to that observed by GCT was\n documented in the area prior to goat introductions, and your trampling\n evidence was not clearly demonstrated to be the result of mountain goat\n use. In addition, your observations were not within a fixed area plot,\n so the density of trampling occurrences cannot be calculated, or\n compared to future data to establish a trend.\n\nAfter the Regional Forester rejected GCT’s demand to remove the goats from the\n\nnational forest immediately, GCT unsuccessfully petitioned the Chief of the FS to\n\norder the goats removed. GCT’s complaint represents the Chief denied its third\n\ndemand and informed GCT the FS “would gather and evaluate the goats’ impact and\n\nwork with the State to determine whether additional actions were warranted.”\n\nReferring to the Regional Forester’s prior letter to GCT, the Chief reiterated, “there\n\nis no compelling evidence to show that the mountain goats introduced by UDWR are\n\ncausing immediate damage to NFS land or resources.”\n\n\n\n\n 23\n\f We do not deny that reasonable minds presently may differ about the impact\n\nthe mountain goats are having on the Mt. Peale RNA. In fact, some disagreement\n\nappears within the FS itself. As we have observed on multiple occasions, “habitat\n\nmanagement is a delicate venture.” Wyoming, 279 F.3d at 1239 (brackets omitted)\n\n(quoting Sierra Club-Black Hills Grp. v. United States Forest Serv., 259 F.3d 1281,\n\n1286 (10th Cir. 2001)). But the present disagreement over whether the FS must send\n\nthe goats packing far away from the Manti-La Sal National Forest, no matter how\n\npressing GCT believes the situation to be, does not alone imbue with finality the\n\nFS’s decision to study the matter further, such that relief upon proper proof is\n\ncurrently available to GCT under APA § 706(2). The FS has acknowledged the\n\nsituation and informed GCT that it needs a reasonable period of time to decide\n\nhow to proceed. 7 See Oil, Chemical and Atomic Workers Int’l Union v. Zegeer, 768\n\n\n 7\n The Regional Forester outlined the FS’s intentions in her May 2015 letter:\n\n The [FS] is continuing to work with UDWR to evaluate [habitat]\n impacts. We have developed a rigorous five year monitoring plan to\n evaluate population trends of four rare alpine plant species and track\n shifts in species composition and ground cover in the alpine zone,\n including the Mount Peale [RNA]. The monitoring protocol includes\n recording direct impacts by grazing animals and uses motion sensing\n camera[s] to determine the animal species involved. Monitoring data\n will be analyzed and evaluated annually relative to Forest Plan direction\n for rare plant species and Federal standards for protection of [RNAs].\n Based on the results of each annual evaluation, the [FS] will work\n cooperatively with UDWR to determine an appropriate course of action\n concerning management of the mountain goats, including whether or not\n removal or reduction in population objectives is warranted.\n\n 24\n\fF.2d 1480, 1485 (D.C. Cir. 1985) (concluding the APA indicates a congressional\n\nview that federal agencies should act within reasonable time frames). This is the\n\nbureaucratic process—like it or not. To suggest the refusal of the FS to remove the\n\ngoats from the national forest and RNA this very moment is a sort of agency action\n\n“mark[ing] the ‘consummation’ of the agency’s decisionmaking process,” rather than\n\na “tentative or interlocutory” action, is simply inconsistent with the complaint’s\n\nfactual allegations and the underlying documents on which those allegations rely.\n\nBennett, 520 U.S. at 178. The district court was correct in holding it lacked subject\n\nmatter jurisdiction to review the FS’s denial of GCT’s third demand for want of final\n\nagency action.\n\n III.\n\n While the FS’s “wait and see” response to GCT’s demand that it remove the\n\nmountain goats from the Manti-La Sal National Forests does not constitute “final\n\nagency action” under the APA, GCT’s second claim is that such response does\n\nconstitute a “failure to act”, redresssable under APA § 706(1) as agency action\n\n“unlawfully withheld.” According to GCT, 36 C.F.R. § 251.23 contains a categorical\n\nimperative the FS refuses to heed: “Research Natural Areas will be retained in a\n\nvirgin or unmodified condition except where measures are required to maintain a\n\nplant community which the area is intended to represent.”\n\n\n\n\n 25\n\f APA § 704’s requirement of final agency action does not square well with a\n\ndefinition of “agency action” that includes a “failure to act.” 5 U.S.C. § 551(13).\n\nAnd obviously, the test the Supreme Court has set forth to determine whether agency\n\naction is final does not readily accommodate an agency’s failure to act. Bennett, 520\n\nU.S. at 177–78. “If an agency has failed to act with respect to a matter that a\n\ncomplaining party seeks to compel under § 706(1), it is hard to comprehend the\n\ncontested inaction as ‘final action’ as that term is defined in Bennett v. Spear.”\n\nWestern Org. of Resource Councils v. Zinke, 892 F.3d 1234, 1247 (D.C. Cir. 2018)\n\n(Edwards, J., concurring). Indeed, we have noted the problem and observed that\n\nsome courts have “implicitly recognized that unlawfully withheld actions are\n\nconsidered final under § 704.” Southern Utah Wilderness Alliance v. Norton, 301\n\nF.3d 1217, 1229 n.9 (10th Cir. 2002), rev’d 542 U.S. 55 (2004) (hereinafter SUWA).\n\n Fortunately, in SUWA the Supreme Court considered “what limits the APA\n\nplaces upon judicial review of agency inaction.” SUWA, 542 U.S. at 61. To “protect\n\nagencies from undue judicial interference with their lawful discretion,” among other\n\nreasons, the Court held “a claim under § 706(1) can proceed only where a plaintiff\n\nasserts that an agency failed to take a discrete agency action that it is required to\n\ntake.” Id. at 64, 66; see Wyoming v. United States Dept. of Interior, 839 F.3d 938,\n\n942 (10th Cir. 2016). The Supreme Court explained APA § 706(1) carries forward\n\ncourts’ traditional practice of reviewing a governmental entity’s failure to act by way\n\n\n 26\n\fof writ of mandamus. “The mandamus remedy was normally limited to enforcement\n\nof ‘a specific, unequivocal command,’ the ordering of a ‘precise act about which an\n\nofficial had no discretion whatever.’” SUWA, 542 U.S. at 63 (brackets, citations\n\nand ellipses omitted). Consistent with such practice, the Court reasoned “§706(1)\n\nempowers a court only to compel an agency to perform a ministerial or non-\n\ndiscretionary act or to take action upon a matter, without directing how it shall act.”\n\nId. at 64 (quotations omitted).\n\n The language of the FS regulation at issue in this case, § 251.23, certainly is\n\nmandatory as to the ultimate objective. The regulation plainly states RNA’s “will\n\nbe retained in a virgin or unmodified condition[.]” The regulation, however, leaves\n\nentirely to the FS the decision of how best to achieve this objective. Indeed, GCT’s\n\ncomplaint recites provisions of the Forest Service Manual (FSM) which suggest as\n\nmuch. The complaint states FSM 4063.30(4) advises the FS to “‘[r]emove exotic\n\nplants or animals [from an RNA] to the extent practicable.’” (emphasis added).\n\nMeanwhile, FSM 4063.32 advises: “If exotic plants or animals have been introduced\n\ninto an established [RNA], the Station Director and the Regional Forester exercise\n\ncontrol measures that are in keeping with established management principles and\n\nstandards to eradicate them, when practical.” (emphasis added).\n\n So assuming the mountain goats presence within the Manti-La Sal National\n\nForest and Mt. Peale RNA is inconsistent with § 251.23’s objective, how shall the\n\n\n 27\n\fFS proceed? FSM 4062.30(4) tells us removing the mountain goats from the national\n\nforest and RNA is one option. FSM 4063.32 tells us eradicating or destroying the\n\ngoats is another option. Or perhaps a reduction in the size of the herd would suffice.\n\nMaybe a fence or other barrier to surround the goats, the habitat, or both would be\n\nfeasible. Maybe a spray or other similar mean exists that would not harm the foliage\n\nwithin the RNA but make it less desirable to a mountain goat’s palate. Section\n\n251.23 does not foreclose any of these options. In other words, the FS regulation\n\nprovides us with no discernible rules under which we may direct the FS to act in\n\nexercising its enforcement powers. Section 251.23 simply does not call for a discrete\n\naction that will assure us the RNA “will be retained in a virgin or unmodified\n\ncondition[.]” See Black’s Law Dictionary 565 (10th ed. 2014) (defining “discrete”\n\nas “[i]individual; separate; distinct”). We are not experts in the field of habitat\n\nmanagement and preservation and surely have no business attempting to instruct the\n\nFS how best to achieve § 251.23’s objective. See SUWA, 542 U.S. at 66–67. The\n\ncrux of the matter is GTC’s complaint does not allege the FS has failed to take a\n\ndiscrete agency action that FS regulations require it take. See SUWA, 542 U.S. at\n\n66. Therefore GCT’s second claim based on the FS’s failure to act is not cognizable.\n\n ***\n\n As modified, the judgment of the district court dismissing GCT’s complaint\n\nis AFFIRMED.\n\n\n 28\n\fNo. 17-4074, tah Native Plant Society, et al. v. United States Forest Service, et al.\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UTAH NATIVE PLANT SOCIETY; Grand Canyon Trust, Plaintiffs-Appellants, v. UNITED STATES FOREST SERVICE; Tom Tidwell, in His Official Capacity as Chief of the U.S. Forest Service, Defendants-Appellees. State of Utah; State of Alaska; State of Colorado; State of Idaho; State of Kansas; State of Nebraska; State of Wyoming; New Mexico Department of Game and Fish; Association of Fish and Wildlife Agencies, Amici Curiae.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-07\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n Tenth Circuit\\n\\n PUBLISH May 7, 2019\\n Elisabeth A. Shumaker\\n UNITED STATES COURT OF APPEALS Clerk of Court\\n\\n TENTH CIRCUIT\\n\\n\\nUTAH NATIVE PLANT SOCIETY;\\nGRAND CANYON TRUST,\\n\\n Plaintiffs - Appellants,\\nv. No. 17-4074\\nUNITED STATES FOREST\\nSERVICE; TOM TIDWELL, in his\\nofficial capacity as Chief of the U.S.\\nForest Service,\\n\\n Defendants - Appellees.\\n----------------------------------------------\\n\\nSTATE OF UTAH; STATE OF\\nALASKA; STATE OF COLORADO;\\nSTATE OF IDAHO; STATE OF\\nKANSAS; STATE OF NEBRASKA;\\nSTATE OF WYOMING; NEW\\nMEXICO DEPARTMENT OF GAME\\nAND FISH; ASSOCIATION OF FISH\\nAND WILDLIFE AGENCIES,\\n\\n Amici Curiae.\\n\\n\\n\\n APPEAL FROM THE UNITED STATES DISTRICT COURT\\n FOR THE DISTRICT OF UTAH\\n (D.C. No. 2:16-CV-00056-PMW)\\n\\fAaron Paul (Neil Levine with him on the briefs), Grand Canyon Trust, Denver,\\nColorado, for Plaintiffs-Appellants.\\n\\nJared C. Bennett, Assistant United States Attorney (John W. Huber, United States\\nAttorney, with him on the brief), Salt Lake City, Utah, for Defendants-Appellees.\\n\\nSean D. Reyes, Utah Attorney General, Tyler R. Green, Utah Solicitor General, and\\nMartin B. Bushman and Gregory Hansen, Assistant Utah Attorneys General, Salt\\nLake City, Utah, filed an Amicus Curiae Brief for the States of Utah, Alaska,\\nColorado, Idaho, Kansas, Nebraska, and Wyoming, and the New Mexico Department\\nof Game and Fish in support of Defendants-Appellees.\\n\\nCarol Frampton and Lane Kisonak, Association of Fish and Wildlife Agencies,\\nWashington, D.C., filed an Amicus Curiae Brief for the Association of Fish and\\nWildlife Agencies in support of Defendants-Appellees.\\n\\n\\nBefore BRISCOE, BALDOCK, and EID, Circuit Judges.\\n\\n\\nBALDOCK, Circuit Judge.\\n\\n\\n The La Sal Mountain Range, located in southeastern Utah on the Colorado\\n\\nPlateau, encompasses the vast acreage of the Manti-La Sal National Forest. The\\n\\nhighest elevations of the national forest support one of the rare alpine communities\\n\\nin the region. At these elevations, sensitive tundra vegetation grows among talus\\n\\nrock and rare plants find their home. To preserve this particular community,\\n\\nDefendant United States Forest Service (FS) in 1988 designated a 2,380 acre portion\\n\\nof the Manti-La Sal National Forest’s highest elevations, namely the summits and\\n\\nridges of Mt. Peale, Mt. Mellenthin, and Mt. Tukuhnikivatz, as the Mt. Peale\\n\\n\\n\\n 2\\n\\fResearch Natural Area (RNA). 1 According to an FS regulation, an RNA should\\n\\n“illustrate adequately or typify for research or educational purposes, the important\\n\\nforest and range types in each forest region, as well as other plant communities that\\n\\nhave special or unique characteristics of scientific interest and importance.” 36\\n\\nC.F.R. § 251.23. The applicable regulation further provides an RNA “will be\\n\\nretained in a virgin or unmodified condition except where measures are required to\\n\\nmaintain a plant community which the area is intended to represent.” Id. According\\n\\nto the instant suit, “until 2013, the Forest Service adhered to its rules and preserved\\n\\nthe [Mt. Peale RNA] in an unmodified natural state.”\\n\\n Now enter the State of Utah’s Division of Wildlife Resources (UDWR), the\\n\\n“wildlife authority for Utah . . . [s]ubject to the broad policymaking authority of the\\n\\nWildlife Board.” Utah Code Ann. § 23-14-1(1)(b), (2)(a). In June 2013, the Utah\\n\\nWildlife Board approved UDWR’s “Utah Mountain Goat Statewide Management\\n\\nPlan.” Among other things, UDWR’s plan anticipated the release of a target\\n\\npopulation of 200 mountain goats into the La Sal Mountains adjacent to the Manti-\\n\\n\\n\\n 1\\n The boundary of the Mt. Peale RNA runs roughly along the treeline\\nsurrounding these three major peaks but in some areas the boundary follows\\nidentifiable topographic features such as cliff bands and ridge spurs. We are told the\\nManti-La Sal National Forest is home to ten plant species found nowhere else in\\nUtah and one found nowhere else in the world. The FS has listed four of these plant\\nspecies, all found within the Mt. Peale RNA, as sensitive. According to the Forest\\nService Manual, “sensitive species” are those for which “population viability is a\\nconcern.”\\n\\n 3\\n\\fLa Sal National Forest for the express purposes of hunting and viewing. The FS,\\n\\nrightly concerned the goats might adversely affect the habitat of the higher alpine\\n\\nregions of the national forest, responded by asking UDWR to delay implementation\\n\\nof its plan while the FS in coordination with UDWR studied the plan’s expected\\n\\nimpact on the national forest and the RNA. Unfortunately, UDWR rejected the\\n\\nFS’s request for an outright delay. UDWR indicated it would begin implementing\\n\\nits plan by transplanting a small number of goats into the mountains, but would work\\n\\ncooperatively with the FS to assess impacts and develop a strategy to prevent\\n\\noverutilization of the habitat. In September 2013, UDWR released twenty mountain\\n\\ngoats on State lands adjacent to the Manti-La Sal National Forest. A year later,\\n\\nUDWR released an additional fifteen mountain goats on the same State lands.\\n\\n At this point, Plaintiff Grand Canyon Trust (GCT) said enough. 2 The goats,\\n\\nto no one’s surprise, had moved into the La Sal Mountains’ higher elevations. There,\\n\\naccording to GCT, the goats were wallowing and foraging within the national forest\\n\\nand more particularly within the Mt. Peale RNA. Noting ongoing harm to the Mt.\\n\\nPeale RNA and citing 36 C.F.R. § 251.23, GCT demanded the FS (1) prohibit\\n\\nUDWR from introducing additional mountain goats onto State lands adjacent to the\\n\\n\\n 2\\n GCT’s mission is to protect and restore the national forests and canyon\\ncountry of the Colorado Plateau. GCT’s Co-Plaintiff, Utah Native Plant Society, has\\nthe arguably narrower but overlapping mission of preserving native plant ecosystems\\nwithin Utah and the Intermountain West. Hereinafter we refer to the two Plaintiffs\\ncollectively as GCT.\\n\\n 4\\n\\fnational forest, (2) regulate UDWR’s occupancy and use of the national forest by\\n\\nrequiring it to obtain special use authorization before releasing additional mountain\\n\\ngoats on State lands, and (3) immediately remove the mountain goats already in the\\n\\nnational forest.\\n\\n The FS denied GCT any relief, at least for the time being. In a letter to GCT,\\n\\nthe Chief of the FS explained “[t]he Forest Service does not regulate or control\\n\\nUDWR’s activities that do not occur on NFS [National Forest Service] land, and your\\n\\nrequest that the Forest Service prevent UDWR from transplanting goats anywhere in\\n\\nthe La Sal Mountains is beyond the control of the Forest Service.” The Chief further\\n\\nexplained UDWR was not required to seek a special use permit to use the national\\n\\nforest before releasing the mountain goats on State lands: “[T]he UDWR did not\\n\\nrelease the mountain goats on NFS land, and therefore was not using or occupying\\n\\nNFS land at the time of the mountain goats release. The mountain goats have strayed\\n\\nonto adjacent NFS land, including the land within the Mount Peale RNA, after they\\n\\nwere released on non-Federal land by UDWR.” Lastly, the FS Chief took a “wait\\n\\nand see” attitude with regard to GCT’s request that the FS remove or destroy any\\n\\nmountain goats not only in the Mt. Peale RNA but throughout the national forest:\\n\\n [T]he Forest Service is working cooperatively with UDWR to evaluate\\n any resource impacts and to determine an appropriate action, including\\n consideration of removal of the mountain goats from the RNA or\\n reduction in herd numbers.\\n ***\\n\\n\\n 5\\n\\f Before initiating any such action, the Forest Service will work with\\n UDWR to gather and evaluate data sufficient to determine whether that\\n action is warranted, and then will work cooperatively with UDWR to\\n determine and implement the appropriate course of action.\\n\\nGCT’s lawsuit for declaratory and injunctive relief followed.\\n\\n I.\\n\\n GCT’s muddled complaint alleged five “claims for relief” against the FS\\n\\narising under federal law, all pursuant to the judicial review provisions of the\\n\\nAdministrative Procedures Act (APA), 5 U.S.C. §§ 701–706. GCT represents that\\n\\nonly two of its claims are before us on appeal. GCT’s first claim seeks relief under\\n\\nAPA § 706(2) and alleges the FS —knowing full well UDWR’s mountain goat plan\\n\\nwould result in goats migrating into the Manti-La Sal National Forest and the Mt.\\n\\nPeale RNA—acted arbitrarily, capriciously, and unlawfully by denying GCT’s three\\n\\ndemands for relief. Meanwhile, GCT’s second claim seeks relief under APA\\n\\n§ 706(1) and alleges the FS unlawfully failed to act by refusing to comply with the\\n\\nFS regulation mandating RNA’s “will be retained in a virgin or unmodified\\n\\ncondition.” 36 C.F.R. § 251.23.\\n\\n The FS moved to dismiss GCT’s complaint in its entirety under Fed. R. Civ.\\n\\nP. 12(b)(1) for failure to allege final agency action as required by APA § 704, and\\n\\nthus subject matter jurisdiction over the Government, which enjoys sovereign\\n\\nimmunity absent congressional waiver. The district court granted the motion:\\n\\n\\n\\n 6\\n\\f Plaintiffs have cleverly amalgamated federal law in an attempt to find\\n some pathway to judicial review. Pulling apart Plaintiffs’ contortions,\\n the court [concludes] that it has no jurisdiction to review the Forest\\n Service’s action or inaction with respect to the mountain goats’\\n occupation of the Manti-La Sal National Forest. . . . The Forest Service\\n has not determined whether the goats’ presence in the Manti-La Sal\\n National Forest violates federal law or the existing Forest Plan. Nor\\n has the Forest Service decided that it will never act on Plaintiffs’\\n requests. The State acted and now the Forest Service is in the\\n reactionary position attempting to determine what agency action, if any,\\n is warranted. Accepting Plaintiffs’ allegations as true, the court [holds]\\n that Plaintiffs have failed to provide the court any action or inaction on\\n behalf of the Forest Service that is reviewable under the APA.\\n\\nUtah Native Plant Soc’y v. United States Forest Serv., 2017 WL 822098, at\\n\\n*5 (D. Utah 2017) (unpublished). GCT appeals. Our jurisdiction arises under 28\\n\\nU.S.C. § 1291. Our review of the complaint’s sufficiency is de novo. See Jones v.\\n\\nNeedham, 856 F.3d 1284, 1289 (10th Cir. 2017).\\n\\n Because we consider the FS to make a facial attack on GCT’s complaint, we\\n\\n“apply a standard patterned on Rule 12(b)(6) and assume the truthfulness of the facts\\n\\nalleged.” Garling v. Envtl. Prot. Agency, 849 F.3d 1289, 1293 n. 3 (10th Cir. 2017).\\n\\nWe may supplement the complaint’s well-pleaded facts, however, with the contents\\n\\nof documents referred to therein “if the documents are central to [GTC’s] claim[s]\\n\\nand the parties do not dispute the documents’ authenticity.” Hampton v. Root9B\\n\\nTech., 897 F.3d 1291, 1297 (10th Cir. 2018). While we uphold dismissal of GCT’s\\n\\ncomplaint under the foregoing standards, we believe the district court missed the\\n\\nmark when it concluded that because the FS is currently in the process of deciding\\n\\n\\n 7\\n\\fwhat to do, if anything, about the goats’ presence in the national forest and RNA, it\\n\\nlacked jurisdiction to review the FS’s “action or inaction” in its entirety.\\n\\n II.\\n\\n We begin by analyzing GCT’s first claim which, as we have described, alleges\\n\\nthree instances of unlawful agency action. APA § 702 generally authorizes suit by\\n\\n“[a] person suffering legal wrong because of agency action.” “‘[A]gency action’\\n\\nincludes the whole or a part of an agency rule, order, license, sanction, relief, or the\\n\\nequivalent or denial thereof, or failure to act[.]” APA §551(13) (emphasis added).\\n\\nAPA § 704 requires the challenged “action”—or, more accurately in this case, the\\n\\nFS’s respective denials of GCT’s three demands—constitute “final agency action.”\\n\\nIn Bennett v. Spear, 520 U.S. 154, 177–78 (1997), the Supreme Court decided that\\n\\nbefore agency action becomes final, such action must meet two conditions: “First,\\n\\nthe action must mark the ‘consummation’ of the agency’s decisionmaking process—it\\n\\nmust not be of a merely tentative or interlocutory nature. And second, the action\\n\\nmust be one by which ‘rights or obligations have been determined,’ or from which\\n\\n‘legal consequences will flow[.]’” (citations omitted). APA § 704’s requirement of\\n\\nfinal agency action readily applies to GCT’s first claim for relief under APA\\n\\n§ 706(2) because subsection (2) directs a reviewing court to “hold unlawful and set\\n\\naside agency action . . . found to be . . . arbitrary, capricious, an abuse of discretion,\\n\\nor otherwise not in accordance with law[.]” (emphasis added).\\n\\n\\n 8\\n\\f A.\\n\\n The first instance of FS action about which GCT complains is the former’s\\n\\ndenial of any authority to prohibit UDWR from releasing mountain goats on Utah\\n\\nState lands adjacent to the Manti-La Sal National Forest. Such denial surely\\n\\nconstitutes final agency action. The FS explained that because it “does not regulate\\n\\nor control UDWR’s activities that do not occur on NFS land,” it cannot “prevent\\n\\nUDWR from transplanting goats anywhere in the La Sal Mountains.” GCT’s first\\n\\ndemand, in other words, was “beyond the control of the Forest Service.” This\\n\\ndetermination was not “merely tentative or interlocutory in nature”; it was\\n\\nconclusive. Bennett, 520 U.S. at 178. The FS told GCT that it did not have\\n\\nthe legal authority to prevent the State of Utah from releasing mountain goats\\n\\non State lands—first demand denied; end of discussion. The FS’s denial of\\n\\nGCT first demand was based on a “final and binding” decision that “mark[ed] the\\n\\n‘consummation’ of the agency’s decisionmaking process” and from which “‘rights\\n\\nand obligations have been determined.’” Id.\\n\\n Yet while the FS’s denial of GCT’s first demand constitutes final agency\\n\\naction, this demand still plainly fails as a matter of law. See Aguilera v. Kirkpatrick,\\n\\n241 F.3d 1286, 1290 (10th Cir. 2001) (recognizing that where a district court\\n\\ndismisses a complaint for lack of subject matter jurisdiction, we may affirm dismissal\\n\\nof the complaint for failure to state a claim under the same standards). GCT\\n\\n\\n 9\\n\\facknowledges, as it must, that Utah has broad trustee and police powers over wildlife\\n\\nwithin its borders. See Kleppe v. New Mexico, 426 U.S. 529, 545 (1976). But these\\n\\npowers, GCT tells us, are constrained by federal preemption principles derived from\\n\\nthe Constitution’s Supremacy Clause. See U.S. Const. art. VI, cl. 2. With this much\\n\\nwe agree. GCT next turns to the Constitution’s Property Clause, which provides:\\n\\n“Congress shall have Power to dispose of and make all needful Rules and\\n\\nRegulations respecting the Territory or other Property belonging to the United\\n\\nStates.” Id. art. IV, § 3, cl. 2. GCT tells us the Property Clause extends to activities\\n\\nthat endanger federal lands but are initiated on non-federal lands. 3 But as a mere\\n\\ngrant of power “to make all needful Rules and Regulations,” the Property Clause’s\\n\\nplain language is not self-executing and does not itself grant the FS authority over\\n\\nUtah State lands adjacent to the Manti-La Sal National Forest.\\n\\n Assuming the Property Clause reaches thus far, Congress, with the aim of\\n\\npreserving federal lands, might rely on it to enact legislation altering the State of\\n\\nUtah’s authority to manage wildlife on its own lands. Federal legislation, however,\\n\\ndoes not supercede the historic police powers of the States “unless that was the clear\\n\\n\\n\\n 3\\n Congress unquestionably has the authority to regulate conduct on private\\nlands that is injurious to the public domain. See United States v. Alford, 274 U.S.\\n264, 267 (1927) (“Congress may prohibit the doing of acts upon privately owned\\nlands that imperil the publicly owned forests.”); Camfield v. United States, 167 U.S.\\n518, 528 (1897) (Congress has the “constitutional right of protecting the public lands\\nfrom nuisances erected upon adjoining [private] property.”).\\n\\n 10\\n\\fand manifest purpose of Congress” in enacting such legislation. Puerto Rico Dept.\\n\\nof Consumer Affairs v. Isla Petrol. Corp., 485 U.S. 495, 500 (1988). While Congress\\n\\nmight enact legislation respecting national forests, the “clear and manifest purpose”\\n\\nof which is to preempt Utah’s traditional trustee and police powers as a sovereign to\\n\\nmanage wildlife within its borders, it has not done so. GCT points us to the Organic\\n\\nAdministration Act of 1897 (Organic Act), which provides: “The Secretary of\\n\\nAgriculture shall make provisions for the protection against destruction by fire and\\n\\ndepredations upon the . . . national forests . . . and he may make such rules and\\n\\nregulations and establish such service as will insure the objects of such reservations,\\n\\nnamely, to regulate their occupancy and use and to preserve the forests thereon from\\n\\ndestruction.” 16 U.S.C. § 551. But the Organic Act’s broad directive that the\\n\\nSecretary “make provisions for the protection against destruction by . . . depredations\\n\\nupon the . . . national forests,” hardly evidences a “clear and manifest” purpose to\\n\\nencroach upon State sovereignty and override Utah’s traditional management of\\n\\nwildlife within its borders outside the Manti-La Sal National Forest.\\n\\n Nor can we say Utah’s placement of mountain goats on State lands “stands as\\n\\nan obstacle to the accomplishment of the full purposes and objectives of Congress”\\n\\nin the management of the national forest. California Coastal Comm’n v. Granite\\n\\nRock Co., 480 U.S. 572, 581 (1987) (quoting Silkwood v. Kerr-McGee Corp., 464\\n\\nU.S. 238, 248 (1984)). Legislation supplemental to the Organic Act calling for\\n\\n\\n 11\\n\\f“cooperative federalism” between federal and state authorities in the area of wildlife\\n\\nmanagement illustrates the point. 4 The Multiple-Use Sustained-Yield Act of 1960\\n\\n(MUSYA), identifies a range of purposes national forests should serve. But the\\n\\nMUSYA also provides “[n]othing herein shall be construed as affecting the\\n\\njurisdiction and responsibilities of the several States with respect to wildlife and fish\\n\\non the national forests.” 16 U.S.C. § 528. If “nothing” in the MUSYA affects the\\n\\njurisdiction of the States with respect to wildlife on the national forests, surely\\n\\n“nothing” therein affects the jurisdiction of the States with respect to wildlife off the\\n\\nnational forests. The Federal Land Policy and Management Act of 1976 (FLPMA),\\n\\ndirects “the public lands be managed in a manner . . . that, where appropriate, will\\n\\npreserve and protect certain lands in their natural condition[.]” The FLPMA further\\n\\n\\n 4\\n Because most federal public land legislation calls for “cooperative\\nfederalism,” express preemption of state laws and regulations is rare in public land\\nlaw. But see, e.g., 16 U.S.C. § 1535(f) (stating state endangered species laws and\\nregulations cannot be less restrictive than federal laws and regulations). Absent\\nexpress preemption, state laws and regulations still may be preempted in either of\\ntwo ways:\\n\\n If Congress evidences an intent to occupy a given field [i.e., field\\n preemption], any state law falling within that field is pre-empted. If\\n Congress has not entirely displaced state regulation over the matter in\\n question, state law is still pre-empted to the extent it actually conflicts\\n with federal law [i.e., conflict preemption], that is, when it is\\n impossible to comply with both state and federal law, or where the state\\n law stands as an obstacle to the accomplishment of the full purposes\\n and objective of Congress.\\n\\nGranite Rock Co., 480 U.S. at 581 (citations omitted).\\n\\n 12\\n\\fprovides, however, that “nothing” in the FLPMA “shall be construed as . . . enlarging\\n\\nor diminishing the responsibility and authority of the States for management of fish\\n\\nand resident wildlife.” 43 U.S.C. §§ 1701(a)(8), 1732(b). And the National Forest\\n\\nManagement Act of 1976 directs the Secretary of Agriculture to develop, maintain,\\n\\nand revise land and resource management plans for the national forests “coordinated\\n\\nwith the land and resource management planning processes of State and local\\n\\ngovernments[.]” 16 U.S.C. § 1604(a). In short, the clarity and manifestness of\\n\\npurpose necessary in the federal statutory scheme GCT relies on to demand the FS\\n\\nprohibit the State of Utah from releasing mountain goats on State lands adjacent to\\n\\nthe Manti-La Sal National Forest is wholly lacking.\\n\\n Like Congress, a federal agency by way of congressional delegation of\\n\\nauthority also may preempt state laws and regulations. Fidelity Fed. Sav. & Loan\\n\\nAss’n v. De La Cuesta, 458 U.S. 141, 153–54 (1982). For example, after providing\\n\\nnotice and opportunity for comment, the FS might issue preemptive regulations\\n\\nimplementing the Organic Act’s directive that the Secretary of Agriculture make\\n\\nprovisions to protect the national forests from depredations. 16 U.S.C. § 551. Such\\n\\nfederal regulations preempt state law to the extent compliance with both is\\n\\nimpossible, or “where the scheme of federal regulation is sufficiently comprehensive\\n\\nto make reasonable the inference that Congress ‘left no room’ for supplementary\\n\\nstate regulation.” Hillsborough Cty. v. Automated Med. Laboratories, Inc., 471 U.S.\\n\\n\\n 13\\n\\f707, 713 (1985); see supra n.4. This assumes, of course, such regulations are\\n\\nconsistent with a reasonable interpretation of the Organic Act and the Secretary\\n\\nreasonably exercised Congress’s delegation of authority. See State of Kansas ex rel.\\n\\nTodd v. United States, 995 F.2d 1505, 1509 (10th Cir. 1993) (citing De La Cuesta,\\n\\n458 U.S. at 153–54 and Chevron, Inc. v. Nat. Res. Def. Counsel, 467 U.S. 837, 844\\n\\n(1984)). But to say the FS may issue preemptive regulations is not to say it may do\\n\\nso subtly. 5 See Isla Petrol. Corp., 485 U.S. at 500. Like our review of the Organic\\n\\nAct and related legislation, where the States have traditionally exercised trustee and\\n\\npolice powers over a field, we assume federal regulations do not preempt the States’\\n\\nexercise of these historic powers unless their intent to do so is “clear and manifest.”\\n\\nHillsborough Cty., 471 U.S. at 715–16.\\n\\n Notably, nothing in 36 C.F.R. § 251.23, the sole FS regulation on which all of\\n\\nGCT’s demands rest, expresses an intent to preempt the State of Utah’s management\\n\\nof wildlife on State lands. Recall § 251.23 is the FS regulation which provides that\\n\\nan RNA within a national forest “will be retained in a virgin or unmodified\\n\\n\\n\\n 5\\n To the degree GCT relies on the Forest Service Manual, the Manti-La-Sal\\nNational Forest Plan, and the Mt. Peale RNA Establishment Record to support its\\nvarious demands—and it does so extensively throughout its complaint—we note such\\ndocuments do not carry the force of law. See Christensen v. Harris Cty., 529 U.S.\\n576, 587 (2000) (distinguishing agency adjudications and notice-and-comment\\nrulemaking, both of which have the force of law, from opinion letters, policy\\nstatements, agency manuals, enforcement guidelines, and the like, all of which lack\\nthe force of law).\\n\\n 14\\n\\fcondition.” But the FS has never proposed the sweeping interpretation of § 251.23\\n\\nthat GCT now endorses, perhaps because in most instances means exist to prevent\\n\\ndepredations of the national forests and RNAs short of wholly disrespecting State\\n\\nsovereignty over State lands, e.g., removing destructive wildlife from the forest.\\n\\nBecause a federal agency may address problems in detail and speak through a number\\n\\nof means, we expect an agency will clearly tell us if it intends for its regulations to\\n\\npreempt the historic police powers of the States. Hillsborough Cty., 471 U.S. at 718;\\n\\nsee also Granite Rock Co., 480 U.S. at 583 (“[I]t is appropriate to expect an\\n\\nadministrative regulation to declare any intention to pre-empt state law with some\\n\\nspecificity.”); Integrity Mgmt. Int’l, Inc. v. Tombs & Sons, Inc., 836 F.2d 485,\\n\\n492–93 (10th Cir. 1987) (“[U]nless an agency has explicitly stated an intent to\\n\\npreempt state law, there is a presumption that no such intent exists.”).\\n\\n Here, the FS has never expressed an intent—let alone a clear and manifest\\n\\none—to preempt the power of the State of Utah in its sovereign capacity to manage\\n\\nwildlife on its own public lands, regardless of where such wildlife wanders off.\\n\\nWhether the FS has the authority to do so by way of congressional delegation\\n\\npursuant to the Organic Act is beside the point. We need do no more than apply the\\n\\napplicable law to the well-pleaded factual allegations of GCT’s complaint (sans the\\n\\nmyriad of legal arguments and conclusions contained therein) to sustain the FS’s\\n\\ndetermination that it lacked the legal authority to prohibit the State of Utah, or more\\n\\n\\n 15\\n\\fparticularly UDWR, from releasing mountain goats on State lands adjacent to the\\n\\nManti-La Sal National Forest. The FS’s legal conclusion that under federal law it\\n\\ncould not prohibit the State of Utah from releasing mountain goats on State lands\\n\\nwas neither “arbitrary, capricious, an abuse of discretion, [n]or otherwise not in\\n\\naccordance with law.” 5 U.S.C. § 706(2)(A).\\n\\n B.\\n\\n The second agency action about which GCT complains is the FS’s denial of\\n\\nthe authority to regulate the State of Utah’s “occupancy” and “use” of the Manti-La\\n\\nSal National Forest by requiring UDWR to obtain a special use permit before\\n\\nreleasing mountain goats on State lands. Like the FS’s denial of GCT’s first\\n\\ndemand, its denial of GCT’s second demand also constitutes final agency action\\n\\nunder the APA. The FS informed GCT that because UDWR released the mountain\\n\\ngoats on State lands, UDWR “was not using or occupying NFS land at the time of\\n\\n[their] release,” and therefore special use authorization from the FS was not required\\n\\nunder FS regulations—second demand denied; end of discussion. This second denial\\n\\nof relief, like the first, was not “tentative or interlocutory,” but was “final and\\n\\nbinding.” Bennett, 520 U.S. at 178. Once the FS decided UDWR was not required\\n\\nto obtain a special use permit before releasing the mountain goats on State lands\\n\\nnothing else was left to decide and legal rights had been determined.\\n\\n\\n\\n\\n 16\\n\\f Still, GCT’s second demand—as novel and far-reaching as its first—also\\n\\nplainly fails as a matter of law. Absent “special use authorization,” Forest Service\\n\\nregulations generally prohibit “uses [except those otherwise enumerated] of National\\n\\nForest System lands . . . and resources.” 36 C.F.R. §251.50. In particular, § 251.23\\n\\nprohibits “occupancy [of an RNA] under a special use permit . . . unless authorized\\n\\nby the Chief of the FS.” GCT says the mountain goats’ release point on State lands\\n\\nis irrelevant to its argument regarding UDWS’s occupancy and use of the national\\n\\nforest. According to GCT, the FS is authorized “to regulate and prohibit the goat\\n\\nintroductions because the State airlifted them to the La Sal Mountains knowing the\\n\\ngoats would use and harm the Manti-La Sal National Forest and Mt. Peale RNA.”\\n\\nTwo pertinent points demonstrate the fallacy of GCT’s argument —based entirely on\\n\\nUDWR’s scienter—that the mountain goats are, in effect, instrumentalities of the\\n\\nState whose presence in the national forest and RNA constitute the State’s occupancy\\n\\nand use of the forest.\\n\\n Federal ownership of lands within a State does not in itself withdraw those\\n\\nlands from the jurisdiction of the State. Kleppe, 426 U.S. 544. “Absent consent or\\n\\ncession a State undoubtedly retains jurisdiction over federal lands within its\\n\\nterritory,” subject to Congress’s “power to enact legislation respecting those lands\\n\\npursuant to the Property Clause.” Id. at 543–44. We have already observed that\\n\\nUtah, not as a private property owner but in its sovereign capacity, has historically\\n\\n\\n 17\\n\\fpossessed broad trustee and police powers over wildlife within its borders. See id.\\n\\nat 545. Just as we did in our preceding analysis regarding the State’s authority to\\n\\nrelease wildlife on its own lands, we assume neither Congress nor the FS intended\\n\\nits enactments to alter the State of Utah’s “historic police powers to manage wildlife\\n\\non federal lands within its borders” unless such intent is “clear and manifest.”\\n\\nWyoming v. United States, 279 F.3d 1214, 1231 (10th Cir. 2002) (emphasis added).\\n\\nAnd again, at the same time, we remain mindful that we “must give full effect to\\n\\nevidence that Congress considered, and sought to preserve, [Utah’s] coordinate\\n\\nregulatory role in our federal scheme.” Id. (emphasis added) (quoting California v.\\n\\nFERC, 495 U.S. 490, 497 (1990)); see supra at 11–13.\\n\\n Where the FS has never asserted exclusive jurisdiction over the management\\n\\nof wildlife in the Manti-La Sal National Forest, GCT’s argument that the State of\\n\\nUtah needs a special use permit before releasing wildlife on State lands—regardless\\n\\nof whether everyone knew such wildlife would end up in the national forest and\\n\\nRNA—runs counter to Congress’s determination, and the FS’s obvious recognition\\n\\nin this case, that the State retains a measure of sovereignty over wildlife management\\n\\nwithin the national forest. See Defenders of Wildlife v. Andrus, 627 F.2d 1238, 1248\\n\\n(D.C. Cir. 1980) (“Despite its ability to take control into its own hands, Congress\\n\\nhas traditionally allotted the authority to manage wildlife to the States.”); 36\\n\\nC.F.R. § 241.2 (FS regulation calling for cooperation with state officials in the\\n\\n\\n 18\\n\\fmanagement of wildlife within the national forests). That the State’s wildlife\\n\\nmanagement responsibilities within the national forest are not exclusive and may be\\n\\noverridden under appropriate circumstances does not mean those management\\n\\nresponsibilities are meaningless absent federal law to the contrary. See Baldwin v.\\n\\nFish and Game Comm’n, 436 U.S. 371, 386 (1978).\\n\\n The next and perhaps more salient point concerning GCT’s second demand is\\n\\nthe mountain goats are ferae naturae or wild animals. See generally Pierson v. Post,\\n\\n3 Cai. 175 (N.Y. Sup. Ct. 1805). As a means of reducing goat populations in other\\n\\nmountainous areas of the State, UDWR captured the goats and then released them\\n\\nonto State lands adjacent to the Manti-La Sal National Forest. Because wild animals\\n\\nare not the private property of those whose lands they occupy, the State of Utah, at\\n\\nleast once it released the goats back into the wild, did not own the goats in the sense\\n\\nthat UDWS’s failure to control their expected movement constituted a sort of\\n\\ntrespass onto national forest lands requiring special use authorization from the FS.\\n\\nOur en banc decision in Mountain States Legal Found. v. Hodel, 799 F.2d 1423 (10th\\n\\nCir. 1986) (en banc) settles the score. In that case, we rejected a private\\n\\nassociation’s argument under the Wild Free-Roaming Horses and Burros Act, 16\\n\\nU.S.C. §§ 1331–37, that “wild horses are . . . instrumentalities of the federal\\n\\ngovernment whose presence on the association’s property constitutes a permanent\\n\\ngovernmental occupation.” Id. at 1428. We explained:\\n\\n\\n 19\\n\\f Neither state nor federal authority over wildlife is premised on any\\n technical “ownership” of wildlife by the government. Although older\\n decisions sometimes referred to government “ownership” of wildlife,\\n that language has been deemed “a fiction expressive in legal shorthand\\n of the importance to its people that a State have power to preserve and\\n regulate the exploitation of an important resource.” Toomer v. Witsell,\\n 334 U.S. 385, 402 (1948). As the Supreme Court declared, “[I]t is pure\\n fantasy to talk of ‘owning’ wild fish, birds, or animals. Neither the\\n States nor the Federal Government . . . has title to these creatures until\\n they are reduced to possession by skillful capture. Douglas v. Seacoast\\n Prod., Inc., 431 U.S. 265, 284 (1977) . . . .\\n\\nMountain States Legal Found., 799 F.2d at 1426. 6\\n\\n The FS’s conclusion regarding GCT’s second demand, namely that it could not\\n\\nrequire the State of Utah to seek special use authorization to occupy and use the\\n\\nManti-La Sal National Forest and Mt. Peale RNA before releasing mountain goats\\n\\non State lands adjacent to the forest, was neither arbitrary, capricious, nor an abuse\\n\\nof discretion, but was entirely consistent with applicable law. Under a proper\\n\\nassessment of this case, GCT’s second demand simply proves too much. The answer\\n\\n\\n 6\\n GCT’s reliance on Light v. United States, 220 U.S. 523 (1911) to support its\\nsecond demand is misplaced. In Light, a private property owner permitted his\\ndomestic cattle, a herd in the range of 500, to move from his property to a Forest\\nReserve and graze thereon in violation of federal regulations establishing grazing\\ndistricts on which only a limited number of cattle were allowed. The Supreme Court\\nupheld an injunction prohibiting the landowner “from pasturing his cattle on the . . .\\nForest Reserve, because he had refused to comply with the regulations adopted by\\nthe Secretary of Agriculture, under the authority conferred by [the Organic Act], to\\nmake rules and regulations as to the use, occupancy, and preservation of forests.”\\nId. at 534. One of among other reasons this case is unlike Light is because once the\\nState released the mountain goats onto State lands and into the wild, any arguable\\nownership interest the State temporarily had in the goats upon their capture\\ncomparable to that of a chattel owner was no more.\\n\\n 20\\n\\fto the legal question of whether federal law required the State of Utah as sovereign\\n\\nto obtain special use authorization to occupy and use the national forest before\\n\\nreleasing mountain goats on State lands is a resounding no.\\n\\n C.\\n\\n Our conclusions thus far—that the State of Utah presently has the authority to\\n\\nrelease mountain goats on State lands adjacent to the Manti-La Sal National Forest\\n\\nand may do so absent special use authorization from the FS—say nothing about the\\n\\nFS’s ability to manage the mountain goats consistent with federal policies and\\n\\nobjectives once the goats enter the national forest and more specifically the Mt. Peale\\n\\nRNA. “The governmental trust responsibility for wildlife is lodged initially in the\\n\\nStates, but only in so far as its exercise may not be incompatible with, or restrained\\n\\nby [federal law].” Mountain States Legal Found., 799 F.2d at 1426 (quotations\\n\\nomitted). And this brings us to the third demand of GTC’s first claim which posits\\n\\nthe FS remove the goats from the national forest and RNA instanter.\\n\\n Lest it become too comfortable with our analysis thus far, we remind the State\\n\\nof Utah, who appears herein as amicus together with seven other States in support\\n\\nof the FS, that the Supreme Court has “repeatedly observed that the power over the\\n\\npublic lands . . . entrusted to Congress is without limitations.” Granite Rock Co.,\\n\\n480 U.S. at 580 (quotations omitted). And the power of the FS under the Organic\\n\\nAct to protect the habitat of national forests “does not admit of doubt.” Hunt v.\\n\\n\\n 21\\n\\fUnited States, 278 U.S. 96, 100 (1928). In Hunt, deer had “greatly injured” the lands\\n\\nof a national game preserve inside a national forest “by overbrowsing upon and\\n\\nkilling valuable young trees, shrubs, bushes, and forage plants.” Id. at 99. The\\n\\nSupreme Court upheld the power of the Secretary of Agriculture under the Organic\\n\\nAct to order the destruction of the deer where necessary to protect the game preserve\\n\\nand national forest. Several years later, in New Mexico State Game Comm’n v.\\n\\nUdall, 410 F.2d 1197 (1969), we held the supervisory powers granted the Secretary\\n\\nof Interior over the management of national parks authorized the Secretary, without\\n\\nthe State’s approval, to direct the killing of a number of deer within a national park\\n\\nfor an ecological study prior to any serious deterioration of habitat. Opining that\\n\\n“[i]n protecting the park property it is immaterial that the United States does not\\n\\nhave exclusive jurisdiction over the land within [the park],” we rejected the State’s\\n\\nargument that “the deer-killing program could be undertaken only after a showing\\n\\nor a finding that there was existing depredation caused by the deer.” Id. at 1199,\\n\\n1201. Given these controlling precedents, we do not question the authority of the FS\\n\\nunder the Organic Act and related legislation—if exercised as a valid preventative\\n\\nor restorative measure—to remove the mountain goats from, or reduce the size of the\\n\\nherd now residing in, the Manti-La Sal National Forest and Mt. Peale RNA.\\n\\n As the reader understands by now, however, the preliminary inquiry is whether\\n\\nGCT’s first claim alleges “final agency action” by asserting the FS did not meet its\\n\\n\\n 22\\n\\fdemand to remove the goats from the national forest and RNA. GCT’s complaint\\n\\nstates that in May 2015, the Regional Forester responded to GCT’s demand to\\n\\nremove the goats: “The Forest Service reiterated that it was developing, with the\\n\\nState’s assistance, a five-year monitoring plan for four rare alpine plants where\\n\\nmonitoring results would be evaluated annually.” The Forester’s letter explained:\\n\\n The Forest Service received your Survey Report on the impacts of\\n mountain goats on plants with special status in November of 2014.\\n While the report suggests negative impacts to plants from mountain\\n goat foraging, it also indicates a need for more refined data collection.\\n In regard to your monitoring documenting trampling evidence within\\n the Mount Peale RNA, evidence similar to that observed by GCT was\\n documented in the area prior to goat introductions, and your trampling\\n evidence was not clearly demonstrated to be the result of mountain goat\\n use. In addition, your observations were not within a fixed area plot,\\n so the density of trampling occurrences cannot be calculated, or\\n compared to future data to establish a trend.\\n\\nAfter the Regional Forester rejected GCT’s demand to remove the goats from the\\n\\nnational forest immediately, GCT unsuccessfully petitioned the Chief of the FS to\\n\\norder the goats removed. GCT’s complaint represents the Chief denied its third\\n\\ndemand and informed GCT the FS “would gather and evaluate the goats’ impact and\\n\\nwork with the State to determine whether additional actions were warranted.”\\n\\nReferring to the Regional Forester’s prior letter to GCT, the Chief reiterated, “there\\n\\nis no compelling evidence to show that the mountain goats introduced by UDWR are\\n\\ncausing immediate damage to NFS land or resources.”\\n\\n\\n\\n\\n 23\\n\\f We do not deny that reasonable minds presently may differ about the impact\\n\\nthe mountain goats are having on the Mt. Peale RNA. In fact, some disagreement\\n\\nappears within the FS itself. As we have observed on multiple occasions, “habitat\\n\\nmanagement is a delicate venture.” Wyoming, 279 F.3d at 1239 (brackets omitted)\\n\\n(quoting Sierra Club-Black Hills Grp. v. United States Forest Serv., 259 F.3d 1281,\\n\\n1286 (10th Cir. 2001)). But the present disagreement over whether the FS must send\\n\\nthe goats packing far away from the Manti-La Sal National Forest, no matter how\\n\\npressing GCT believes the situation to be, does not alone imbue with finality the\\n\\nFS’s decision to study the matter further, such that relief upon proper proof is\\n\\ncurrently available to GCT under APA § 706(2). The FS has acknowledged the\\n\\nsituation and informed GCT that it needs a reasonable period of time to decide\\n\\nhow to proceed. 7 See Oil, Chemical and Atomic Workers Int’l Union v. Zegeer, 768\\n\\n\\n 7\\n The Regional Forester outlined the FS’s intentions in her May 2015 letter:\\n\\n The [FS] is continuing to work with UDWR to evaluate [habitat]\\n impacts. We have developed a rigorous five year monitoring plan to\\n evaluate population trends of four rare alpine plant species and track\\n shifts in species composition and ground cover in the alpine zone,\\n including the Mount Peale [RNA]. The monitoring protocol includes\\n recording direct impacts by grazing animals and uses motion sensing\\n camera[s] to determine the animal species involved. Monitoring data\\n will be analyzed and evaluated annually relative to Forest Plan direction\\n for rare plant species and Federal standards for protection of [RNAs].\\n Based on the results of each annual evaluation, the [FS] will work\\n cooperatively with UDWR to determine an appropriate course of action\\n concerning management of the mountain goats, including whether or not\\n removal or reduction in population objectives is warranted.\\n\\n 24\\n\\fF.2d 1480, 1485 (D.C. Cir. 1985) (concluding the APA indicates a congressional\\n\\nview that federal agencies should act within reasonable time frames). This is the\\n\\nbureaucratic process—like it or not. To suggest the refusal of the FS to remove the\\n\\ngoats from the national forest and RNA this very moment is a sort of agency action\\n\\n“mark[ing] the ‘consummation’ of the agency’s decisionmaking process,” rather than\\n\\na “tentative or interlocutory” action, is simply inconsistent with the complaint’s\\n\\nfactual allegations and the underlying documents on which those allegations rely.\\n\\nBennett, 520 U.S. at 178. The district court was correct in holding it lacked subject\\n\\nmatter jurisdiction to review the FS’s denial of GCT’s third demand for want of final\\n\\nagency action.\\n\\n III.\\n\\n While the FS’s “wait and see” response to GCT’s demand that it remove the\\n\\nmountain goats from the Manti-La Sal National Forests does not constitute “final\\n\\nagency action” under the APA, GCT’s second claim is that such response does\\n\\nconstitute a “failure to act”, redresssable under APA § 706(1) as agency action\\n\\n“unlawfully withheld.” According to GCT, 36 C.F.R. § 251.23 contains a categorical\\n\\nimperative the FS refuses to heed: “Research Natural Areas will be retained in a\\n\\nvirgin or unmodified condition except where measures are required to maintain a\\n\\nplant community which the area is intended to represent.”\\n\\n\\n\\n\\n 25\\n\\f APA § 704’s requirement of final agency action does not square well with a\\n\\ndefinition of “agency action” that includes a “failure to act.” 5 U.S.C. § 551(13).\\n\\nAnd obviously, the test the Supreme Court has set forth to determine whether agency\\n\\naction is final does not readily accommodate an agency’s failure to act. Bennett, 520\\n\\nU.S. at 177–78. “If an agency has failed to act with respect to a matter that a\\n\\ncomplaining party seeks to compel under § 706(1), it is hard to comprehend the\\n\\ncontested inaction as ‘final action’ as that term is defined in Bennett v. Spear.”\\n\\nWestern Org. of Resource Councils v. Zinke, 892 F.3d 1234, 1247 (D.C. Cir. 2018)\\n\\n(Edwards, J., concurring). Indeed, we have noted the problem and observed that\\n\\nsome courts have “implicitly recognized that unlawfully withheld actions are\\n\\nconsidered final under § 704.” Southern Utah Wilderness Alliance v. Norton, 301\\n\\nF.3d 1217, 1229 n.9 (10th Cir. 2002), rev’d 542 U.S. 55 (2004) (hereinafter SUWA).\\n\\n Fortunately, in SUWA the Supreme Court considered “what limits the APA\\n\\nplaces upon judicial review of agency inaction.” SUWA, 542 U.S. at 61. To “protect\\n\\nagencies from undue judicial interference with their lawful discretion,” among other\\n\\nreasons, the Court held “a claim under § 706(1) can proceed only where a plaintiff\\n\\nasserts that an agency failed to take a discrete agency action that it is required to\\n\\ntake.” Id. at 64, 66; see Wyoming v. United States Dept. of Interior, 839 F.3d 938,\\n\\n942 (10th Cir. 2016). The Supreme Court explained APA § 706(1) carries forward\\n\\ncourts’ traditional practice of reviewing a governmental entity’s failure to act by way\\n\\n\\n 26\\n\\fof writ of mandamus. “The mandamus remedy was normally limited to enforcement\\n\\nof ‘a specific, unequivocal command,’ the ordering of a ‘precise act about which an\\n\\nofficial had no discretion whatever.’” SUWA, 542 U.S. at 63 (brackets, citations\\n\\nand ellipses omitted). Consistent with such practice, the Court reasoned “§706(1)\\n\\nempowers a court only to compel an agency to perform a ministerial or non-\\n\\ndiscretionary act or to take action upon a matter, without directing how it shall act.”\\n\\nId. at 64 (quotations omitted).\\n\\n The language of the FS regulation at issue in this case, § 251.23, certainly is\\n\\nmandatory as to the ultimate objective. The regulation plainly states RNA’s “will\\n\\nbe retained in a virgin or unmodified condition[.]” The regulation, however, leaves\\n\\nentirely to the FS the decision of how best to achieve this objective. Indeed, GCT’s\\n\\ncomplaint recites provisions of the Forest Service Manual (FSM) which suggest as\\n\\nmuch. The complaint states FSM 4063.30(4) advises the FS to “‘[r]emove exotic\\n\\nplants or animals [from an RNA] to the extent practicable.’” (emphasis added).\\n\\nMeanwhile, FSM 4063.32 advises: “If exotic plants or animals have been introduced\\n\\ninto an established [RNA], the Station Director and the Regional Forester exercise\\n\\ncontrol measures that are in keeping with established management principles and\\n\\nstandards to eradicate them, when practical.” (emphasis added).\\n\\n So assuming the mountain goats presence within the Manti-La Sal National\\n\\nForest and Mt. Peale RNA is inconsistent with § 251.23’s objective, how shall the\\n\\n\\n 27\\n\\fFS proceed? FSM 4062.30(4) tells us removing the mountain goats from the national\\n\\nforest and RNA is one option. FSM 4063.32 tells us eradicating or destroying the\\n\\ngoats is another option. Or perhaps a reduction in the size of the herd would suffice.\\n\\nMaybe a fence or other barrier to surround the goats, the habitat, or both would be\\n\\nfeasible. Maybe a spray or other similar mean exists that would not harm the foliage\\n\\nwithin the RNA but make it less desirable to a mountain goat’s palate. Section\\n\\n251.23 does not foreclose any of these options. In other words, the FS regulation\\n\\nprovides us with no discernible rules under which we may direct the FS to act in\\n\\nexercising its enforcement powers. Section 251.23 simply does not call for a discrete\\n\\naction that will assure us the RNA “will be retained in a virgin or unmodified\\n\\ncondition[.]” See Black’s Law Dictionary 565 (10th ed. 2014) (defining “discrete”\\n\\nas “[i]individual; separate; distinct”). We are not experts in the field of habitat\\n\\nmanagement and preservation and surely have no business attempting to instruct the\\n\\nFS how best to achieve § 251.23’s objective. See SUWA, 542 U.S. at 66–67. The\\n\\ncrux of the matter is GTC’s complaint does not allege the FS has failed to take a\\n\\ndiscrete agency action that FS regulations require it take. See SUWA, 542 U.S. at\\n\\n66. Therefore GCT’s second claim based on the FS’s failure to act is not cognizable.\\n\\n ***\\n\\n As modified, the judgment of the district court dismissing GCT’s complaint\\n\\nis AFFIRMED.\\n\\n\\n 28\\n\\fNo. 17-4074, tah Native Plant Society, et al. v. United States Forest Service, et al.\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2260,"cells":{"id":{"kind":"number","value":4617604,"string":"4,617,604"},"name":{"kind":"string","value":"John Thomas TALLEY, Plaintiff - Appellant, v. TIME, INC., D/B/A Sports Illustrated Magazine; George Dohrmann ; Thayer Evans, Defendants - Appellees."},"name_abbreviation":{"kind":"string","value":"Talley v. Time, Inc."},"decision_date":{"kind":"string","value":"2019-05-08"},"docket_number":{"kind":"string","value":"18-6169"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Matheson, Murphy, Eid\", \"parties\": \"\", \"opinions\": [{\"author\": \"MATHESON, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 8, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n JOHN THOMAS TALLEY,\\n\\n Plaintiff - Appellant,\\n\\n v. No. 18-6169\\n\\n TIME, INC., d/b/a Sports Illustrated\\n Magazine; GEORGE DOHRMANN;\\n THAYER EVANS,\\n\\n Defendants - Appellees.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the Western District of Oklahoma\\n (D.C. No. 5:14-CV-00853-D)\\n _________________________________\\n\\nRaymond S. Allred (Gary L. Richardson, Charles L. Richardson, Alisa G. Hopkins, and\\nLia R. Rottman, with him on the briefs), of Richardson Richardson Boudreaux, PPLC,\\nTulsa, Oklahoma, for Plaintiff - Appellant.\\n\\nRobert D. Nelon (Jon Epstein, with him on the brief), of Hall, Estill, Hardwick, Gable,\\nGolden & Nelson, P.C., Oklahoma City, Oklahoma, for Defendants - Appellees.\\n _________________________________\\n\\nBefore MATHESON, MURPHY, and EID, Circuit Judges.\\n _________________________________\\n\\nMATHESON, Circuit Judge.\\n _________________________________\\n\\f In 2013, Sports Illustrated magazine (“SI”) published a five-article series on\\n\\nthe Oklahoma State University (“OSU”) football program. The series explored\\n\\n“illicit payments” and other “extreme measures” OSU used to recruit and retain top\\n\\nplayers. Aplt. App., Vol. II at A446; Aplt. App., Vol. III at A699. The first article in\\n\\nthe series, titled “The Money,” described an assistant coach who offered “de facto\\n\\nbonus[es] . . . based on performances on the field.” Aplt. App., Vol. II at A448. It\\n\\nalso discussed boosters and coaches who made “direct payments to players . . .\\n\\nindependent of performance,” id., and “funnel[ed] money to players through dubious\\n\\nwork arrangements,” id. at A452.1 And it briefly profiled John Talley, a booster who\\n\\n“had been close to the football program since at least 2002” and who allegedly\\n\\n“grossly overpaid [OSU players] for jobs they did or compensated them for jobs they\\n\\ndidn’t do.” Id.\\n\\n Mr. Talley sued Time, Inc., which publishes SI, and SI reporters Thayer Evans\\n\\nand George Dohrmann (collectively, “the Defendants”) in state court, claiming that\\n\\nthe article placed him in a false light and invaded his privacy. Invoking diversity\\n\\njurisdiction under 28 U.S.C. § 1332, the Defendants removed the case to the United\\n\\nStates District Court for the Western District of Oklahoma. After discovery, the\\n\\n\\n\\n\\n 1\\n According to the National Collegiate Athletic Association (“NCAA”), a\\nbooster—or “representative[] of [an] institution’s athletic interests”—is an individual\\nwho supports “teams and athletics departments through donations of time and\\nfinancial resources which help student-athletes succeed on and off the playing field.”\\nSee https://perma.cc/R96W-G7AZ.\\n 2\\n\\fDefendants moved for summary judgment. The district court granted the motion.\\n\\nMr. Talley timely appealed.\\n\\n Exercising jurisdiction under 28 U.S.C. § 1291, we affirm because Mr. Talley\\n\\nhas not demonstrated a genuine issue of material fact as to whether the Defendants\\n\\nacted with actual malice, an element of Oklahoma’s false light tort.\\n\\n I. BACKGROUND\\n A. Oklahoma’s False Light Tort2\\n\\n Oklahoma recognizes the common law tort of false light invasion of privacy.\\n\\nIt has adopted the Restatement (Second) of Torts § 652E, which reads:\\n\\n One who gives publicity to a matter concerning another\\n that places the other before the public in a false light is\\n subject to liability to the other for invasion of his privacy,\\n if\\n\\n (a) the false light in which the other was placed would be\\n highly offensive to a reasonable person, and\\n\\n (b) the actor had knowledge of or acted in reckless\\n disregard as to the falsity of the publicized matter and the\\n false light in which the other would be placed.\\n\\nSee McCormack v. Okla. Publ’g Co., 613 P.2d 737, 740 (Okla. 1980) (recognizing\\n\\n“the tort of invasion of privacy . . . as set out in the Restatement”); Colbert v. World\\n\\nPubl’g Co., 747 P.2d 286, 290 (Okla. 1987) (noting that the Oklahoma Supreme\\n\\n\\n 2\\n Because federal court jurisdiction in this case is based on the diversity of\\ncitizenship between the parties, 28 U.S.C. § 1332, we apply the substantive law of\\nthe forum state—Oklahoma. See Haberman v. Hartford Ins. Grp., 443 F.3d 1257,\\n1264 (10th Cir. 2006) (“In diversity cases, the substantive law of the forum state\\ngoverns the analysis of the underlying claims . . . .”).\\n 3\\n\\fCourt has “specifically adopt[ed] the treatment of [invasion of privacy] in the\\n\\nRestatement of the Law of Torts (Second)”).\\n\\n False light plaintiffs must prove three elements:\\n\\n (1) “the defendant gave publicity to a matter concerning\\n the plaintiff that placed the plaintiff before the public in a\\n false light,”\\n\\n (2) “the false light in which the plaintiff was placed would\\n be highly offensive to a reasonable person,” and\\n\\n (3) “the defendant had knowledge of or acted in reckless\\n disregard as to the falsity of the publicized matter and the\\n false light in which the other would be placed.”\\n\\nMitchell v. Griffin Television, LLC, 60 P.3d 1058, 1061 (Okla. Civ. App. 2002).\\n\\n Oklahoma courts have specified that the third element—“knowledge of or . . .\\n\\nreckless disregard as to the falsity of the publicized matter”—is identical to the actual\\n\\nmalice standard articulated in New York Times Co. v. Sullivan, 376 U.S. 254 (1964).\\n\\nSee Herbert v. Okla. Christian Coal., 992 P.2d 322, 328 (Okla. 1999) (quoting New\\n\\nYork Times, 376 U.S. at 280).3 We discuss this standard in greater detail below.\\n\\n B. Factual Background\\n\\n SI is a sports magazine published by Time, Inc. Aplt. App. Vol. I at A85. In\\n\\nearly 2012, Mr. Evans, who was then a reporter at Fox Sports, learned that the OSU\\n\\nfootball program might have been using financial inducements to attract and retain\\n\\n\\n 3\\n Because Oklahoma has explicitly adopted the actual malice standard for false\\nlight invasion of privacy claims, the following analysis uses the term “actual malice”\\nas shorthand for the “knowledge of or . . . reckless disregard” element of the false\\nlight tort. Mitchell, 60 P.3d at 1061.\\n 4\\n\\fplayers. Id. at A86; Aplt. App., Vol. II at A388. That fall, after taking a job at SI,\\n\\nMr. Evans shared this information with SI’s Executive Editor B.J. Schecter. Aplt.\\n\\nApp., Vol. II at A388. Mr. Schecter asked Mr. Dohrmann if he would be interested\\n\\nin working with Mr. Evans on a story about the OSU program. Id. When Mr.\\n\\nDohrmann agreed, SI began a 10-month investigation into OSU’s recruiting and\\n\\nretention practices. Aplt. App., Vol. I at A87; Aplt. App., Vol. II at A388, A438.\\n\\nMr. Schecter led the investigation, which involved dozens of interviews with OSU\\n\\nplayers, coaches, and boosters. Aplt. App., Vol. I at A86-88; Aplt. App., Vol. II at\\n\\nA438, A442.\\n\\n In September 2013, SI published its findings in a five-part article series titled\\n\\n“The Dirty Game.” Aplt. App., Vol. II at A445-82. Below, we quote the passage\\n\\nabout Mr. Talley, which appeared in the first article of the series. We then describe\\n\\nthe steps SI took to investigate, research, draft, and edit the Talley passage.\\n\\n The Article\\n\\n Mr. Dohrmann and Mr. Evans co-authored “The Dirty Game” using\\n\\ninformation they gathered during SI’s investigation. Aplt. App., Vol. I at A87-88;\\n\\nAplt. App., Vol. III at A770. The first article of the series—a roughly 5,000-word\\n\\npiece titled “The Money”—described gratuities and inducements that OSU used to\\n\\nattract and retain top players. Aplt. App., Vol. II at A445-53. It detailed financial\\n\\nbenefits—including payments for performance on the field—that coaches offered to\\n\\nplayers on the team. Id. It also described how several “boosters,” including Mr.\\n\\n 5\\n\\fTalley, “funnel[ed] money to players,” id. at A452, by paying them “for little or no\\n\\nwork,” id.\\n\\n Mr. Talley was the North Central Area Director of the Fellowship of Christian\\n\\nAthletes (“FCA”).4 Id. at A452; Aplt. App., Vol. I at A135. The 442-word passage\\n\\nabout him reads, in full, as follows:\\n\\n According to multiple players, though, the\\n generosity of [booster Kay] Norris, who died of lung\\n cancer in 2006, was exceeded by that of other [OSU]\\n Cowboys supporters. John Talley, an area director of the\\n Fellowship of Christian Athletes, had been close to the\\n football program since at least 2002, when his son, Saul,\\n was a walk-on long snapper. “John Talley was the hot\\n name around campus,” [player Rodrick] Johnson says. “If\\n you needed a job, call John Talley.”\\n\\n [Players Fath’] Carter, [Brad] Girtman, [Rodrick]\\n Johnson and Thomas Wright each say that Talley either\\n grossly overpaid them for jobs they did or compensated\\n them for jobs they didn’t do. They allege that numerous\\n other players benefited from Talley's generosity too.\\n Girtman says Talley paid him $1,500 to $2,000 every two\\n weeks during one summer to work on his horse ranch, far\\n more than the job was worth. Talley could also be counted\\n on to set up speaking gigs for players, paying $100 for a\\n 15- to 20-minute talk. “You might get more depending on\\n who you were,” says Shaw. Carter says he and a few other\\n players were once paid by Talley to help shoe horses.\\n Asked if the players did the work, Carter says, “Are you\\n kidding? Most of us hadn’t even seen a horse before.”\\n\\n Quarterback Aso Pogi (1999 to 2002) says he and\\n another player lived at Talley’s ranch one summer rent-\\n 4\\n In his deposition, Mr. Talley explained that the FCA’s mission is “[t]o reach\\ncoaches, student athletes, and all who they influence, to give the opportunity to\\nreceive Jesus Christ as Lord and Savior, and to serve Him in their relationships and in\\nthe church.” Aplt. App., Vol. I at A136.\\n 6\\n\\f free. In retrospect Pogi says, “It’s a big deal. I was the\\n starting quarterback.” (Talley says that Pogi lived at his\\n ranch and had to work to cover his rent; Pogi denies that\\n he did any work.)\\n\\n Talley says that he sometimes paid players a fee for\\n speaking engagements and that they frequently did work\\n on his ranch, noting he always paid an hourly wage. He\\n also says he cleared the speaking fees and the hourly\\n employment through the university’s compliance office. “I\\n have paid lots of players to work on my ranch,” Talley\\n says. “But I would never pay someone not to work.”\\n\\n OSU compliance director Kevin Fite says of the\\n speaking engagements arranged by Talley, “They were not\\n cleared through our office as paid speaking engagements.\\n In fact, two of my staff members indicated to me that they\\n had had conversations with John and told him you cannot\\n pay for speaking engagements. If you want to employ our\\n student-athletes for other things, that’s fine, but you cannot\\n pay them for speaking engagements.”\\n\\n While Fite says the school cleared Talley to employ\\n athletes on his ranch, he acknowledges that Talley’s\\n paying in cash “is not something I am comfortable with. I\\n think that’s a concern. I would prefer to see it done a\\n different way.”\\n\\nGeorge Dohrmann & Thayer Evans, Special Report on Oklahoma State Football: Part 1\\n\\n– The Money, Sports Illustrated, Sept. 16, 2013, at 39-40; Aplt. App., Vol. II at A452.\\n\\n The Reporting Process\\n\\n As previously noted, SI began investigating the OSU football team in late\\n\\n2012. Aplt. App., Vol. I at A86-87. Between 2000 and 2005, OSU achieved its first\\n\\nwinning seasons in more than a decade. Aplt. App., Vol. II at A445. The Defendants\\n\\nsuspected that new and perhaps impermissible recruiting strategies might have\\n\\n 7\\n\\fcontributed to this sudden success. Id. They focused their research on individuals\\n\\nwho were involved with the program between 2000 and 2005. Id. at A388.\\n\\n a. Interviews with players and Mr. Talley\\n\\n The SI reporters interviewed 60 to 70 former and current OSU players,\\n\\ncoaches, boosters, and administrators. Aplt. App., Vol. I at A87; Aplt. App., Vol. II\\n\\nat A388-90; Aplt. App., Vol. III at A747. The reporters recorded the interviews they\\n\\nused to write the passage about Mr. Talley. Aplt. App., Vol. II at A389. These\\n\\nrecordings were later produced during discovery.5 In addition, Mr. Schecter\\n\\n\\n\\n\\n 5\\n In support of their motion for summary judgment, the Defendants provided\\nthe district court with audio excerpts from Mr. Dohrmann’s interview with former\\nOSU player Fath’ Carter, Aplt. App., Vol. II at A483; Mr. Evans’s interviews with\\nformer players Rodrick Johnson, id. at A487, Seymour Shaw, id. at A497, Brad\\nGirtman, id. at A505, Thomas Wright, id. at A517, Aso Pogi, id. at A512, Larry\\nBrown, id. at A518, and Chijuan Mack, id. at A519; Mr. Dohrmann and Mr. Evans’s\\ninterview with Thomas Wright, id. at A509, and Mr. Schecter and Mr. Dohrmann’s\\ninterview with OSU officials, id. at A523. The Defendants also provided audio\\nexcerpts from an interview that NCAA investigators conducted with OSU operations\\ndirector Mack Butler during the NCAA’s post-article investigation. Aplt. App., Vol.\\nIII at A546. Mr. Talley submitted full-length interview recordings of Mr. Evans’s\\ninterviews with former players Aso Pogi, Aplt. App., Vol. IV at A894, Calvin\\nMickens, id. at A895, Chijuan Mack, id. at A896, Thomas Wright, id. at A897, and\\nXavier Lawson-Kennedy, id. at A898.\\n\\n 8\\n\\finterviewed Mr. Talley.6 Id. at A404. We describe below the information gathered\\n\\nabout Mr. Talley during these interviews.7\\n\\n i. Mr. Evans’s interviews\\n\\n Mr. Evans conducted most of the interviews. Id. at A388. After each\\n\\ninterview, he reviewed his notes and/or the recording and e-mailed summaries to Mr.\\n\\nDohrmann and Mr. Schecter. Id. at A389-90, A408, A438. He also occasionally re-\\n\\ninterviewed players to ensure that his information was accurate. Id. at A390.\\n\\n 1) Payments for speeches and work\\n\\n Between November 2012 and January 2013, Mr. Evans spoke to former OSU\\n\\nplayers Brad Girtman, Seymour Shaw, Prentiss Elliott, Chijuan Mack, Xavier\\n\\nLawson-Kennedy, Doug Bond, Thomas Wright, Rodrick Johnson, T.J. Minor, and\\n\\nLarry Brown. Id. at A389. The players reported the following:\\n\\n Brad Girtman revealed that Mr. Talley paid him “fifteen hundred, a\\n thousand” dollars to perform “ranch hand” tasks. Dist. Ct. Doc. 60, Ex. 17\\n at 0:14-0:20, 0:42 (Girtman Interview); see also Aplt. App., Vol. II at\\n A508. When Mr. Evans asked if these payments were excessive, Mr.\\n Girtman responded, “I mean, I thought he was overpaying me, cus I wasn’t\\n sure what I was doing.” Girtman Interview at 0:06-0:13.\\n\\n Seymour Shaw reported that Mr. Talley “always paid [players] to go talk”\\n and that “if you needed some money, you’d go to John Talley.” Dist. Ct.\\n\\n 6\\n Although Mr. Schecter recorded his interview with Mr. Talley, he stated that\\nthe file was “corrupted after a minute and a half.” Aplt. App., Vol. II at A410.\\nAccordingly, the recording is not available.\\n 7\\n In this opinion, we have quoted from the interview recordings, which are part\\nof the record on appeal, without the benefit of transcripts. The parties did not\\nprovide certified transcripts.\\n 9\\n\\f Doc. 60, Ex. 15 at 1:09-1:13, 1:16-1:19 (Shaw Interview); see also Aplt.\\n App., Vol. II at A500.\\n\\n Chijuan Mack volunteered Mr. Talley’s name without any prompting from\\n Mr. Evans and described the speaking arrangements and team building\\n activities that Mr. Talley organized for OSU players. Dist. Ct. Doc. 71, Ex.\\n 12 at 45:49-46:37 (Mack Interview). When Mr. Evans asked, “So, like,\\n during the season you would go speak to schools, read to schools, and\\n they’d pay you like a normal job, obviously?,” Mr. Mack responded, “No,\\n during the season you couldn’t get paid during the season. . . . But during\\n the summer, you’d get to go there, he got a big farm like, he’d do stuff like\\n focus groups . . . That’s when you would get paid.” Id. at 47:45-48:56.8\\n\\n Mr. Evans asked Larry Brown, “You would go talk to kids and [Mr. Talley]\\n would pay you to go talk to kids, right?” Mr. Brown responded, “Yeah.”\\n Dist. Ct. Doc. 60, Ex. 25 at 0:39-0:45 (Brown Interview).\\n\\n Thomas Wright denied that Mr. Talley ever overpaid him for work. Dist.\\n Ct. Doc. 71, Ex. 13 at 6:23-36 (Evans Wright Interview). When Mr. Evans\\n mentioned that “some guys got paid” for Mr. Talley’s speaking\\n engagements, Mr. Wright responded, “I know some guys did, but I didn’t.\\n I didn’t get paid for that.” Id. at 6:27-45. In a different interview, Mr.\\n Wright stated that OSU players worked for boosters but “got kinda\\n overpaid.” Dist. Ct. Doc. 60, Ex. 19 at 0:00-0:21 (Evans Dohrmann Wright\\n Interview). When asked about Mr. Talley, Mr. Wright said, “I don’t think\\n he was into all that, he seemed pretty good, but I mean he had to have been\\n a booster I would think . . . . He was hooking us up big time with jobs, but I\\n\\n\\n\\n 8\\n Mr. Mack denied that players were overpaid for work and stated that OSU\\n“made sure they did everything by the law.” Mack Interview at 39:40-40:18. But he\\nalso reported that OSU did all it could to take advantage of what was permitted under\\nthe rules: “[If] the rules say that you can do this, . . . if that’s the case, [OSU would\\nfollow] the rule all the way to the nitty gritty. . . . So they would have somebody go\\nto check that and he would come back and be like, ‘Well look they can do this and\\nthis,’ so the next time we’d get our monthly check, the check might go up a hundred\\nor 200 . . . it would fluctuate because they tryin’ to get us more.” Id. at 42:36-43:14.\\nAs another example, Mr. Mack reported that coaches would not hand players extra\\ncash but instead gave team captains additional money—two or three hundred\\ndollars—on their OSU ID cards, which players could spend anywhere on campus.\\nSee id. at 43:15-45:12.\\n 10\\n\\f don’t think, as far as giving us money, I don’t think—he’d never hand us\\n money . . . but he would definitely hook us up with jobs.” Id. at 0:53-1:21.\\n\\n Rodrick Johnson reported that Mr. Talley overpaid him for work. When\\n Mr. Evans asked about “jobs that you guys got paid crazy amounts for,”\\n Mr. Johnson immediately interrupted and said, “John Talley, John Talley.\\n Oh, he owes me, still to this day.” Dist. Ct. Doc. 60, Ex. 13 at 0:00-0:07\\n (Johnson Interview). Mr. Johnson then added, “He used to pay very well. I\\n would work for about three hours and I would get paid probably about 400\\n bucks.” Id. at 0:15-0:22. Mr. Johnson described cutting bushes and doing\\n yard work on Mr. Talley’s property and said, “Max[imum,] I would do\\n probably about ten hours and I would get—a lot of money. Like, it’d be\\n enough to actually make it through the summer.” Id. at 0:51-1:00. Mr.\\n Johnson also noted that, while some employers paid with an “actual check\\n that wasn’t anything under the table,” “Talley would pay in cash.” Id. at\\n 2:32-2:39. Additionally, Mr. Johnson said that Mr. Talley paid him for\\n speaking engagements and that “one time I went to speak at a school and he\\n paid me 100 bucks, and it was, like, for 20 minutes” and that “[t]here were\\n guys that did that almost every day.” Id. at 2:42-3:02. He also stated “John\\n Talley was the hot name around campus tryin’ to get jobs. If you need a\\n job, call John Talley.” Id. at 3:20-3:25; see also Aplt. App., Vol. II at\\n A494.\\n\\n Xavier Lawson-Kennedy stated that he never worked for Mr. Talley but\\n that he “actually wanted to” because “[Mr. Talley] had the funnest . . . he\\n had the best jobs to do, like go talk to kids.” Dist. Ct. Doc. 71, Ex. 14 at\\n 13:20-32 (Lawson-Kennedy Interview).\\n\\n By March 2013 Mr. Evans had spoken with 19 players. According to his\\n\\nnotes, “five [of these] admitted to taking cash, including three who said they were\\n\\npaid for their play, and two others admitted receiving extra per diem money.” Aplt.\\n\\nApp., Vol. II at A389. In addition, “[f]ive players said they were either paid for no-\\n\\nshow jobs or were significantly overpaid for work.” Id. Multiple players—including\\n\\nMr. Girtman, Mr. Shaw, Mr. Brown, Mr. Wright, and Mr. Johnson—volunteered Mr.\\n\\n\\n\\n 11\\n\\fTalley’s name or provided detail about his involvement with the OSU program. Id. at\\n\\nA389, A438.\\n\\n 2) Mr. Pogi living at the ranch\\n\\n Shortly before publishing the article, Mr. Evans interviewed former OSU\\n\\nquarterback Aso Pogi.9 Id. at A390. Mr. Pogi said he frequently participated in Mr.\\n\\nTalley’s speaking engagements but insisted he was never paid to speak. Dist. Ct.\\n\\nDoc. 71, Ex. 10 at 4:43-4:52 (Pogi Interview). He also described living on Mr.\\n\\nTalley’s ranch one summer. The relevant exchange proceeded as follows:\\n\\n Mr. Evans: So, how many times do you estimate John\\n [Talley] gave you money? John admitted that he gave\\n money. Just that way you know that I’m not lying to you.\\n John admitted it, said that he cleared it with the school, the\\n school said they never cleared it, and that John was never\\n supposed to give you guys money.\\n\\n Mr. Pogi: Um, I don’t know, man, it was, you know, just\\n speaking engagements—\\n\\n Mr. Evans: You spoke a lot, though?\\n\\n Mr. Pogi: Yeah I did, and, and, you know, we don’t get\\n anything.\\n\\n Mr. Evans: I know, I know, listen, and that’s another\\n argument for another day. . . . But you spoke dozens of\\n times, is what people said.\\n\\n\\n 9\\n The record does not indicate when this interview occurred, but in the\\ninterview recording, Mr. Evans told Mr. Pogi, “We talked to John [Talley]\\nyesterday.” Dist. Ct. Doc. 71, Ex. 10 at 5:56-6:02 (Pogi Interview). Mr. Schecter\\ninterviewed Mr. Talley on September 3, 2013, Aplt. App., Vol. II at at A404, which\\nsuggests that Mr. Evans’s conversation with Mr. Pogi occurred on September 4,\\n2013.\\n 12\\n\\fMr. Pogi: Yeah.\\n\\nMr. Evans: And he gave you money dozens of times.\\n\\nMr. Pogi: I was on the road a lot to speak. And it was just\\nfor my gas, you know, just cus I had to drive my personal\\nvehicle there, you know what I mean? But, um—\\n\\nMr. Evans: It’s not an indictment that you’ve done\\nanything wrong, Aso, okay? I’m not—\\n\\nMr. Pogi: And listen, I’m, I’m not really, I’m not taking it\\nthat way. I’m, I’m kinda like, this is kinda throwing me\\noff—\\n\\nMr. Evans: It is, and it should. . . . There’s no good way to\\ndo it, Aso. You have to understand, I mean, from my\\nperspective, there’s no good way to do it. Cus if I call you\\nahead of time, you know, I want to get in front of you\\nbecause, again, like, your name is in the story for money.\\n\\nMr. Pogi: Yeah, that, and that, that kinda, that kinda hurts\\nme a little bit.\\n\\nMr. Evans: I mean, Aso, I mean, I’m sorry, you know? I\\nmean, there’s just nothing I can do about it. You know\\nwhat I’m saying? I mean, like, that’s why I came to get\\nyour response. And we’ll put your response in there.\\n\\nMr. Pogi: Well let me, let me just say this, then. Let me\\nsay that, um, I’d like to just, um, I’m not going to sit here\\nand plead the Fifth or anything like that, but I, I’d like to,\\nlike, you know, do my own research on it, because I’m\\nbeing honest with you in telling you that, you know, we\\nreceived gas money, and—\\n\\nMr. Evans: That’s fine. I mean, I’ll tell you what you’re\\ngonna find. Because I know it, I mean, I know it from the\\nNCAA perspective, right? I mean, like I said, we went to\\nthem and told them, right? John said that he had had that\\napproved, okay? Compliance said that they never\\napproved it, Aso. So he was—and it’s against the rules for\\n\\n 13\\n\\fyou to be paid during the season, any of that stuff, for\\nspeaking engagements, et cetera.\\n\\nMr. Pogi: And guys put me out there?\\n\\nMr. Evans: They threw, oh, absolutely.\\n\\nMr. Pogi: That I was the main one, huh?\\n\\nMr. Evans: No. You’re not the main one. I mean, there’s\\na, it’s a long list, my man. Okay?\\n\\nMr. Pogi: I mean, I, I just, I did a—\\n\\nMr. Evans: You worked at his ranch, too.\\n\\nMr. Pogi: I did a lot.\\n\\nMr. Evans: You worked at his ranch.\\n\\nMr. Pogi: I—I lived there.\\n\\nMr. Evans: You lived there, but you never, you never\\nworked—\\n\\nMr. Pogi: I ne—I didn’t, I didn’t do anything like—\\n\\nMr. Evans: You knew guys came out there and worked. I\\nmean he says estimates a thousand athletes have worked at\\nhis ranch.\\n\\nMr. Pogi: Yeah.\\n\\nMr. Evans: A thousand. I mean some people said that\\nthey got paid for not doing anything at his ranch. You\\nknow they just came out and they just basically got\\nmoney—\\n\\nMr. Pogi: [Laughs]\\n\\n....\\n\\n\\n\\n 14\\n\\f Mr. Evans: I mean, you lived with John [Talley], right? I\\n mean, what was the arrangement?\\n\\n Mr. Pogi: I had no arrangement. That’s the thing that’s\\n throwing me off. I’m like, “Arrangement?” I-I-I didn’t\\n make, you know, any money.\\n\\n Mr. Evans: But you shouldn’t have been, I mean, like, you\\n lived with him.\\n\\n Mr. Pogi: Yeah I lived with him.\\n\\n Mr. Evans: I mean, like, I mean did anybody ever—\\n\\n Mr. Pogi: Me and George Horton, we, we lived with John,\\n and, you know, we—\\n\\n Mr. Evans: He didn’t charge you rent, obviously.\\n\\n Mr. Pogi: No, he didn’t charge us rent. No, no, we lived\\n there for a summer, you know and that was about it.\\n\\n Mr. Evans: And you saw the guys come out and work.\\n What’d you do for money in the summers? You went and\\n did the speaking engagements?\\n\\n Mr. Pogi: I did speaking engagements. I did a lot of\\n speaking. But I wasn’t getting paid like that. I mean, I got\\n gas money.\\n\\nId. at 9:41-12:29; 17:24-18:13.\\n\\n ii. Mr. Dohrmann’s interviews\\n\\n Mr. Dohrmann also spoke with players and OSU officials. He met in Denver\\n\\nwith former OSU player Fath’ Carter. During that interview, Mr. Dohrmann said,\\n\\n“The other one I heard was . . . that there were like some funky jobs, like you go and\\n\\nmow the lawn, or you don’t mow the lawn.” Dist. Ct. Doc. 60, Ex. 11 at 0:00-0:11\\n\\n(Carter Interview). Before Mr. Dohrmann could finish the question, Mr. Carter\\n 15\\n\\finterrupted and said, “You’re talking about John Talley.” Id. at 0:12-0:14. Mr.\\n\\nCarter then added, “Yeah, however that was constructed, I have no idea. But I was a\\n\\nbig part of that . . . a lot of athletes.” Id. at 0:18-0:28. Mr. Dohrmann asked if there\\n\\nwas “one funny job” that Mr. Carter remembered. Id. at 0:30-0:34. The conversation\\n\\nproceeded as follows:\\n\\n Mr. Carter: There wasn’t a job!\\n\\n Mr. Dohrmann: Yeah but I mean, what was the job on\\n paper . . . ?\\n\\n Mr. Carter: Uh, well there was no paper for one.\\n\\n Mr. Dohrmann: Well, you know what I mean. In theory,\\n you were supposed to—\\n\\n Mr. Carter: It would be, um, like one funny one was out to\\n his ranch, I’m putting the horseshoes on the horses.\\n\\n Mr. Dohrmann: But you don’t actually, no way you guys,\\n you guys never got on a horse in your life.\\n\\n Mr. Carter: [Laughing] Yeah. . . . Yeah that was a quick\\n buck, cash.\\n\\n ....\\n\\n Mr. Dohrmann: How did guys view it? Did they view it\\n like, “We earned this, like, this is only fair? Doin’ what\\n we’re doin’.”\\n\\n Mr. Carter: It was fair, but we viewed it as, “I’m gonna\\n get paid.” You know, “Let me do some work for John\\n Talley so I can go out and buy some shoes.”\\n\\nId. at 0:34-2:24; see also Aplt. App., Vol. II A323-24, A484.\\n\\n\\n\\n 16\\n\\f Mr. Dohrmann later called Mr. Carter to verify his statements about shoeing\\n\\nhorses. At his deposition, Mr. Dohrmann testified that during this phone call, Mr.\\n\\nCarter again said “something about shoeing horses and [that he had] never seen a\\n\\nhorse before” and that “[h]e didn’t do the work but he was paid.” Aplt. App., Vol. II\\n\\nat A325-27.\\n\\n iii. Mr. Schecter’s interview with Mr. Talley\\n\\n On September 3, 2013, Mr. Schecter had a brief conversation with Mr. Talley\\n\\noutside the OSU basketball arena.10 Id. at A404. Mr. Schecter informed Mr. Talley\\n\\nof the allegations against him. Aplt. App., Vol. III at A718. He also asked about\\n\\nspeaking arrangements and whether Mr. Talley had overpaid players for work. Id.;\\n\\nAplt. App., Vol. II at A443. Mr. Talley confirmed he had hired and paid OSU\\n\\nplayers to work on his property but insisted he had cleared the employment\\n\\narrangements with OSU’s compliance office. Aplt. App., Vol. I at A168; Aplt. App.,\\n\\nVol. II at A417. Mr. Schecter recorded the conversation on his cell phone, Aplt.\\n\\nApp., Vol. II at A409, and summarized the interview in an e-mail that he sent to Mr.\\n\\nEvans and Mr. Dohrmann. See id. at A443, A520-23.11 He also gave Mr. Talley his\\n\\n\\n 10\\n Mr. Talley stated Mr. Schecter was “in a hurry to get out of [the car],” Aplt.\\nApp., Vol. I at A204, and that the whole interview lasted about five minutes, Aplt.\\nApp., Vol. III at A680. Mr. Schecter said the interview lasted about 15 to 20\\nminutes. Aplt. App., Vol. II at A443.\\n 11\\n Mr. Talley claimed in his deposition that Mr. Schecter arranged a second\\nmeeting with him and OSU’s general counsel on Friday of the same week but\\ncancelled the meeting because “he had enough information.” Aplt. App., Vol. III at\\n 17\\n\\fcontact information and invited him to reach out with any questions. Id. at A424,\\n\\nA443.\\n\\n On September 6, 2013, Mr. Schecter sent Mr. Talley an e-mail that read, “Aso\\n\\nPogi told us that he . . . lived on your range [sic] rent-free for one summer. Is that\\n\\ntrue?” Id. at A515; see also id. at A425. Mr. Talley responded, “No, there was an\\n\\nexpectation of work for [Mr. Pogi’s] room and board that was done.” Id. at A514.\\n\\nMr. Schecter then asked if Mr. Talley “report[ed] this arrangement to Oklahoma\\n\\nState,” and Mr. Talley responded, “[Y]es, to athletic compliance.” Id.; see also id. at\\n\\nA425.\\n\\n b. Meetings with OSU officials\\n\\n On September 3, 2013, Mr. Schecter and Mr. Dohrmann met with OSU\\n\\nAthletic Director Mike Holder, Associate Athletic Director for Compliance Kevin\\n\\nFite, and General Counsel Gary Clark to “solicit their comment.” Aplt. App., Vol. II\\n\\nat A439; see also id. at A443; Aplt. App., Vol. III at A766. This meeting was not\\n\\nrecorded, but both Mr. Schecter and Mr. Dohrmann testified at their depositions that\\n\\nthey spent several hours “present[ing] the substance of the information [they] had\\n\\nlearned in [their] investigation about the role money, drugs, women, and academics\\n\\nplayed in the OSU football program.” Aplt. App., Vol. II at A439; see also id. at\\n\\n\\n\\n\\nA719. Mr. Schecter “categorically den[ied]” this claim during his deposition. Aplt.\\nApp., Vol. II at A431-32.\\n 18\\n\\fA443. In his affidavit, Mr. Schecter said “this meeting was ‘off the record’”—“the\\n\\nofficials did not give us any comments for publication.” Id. at A443.\\n\\n On September 4, 2013, Mr. Schecter and Mr. Dohrmann held a second meeting\\n\\nwith the same OSU officials. This time, they recorded the meeting. See Dist. Ct.\\n\\nDoc. 60, Ex. 28 (OSU Officials Interview); see also Aplt. App., Vol. II at A439,\\n\\nA443. They asked the OSU officials to verify Mr. Talley’s claim that he had\\n\\nreceived clearance to pay students for speaking engagements.12 Mr. Fite said the\\n\\nspeaking engagements “were not cleared through our office as paid speaking\\n\\nengagements.” OSU Officials Interview at 1:02-1:07. He added, “In fact, two of my\\n\\nstaff members indicated to me this morning that they had had conversations with [Mr.\\n\\nTalley] and had told him, ‘You cannot pay for speaking engagements. If you wanna\\n\\nemploy our student athletes for other things, that is fine, but you cannot pay them for\\n\\nspeaking engagements.’” Id. at 1:07-1:25.\\n\\n c. Writing and editing\\n\\n In spring 2013, the SI reporters determined they had gathered enough\\n\\ninformation to begin drafting the article. Aplt. App., Vol. II at A438. Mr. Dohrmann\\n\\nassumed primary writing duties. As he wrote, he reviewed Mr. Evans’s notes and\\n\\n\\n 12\\n In the interview recording, Mr. Schecter said, “One thing [Mr. Talley] did\\nsay was that, whether it was routinely or regularly, but certainly plenty of times, that\\nhe did, indeed, set up speaking engagements for football players, and that on\\nnumerous occasions that they were paid for those speaking engagements. He said it\\ncoulda been 50 dollars, it coulda been 100 dollars, or whatever, but that was cleared\\nthrough your office.” OSU Officials Interview at 0:09-0:42.\\n 19\\n\\flistened to audio recordings of the interviews. Id. at A439. He also identified\\n\\n“places where [the reporters] needed more information, or the name of a source, or\\n\\nspecific details about what a former player had said about his experience.” Id. Mr.\\n\\nDohrmann sent drafts of the article to editors and to Mr. Evans, who reviewed the\\n\\nwork as it was written. Id. at A390. He also spoke frequently with Mr. Evans and\\n\\nMr. Schecter to ensure “[they] had sufficient substantiation for what SI was\\n\\nreporting.” Id.\\n\\n Mr. Dohrmann’s drafts underwent SI’s standard editing and review process,\\n\\nwhich Mr. Schecter described as follows:\\n\\n Well . . . it starts off with a draft of the story being filed.\\n That story is then edited, fact-checked, vetted by our legal\\n team, copy-edited, read one more time by the writers and\\n editors involved in the . . . story, and then finally, it goes to\\n press.\\n\\nId. at A400. As part of this revision process, other SI editors “[made] notes in\\n\\nthe drafts to suggest word changes for clarity or flow, or ask[ed] questions\\n\\nabout what the sources said about the facts.” Id. at A439. In addition, SI fact\\n\\ncheckers reviewed each draft and “would confirm specific facts, such as the\\n\\nspelling of a name, the dates when players attended OSU, the name of the high\\n\\nschool from which a player was recruited, and so on.” Id.\\n\\n Mr. Schecter also performed an editing role, which involved “making\\n\\nsure . . . the story [was] clear and concise . . . and . . . mak[ing] sure that things\\n\\ntrack”—that is, “if you say something, it’s supported by something else, and\\n\\n 20\\n\\fthat the piece is fair and balanced.” Id. at A399. He repeatedly listened to the\\n\\nrecording of his conversation with Mr. Talley to “confirm the accuracy of the\\n\\nquotes that [the Defendants] were using . . . and make sure that [they] gave\\n\\n[Mr. Talley] every attempt to deny the allegations that [they] made against\\n\\nhim.” Id. at A415-16.\\n\\n d. Pre-publication legal and editorial review and publication\\n\\n SI completed edits and revisions just days after the September 4 meeting with\\n\\nthe OSU officials. Id. at A444. Time’s in-house counsel reviewed the final draft, id.,\\n\\nand Chris Stone, SI’s Managing Editor, approved it, id. at A439, A444. SI published\\n\\nthe first article online on September 10, 2013, and released the remaining four\\n\\narticles online between September 11 and September 17, 2013. Aplt. App., Vol. III\\n\\nat A700-A701. It also printed the first article in its September 16, 2013 print issue\\n\\nand included the final article in its September 23, 2013 print issue.13 Id.\\n\\n Individual Defendants’ Depositions and Affidavits\\n\\n After Mr. Talley filed his lawsuit, the reporters and editor responsible for “The\\n\\nDirty Game” all stated they believed the series was truthful and substantiated. In his\\n\\ndeposition, Mr. Evans said, “I believe that we published accurate information about\\n\\nthe allegations that players had made about Mr. Talley.” Aplt. App., Vol. II at A379.\\n\\n\\n\\n\\n 13\\n SI published the second, third, and fourth articles only online.\\n\\n\\n 21\\n\\fAnd in his affidavit, Mr. Evans said he “was completely satisfied that what we were\\n\\nreporting was truthful based on the information we had gotten from the dozens of on-\\n\\nthe-record sources.” Id. at A390. As to the passages on Mr. Talley, he stated:\\n\\n [T]hose sources—players who had been at OSU at\\n different times and who were interviewed independently—\\n corroborated one another. By talking with them personally\\n I was able to assess their credibility, and I did not sense\\n any bias toward [Mr.] Talley or other reasons that would\\n make me doubt the accuracy of what they were telling me\\n about him or what we reported in the article. I remain\\n completely satisfied in this regard today.\\n\\nId. at A390-91.\\n\\n In his deposition, Mr. Dohrmann said “[i]t’s very difficult to get players to\\n\\n[admit to NCAA violations]” and that “[f]ive players is a significant number [of\\n\\nsources] with a story like this.” Id. at A337. He had “done a lot of stories like this”\\n\\nand had “done stories with far less than five [sources].” Id. Because “a number of\\n\\nsources . . . told [the reporters] a similar or same story about Oklahoma State and\\n\\nJohn Talley,” he felt “absolutely certain about what we were writing.” Id. at A342.\\n\\nMr. Dohrmann also stated in his affidavit that he “had heavily researched the article\\n\\nand reviewed all the sources,” “the facts [the interviewees] provided were consistent\\n\\nwith and corroborative of one another,” he “did not observe any signs of bias . . .\\n\\namong the sources or other facts that would cause [him] to question their credibility,”\\n\\nand he “did not doubt the accuracy of any statement in the article.” Id. at 439-40.\\n\\n At his deposition, Mr. Schecter said he believed the article “was very well\\n\\ndone” and “was all true.” Id. at A431. And in his affidavit, he stated, “I believed\\n 22\\n\\fwhen the article . . . was published it was accurate and truthful. I was satisfied that\\n\\nall the statements in the article about [Mr.] Talley were adequately substantiated by\\n\\nmultiple sources and were truthful. . . . My opinion has not changed despite [Mr.]\\n\\nTalley’s lawsuit.” Id. at A444.\\n\\n C. Procedural Background\\n\\n In July 2014, Mr. Talley filed his lawsuit in state court. Aplt. App., Vol. I at\\n\\nA11. He named Time, Inc., Mr. Dohrmann, and Mr. Evans as defendants, but he did\\n\\nnot sue Mr. Schecter. Invoking diversity jurisdiction under 28 U.S.C. § 1332, the\\n\\nDefendants removed the case to the United States District Court for the Western\\n\\nDistrict of Oklahoma.\\n\\n After the parties completed the discovery process, the Defendants moved for\\n\\nsummary judgment. They argued, among other things, that Mr. Talley was “unable\\n\\nto prove with competent evidence that at least one of the statements about which he\\n\\ncomplains satisfies all of the elements of a false light claim.” Id. at A107. Mr.\\n\\nTalley opposed the motion, claiming “disputed issues of material fact exist[ed]” with\\n\\nrespect to all three elements of his false light claim. Aplt. App., Vol. III at A694.\\n\\n The district court granted summary judgment for the Defendants, finding Mr.\\n\\nTalley could not demonstrate a genuine dispute of material fact regarding the first\\n\\n(falsity) or third (actual malice) elements of his false light claim. Talley v. Time, Inc.\\n\\nd/b/a Sports Illustrated Magazine, No. CIV-14-853-D, 2018 WL 4558993, at *5-6\\n\\n(W.D. Okla. Sept. 21, 2018).\\n\\n 23\\n\\f With respect to the third element—whether SI acted with actual malice—the\\n\\ncourt found “[Mr. Talley] present[ed] no facts or evidence to show that Defendants\\n\\nknew the allegations they reported about [him] were false.” Aplt. App., Vol. V at\\n\\nA1197. Although Mr. Talley argued Defendants “were pursuing an agenda” and\\n\\ncrafted “a sensational, unfavorable” narrative to get “the story they wanted,” the\\n\\ncourt found his allegations were “unsupported by any facts” and could not\\n\\n“reasonably be found to show either actual knowledge or a high degree of awareness\\n\\nby Defendants that the allegations about [Mr. Talley] . . . were probably false.” Id. at\\n\\nA1203. The court thus concluded Mr. Talley “present[ed] no facts or evidence that\\n\\nmight reasonably satisfy the rigorous standard required to establish ‘actual malice’ or\\n\\neven to demonstrate a genuine dispute of material fact in this regard.” Id.\\n\\n II. DISCUSSION\\n\\n The following discussion concludes that Mr. Talley has not shown that a\\n\\nreasonable jury could find that the Defendants acted with actual malice. Summary\\n\\njudgment was therefore appropriate.\\n\\n A. Legal Background\\n\\n This section describes (1) the standard of review for summary judgment, (2)\\n\\nthe elements of Oklahoma’s false light tort, and (3) the actual malice standard.\\n\\n Standard of Review\\n\\n As this court has recognized in defamation cases, “[we] review summary\\n\\njudgment decisions de novo, applying the same legal standard as the district court.”\\n\\n 24\\n\\fCory v. Allstate Ins., 583 F.3d 1240, 1243 (10th Cir. 2009) (quotations omitted).\\n\\n“The court shall grant summary judgment if the movant shows that there is no\\n\\ngenuine dispute as to any material fact and the movant is entitled to judgment as a\\n\\nmatter of law.” Fed. R. Civ. P. 56(a). “When applying this standard, we view the\\n\\nevidence and draw reasonable inferences therefrom in the light most favorable to the\\n\\nnonmoving party.” Cory, 583 F.3d at 1243 (quotations omitted).\\n\\n “[A] party seeking summary judgment always bears the initial responsibility of\\n\\n. . . demonstrat[ing] the absence of a genuine issue of material fact.” Celotex Corp.\\n\\nv. Catrett, 477 U.S. 317, 323 (1986); see also Savant Homes, Inc. v. Collins, 809\\n\\nF.3d 1133, 1137 (10th Cir. 2016). “A movant that does not bear the burden of\\n\\npersuasion at trial may satisfy this burden by pointing out to the court a lack of\\n\\nevidence on an essential element of the nonmovant’s claim.” Teets v. Great-West\\n\\nLife & Annuity Ins. Co., 919 F.3d. 1232, 1243 (10th Cir. 2019) (quotations omitted).\\n\\n “If the movant meets this initial burden, the burden then shifts to the\\n\\nnonmovant to set forth specific facts from which a rational trier of fact could find for\\n\\nthe nonmovant.” Id. (quotations omitted). “These facts must establish, at a\\n\\nminimum, an inference of the presence of each element essential to the case.” Savant\\n\\nHomes, 809 F.3d at 1137-38 (quotations omitted). The movant is entitled to\\n\\nsummary judgment if the nonmoving party cannot provide facts “to make a sufficient\\n\\nshowing on an essential element of her case with respect to which she has the burden\\n\\nof proof.” Id. at 1138 (quotations omitted).\\n\\n 25\\n\\f Both the Supreme Court and Oklahoma state courts have held that at trial, the\\n\\nplaintiff must prove actual malice with “convincing clarity.” New York Times, 376\\n\\nU.S. at 286-87; Colbert, 747 P.2d at 291. The Supreme Court has said courts “must\\n\\nbear in mind” this heightened burden of proof when ruling on a defendant’s motion\\n\\nfor summary judgment. Anderson v. Liberty Lobby, Inc., 477 U.S. 242, 254 (1986)\\n\\n(holding that courts must consider “the actual quantum and quality of proof necessary\\n\\nto support liability under New York Times” when considering summary judgment on\\n\\nthe actual malice issue). “[I]f the evidence presented in the opposing affidavits is of\\n\\ninsufficient caliber or quantity to allow a rational finder of fact to find actual malice\\n\\nby clear and convincing evidence,” then “there is no genuine issue” and summary\\n\\njudgment is appropriate. Spacecon Specialty Contractors, LLC v. Bensinger, 713\\n\\nF.3d 1028, 1048 n.13 (10th Cir. 2013) (quotations omitted).14\\n\\n Oklahoma’s False Light Tort\\n\\n As discussed above, Oklahoma recognizes the common law tort of false light\\n\\ninvasion of privacy. The plaintiff must show:\\n\\n (1) “the defendant gave publicity to a matter concerning\\n the plaintiff that placed the plaintiff before the public in a\\n false light,”\\n\\n\\n\\n 14\\n Spacecon involved a defamation claim brought under Colorado law, which\\nrequired the plaintiff to demonstrate actual malice by clear and convincing evidence.\\n713 F.3d at 1041.\\n\\n\\n\\n 26\\n\\f (2) “the false light in which the plaintiff was placed would\\n be highly offensive to a reasonable person,”\\n\\n (3) “the defendant had knowledge of or acted in reckless\\n disregard as to the falsity of the publicized matter and the\\n false light in which the other would be placed.”\\n\\nMitchell, 60 P.3d at 1061 (citing McCormack, 613 P.2d at 740); see also Restatement\\n\\n(Second) of Torts § 652E (Am. Law Inst. 1977).\\n\\n “[E]ssential to . . . a false light privacy claim . . . is a determination that that\\n\\nthe matter published concerning the plaintiff is not true.” Rinsley v. Brandt, 700 F.2d\\n\\n1304, 1307 (10th Cir. 1983) (quotations omitted).15 Thus, to establish the first\\n\\nelement of a false light claim, a plaintiff must show the defendant made a statement\\n\\nthat “portrayed [plaintiff] in [a] false manner or that statements were untrue or\\n\\nmisleading.” McCormack, 613 P.2d at 741 (holding that plaintiff failed to state a\\n\\ncause of action for false light invasion of privacy because plaintiff did not allege that\\n\\nthe published statements were false or misleading). True statements are not\\n\\nactionable under Oklahoma’s false light tort.\\n\\n To satisfy the second element, the plaintiff must show “a reasonable [person]\\n\\nwould be justified in the eyes of the community in feeling seriously offended and\\n\\naggrieved by the publicity.” Restatement (Second) of Torts §652E, cmt. c. Put\\n\\ndifferently, “[i]t is only when there is such a major misrepresentation of [the\\n\\n\\n 15\\n Rinsley involved a false light invasion of privacy claim brought under\\nKansas law. Like Oklahoma, Kansas has adopted the false light invasion of privacy\\naction set forth in Restatement (Second) of Torts § 652E. See Rinsley, 700 F.2d at\\n1307.\\n 27\\n\\fplaintiff’s] character, history, activities or beliefs that serious offense may reasonably\\n\\nbe expected to be taken by a reasonable man in his position, that there is a cause of\\n\\naction for invasion of privacy.” Id.\\n\\n The third element—knowledge of or reckless disregard as to falsity—is\\n\\nidentical to the actual malice standard from New York Times Co. v. Sullivan. See\\n\\nColbert, 747 P.2d at 290-92 (noting that Oklahoma has “adopted” the actual malice\\n\\ntest from Time, Inc. v. Hill, 385 U.S. 374 (1967), which applied the New York Times\\n\\nactual malice standard in a false light invasion of privacy case); Grogan v. Kokh,\\n\\nLLC, 256 P.3d 1021, 1030 (Okla. Civ. App. 2011) (noting that “the Oklahoma\\n\\nSupreme Court has adopted the [New York Times] actual malice test for false light\\n\\ninvasion of privacy claims”).16 Thus, to establish the third element of a false light\\n\\nclaim, a plaintiff must show the defendant made or published its statements “with\\n\\n‘actual malice’—that is, with knowledge that [they were] false or with reckless\\n\\ndisregard to whether [they were] false or not.” New York Times, 376 U.S. at 280.\\n\\nWe next discuss the Supreme Court cases that have articulated and developed this\\n\\nstandard.\\n\\n\\n\\n\\n 16\\n Although the Supreme Court has applied the actual malice standard in at\\nleast one false light invasion of privacy case, see Time, Inc., 385 U.S. 374, the\\nstandard originated in New York Times, which was a defamation case. As a result,\\nOklahoma courts analyzing the third element of a false light tort claim routinely look\\nto and rely on both defamation and false light case law. See, e.g., Grogan, 256 P.3d\\nat 1031 (“analogizing to defamation law” where there is no clear false light case law\\non point).\\n 28\\n\\f Actual Malice\\n\\n a. New York Times and its progeny\\n\\n In New York Times v. Sullivan, the Supreme Court said that a publication “was\\n\\nmade with ‘actual malice’” when the defendant published “with knowledge that it was\\n\\nfalse or with reckless disregard of whether it was false or not.” 376 U.S. at 279-80; see\\n\\nGertz v. Robert Welch, Inc., 418 U.S. 323, 343 (1974). The plaintiff’s burden of proving\\n\\nactual malice cannot be met by a preponderance of the evidence. Actual malice must be\\n\\nshown with “convincing clarity,” New York Times, 376 U.S. at 285-86—that is, by “clear\\n\\nand convincing proof,” Gertz, 418 U.S. at 342.\\n\\n Actual malice is not a negligence or gross negligence standard. See Garrison v.\\n\\nLouisiana, 379 U.S. 64, 79 (1964); Hardin v. Santa Fe Reporter, Inc., 745 F.2d 1323,\\n\\n1326 (10th Cir. 1984) (holding that reporter’s negligence in failing to investigate a\\n\\nsource’s background and in writing the article could not establish actual malice). It\\n\\nrequires more than showing a publication was false and defamatory, New York Times,\\n\\n376 U.S. at 288, and more than “a departure from reasonably prudent conduct,” Harte-\\n\\nHanks Commc’ns, Inc. v. Connaughton, 491 U.S. 657, 688 (1989).\\n\\n Actual malice is a subjective standard that requires proof of a “mental element.”\\n\\nMonitor Patriot Co. v. Roy, 401 U.S. 265, 276 (1971); see Harte-Hanks, 491 U.S. at 688\\n\\n(stating actual malice is a subjective standard). The actual malice inquiry thus “rests\\n\\nentirely on an evaluation of [the publisher’s] state of mind when he wrote his initial\\n\\n\\n\\n 29\\n\\freport, or when he checked the article against that report.” Bose Corp. v. Consumers\\n\\nUnion of U.S., Inc., 466 U.S. 485, 494 (1984).\\n\\n In St. Amant v. Thompson, 390 U.S. 727 (1968), the Supreme Court explained:\\n\\n [R]eckless conduct is not measured by whether a reasonably\\n prudent man would have published, or would have\\n investigated before publishing. There must be sufficient\\n evidence to permit the conclusion that the defendant in fact\\n entertained serious doubts as to the truth of his publication.\\n Publishing with such doubts shows reckless disregard for\\n truth or falsity and demonstrates actual malice.\\n\\nId. at 731.\\n\\n A plaintiff does not create a jury question of actual malice by showing that a\\n\\npublisher failed to investigate before publishing. Gertz, 418 U.S. at 332; St. Amant,\\n\\n390 U.S. at 731; Beckley Newspapers Corp. v. Hanks, 389 U.S. 81, 84-85 (1967) (per\\n\\ncuriam)17; New York Times, 376 U.S. at 28718; Revell v. Hoffman, 309 F.3d 1228,\\n\\n1233 (10th Cir. 2002). Nor does a plaintiff do so by showing that a publisher\\n\\nmisinterpreted the source material or omitted details favorable to the plaintiff. Time,\\n\\nInc. v. Pape, 401 U.S. at 282, 290-92 (1971). A publisher’s decision to omit details\\n\\n\\n\\n 17\\n In Beckley, for example, the Supreme Court, having reviewed testimony\\nfrom the newspaper’s general manager that no investigation of the allegedly\\ndefamatory statements had been made, held, “[I]t cannot be said on this record that\\nany failure of petitioner to make a prior investigation constituted proof sufficient to\\npresent a jury question whether the statements were published with reckless disregard\\nor whether they were false or not.” 389 U.S. at 84-85.\\n 18\\n In New York Times, the Court found the evidence insufficient to establish\\nactual malice even though checking news stories in the Time’s own files would have\\nrevealed the falsity of a part of the challenged publication. 376 U.S. at 287-88.\\n 30\\n\\ffavorable to the plaintiff does not, itself, show actual malice. See id. (finding no\\n\\nactual malice where a publisher did not specify that “it was reporting no more than\\n\\nallegations”). Even “a deliberate alteration of the words uttered by a plaintiff does\\n\\nnot equate with [actual malice] . . . unless the alteration results in a material change\\n\\nin the meaning conveyed by the statement.” Masson v. New Yorker Magazine, Inc.,\\n\\n501 U.S. 496, 517 (1991).\\n\\n Actual malice may be found when a publisher had a “subjective awareness of\\n\\nprobable falsity.” Gertz, 418 U.S. at 334 n.6. For example, evidence that a publisher\\n\\nknew its sources were unreliable but made no attempt to verify their information,\\n\\nCurtis Publ’g Co. v. Butts, 388 U.S. 130, 157-59 (1967), or that a publisher knew it\\n\\nwas publishing contested allegations but deliberately ignored sources or information\\n\\nthat might reveal what actually happened, Harte-Hanks, 491 U.S. at 690, may\\n\\nestablish actual malice. Other examples include “a story [that] is fabricated by the\\n\\ndefendant, is the product of his imagination, or is based wholly on an unverified\\n\\nanonymous telephone call”; circumstances where the published statements “are so\\n\\ninherently improbable that only a reckless man would have put them in circulation”;\\n\\nor situations “where there are obvious reasons to doubt the veracity of the informant\\n\\nor the accuracy of his reports.” St. Amant, 390 U.S. at 732.\\n\\n Most of the Supreme Court’s actual malice case law, including New York\\n\\nTimes, comes from defamation suits. But the Supreme Court has, like Oklahoma,\\n\\napplied the actual malice standard to a false light claim. In Time, Inc. v. Hill, 385\\n\\n 31\\n\\fU.S. 374 (1967), the Court held that “the constitutional protections for speech and\\n\\npress preclude[d] the application of [a] New York [false light invasion of privacy]\\n\\nstatute . . . in the absence of proof that the defendant published the report with\\n\\nknowledge of its falsity or in reckless disregard of the truth.” Id. at 387-88.\\n\\n b. Oklahoma actual malice cases\\n\\n Because Oklahoma courts have expressly adopted the New York Times actual\\n\\nmalice standard, Oklahoma’s defamation and false light case law is consistent with\\n\\nthe actual malice principles described above.19 Like the Supreme Court, Oklahoma\\n\\n\\n 19\\n In Dun & Bradstreet, Inc. v. Greenmoss Builders, Inc., 472 U.S. 749, 758-61\\n(1985), the Supreme Court held that the First Amendment requires proof of actual malice\\nonly when the statements at issue involve matters of public concern. In recognizing the\\nfalse light invasion of privacy tort and equating the third element of that tort to the New\\nYork Times actual malice standard, Oklahoma courts have not drawn a distinction\\nbetween false light claims for statements involving matters of public concern as opposed\\nto private concern. We need not address whether Oklahoma courts would draw any such\\ndistinction, because Mr. Talley has not argued that the statements at issue here involve\\nmatters of private concern or that the actual malice standard should not apply in this case.\\n Moreover, the form, content, and context of the SI publication establish that the\\nstatements at issue here involve a matter of public concern. See id. at 761 (explaining\\nthat when determining whether allegedly libelous statements involve a matter of public\\nconcern, courts should consider the form, content, and context of the speech). The\\nstatements were printed in a widely-circulated publication. Compare Spacecon, 713 F.3d\\nat 1039 (holding that “a documentary meant to be shown to the public” qualified as\\nspeech on a matter of public concern), with Dun & Bradstreet, 472 U.S. at 762 (holding\\nthat a credit report “made available only to five subscribers” was not speech on a matter\\nof public concern).\\n More telling, they involved allegations against the football program at one of\\nOklahoma’s major publicly-funded universities. See City of San Diego v. Roe, 543 U.S.\\n77, 83-84 (2004) (“[P]ublic concern is something that is a subject of legitimate news\\ninterest; that is, a subject of general interest and of value and concern to the public . . . .”);\\nSpacecon, 713 F.3d at 1039 (holding that a documentary film exposing mistreatment of\\nMexican construction workers involved speech on a matter of public concern); Dun &\\n 32\\n\\fcourts have recognized that actual malice exists when “the defendant had a high\\n\\ndegree of awareness of probable falsity or in fact entertained serious doubts as to the\\n\\ntruth of the publication.” Colbert, 747 P.2d at 291. They also have noted that\\n\\n“negligence is not enough to rise to the level of ‘actual malice’” and that “malice\\n\\nmay not be inferred simply from showing that the publication was untrue.” Herbert,\\n\\n992 P.2d at 328. As in New York Times, St. Amant, and other Supreme Court cases,\\n\\nOklahoma courts have stated that “failure to investigate does not establish the actual\\n\\nmalice standard.” Jurkowski v. Crawley, 637 P.2d 56, 61 (Okla. 1981). They also\\n\\nhave followed the Supreme Court in treating the actual malice standard as a\\n\\nsubjective inquiry and have stated that actual malice exists only when there is\\n\\n“sufficient evidence to permit the conclusion that the defendant in fact entertained\\n\\nserious doubts as to the truth of his publication.” Washington v. World Publ’g. Co.,\\n\\n506 P.2d 913, 918 (Okla. 1972) (quotations omitted).20\\n\\n\\n\\nBradstreet, 472 U.S. at 762 (holding that credit report was not speech on a matter of\\npublic concern because it was “solely in the individual interest of the speaker and its\\nspecific business audience”). Thus, even if Oklahoma courts would distinguish between\\nspeech on matters of public and private concern, the actual malice standard applies in this\\ncase.\\n 20\\n In New York Times, 376 U.S. 254, and Curtis Publishing Co. v. Butts, 388 U.S.\\n130, the Supreme Court held that the actual malice requirement applies when the\\nallegedly defamatory speech is about a public figure or public official. In Gertz, the\\nCourt held that the actual malice standard applies to public figures but does not apply in\\ncases brought by private-figure plaintiffs. 418 U.S. at 345-48.\\n In 1967, the Supreme Court said in Hill that the New York Times actual malice\\nstandard also applies to false light cases. See supra note 16. It is not clear whether the\\n1974 Gertz holding—which restricts the actual malice standard to cases brought by\\n 33\\n\\f B. Analysis\\n\\n Although the parties have briefed both the first and third false light elements,\\n\\nMr. Talley’s failure to establish either element will defeat his claim. We can resolve\\n\\nthis appeal by addressing only the third element—actual malice.\\n\\n Evidence on Preparation of the Article Lacks Proof of Actual Malice\\n\\n The record shows the Defendants conducted a long and thorough investigation\\n\\nbefore publishing their article. For ten months, the reporters sought out and spoke to\\n\\ndozens of OSU players, coaches, and administrators. They recorded their interviews\\n\\nelectronically and in writing. They consulted their notes and each other while\\n\\ndrafting the article, and they occasionally re-interviewed individuals to ensure that\\n\\n\\n\\n\\npublic officials and public figures—similarly limits the standard’s application in false\\nlight cases. As one leading commentator has noted, “[a] significant number of cases have\\nheld that Hill should be regarded as modified by Gertz, and that actual malice is not\\nrequired . . . in false light cases with private figure plaintiffs.” 2 Rodney A. Smolla, Law\\nof Defamation § 10:16 (2d ed. Nov. 2018 update). But “there is also . . . substantial\\nauthority, including the Restatement Second, Torts, for the proposition that all false light\\nclaims must meet the actual malice standard.” Id. Gertz thus leaves open the question of\\nwhether actual malice is required in all false light cases, or only in cases involving\\nstatements about public officials or public figures. See Restatement (Second) of Torts\\n§652E, cmt. d.\\n We need not address this question for two reasons. First, Mr. Talley has not\\nargued that he is a private figure. Second, Oklahoma courts have applied the actual\\nmalice standard in false light cases involving both public- and private-figure plaintiffs.\\nSee Colbert, 747 P.2d at 288, 291 (Okla. 1987) (applying the actual malice standard\\nin a false light case involving a plaintiff who was “unquestionably a private figure”);\\nGrogan, 256 P.3d at 1029 (holding that the actual malice standard is “required for false\\nlight invasion of privacy cases involving public figures”).\\n 34\\n\\ftheir information was correct. They also fact-checked and edited their article several\\n\\ntimes and had their legal team review the piece before publication.\\n\\n Unlike the publishers in Harte-Hanks, the Defendants did not deliberately\\n\\nignore sources that might have disputed their account. See 491 U.S. at 690. Rather,\\n\\nthey interviewed multiple sources around the country who substantially corroborated\\n\\neach other. They also verified the information they published by re-interviewing\\n\\ntheir sources and fact-checking the final piece. Mr. Talley has provided no evidence\\n\\nthat the Defendants “fabricated” their story, based their claims about him on “an\\n\\nunverified anonymous telephone call,” or published allegations that were “so\\n\\ninherently improbable that only a reckless man would have put them into\\n\\ncirculation.” St. Amant, 390 U.S. at 732. He thus “proffers no evidence indicating\\n\\nthat [the Defendants] entertained doubts regarding the truth of the statements in [the\\n\\npublication].” Revell, 309 F.3d at 1233.\\n\\n In addition, the record shows that the reporters had ample evidence to support\\n\\nthe statements in the article about Mr. Talley. Mr. Pogi and Mr. Talley told the\\n\\nreporters that Mr. Pogi lived on Mr. Talley’s ranch without paying rent; four players\\n\\n(Mr. Shaw, Mr. Mack, Mr. Brown, and Mr. Johnson) said Mr. Talley paid them or\\n\\nothers they knew for speaking engagements; and three (Mr. Girtman, Mr. Carter, and\\n\\nMr. Johnson) said Mr. Talley overpaid them for work. At least two of these sources\\n\\n(Mr. Mack and Mr. Carter) brought up Mr. Talley’s name without prompting. And,\\n\\nas we show below, Mr. Pogi made statements in his interview that the Defendants\\n\\n 35\\n\\fcould reasonably have interpreted to mean he did not work at Mr. Talley’s ranch.\\n\\nFurther, the players were interviewed independently of one another in different parts\\n\\nof the country and provided consistent accounts.\\n\\n In sum, the evidence shows the Defendants’ article was based on an extended\\n\\nresearch process and was not the product of deliberate “falsification,” Pape, 401 U.S.\\n\\nat 289, or the “use of calculated falsehood,” Garrison, 379 U.S. at 75. There is no\\n\\nindication they published with “a high degree of awareness of probable falsity or . . .\\n\\nentertained [any] serious doubts as to the truth of the publication.” Colbert, 747 P.2d\\n\\nat 291. Ample evidence supported their reporting about Mr. Talley, who cannot\\n\\nshow with “convincing clarity” that the Defendants acted with actual malice. Id.\\n\\n Mr. Talley’s Arguments\\n\\n Mr. Talley argues the Defendants exhibited actual malice by (a) deliberately\\n\\nmisstating facts about Mr. Pogi’s rent arrangement, (b) falsely reporting that Mr.\\n\\nTalley paid players for speaking engagements, (c) relying on biased and non-credible\\n\\nsources, (d) writing with a slanted agenda, and (e) publishing erroneous and incorrect\\n\\nstatements. These arguments do not withstand scrutiny.\\n\\n a. Mr. Pogi’s rent\\n\\n Mr. Talley argues the Defendants published with actual malice by\\n\\n“inaccurately reporting” that Mr. Pogi lived on Mr. Talley’s property rent-free. Aplt.\\n\\nBr. at 15. The Defendants reported in the article that “[Mr.] Pogi denies that he did\\n\\nany work.” Aplt. App., Vol. II at A452. According to Mr. Talley, however, “the\\n\\n 36\\n\\finterview recording [between Mr. Evans and Mr. Pogi] clearly states Aso Pogi\\n\\nworked extremely hard in exchange for rent.” Aplt. Reply Br. at 5; see also Aplt. Br.\\n\\nat 6, 16. As a result, Mr. Talley characterizes this allegation in the article as\\n\\n“blatantly false” and “misconstrued,” Aplt. Br. at 16-17, and he suggests the\\n\\nDefendants’ failure to “accurately report what the interviewees stated” is evidence of\\n\\nactual malice, id. at 20.\\n\\n This argument is unavailing. The article states:\\n\\n Quarterback Aso Pogi (1999 to 2002) says he and another\\n player lived at Talley’s ranch one summer rent-free. In\\n retrospect Pogi says, “It’s a big deal. I was the starting\\n quarterback.” (Talley says that Pogi lived at his ranch and\\n had to work to cover his rent; Pogi denies that he did any\\n work.).\\n\\nAplt. App., Vol. II at A452. The interview recording does not show this passage\\n\\n“obviously misquote[s] [or] inaccurately report[s] what [Mr.] Pogi stated.” Aplt.\\n\\nReply Br. at 5. Further, it does not suggest the Defendants published with “a high\\n\\ndegree of awareness of . . . probable falsity.” Garrison, 379 U.S. at 74.\\n\\n In the interview recording, Mr. Pogi said he lived on Mr. Talley’s property\\n\\nrent-free. Pogi Interview at 17:32-18:13. He also stated, as the Defendants reported,\\n\\n“It’s a big deal. I mean, I was the starting quarterback.” Id. at 23:20-25. Nowhere\\n\\nin the interview does Mr. Pogi state that he worked “extremely hard in exchange for\\n\\nrent,” as Mr. Talley insists. Aplt. Reply Br. at 5.\\n\\n\\n\\n\\n 37\\n\\f After reviewing the entire recording of Mr. Evans’s interview with Mr. Pogi,\\n\\nwe found only one statement—“I did a lot,” Pogi Interview at 12:02-12:04—that\\n\\ncould possibly indicate that Mr. Pogi worked on the ranch at all. But that statement\\n\\nis ambiguous. Mr. Pogi did not specifically state what it was he “did a lot.” Further,\\n\\nhe made the statement after telling Mr. Evans that he was “on the road a lot to speak”\\n\\nand had participated in “a lot” of speaking engagements. Id. at 10:00-11:51. It is\\n\\ntherefore possible the statement referenced his speaking engagements rather than\\n\\nranch work. Further, when Mr. Evans prompted, “You lived [on the ranch], but you\\n\\nnever, you never worked—,” Mr. Pogi responded, “I ne—I didn’t, I didn’t do\\n\\nanything like—.” Id. at 12:08-12:11. And a few questions later, Mr. Pogi insisted he\\n\\n“had no arrangement” with Mr. Talley. Id. at 17:29-17:30.\\n\\n The interview recording thus includes no definitive statement that Mr. Pogi\\n\\nworked on the ranch. Although his statement that he “did a lot” might be understood\\n\\nto mean he worked, it could reasonably be interpreted as a reference to speaking\\n\\nengagements. At most, the Defendants misinterpreted the statement, but a\\n\\ndefendant’s misinterpretation of source material that “bristle[s] with ambiguities”\\n\\ndoes not constitute actual malice. Pape, 401 U.S. at 290 (holding that when faced\\n\\nwith ambiguous source material, a defendant’s “deliberate choice of [one]\\n\\n\\n\\n\\n 38\\n\\finterpretation, though arguably reflecting a misconception, [is] not enough to create a\\n\\njury issue of ‘malice’ under New York Times”).21\\n\\n Accordingly, even if the Defendants misinterpreted Mr. Pogi’s statement that\\n\\nhe “did a lot,” their misunderstanding would not establish actual malice. The\\n\\nevidence does not support Mr. Talley’s contention that the Defendants “blatantly\\n\\nmisquoted what Aso Pogi said,” Aplt. Reply Br. at 5, or show they published\\n\\nstatements about Mr. Pogi with reckless disregard for the truth.22\\n\\n\\n 21\\n See also Orr v. Argus-Press Co., 586 F.2d 1108, 1116 (6th Cir. 1978)\\n(finding no actual malice when defendants published a rational interpretation of\\nambiguous source material); Simmons Ford, Inc. v. Consumers Union of U.S., Inc.,\\n516 F. Supp. 742, 751-52 (S.D.N.Y. 1981) (finding no actual malice when defendants\\npublished a reasonable but mistaken interpretation of a regulation that “hardly\\nqualify[ed] as a model of clarity”); Farrakhan v. N.Y.P. Holdings, Inc., 168 Misc. 2d\\n536, 542 (N.Y. Sup. Ct. 1995) (concluding that “even if defendants misinterpreted\\n[an interviewee’s] statement, such misinterpretation does not arise to a level of\\nconstitutional malice”); Suozzi v. Parente, 616 N.Y.S.2d 355, 359 (N.Y. App. Div.\\n1994) (noting that actual malice cannot “be founded on the misinterpretation of a\\nsource or the resolution of an ambiguity adversely to the plaintiff”).\\n 22\\n Mr. Talley’s insistence that the “Defendants blatantly misquoted what Aso\\nPogi said,” Aplt. Reply Br. at 5, may be based on an interview that Chuck Smrt,\\nOSU’s outside compliance consultant, conducted with Mr. Pogi during the NCAA’s\\ninvestigation of the OSU football program after the SI article series was published.\\nIn this interview, Mr. Pogi claimed he “worked pretty hard on [Mr. Talley’s] farm”\\nand that there was “a lost [sic] land to keep up as far as cutting grass, as far as\\ncleaning the pool and just doing quite a bit of things. Feeding the animals, it was\\nevery single day.” Aplt. App., Vol. IV at A853. These statements support Mr.\\nTalley’s contention that Mr. Pogi did, in fact, work in exchange for lodging. But\\nbecause this interview occurred after the SI article was published, it does not prove\\nthe Defendants deliberately misquoted Mr. Pogi—or otherwise acted with actual\\nmalice—at the time of the original publication. See Bose, 466 U.S. at 494 (noting\\nthat “the actual-malice determination rests entirely on an evaluation of [the author’s]\\nstate of mind when he wrote his initial report” (emphasis added)).\\n 39\\n\\f b. Payment for speaking engagements\\n\\n Mr. Talley also argues the Defendants acted with actual malice when they\\n\\nreported he paid players to speak at events “in violation of NCAA rules and OSU\\n\\npolicy.” Aplt. Br. at 16. According to Mr. Talley, “Defendants were made aware . . .\\n\\nthat ‘speaking’ meant reimbursement for gas and food” but nonetheless “deliberately\\n\\nchose to disregard its true meaning in order to portray [Mr. Talley] as paying in\\n\\nviolation of rules.” Id. at 18. Mr. Talley also argues that “Defendants never had\\n\\nreason to believe [Mr. Talley] was breaking the rules or illegally paying athletes.”23\\n\\nId.\\n\\n These arguments, too, are unpersuasive. Although some players insisted they\\n\\nwere reimbursed only for expenses, many (including Mr. Johnson, Mr. Brown, Mr.\\n\\nWright, and Mr. Shaw) admitted that they or others they knew had received speaking\\n\\n\\n\\n\\n 23\\n To support his argument, Mr. Talley adds that “Defendants knew [the]\\nNCAA investigated the subject and never determined any violation of the rules by\\n[Mr. Talley].” Aplt. Br. at 18. This argument is unpersuasive. The NCAA\\ninvestigated the OSU football program after the Defendants published “The Dirty\\nGame.” See, e.g., Aplt. App., Vol. III at A607 (transcript of NCAA investigatory\\ninterview with OSU officials, dated October 17, 2013). As noted above, the actual\\nmalice issue focuses on what the author knew (or did not know) at the time of\\npublication, Bose, 466 U.S. at 494, and “[e]vidence concerning events after an article\\nhas been printed and distributed, has little, if any, bearing on that issue,” Forbes Inc.\\nv. Granada Biosciences, Inc., 124 S.W.3d 167, 174 (Tex. 2003). If, as Mr. Talley\\nclaims, the NCAA found that his payments did not violate any rules, those findings\\nwere not available to the Defendants when they published the article and could not\\nhave influenced their state of mind at the time of publication. The NCAA\\ninvestigation is thus irrelevant.\\n\\n 40\\n\\ffees. Mr. Johnson, for example, said Mr. Talley once paid him 100 dollars to speak\\n\\nfor 20 minutes. Johnson Interview at 2:42-3:02. Even if Mr. Talley paid speaking\\n\\nfees to certain players and not others, the Defendants still had grounds to believe and\\n\\nreport that at least some players received money beyond simple reimbursement. That\\n\\nsome players denied receiving speaking fees or claimed they were only reimbursed\\n\\nfor expenses does not prove the Defendants “in fact entertained serious doubts” about\\n\\nthe players who reported otherwise. St. Amant, 390 U.S. at 731; Colbert, 747 P.2d\\n\\nat 291.\\n\\n In addition, Mr. Schecter’s notes from his interview with Mr. Talley reflect\\n\\nthat Mr. Talley admitted to paying speaking fees.24 Shortly after meeting with Mr.\\n\\nTalley, Mr. Schecter sent Mr. Dohrmann an e-mail listing “John Talley[’s] Responses\\n\\n\\n\\n\\n 24\\n Although Mr. Schecter recorded the interview with Mr. Talley, the audio file\\nwas corrupted. See supra note 6. Accordingly, Mr. Schecter’s e-mail to Mr. Dohrmann\\nis the only recorded source of information about the interview. In his affidavit, Mr.\\nSchecter stated that he drafted this e-mail shortly after speaking with Mr. Talley: “When\\nI got back to my hotel, I listened to the recording, then made notes, including writing\\ndown some direct quotes, as I re-listened to the audio. I emailed my notes to [Mr.]\\nDohrmann and [Mr.] Evans.” Aplt. App., Vol. II at A443. He also testified at his\\ndeposition that he listened to the interview recording “[i]mmediately after I got back to\\nmy hotel room . . . I would say within an hour after I finished my conversation with Mr.\\nTalley.” Id. at A411.\\n During his deposition, Mr. Talley claimed Mr. Schecter “was in a hurry” and\\n“didn’t really give [him] an opportunity to” explain himself fully during the interview.\\nAplt. App., Vol I at A204. But Mr. Talley did not challenge any of the information or\\nquotations contained in the e-mail. In fact, Mr. Talley reviewed the entire e-mail and\\nconfirmed he made all the statements that Mr. Schecter attributed to him. Id. at A202-05.\\n\\n 41\\n\\fto allegations we have against him.” Aplt. App., Vol. II at A520. On the topic of\\n\\n“[p]aying players for speaking engagements,” Mr. Schecter wrote the following:\\n\\n [Mr. Talley said:] “It depends on . . . there’s a\\n NCAA rule that if they’re paying us . . . and most of the\\n time it’s for team building activities. It’s not just\\n speaking. But we have done some school assemblies. Last\\n year we did four all sports banquets. And if the school is\\n used to paying someone than [sic] it’s legal to get paid.\\n But there’s a fine line.”\\n\\n Talley says he ran everything (the jobs and the\\n speaking gigs) through the associate compliance director\\n who is assigned to the football team.\\n\\n “If [players] were allowed to be paid (for speaking\\n engagements) they were paid. We’ve spoken in\\n churches.[”] (They got paid for speaking in churches\\n “only if the churches paid someone before.”) Talley says a\\n typical speaking fee would be $25-$50. “I can always pay\\n for if they’re driving their car we can pay for gas and stuff\\n like that.”\\n\\n Players said it was $100 or more per speaking\\n engagement. “It depends on where we were going,” Talley\\n said. “I’m not saying they couldn’t because it was a long\\n time ago, but usually it was not that much.”\\n\\nId. at A521. Although it is possible Mr. Schecter and Mr. Dohrmann misunderstood\\n\\nor misinterpreted Mr. Talley’s comments, these interview notes suggest the\\n\\nDefendants had a reasonable basis to believe Mr. Talley paid speaking fees to some\\n\\nplayers.25 Further, as discussed above, a defendant’s misinterpretation of source\\n\\n\\n 25\\n During his deposition, Mr. Talley acknowledged that his statements to Mr.\\nSchecter were ambiguous. When asked, “Do you find anything in [Mr.] Schecter’s\\nemail that would suggest you made [the] distinction [between speaking and team\\nbuilding] to him?,” Mr. Talley responded, “Yes and no. Yes, I was trying to. No, he\\n 42\\n\\fmaterial does not necessarily establish actual malice. Pape, 401 U.S. at 290. Thus,\\n\\neven if the Defendants misunderstood Mr. Talley’s claim that “[players] were paid”\\n\\nto mean speaking fees rather than reimbursements, that misunderstanding would not\\n\\nprove they published with actual malice.\\n\\n In sum, although some players claimed they did not receive money to speak,\\n\\nmultiple players reported that Mr. Talley arranged paid speaking engagements.\\n\\nFurther, notes from Mr. Schecter’s interview with Mr. Talley suggest that Mr. Talley\\n\\nadmitted to paying speaking fees. In publishing these allegations, the Defendants did\\n\\nnot show reckless disregard for the truth. Rather, they reported information that\\n\\nmultiple sources confirmed and corroborated. The record does not suggest the\\n\\nDefendants “in fact entertained serious doubts as to the truth of [their] publication,”\\n\\nSt. Amant, 390 U.S. at 731; Colbert, 747 P.2d at 291, and Mr. Talley identifies no\\n\\nevidence to demonstrate with “convincing clarity” that the Defendants reported about\\n\\nhis paying players for speaking engagements with actual malice, New York Times,\\n\\n376 U.S. at 286-87.\\n\\n c. Credibility of article sources\\n\\n Mr. Talley contends the Defendants demonstrated actual malice by “[seeking]\\n\\nout non-credible, untrustworthy, and troubled sources,” Aplt. Br. at 21, and by\\n\\n\\n\\nwas in a hurry to get out of my van. So he didn’t really give me an opportunity to.\\n. . . I was trying to clarify that I reimburse people for going to speak. . . . But he\\ndidn’t stay around long enough to hear it.” Aplt. App., Vol. I at A204.\\n\\n 43\\n\\finterviewing and quoting OSU players of “suspect veracity,” Aplt. Reply Br. at 8.\\n\\nHe notes that some of the players featured in the article had “troubled histor[ies] . . .\\n\\nincluding drug usage, scholastic problems with OSU, and criminal issues.” Aplt. Br.\\n\\nat 14. He claims the Defendants’ “conscious decision to feature those interviewees in\\n\\nthe article . . . is evidence of Defendants’ malicious intent.” Aplt. Reply Br. at 8.\\n\\nWe disagree.\\n\\n Although the record shows the Defendants interviewed and quoted some OSU\\n\\nplayers who used drugs or had criminal records,26 “[s]ources need not be paragons of\\n\\nvirtue for journalists safely to rely on them.” 1 Robert D. Sack, Sack on Defamation:\\n\\nLibel, Slander, and Related Problems §5:5.2(C) at 5-109 (5th ed. 2017). Courts have\\n\\nconsistently held that reliance on tainted or troubled sources does not alone establish\\n\\nactual malice. See, e.g., Pemberton v. Birmingham News Co., 482 So. 2d 257, 266\\n\\n\\n\\n\\n 26\\n For their segment on Mr. Talley, the Defendants relied primarily on\\nstatements and interviews from Mr. Girtman, Mr. Shaw, Mr. Mack, Mr. Brown, Mr.\\nWright, Mr. Johnson, Mr. Lawson-Kennedy, Mr. Pogi, and Mr. Carter. The\\ninterviews revealed that several of these sources had substance abuse problems: Mr.\\nGirtman used drugs and failed drug tests, Aplt. App., Vol. III at A801; Mr. Johnson\\nadmitted to smoking marijuana, Aplt. App., Vol. II at A490, A492-93; Mr. Shaw\\nfailed drug tests and used a masking agent to conceal his marijuana use, id. at A501;\\nand Mr. Mack and Mr. Brown either used drugs or knew of other players who did,\\nid.at A389, A464. The record also suggests at least two of these players may have\\nhad criminal records. Mr. Talley’s original complaint stated that Mr. Shaw had been\\nconvicted of larceny and burglary, though it is not clear that the Defendants knew\\nthis when they published their article. Aplt. App., Vol. IV at A909. In addition, the\\ncall between Mr. Evans and Mr. Wright was timed and took place over a controlled\\nline which indicates Mr. Wright was either in jail or prison. Evans Wright Interview\\nat 10:15-10:39.\\n 44\\n\\f(Ala. 1985) (finding that defendant’s reliance on statements from an ex-convict was\\n\\ninsufficient to show actual malice); Secord v. Cockburn, 747 F. Supp. 779, 794\\n\\n(D.D.C. 1990) (holding that “[t]he use of convicted felons cannot alone constitute a\\n\\nfact of actual malice”). The fact that some of the Defendants’ sources were not\\n\\n“paragons of virtue” is thus insufficient to show actual malice. Sack, §5:5.2(C) at 5-\\n\\n109.\\n\\n Courts also have noted that “newspaper investigation of reports of corruption\\n\\nmust often obtain first-hand corroboration from those present in the barrooms or\\n\\ngambling houses, rather than from citizens who spend their time only at home, in\\n\\nchurch, or at work in less colorful occupations.” Kidder v. Anderson, 354 So.2d 1306\\n\\n(La. 1978). Here, the five-article series reported on drug use, financial misconduct,\\n\\nand academic dishonesty in the OSU football program. To prepare this report, the\\n\\nDefendants necessarily had to rely on sources who may have participated in these\\n\\nactivities. Rather than demonstrating that the Defendants published with actual\\n\\nmalice, this shows they sought information from the sources who were in the best\\n\\nposition to describe these possible features of the OSU program. See Pemberton, 482\\n\\nSo. 2d at 266 (noting that “the fact that [a source] was an ex[-]convict did not\\n\\ndiminish his credibility . . . but rather made it more probable that he would have\\n\\ninside information” that could aid the defendants’ investigation).\\n\\n Although some of the interviewees who provided information about Mr. Talley\\n\\nused drugs or had criminal records, the reporters stated they “did not observe any . . .\\n\\n 45\\n\\ffacts that would cause [them] to question [the players’] credibility.” Aplt. App., Vol.\\n\\nII at A440 (Dohrmann Affidavit); see id. at A390-91 (Evans Affidavit). The SI\\n\\nreporters interviewed multiple individuals—including some who did not have\\n\\ntroubled pasts—and stated that, though “players spoke to [them] independently, at\\n\\ndifferent times and different places, . . . the facts those players provided were\\n\\nconsistent with and corroborative of one another.” Id. at A439-40 (Dohrmann\\n\\nAffidavit); see id. at A390-91 (Evans Affidavit). “That these . . . sources\\n\\ncorroborated each other’s allegations sufficiently establishes [that the Defendants]\\n\\ndispelled [any of their] doubts” about the players’ veracity. Spacecon, 713 F.3d at\\n\\n1046. Mr. Talley thus has not shown there were “obvious reasons to doubt the\\n\\nveracity” of the player sources. St. Amant, 390 U.S. at 732.\\n\\n In sum, Mr. Talley has failed to show the Defendants’ use of “troubled” or\\n\\ntainted sources demonstrated actual malice. Aplt. Br. at 14. The record shows the\\n\\npassages relating to Mr. Talley were based on “sources which were not believed to be\\n\\nfalse.” Rosanova v. Playboy Enters., Inc., 580 F.2d 859, 862 (5th Cir. 1978). Unlike\\n\\nthe defendants in Butts, the Defendants did not rely on a single, questionable source\\n\\nwithout fact-checking, interviewing additional witnesses, or seeking independent\\n\\nsupport. 388 U.S. at 157-58. And this case has no resemblance to Harte-Hanks,\\n\\nwhere the defendants knew the facts in their publication “had been denied . . . by five\\n\\nother witnesses before the story was published.” 491 U.S. at 691. Although the\\n\\narticle here quoted some of the players who had “troubled histor[ies],” Aplt. Br. at\\n\\n 46\\n\\f14, Mr. Talley has not shown the Defendants had “obvious reasons to doubt the\\n\\nveracity of the [players] or the accuracy of [their] reports,” Harte-Hanks, 491 U.S. at\\n\\n688 (quotations omitted). Nor has he shown that the players’ drug use or other\\n\\nmisconduct gave the Defendants a “high degree of awareness of probable falsity\\n\\nor . . . serious doubts as to the truth of [their] publication.” Colbert, 747 P.2d at 291.\\n\\n d. Slant, bias, motive, and omissions\\n\\n Mr. Talley argues the Defendants exhibited actual malice by presenting a\\n\\nslanted, biased, and “sensationalized” narrative. Aplt. Br. at 4. He contends the\\n\\nDefendants crafted their story to fit their “own investments and motives,” id. at 13,\\n\\nand demonstrated actual malice by “specifically target[ing],” Aplt. Reply Br. at 8, his\\n\\nreputation “as a respected pastor and mentor,” id. at 2. He also claims the\\n\\nDefendants “omit[ted] material statements.” Aplt. Br. at 21. These arguments also\\n\\nfail.\\n\\n i. Slant and bias\\n\\n Mr. Talley suggests the “Defendants sought a certain narrative from\\n\\ninterviewees,” id. at 14, and “achieved the story they desired to portray,” id., by\\n\\n“seek[ing] out biased individuals who would provide a sensational story,” id. at 4.\\n\\nBut he provides no concrete supporting evidence to show this was the case. Even if\\n\\nhe could, it would not show the Defendants published with actual malice.\\n\\n Although the Defendants may have developed a theme for their article—their\\n\\ne-mail correspondence, for example, includes a discussion of whether a particular\\n\\n 47\\n\\fplayer’s “experience fits our narrative,” Aplt. App., Vol. II at A498—that alone does\\n\\nnot show they doubted the truth of their publication. Indeed, the Defendants, not Mr.\\n\\nTalley, are entitled to choose their theme. It is the “function of editors” to decide\\n\\n“[t]he choice of material to go into a newspaper.” Miami Herald Publ’g Co. v.\\n\\nTornillo, 418 U.S. 241, 255 (1974). Further, “[t]he fact that a commentary is one\\n\\nsided . . . has no tendency to prove that the publisher believed it to be false.”\\n\\nMcFarlane v. Esquire Magazine, 74 F.3d 1296, 1307 (D.C. Cir. 1996). Thus, to the\\n\\nextent Mr. Talley could provide evidence to show the Defendants wrote an article\\n\\nconsistent with a theme or narrative, he has not established they published with actual\\n\\nmalice.\\n\\n ii. Motive\\n\\n Mr. Talley contends the Defendants had “independent knowledge of [Mr.\\n\\nTalley’s] standing in the community,” Aplt. Br. at 20, and “specifically targeted” his\\n\\n“reputation for honesty,” Aplt. Reply Br. at 8. He further claims the Defendants had\\n\\n“obvious reasons to doubt the veracity of the . . . information discovered in their\\n\\ninvestigations . . . due to . . . [their] own investments and motives.” Aplt. Br. at 13.\\n\\n Despite his contention that the Defendants published with improper motives,\\n\\nMr. Talley does not specify what those “investments and motives” might have been.\\n\\nId. He also does not identify any evidence that the Defendants “specifically targeted”\\n\\nhim. Aplt. Reply Br. at 8. The Defendants spent only a fraction (442 words) of their\\n\\n20,000-word, five-part series discussing Mr. Talley, which suggests their purpose\\n\\n 48\\n\\fwas not to tarnish his reputation. But even if the Defendants “targeted” Mr. Talley,\\n\\nthat would not prove they had doubts about the article’s veracity or published with\\n\\nactual malice. See, e.g., Spacecon, 713 F.3d 1028 (noting that “a publisher’s\\n\\nadversarial stance . . . is not necessarily indicative of actual malice”) (quotations\\n\\nomitted).\\n\\n Although “[t]he motivation behind a publication is a factor to consider,” id. at\\n\\n1042, “courts must be careful not to place too much reliance on [motive],” Harte-\\n\\nHanks, 491 U.S. at 668; see also Old Dominion Branch No. 496, Nat’l Ass’n of Letter\\n\\nCarriers v. Austin, 418 U.S. 264, 281-82 (stating that “ill will toward the plaintiff, or\\n\\nbad motives are not elements of the New York Times standard”). As this court said in\\n\\nSpacecon, “[E]vidence of [defendant’s] . . . bias is not enough to show he acted with\\n\\nactual malice.” 713 F.3d at 1043; see also Harte-Hanks, 491 U.S. at 665;\\n\\nTavoulareas v. Piro, 817 F.2d 762, 795 (D.C. Cir. 1987) (stating a publisher’s\\n\\n“adversarial stance” may be “fully consistent with professional, investigative\\n\\nreporting” and is not necessarily “indicative of actual malice”) (quotations omitted).\\n\\nMr. Talley has not identified evidence of the Defendants’ bias against him, much less\\n\\nshown that bias established actual malice.\\n\\n iii. Omissions\\n\\n Mr. Talley briefly argues the Defendants showed actual malice by “omitting\\n\\nmaterial statements.” Aplt. Br. at 14. Mr. Talley does not identify in his briefing\\n\\nwhat, specifically, the Defendants omitted from their article. Even if he had done so,\\n\\n 49\\n\\fhe has not shown how omissions would prove the Defendants published with actual\\n\\nmalice.27 Courts have noted that “the author of an article will have to choose which\\n\\nfacts to include and which to omit,” because “[i]t is impossible to print all of the facts\\n\\non which an opinion or belief is based, especially when an article comprises a critical\\n\\nanalysis.” Reliance Ins. Co. v. Barron’s, 442 F. Supp. 1341, 1352 (S.D.N.Y. 1977).\\n\\nAccordingly, “recovery for a false light tort may not be predicated on . . . [a\\n\\ndefendant’s failure] to include additional facts which might have cast the plaintiff in\\n\\na more favorable or balanced light.” Machleder v. Diaz, 801 F.2d 46, 55 (2d Cir.\\n\\n1986); see also Reliance Ins. Co., 442 F. Supp. at 1352 (citations omitted) (finding\\n\\nthat “selective omission of relevant data” does not provide “circumstantial evidence\\n\\nof defendants’ actual malice”); Pape, 401 U.S. at 282, 290-92 (holding that a\\n\\npublisher did not demonstrate actual malice by omitting the word “alleged” from its\\n\\ndescription of a legal complaint against police officers). Mr. Talley has not shown\\n\\nthe Defendants’ decision to publish certain facts while omitting others demonstrates\\n\\nactual malice.\\n\\n\\n\\n\\n 27\\n In his initial complaint, Mr. Talley argued the Defendants “omitt[ed]\\nmaterial facts about the true, and proper nature of Aso Pogi’s temporary living\\narrangements with [Mr. Talley’s] family.” Aplt. App., Vol. I at A19. And in\\nresponse to their motion for summary judgment, he argued the Defendants “omitted\\nplayers who reported never having seen or heard of players being paid for speaking\\nengagements.” Aplt. App., Vol. III at A680. On appeal, however, Mr. Talley makes\\nonly general allegations about omissions and does not identify any specific facts or\\nstatements that the Defendants excluded from their article.\\n\\n 50\\n\\f e. Error(s)\\n\\n Mr. Talley contends the Defendants demonstrated actual malice by publishing\\n\\ninaccurate information. See Aplt. Br. at 4, 20. But other than his misplaced claim\\n\\nabout misquoting Mr. Pogi, which we addressed above, Mr. Talley does not identify\\n\\nany specific errors or inaccuracies in his appellate briefs.28 This argument is\\n\\ntherefore inadequately briefed. Moreover, the record shows the Defendants fact-\\n\\nchecked and verified the information they used in their article. Without evidence of\\n\\nany knowing or reckless falsehood, Mr. Talley cannot show the Defendants’ alleged,\\n\\nunspecified mistakes were anything more than negligent, which is “insufficient to\\n\\nshow the recklessness that is required for a finding of actual malice.” New York\\n\\nTimes, 376 U.S. at 288.\\n\\n Relatedly, the Supreme Court has held that “failure to investigate . . . is not\\n\\nsufficient to establish reckless disregard.” Harte-Hanks, 491 U.S. at 688. A plaintiff\\n\\ncannot demonstrate malice “merely by showing that the publication was erroneous.”\\n\\nHerbert, 992 P.2d at 329 (citing Gertz, 418 U.S. at 340-41; St. Amant, 390 U.S. at\\n\\n\\n\\n 28\\n In his initial complaint, Mr. Talley alleged the Defendants failed to check\\nfacts about Mr. Carter’s academic record. See Aplt. App., Vol. IV at A910. Mr.\\nTalley does not raise this argument on appeal, so we do not address it here. See City\\nof Colo. Springs v. Solis, 589 F.3d 1121, 1135 n.5 (“[A]rguments not raised in the\\nopening brief are waived.”); Bronson v. Swensen, 500 F.3d 1099, 1104 (10th Cir.\\n2007) (“[W]e routinely have declined to consider arguments that are not raised, or are\\ninadequately presented, in an appellant’s opening brief.”)\\n\\n\\n\\n 51\\n\\f732; New York Times, 376 U.S. at 281). Thus, Mr. Talley’s general allegation about\\n\\ninaccuracy does not show the Defendants “had a high degree of awareness of\\n\\nprobable falsity or in fact entertained serious doubts as to the truth of the\\n\\npublication.” Colbert, 747 P.2d at 291.\\n\\n * * * *\\n\\n The Oklahoma Supreme Court described “[t]he ‘actual malice’ standard [as] a\\n\\nformidable one.” Herbert, 992 P.2d at 328. Mr. Talley has failed to show he could\\n\\nsatisfy it here. The Defendants were thorough in their investigation, editing, and\\n\\nreview. Mr. Talley has not shown they published with “knowledge that [their\\n\\nstatements were] false or with reckless disregard of whether [they were] false or not.”\\n\\nNew York Times, 376 U.S. at 280. He cannot show “with convincing clarity” that the\\n\\nDefendants acted with actual malice. Colbert, 747 P.2d at 291.\\n\\n III. CONCLUSION\\n\\n We affirm the district court’s entry of summary judgment in favor of the\\n\\nDefendants.\\n\\n\\n\\n\\n 52\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4394857/\", \"author_raw\": \"MATHESON, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"MATHESON"},"judge2":{"kind":"string","value":"MURPHY"},"judge3":{"kind":"string","value":"EID"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4617604/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: John Thomas TALLEY, Plaintiff - Appellant, v. TIME, INC., D/B/A Sports Illustrated Magazine; George Dohrmann ; Thayer Evans, Defendants - Appellees.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-08\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 8, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\n JOHN THOMAS TALLEY,\n\n Plaintiff - Appellant,\n\n v. No. 18-6169\n\n TIME, INC., d/b/a Sports Illustrated\n Magazine; GEORGE DOHRMANN;\n THAYER EVANS,\n\n Defendants - Appellees.\n _________________________________\n\n Appeal from the United States District Court\n for the Western District of Oklahoma\n (D.C. No. 5:14-CV-00853-D)\n _________________________________\n\nRaymond S. Allred (Gary L. Richardson, Charles L. Richardson, Alisa G. Hopkins, and\nLia R. Rottman, with him on the briefs), of Richardson Richardson Boudreaux, PPLC,\nTulsa, Oklahoma, for Plaintiff - Appellant.\n\nRobert D. Nelon (Jon Epstein, with him on the brief), of Hall, Estill, Hardwick, Gable,\nGolden & Nelson, P.C., Oklahoma City, Oklahoma, for Defendants - Appellees.\n _________________________________\n\nBefore MATHESON, MURPHY, and EID, Circuit Judges.\n _________________________________\n\nMATHESON, Circuit Judge.\n _________________________________\n\f In 2013, Sports Illustrated magazine (“SI”) published a five-article series on\n\nthe Oklahoma State University (“OSU”) football program. The series explored\n\n“illicit payments” and other “extreme measures” OSU used to recruit and retain top\n\nplayers. Aplt. App., Vol. II at A446; Aplt. App., Vol. III at A699. The first article in\n\nthe series, titled “The Money,” described an assistant coach who offered “de facto\n\nbonus[es] . . . based on performances on the field.” Aplt. App., Vol. II at A448. It\n\nalso discussed boosters and coaches who made “direct payments to players . . .\n\nindependent of performance,” id., and “funnel[ed] money to players through dubious\n\nwork arrangements,” id. at A452.1 And it briefly profiled John Talley, a booster who\n\n“had been close to the football program since at least 2002” and who allegedly\n\n“grossly overpaid [OSU players] for jobs they did or compensated them for jobs they\n\ndidn’t do.” Id.\n\n Mr. Talley sued Time, Inc., which publishes SI, and SI reporters Thayer Evans\n\nand George Dohrmann (collectively, “the Defendants”) in state court, claiming that\n\nthe article placed him in a false light and invaded his privacy. Invoking diversity\n\njurisdiction under 28 U.S.C. § 1332, the Defendants removed the case to the United\n\nStates District Court for the Western District of Oklahoma. After discovery, the\n\n\n\n\n 1\n According to the National Collegiate Athletic Association (“NCAA”), a\nbooster—or “representative[] of [an] institution’s athletic interests”—is an individual\nwho supports “teams and athletics departments through donations of time and\nfinancial resources which help student-athletes succeed on and off the playing field.”\nSee https://perma.cc/R96W-G7AZ.\n 2\n\fDefendants moved for summary judgment. The district court granted the motion.\n\nMr. Talley timely appealed.\n\n Exercising jurisdiction under 28 U.S.C. § 1291, we affirm because Mr. Talley\n\nhas not demonstrated a genuine issue of material fact as to whether the Defendants\n\nacted with actual malice, an element of Oklahoma’s false light tort.\n\n I. BACKGROUND\n A. Oklahoma’s False Light Tort2\n\n Oklahoma recognizes the common law tort of false light invasion of privacy.\n\nIt has adopted the Restatement (Second) of Torts § 652E, which reads:\n\n One who gives publicity to a matter concerning another\n that places the other before the public in a false light is\n subject to liability to the other for invasion of his privacy,\n if\n\n (a) the false light in which the other was placed would be\n highly offensive to a reasonable person, and\n\n (b) the actor had knowledge of or acted in reckless\n disregard as to the falsity of the publicized matter and the\n false light in which the other would be placed.\n\nSee McCormack v. Okla. Publ’g Co., 613 P.2d 737, 740 (Okla. 1980) (recognizing\n\n“the tort of invasion of privacy . . . as set out in the Restatement”); Colbert v. World\n\nPubl’g Co., 747 P.2d 286, 290 (Okla. 1987) (noting that the Oklahoma Supreme\n\n\n 2\n Because federal court jurisdiction in this case is based on the diversity of\ncitizenship between the parties, 28 U.S.C. § 1332, we apply the substantive law of\nthe forum state—Oklahoma. See Haberman v. Hartford Ins. Grp., 443 F.3d 1257,\n1264 (10th Cir. 2006) (“In diversity cases, the substantive law of the forum state\ngoverns the analysis of the underlying claims . . . .”).\n 3\n\fCourt has “specifically adopt[ed] the treatment of [invasion of privacy] in the\n\nRestatement of the Law of Torts (Second)”).\n\n False light plaintiffs must prove three elements:\n\n (1) “the defendant gave publicity to a matter concerning\n the plaintiff that placed the plaintiff before the public in a\n false light,”\n\n (2) “the false light in which the plaintiff was placed would\n be highly offensive to a reasonable person,” and\n\n (3) “the defendant had knowledge of or acted in reckless\n disregard as to the falsity of the publicized matter and the\n false light in which the other would be placed.”\n\nMitchell v. Griffin Television, LLC, 60 P.3d 1058, 1061 (Okla. Civ. App. 2002).\n\n Oklahoma courts have specified that the third element—“knowledge of or . . .\n\nreckless disregard as to the falsity of the publicized matter”—is identical to the actual\n\nmalice standard articulated in New York Times Co. v. Sullivan, 376 U.S. 254 (1964).\n\nSee Herbert v. Okla. Christian Coal., 992 P.2d 322, 328 (Okla. 1999) (quoting New\n\nYork Times, 376 U.S. at 280).3 We discuss this standard in greater detail below.\n\n B. Factual Background\n\n SI is a sports magazine published by Time, Inc. Aplt. App. Vol. I at A85. In\n\nearly 2012, Mr. Evans, who was then a reporter at Fox Sports, learned that the OSU\n\nfootball program might have been using financial inducements to attract and retain\n\n\n 3\n Because Oklahoma has explicitly adopted the actual malice standard for false\nlight invasion of privacy claims, the following analysis uses the term “actual malice”\nas shorthand for the “knowledge of or . . . reckless disregard” element of the false\nlight tort. Mitchell, 60 P.3d at 1061.\n 4\n\fplayers. Id. at A86; Aplt. App., Vol. II at A388. That fall, after taking a job at SI,\n\nMr. Evans shared this information with SI’s Executive Editor B.J. Schecter. Aplt.\n\nApp., Vol. II at A388. Mr. Schecter asked Mr. Dohrmann if he would be interested\n\nin working with Mr. Evans on a story about the OSU program. Id. When Mr.\n\nDohrmann agreed, SI began a 10-month investigation into OSU’s recruiting and\n\nretention practices. Aplt. App., Vol. I at A87; Aplt. App., Vol. II at A388, A438.\n\nMr. Schecter led the investigation, which involved dozens of interviews with OSU\n\nplayers, coaches, and boosters. Aplt. App., Vol. I at A86-88; Aplt. App., Vol. II at\n\nA438, A442.\n\n In September 2013, SI published its findings in a five-part article series titled\n\n“The Dirty Game.” Aplt. App., Vol. II at A445-82. Below, we quote the passage\n\nabout Mr. Talley, which appeared in the first article of the series. We then describe\n\nthe steps SI took to investigate, research, draft, and edit the Talley passage.\n\n The Article\n\n Mr. Dohrmann and Mr. Evans co-authored “The Dirty Game” using\n\ninformation they gathered during SI’s investigation. Aplt. App., Vol. I at A87-88;\n\nAplt. App., Vol. III at A770. The first article of the series—a roughly 5,000-word\n\npiece titled “The Money”—described gratuities and inducements that OSU used to\n\nattract and retain top players. Aplt. App., Vol. II at A445-53. It detailed financial\n\nbenefits—including payments for performance on the field—that coaches offered to\n\nplayers on the team. Id. It also described how several “boosters,” including Mr.\n\n 5\n\fTalley, “funnel[ed] money to players,” id. at A452, by paying them “for little or no\n\nwork,” id.\n\n Mr. Talley was the North Central Area Director of the Fellowship of Christian\n\nAthletes (“FCA”).4 Id. at A452; Aplt. App., Vol. I at A135. The 442-word passage\n\nabout him reads, in full, as follows:\n\n According to multiple players, though, the\n generosity of [booster Kay] Norris, who died of lung\n cancer in 2006, was exceeded by that of other [OSU]\n Cowboys supporters. John Talley, an area director of the\n Fellowship of Christian Athletes, had been close to the\n football program since at least 2002, when his son, Saul,\n was a walk-on long snapper. “John Talley was the hot\n name around campus,” [player Rodrick] Johnson says. “If\n you needed a job, call John Talley.”\n\n [Players Fath’] Carter, [Brad] Girtman, [Rodrick]\n Johnson and Thomas Wright each say that Talley either\n grossly overpaid them for jobs they did or compensated\n them for jobs they didn’t do. They allege that numerous\n other players benefited from Talley's generosity too.\n Girtman says Talley paid him $1,500 to $2,000 every two\n weeks during one summer to work on his horse ranch, far\n more than the job was worth. Talley could also be counted\n on to set up speaking gigs for players, paying $100 for a\n 15- to 20-minute talk. “You might get more depending on\n who you were,” says Shaw. Carter says he and a few other\n players were once paid by Talley to help shoe horses.\n Asked if the players did the work, Carter says, “Are you\n kidding? Most of us hadn’t even seen a horse before.”\n\n Quarterback Aso Pogi (1999 to 2002) says he and\n another player lived at Talley’s ranch one summer rent-\n 4\n In his deposition, Mr. Talley explained that the FCA’s mission is “[t]o reach\ncoaches, student athletes, and all who they influence, to give the opportunity to\nreceive Jesus Christ as Lord and Savior, and to serve Him in their relationships and in\nthe church.” Aplt. App., Vol. I at A136.\n 6\n\f free. In retrospect Pogi says, “It’s a big deal. I was the\n starting quarterback.” (Talley says that Pogi lived at his\n ranch and had to work to cover his rent; Pogi denies that\n he did any work.)\n\n Talley says that he sometimes paid players a fee for\n speaking engagements and that they frequently did work\n on his ranch, noting he always paid an hourly wage. He\n also says he cleared the speaking fees and the hourly\n employment through the university’s compliance office. “I\n have paid lots of players to work on my ranch,” Talley\n says. “But I would never pay someone not to work.”\n\n OSU compliance director Kevin Fite says of the\n speaking engagements arranged by Talley, “They were not\n cleared through our office as paid speaking engagements.\n In fact, two of my staff members indicated to me that they\n had had conversations with John and told him you cannot\n pay for speaking engagements. If you want to employ our\n student-athletes for other things, that’s fine, but you cannot\n pay them for speaking engagements.”\n\n While Fite says the school cleared Talley to employ\n athletes on his ranch, he acknowledges that Talley’s\n paying in cash “is not something I am comfortable with. I\n think that’s a concern. I would prefer to see it done a\n different way.”\n\nGeorge Dohrmann & Thayer Evans, Special Report on Oklahoma State Football: Part 1\n\n– The Money, Sports Illustrated, Sept. 16, 2013, at 39-40; Aplt. App., Vol. II at A452.\n\n The Reporting Process\n\n As previously noted, SI began investigating the OSU football team in late\n\n2012. Aplt. App., Vol. I at A86-87. Between 2000 and 2005, OSU achieved its first\n\nwinning seasons in more than a decade. Aplt. App., Vol. II at A445. The Defendants\n\nsuspected that new and perhaps impermissible recruiting strategies might have\n\n 7\n\fcontributed to this sudden success. Id. They focused their research on individuals\n\nwho were involved with the program between 2000 and 2005. Id. at A388.\n\n a. Interviews with players and Mr. Talley\n\n The SI reporters interviewed 60 to 70 former and current OSU players,\n\ncoaches, boosters, and administrators. Aplt. App., Vol. I at A87; Aplt. App., Vol. II\n\nat A388-90; Aplt. App., Vol. III at A747. The reporters recorded the interviews they\n\nused to write the passage about Mr. Talley. Aplt. App., Vol. II at A389. These\n\nrecordings were later produced during discovery.5 In addition, Mr. Schecter\n\n\n\n\n 5\n In support of their motion for summary judgment, the Defendants provided\nthe district court with audio excerpts from Mr. Dohrmann’s interview with former\nOSU player Fath’ Carter, Aplt. App., Vol. II at A483; Mr. Evans’s interviews with\nformer players Rodrick Johnson, id. at A487, Seymour Shaw, id. at A497, Brad\nGirtman, id. at A505, Thomas Wright, id. at A517, Aso Pogi, id. at A512, Larry\nBrown, id. at A518, and Chijuan Mack, id. at A519; Mr. Dohrmann and Mr. Evans’s\ninterview with Thomas Wright, id. at A509, and Mr. Schecter and Mr. Dohrmann’s\ninterview with OSU officials, id. at A523. The Defendants also provided audio\nexcerpts from an interview that NCAA investigators conducted with OSU operations\ndirector Mack Butler during the NCAA’s post-article investigation. Aplt. App., Vol.\nIII at A546. Mr. Talley submitted full-length interview recordings of Mr. Evans’s\ninterviews with former players Aso Pogi, Aplt. App., Vol. IV at A894, Calvin\nMickens, id. at A895, Chijuan Mack, id. at A896, Thomas Wright, id. at A897, and\nXavier Lawson-Kennedy, id. at A898.\n\n 8\n\finterviewed Mr. Talley.6 Id. at A404. We describe below the information gathered\n\nabout Mr. Talley during these interviews.7\n\n i. Mr. Evans’s interviews\n\n Mr. Evans conducted most of the interviews. Id. at A388. After each\n\ninterview, he reviewed his notes and/or the recording and e-mailed summaries to Mr.\n\nDohrmann and Mr. Schecter. Id. at A389-90, A408, A438. He also occasionally re-\n\ninterviewed players to ensure that his information was accurate. Id. at A390.\n\n 1) Payments for speeches and work\n\n Between November 2012 and January 2013, Mr. Evans spoke to former OSU\n\nplayers Brad Girtman, Seymour Shaw, Prentiss Elliott, Chijuan Mack, Xavier\n\nLawson-Kennedy, Doug Bond, Thomas Wright, Rodrick Johnson, T.J. Minor, and\n\nLarry Brown. Id. at A389. The players reported the following:\n\n Brad Girtman revealed that Mr. Talley paid him “fifteen hundred, a\n thousand” dollars to perform “ranch hand” tasks. Dist. Ct. Doc. 60, Ex. 17\n at 0:14-0:20, 0:42 (Girtman Interview); see also Aplt. App., Vol. II at\n A508. When Mr. Evans asked if these payments were excessive, Mr.\n Girtman responded, “I mean, I thought he was overpaying me, cus I wasn’t\n sure what I was doing.” Girtman Interview at 0:06-0:13.\n\n Seymour Shaw reported that Mr. Talley “always paid [players] to go talk”\n and that “if you needed some money, you’d go to John Talley.” Dist. Ct.\n\n 6\n Although Mr. Schecter recorded his interview with Mr. Talley, he stated that\nthe file was “corrupted after a minute and a half.” Aplt. App., Vol. II at A410.\nAccordingly, the recording is not available.\n 7\n In this opinion, we have quoted from the interview recordings, which are part\nof the record on appeal, without the benefit of transcripts. The parties did not\nprovide certified transcripts.\n 9\n\f Doc. 60, Ex. 15 at 1:09-1:13, 1:16-1:19 (Shaw Interview); see also Aplt.\n App., Vol. II at A500.\n\n Chijuan Mack volunteered Mr. Talley’s name without any prompting from\n Mr. Evans and described the speaking arrangements and team building\n activities that Mr. Talley organized for OSU players. Dist. Ct. Doc. 71, Ex.\n 12 at 45:49-46:37 (Mack Interview). When Mr. Evans asked, “So, like,\n during the season you would go speak to schools, read to schools, and\n they’d pay you like a normal job, obviously?,” Mr. Mack responded, “No,\n during the season you couldn’t get paid during the season. . . . But during\n the summer, you’d get to go there, he got a big farm like, he’d do stuff like\n focus groups . . . That’s when you would get paid.” Id. at 47:45-48:56.8\n\n Mr. Evans asked Larry Brown, “You would go talk to kids and [Mr. Talley]\n would pay you to go talk to kids, right?” Mr. Brown responded, “Yeah.”\n Dist. Ct. Doc. 60, Ex. 25 at 0:39-0:45 (Brown Interview).\n\n Thomas Wright denied that Mr. Talley ever overpaid him for work. Dist.\n Ct. Doc. 71, Ex. 13 at 6:23-36 (Evans Wright Interview). When Mr. Evans\n mentioned that “some guys got paid” for Mr. Talley’s speaking\n engagements, Mr. Wright responded, “I know some guys did, but I didn’t.\n I didn’t get paid for that.” Id. at 6:27-45. In a different interview, Mr.\n Wright stated that OSU players worked for boosters but “got kinda\n overpaid.” Dist. Ct. Doc. 60, Ex. 19 at 0:00-0:21 (Evans Dohrmann Wright\n Interview). When asked about Mr. Talley, Mr. Wright said, “I don’t think\n he was into all that, he seemed pretty good, but I mean he had to have been\n a booster I would think . . . . He was hooking us up big time with jobs, but I\n\n\n\n 8\n Mr. Mack denied that players were overpaid for work and stated that OSU\n“made sure they did everything by the law.” Mack Interview at 39:40-40:18. But he\nalso reported that OSU did all it could to take advantage of what was permitted under\nthe rules: “[If] the rules say that you can do this, . . . if that’s the case, [OSU would\nfollow] the rule all the way to the nitty gritty. . . . So they would have somebody go\nto check that and he would come back and be like, ‘Well look they can do this and\nthis,’ so the next time we’d get our monthly check, the check might go up a hundred\nor 200 . . . it would fluctuate because they tryin’ to get us more.” Id. at 42:36-43:14.\nAs another example, Mr. Mack reported that coaches would not hand players extra\ncash but instead gave team captains additional money—two or three hundred\ndollars—on their OSU ID cards, which players could spend anywhere on campus.\nSee id. at 43:15-45:12.\n 10\n\f don’t think, as far as giving us money, I don’t think—he’d never hand us\n money . . . but he would definitely hook us up with jobs.” Id. at 0:53-1:21.\n\n Rodrick Johnson reported that Mr. Talley overpaid him for work. When\n Mr. Evans asked about “jobs that you guys got paid crazy amounts for,”\n Mr. Johnson immediately interrupted and said, “John Talley, John Talley.\n Oh, he owes me, still to this day.” Dist. Ct. Doc. 60, Ex. 13 at 0:00-0:07\n (Johnson Interview). Mr. Johnson then added, “He used to pay very well. I\n would work for about three hours and I would get paid probably about 400\n bucks.” Id. at 0:15-0:22. Mr. Johnson described cutting bushes and doing\n yard work on Mr. Talley’s property and said, “Max[imum,] I would do\n probably about ten hours and I would get—a lot of money. Like, it’d be\n enough to actually make it through the summer.” Id. at 0:51-1:00. Mr.\n Johnson also noted that, while some employers paid with an “actual check\n that wasn’t anything under the table,” “Talley would pay in cash.” Id. at\n 2:32-2:39. Additionally, Mr. Johnson said that Mr. Talley paid him for\n speaking engagements and that “one time I went to speak at a school and he\n paid me 100 bucks, and it was, like, for 20 minutes” and that “[t]here were\n guys that did that almost every day.” Id. at 2:42-3:02. He also stated “John\n Talley was the hot name around campus tryin’ to get jobs. If you need a\n job, call John Talley.” Id. at 3:20-3:25; see also Aplt. App., Vol. II at\n A494.\n\n Xavier Lawson-Kennedy stated that he never worked for Mr. Talley but\n that he “actually wanted to” because “[Mr. Talley] had the funnest . . . he\n had the best jobs to do, like go talk to kids.” Dist. Ct. Doc. 71, Ex. 14 at\n 13:20-32 (Lawson-Kennedy Interview).\n\n By March 2013 Mr. Evans had spoken with 19 players. According to his\n\nnotes, “five [of these] admitted to taking cash, including three who said they were\n\npaid for their play, and two others admitted receiving extra per diem money.” Aplt.\n\nApp., Vol. II at A389. In addition, “[f]ive players said they were either paid for no-\n\nshow jobs or were significantly overpaid for work.” Id. Multiple players—including\n\nMr. Girtman, Mr. Shaw, Mr. Brown, Mr. Wright, and Mr. Johnson—volunteered Mr.\n\n\n\n 11\n\fTalley’s name or provided detail about his involvement with the OSU program. Id. at\n\nA389, A438.\n\n 2) Mr. Pogi living at the ranch\n\n Shortly before publishing the article, Mr. Evans interviewed former OSU\n\nquarterback Aso Pogi.9 Id. at A390. Mr. Pogi said he frequently participated in Mr.\n\nTalley’s speaking engagements but insisted he was never paid to speak. Dist. Ct.\n\nDoc. 71, Ex. 10 at 4:43-4:52 (Pogi Interview). He also described living on Mr.\n\nTalley’s ranch one summer. The relevant exchange proceeded as follows:\n\n Mr. Evans: So, how many times do you estimate John\n [Talley] gave you money? John admitted that he gave\n money. Just that way you know that I’m not lying to you.\n John admitted it, said that he cleared it with the school, the\n school said they never cleared it, and that John was never\n supposed to give you guys money.\n\n Mr. Pogi: Um, I don’t know, man, it was, you know, just\n speaking engagements—\n\n Mr. Evans: You spoke a lot, though?\n\n Mr. Pogi: Yeah I did, and, and, you know, we don’t get\n anything.\n\n Mr. Evans: I know, I know, listen, and that’s another\n argument for another day. . . . But you spoke dozens of\n times, is what people said.\n\n\n 9\n The record does not indicate when this interview occurred, but in the\ninterview recording, Mr. Evans told Mr. Pogi, “We talked to John [Talley]\nyesterday.” Dist. Ct. Doc. 71, Ex. 10 at 5:56-6:02 (Pogi Interview). Mr. Schecter\ninterviewed Mr. Talley on September 3, 2013, Aplt. App., Vol. II at at A404, which\nsuggests that Mr. Evans’s conversation with Mr. Pogi occurred on September 4,\n2013.\n 12\n\fMr. Pogi: Yeah.\n\nMr. Evans: And he gave you money dozens of times.\n\nMr. Pogi: I was on the road a lot to speak. And it was just\nfor my gas, you know, just cus I had to drive my personal\nvehicle there, you know what I mean? But, um—\n\nMr. Evans: It’s not an indictment that you’ve done\nanything wrong, Aso, okay? I’m not—\n\nMr. Pogi: And listen, I’m, I’m not really, I’m not taking it\nthat way. I’m, I’m kinda like, this is kinda throwing me\noff—\n\nMr. Evans: It is, and it should. . . . There’s no good way to\ndo it, Aso. You have to understand, I mean, from my\nperspective, there’s no good way to do it. Cus if I call you\nahead of time, you know, I want to get in front of you\nbecause, again, like, your name is in the story for money.\n\nMr. Pogi: Yeah, that, and that, that kinda, that kinda hurts\nme a little bit.\n\nMr. Evans: I mean, Aso, I mean, I’m sorry, you know? I\nmean, there’s just nothing I can do about it. You know\nwhat I’m saying? I mean, like, that’s why I came to get\nyour response. And we’ll put your response in there.\n\nMr. Pogi: Well let me, let me just say this, then. Let me\nsay that, um, I’d like to just, um, I’m not going to sit here\nand plead the Fifth or anything like that, but I, I’d like to,\nlike, you know, do my own research on it, because I’m\nbeing honest with you in telling you that, you know, we\nreceived gas money, and—\n\nMr. Evans: That’s fine. I mean, I’ll tell you what you’re\ngonna find. Because I know it, I mean, I know it from the\nNCAA perspective, right? I mean, like I said, we went to\nthem and told them, right? John said that he had had that\napproved, okay? Compliance said that they never\napproved it, Aso. So he was—and it’s against the rules for\n\n 13\n\fyou to be paid during the season, any of that stuff, for\nspeaking engagements, et cetera.\n\nMr. Pogi: And guys put me out there?\n\nMr. Evans: They threw, oh, absolutely.\n\nMr. Pogi: That I was the main one, huh?\n\nMr. Evans: No. You’re not the main one. I mean, there’s\na, it’s a long list, my man. Okay?\n\nMr. Pogi: I mean, I, I just, I did a—\n\nMr. Evans: You worked at his ranch, too.\n\nMr. Pogi: I did a lot.\n\nMr. Evans: You worked at his ranch.\n\nMr. Pogi: I—I lived there.\n\nMr. Evans: You lived there, but you never, you never\nworked—\n\nMr. Pogi: I ne—I didn’t, I didn’t do anything like—\n\nMr. Evans: You knew guys came out there and worked. I\nmean he says estimates a thousand athletes have worked at\nhis ranch.\n\nMr. Pogi: Yeah.\n\nMr. Evans: A thousand. I mean some people said that\nthey got paid for not doing anything at his ranch. You\nknow they just came out and they just basically got\nmoney—\n\nMr. Pogi: [Laughs]\n\n....\n\n\n\n 14\n\f Mr. Evans: I mean, you lived with John [Talley], right? I\n mean, what was the arrangement?\n\n Mr. Pogi: I had no arrangement. That’s the thing that’s\n throwing me off. I’m like, “Arrangement?” I-I-I didn’t\n make, you know, any money.\n\n Mr. Evans: But you shouldn’t have been, I mean, like, you\n lived with him.\n\n Mr. Pogi: Yeah I lived with him.\n\n Mr. Evans: I mean, like, I mean did anybody ever—\n\n Mr. Pogi: Me and George Horton, we, we lived with John,\n and, you know, we—\n\n Mr. Evans: He didn’t charge you rent, obviously.\n\n Mr. Pogi: No, he didn’t charge us rent. No, no, we lived\n there for a summer, you know and that was about it.\n\n Mr. Evans: And you saw the guys come out and work.\n What’d you do for money in the summers? You went and\n did the speaking engagements?\n\n Mr. Pogi: I did speaking engagements. I did a lot of\n speaking. But I wasn’t getting paid like that. I mean, I got\n gas money.\n\nId. at 9:41-12:29; 17:24-18:13.\n\n ii. Mr. Dohrmann’s interviews\n\n Mr. Dohrmann also spoke with players and OSU officials. He met in Denver\n\nwith former OSU player Fath’ Carter. During that interview, Mr. Dohrmann said,\n\n“The other one I heard was . . . that there were like some funky jobs, like you go and\n\nmow the lawn, or you don’t mow the lawn.” Dist. Ct. Doc. 60, Ex. 11 at 0:00-0:11\n\n(Carter Interview). Before Mr. Dohrmann could finish the question, Mr. Carter\n 15\n\finterrupted and said, “You’re talking about John Talley.” Id. at 0:12-0:14. Mr.\n\nCarter then added, “Yeah, however that was constructed, I have no idea. But I was a\n\nbig part of that . . . a lot of athletes.” Id. at 0:18-0:28. Mr. Dohrmann asked if there\n\nwas “one funny job” that Mr. Carter remembered. Id. at 0:30-0:34. The conversation\n\nproceeded as follows:\n\n Mr. Carter: There wasn’t a job!\n\n Mr. Dohrmann: Yeah but I mean, what was the job on\n paper . . . ?\n\n Mr. Carter: Uh, well there was no paper for one.\n\n Mr. Dohrmann: Well, you know what I mean. In theory,\n you were supposed to—\n\n Mr. Carter: It would be, um, like one funny one was out to\n his ranch, I’m putting the horseshoes on the horses.\n\n Mr. Dohrmann: But you don’t actually, no way you guys,\n you guys never got on a horse in your life.\n\n Mr. Carter: [Laughing] Yeah. . . . Yeah that was a quick\n buck, cash.\n\n ....\n\n Mr. Dohrmann: How did guys view it? Did they view it\n like, “We earned this, like, this is only fair? Doin’ what\n we’re doin’.”\n\n Mr. Carter: It was fair, but we viewed it as, “I’m gonna\n get paid.” You know, “Let me do some work for John\n Talley so I can go out and buy some shoes.”\n\nId. at 0:34-2:24; see also Aplt. App., Vol. II A323-24, A484.\n\n\n\n 16\n\f Mr. Dohrmann later called Mr. Carter to verify his statements about shoeing\n\nhorses. At his deposition, Mr. Dohrmann testified that during this phone call, Mr.\n\nCarter again said “something about shoeing horses and [that he had] never seen a\n\nhorse before” and that “[h]e didn’t do the work but he was paid.” Aplt. App., Vol. II\n\nat A325-27.\n\n iii. Mr. Schecter’s interview with Mr. Talley\n\n On September 3, 2013, Mr. Schecter had a brief conversation with Mr. Talley\n\noutside the OSU basketball arena.10 Id. at A404. Mr. Schecter informed Mr. Talley\n\nof the allegations against him. Aplt. App., Vol. III at A718. He also asked about\n\nspeaking arrangements and whether Mr. Talley had overpaid players for work. Id.;\n\nAplt. App., Vol. II at A443. Mr. Talley confirmed he had hired and paid OSU\n\nplayers to work on his property but insisted he had cleared the employment\n\narrangements with OSU’s compliance office. Aplt. App., Vol. I at A168; Aplt. App.,\n\nVol. II at A417. Mr. Schecter recorded the conversation on his cell phone, Aplt.\n\nApp., Vol. II at A409, and summarized the interview in an e-mail that he sent to Mr.\n\nEvans and Mr. Dohrmann. See id. at A443, A520-23.11 He also gave Mr. Talley his\n\n\n 10\n Mr. Talley stated Mr. Schecter was “in a hurry to get out of [the car],” Aplt.\nApp., Vol. I at A204, and that the whole interview lasted about five minutes, Aplt.\nApp., Vol. III at A680. Mr. Schecter said the interview lasted about 15 to 20\nminutes. Aplt. App., Vol. II at A443.\n 11\n Mr. Talley claimed in his deposition that Mr. Schecter arranged a second\nmeeting with him and OSU’s general counsel on Friday of the same week but\ncancelled the meeting because “he had enough information.” Aplt. App., Vol. III at\n 17\n\fcontact information and invited him to reach out with any questions. Id. at A424,\n\nA443.\n\n On September 6, 2013, Mr. Schecter sent Mr. Talley an e-mail that read, “Aso\n\nPogi told us that he . . . lived on your range [sic] rent-free for one summer. Is that\n\ntrue?” Id. at A515; see also id. at A425. Mr. Talley responded, “No, there was an\n\nexpectation of work for [Mr. Pogi’s] room and board that was done.” Id. at A514.\n\nMr. Schecter then asked if Mr. Talley “report[ed] this arrangement to Oklahoma\n\nState,” and Mr. Talley responded, “[Y]es, to athletic compliance.” Id.; see also id. at\n\nA425.\n\n b. Meetings with OSU officials\n\n On September 3, 2013, Mr. Schecter and Mr. Dohrmann met with OSU\n\nAthletic Director Mike Holder, Associate Athletic Director for Compliance Kevin\n\nFite, and General Counsel Gary Clark to “solicit their comment.” Aplt. App., Vol. II\n\nat A439; see also id. at A443; Aplt. App., Vol. III at A766. This meeting was not\n\nrecorded, but both Mr. Schecter and Mr. Dohrmann testified at their depositions that\n\nthey spent several hours “present[ing] the substance of the information [they] had\n\nlearned in [their] investigation about the role money, drugs, women, and academics\n\nplayed in the OSU football program.” Aplt. App., Vol. II at A439; see also id. at\n\n\n\n\nA719. Mr. Schecter “categorically den[ied]” this claim during his deposition. Aplt.\nApp., Vol. II at A431-32.\n 18\n\fA443. In his affidavit, Mr. Schecter said “this meeting was ‘off the record’”—“the\n\nofficials did not give us any comments for publication.” Id. at A443.\n\n On September 4, 2013, Mr. Schecter and Mr. Dohrmann held a second meeting\n\nwith the same OSU officials. This time, they recorded the meeting. See Dist. Ct.\n\nDoc. 60, Ex. 28 (OSU Officials Interview); see also Aplt. App., Vol. II at A439,\n\nA443. They asked the OSU officials to verify Mr. Talley’s claim that he had\n\nreceived clearance to pay students for speaking engagements.12 Mr. Fite said the\n\nspeaking engagements “were not cleared through our office as paid speaking\n\nengagements.” OSU Officials Interview at 1:02-1:07. He added, “In fact, two of my\n\nstaff members indicated to me this morning that they had had conversations with [Mr.\n\nTalley] and had told him, ‘You cannot pay for speaking engagements. If you wanna\n\nemploy our student athletes for other things, that is fine, but you cannot pay them for\n\nspeaking engagements.’” Id. at 1:07-1:25.\n\n c. Writing and editing\n\n In spring 2013, the SI reporters determined they had gathered enough\n\ninformation to begin drafting the article. Aplt. App., Vol. II at A438. Mr. Dohrmann\n\nassumed primary writing duties. As he wrote, he reviewed Mr. Evans’s notes and\n\n\n 12\n In the interview recording, Mr. Schecter said, “One thing [Mr. Talley] did\nsay was that, whether it was routinely or regularly, but certainly plenty of times, that\nhe did, indeed, set up speaking engagements for football players, and that on\nnumerous occasions that they were paid for those speaking engagements. He said it\ncoulda been 50 dollars, it coulda been 100 dollars, or whatever, but that was cleared\nthrough your office.” OSU Officials Interview at 0:09-0:42.\n 19\n\flistened to audio recordings of the interviews. Id. at A439. He also identified\n\n“places where [the reporters] needed more information, or the name of a source, or\n\nspecific details about what a former player had said about his experience.” Id. Mr.\n\nDohrmann sent drafts of the article to editors and to Mr. Evans, who reviewed the\n\nwork as it was written. Id. at A390. He also spoke frequently with Mr. Evans and\n\nMr. Schecter to ensure “[they] had sufficient substantiation for what SI was\n\nreporting.” Id.\n\n Mr. Dohrmann’s drafts underwent SI’s standard editing and review process,\n\nwhich Mr. Schecter described as follows:\n\n Well . . . it starts off with a draft of the story being filed.\n That story is then edited, fact-checked, vetted by our legal\n team, copy-edited, read one more time by the writers and\n editors involved in the . . . story, and then finally, it goes to\n press.\n\nId. at A400. As part of this revision process, other SI editors “[made] notes in\n\nthe drafts to suggest word changes for clarity or flow, or ask[ed] questions\n\nabout what the sources said about the facts.” Id. at A439. In addition, SI fact\n\ncheckers reviewed each draft and “would confirm specific facts, such as the\n\nspelling of a name, the dates when players attended OSU, the name of the high\n\nschool from which a player was recruited, and so on.” Id.\n\n Mr. Schecter also performed an editing role, which involved “making\n\nsure . . . the story [was] clear and concise . . . and . . . mak[ing] sure that things\n\ntrack”—that is, “if you say something, it’s supported by something else, and\n\n 20\n\fthat the piece is fair and balanced.” Id. at A399. He repeatedly listened to the\n\nrecording of his conversation with Mr. Talley to “confirm the accuracy of the\n\nquotes that [the Defendants] were using . . . and make sure that [they] gave\n\n[Mr. Talley] every attempt to deny the allegations that [they] made against\n\nhim.” Id. at A415-16.\n\n d. Pre-publication legal and editorial review and publication\n\n SI completed edits and revisions just days after the September 4 meeting with\n\nthe OSU officials. Id. at A444. Time’s in-house counsel reviewed the final draft, id.,\n\nand Chris Stone, SI’s Managing Editor, approved it, id. at A439, A444. SI published\n\nthe first article online on September 10, 2013, and released the remaining four\n\narticles online between September 11 and September 17, 2013. Aplt. App., Vol. III\n\nat A700-A701. It also printed the first article in its September 16, 2013 print issue\n\nand included the final article in its September 23, 2013 print issue.13 Id.\n\n Individual Defendants’ Depositions and Affidavits\n\n After Mr. Talley filed his lawsuit, the reporters and editor responsible for “The\n\nDirty Game” all stated they believed the series was truthful and substantiated. In his\n\ndeposition, Mr. Evans said, “I believe that we published accurate information about\n\nthe allegations that players had made about Mr. Talley.” Aplt. App., Vol. II at A379.\n\n\n\n\n 13\n SI published the second, third, and fourth articles only online.\n\n\n 21\n\fAnd in his affidavit, Mr. Evans said he “was completely satisfied that what we were\n\nreporting was truthful based on the information we had gotten from the dozens of on-\n\nthe-record sources.” Id. at A390. As to the passages on Mr. Talley, he stated:\n\n [T]hose sources—players who had been at OSU at\n different times and who were interviewed independently—\n corroborated one another. By talking with them personally\n I was able to assess their credibility, and I did not sense\n any bias toward [Mr.] Talley or other reasons that would\n make me doubt the accuracy of what they were telling me\n about him or what we reported in the article. I remain\n completely satisfied in this regard today.\n\nId. at A390-91.\n\n In his deposition, Mr. Dohrmann said “[i]t’s very difficult to get players to\n\n[admit to NCAA violations]” and that “[f]ive players is a significant number [of\n\nsources] with a story like this.” Id. at A337. He had “done a lot of stories like this”\n\nand had “done stories with far less than five [sources].” Id. Because “a number of\n\nsources . . . told [the reporters] a similar or same story about Oklahoma State and\n\nJohn Talley,” he felt “absolutely certain about what we were writing.” Id. at A342.\n\nMr. Dohrmann also stated in his affidavit that he “had heavily researched the article\n\nand reviewed all the sources,” “the facts [the interviewees] provided were consistent\n\nwith and corroborative of one another,” he “did not observe any signs of bias . . .\n\namong the sources or other facts that would cause [him] to question their credibility,”\n\nand he “did not doubt the accuracy of any statement in the article.” Id. at 439-40.\n\n At his deposition, Mr. Schecter said he believed the article “was very well\n\ndone” and “was all true.” Id. at A431. And in his affidavit, he stated, “I believed\n 22\n\fwhen the article . . . was published it was accurate and truthful. I was satisfied that\n\nall the statements in the article about [Mr.] Talley were adequately substantiated by\n\nmultiple sources and were truthful. . . . My opinion has not changed despite [Mr.]\n\nTalley’s lawsuit.” Id. at A444.\n\n C. Procedural Background\n\n In July 2014, Mr. Talley filed his lawsuit in state court. Aplt. App., Vol. I at\n\nA11. He named Time, Inc., Mr. Dohrmann, and Mr. Evans as defendants, but he did\n\nnot sue Mr. Schecter. Invoking diversity jurisdiction under 28 U.S.C. § 1332, the\n\nDefendants removed the case to the United States District Court for the Western\n\nDistrict of Oklahoma.\n\n After the parties completed the discovery process, the Defendants moved for\n\nsummary judgment. They argued, among other things, that Mr. Talley was “unable\n\nto prove with competent evidence that at least one of the statements about which he\n\ncomplains satisfies all of the elements of a false light claim.” Id. at A107. Mr.\n\nTalley opposed the motion, claiming “disputed issues of material fact exist[ed]” with\n\nrespect to all three elements of his false light claim. Aplt. App., Vol. III at A694.\n\n The district court granted summary judgment for the Defendants, finding Mr.\n\nTalley could not demonstrate a genuine dispute of material fact regarding the first\n\n(falsity) or third (actual malice) elements of his false light claim. Talley v. Time, Inc.\n\nd/b/a Sports Illustrated Magazine, No. CIV-14-853-D, 2018 WL 4558993, at *5-6\n\n(W.D. Okla. Sept. 21, 2018).\n\n 23\n\f With respect to the third element—whether SI acted with actual malice—the\n\ncourt found “[Mr. Talley] present[ed] no facts or evidence to show that Defendants\n\nknew the allegations they reported about [him] were false.” Aplt. App., Vol. V at\n\nA1197. Although Mr. Talley argued Defendants “were pursuing an agenda” and\n\ncrafted “a sensational, unfavorable” narrative to get “the story they wanted,” the\n\ncourt found his allegations were “unsupported by any facts” and could not\n\n“reasonably be found to show either actual knowledge or a high degree of awareness\n\nby Defendants that the allegations about [Mr. Talley] . . . were probably false.” Id. at\n\nA1203. The court thus concluded Mr. Talley “present[ed] no facts or evidence that\n\nmight reasonably satisfy the rigorous standard required to establish ‘actual malice’ or\n\neven to demonstrate a genuine dispute of material fact in this regard.” Id.\n\n II. DISCUSSION\n\n The following discussion concludes that Mr. Talley has not shown that a\n\nreasonable jury could find that the Defendants acted with actual malice. Summary\n\njudgment was therefore appropriate.\n\n A. Legal Background\n\n This section describes (1) the standard of review for summary judgment, (2)\n\nthe elements of Oklahoma’s false light tort, and (3) the actual malice standard.\n\n Standard of Review\n\n As this court has recognized in defamation cases, “[we] review summary\n\njudgment decisions de novo, applying the same legal standard as the district court.”\n\n 24\n\fCory v. Allstate Ins., 583 F.3d 1240, 1243 (10th Cir. 2009) (quotations omitted).\n\n“The court shall grant summary judgment if the movant shows that there is no\n\ngenuine dispute as to any material fact and the movant is entitled to judgment as a\n\nmatter of law.” Fed. R. Civ. P. 56(a). “When applying this standard, we view the\n\nevidence and draw reasonable inferences therefrom in the light most favorable to the\n\nnonmoving party.” Cory, 583 F.3d at 1243 (quotations omitted).\n\n “[A] party seeking summary judgment always bears the initial responsibility of\n\n. . . demonstrat[ing] the absence of a genuine issue of material fact.” Celotex Corp.\n\nv. Catrett, 477 U.S. 317, 323 (1986); see also Savant Homes, Inc. v. Collins, 809\n\nF.3d 1133, 1137 (10th Cir. 2016). “A movant that does not bear the burden of\n\npersuasion at trial may satisfy this burden by pointing out to the court a lack of\n\nevidence on an essential element of the nonmovant’s claim.” Teets v. Great-West\n\nLife & Annuity Ins. Co., 919 F.3d. 1232, 1243 (10th Cir. 2019) (quotations omitted).\n\n “If the movant meets this initial burden, the burden then shifts to the\n\nnonmovant to set forth specific facts from which a rational trier of fact could find for\n\nthe nonmovant.” Id. (quotations omitted). “These facts must establish, at a\n\nminimum, an inference of the presence of each element essential to the case.” Savant\n\nHomes, 809 F.3d at 1137-38 (quotations omitted). The movant is entitled to\n\nsummary judgment if the nonmoving party cannot provide facts “to make a sufficient\n\nshowing on an essential element of her case with respect to which she has the burden\n\nof proof.” Id. at 1138 (quotations omitted).\n\n 25\n\f Both the Supreme Court and Oklahoma state courts have held that at trial, the\n\nplaintiff must prove actual malice with “convincing clarity.” New York Times, 376\n\nU.S. at 286-87; Colbert, 747 P.2d at 291. The Supreme Court has said courts “must\n\nbear in mind” this heightened burden of proof when ruling on a defendant’s motion\n\nfor summary judgment. Anderson v. Liberty Lobby, Inc., 477 U.S. 242, 254 (1986)\n\n(holding that courts must consider “the actual quantum and quality of proof necessary\n\nto support liability under New York Times” when considering summary judgment on\n\nthe actual malice issue). “[I]f the evidence presented in the opposing affidavits is of\n\ninsufficient caliber or quantity to allow a rational finder of fact to find actual malice\n\nby clear and convincing evidence,” then “there is no genuine issue” and summary\n\njudgment is appropriate. Spacecon Specialty Contractors, LLC v. Bensinger, 713\n\nF.3d 1028, 1048 n.13 (10th Cir. 2013) (quotations omitted).14\n\n Oklahoma’s False Light Tort\n\n As discussed above, Oklahoma recognizes the common law tort of false light\n\ninvasion of privacy. The plaintiff must show:\n\n (1) “the defendant gave publicity to a matter concerning\n the plaintiff that placed the plaintiff before the public in a\n false light,”\n\n\n\n 14\n Spacecon involved a defamation claim brought under Colorado law, which\nrequired the plaintiff to demonstrate actual malice by clear and convincing evidence.\n713 F.3d at 1041.\n\n\n\n 26\n\f (2) “the false light in which the plaintiff was placed would\n be highly offensive to a reasonable person,”\n\n (3) “the defendant had knowledge of or acted in reckless\n disregard as to the falsity of the publicized matter and the\n false light in which the other would be placed.”\n\nMitchell, 60 P.3d at 1061 (citing McCormack, 613 P.2d at 740); see also Restatement\n\n(Second) of Torts § 652E (Am. Law Inst. 1977).\n\n “[E]ssential to . . . a false light privacy claim . . . is a determination that that\n\nthe matter published concerning the plaintiff is not true.” Rinsley v. Brandt, 700 F.2d\n\n1304, 1307 (10th Cir. 1983) (quotations omitted).15 Thus, to establish the first\n\nelement of a false light claim, a plaintiff must show the defendant made a statement\n\nthat “portrayed [plaintiff] in [a] false manner or that statements were untrue or\n\nmisleading.” McCormack, 613 P.2d at 741 (holding that plaintiff failed to state a\n\ncause of action for false light invasion of privacy because plaintiff did not allege that\n\nthe published statements were false or misleading). True statements are not\n\nactionable under Oklahoma’s false light tort.\n\n To satisfy the second element, the plaintiff must show “a reasonable [person]\n\nwould be justified in the eyes of the community in feeling seriously offended and\n\naggrieved by the publicity.” Restatement (Second) of Torts §652E, cmt. c. Put\n\ndifferently, “[i]t is only when there is such a major misrepresentation of [the\n\n\n 15\n Rinsley involved a false light invasion of privacy claim brought under\nKansas law. Like Oklahoma, Kansas has adopted the false light invasion of privacy\naction set forth in Restatement (Second) of Torts § 652E. See Rinsley, 700 F.2d at\n1307.\n 27\n\fplaintiff’s] character, history, activities or beliefs that serious offense may reasonably\n\nbe expected to be taken by a reasonable man in his position, that there is a cause of\n\naction for invasion of privacy.” Id.\n\n The third element—knowledge of or reckless disregard as to falsity—is\n\nidentical to the actual malice standard from New York Times Co. v. Sullivan. See\n\nColbert, 747 P.2d at 290-92 (noting that Oklahoma has “adopted” the actual malice\n\ntest from Time, Inc. v. Hill, 385 U.S. 374 (1967), which applied the New York Times\n\nactual malice standard in a false light invasion of privacy case); Grogan v. Kokh,\n\nLLC, 256 P.3d 1021, 1030 (Okla. Civ. App. 2011) (noting that “the Oklahoma\n\nSupreme Court has adopted the [New York Times] actual malice test for false light\n\ninvasion of privacy claims”).16 Thus, to establish the third element of a false light\n\nclaim, a plaintiff must show the defendant made or published its statements “with\n\n‘actual malice’—that is, with knowledge that [they were] false or with reckless\n\ndisregard to whether [they were] false or not.” New York Times, 376 U.S. at 280.\n\nWe next discuss the Supreme Court cases that have articulated and developed this\n\nstandard.\n\n\n\n\n 16\n Although the Supreme Court has applied the actual malice standard in at\nleast one false light invasion of privacy case, see Time, Inc., 385 U.S. 374, the\nstandard originated in New York Times, which was a defamation case. As a result,\nOklahoma courts analyzing the third element of a false light tort claim routinely look\nto and rely on both defamation and false light case law. See, e.g., Grogan, 256 P.3d\nat 1031 (“analogizing to defamation law” where there is no clear false light case law\non point).\n 28\n\f Actual Malice\n\n a. New York Times and its progeny\n\n In New York Times v. Sullivan, the Supreme Court said that a publication “was\n\nmade with ‘actual malice’” when the defendant published “with knowledge that it was\n\nfalse or with reckless disregard of whether it was false or not.” 376 U.S. at 279-80; see\n\nGertz v. Robert Welch, Inc., 418 U.S. 323, 343 (1974). The plaintiff’s burden of proving\n\nactual malice cannot be met by a preponderance of the evidence. Actual malice must be\n\nshown with “convincing clarity,” New York Times, 376 U.S. at 285-86—that is, by “clear\n\nand convincing proof,” Gertz, 418 U.S. at 342.\n\n Actual malice is not a negligence or gross negligence standard. See Garrison v.\n\nLouisiana, 379 U.S. 64, 79 (1964); Hardin v. Santa Fe Reporter, Inc., 745 F.2d 1323,\n\n1326 (10th Cir. 1984) (holding that reporter’s negligence in failing to investigate a\n\nsource’s background and in writing the article could not establish actual malice). It\n\nrequires more than showing a publication was false and defamatory, New York Times,\n\n376 U.S. at 288, and more than “a departure from reasonably prudent conduct,” Harte-\n\nHanks Commc’ns, Inc. v. Connaughton, 491 U.S. 657, 688 (1989).\n\n Actual malice is a subjective standard that requires proof of a “mental element.”\n\nMonitor Patriot Co. v. Roy, 401 U.S. 265, 276 (1971); see Harte-Hanks, 491 U.S. at 688\n\n(stating actual malice is a subjective standard). The actual malice inquiry thus “rests\n\nentirely on an evaluation of [the publisher’s] state of mind when he wrote his initial\n\n\n\n 29\n\freport, or when he checked the article against that report.” Bose Corp. v. Consumers\n\nUnion of U.S., Inc., 466 U.S. 485, 494 (1984).\n\n In St. Amant v. Thompson, 390 U.S. 727 (1968), the Supreme Court explained:\n\n [R]eckless conduct is not measured by whether a reasonably\n prudent man would have published, or would have\n investigated before publishing. There must be sufficient\n evidence to permit the conclusion that the defendant in fact\n entertained serious doubts as to the truth of his publication.\n Publishing with such doubts shows reckless disregard for\n truth or falsity and demonstrates actual malice.\n\nId. at 731.\n\n A plaintiff does not create a jury question of actual malice by showing that a\n\npublisher failed to investigate before publishing. Gertz, 418 U.S. at 332; St. Amant,\n\n390 U.S. at 731; Beckley Newspapers Corp. v. Hanks, 389 U.S. 81, 84-85 (1967) (per\n\ncuriam)17; New York Times, 376 U.S. at 28718; Revell v. Hoffman, 309 F.3d 1228,\n\n1233 (10th Cir. 2002). Nor does a plaintiff do so by showing that a publisher\n\nmisinterpreted the source material or omitted details favorable to the plaintiff. Time,\n\nInc. v. Pape, 401 U.S. at 282, 290-92 (1971). A publisher’s decision to omit details\n\n\n\n 17\n In Beckley, for example, the Supreme Court, having reviewed testimony\nfrom the newspaper’s general manager that no investigation of the allegedly\ndefamatory statements had been made, held, “[I]t cannot be said on this record that\nany failure of petitioner to make a prior investigation constituted proof sufficient to\npresent a jury question whether the statements were published with reckless disregard\nor whether they were false or not.” 389 U.S. at 84-85.\n 18\n In New York Times, the Court found the evidence insufficient to establish\nactual malice even though checking news stories in the Time’s own files would have\nrevealed the falsity of a part of the challenged publication. 376 U.S. at 287-88.\n 30\n\ffavorable to the plaintiff does not, itself, show actual malice. See id. (finding no\n\nactual malice where a publisher did not specify that “it was reporting no more than\n\nallegations”). Even “a deliberate alteration of the words uttered by a plaintiff does\n\nnot equate with [actual malice] . . . unless the alteration results in a material change\n\nin the meaning conveyed by the statement.” Masson v. New Yorker Magazine, Inc.,\n\n501 U.S. 496, 517 (1991).\n\n Actual malice may be found when a publisher had a “subjective awareness of\n\nprobable falsity.” Gertz, 418 U.S. at 334 n.6. For example, evidence that a publisher\n\nknew its sources were unreliable but made no attempt to verify their information,\n\nCurtis Publ’g Co. v. Butts, 388 U.S. 130, 157-59 (1967), or that a publisher knew it\n\nwas publishing contested allegations but deliberately ignored sources or information\n\nthat might reveal what actually happened, Harte-Hanks, 491 U.S. at 690, may\n\nestablish actual malice. Other examples include “a story [that] is fabricated by the\n\ndefendant, is the product of his imagination, or is based wholly on an unverified\n\nanonymous telephone call”; circumstances where the published statements “are so\n\ninherently improbable that only a reckless man would have put them in circulation”;\n\nor situations “where there are obvious reasons to doubt the veracity of the informant\n\nor the accuracy of his reports.” St. Amant, 390 U.S. at 732.\n\n Most of the Supreme Court’s actual malice case law, including New York\n\nTimes, comes from defamation suits. But the Supreme Court has, like Oklahoma,\n\napplied the actual malice standard to a false light claim. In Time, Inc. v. Hill, 385\n\n 31\n\fU.S. 374 (1967), the Court held that “the constitutional protections for speech and\n\npress preclude[d] the application of [a] New York [false light invasion of privacy]\n\nstatute . . . in the absence of proof that the defendant published the report with\n\nknowledge of its falsity or in reckless disregard of the truth.” Id. at 387-88.\n\n b. Oklahoma actual malice cases\n\n Because Oklahoma courts have expressly adopted the New York Times actual\n\nmalice standard, Oklahoma’s defamation and false light case law is consistent with\n\nthe actual malice principles described above.19 Like the Supreme Court, Oklahoma\n\n\n 19\n In Dun & Bradstreet, Inc. v. Greenmoss Builders, Inc., 472 U.S. 749, 758-61\n(1985), the Supreme Court held that the First Amendment requires proof of actual malice\nonly when the statements at issue involve matters of public concern. In recognizing the\nfalse light invasion of privacy tort and equating the third element of that tort to the New\nYork Times actual malice standard, Oklahoma courts have not drawn a distinction\nbetween false light claims for statements involving matters of public concern as opposed\nto private concern. We need not address whether Oklahoma courts would draw any such\ndistinction, because Mr. Talley has not argued that the statements at issue here involve\nmatters of private concern or that the actual malice standard should not apply in this case.\n Moreover, the form, content, and context of the SI publication establish that the\nstatements at issue here involve a matter of public concern. See id. at 761 (explaining\nthat when determining whether allegedly libelous statements involve a matter of public\nconcern, courts should consider the form, content, and context of the speech). The\nstatements were printed in a widely-circulated publication. Compare Spacecon, 713 F.3d\nat 1039 (holding that “a documentary meant to be shown to the public” qualified as\nspeech on a matter of public concern), with Dun & Bradstreet, 472 U.S. at 762 (holding\nthat a credit report “made available only to five subscribers” was not speech on a matter\nof public concern).\n More telling, they involved allegations against the football program at one of\nOklahoma’s major publicly-funded universities. See City of San Diego v. Roe, 543 U.S.\n77, 83-84 (2004) (“[P]ublic concern is something that is a subject of legitimate news\ninterest; that is, a subject of general interest and of value and concern to the public . . . .”);\nSpacecon, 713 F.3d at 1039 (holding that a documentary film exposing mistreatment of\nMexican construction workers involved speech on a matter of public concern); Dun &\n 32\n\fcourts have recognized that actual malice exists when “the defendant had a high\n\ndegree of awareness of probable falsity or in fact entertained serious doubts as to the\n\ntruth of the publication.” Colbert, 747 P.2d at 291. They also have noted that\n\n“negligence is not enough to rise to the level of ‘actual malice’” and that “malice\n\nmay not be inferred simply from showing that the publication was untrue.” Herbert,\n\n992 P.2d at 328. As in New York Times, St. Amant, and other Supreme Court cases,\n\nOklahoma courts have stated that “failure to investigate does not establish the actual\n\nmalice standard.” Jurkowski v. Crawley, 637 P.2d 56, 61 (Okla. 1981). They also\n\nhave followed the Supreme Court in treating the actual malice standard as a\n\nsubjective inquiry and have stated that actual malice exists only when there is\n\n“sufficient evidence to permit the conclusion that the defendant in fact entertained\n\nserious doubts as to the truth of his publication.” Washington v. World Publ’g. Co.,\n\n506 P.2d 913, 918 (Okla. 1972) (quotations omitted).20\n\n\n\nBradstreet, 472 U.S. at 762 (holding that credit report was not speech on a matter of\npublic concern because it was “solely in the individual interest of the speaker and its\nspecific business audience”). Thus, even if Oklahoma courts would distinguish between\nspeech on matters of public and private concern, the actual malice standard applies in this\ncase.\n 20\n In New York Times, 376 U.S. 254, and Curtis Publishing Co. v. Butts, 388 U.S.\n130, the Supreme Court held that the actual malice requirement applies when the\nallegedly defamatory speech is about a public figure or public official. In Gertz, the\nCourt held that the actual malice standard applies to public figures but does not apply in\ncases brought by private-figure plaintiffs. 418 U.S. at 345-48.\n In 1967, the Supreme Court said in Hill that the New York Times actual malice\nstandard also applies to false light cases. See supra note 16. It is not clear whether the\n1974 Gertz holding—which restricts the actual malice standard to cases brought by\n 33\n\f B. Analysis\n\n Although the parties have briefed both the first and third false light elements,\n\nMr. Talley’s failure to establish either element will defeat his claim. We can resolve\n\nthis appeal by addressing only the third element—actual malice.\n\n Evidence on Preparation of the Article Lacks Proof of Actual Malice\n\n The record shows the Defendants conducted a long and thorough investigation\n\nbefore publishing their article. For ten months, the reporters sought out and spoke to\n\ndozens of OSU players, coaches, and administrators. They recorded their interviews\n\nelectronically and in writing. They consulted their notes and each other while\n\ndrafting the article, and they occasionally re-interviewed individuals to ensure that\n\n\n\n\npublic officials and public figures—similarly limits the standard’s application in false\nlight cases. As one leading commentator has noted, “[a] significant number of cases have\nheld that Hill should be regarded as modified by Gertz, and that actual malice is not\nrequired . . . in false light cases with private figure plaintiffs.” 2 Rodney A. Smolla, Law\nof Defamation § 10:16 (2d ed. Nov. 2018 update). But “there is also . . . substantial\nauthority, including the Restatement Second, Torts, for the proposition that all false light\nclaims must meet the actual malice standard.” Id. Gertz thus leaves open the question of\nwhether actual malice is required in all false light cases, or only in cases involving\nstatements about public officials or public figures. See Restatement (Second) of Torts\n§652E, cmt. d.\n We need not address this question for two reasons. First, Mr. Talley has not\nargued that he is a private figure. Second, Oklahoma courts have applied the actual\nmalice standard in false light cases involving both public- and private-figure plaintiffs.\nSee Colbert, 747 P.2d at 288, 291 (Okla. 1987) (applying the actual malice standard\nin a false light case involving a plaintiff who was “unquestionably a private figure”);\nGrogan, 256 P.3d at 1029 (holding that the actual malice standard is “required for false\nlight invasion of privacy cases involving public figures”).\n 34\n\ftheir information was correct. They also fact-checked and edited their article several\n\ntimes and had their legal team review the piece before publication.\n\n Unlike the publishers in Harte-Hanks, the Defendants did not deliberately\n\nignore sources that might have disputed their account. See 491 U.S. at 690. Rather,\n\nthey interviewed multiple sources around the country who substantially corroborated\n\neach other. They also verified the information they published by re-interviewing\n\ntheir sources and fact-checking the final piece. Mr. Talley has provided no evidence\n\nthat the Defendants “fabricated” their story, based their claims about him on “an\n\nunverified anonymous telephone call,” or published allegations that were “so\n\ninherently improbable that only a reckless man would have put them into\n\ncirculation.” St. Amant, 390 U.S. at 732. He thus “proffers no evidence indicating\n\nthat [the Defendants] entertained doubts regarding the truth of the statements in [the\n\npublication].” Revell, 309 F.3d at 1233.\n\n In addition, the record shows that the reporters had ample evidence to support\n\nthe statements in the article about Mr. Talley. Mr. Pogi and Mr. Talley told the\n\nreporters that Mr. Pogi lived on Mr. Talley’s ranch without paying rent; four players\n\n(Mr. Shaw, Mr. Mack, Mr. Brown, and Mr. Johnson) said Mr. Talley paid them or\n\nothers they knew for speaking engagements; and three (Mr. Girtman, Mr. Carter, and\n\nMr. Johnson) said Mr. Talley overpaid them for work. At least two of these sources\n\n(Mr. Mack and Mr. Carter) brought up Mr. Talley’s name without prompting. And,\n\nas we show below, Mr. Pogi made statements in his interview that the Defendants\n\n 35\n\fcould reasonably have interpreted to mean he did not work at Mr. Talley’s ranch.\n\nFurther, the players were interviewed independently of one another in different parts\n\nof the country and provided consistent accounts.\n\n In sum, the evidence shows the Defendants’ article was based on an extended\n\nresearch process and was not the product of deliberate “falsification,” Pape, 401 U.S.\n\nat 289, or the “use of calculated falsehood,” Garrison, 379 U.S. at 75. There is no\n\nindication they published with “a high degree of awareness of probable falsity or . . .\n\nentertained [any] serious doubts as to the truth of the publication.” Colbert, 747 P.2d\n\nat 291. Ample evidence supported their reporting about Mr. Talley, who cannot\n\nshow with “convincing clarity” that the Defendants acted with actual malice. Id.\n\n Mr. Talley’s Arguments\n\n Mr. Talley argues the Defendants exhibited actual malice by (a) deliberately\n\nmisstating facts about Mr. Pogi’s rent arrangement, (b) falsely reporting that Mr.\n\nTalley paid players for speaking engagements, (c) relying on biased and non-credible\n\nsources, (d) writing with a slanted agenda, and (e) publishing erroneous and incorrect\n\nstatements. These arguments do not withstand scrutiny.\n\n a. Mr. Pogi’s rent\n\n Mr. Talley argues the Defendants published with actual malice by\n\n“inaccurately reporting” that Mr. Pogi lived on Mr. Talley’s property rent-free. Aplt.\n\nBr. at 15. The Defendants reported in the article that “[Mr.] Pogi denies that he did\n\nany work.” Aplt. App., Vol. II at A452. According to Mr. Talley, however, “the\n\n 36\n\finterview recording [between Mr. Evans and Mr. Pogi] clearly states Aso Pogi\n\nworked extremely hard in exchange for rent.” Aplt. Reply Br. at 5; see also Aplt. Br.\n\nat 6, 16. As a result, Mr. Talley characterizes this allegation in the article as\n\n“blatantly false” and “misconstrued,” Aplt. Br. at 16-17, and he suggests the\n\nDefendants’ failure to “accurately report what the interviewees stated” is evidence of\n\nactual malice, id. at 20.\n\n This argument is unavailing. The article states:\n\n Quarterback Aso Pogi (1999 to 2002) says he and another\n player lived at Talley’s ranch one summer rent-free. In\n retrospect Pogi says, “It’s a big deal. I was the starting\n quarterback.” (Talley says that Pogi lived at his ranch and\n had to work to cover his rent; Pogi denies that he did any\n work.).\n\nAplt. App., Vol. II at A452. The interview recording does not show this passage\n\n“obviously misquote[s] [or] inaccurately report[s] what [Mr.] Pogi stated.” Aplt.\n\nReply Br. at 5. Further, it does not suggest the Defendants published with “a high\n\ndegree of awareness of . . . probable falsity.” Garrison, 379 U.S. at 74.\n\n In the interview recording, Mr. Pogi said he lived on Mr. Talley’s property\n\nrent-free. Pogi Interview at 17:32-18:13. He also stated, as the Defendants reported,\n\n“It’s a big deal. I mean, I was the starting quarterback.” Id. at 23:20-25. Nowhere\n\nin the interview does Mr. Pogi state that he worked “extremely hard in exchange for\n\nrent,” as Mr. Talley insists. Aplt. Reply Br. at 5.\n\n\n\n\n 37\n\f After reviewing the entire recording of Mr. Evans’s interview with Mr. Pogi,\n\nwe found only one statement—“I did a lot,” Pogi Interview at 12:02-12:04—that\n\ncould possibly indicate that Mr. Pogi worked on the ranch at all. But that statement\n\nis ambiguous. Mr. Pogi did not specifically state what it was he “did a lot.” Further,\n\nhe made the statement after telling Mr. Evans that he was “on the road a lot to speak”\n\nand had participated in “a lot” of speaking engagements. Id. at 10:00-11:51. It is\n\ntherefore possible the statement referenced his speaking engagements rather than\n\nranch work. Further, when Mr. Evans prompted, “You lived [on the ranch], but you\n\nnever, you never worked—,” Mr. Pogi responded, “I ne—I didn’t, I didn’t do\n\nanything like—.” Id. at 12:08-12:11. And a few questions later, Mr. Pogi insisted he\n\n“had no arrangement” with Mr. Talley. Id. at 17:29-17:30.\n\n The interview recording thus includes no definitive statement that Mr. Pogi\n\nworked on the ranch. Although his statement that he “did a lot” might be understood\n\nto mean he worked, it could reasonably be interpreted as a reference to speaking\n\nengagements. At most, the Defendants misinterpreted the statement, but a\n\ndefendant’s misinterpretation of source material that “bristle[s] with ambiguities”\n\ndoes not constitute actual malice. Pape, 401 U.S. at 290 (holding that when faced\n\nwith ambiguous source material, a defendant’s “deliberate choice of [one]\n\n\n\n\n 38\n\finterpretation, though arguably reflecting a misconception, [is] not enough to create a\n\njury issue of ‘malice’ under New York Times”).21\n\n Accordingly, even if the Defendants misinterpreted Mr. Pogi’s statement that\n\nhe “did a lot,” their misunderstanding would not establish actual malice. The\n\nevidence does not support Mr. Talley’s contention that the Defendants “blatantly\n\nmisquoted what Aso Pogi said,” Aplt. Reply Br. at 5, or show they published\n\nstatements about Mr. Pogi with reckless disregard for the truth.22\n\n\n 21\n See also Orr v. Argus-Press Co., 586 F.2d 1108, 1116 (6th Cir. 1978)\n(finding no actual malice when defendants published a rational interpretation of\nambiguous source material); Simmons Ford, Inc. v. Consumers Union of U.S., Inc.,\n516 F. Supp. 742, 751-52 (S.D.N.Y. 1981) (finding no actual malice when defendants\npublished a reasonable but mistaken interpretation of a regulation that “hardly\nqualify[ed] as a model of clarity”); Farrakhan v. N.Y.P. Holdings, Inc., 168 Misc. 2d\n536, 542 (N.Y. Sup. Ct. 1995) (concluding that “even if defendants misinterpreted\n[an interviewee’s] statement, such misinterpretation does not arise to a level of\nconstitutional malice”); Suozzi v. Parente, 616 N.Y.S.2d 355, 359 (N.Y. App. Div.\n1994) (noting that actual malice cannot “be founded on the misinterpretation of a\nsource or the resolution of an ambiguity adversely to the plaintiff”).\n 22\n Mr. Talley’s insistence that the “Defendants blatantly misquoted what Aso\nPogi said,” Aplt. Reply Br. at 5, may be based on an interview that Chuck Smrt,\nOSU’s outside compliance consultant, conducted with Mr. Pogi during the NCAA’s\ninvestigation of the OSU football program after the SI article series was published.\nIn this interview, Mr. Pogi claimed he “worked pretty hard on [Mr. Talley’s] farm”\nand that there was “a lost [sic] land to keep up as far as cutting grass, as far as\ncleaning the pool and just doing quite a bit of things. Feeding the animals, it was\nevery single day.” Aplt. App., Vol. IV at A853. These statements support Mr.\nTalley’s contention that Mr. Pogi did, in fact, work in exchange for lodging. But\nbecause this interview occurred after the SI article was published, it does not prove\nthe Defendants deliberately misquoted Mr. Pogi—or otherwise acted with actual\nmalice—at the time of the original publication. See Bose, 466 U.S. at 494 (noting\nthat “the actual-malice determination rests entirely on an evaluation of [the author’s]\nstate of mind when he wrote his initial report” (emphasis added)).\n 39\n\f b. Payment for speaking engagements\n\n Mr. Talley also argues the Defendants acted with actual malice when they\n\nreported he paid players to speak at events “in violation of NCAA rules and OSU\n\npolicy.” Aplt. Br. at 16. According to Mr. Talley, “Defendants were made aware . . .\n\nthat ‘speaking’ meant reimbursement for gas and food” but nonetheless “deliberately\n\nchose to disregard its true meaning in order to portray [Mr. Talley] as paying in\n\nviolation of rules.” Id. at 18. Mr. Talley also argues that “Defendants never had\n\nreason to believe [Mr. Talley] was breaking the rules or illegally paying athletes.”23\n\nId.\n\n These arguments, too, are unpersuasive. Although some players insisted they\n\nwere reimbursed only for expenses, many (including Mr. Johnson, Mr. Brown, Mr.\n\nWright, and Mr. Shaw) admitted that they or others they knew had received speaking\n\n\n\n\n 23\n To support his argument, Mr. Talley adds that “Defendants knew [the]\nNCAA investigated the subject and never determined any violation of the rules by\n[Mr. Talley].” Aplt. Br. at 18. This argument is unpersuasive. The NCAA\ninvestigated the OSU football program after the Defendants published “The Dirty\nGame.” See, e.g., Aplt. App., Vol. III at A607 (transcript of NCAA investigatory\ninterview with OSU officials, dated October 17, 2013). As noted above, the actual\nmalice issue focuses on what the author knew (or did not know) at the time of\npublication, Bose, 466 U.S. at 494, and “[e]vidence concerning events after an article\nhas been printed and distributed, has little, if any, bearing on that issue,” Forbes Inc.\nv. Granada Biosciences, Inc., 124 S.W.3d 167, 174 (Tex. 2003). If, as Mr. Talley\nclaims, the NCAA found that his payments did not violate any rules, those findings\nwere not available to the Defendants when they published the article and could not\nhave influenced their state of mind at the time of publication. The NCAA\ninvestigation is thus irrelevant.\n\n 40\n\ffees. Mr. Johnson, for example, said Mr. Talley once paid him 100 dollars to speak\n\nfor 20 minutes. Johnson Interview at 2:42-3:02. Even if Mr. Talley paid speaking\n\nfees to certain players and not others, the Defendants still had grounds to believe and\n\nreport that at least some players received money beyond simple reimbursement. That\n\nsome players denied receiving speaking fees or claimed they were only reimbursed\n\nfor expenses does not prove the Defendants “in fact entertained serious doubts” about\n\nthe players who reported otherwise. St. Amant, 390 U.S. at 731; Colbert, 747 P.2d\n\nat 291.\n\n In addition, Mr. Schecter’s notes from his interview with Mr. Talley reflect\n\nthat Mr. Talley admitted to paying speaking fees.24 Shortly after meeting with Mr.\n\nTalley, Mr. Schecter sent Mr. Dohrmann an e-mail listing “John Talley[’s] Responses\n\n\n\n\n 24\n Although Mr. Schecter recorded the interview with Mr. Talley, the audio file\nwas corrupted. See supra note 6. Accordingly, Mr. Schecter’s e-mail to Mr. Dohrmann\nis the only recorded source of information about the interview. In his affidavit, Mr.\nSchecter stated that he drafted this e-mail shortly after speaking with Mr. Talley: “When\nI got back to my hotel, I listened to the recording, then made notes, including writing\ndown some direct quotes, as I re-listened to the audio. I emailed my notes to [Mr.]\nDohrmann and [Mr.] Evans.” Aplt. App., Vol. II at A443. He also testified at his\ndeposition that he listened to the interview recording “[i]mmediately after I got back to\nmy hotel room . . . I would say within an hour after I finished my conversation with Mr.\nTalley.” Id. at A411.\n During his deposition, Mr. Talley claimed Mr. Schecter “was in a hurry” and\n“didn’t really give [him] an opportunity to” explain himself fully during the interview.\nAplt. App., Vol I at A204. But Mr. Talley did not challenge any of the information or\nquotations contained in the e-mail. In fact, Mr. Talley reviewed the entire e-mail and\nconfirmed he made all the statements that Mr. Schecter attributed to him. Id. at A202-05.\n\n 41\n\fto allegations we have against him.” Aplt. App., Vol. II at A520. On the topic of\n\n“[p]aying players for speaking engagements,” Mr. Schecter wrote the following:\n\n [Mr. Talley said:] “It depends on . . . there’s a\n NCAA rule that if they’re paying us . . . and most of the\n time it’s for team building activities. It’s not just\n speaking. But we have done some school assemblies. Last\n year we did four all sports banquets. And if the school is\n used to paying someone than [sic] it’s legal to get paid.\n But there’s a fine line.”\n\n Talley says he ran everything (the jobs and the\n speaking gigs) through the associate compliance director\n who is assigned to the football team.\n\n “If [players] were allowed to be paid (for speaking\n engagements) they were paid. We’ve spoken in\n churches.[”] (They got paid for speaking in churches\n “only if the churches paid someone before.”) Talley says a\n typical speaking fee would be $25-$50. “I can always pay\n for if they’re driving their car we can pay for gas and stuff\n like that.”\n\n Players said it was $100 or more per speaking\n engagement. “It depends on where we were going,” Talley\n said. “I’m not saying they couldn’t because it was a long\n time ago, but usually it was not that much.”\n\nId. at A521. Although it is possible Mr. Schecter and Mr. Dohrmann misunderstood\n\nor misinterpreted Mr. Talley’s comments, these interview notes suggest the\n\nDefendants had a reasonable basis to believe Mr. Talley paid speaking fees to some\n\nplayers.25 Further, as discussed above, a defendant’s misinterpretation of source\n\n\n 25\n During his deposition, Mr. Talley acknowledged that his statements to Mr.\nSchecter were ambiguous. When asked, “Do you find anything in [Mr.] Schecter’s\nemail that would suggest you made [the] distinction [between speaking and team\nbuilding] to him?,” Mr. Talley responded, “Yes and no. Yes, I was trying to. No, he\n 42\n\fmaterial does not necessarily establish actual malice. Pape, 401 U.S. at 290. Thus,\n\neven if the Defendants misunderstood Mr. Talley’s claim that “[players] were paid”\n\nto mean speaking fees rather than reimbursements, that misunderstanding would not\n\nprove they published with actual malice.\n\n In sum, although some players claimed they did not receive money to speak,\n\nmultiple players reported that Mr. Talley arranged paid speaking engagements.\n\nFurther, notes from Mr. Schecter’s interview with Mr. Talley suggest that Mr. Talley\n\nadmitted to paying speaking fees. In publishing these allegations, the Defendants did\n\nnot show reckless disregard for the truth. Rather, they reported information that\n\nmultiple sources confirmed and corroborated. The record does not suggest the\n\nDefendants “in fact entertained serious doubts as to the truth of [their] publication,”\n\nSt. Amant, 390 U.S. at 731; Colbert, 747 P.2d at 291, and Mr. Talley identifies no\n\nevidence to demonstrate with “convincing clarity” that the Defendants reported about\n\nhis paying players for speaking engagements with actual malice, New York Times,\n\n376 U.S. at 286-87.\n\n c. Credibility of article sources\n\n Mr. Talley contends the Defendants demonstrated actual malice by “[seeking]\n\nout non-credible, untrustworthy, and troubled sources,” Aplt. Br. at 21, and by\n\n\n\nwas in a hurry to get out of my van. So he didn’t really give me an opportunity to.\n. . . I was trying to clarify that I reimburse people for going to speak. . . . But he\ndidn’t stay around long enough to hear it.” Aplt. App., Vol. I at A204.\n\n 43\n\finterviewing and quoting OSU players of “suspect veracity,” Aplt. Reply Br. at 8.\n\nHe notes that some of the players featured in the article had “troubled histor[ies] . . .\n\nincluding drug usage, scholastic problems with OSU, and criminal issues.” Aplt. Br.\n\nat 14. He claims the Defendants’ “conscious decision to feature those interviewees in\n\nthe article . . . is evidence of Defendants’ malicious intent.” Aplt. Reply Br. at 8.\n\nWe disagree.\n\n Although the record shows the Defendants interviewed and quoted some OSU\n\nplayers who used drugs or had criminal records,26 “[s]ources need not be paragons of\n\nvirtue for journalists safely to rely on them.” 1 Robert D. Sack, Sack on Defamation:\n\nLibel, Slander, and Related Problems §5:5.2(C) at 5-109 (5th ed. 2017). Courts have\n\nconsistently held that reliance on tainted or troubled sources does not alone establish\n\nactual malice. See, e.g., Pemberton v. Birmingham News Co., 482 So. 2d 257, 266\n\n\n\n\n 26\n For their segment on Mr. Talley, the Defendants relied primarily on\nstatements and interviews from Mr. Girtman, Mr. Shaw, Mr. Mack, Mr. Brown, Mr.\nWright, Mr. Johnson, Mr. Lawson-Kennedy, Mr. Pogi, and Mr. Carter. The\ninterviews revealed that several of these sources had substance abuse problems: Mr.\nGirtman used drugs and failed drug tests, Aplt. App., Vol. III at A801; Mr. Johnson\nadmitted to smoking marijuana, Aplt. App., Vol. II at A490, A492-93; Mr. Shaw\nfailed drug tests and used a masking agent to conceal his marijuana use, id. at A501;\nand Mr. Mack and Mr. Brown either used drugs or knew of other players who did,\nid.at A389, A464. The record also suggests at least two of these players may have\nhad criminal records. Mr. Talley’s original complaint stated that Mr. Shaw had been\nconvicted of larceny and burglary, though it is not clear that the Defendants knew\nthis when they published their article. Aplt. App., Vol. IV at A909. In addition, the\ncall between Mr. Evans and Mr. Wright was timed and took place over a controlled\nline which indicates Mr. Wright was either in jail or prison. Evans Wright Interview\nat 10:15-10:39.\n 44\n\f(Ala. 1985) (finding that defendant’s reliance on statements from an ex-convict was\n\ninsufficient to show actual malice); Secord v. Cockburn, 747 F. Supp. 779, 794\n\n(D.D.C. 1990) (holding that “[t]he use of convicted felons cannot alone constitute a\n\nfact of actual malice”). The fact that some of the Defendants’ sources were not\n\n“paragons of virtue” is thus insufficient to show actual malice. Sack, §5:5.2(C) at 5-\n\n109.\n\n Courts also have noted that “newspaper investigation of reports of corruption\n\nmust often obtain first-hand corroboration from those present in the barrooms or\n\ngambling houses, rather than from citizens who spend their time only at home, in\n\nchurch, or at work in less colorful occupations.” Kidder v. Anderson, 354 So.2d 1306\n\n(La. 1978). Here, the five-article series reported on drug use, financial misconduct,\n\nand academic dishonesty in the OSU football program. To prepare this report, the\n\nDefendants necessarily had to rely on sources who may have participated in these\n\nactivities. Rather than demonstrating that the Defendants published with actual\n\nmalice, this shows they sought information from the sources who were in the best\n\nposition to describe these possible features of the OSU program. See Pemberton, 482\n\nSo. 2d at 266 (noting that “the fact that [a source] was an ex[-]convict did not\n\ndiminish his credibility . . . but rather made it more probable that he would have\n\ninside information” that could aid the defendants’ investigation).\n\n Although some of the interviewees who provided information about Mr. Talley\n\nused drugs or had criminal records, the reporters stated they “did not observe any . . .\n\n 45\n\ffacts that would cause [them] to question [the players’] credibility.” Aplt. App., Vol.\n\nII at A440 (Dohrmann Affidavit); see id. at A390-91 (Evans Affidavit). The SI\n\nreporters interviewed multiple individuals—including some who did not have\n\ntroubled pasts—and stated that, though “players spoke to [them] independently, at\n\ndifferent times and different places, . . . the facts those players provided were\n\nconsistent with and corroborative of one another.” Id. at A439-40 (Dohrmann\n\nAffidavit); see id. at A390-91 (Evans Affidavit). “That these . . . sources\n\ncorroborated each other’s allegations sufficiently establishes [that the Defendants]\n\ndispelled [any of their] doubts” about the players’ veracity. Spacecon, 713 F.3d at\n\n1046. Mr. Talley thus has not shown there were “obvious reasons to doubt the\n\nveracity” of the player sources. St. Amant, 390 U.S. at 732.\n\n In sum, Mr. Talley has failed to show the Defendants’ use of “troubled” or\n\ntainted sources demonstrated actual malice. Aplt. Br. at 14. The record shows the\n\npassages relating to Mr. Talley were based on “sources which were not believed to be\n\nfalse.” Rosanova v. Playboy Enters., Inc., 580 F.2d 859, 862 (5th Cir. 1978). Unlike\n\nthe defendants in Butts, the Defendants did not rely on a single, questionable source\n\nwithout fact-checking, interviewing additional witnesses, or seeking independent\n\nsupport. 388 U.S. at 157-58. And this case has no resemblance to Harte-Hanks,\n\nwhere the defendants knew the facts in their publication “had been denied . . . by five\n\nother witnesses before the story was published.” 491 U.S. at 691. Although the\n\narticle here quoted some of the players who had “troubled histor[ies],” Aplt. Br. at\n\n 46\n\f14, Mr. Talley has not shown the Defendants had “obvious reasons to doubt the\n\nveracity of the [players] or the accuracy of [their] reports,” Harte-Hanks, 491 U.S. at\n\n688 (quotations omitted). Nor has he shown that the players’ drug use or other\n\nmisconduct gave the Defendants a “high degree of awareness of probable falsity\n\nor . . . serious doubts as to the truth of [their] publication.” Colbert, 747 P.2d at 291.\n\n d. Slant, bias, motive, and omissions\n\n Mr. Talley argues the Defendants exhibited actual malice by presenting a\n\nslanted, biased, and “sensationalized” narrative. Aplt. Br. at 4. He contends the\n\nDefendants crafted their story to fit their “own investments and motives,” id. at 13,\n\nand demonstrated actual malice by “specifically target[ing],” Aplt. Reply Br. at 8, his\n\nreputation “as a respected pastor and mentor,” id. at 2. He also claims the\n\nDefendants “omit[ted] material statements.” Aplt. Br. at 21. These arguments also\n\nfail.\n\n i. Slant and bias\n\n Mr. Talley suggests the “Defendants sought a certain narrative from\n\ninterviewees,” id. at 14, and “achieved the story they desired to portray,” id., by\n\n“seek[ing] out biased individuals who would provide a sensational story,” id. at 4.\n\nBut he provides no concrete supporting evidence to show this was the case. Even if\n\nhe could, it would not show the Defendants published with actual malice.\n\n Although the Defendants may have developed a theme for their article—their\n\ne-mail correspondence, for example, includes a discussion of whether a particular\n\n 47\n\fplayer’s “experience fits our narrative,” Aplt. App., Vol. II at A498—that alone does\n\nnot show they doubted the truth of their publication. Indeed, the Defendants, not Mr.\n\nTalley, are entitled to choose their theme. It is the “function of editors” to decide\n\n“[t]he choice of material to go into a newspaper.” Miami Herald Publ’g Co. v.\n\nTornillo, 418 U.S. 241, 255 (1974). Further, “[t]he fact that a commentary is one\n\nsided . . . has no tendency to prove that the publisher believed it to be false.”\n\nMcFarlane v. Esquire Magazine, 74 F.3d 1296, 1307 (D.C. Cir. 1996). Thus, to the\n\nextent Mr. Talley could provide evidence to show the Defendants wrote an article\n\nconsistent with a theme or narrative, he has not established they published with actual\n\nmalice.\n\n ii. Motive\n\n Mr. Talley contends the Defendants had “independent knowledge of [Mr.\n\nTalley’s] standing in the community,” Aplt. Br. at 20, and “specifically targeted” his\n\n“reputation for honesty,” Aplt. Reply Br. at 8. He further claims the Defendants had\n\n“obvious reasons to doubt the veracity of the . . . information discovered in their\n\ninvestigations . . . due to . . . [their] own investments and motives.” Aplt. Br. at 13.\n\n Despite his contention that the Defendants published with improper motives,\n\nMr. Talley does not specify what those “investments and motives” might have been.\n\nId. He also does not identify any evidence that the Defendants “specifically targeted”\n\nhim. Aplt. Reply Br. at 8. The Defendants spent only a fraction (442 words) of their\n\n20,000-word, five-part series discussing Mr. Talley, which suggests their purpose\n\n 48\n\fwas not to tarnish his reputation. But even if the Defendants “targeted” Mr. Talley,\n\nthat would not prove they had doubts about the article’s veracity or published with\n\nactual malice. See, e.g., Spacecon, 713 F.3d 1028 (noting that “a publisher’s\n\nadversarial stance . . . is not necessarily indicative of actual malice”) (quotations\n\nomitted).\n\n Although “[t]he motivation behind a publication is a factor to consider,” id. at\n\n1042, “courts must be careful not to place too much reliance on [motive],” Harte-\n\nHanks, 491 U.S. at 668; see also Old Dominion Branch No. 496, Nat’l Ass’n of Letter\n\nCarriers v. Austin, 418 U.S. 264, 281-82 (stating that “ill will toward the plaintiff, or\n\nbad motives are not elements of the New York Times standard”). As this court said in\n\nSpacecon, “[E]vidence of [defendant’s] . . . bias is not enough to show he acted with\n\nactual malice.” 713 F.3d at 1043; see also Harte-Hanks, 491 U.S. at 665;\n\nTavoulareas v. Piro, 817 F.2d 762, 795 (D.C. Cir. 1987) (stating a publisher’s\n\n“adversarial stance” may be “fully consistent with professional, investigative\n\nreporting” and is not necessarily “indicative of actual malice”) (quotations omitted).\n\nMr. Talley has not identified evidence of the Defendants’ bias against him, much less\n\nshown that bias established actual malice.\n\n iii. Omissions\n\n Mr. Talley briefly argues the Defendants showed actual malice by “omitting\n\nmaterial statements.” Aplt. Br. at 14. Mr. Talley does not identify in his briefing\n\nwhat, specifically, the Defendants omitted from their article. Even if he had done so,\n\n 49\n\fhe has not shown how omissions would prove the Defendants published with actual\n\nmalice.27 Courts have noted that “the author of an article will have to choose which\n\nfacts to include and which to omit,” because “[i]t is impossible to print all of the facts\n\non which an opinion or belief is based, especially when an article comprises a critical\n\nanalysis.” Reliance Ins. Co. v. Barron’s, 442 F. Supp. 1341, 1352 (S.D.N.Y. 1977).\n\nAccordingly, “recovery for a false light tort may not be predicated on . . . [a\n\ndefendant’s failure] to include additional facts which might have cast the plaintiff in\n\na more favorable or balanced light.” Machleder v. Diaz, 801 F.2d 46, 55 (2d Cir.\n\n1986); see also Reliance Ins. Co., 442 F. Supp. at 1352 (citations omitted) (finding\n\nthat “selective omission of relevant data” does not provide “circumstantial evidence\n\nof defendants’ actual malice”); Pape, 401 U.S. at 282, 290-92 (holding that a\n\npublisher did not demonstrate actual malice by omitting the word “alleged” from its\n\ndescription of a legal complaint against police officers). Mr. Talley has not shown\n\nthe Defendants’ decision to publish certain facts while omitting others demonstrates\n\nactual malice.\n\n\n\n\n 27\n In his initial complaint, Mr. Talley argued the Defendants “omitt[ed]\nmaterial facts about the true, and proper nature of Aso Pogi’s temporary living\narrangements with [Mr. Talley’s] family.” Aplt. App., Vol. I at A19. And in\nresponse to their motion for summary judgment, he argued the Defendants “omitted\nplayers who reported never having seen or heard of players being paid for speaking\nengagements.” Aplt. App., Vol. III at A680. On appeal, however, Mr. Talley makes\nonly general allegations about omissions and does not identify any specific facts or\nstatements that the Defendants excluded from their article.\n\n 50\n\f e. Error(s)\n\n Mr. Talley contends the Defendants demonstrated actual malice by publishing\n\ninaccurate information. See Aplt. Br. at 4, 20. But other than his misplaced claim\n\nabout misquoting Mr. Pogi, which we addressed above, Mr. Talley does not identify\n\nany specific errors or inaccuracies in his appellate briefs.28 This argument is\n\ntherefore inadequately briefed. Moreover, the record shows the Defendants fact-\n\nchecked and verified the information they used in their article. Without evidence of\n\nany knowing or reckless falsehood, Mr. Talley cannot show the Defendants’ alleged,\n\nunspecified mistakes were anything more than negligent, which is “insufficient to\n\nshow the recklessness that is required for a finding of actual malice.” New York\n\nTimes, 376 U.S. at 288.\n\n Relatedly, the Supreme Court has held that “failure to investigate . . . is not\n\nsufficient to establish reckless disregard.” Harte-Hanks, 491 U.S. at 688. A plaintiff\n\ncannot demonstrate malice “merely by showing that the publication was erroneous.”\n\nHerbert, 992 P.2d at 329 (citing Gertz, 418 U.S. at 340-41; St. Amant, 390 U.S. at\n\n\n\n 28\n In his initial complaint, Mr. Talley alleged the Defendants failed to check\nfacts about Mr. Carter’s academic record. See Aplt. App., Vol. IV at A910. Mr.\nTalley does not raise this argument on appeal, so we do not address it here. See City\nof Colo. Springs v. Solis, 589 F.3d 1121, 1135 n.5 (“[A]rguments not raised in the\nopening brief are waived.”); Bronson v. Swensen, 500 F.3d 1099, 1104 (10th Cir.\n2007) (“[W]e routinely have declined to consider arguments that are not raised, or are\ninadequately presented, in an appellant’s opening brief.”)\n\n\n\n 51\n\f732; New York Times, 376 U.S. at 281). Thus, Mr. Talley’s general allegation about\n\ninaccuracy does not show the Defendants “had a high degree of awareness of\n\nprobable falsity or in fact entertained serious doubts as to the truth of the\n\npublication.” Colbert, 747 P.2d at 291.\n\n * * * *\n\n The Oklahoma Supreme Court described “[t]he ‘actual malice’ standard [as] a\n\nformidable one.” Herbert, 992 P.2d at 328. Mr. Talley has failed to show he could\n\nsatisfy it here. The Defendants were thorough in their investigation, editing, and\n\nreview. Mr. Talley has not shown they published with “knowledge that [their\n\nstatements were] false or with reckless disregard of whether [they were] false or not.”\n\nNew York Times, 376 U.S. at 280. He cannot show “with convincing clarity” that the\n\nDefendants acted with actual malice. Colbert, 747 P.2d at 291.\n\n III. CONCLUSION\n\n We affirm the district court’s entry of summary judgment in favor of the\n\nDefendants.\n\n\n\n\n 52\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: John Thomas TALLEY, Plaintiff - Appellant, v. TIME, INC., D/B/A Sports Illustrated Magazine; George Dohrmann ; Thayer Evans, Defendants - Appellees.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-08\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 8, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n JOHN THOMAS TALLEY,\\n\\n Plaintiff - Appellant,\\n\\n v. No. 18-6169\\n\\n TIME, INC., d/b/a Sports Illustrated\\n Magazine; GEORGE DOHRMANN;\\n THAYER EVANS,\\n\\n Defendants - Appellees.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the Western District of Oklahoma\\n (D.C. No. 5:14-CV-00853-D)\\n _________________________________\\n\\nRaymond S. Allred (Gary L. Richardson, Charles L. Richardson, Alisa G. Hopkins, and\\nLia R. Rottman, with him on the briefs), of Richardson Richardson Boudreaux, PPLC,\\nTulsa, Oklahoma, for Plaintiff - Appellant.\\n\\nRobert D. Nelon (Jon Epstein, with him on the brief), of Hall, Estill, Hardwick, Gable,\\nGolden & Nelson, P.C., Oklahoma City, Oklahoma, for Defendants - Appellees.\\n _________________________________\\n\\nBefore MATHESON, MURPHY, and EID, Circuit Judges.\\n _________________________________\\n\\nMATHESON, Circuit Judge.\\n _________________________________\\n\\f In 2013, Sports Illustrated magazine (“SI”) published a five-article series on\\n\\nthe Oklahoma State University (“OSU”) football program. The series explored\\n\\n“illicit payments” and other “extreme measures” OSU used to recruit and retain top\\n\\nplayers. Aplt. App., Vol. II at A446; Aplt. App., Vol. III at A699. The first article in\\n\\nthe series, titled “The Money,” described an assistant coach who offered “de facto\\n\\nbonus[es] . . . based on performances on the field.” Aplt. App., Vol. II at A448. It\\n\\nalso discussed boosters and coaches who made “direct payments to players . . .\\n\\nindependent of performance,” id., and “funnel[ed] money to players through dubious\\n\\nwork arrangements,” id. at A452.1 And it briefly profiled John Talley, a booster who\\n\\n“had been close to the football program since at least 2002” and who allegedly\\n\\n“grossly overpaid [OSU players] for jobs they did or compensated them for jobs they\\n\\ndidn’t do.” Id.\\n\\n Mr. Talley sued Time, Inc., which publishes SI, and SI reporters Thayer Evans\\n\\nand George Dohrmann (collectively, “the Defendants”) in state court, claiming that\\n\\nthe article placed him in a false light and invaded his privacy. Invoking diversity\\n\\njurisdiction under 28 U.S.C. § 1332, the Defendants removed the case to the United\\n\\nStates District Court for the Western District of Oklahoma. After discovery, the\\n\\n\\n\\n\\n 1\\n According to the National Collegiate Athletic Association (“NCAA”), a\\nbooster—or “representative[] of [an] institution’s athletic interests”—is an individual\\nwho supports “teams and athletics departments through donations of time and\\nfinancial resources which help student-athletes succeed on and off the playing field.”\\nSee https://perma.cc/R96W-G7AZ.\\n 2\\n\\fDefendants moved for summary judgment. The district court granted the motion.\\n\\nMr. Talley timely appealed.\\n\\n Exercising jurisdiction under 28 U.S.C. § 1291, we affirm because Mr. Talley\\n\\nhas not demonstrated a genuine issue of material fact as to whether the Defendants\\n\\nacted with actual malice, an element of Oklahoma’s false light tort.\\n\\n I. BACKGROUND\\n A. Oklahoma’s False Light Tort2\\n\\n Oklahoma recognizes the common law tort of false light invasion of privacy.\\n\\nIt has adopted the Restatement (Second) of Torts § 652E, which reads:\\n\\n One who gives publicity to a matter concerning another\\n that places the other before the public in a false light is\\n subject to liability to the other for invasion of his privacy,\\n if\\n\\n (a) the false light in which the other was placed would be\\n highly offensive to a reasonable person, and\\n\\n (b) the actor had knowledge of or acted in reckless\\n disregard as to the falsity of the publicized matter and the\\n false light in which the other would be placed.\\n\\nSee McCormack v. Okla. Publ’g Co., 613 P.2d 737, 740 (Okla. 1980) (recognizing\\n\\n“the tort of invasion of privacy . . . as set out in the Restatement”); Colbert v. World\\n\\nPubl’g Co., 747 P.2d 286, 290 (Okla. 1987) (noting that the Oklahoma Supreme\\n\\n\\n 2\\n Because federal court jurisdiction in this case is based on the diversity of\\ncitizenship between the parties, 28 U.S.C. § 1332, we apply the substantive law of\\nthe forum state—Oklahoma. See Haberman v. Hartford Ins. Grp., 443 F.3d 1257,\\n1264 (10th Cir. 2006) (“In diversity cases, the substantive law of the forum state\\ngoverns the analysis of the underlying claims . . . .”).\\n 3\\n\\fCourt has “specifically adopt[ed] the treatment of [invasion of privacy] in the\\n\\nRestatement of the Law of Torts (Second)”).\\n\\n False light plaintiffs must prove three elements:\\n\\n (1) “the defendant gave publicity to a matter concerning\\n the plaintiff that placed the plaintiff before the public in a\\n false light,”\\n\\n (2) “the false light in which the plaintiff was placed would\\n be highly offensive to a reasonable person,” and\\n\\n (3) “the defendant had knowledge of or acted in reckless\\n disregard as to the falsity of the publicized matter and the\\n false light in which the other would be placed.”\\n\\nMitchell v. Griffin Television, LLC, 60 P.3d 1058, 1061 (Okla. Civ. App. 2002).\\n\\n Oklahoma courts have specified that the third element—“knowledge of or . . .\\n\\nreckless disregard as to the falsity of the publicized matter”—is identical to the actual\\n\\nmalice standard articulated in New York Times Co. v. Sullivan, 376 U.S. 254 (1964).\\n\\nSee Herbert v. Okla. Christian Coal., 992 P.2d 322, 328 (Okla. 1999) (quoting New\\n\\nYork Times, 376 U.S. at 280).3 We discuss this standard in greater detail below.\\n\\n B. Factual Background\\n\\n SI is a sports magazine published by Time, Inc. Aplt. App. Vol. I at A85. In\\n\\nearly 2012, Mr. Evans, who was then a reporter at Fox Sports, learned that the OSU\\n\\nfootball program might have been using financial inducements to attract and retain\\n\\n\\n 3\\n Because Oklahoma has explicitly adopted the actual malice standard for false\\nlight invasion of privacy claims, the following analysis uses the term “actual malice”\\nas shorthand for the “knowledge of or . . . reckless disregard” element of the false\\nlight tort. Mitchell, 60 P.3d at 1061.\\n 4\\n\\fplayers. Id. at A86; Aplt. App., Vol. II at A388. That fall, after taking a job at SI,\\n\\nMr. Evans shared this information with SI’s Executive Editor B.J. Schecter. Aplt.\\n\\nApp., Vol. II at A388. Mr. Schecter asked Mr. Dohrmann if he would be interested\\n\\nin working with Mr. Evans on a story about the OSU program. Id. When Mr.\\n\\nDohrmann agreed, SI began a 10-month investigation into OSU’s recruiting and\\n\\nretention practices. Aplt. App., Vol. I at A87; Aplt. App., Vol. II at A388, A438.\\n\\nMr. Schecter led the investigation, which involved dozens of interviews with OSU\\n\\nplayers, coaches, and boosters. Aplt. App., Vol. I at A86-88; Aplt. App., Vol. II at\\n\\nA438, A442.\\n\\n In September 2013, SI published its findings in a five-part article series titled\\n\\n“The Dirty Game.” Aplt. App., Vol. II at A445-82. Below, we quote the passage\\n\\nabout Mr. Talley, which appeared in the first article of the series. We then describe\\n\\nthe steps SI took to investigate, research, draft, and edit the Talley passage.\\n\\n The Article\\n\\n Mr. Dohrmann and Mr. Evans co-authored “The Dirty Game” using\\n\\ninformation they gathered during SI’s investigation. Aplt. App., Vol. I at A87-88;\\n\\nAplt. App., Vol. III at A770. The first article of the series—a roughly 5,000-word\\n\\npiece titled “The Money”—described gratuities and inducements that OSU used to\\n\\nattract and retain top players. Aplt. App., Vol. II at A445-53. It detailed financial\\n\\nbenefits—including payments for performance on the field—that coaches offered to\\n\\nplayers on the team. Id. It also described how several “boosters,” including Mr.\\n\\n 5\\n\\fTalley, “funnel[ed] money to players,” id. at A452, by paying them “for little or no\\n\\nwork,” id.\\n\\n Mr. Talley was the North Central Area Director of the Fellowship of Christian\\n\\nAthletes (“FCA”).4 Id. at A452; Aplt. App., Vol. I at A135. The 442-word passage\\n\\nabout him reads, in full, as follows:\\n\\n According to multiple players, though, the\\n generosity of [booster Kay] Norris, who died of lung\\n cancer in 2006, was exceeded by that of other [OSU]\\n Cowboys supporters. John Talley, an area director of the\\n Fellowship of Christian Athletes, had been close to the\\n football program since at least 2002, when his son, Saul,\\n was a walk-on long snapper. “John Talley was the hot\\n name around campus,” [player Rodrick] Johnson says. “If\\n you needed a job, call John Talley.”\\n\\n [Players Fath’] Carter, [Brad] Girtman, [Rodrick]\\n Johnson and Thomas Wright each say that Talley either\\n grossly overpaid them for jobs they did or compensated\\n them for jobs they didn’t do. They allege that numerous\\n other players benefited from Talley's generosity too.\\n Girtman says Talley paid him $1,500 to $2,000 every two\\n weeks during one summer to work on his horse ranch, far\\n more than the job was worth. Talley could also be counted\\n on to set up speaking gigs for players, paying $100 for a\\n 15- to 20-minute talk. “You might get more depending on\\n who you were,” says Shaw. Carter says he and a few other\\n players were once paid by Talley to help shoe horses.\\n Asked if the players did the work, Carter says, “Are you\\n kidding? Most of us hadn’t even seen a horse before.”\\n\\n Quarterback Aso Pogi (1999 to 2002) says he and\\n another player lived at Talley’s ranch one summer rent-\\n 4\\n In his deposition, Mr. Talley explained that the FCA’s mission is “[t]o reach\\ncoaches, student athletes, and all who they influence, to give the opportunity to\\nreceive Jesus Christ as Lord and Savior, and to serve Him in their relationships and in\\nthe church.” Aplt. App., Vol. I at A136.\\n 6\\n\\f free. In retrospect Pogi says, “It’s a big deal. I was the\\n starting quarterback.” (Talley says that Pogi lived at his\\n ranch and had to work to cover his rent; Pogi denies that\\n he did any work.)\\n\\n Talley says that he sometimes paid players a fee for\\n speaking engagements and that they frequently did work\\n on his ranch, noting he always paid an hourly wage. He\\n also says he cleared the speaking fees and the hourly\\n employment through the university’s compliance office. “I\\n have paid lots of players to work on my ranch,” Talley\\n says. “But I would never pay someone not to work.”\\n\\n OSU compliance director Kevin Fite says of the\\n speaking engagements arranged by Talley, “They were not\\n cleared through our office as paid speaking engagements.\\n In fact, two of my staff members indicated to me that they\\n had had conversations with John and told him you cannot\\n pay for speaking engagements. If you want to employ our\\n student-athletes for other things, that’s fine, but you cannot\\n pay them for speaking engagements.”\\n\\n While Fite says the school cleared Talley to employ\\n athletes on his ranch, he acknowledges that Talley’s\\n paying in cash “is not something I am comfortable with. I\\n think that’s a concern. I would prefer to see it done a\\n different way.”\\n\\nGeorge Dohrmann & Thayer Evans, Special Report on Oklahoma State Football: Part 1\\n\\n– The Money, Sports Illustrated, Sept. 16, 2013, at 39-40; Aplt. App., Vol. II at A452.\\n\\n The Reporting Process\\n\\n As previously noted, SI began investigating the OSU football team in late\\n\\n2012. Aplt. App., Vol. I at A86-87. Between 2000 and 2005, OSU achieved its first\\n\\nwinning seasons in more than a decade. Aplt. App., Vol. II at A445. The Defendants\\n\\nsuspected that new and perhaps impermissible recruiting strategies might have\\n\\n 7\\n\\fcontributed to this sudden success. Id. They focused their research on individuals\\n\\nwho were involved with the program between 2000 and 2005. Id. at A388.\\n\\n a. Interviews with players and Mr. Talley\\n\\n The SI reporters interviewed 60 to 70 former and current OSU players,\\n\\ncoaches, boosters, and administrators. Aplt. App., Vol. I at A87; Aplt. App., Vol. II\\n\\nat A388-90; Aplt. App., Vol. III at A747. The reporters recorded the interviews they\\n\\nused to write the passage about Mr. Talley. Aplt. App., Vol. II at A389. These\\n\\nrecordings were later produced during discovery.5 In addition, Mr. Schecter\\n\\n\\n\\n\\n 5\\n In support of their motion for summary judgment, the Defendants provided\\nthe district court with audio excerpts from Mr. Dohrmann’s interview with former\\nOSU player Fath’ Carter, Aplt. App., Vol. II at A483; Mr. Evans’s interviews with\\nformer players Rodrick Johnson, id. at A487, Seymour Shaw, id. at A497, Brad\\nGirtman, id. at A505, Thomas Wright, id. at A517, Aso Pogi, id. at A512, Larry\\nBrown, id. at A518, and Chijuan Mack, id. at A519; Mr. Dohrmann and Mr. Evans’s\\ninterview with Thomas Wright, id. at A509, and Mr. Schecter and Mr. Dohrmann’s\\ninterview with OSU officials, id. at A523. The Defendants also provided audio\\nexcerpts from an interview that NCAA investigators conducted with OSU operations\\ndirector Mack Butler during the NCAA’s post-article investigation. Aplt. App., Vol.\\nIII at A546. Mr. Talley submitted full-length interview recordings of Mr. Evans’s\\ninterviews with former players Aso Pogi, Aplt. App., Vol. IV at A894, Calvin\\nMickens, id. at A895, Chijuan Mack, id. at A896, Thomas Wright, id. at A897, and\\nXavier Lawson-Kennedy, id. at A898.\\n\\n 8\\n\\finterviewed Mr. Talley.6 Id. at A404. We describe below the information gathered\\n\\nabout Mr. Talley during these interviews.7\\n\\n i. Mr. Evans’s interviews\\n\\n Mr. Evans conducted most of the interviews. Id. at A388. After each\\n\\ninterview, he reviewed his notes and/or the recording and e-mailed summaries to Mr.\\n\\nDohrmann and Mr. Schecter. Id. at A389-90, A408, A438. He also occasionally re-\\n\\ninterviewed players to ensure that his information was accurate. Id. at A390.\\n\\n 1) Payments for speeches and work\\n\\n Between November 2012 and January 2013, Mr. Evans spoke to former OSU\\n\\nplayers Brad Girtman, Seymour Shaw, Prentiss Elliott, Chijuan Mack, Xavier\\n\\nLawson-Kennedy, Doug Bond, Thomas Wright, Rodrick Johnson, T.J. Minor, and\\n\\nLarry Brown. Id. at A389. The players reported the following:\\n\\n Brad Girtman revealed that Mr. Talley paid him “fifteen hundred, a\\n thousand” dollars to perform “ranch hand” tasks. Dist. Ct. Doc. 60, Ex. 17\\n at 0:14-0:20, 0:42 (Girtman Interview); see also Aplt. App., Vol. II at\\n A508. When Mr. Evans asked if these payments were excessive, Mr.\\n Girtman responded, “I mean, I thought he was overpaying me, cus I wasn’t\\n sure what I was doing.” Girtman Interview at 0:06-0:13.\\n\\n Seymour Shaw reported that Mr. Talley “always paid [players] to go talk”\\n and that “if you needed some money, you’d go to John Talley.” Dist. Ct.\\n\\n 6\\n Although Mr. Schecter recorded his interview with Mr. Talley, he stated that\\nthe file was “corrupted after a minute and a half.” Aplt. App., Vol. II at A410.\\nAccordingly, the recording is not available.\\n 7\\n In this opinion, we have quoted from the interview recordings, which are part\\nof the record on appeal, without the benefit of transcripts. The parties did not\\nprovide certified transcripts.\\n 9\\n\\f Doc. 60, Ex. 15 at 1:09-1:13, 1:16-1:19 (Shaw Interview); see also Aplt.\\n App., Vol. II at A500.\\n\\n Chijuan Mack volunteered Mr. Talley’s name without any prompting from\\n Mr. Evans and described the speaking arrangements and team building\\n activities that Mr. Talley organized for OSU players. Dist. Ct. Doc. 71, Ex.\\n 12 at 45:49-46:37 (Mack Interview). When Mr. Evans asked, “So, like,\\n during the season you would go speak to schools, read to schools, and\\n they’d pay you like a normal job, obviously?,” Mr. Mack responded, “No,\\n during the season you couldn’t get paid during the season. . . . But during\\n the summer, you’d get to go there, he got a big farm like, he’d do stuff like\\n focus groups . . . That’s when you would get paid.” Id. at 47:45-48:56.8\\n\\n Mr. Evans asked Larry Brown, “You would go talk to kids and [Mr. Talley]\\n would pay you to go talk to kids, right?” Mr. Brown responded, “Yeah.”\\n Dist. Ct. Doc. 60, Ex. 25 at 0:39-0:45 (Brown Interview).\\n\\n Thomas Wright denied that Mr. Talley ever overpaid him for work. Dist.\\n Ct. Doc. 71, Ex. 13 at 6:23-36 (Evans Wright Interview). When Mr. Evans\\n mentioned that “some guys got paid” for Mr. Talley’s speaking\\n engagements, Mr. Wright responded, “I know some guys did, but I didn’t.\\n I didn’t get paid for that.” Id. at 6:27-45. In a different interview, Mr.\\n Wright stated that OSU players worked for boosters but “got kinda\\n overpaid.” Dist. Ct. Doc. 60, Ex. 19 at 0:00-0:21 (Evans Dohrmann Wright\\n Interview). When asked about Mr. Talley, Mr. Wright said, “I don’t think\\n he was into all that, he seemed pretty good, but I mean he had to have been\\n a booster I would think . . . . He was hooking us up big time with jobs, but I\\n\\n\\n\\n 8\\n Mr. Mack denied that players were overpaid for work and stated that OSU\\n“made sure they did everything by the law.” Mack Interview at 39:40-40:18. But he\\nalso reported that OSU did all it could to take advantage of what was permitted under\\nthe rules: “[If] the rules say that you can do this, . . . if that’s the case, [OSU would\\nfollow] the rule all the way to the nitty gritty. . . . So they would have somebody go\\nto check that and he would come back and be like, ‘Well look they can do this and\\nthis,’ so the next time we’d get our monthly check, the check might go up a hundred\\nor 200 . . . it would fluctuate because they tryin’ to get us more.” Id. at 42:36-43:14.\\nAs another example, Mr. Mack reported that coaches would not hand players extra\\ncash but instead gave team captains additional money—two or three hundred\\ndollars—on their OSU ID cards, which players could spend anywhere on campus.\\nSee id. at 43:15-45:12.\\n 10\\n\\f don’t think, as far as giving us money, I don’t think—he’d never hand us\\n money . . . but he would definitely hook us up with jobs.” Id. at 0:53-1:21.\\n\\n Rodrick Johnson reported that Mr. Talley overpaid him for work. When\\n Mr. Evans asked about “jobs that you guys got paid crazy amounts for,”\\n Mr. Johnson immediately interrupted and said, “John Talley, John Talley.\\n Oh, he owes me, still to this day.” Dist. Ct. Doc. 60, Ex. 13 at 0:00-0:07\\n (Johnson Interview). Mr. Johnson then added, “He used to pay very well. I\\n would work for about three hours and I would get paid probably about 400\\n bucks.” Id. at 0:15-0:22. Mr. Johnson described cutting bushes and doing\\n yard work on Mr. Talley’s property and said, “Max[imum,] I would do\\n probably about ten hours and I would get—a lot of money. Like, it’d be\\n enough to actually make it through the summer.” Id. at 0:51-1:00. Mr.\\n Johnson also noted that, while some employers paid with an “actual check\\n that wasn’t anything under the table,” “Talley would pay in cash.” Id. at\\n 2:32-2:39. Additionally, Mr. Johnson said that Mr. Talley paid him for\\n speaking engagements and that “one time I went to speak at a school and he\\n paid me 100 bucks, and it was, like, for 20 minutes” and that “[t]here were\\n guys that did that almost every day.” Id. at 2:42-3:02. He also stated “John\\n Talley was the hot name around campus tryin’ to get jobs. If you need a\\n job, call John Talley.” Id. at 3:20-3:25; see also Aplt. App., Vol. II at\\n A494.\\n\\n Xavier Lawson-Kennedy stated that he never worked for Mr. Talley but\\n that he “actually wanted to” because “[Mr. Talley] had the funnest . . . he\\n had the best jobs to do, like go talk to kids.” Dist. Ct. Doc. 71, Ex. 14 at\\n 13:20-32 (Lawson-Kennedy Interview).\\n\\n By March 2013 Mr. Evans had spoken with 19 players. According to his\\n\\nnotes, “five [of these] admitted to taking cash, including three who said they were\\n\\npaid for their play, and two others admitted receiving extra per diem money.” Aplt.\\n\\nApp., Vol. II at A389. In addition, “[f]ive players said they were either paid for no-\\n\\nshow jobs or were significantly overpaid for work.” Id. Multiple players—including\\n\\nMr. Girtman, Mr. Shaw, Mr. Brown, Mr. Wright, and Mr. Johnson—volunteered Mr.\\n\\n\\n\\n 11\\n\\fTalley’s name or provided detail about his involvement with the OSU program. Id. at\\n\\nA389, A438.\\n\\n 2) Mr. Pogi living at the ranch\\n\\n Shortly before publishing the article, Mr. Evans interviewed former OSU\\n\\nquarterback Aso Pogi.9 Id. at A390. Mr. Pogi said he frequently participated in Mr.\\n\\nTalley’s speaking engagements but insisted he was never paid to speak. Dist. Ct.\\n\\nDoc. 71, Ex. 10 at 4:43-4:52 (Pogi Interview). He also described living on Mr.\\n\\nTalley’s ranch one summer. The relevant exchange proceeded as follows:\\n\\n Mr. Evans: So, how many times do you estimate John\\n [Talley] gave you money? John admitted that he gave\\n money. Just that way you know that I’m not lying to you.\\n John admitted it, said that he cleared it with the school, the\\n school said they never cleared it, and that John was never\\n supposed to give you guys money.\\n\\n Mr. Pogi: Um, I don’t know, man, it was, you know, just\\n speaking engagements—\\n\\n Mr. Evans: You spoke a lot, though?\\n\\n Mr. Pogi: Yeah I did, and, and, you know, we don’t get\\n anything.\\n\\n Mr. Evans: I know, I know, listen, and that’s another\\n argument for another day. . . . But you spoke dozens of\\n times, is what people said.\\n\\n\\n 9\\n The record does not indicate when this interview occurred, but in the\\ninterview recording, Mr. Evans told Mr. Pogi, “We talked to John [Talley]\\nyesterday.” Dist. Ct. Doc. 71, Ex. 10 at 5:56-6:02 (Pogi Interview). Mr. Schecter\\ninterviewed Mr. Talley on September 3, 2013, Aplt. App., Vol. II at at A404, which\\nsuggests that Mr. Evans’s conversation with Mr. Pogi occurred on September 4,\\n2013.\\n 12\\n\\fMr. Pogi: Yeah.\\n\\nMr. Evans: And he gave you money dozens of times.\\n\\nMr. Pogi: I was on the road a lot to speak. And it was just\\nfor my gas, you know, just cus I had to drive my personal\\nvehicle there, you know what I mean? But, um—\\n\\nMr. Evans: It’s not an indictment that you’ve done\\nanything wrong, Aso, okay? I’m not—\\n\\nMr. Pogi: And listen, I’m, I’m not really, I’m not taking it\\nthat way. I’m, I’m kinda like, this is kinda throwing me\\noff—\\n\\nMr. Evans: It is, and it should. . . . There’s no good way to\\ndo it, Aso. You have to understand, I mean, from my\\nperspective, there’s no good way to do it. Cus if I call you\\nahead of time, you know, I want to get in front of you\\nbecause, again, like, your name is in the story for money.\\n\\nMr. Pogi: Yeah, that, and that, that kinda, that kinda hurts\\nme a little bit.\\n\\nMr. Evans: I mean, Aso, I mean, I’m sorry, you know? I\\nmean, there’s just nothing I can do about it. You know\\nwhat I’m saying? I mean, like, that’s why I came to get\\nyour response. And we’ll put your response in there.\\n\\nMr. Pogi: Well let me, let me just say this, then. Let me\\nsay that, um, I’d like to just, um, I’m not going to sit here\\nand plead the Fifth or anything like that, but I, I’d like to,\\nlike, you know, do my own research on it, because I’m\\nbeing honest with you in telling you that, you know, we\\nreceived gas money, and—\\n\\nMr. Evans: That’s fine. I mean, I’ll tell you what you’re\\ngonna find. Because I know it, I mean, I know it from the\\nNCAA perspective, right? I mean, like I said, we went to\\nthem and told them, right? John said that he had had that\\napproved, okay? Compliance said that they never\\napproved it, Aso. So he was—and it’s against the rules for\\n\\n 13\\n\\fyou to be paid during the season, any of that stuff, for\\nspeaking engagements, et cetera.\\n\\nMr. Pogi: And guys put me out there?\\n\\nMr. Evans: They threw, oh, absolutely.\\n\\nMr. Pogi: That I was the main one, huh?\\n\\nMr. Evans: No. You’re not the main one. I mean, there’s\\na, it’s a long list, my man. Okay?\\n\\nMr. Pogi: I mean, I, I just, I did a—\\n\\nMr. Evans: You worked at his ranch, too.\\n\\nMr. Pogi: I did a lot.\\n\\nMr. Evans: You worked at his ranch.\\n\\nMr. Pogi: I—I lived there.\\n\\nMr. Evans: You lived there, but you never, you never\\nworked—\\n\\nMr. Pogi: I ne—I didn’t, I didn’t do anything like—\\n\\nMr. Evans: You knew guys came out there and worked. I\\nmean he says estimates a thousand athletes have worked at\\nhis ranch.\\n\\nMr. Pogi: Yeah.\\n\\nMr. Evans: A thousand. I mean some people said that\\nthey got paid for not doing anything at his ranch. You\\nknow they just came out and they just basically got\\nmoney—\\n\\nMr. Pogi: [Laughs]\\n\\n....\\n\\n\\n\\n 14\\n\\f Mr. Evans: I mean, you lived with John [Talley], right? I\\n mean, what was the arrangement?\\n\\n Mr. Pogi: I had no arrangement. That’s the thing that’s\\n throwing me off. I’m like, “Arrangement?” I-I-I didn’t\\n make, you know, any money.\\n\\n Mr. Evans: But you shouldn’t have been, I mean, like, you\\n lived with him.\\n\\n Mr. Pogi: Yeah I lived with him.\\n\\n Mr. Evans: I mean, like, I mean did anybody ever—\\n\\n Mr. Pogi: Me and George Horton, we, we lived with John,\\n and, you know, we—\\n\\n Mr. Evans: He didn’t charge you rent, obviously.\\n\\n Mr. Pogi: No, he didn’t charge us rent. No, no, we lived\\n there for a summer, you know and that was about it.\\n\\n Mr. Evans: And you saw the guys come out and work.\\n What’d you do for money in the summers? You went and\\n did the speaking engagements?\\n\\n Mr. Pogi: I did speaking engagements. I did a lot of\\n speaking. But I wasn’t getting paid like that. I mean, I got\\n gas money.\\n\\nId. at 9:41-12:29; 17:24-18:13.\\n\\n ii. Mr. Dohrmann’s interviews\\n\\n Mr. Dohrmann also spoke with players and OSU officials. He met in Denver\\n\\nwith former OSU player Fath’ Carter. During that interview, Mr. Dohrmann said,\\n\\n“The other one I heard was . . . that there were like some funky jobs, like you go and\\n\\nmow the lawn, or you don’t mow the lawn.” Dist. Ct. Doc. 60, Ex. 11 at 0:00-0:11\\n\\n(Carter Interview). Before Mr. Dohrmann could finish the question, Mr. Carter\\n 15\\n\\finterrupted and said, “You’re talking about John Talley.” Id. at 0:12-0:14. Mr.\\n\\nCarter then added, “Yeah, however that was constructed, I have no idea. But I was a\\n\\nbig part of that . . . a lot of athletes.” Id. at 0:18-0:28. Mr. Dohrmann asked if there\\n\\nwas “one funny job” that Mr. Carter remembered. Id. at 0:30-0:34. The conversation\\n\\nproceeded as follows:\\n\\n Mr. Carter: There wasn’t a job!\\n\\n Mr. Dohrmann: Yeah but I mean, what was the job on\\n paper . . . ?\\n\\n Mr. Carter: Uh, well there was no paper for one.\\n\\n Mr. Dohrmann: Well, you know what I mean. In theory,\\n you were supposed to—\\n\\n Mr. Carter: It would be, um, like one funny one was out to\\n his ranch, I’m putting the horseshoes on the horses.\\n\\n Mr. Dohrmann: But you don’t actually, no way you guys,\\n you guys never got on a horse in your life.\\n\\n Mr. Carter: [Laughing] Yeah. . . . Yeah that was a quick\\n buck, cash.\\n\\n ....\\n\\n Mr. Dohrmann: How did guys view it? Did they view it\\n like, “We earned this, like, this is only fair? Doin’ what\\n we’re doin’.”\\n\\n Mr. Carter: It was fair, but we viewed it as, “I’m gonna\\n get paid.” You know, “Let me do some work for John\\n Talley so I can go out and buy some shoes.”\\n\\nId. at 0:34-2:24; see also Aplt. App., Vol. II A323-24, A484.\\n\\n\\n\\n 16\\n\\f Mr. Dohrmann later called Mr. Carter to verify his statements about shoeing\\n\\nhorses. At his deposition, Mr. Dohrmann testified that during this phone call, Mr.\\n\\nCarter again said “something about shoeing horses and [that he had] never seen a\\n\\nhorse before” and that “[h]e didn’t do the work but he was paid.” Aplt. App., Vol. II\\n\\nat A325-27.\\n\\n iii. Mr. Schecter’s interview with Mr. Talley\\n\\n On September 3, 2013, Mr. Schecter had a brief conversation with Mr. Talley\\n\\noutside the OSU basketball arena.10 Id. at A404. Mr. Schecter informed Mr. Talley\\n\\nof the allegations against him. Aplt. App., Vol. III at A718. He also asked about\\n\\nspeaking arrangements and whether Mr. Talley had overpaid players for work. Id.;\\n\\nAplt. App., Vol. II at A443. Mr. Talley confirmed he had hired and paid OSU\\n\\nplayers to work on his property but insisted he had cleared the employment\\n\\narrangements with OSU’s compliance office. Aplt. App., Vol. I at A168; Aplt. App.,\\n\\nVol. II at A417. Mr. Schecter recorded the conversation on his cell phone, Aplt.\\n\\nApp., Vol. II at A409, and summarized the interview in an e-mail that he sent to Mr.\\n\\nEvans and Mr. Dohrmann. See id. at A443, A520-23.11 He also gave Mr. Talley his\\n\\n\\n 10\\n Mr. Talley stated Mr. Schecter was “in a hurry to get out of [the car],” Aplt.\\nApp., Vol. I at A204, and that the whole interview lasted about five minutes, Aplt.\\nApp., Vol. III at A680. Mr. Schecter said the interview lasted about 15 to 20\\nminutes. Aplt. App., Vol. II at A443.\\n 11\\n Mr. Talley claimed in his deposition that Mr. Schecter arranged a second\\nmeeting with him and OSU’s general counsel on Friday of the same week but\\ncancelled the meeting because “he had enough information.” Aplt. App., Vol. III at\\n 17\\n\\fcontact information and invited him to reach out with any questions. Id. at A424,\\n\\nA443.\\n\\n On September 6, 2013, Mr. Schecter sent Mr. Talley an e-mail that read, “Aso\\n\\nPogi told us that he . . . lived on your range [sic] rent-free for one summer. Is that\\n\\ntrue?” Id. at A515; see also id. at A425. Mr. Talley responded, “No, there was an\\n\\nexpectation of work for [Mr. Pogi’s] room and board that was done.” Id. at A514.\\n\\nMr. Schecter then asked if Mr. Talley “report[ed] this arrangement to Oklahoma\\n\\nState,” and Mr. Talley responded, “[Y]es, to athletic compliance.” Id.; see also id. at\\n\\nA425.\\n\\n b. Meetings with OSU officials\\n\\n On September 3, 2013, Mr. Schecter and Mr. Dohrmann met with OSU\\n\\nAthletic Director Mike Holder, Associate Athletic Director for Compliance Kevin\\n\\nFite, and General Counsel Gary Clark to “solicit their comment.” Aplt. App., Vol. II\\n\\nat A439; see also id. at A443; Aplt. App., Vol. III at A766. This meeting was not\\n\\nrecorded, but both Mr. Schecter and Mr. Dohrmann testified at their depositions that\\n\\nthey spent several hours “present[ing] the substance of the information [they] had\\n\\nlearned in [their] investigation about the role money, drugs, women, and academics\\n\\nplayed in the OSU football program.” Aplt. App., Vol. II at A439; see also id. at\\n\\n\\n\\n\\nA719. Mr. Schecter “categorically den[ied]” this claim during his deposition. Aplt.\\nApp., Vol. II at A431-32.\\n 18\\n\\fA443. In his affidavit, Mr. Schecter said “this meeting was ‘off the record’”—“the\\n\\nofficials did not give us any comments for publication.” Id. at A443.\\n\\n On September 4, 2013, Mr. Schecter and Mr. Dohrmann held a second meeting\\n\\nwith the same OSU officials. This time, they recorded the meeting. See Dist. Ct.\\n\\nDoc. 60, Ex. 28 (OSU Officials Interview); see also Aplt. App., Vol. II at A439,\\n\\nA443. They asked the OSU officials to verify Mr. Talley’s claim that he had\\n\\nreceived clearance to pay students for speaking engagements.12 Mr. Fite said the\\n\\nspeaking engagements “were not cleared through our office as paid speaking\\n\\nengagements.” OSU Officials Interview at 1:02-1:07. He added, “In fact, two of my\\n\\nstaff members indicated to me this morning that they had had conversations with [Mr.\\n\\nTalley] and had told him, ‘You cannot pay for speaking engagements. If you wanna\\n\\nemploy our student athletes for other things, that is fine, but you cannot pay them for\\n\\nspeaking engagements.’” Id. at 1:07-1:25.\\n\\n c. Writing and editing\\n\\n In spring 2013, the SI reporters determined they had gathered enough\\n\\ninformation to begin drafting the article. Aplt. App., Vol. II at A438. Mr. Dohrmann\\n\\nassumed primary writing duties. As he wrote, he reviewed Mr. Evans’s notes and\\n\\n\\n 12\\n In the interview recording, Mr. Schecter said, “One thing [Mr. Talley] did\\nsay was that, whether it was routinely or regularly, but certainly plenty of times, that\\nhe did, indeed, set up speaking engagements for football players, and that on\\nnumerous occasions that they were paid for those speaking engagements. He said it\\ncoulda been 50 dollars, it coulda been 100 dollars, or whatever, but that was cleared\\nthrough your office.” OSU Officials Interview at 0:09-0:42.\\n 19\\n\\flistened to audio recordings of the interviews. Id. at A439. He also identified\\n\\n“places where [the reporters] needed more information, or the name of a source, or\\n\\nspecific details about what a former player had said about his experience.” Id. Mr.\\n\\nDohrmann sent drafts of the article to editors and to Mr. Evans, who reviewed the\\n\\nwork as it was written. Id. at A390. He also spoke frequently with Mr. Evans and\\n\\nMr. Schecter to ensure “[they] had sufficient substantiation for what SI was\\n\\nreporting.” Id.\\n\\n Mr. Dohrmann’s drafts underwent SI’s standard editing and review process,\\n\\nwhich Mr. Schecter described as follows:\\n\\n Well . . . it starts off with a draft of the story being filed.\\n That story is then edited, fact-checked, vetted by our legal\\n team, copy-edited, read one more time by the writers and\\n editors involved in the . . . story, and then finally, it goes to\\n press.\\n\\nId. at A400. As part of this revision process, other SI editors “[made] notes in\\n\\nthe drafts to suggest word changes for clarity or flow, or ask[ed] questions\\n\\nabout what the sources said about the facts.” Id. at A439. In addition, SI fact\\n\\ncheckers reviewed each draft and “would confirm specific facts, such as the\\n\\nspelling of a name, the dates when players attended OSU, the name of the high\\n\\nschool from which a player was recruited, and so on.” Id.\\n\\n Mr. Schecter also performed an editing role, which involved “making\\n\\nsure . . . the story [was] clear and concise . . . and . . . mak[ing] sure that things\\n\\ntrack”—that is, “if you say something, it’s supported by something else, and\\n\\n 20\\n\\fthat the piece is fair and balanced.” Id. at A399. He repeatedly listened to the\\n\\nrecording of his conversation with Mr. Talley to “confirm the accuracy of the\\n\\nquotes that [the Defendants] were using . . . and make sure that [they] gave\\n\\n[Mr. Talley] every attempt to deny the allegations that [they] made against\\n\\nhim.” Id. at A415-16.\\n\\n d. Pre-publication legal and editorial review and publication\\n\\n SI completed edits and revisions just days after the September 4 meeting with\\n\\nthe OSU officials. Id. at A444. Time’s in-house counsel reviewed the final draft, id.,\\n\\nand Chris Stone, SI’s Managing Editor, approved it, id. at A439, A444. SI published\\n\\nthe first article online on September 10, 2013, and released the remaining four\\n\\narticles online between September 11 and September 17, 2013. Aplt. App., Vol. III\\n\\nat A700-A701. It also printed the first article in its September 16, 2013 print issue\\n\\nand included the final article in its September 23, 2013 print issue.13 Id.\\n\\n Individual Defendants’ Depositions and Affidavits\\n\\n After Mr. Talley filed his lawsuit, the reporters and editor responsible for “The\\n\\nDirty Game” all stated they believed the series was truthful and substantiated. In his\\n\\ndeposition, Mr. Evans said, “I believe that we published accurate information about\\n\\nthe allegations that players had made about Mr. Talley.” Aplt. App., Vol. II at A379.\\n\\n\\n\\n\\n 13\\n SI published the second, third, and fourth articles only online.\\n\\n\\n 21\\n\\fAnd in his affidavit, Mr. Evans said he “was completely satisfied that what we were\\n\\nreporting was truthful based on the information we had gotten from the dozens of on-\\n\\nthe-record sources.” Id. at A390. As to the passages on Mr. Talley, he stated:\\n\\n [T]hose sources—players who had been at OSU at\\n different times and who were interviewed independently—\\n corroborated one another. By talking with them personally\\n I was able to assess their credibility, and I did not sense\\n any bias toward [Mr.] Talley or other reasons that would\\n make me doubt the accuracy of what they were telling me\\n about him or what we reported in the article. I remain\\n completely satisfied in this regard today.\\n\\nId. at A390-91.\\n\\n In his deposition, Mr. Dohrmann said “[i]t’s very difficult to get players to\\n\\n[admit to NCAA violations]” and that “[f]ive players is a significant number [of\\n\\nsources] with a story like this.” Id. at A337. He had “done a lot of stories like this”\\n\\nand had “done stories with far less than five [sources].” Id. Because “a number of\\n\\nsources . . . told [the reporters] a similar or same story about Oklahoma State and\\n\\nJohn Talley,” he felt “absolutely certain about what we were writing.” Id. at A342.\\n\\nMr. Dohrmann also stated in his affidavit that he “had heavily researched the article\\n\\nand reviewed all the sources,” “the facts [the interviewees] provided were consistent\\n\\nwith and corroborative of one another,” he “did not observe any signs of bias . . .\\n\\namong the sources or other facts that would cause [him] to question their credibility,”\\n\\nand he “did not doubt the accuracy of any statement in the article.” Id. at 439-40.\\n\\n At his deposition, Mr. Schecter said he believed the article “was very well\\n\\ndone” and “was all true.” Id. at A431. And in his affidavit, he stated, “I believed\\n 22\\n\\fwhen the article . . . was published it was accurate and truthful. I was satisfied that\\n\\nall the statements in the article about [Mr.] Talley were adequately substantiated by\\n\\nmultiple sources and were truthful. . . . My opinion has not changed despite [Mr.]\\n\\nTalley’s lawsuit.” Id. at A444.\\n\\n C. Procedural Background\\n\\n In July 2014, Mr. Talley filed his lawsuit in state court. Aplt. App., Vol. I at\\n\\nA11. He named Time, Inc., Mr. Dohrmann, and Mr. Evans as defendants, but he did\\n\\nnot sue Mr. Schecter. Invoking diversity jurisdiction under 28 U.S.C. § 1332, the\\n\\nDefendants removed the case to the United States District Court for the Western\\n\\nDistrict of Oklahoma.\\n\\n After the parties completed the discovery process, the Defendants moved for\\n\\nsummary judgment. They argued, among other things, that Mr. Talley was “unable\\n\\nto prove with competent evidence that at least one of the statements about which he\\n\\ncomplains satisfies all of the elements of a false light claim.” Id. at A107. Mr.\\n\\nTalley opposed the motion, claiming “disputed issues of material fact exist[ed]” with\\n\\nrespect to all three elements of his false light claim. Aplt. App., Vol. III at A694.\\n\\n The district court granted summary judgment for the Defendants, finding Mr.\\n\\nTalley could not demonstrate a genuine dispute of material fact regarding the first\\n\\n(falsity) or third (actual malice) elements of his false light claim. Talley v. Time, Inc.\\n\\nd/b/a Sports Illustrated Magazine, No. CIV-14-853-D, 2018 WL 4558993, at *5-6\\n\\n(W.D. Okla. Sept. 21, 2018).\\n\\n 23\\n\\f With respect to the third element—whether SI acted with actual malice—the\\n\\ncourt found “[Mr. Talley] present[ed] no facts or evidence to show that Defendants\\n\\nknew the allegations they reported about [him] were false.” Aplt. App., Vol. V at\\n\\nA1197. Although Mr. Talley argued Defendants “were pursuing an agenda” and\\n\\ncrafted “a sensational, unfavorable” narrative to get “the story they wanted,” the\\n\\ncourt found his allegations were “unsupported by any facts” and could not\\n\\n“reasonably be found to show either actual knowledge or a high degree of awareness\\n\\nby Defendants that the allegations about [Mr. Talley] . . . were probably false.” Id. at\\n\\nA1203. The court thus concluded Mr. Talley “present[ed] no facts or evidence that\\n\\nmight reasonably satisfy the rigorous standard required to establish ‘actual malice’ or\\n\\neven to demonstrate a genuine dispute of material fact in this regard.” Id.\\n\\n II. DISCUSSION\\n\\n The following discussion concludes that Mr. Talley has not shown that a\\n\\nreasonable jury could find that the Defendants acted with actual malice. Summary\\n\\njudgment was therefore appropriate.\\n\\n A. Legal Background\\n\\n This section describes (1) the standard of review for summary judgment, (2)\\n\\nthe elements of Oklahoma’s false light tort, and (3) the actual malice standard.\\n\\n Standard of Review\\n\\n As this court has recognized in defamation cases, “[we] review summary\\n\\njudgment decisions de novo, applying the same legal standard as the district court.”\\n\\n 24\\n\\fCory v. Allstate Ins., 583 F.3d 1240, 1243 (10th Cir. 2009) (quotations omitted).\\n\\n“The court shall grant summary judgment if the movant shows that there is no\\n\\ngenuine dispute as to any material fact and the movant is entitled to judgment as a\\n\\nmatter of law.” Fed. R. Civ. P. 56(a). “When applying this standard, we view the\\n\\nevidence and draw reasonable inferences therefrom in the light most favorable to the\\n\\nnonmoving party.” Cory, 583 F.3d at 1243 (quotations omitted).\\n\\n “[A] party seeking summary judgment always bears the initial responsibility of\\n\\n. . . demonstrat[ing] the absence of a genuine issue of material fact.” Celotex Corp.\\n\\nv. Catrett, 477 U.S. 317, 323 (1986); see also Savant Homes, Inc. v. Collins, 809\\n\\nF.3d 1133, 1137 (10th Cir. 2016). “A movant that does not bear the burden of\\n\\npersuasion at trial may satisfy this burden by pointing out to the court a lack of\\n\\nevidence on an essential element of the nonmovant’s claim.” Teets v. Great-West\\n\\nLife & Annuity Ins. Co., 919 F.3d. 1232, 1243 (10th Cir. 2019) (quotations omitted).\\n\\n “If the movant meets this initial burden, the burden then shifts to the\\n\\nnonmovant to set forth specific facts from which a rational trier of fact could find for\\n\\nthe nonmovant.” Id. (quotations omitted). “These facts must establish, at a\\n\\nminimum, an inference of the presence of each element essential to the case.” Savant\\n\\nHomes, 809 F.3d at 1137-38 (quotations omitted). The movant is entitled to\\n\\nsummary judgment if the nonmoving party cannot provide facts “to make a sufficient\\n\\nshowing on an essential element of her case with respect to which she has the burden\\n\\nof proof.” Id. at 1138 (quotations omitted).\\n\\n 25\\n\\f Both the Supreme Court and Oklahoma state courts have held that at trial, the\\n\\nplaintiff must prove actual malice with “convincing clarity.” New York Times, 376\\n\\nU.S. at 286-87; Colbert, 747 P.2d at 291. The Supreme Court has said courts “must\\n\\nbear in mind” this heightened burden of proof when ruling on a defendant’s motion\\n\\nfor summary judgment. Anderson v. Liberty Lobby, Inc., 477 U.S. 242, 254 (1986)\\n\\n(holding that courts must consider “the actual quantum and quality of proof necessary\\n\\nto support liability under New York Times” when considering summary judgment on\\n\\nthe actual malice issue). “[I]f the evidence presented in the opposing affidavits is of\\n\\ninsufficient caliber or quantity to allow a rational finder of fact to find actual malice\\n\\nby clear and convincing evidence,” then “there is no genuine issue” and summary\\n\\njudgment is appropriate. Spacecon Specialty Contractors, LLC v. Bensinger, 713\\n\\nF.3d 1028, 1048 n.13 (10th Cir. 2013) (quotations omitted).14\\n\\n Oklahoma’s False Light Tort\\n\\n As discussed above, Oklahoma recognizes the common law tort of false light\\n\\ninvasion of privacy. The plaintiff must show:\\n\\n (1) “the defendant gave publicity to a matter concerning\\n the plaintiff that placed the plaintiff before the public in a\\n false light,”\\n\\n\\n\\n 14\\n Spacecon involved a defamation claim brought under Colorado law, which\\nrequired the plaintiff to demonstrate actual malice by clear and convincing evidence.\\n713 F.3d at 1041.\\n\\n\\n\\n 26\\n\\f (2) “the false light in which the plaintiff was placed would\\n be highly offensive to a reasonable person,”\\n\\n (3) “the defendant had knowledge of or acted in reckless\\n disregard as to the falsity of the publicized matter and the\\n false light in which the other would be placed.”\\n\\nMitchell, 60 P.3d at 1061 (citing McCormack, 613 P.2d at 740); see also Restatement\\n\\n(Second) of Torts § 652E (Am. Law Inst. 1977).\\n\\n “[E]ssential to . . . a false light privacy claim . . . is a determination that that\\n\\nthe matter published concerning the plaintiff is not true.” Rinsley v. Brandt, 700 F.2d\\n\\n1304, 1307 (10th Cir. 1983) (quotations omitted).15 Thus, to establish the first\\n\\nelement of a false light claim, a plaintiff must show the defendant made a statement\\n\\nthat “portrayed [plaintiff] in [a] false manner or that statements were untrue or\\n\\nmisleading.” McCormack, 613 P.2d at 741 (holding that plaintiff failed to state a\\n\\ncause of action for false light invasion of privacy because plaintiff did not allege that\\n\\nthe published statements were false or misleading). True statements are not\\n\\nactionable under Oklahoma’s false light tort.\\n\\n To satisfy the second element, the plaintiff must show “a reasonable [person]\\n\\nwould be justified in the eyes of the community in feeling seriously offended and\\n\\naggrieved by the publicity.” Restatement (Second) of Torts §652E, cmt. c. Put\\n\\ndifferently, “[i]t is only when there is such a major misrepresentation of [the\\n\\n\\n 15\\n Rinsley involved a false light invasion of privacy claim brought under\\nKansas law. Like Oklahoma, Kansas has adopted the false light invasion of privacy\\naction set forth in Restatement (Second) of Torts § 652E. See Rinsley, 700 F.2d at\\n1307.\\n 27\\n\\fplaintiff’s] character, history, activities or beliefs that serious offense may reasonably\\n\\nbe expected to be taken by a reasonable man in his position, that there is a cause of\\n\\naction for invasion of privacy.” Id.\\n\\n The third element—knowledge of or reckless disregard as to falsity—is\\n\\nidentical to the actual malice standard from New York Times Co. v. Sullivan. See\\n\\nColbert, 747 P.2d at 290-92 (noting that Oklahoma has “adopted” the actual malice\\n\\ntest from Time, Inc. v. Hill, 385 U.S. 374 (1967), which applied the New York Times\\n\\nactual malice standard in a false light invasion of privacy case); Grogan v. Kokh,\\n\\nLLC, 256 P.3d 1021, 1030 (Okla. Civ. App. 2011) (noting that “the Oklahoma\\n\\nSupreme Court has adopted the [New York Times] actual malice test for false light\\n\\ninvasion of privacy claims”).16 Thus, to establish the third element of a false light\\n\\nclaim, a plaintiff must show the defendant made or published its statements “with\\n\\n‘actual malice’—that is, with knowledge that [they were] false or with reckless\\n\\ndisregard to whether [they were] false or not.” New York Times, 376 U.S. at 280.\\n\\nWe next discuss the Supreme Court cases that have articulated and developed this\\n\\nstandard.\\n\\n\\n\\n\\n 16\\n Although the Supreme Court has applied the actual malice standard in at\\nleast one false light invasion of privacy case, see Time, Inc., 385 U.S. 374, the\\nstandard originated in New York Times, which was a defamation case. As a result,\\nOklahoma courts analyzing the third element of a false light tort claim routinely look\\nto and rely on both defamation and false light case law. See, e.g., Grogan, 256 P.3d\\nat 1031 (“analogizing to defamation law” where there is no clear false light case law\\non point).\\n 28\\n\\f Actual Malice\\n\\n a. New York Times and its progeny\\n\\n In New York Times v. Sullivan, the Supreme Court said that a publication “was\\n\\nmade with ‘actual malice’” when the defendant published “with knowledge that it was\\n\\nfalse or with reckless disregard of whether it was false or not.” 376 U.S. at 279-80; see\\n\\nGertz v. Robert Welch, Inc., 418 U.S. 323, 343 (1974). The plaintiff’s burden of proving\\n\\nactual malice cannot be met by a preponderance of the evidence. Actual malice must be\\n\\nshown with “convincing clarity,” New York Times, 376 U.S. at 285-86—that is, by “clear\\n\\nand convincing proof,” Gertz, 418 U.S. at 342.\\n\\n Actual malice is not a negligence or gross negligence standard. See Garrison v.\\n\\nLouisiana, 379 U.S. 64, 79 (1964); Hardin v. Santa Fe Reporter, Inc., 745 F.2d 1323,\\n\\n1326 (10th Cir. 1984) (holding that reporter’s negligence in failing to investigate a\\n\\nsource’s background and in writing the article could not establish actual malice). It\\n\\nrequires more than showing a publication was false and defamatory, New York Times,\\n\\n376 U.S. at 288, and more than “a departure from reasonably prudent conduct,” Harte-\\n\\nHanks Commc’ns, Inc. v. Connaughton, 491 U.S. 657, 688 (1989).\\n\\n Actual malice is a subjective standard that requires proof of a “mental element.”\\n\\nMonitor Patriot Co. v. Roy, 401 U.S. 265, 276 (1971); see Harte-Hanks, 491 U.S. at 688\\n\\n(stating actual malice is a subjective standard). The actual malice inquiry thus “rests\\n\\nentirely on an evaluation of [the publisher’s] state of mind when he wrote his initial\\n\\n\\n\\n 29\\n\\freport, or when he checked the article against that report.” Bose Corp. v. Consumers\\n\\nUnion of U.S., Inc., 466 U.S. 485, 494 (1984).\\n\\n In St. Amant v. Thompson, 390 U.S. 727 (1968), the Supreme Court explained:\\n\\n [R]eckless conduct is not measured by whether a reasonably\\n prudent man would have published, or would have\\n investigated before publishing. There must be sufficient\\n evidence to permit the conclusion that the defendant in fact\\n entertained serious doubts as to the truth of his publication.\\n Publishing with such doubts shows reckless disregard for\\n truth or falsity and demonstrates actual malice.\\n\\nId. at 731.\\n\\n A plaintiff does not create a jury question of actual malice by showing that a\\n\\npublisher failed to investigate before publishing. Gertz, 418 U.S. at 332; St. Amant,\\n\\n390 U.S. at 731; Beckley Newspapers Corp. v. Hanks, 389 U.S. 81, 84-85 (1967) (per\\n\\ncuriam)17; New York Times, 376 U.S. at 28718; Revell v. Hoffman, 309 F.3d 1228,\\n\\n1233 (10th Cir. 2002). Nor does a plaintiff do so by showing that a publisher\\n\\nmisinterpreted the source material or omitted details favorable to the plaintiff. Time,\\n\\nInc. v. Pape, 401 U.S. at 282, 290-92 (1971). A publisher’s decision to omit details\\n\\n\\n\\n 17\\n In Beckley, for example, the Supreme Court, having reviewed testimony\\nfrom the newspaper’s general manager that no investigation of the allegedly\\ndefamatory statements had been made, held, “[I]t cannot be said on this record that\\nany failure of petitioner to make a prior investigation constituted proof sufficient to\\npresent a jury question whether the statements were published with reckless disregard\\nor whether they were false or not.” 389 U.S. at 84-85.\\n 18\\n In New York Times, the Court found the evidence insufficient to establish\\nactual malice even though checking news stories in the Time’s own files would have\\nrevealed the falsity of a part of the challenged publication. 376 U.S. at 287-88.\\n 30\\n\\ffavorable to the plaintiff does not, itself, show actual malice. See id. (finding no\\n\\nactual malice where a publisher did not specify that “it was reporting no more than\\n\\nallegations”). Even “a deliberate alteration of the words uttered by a plaintiff does\\n\\nnot equate with [actual malice] . . . unless the alteration results in a material change\\n\\nin the meaning conveyed by the statement.” Masson v. New Yorker Magazine, Inc.,\\n\\n501 U.S. 496, 517 (1991).\\n\\n Actual malice may be found when a publisher had a “subjective awareness of\\n\\nprobable falsity.” Gertz, 418 U.S. at 334 n.6. For example, evidence that a publisher\\n\\nknew its sources were unreliable but made no attempt to verify their information,\\n\\nCurtis Publ’g Co. v. Butts, 388 U.S. 130, 157-59 (1967), or that a publisher knew it\\n\\nwas publishing contested allegations but deliberately ignored sources or information\\n\\nthat might reveal what actually happened, Harte-Hanks, 491 U.S. at 690, may\\n\\nestablish actual malice. Other examples include “a story [that] is fabricated by the\\n\\ndefendant, is the product of his imagination, or is based wholly on an unverified\\n\\nanonymous telephone call”; circumstances where the published statements “are so\\n\\ninherently improbable that only a reckless man would have put them in circulation”;\\n\\nor situations “where there are obvious reasons to doubt the veracity of the informant\\n\\nor the accuracy of his reports.” St. Amant, 390 U.S. at 732.\\n\\n Most of the Supreme Court’s actual malice case law, including New York\\n\\nTimes, comes from defamation suits. But the Supreme Court has, like Oklahoma,\\n\\napplied the actual malice standard to a false light claim. In Time, Inc. v. Hill, 385\\n\\n 31\\n\\fU.S. 374 (1967), the Court held that “the constitutional protections for speech and\\n\\npress preclude[d] the application of [a] New York [false light invasion of privacy]\\n\\nstatute . . . in the absence of proof that the defendant published the report with\\n\\nknowledge of its falsity or in reckless disregard of the truth.” Id. at 387-88.\\n\\n b. Oklahoma actual malice cases\\n\\n Because Oklahoma courts have expressly adopted the New York Times actual\\n\\nmalice standard, Oklahoma’s defamation and false light case law is consistent with\\n\\nthe actual malice principles described above.19 Like the Supreme Court, Oklahoma\\n\\n\\n 19\\n In Dun & Bradstreet, Inc. v. Greenmoss Builders, Inc., 472 U.S. 749, 758-61\\n(1985), the Supreme Court held that the First Amendment requires proof of actual malice\\nonly when the statements at issue involve matters of public concern. In recognizing the\\nfalse light invasion of privacy tort and equating the third element of that tort to the New\\nYork Times actual malice standard, Oklahoma courts have not drawn a distinction\\nbetween false light claims for statements involving matters of public concern as opposed\\nto private concern. We need not address whether Oklahoma courts would draw any such\\ndistinction, because Mr. Talley has not argued that the statements at issue here involve\\nmatters of private concern or that the actual malice standard should not apply in this case.\\n Moreover, the form, content, and context of the SI publication establish that the\\nstatements at issue here involve a matter of public concern. See id. at 761 (explaining\\nthat when determining whether allegedly libelous statements involve a matter of public\\nconcern, courts should consider the form, content, and context of the speech). The\\nstatements were printed in a widely-circulated publication. Compare Spacecon, 713 F.3d\\nat 1039 (holding that “a documentary meant to be shown to the public” qualified as\\nspeech on a matter of public concern), with Dun & Bradstreet, 472 U.S. at 762 (holding\\nthat a credit report “made available only to five subscribers” was not speech on a matter\\nof public concern).\\n More telling, they involved allegations against the football program at one of\\nOklahoma’s major publicly-funded universities. See City of San Diego v. Roe, 543 U.S.\\n77, 83-84 (2004) (“[P]ublic concern is something that is a subject of legitimate news\\ninterest; that is, a subject of general interest and of value and concern to the public . . . .”);\\nSpacecon, 713 F.3d at 1039 (holding that a documentary film exposing mistreatment of\\nMexican construction workers involved speech on a matter of public concern); Dun &\\n 32\\n\\fcourts have recognized that actual malice exists when “the defendant had a high\\n\\ndegree of awareness of probable falsity or in fact entertained serious doubts as to the\\n\\ntruth of the publication.” Colbert, 747 P.2d at 291. They also have noted that\\n\\n“negligence is not enough to rise to the level of ‘actual malice’” and that “malice\\n\\nmay not be inferred simply from showing that the publication was untrue.” Herbert,\\n\\n992 P.2d at 328. As in New York Times, St. Amant, and other Supreme Court cases,\\n\\nOklahoma courts have stated that “failure to investigate does not establish the actual\\n\\nmalice standard.” Jurkowski v. Crawley, 637 P.2d 56, 61 (Okla. 1981). They also\\n\\nhave followed the Supreme Court in treating the actual malice standard as a\\n\\nsubjective inquiry and have stated that actual malice exists only when there is\\n\\n“sufficient evidence to permit the conclusion that the defendant in fact entertained\\n\\nserious doubts as to the truth of his publication.” Washington v. World Publ’g. Co.,\\n\\n506 P.2d 913, 918 (Okla. 1972) (quotations omitted).20\\n\\n\\n\\nBradstreet, 472 U.S. at 762 (holding that credit report was not speech on a matter of\\npublic concern because it was “solely in the individual interest of the speaker and its\\nspecific business audience”). Thus, even if Oklahoma courts would distinguish between\\nspeech on matters of public and private concern, the actual malice standard applies in this\\ncase.\\n 20\\n In New York Times, 376 U.S. 254, and Curtis Publishing Co. v. Butts, 388 U.S.\\n130, the Supreme Court held that the actual malice requirement applies when the\\nallegedly defamatory speech is about a public figure or public official. In Gertz, the\\nCourt held that the actual malice standard applies to public figures but does not apply in\\ncases brought by private-figure plaintiffs. 418 U.S. at 345-48.\\n In 1967, the Supreme Court said in Hill that the New York Times actual malice\\nstandard also applies to false light cases. See supra note 16. It is not clear whether the\\n1974 Gertz holding—which restricts the actual malice standard to cases brought by\\n 33\\n\\f B. Analysis\\n\\n Although the parties have briefed both the first and third false light elements,\\n\\nMr. Talley’s failure to establish either element will defeat his claim. We can resolve\\n\\nthis appeal by addressing only the third element—actual malice.\\n\\n Evidence on Preparation of the Article Lacks Proof of Actual Malice\\n\\n The record shows the Defendants conducted a long and thorough investigation\\n\\nbefore publishing their article. For ten months, the reporters sought out and spoke to\\n\\ndozens of OSU players, coaches, and administrators. They recorded their interviews\\n\\nelectronically and in writing. They consulted their notes and each other while\\n\\ndrafting the article, and they occasionally re-interviewed individuals to ensure that\\n\\n\\n\\n\\npublic officials and public figures—similarly limits the standard’s application in false\\nlight cases. As one leading commentator has noted, “[a] significant number of cases have\\nheld that Hill should be regarded as modified by Gertz, and that actual malice is not\\nrequired . . . in false light cases with private figure plaintiffs.” 2 Rodney A. Smolla, Law\\nof Defamation § 10:16 (2d ed. Nov. 2018 update). But “there is also . . . substantial\\nauthority, including the Restatement Second, Torts, for the proposition that all false light\\nclaims must meet the actual malice standard.” Id. Gertz thus leaves open the question of\\nwhether actual malice is required in all false light cases, or only in cases involving\\nstatements about public officials or public figures. See Restatement (Second) of Torts\\n§652E, cmt. d.\\n We need not address this question for two reasons. First, Mr. Talley has not\\nargued that he is a private figure. Second, Oklahoma courts have applied the actual\\nmalice standard in false light cases involving both public- and private-figure plaintiffs.\\nSee Colbert, 747 P.2d at 288, 291 (Okla. 1987) (applying the actual malice standard\\nin a false light case involving a plaintiff who was “unquestionably a private figure”);\\nGrogan, 256 P.3d at 1029 (holding that the actual malice standard is “required for false\\nlight invasion of privacy cases involving public figures”).\\n 34\\n\\ftheir information was correct. They also fact-checked and edited their article several\\n\\ntimes and had their legal team review the piece before publication.\\n\\n Unlike the publishers in Harte-Hanks, the Defendants did not deliberately\\n\\nignore sources that might have disputed their account. See 491 U.S. at 690. Rather,\\n\\nthey interviewed multiple sources around the country who substantially corroborated\\n\\neach other. They also verified the information they published by re-interviewing\\n\\ntheir sources and fact-checking the final piece. Mr. Talley has provided no evidence\\n\\nthat the Defendants “fabricated” their story, based their claims about him on “an\\n\\nunverified anonymous telephone call,” or published allegations that were “so\\n\\ninherently improbable that only a reckless man would have put them into\\n\\ncirculation.” St. Amant, 390 U.S. at 732. He thus “proffers no evidence indicating\\n\\nthat [the Defendants] entertained doubts regarding the truth of the statements in [the\\n\\npublication].” Revell, 309 F.3d at 1233.\\n\\n In addition, the record shows that the reporters had ample evidence to support\\n\\nthe statements in the article about Mr. Talley. Mr. Pogi and Mr. Talley told the\\n\\nreporters that Mr. Pogi lived on Mr. Talley’s ranch without paying rent; four players\\n\\n(Mr. Shaw, Mr. Mack, Mr. Brown, and Mr. Johnson) said Mr. Talley paid them or\\n\\nothers they knew for speaking engagements; and three (Mr. Girtman, Mr. Carter, and\\n\\nMr. Johnson) said Mr. Talley overpaid them for work. At least two of these sources\\n\\n(Mr. Mack and Mr. Carter) brought up Mr. Talley’s name without prompting. And,\\n\\nas we show below, Mr. Pogi made statements in his interview that the Defendants\\n\\n 35\\n\\fcould reasonably have interpreted to mean he did not work at Mr. Talley’s ranch.\\n\\nFurther, the players were interviewed independently of one another in different parts\\n\\nof the country and provided consistent accounts.\\n\\n In sum, the evidence shows the Defendants’ article was based on an extended\\n\\nresearch process and was not the product of deliberate “falsification,” Pape, 401 U.S.\\n\\nat 289, or the “use of calculated falsehood,” Garrison, 379 U.S. at 75. There is no\\n\\nindication they published with “a high degree of awareness of probable falsity or . . .\\n\\nentertained [any] serious doubts as to the truth of the publication.” Colbert, 747 P.2d\\n\\nat 291. Ample evidence supported their reporting about Mr. Talley, who cannot\\n\\nshow with “convincing clarity” that the Defendants acted with actual malice. Id.\\n\\n Mr. Talley’s Arguments\\n\\n Mr. Talley argues the Defendants exhibited actual malice by (a) deliberately\\n\\nmisstating facts about Mr. Pogi’s rent arrangement, (b) falsely reporting that Mr.\\n\\nTalley paid players for speaking engagements, (c) relying on biased and non-credible\\n\\nsources, (d) writing with a slanted agenda, and (e) publishing erroneous and incorrect\\n\\nstatements. These arguments do not withstand scrutiny.\\n\\n a. Mr. Pogi’s rent\\n\\n Mr. Talley argues the Defendants published with actual malice by\\n\\n“inaccurately reporting” that Mr. Pogi lived on Mr. Talley’s property rent-free. Aplt.\\n\\nBr. at 15. The Defendants reported in the article that “[Mr.] Pogi denies that he did\\n\\nany work.” Aplt. App., Vol. II at A452. According to Mr. Talley, however, “the\\n\\n 36\\n\\finterview recording [between Mr. Evans and Mr. Pogi] clearly states Aso Pogi\\n\\nworked extremely hard in exchange for rent.” Aplt. Reply Br. at 5; see also Aplt. Br.\\n\\nat 6, 16. As a result, Mr. Talley characterizes this allegation in the article as\\n\\n“blatantly false” and “misconstrued,” Aplt. Br. at 16-17, and he suggests the\\n\\nDefendants’ failure to “accurately report what the interviewees stated” is evidence of\\n\\nactual malice, id. at 20.\\n\\n This argument is unavailing. The article states:\\n\\n Quarterback Aso Pogi (1999 to 2002) says he and another\\n player lived at Talley’s ranch one summer rent-free. In\\n retrospect Pogi says, “It’s a big deal. I was the starting\\n quarterback.” (Talley says that Pogi lived at his ranch and\\n had to work to cover his rent; Pogi denies that he did any\\n work.).\\n\\nAplt. App., Vol. II at A452. The interview recording does not show this passage\\n\\n“obviously misquote[s] [or] inaccurately report[s] what [Mr.] Pogi stated.” Aplt.\\n\\nReply Br. at 5. Further, it does not suggest the Defendants published with “a high\\n\\ndegree of awareness of . . . probable falsity.” Garrison, 379 U.S. at 74.\\n\\n In the interview recording, Mr. Pogi said he lived on Mr. Talley’s property\\n\\nrent-free. Pogi Interview at 17:32-18:13. He also stated, as the Defendants reported,\\n\\n“It’s a big deal. I mean, I was the starting quarterback.” Id. at 23:20-25. Nowhere\\n\\nin the interview does Mr. Pogi state that he worked “extremely hard in exchange for\\n\\nrent,” as Mr. Talley insists. Aplt. Reply Br. at 5.\\n\\n\\n\\n\\n 37\\n\\f After reviewing the entire recording of Mr. Evans’s interview with Mr. Pogi,\\n\\nwe found only one statement—“I did a lot,” Pogi Interview at 12:02-12:04—that\\n\\ncould possibly indicate that Mr. Pogi worked on the ranch at all. But that statement\\n\\nis ambiguous. Mr. Pogi did not specifically state what it was he “did a lot.” Further,\\n\\nhe made the statement after telling Mr. Evans that he was “on the road a lot to speak”\\n\\nand had participated in “a lot” of speaking engagements. Id. at 10:00-11:51. It is\\n\\ntherefore possible the statement referenced his speaking engagements rather than\\n\\nranch work. Further, when Mr. Evans prompted, “You lived [on the ranch], but you\\n\\nnever, you never worked—,” Mr. Pogi responded, “I ne—I didn’t, I didn’t do\\n\\nanything like—.” Id. at 12:08-12:11. And a few questions later, Mr. Pogi insisted he\\n\\n“had no arrangement” with Mr. Talley. Id. at 17:29-17:30.\\n\\n The interview recording thus includes no definitive statement that Mr. Pogi\\n\\nworked on the ranch. Although his statement that he “did a lot” might be understood\\n\\nto mean he worked, it could reasonably be interpreted as a reference to speaking\\n\\nengagements. At most, the Defendants misinterpreted the statement, but a\\n\\ndefendant’s misinterpretation of source material that “bristle[s] with ambiguities”\\n\\ndoes not constitute actual malice. Pape, 401 U.S. at 290 (holding that when faced\\n\\nwith ambiguous source material, a defendant’s “deliberate choice of [one]\\n\\n\\n\\n\\n 38\\n\\finterpretation, though arguably reflecting a misconception, [is] not enough to create a\\n\\njury issue of ‘malice’ under New York Times”).21\\n\\n Accordingly, even if the Defendants misinterpreted Mr. Pogi’s statement that\\n\\nhe “did a lot,” their misunderstanding would not establish actual malice. The\\n\\nevidence does not support Mr. Talley’s contention that the Defendants “blatantly\\n\\nmisquoted what Aso Pogi said,” Aplt. Reply Br. at 5, or show they published\\n\\nstatements about Mr. Pogi with reckless disregard for the truth.22\\n\\n\\n 21\\n See also Orr v. Argus-Press Co., 586 F.2d 1108, 1116 (6th Cir. 1978)\\n(finding no actual malice when defendants published a rational interpretation of\\nambiguous source material); Simmons Ford, Inc. v. Consumers Union of U.S., Inc.,\\n516 F. Supp. 742, 751-52 (S.D.N.Y. 1981) (finding no actual malice when defendants\\npublished a reasonable but mistaken interpretation of a regulation that “hardly\\nqualify[ed] as a model of clarity”); Farrakhan v. N.Y.P. Holdings, Inc., 168 Misc. 2d\\n536, 542 (N.Y. Sup. Ct. 1995) (concluding that “even if defendants misinterpreted\\n[an interviewee’s] statement, such misinterpretation does not arise to a level of\\nconstitutional malice”); Suozzi v. Parente, 616 N.Y.S.2d 355, 359 (N.Y. App. Div.\\n1994) (noting that actual malice cannot “be founded on the misinterpretation of a\\nsource or the resolution of an ambiguity adversely to the plaintiff”).\\n 22\\n Mr. Talley’s insistence that the “Defendants blatantly misquoted what Aso\\nPogi said,” Aplt. Reply Br. at 5, may be based on an interview that Chuck Smrt,\\nOSU’s outside compliance consultant, conducted with Mr. Pogi during the NCAA’s\\ninvestigation of the OSU football program after the SI article series was published.\\nIn this interview, Mr. Pogi claimed he “worked pretty hard on [Mr. Talley’s] farm”\\nand that there was “a lost [sic] land to keep up as far as cutting grass, as far as\\ncleaning the pool and just doing quite a bit of things. Feeding the animals, it was\\nevery single day.” Aplt. App., Vol. IV at A853. These statements support Mr.\\nTalley’s contention that Mr. Pogi did, in fact, work in exchange for lodging. But\\nbecause this interview occurred after the SI article was published, it does not prove\\nthe Defendants deliberately misquoted Mr. Pogi—or otherwise acted with actual\\nmalice—at the time of the original publication. See Bose, 466 U.S. at 494 (noting\\nthat “the actual-malice determination rests entirely on an evaluation of [the author’s]\\nstate of mind when he wrote his initial report” (emphasis added)).\\n 39\\n\\f b. Payment for speaking engagements\\n\\n Mr. Talley also argues the Defendants acted with actual malice when they\\n\\nreported he paid players to speak at events “in violation of NCAA rules and OSU\\n\\npolicy.” Aplt. Br. at 16. According to Mr. Talley, “Defendants were made aware . . .\\n\\nthat ‘speaking’ meant reimbursement for gas and food” but nonetheless “deliberately\\n\\nchose to disregard its true meaning in order to portray [Mr. Talley] as paying in\\n\\nviolation of rules.” Id. at 18. Mr. Talley also argues that “Defendants never had\\n\\nreason to believe [Mr. Talley] was breaking the rules or illegally paying athletes.”23\\n\\nId.\\n\\n These arguments, too, are unpersuasive. Although some players insisted they\\n\\nwere reimbursed only for expenses, many (including Mr. Johnson, Mr. Brown, Mr.\\n\\nWright, and Mr. Shaw) admitted that they or others they knew had received speaking\\n\\n\\n\\n\\n 23\\n To support his argument, Mr. Talley adds that “Defendants knew [the]\\nNCAA investigated the subject and never determined any violation of the rules by\\n[Mr. Talley].” Aplt. Br. at 18. This argument is unpersuasive. The NCAA\\ninvestigated the OSU football program after the Defendants published “The Dirty\\nGame.” See, e.g., Aplt. App., Vol. III at A607 (transcript of NCAA investigatory\\ninterview with OSU officials, dated October 17, 2013). As noted above, the actual\\nmalice issue focuses on what the author knew (or did not know) at the time of\\npublication, Bose, 466 U.S. at 494, and “[e]vidence concerning events after an article\\nhas been printed and distributed, has little, if any, bearing on that issue,” Forbes Inc.\\nv. Granada Biosciences, Inc., 124 S.W.3d 167, 174 (Tex. 2003). If, as Mr. Talley\\nclaims, the NCAA found that his payments did not violate any rules, those findings\\nwere not available to the Defendants when they published the article and could not\\nhave influenced their state of mind at the time of publication. The NCAA\\ninvestigation is thus irrelevant.\\n\\n 40\\n\\ffees. Mr. Johnson, for example, said Mr. Talley once paid him 100 dollars to speak\\n\\nfor 20 minutes. Johnson Interview at 2:42-3:02. Even if Mr. Talley paid speaking\\n\\nfees to certain players and not others, the Defendants still had grounds to believe and\\n\\nreport that at least some players received money beyond simple reimbursement. That\\n\\nsome players denied receiving speaking fees or claimed they were only reimbursed\\n\\nfor expenses does not prove the Defendants “in fact entertained serious doubts” about\\n\\nthe players who reported otherwise. St. Amant, 390 U.S. at 731; Colbert, 747 P.2d\\n\\nat 291.\\n\\n In addition, Mr. Schecter’s notes from his interview with Mr. Talley reflect\\n\\nthat Mr. Talley admitted to paying speaking fees.24 Shortly after meeting with Mr.\\n\\nTalley, Mr. Schecter sent Mr. Dohrmann an e-mail listing “John Talley[’s] Responses\\n\\n\\n\\n\\n 24\\n Although Mr. Schecter recorded the interview with Mr. Talley, the audio file\\nwas corrupted. See supra note 6. Accordingly, Mr. Schecter’s e-mail to Mr. Dohrmann\\nis the only recorded source of information about the interview. In his affidavit, Mr.\\nSchecter stated that he drafted this e-mail shortly after speaking with Mr. Talley: “When\\nI got back to my hotel, I listened to the recording, then made notes, including writing\\ndown some direct quotes, as I re-listened to the audio. I emailed my notes to [Mr.]\\nDohrmann and [Mr.] Evans.” Aplt. App., Vol. II at A443. He also testified at his\\ndeposition that he listened to the interview recording “[i]mmediately after I got back to\\nmy hotel room . . . I would say within an hour after I finished my conversation with Mr.\\nTalley.” Id. at A411.\\n During his deposition, Mr. Talley claimed Mr. Schecter “was in a hurry” and\\n“didn’t really give [him] an opportunity to” explain himself fully during the interview.\\nAplt. App., Vol I at A204. But Mr. Talley did not challenge any of the information or\\nquotations contained in the e-mail. In fact, Mr. Talley reviewed the entire e-mail and\\nconfirmed he made all the statements that Mr. Schecter attributed to him. Id. at A202-05.\\n\\n 41\\n\\fto allegations we have against him.” Aplt. App., Vol. II at A520. On the topic of\\n\\n“[p]aying players for speaking engagements,” Mr. Schecter wrote the following:\\n\\n [Mr. Talley said:] “It depends on . . . there’s a\\n NCAA rule that if they’re paying us . . . and most of the\\n time it’s for team building activities. It’s not just\\n speaking. But we have done some school assemblies. Last\\n year we did four all sports banquets. And if the school is\\n used to paying someone than [sic] it’s legal to get paid.\\n But there’s a fine line.”\\n\\n Talley says he ran everything (the jobs and the\\n speaking gigs) through the associate compliance director\\n who is assigned to the football team.\\n\\n “If [players] were allowed to be paid (for speaking\\n engagements) they were paid. We’ve spoken in\\n churches.[”] (They got paid for speaking in churches\\n “only if the churches paid someone before.”) Talley says a\\n typical speaking fee would be $25-$50. “I can always pay\\n for if they’re driving their car we can pay for gas and stuff\\n like that.”\\n\\n Players said it was $100 or more per speaking\\n engagement. “It depends on where we were going,” Talley\\n said. “I’m not saying they couldn’t because it was a long\\n time ago, but usually it was not that much.”\\n\\nId. at A521. Although it is possible Mr. Schecter and Mr. Dohrmann misunderstood\\n\\nor misinterpreted Mr. Talley’s comments, these interview notes suggest the\\n\\nDefendants had a reasonable basis to believe Mr. Talley paid speaking fees to some\\n\\nplayers.25 Further, as discussed above, a defendant’s misinterpretation of source\\n\\n\\n 25\\n During his deposition, Mr. Talley acknowledged that his statements to Mr.\\nSchecter were ambiguous. When asked, “Do you find anything in [Mr.] Schecter’s\\nemail that would suggest you made [the] distinction [between speaking and team\\nbuilding] to him?,” Mr. Talley responded, “Yes and no. Yes, I was trying to. No, he\\n 42\\n\\fmaterial does not necessarily establish actual malice. Pape, 401 U.S. at 290. Thus,\\n\\neven if the Defendants misunderstood Mr. Talley’s claim that “[players] were paid”\\n\\nto mean speaking fees rather than reimbursements, that misunderstanding would not\\n\\nprove they published with actual malice.\\n\\n In sum, although some players claimed they did not receive money to speak,\\n\\nmultiple players reported that Mr. Talley arranged paid speaking engagements.\\n\\nFurther, notes from Mr. Schecter’s interview with Mr. Talley suggest that Mr. Talley\\n\\nadmitted to paying speaking fees. In publishing these allegations, the Defendants did\\n\\nnot show reckless disregard for the truth. Rather, they reported information that\\n\\nmultiple sources confirmed and corroborated. The record does not suggest the\\n\\nDefendants “in fact entertained serious doubts as to the truth of [their] publication,”\\n\\nSt. Amant, 390 U.S. at 731; Colbert, 747 P.2d at 291, and Mr. Talley identifies no\\n\\nevidence to demonstrate with “convincing clarity” that the Defendants reported about\\n\\nhis paying players for speaking engagements with actual malice, New York Times,\\n\\n376 U.S. at 286-87.\\n\\n c. Credibility of article sources\\n\\n Mr. Talley contends the Defendants demonstrated actual malice by “[seeking]\\n\\nout non-credible, untrustworthy, and troubled sources,” Aplt. Br. at 21, and by\\n\\n\\n\\nwas in a hurry to get out of my van. So he didn’t really give me an opportunity to.\\n. . . I was trying to clarify that I reimburse people for going to speak. . . . But he\\ndidn’t stay around long enough to hear it.” Aplt. App., Vol. I at A204.\\n\\n 43\\n\\finterviewing and quoting OSU players of “suspect veracity,” Aplt. Reply Br. at 8.\\n\\nHe notes that some of the players featured in the article had “troubled histor[ies] . . .\\n\\nincluding drug usage, scholastic problems with OSU, and criminal issues.” Aplt. Br.\\n\\nat 14. He claims the Defendants’ “conscious decision to feature those interviewees in\\n\\nthe article . . . is evidence of Defendants’ malicious intent.” Aplt. Reply Br. at 8.\\n\\nWe disagree.\\n\\n Although the record shows the Defendants interviewed and quoted some OSU\\n\\nplayers who used drugs or had criminal records,26 “[s]ources need not be paragons of\\n\\nvirtue for journalists safely to rely on them.” 1 Robert D. Sack, Sack on Defamation:\\n\\nLibel, Slander, and Related Problems §5:5.2(C) at 5-109 (5th ed. 2017). Courts have\\n\\nconsistently held that reliance on tainted or troubled sources does not alone establish\\n\\nactual malice. See, e.g., Pemberton v. Birmingham News Co., 482 So. 2d 257, 266\\n\\n\\n\\n\\n 26\\n For their segment on Mr. Talley, the Defendants relied primarily on\\nstatements and interviews from Mr. Girtman, Mr. Shaw, Mr. Mack, Mr. Brown, Mr.\\nWright, Mr. Johnson, Mr. Lawson-Kennedy, Mr. Pogi, and Mr. Carter. The\\ninterviews revealed that several of these sources had substance abuse problems: Mr.\\nGirtman used drugs and failed drug tests, Aplt. App., Vol. III at A801; Mr. Johnson\\nadmitted to smoking marijuana, Aplt. App., Vol. II at A490, A492-93; Mr. Shaw\\nfailed drug tests and used a masking agent to conceal his marijuana use, id. at A501;\\nand Mr. Mack and Mr. Brown either used drugs or knew of other players who did,\\nid.at A389, A464. The record also suggests at least two of these players may have\\nhad criminal records. Mr. Talley’s original complaint stated that Mr. Shaw had been\\nconvicted of larceny and burglary, though it is not clear that the Defendants knew\\nthis when they published their article. Aplt. App., Vol. IV at A909. In addition, the\\ncall between Mr. Evans and Mr. Wright was timed and took place over a controlled\\nline which indicates Mr. Wright was either in jail or prison. Evans Wright Interview\\nat 10:15-10:39.\\n 44\\n\\f(Ala. 1985) (finding that defendant’s reliance on statements from an ex-convict was\\n\\ninsufficient to show actual malice); Secord v. Cockburn, 747 F. Supp. 779, 794\\n\\n(D.D.C. 1990) (holding that “[t]he use of convicted felons cannot alone constitute a\\n\\nfact of actual malice”). The fact that some of the Defendants’ sources were not\\n\\n“paragons of virtue” is thus insufficient to show actual malice. Sack, §5:5.2(C) at 5-\\n\\n109.\\n\\n Courts also have noted that “newspaper investigation of reports of corruption\\n\\nmust often obtain first-hand corroboration from those present in the barrooms or\\n\\ngambling houses, rather than from citizens who spend their time only at home, in\\n\\nchurch, or at work in less colorful occupations.” Kidder v. Anderson, 354 So.2d 1306\\n\\n(La. 1978). Here, the five-article series reported on drug use, financial misconduct,\\n\\nand academic dishonesty in the OSU football program. To prepare this report, the\\n\\nDefendants necessarily had to rely on sources who may have participated in these\\n\\nactivities. Rather than demonstrating that the Defendants published with actual\\n\\nmalice, this shows they sought information from the sources who were in the best\\n\\nposition to describe these possible features of the OSU program. See Pemberton, 482\\n\\nSo. 2d at 266 (noting that “the fact that [a source] was an ex[-]convict did not\\n\\ndiminish his credibility . . . but rather made it more probable that he would have\\n\\ninside information” that could aid the defendants’ investigation).\\n\\n Although some of the interviewees who provided information about Mr. Talley\\n\\nused drugs or had criminal records, the reporters stated they “did not observe any . . .\\n\\n 45\\n\\ffacts that would cause [them] to question [the players’] credibility.” Aplt. App., Vol.\\n\\nII at A440 (Dohrmann Affidavit); see id. at A390-91 (Evans Affidavit). The SI\\n\\nreporters interviewed multiple individuals—including some who did not have\\n\\ntroubled pasts—and stated that, though “players spoke to [them] independently, at\\n\\ndifferent times and different places, . . . the facts those players provided were\\n\\nconsistent with and corroborative of one another.” Id. at A439-40 (Dohrmann\\n\\nAffidavit); see id. at A390-91 (Evans Affidavit). “That these . . . sources\\n\\ncorroborated each other’s allegations sufficiently establishes [that the Defendants]\\n\\ndispelled [any of their] doubts” about the players’ veracity. Spacecon, 713 F.3d at\\n\\n1046. Mr. Talley thus has not shown there were “obvious reasons to doubt the\\n\\nveracity” of the player sources. St. Amant, 390 U.S. at 732.\\n\\n In sum, Mr. Talley has failed to show the Defendants’ use of “troubled” or\\n\\ntainted sources demonstrated actual malice. Aplt. Br. at 14. The record shows the\\n\\npassages relating to Mr. Talley were based on “sources which were not believed to be\\n\\nfalse.” Rosanova v. Playboy Enters., Inc., 580 F.2d 859, 862 (5th Cir. 1978). Unlike\\n\\nthe defendants in Butts, the Defendants did not rely on a single, questionable source\\n\\nwithout fact-checking, interviewing additional witnesses, or seeking independent\\n\\nsupport. 388 U.S. at 157-58. And this case has no resemblance to Harte-Hanks,\\n\\nwhere the defendants knew the facts in their publication “had been denied . . . by five\\n\\nother witnesses before the story was published.” 491 U.S. at 691. Although the\\n\\narticle here quoted some of the players who had “troubled histor[ies],” Aplt. Br. at\\n\\n 46\\n\\f14, Mr. Talley has not shown the Defendants had “obvious reasons to doubt the\\n\\nveracity of the [players] or the accuracy of [their] reports,” Harte-Hanks, 491 U.S. at\\n\\n688 (quotations omitted). Nor has he shown that the players’ drug use or other\\n\\nmisconduct gave the Defendants a “high degree of awareness of probable falsity\\n\\nor . . . serious doubts as to the truth of [their] publication.” Colbert, 747 P.2d at 291.\\n\\n d. Slant, bias, motive, and omissions\\n\\n Mr. Talley argues the Defendants exhibited actual malice by presenting a\\n\\nslanted, biased, and “sensationalized” narrative. Aplt. Br. at 4. He contends the\\n\\nDefendants crafted their story to fit their “own investments and motives,” id. at 13,\\n\\nand demonstrated actual malice by “specifically target[ing],” Aplt. Reply Br. at 8, his\\n\\nreputation “as a respected pastor and mentor,” id. at 2. He also claims the\\n\\nDefendants “omit[ted] material statements.” Aplt. Br. at 21. These arguments also\\n\\nfail.\\n\\n i. Slant and bias\\n\\n Mr. Talley suggests the “Defendants sought a certain narrative from\\n\\ninterviewees,” id. at 14, and “achieved the story they desired to portray,” id., by\\n\\n“seek[ing] out biased individuals who would provide a sensational story,” id. at 4.\\n\\nBut he provides no concrete supporting evidence to show this was the case. Even if\\n\\nhe could, it would not show the Defendants published with actual malice.\\n\\n Although the Defendants may have developed a theme for their article—their\\n\\ne-mail correspondence, for example, includes a discussion of whether a particular\\n\\n 47\\n\\fplayer’s “experience fits our narrative,” Aplt. App., Vol. II at A498—that alone does\\n\\nnot show they doubted the truth of their publication. Indeed, the Defendants, not Mr.\\n\\nTalley, are entitled to choose their theme. It is the “function of editors” to decide\\n\\n“[t]he choice of material to go into a newspaper.” Miami Herald Publ’g Co. v.\\n\\nTornillo, 418 U.S. 241, 255 (1974). Further, “[t]he fact that a commentary is one\\n\\nsided . . . has no tendency to prove that the publisher believed it to be false.”\\n\\nMcFarlane v. Esquire Magazine, 74 F.3d 1296, 1307 (D.C. Cir. 1996). Thus, to the\\n\\nextent Mr. Talley could provide evidence to show the Defendants wrote an article\\n\\nconsistent with a theme or narrative, he has not established they published with actual\\n\\nmalice.\\n\\n ii. Motive\\n\\n Mr. Talley contends the Defendants had “independent knowledge of [Mr.\\n\\nTalley’s] standing in the community,” Aplt. Br. at 20, and “specifically targeted” his\\n\\n“reputation for honesty,” Aplt. Reply Br. at 8. He further claims the Defendants had\\n\\n“obvious reasons to doubt the veracity of the . . . information discovered in their\\n\\ninvestigations . . . due to . . . [their] own investments and motives.” Aplt. Br. at 13.\\n\\n Despite his contention that the Defendants published with improper motives,\\n\\nMr. Talley does not specify what those “investments and motives” might have been.\\n\\nId. He also does not identify any evidence that the Defendants “specifically targeted”\\n\\nhim. Aplt. Reply Br. at 8. The Defendants spent only a fraction (442 words) of their\\n\\n20,000-word, five-part series discussing Mr. Talley, which suggests their purpose\\n\\n 48\\n\\fwas not to tarnish his reputation. But even if the Defendants “targeted” Mr. Talley,\\n\\nthat would not prove they had doubts about the article’s veracity or published with\\n\\nactual malice. See, e.g., Spacecon, 713 F.3d 1028 (noting that “a publisher’s\\n\\nadversarial stance . . . is not necessarily indicative of actual malice”) (quotations\\n\\nomitted).\\n\\n Although “[t]he motivation behind a publication is a factor to consider,” id. at\\n\\n1042, “courts must be careful not to place too much reliance on [motive],” Harte-\\n\\nHanks, 491 U.S. at 668; see also Old Dominion Branch No. 496, Nat’l Ass’n of Letter\\n\\nCarriers v. Austin, 418 U.S. 264, 281-82 (stating that “ill will toward the plaintiff, or\\n\\nbad motives are not elements of the New York Times standard”). As this court said in\\n\\nSpacecon, “[E]vidence of [defendant’s] . . . bias is not enough to show he acted with\\n\\nactual malice.” 713 F.3d at 1043; see also Harte-Hanks, 491 U.S. at 665;\\n\\nTavoulareas v. Piro, 817 F.2d 762, 795 (D.C. Cir. 1987) (stating a publisher’s\\n\\n“adversarial stance” may be “fully consistent with professional, investigative\\n\\nreporting” and is not necessarily “indicative of actual malice”) (quotations omitted).\\n\\nMr. Talley has not identified evidence of the Defendants’ bias against him, much less\\n\\nshown that bias established actual malice.\\n\\n iii. Omissions\\n\\n Mr. Talley briefly argues the Defendants showed actual malice by “omitting\\n\\nmaterial statements.” Aplt. Br. at 14. Mr. Talley does not identify in his briefing\\n\\nwhat, specifically, the Defendants omitted from their article. Even if he had done so,\\n\\n 49\\n\\fhe has not shown how omissions would prove the Defendants published with actual\\n\\nmalice.27 Courts have noted that “the author of an article will have to choose which\\n\\nfacts to include and which to omit,” because “[i]t is impossible to print all of the facts\\n\\non which an opinion or belief is based, especially when an article comprises a critical\\n\\nanalysis.” Reliance Ins. Co. v. Barron’s, 442 F. Supp. 1341, 1352 (S.D.N.Y. 1977).\\n\\nAccordingly, “recovery for a false light tort may not be predicated on . . . [a\\n\\ndefendant’s failure] to include additional facts which might have cast the plaintiff in\\n\\na more favorable or balanced light.” Machleder v. Diaz, 801 F.2d 46, 55 (2d Cir.\\n\\n1986); see also Reliance Ins. Co., 442 F. Supp. at 1352 (citations omitted) (finding\\n\\nthat “selective omission of relevant data” does not provide “circumstantial evidence\\n\\nof defendants’ actual malice”); Pape, 401 U.S. at 282, 290-92 (holding that a\\n\\npublisher did not demonstrate actual malice by omitting the word “alleged” from its\\n\\ndescription of a legal complaint against police officers). Mr. Talley has not shown\\n\\nthe Defendants’ decision to publish certain facts while omitting others demonstrates\\n\\nactual malice.\\n\\n\\n\\n\\n 27\\n In his initial complaint, Mr. Talley argued the Defendants “omitt[ed]\\nmaterial facts about the true, and proper nature of Aso Pogi’s temporary living\\narrangements with [Mr. Talley’s] family.” Aplt. App., Vol. I at A19. And in\\nresponse to their motion for summary judgment, he argued the Defendants “omitted\\nplayers who reported never having seen or heard of players being paid for speaking\\nengagements.” Aplt. App., Vol. III at A680. On appeal, however, Mr. Talley makes\\nonly general allegations about omissions and does not identify any specific facts or\\nstatements that the Defendants excluded from their article.\\n\\n 50\\n\\f e. Error(s)\\n\\n Mr. Talley contends the Defendants demonstrated actual malice by publishing\\n\\ninaccurate information. See Aplt. Br. at 4, 20. But other than his misplaced claim\\n\\nabout misquoting Mr. Pogi, which we addressed above, Mr. Talley does not identify\\n\\nany specific errors or inaccuracies in his appellate briefs.28 This argument is\\n\\ntherefore inadequately briefed. Moreover, the record shows the Defendants fact-\\n\\nchecked and verified the information they used in their article. Without evidence of\\n\\nany knowing or reckless falsehood, Mr. Talley cannot show the Defendants’ alleged,\\n\\nunspecified mistakes were anything more than negligent, which is “insufficient to\\n\\nshow the recklessness that is required for a finding of actual malice.” New York\\n\\nTimes, 376 U.S. at 288.\\n\\n Relatedly, the Supreme Court has held that “failure to investigate . . . is not\\n\\nsufficient to establish reckless disregard.” Harte-Hanks, 491 U.S. at 688. A plaintiff\\n\\ncannot demonstrate malice “merely by showing that the publication was erroneous.”\\n\\nHerbert, 992 P.2d at 329 (citing Gertz, 418 U.S. at 340-41; St. Amant, 390 U.S. at\\n\\n\\n\\n 28\\n In his initial complaint, Mr. Talley alleged the Defendants failed to check\\nfacts about Mr. Carter’s academic record. See Aplt. App., Vol. IV at A910. Mr.\\nTalley does not raise this argument on appeal, so we do not address it here. See City\\nof Colo. Springs v. Solis, 589 F.3d 1121, 1135 n.5 (“[A]rguments not raised in the\\nopening brief are waived.”); Bronson v. Swensen, 500 F.3d 1099, 1104 (10th Cir.\\n2007) (“[W]e routinely have declined to consider arguments that are not raised, or are\\ninadequately presented, in an appellant’s opening brief.”)\\n\\n\\n\\n 51\\n\\f732; New York Times, 376 U.S. at 281). Thus, Mr. Talley’s general allegation about\\n\\ninaccuracy does not show the Defendants “had a high degree of awareness of\\n\\nprobable falsity or in fact entertained serious doubts as to the truth of the\\n\\npublication.” Colbert, 747 P.2d at 291.\\n\\n * * * *\\n\\n The Oklahoma Supreme Court described “[t]he ‘actual malice’ standard [as] a\\n\\nformidable one.” Herbert, 992 P.2d at 328. Mr. Talley has failed to show he could\\n\\nsatisfy it here. The Defendants were thorough in their investigation, editing, and\\n\\nreview. Mr. Talley has not shown they published with “knowledge that [their\\n\\nstatements were] false or with reckless disregard of whether [they were] false or not.”\\n\\nNew York Times, 376 U.S. at 280. He cannot show “with convincing clarity” that the\\n\\nDefendants acted with actual malice. Colbert, 747 P.2d at 291.\\n\\n III. CONCLUSION\\n\\n We affirm the district court’s entry of summary judgment in favor of the\\n\\nDefendants.\\n\\n\\n\\n\\n 52\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2261,"cells":{"id":{"kind":"number","value":4619076,"string":"4,619,076"},"name":{"kind":"string","value":"UNITED STATES of America Plaintiff - Appellee, v. Jason LOERA, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Loera"},"decision_date":{"kind":"string","value":"2019-05-13"},"docket_number":{"kind":"string","value":"17-2180"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Lucero, Ebel, Phillips\", \"parties\": \"\", \"opinions\": [{\"author\": \"EBEL, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 13, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n UNITED STATES OF AMERICA\\n\\n Plaintiff - Appellee,\\n\\n v. No. 17-2180\\n\\n JASON LOERA,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of New Mexico\\n (D.C. No. 1:13-CR-01876-JB-1)\\n _________________________________\\n\\nJerry A. Walz, Walz and Associates, P.C., Albuquerque, New Mexico for Defendant-\\nAppellant.\\n\\nKristopher N. Houghton, Assistant United States Attorney (John C. Anderson, United\\nStates Attorney, with him on the brief), Albuquerque, New Mexico for Plaintiff-\\nAppellee.\\n _________________________________\\n\\nBefore LUCERO, EBEL, and PHILLIPS, Circuit Judges.\\n _________________________________\\n\\nEBEL, Circuit Judge.\\n _________________________________\\n\\n This appeal requires us to apply Fourth Amendment principles to a situation\\n\\nwhere a police officer executing a warrant to search an electronic storage device for\\n\\nevidence of one crime discovers evidence of other criminal activity. Here, while\\n\\fexecuting a warrant to search Jason Loera’s home for evidence of computer fraud,\\n\\nFBI agents discovered child pornography on four of Loera’s CDs. Despite\\n\\ndiscovering the pornography, the agents continued their search for evidence of\\n\\ncomputer fraud—one agent continued to search the CDs that were found to contain\\n\\nsome child pornography and a second agent searched other electronic devices\\n\\nbelonging to Loera, not including those particular CDs (Search 1). After the agents\\n\\nfinished their on-site search, they seized a number of electronic devices that appeared\\n\\nto contain evidence of computer fraud, plus the four CDs that were found to contain\\n\\nchild pornography, and then brought the seized items back to their office. One week\\n\\nlater, one of the agents reopened the CDs that he knew contained some child\\n\\npornography so that he could describe a few pornographic images in an affidavit\\n\\nrequesting a (second) warrant to search all of the seized electronic devices for child\\n\\npornography (Search 2). A magistrate judge issued the warrant, and, upon executing\\n\\nit through two searches, the agents found more child pornography.\\n\\n In the subsequent prosecution against him for possessing child pornography,\\n\\nLoera filed a motion to suppress the evidence seized pursuant to each search, arguing\\n\\nthat the searches violated the Fourth Amendment. On denial of his motion, Loera\\n\\npled guilty to receipt of child pornography but preserved his right to appeal that\\n\\ndenial. Exercising jurisdiction under 28 U.S.C. § 1291, we affirm the denial of\\n\\nLoera’s motion to suppress. We hold, among other things, that the Fourth\\n\\nAmendment does not require police officers to stop executing an electronic search\\n\\nwarrant when they discover evidence of an ongoing crime outside the scope of the\\n\\n 2\\n\\fwarrant, so long as their search remains directed at uncovering evidence specified in\\n\\nthat warrant.\\n\\n I. BACKGROUND\\n\\n This case involves several police searches governed by the Fourth\\n\\nAmendment. The Fourth Amendment protects “the right of the people to be secure in\\n\\ntheir persons, houses, papers, and effects, against unreasonable searches and\\n\\nseizures.” U.S. Const. amend. IV. Generally, for a search to be reasonable, it must\\n\\nbe authorized by a warrant that “particularly” describes “the place to be searched, and\\n\\nthe persons or things to be seized.” U.S. Const. amend. IV. Once officers obtain a\\n\\nsufficiently particular warrant, they must execute it according to the warrant’s terms.\\n\\nHorton v. California, 496 U.S. 128, 140 (1990). The following undisputed facts\\n\\nexplain how the warrant-based searches in this case arose.\\n\\n In 2012, the FBI began investigating Jason Loera for illegally intercepting e-\\n\\nmails intended for then-sitting New Mexico Governor Susana Martinez and her staff\\n\\nin violation of 18 U.S.C. § 2511 (illegal interception) and 18 U.S.C. § 1030\\n\\n(computer fraud) [collectively, “computer fraud”]. As part of that investigation\\n\\n(more details of which can be found in the district court’s opinion United States v.\\n\\nLoera, 59 F. Supp. 3d 1089, 1095–1108 (D.N.M. 2014)), FBI agents applied for and\\n\\nreceived a warrant to search Loera’s residence for computer fraud, including any\\n\\nsuch evidence residing on electronic devices or storage media (“the first warrant”).\\n\\n The first warrant authorized FBI agents to search and seize, in relevant part,\\n\\n“All records, in any form, relating to violations of [computer fraud], involving Jason\\n\\n 3\\n\\fLoera.” ROA Vol. I at 37. The warrant defined the terms “records” and “information”\\n\\nas including: “all of the foregoing items of evidence in whatever forms and by whatever\\n\\nmeans they may have been created or stored, including any form of computer or\\n\\nelectronic storage (such as hard disks or other media that can store data).” Id. at 39. In a\\n\\nseparate provision, the warrant sought “Any computers, cell phones, and/or electronic\\n\\nmedia that could have been used as a means to commit the offenses described on the\\n\\nwarrant.” Id. at 87. Finally, for any electronic device, whether it was used to commit the\\n\\noffenses or simply had relevant records stored on it, the warrant permitted the agents to\\n\\nsearch and seize evidence of who used, owned, or controlled the device, such as\\n\\n“configuration files . . . documents, browsing history . . . photographs, and\\n\\ncorrespondence . . . .” Id. at 38.\\n\\n A. The First Search\\n\\n On November 20, 2012, FBI agents including Agent Aaron Cravens and\\n\\nSpecial Agent Brian Nishida executed the first search warrant. They discovered a\\n\\nlarge volume of electronic media in Loera’s residence, including CDs, DVDs, laptop\\n\\ncomputers, external hard drives, a USB flash drive, an iPhone, and an iPad. Cravens\\n\\nand Nishida were responsible for “previewing” the CDs at Loera’s residence to\\n\\nensure that the FBI seized only those CDs that contained information relevant to the\\n\\nauthorized investigation. ROA Vol. II at 53, 58. The two agents split up the CDs\\n\\nbetween themselves and searched them separately.\\n\\n Cravens tried to view the files of the first CD using a program called FTK\\n\\nImager, which would have allowed Cravens to limit his search to a particular type of\\n\\n 4\\n\\ffile, for example, only image, text, or audio files. However, the program did not\\n\\nwork. Consequently, Cravens opened the CD on a computer and used the “thumbnail\\n\\nview” to preview the files stored on it, meaning, he saw small images of the files, the\\n\\nfile names, and the file types in a vertical list that he had to scroll through to see in\\n\\nits entirety. Although Cravens believed he had authority under the first warrant to view\\n\\nthe entire contents of the CD, Cravens used the thumbnail-image view to fast-track his\\n\\nsearch. He would scroll past irrelevant files but “click[] on anything that didn’t appear\\n\\ncorrect, or any documents” to open them. Id. at 92. While Cravens was “scrolling\\n\\ndown through the images or files . . . on the CDs, [he] found what looked like a nude\\n\\nchild.” Id. at 60. He opened the file to confirm that it was an image of child\\n\\npornography. After determining that it was, Cravens ejected the CD from his\\n\\ncomputer, set it aside, and alerted Agent Nishida and the FBI agent in charge of\\n\\nLoera’s case. Then, Cravens searched the rest of the CDs assigned to him for\\n\\nevidence of computer fraud. Cravens later found a child pornography image on a\\n\\nsecond CD. Just as he did with the first, Cravens set the CD aside after discovering the\\n\\nillegal images and did not open any other files on that CD.\\n\\n Agent Nishida took a different approach to his search. He previewed the files\\n\\non his assigned CDs using the “details view” of Windows Explorer, meaning that he\\n\\nsaw a list of files, file names, and last-modified dates of those files, but not pictures\\n\\nassociated with the files. Id. at 157. For his search of the CDs, or “triage,” as he called\\n\\nit, Nishida would open two or three files on each CD and then determine from that\\n\\nsample whether the CD should be seized pursuant to the warrant. Id. at 160. If Nishida\\n\\n 5\\n\\ffound something he believed might be responsive to the warrant in the files that he\\n\\nsampled, he would set the CD aside to be reviewed off-site. As he was sampling files,\\n\\nNishida found child pornography on two CDs. Unlike Cravens, Nishida did not cease his\\n\\nsearch of those CDs after discovering child pornography; he continued sampling files on\\n\\nthe CDs to determine if they contained information that was responsive to the warrant.\\n\\n The FBI seized thirteen CDs in total from Loera’s residence: four contained child\\n\\npornography images and nine contained evidence of computer fraud.1 In addition to the\\n\\nthirteen CDs, the FBI seized computers, external hard drives, an iPhone, and an iPad.\\n\\n B. The Second Search\\n\\n One week later, on November 27, 2012, Cravens decided to apply for a search\\n\\nwarrant to search the items seized from Loera’s residence for child pornography.\\n\\nCravens wanted to include in his warrant affidavit a detailed description of one child\\n\\npornography image from each of the four CDs on which he and Nishida had found child\\n\\npornography during their on-site preview. Consequently, Cravens opened each of the\\n\\nfour CDs, viewing several images on each, to find child pornography images that he\\n\\ncould accurately describe. Viewing the photos and drafting the affidavit took a total of\\n\\ntwo-and-a-half hours. However, Cravens testified before the district court that he did not\\n\\nspend “anywhere near the two-and-a-half hours” actually looking at photos on the CDs.\\n\\nId. at 74-75.\\n\\n\\n\\n1\\n There is no indication in the record whether the four CDs that contained child\\npornography also contained evidence responsive to the warrant. However, Loera does\\nnot challenge the FBI’s seizure of those CDs pursuant to the first warrant.\\n 6\\n\\f Cravens’ affidavit included two sections. In Section I, Cravens described his\\n\\ntraining and experience with computers and child pornography. In Section II, Cravens\\n\\nexplained the details of the FBI’s investigation of Loera that led to the agent’s discovery\\n\\nof child pornography on the CDs in Loera’s residence. In particular, paragraph 21\\n\\ndescribed in general terms how Cravens discovered the child pornography:\\n\\n 21. In the process of executing this warrant, an FBI certified computer\\n forensic examiner and a computer analysis response team (CART)\\n technician previewed the loose media located during the search (e.g.,\\n thumb drives, CD-Rs, DVD-Rs, memory cards, etc.) for evidence\\n relevant to the original unrelated investigation. During the preview, the\\n examiners identified four writable CDs which appeared to contain\\n images of child pornography. The CDs were seized and placed in the\\n evidence control room at the local FBI office.\\n\\nROA Vol. I at 120. In paragraph 23, Cravens explained that on November 27, 2012,\\n\\nhe “reviewed the four CDs . . . that were believed to contain child pornography,” id.\\n\\nat 121, and that “[d]uring the review of the CDs, [he] observed multiple pictures of\\n\\nchildren many of which are in various states of dress,” id. Then, in paragraphs\\n\\n24-27, Cravens provided a detailed description of one image from each CD that\\n\\ndepicted a minor engaged in sexually explicit conduct. Cravens’ descriptions\\n\\nincluded the apparent age of the minor and the conduct depicted. On November 29,\\n\\n2012, based on Cravens’ affidavit, a federal magistrate judge approved a warrant to\\n\\nsearch the thirteen CDs and six other electronic devices that were seized from Loera’s\\n\\nresidence for child pornography (“the second warrant”).\\n\\n\\n\\n\\n 7\\n\\f C. Searches Pursuant to the Second Warrant\\n\\n Agent Nishida executed the second warrant on two separate dates. In December\\n\\n2012, Nishida searched Loera’s laptop pursuant to both the first and second warrants,\\n\\nlooking for evidence of computer fraud and child pornography. He discovered more than\\n\\n730 child pornography images on Loera’s laptop. In April 2013, Nishida searched the\\n\\nfour CDs seized from Loera’s residence for child pornography pursuant to the second\\n\\nwarrant. He discovered approximately 330 images and two movies of child pornography\\n\\non those CDs.\\n\\n D. Proceedings Below\\n\\n A federal grand jury indicted Loera on several counts of possessing child\\n\\npornography that implicated the images found on both his laptop and his CDs. Loera\\n\\nfiled a motion to suppress that child pornography evidence, and the district court\\n\\ndenied the motion. Loera filed a motion for reconsideration, which the district court\\n\\nalso denied. Following that denial, Loera pled guilty to one count of knowingly\\n\\nreceiving child pornography in violation of 18 U.S.C. §§ 2252(a)(2), 2252(b)(1), and\\n\\n2256, pursuant to a plea agreement, but he reserved the right to appeal the denial of\\n\\nhis motions.\\n\\n On appeal, Loera argues that the district court should have suppressed the\\n\\nchild pornography evidence discovered during the first search, the second search, and\\n\\nthe searches conducted pursuant to the second warrant because, according to Loera,\\n\\neach search was unlawful. Loera argues that the first search exceeded the scope of\\n\\nthe first warrant, the second search exceeded the scope of the first warrant, and the\\n\\n 8\\n\\flast two searches, while authorized by the second warrant, were unlawful because\\n\\nthat warrant was invalid. Additionally, Loera maintains that none of the exceptions\\n\\nto the warrant requirement apply to the searches in this case. We conclude that the\\n\\nfirst search was lawful, but we agree with Loera that the remaining searches were\\n\\nunlawful. Nevertheless, we AFFIRM the district court’s denial of Loera’s motion to\\n\\nsuppress and motion to reconsider under the inevitable discovery doctrine.\\n\\n II. DISCUSSION\\n\\n A. Standard of Review\\n\\n “When reviewing the district court’s denial of a motion to suppress, we view\\n\\nthe evidence in the light most favorable to the government and accept the district\\n\\ncourt’s factual findings unless they are clearly erroneous,” United States v. Grimmett,\\n\\n439 F.3d 1263, 1268 (10th Cir. 2006), but “[t]he ultimate question of reasonableness\\n\\nunder the Fourth Amendment is a legal conclusion that we review de novo.” Id.\\n\\nAccordingly, de novo review applies to the issues we address in this opinion,\\n\\nincluding, the scope of a search warrant, United States v. Angelos, 433 F.3d 738, 745\\n\\n(10th Cir. 2006), the sufficiency of a search warrant, United States v. Danhauer, 229\\n\\nF.3d 1002, 1005 (10th Cir. 2000), the applicability of the good-faith exception, id.,\\n\\nand the applicability of the inevitable discovery doctrine, United States v. Christy, 739\\n\\nF.3d 534, 540 (10th Cir. 2014).\\n\\n B. Validity of the Government’s Application for the First Warrant\\n\\n First, Loera argues that the FBI agents obtained the initial warrant to search\\n\\nhis residence for evidence of computer fraud as a pretext to search instead for\\n\\n 9\\n\\fevidence of child pornography. The district court disagreed, finding that the sole\\n\\npurpose of the first search was to uncover evidence of computer fraud. We affirm\\n\\nthat conclusion.\\n\\n Loera’s pretext argument is based on a statement that Agent Nishida made in a\\n\\nreport dated February 28, 2013, three months after the first and second searches were\\n\\nconducted. In that report, Nishida wrote:\\n\\n On November 14, 2012, SA Michael Boady requested that the above\\n listed specimen or specimens be examined for evidence of intercepting a\\n communication. For example, e-mail messages to or from the domain\\n Susanna2010.com. In addition, SA Boady requested that the evidence\\n also be examined for evidence of child pornography possession and\\n receipt.\\n\\nROA Vol. II at 191–92. Loera argues that this report proves that on November 14,\\n\\n2012, six days before the first search, Agent Nishida received instructions to search\\n\\nLoera’s home and effects for evidence of child pornography.\\n\\n The district court made explicit factual findings to the contrary, which are\\n\\nsupported by the record. First, the district court found that, had the FBI agents had\\n\\nsuspicions that Loera possessed child pornography, agents would have included that\\n\\ninformation in their application for the first warrant. Second, Agent Nishida testified\\n\\nat the suppression hearing that the February 2013 report summarized two separate\\n\\ninstructions from SA Boady: on November 14, 2012, Boady instructed Nishida to\\n\\nsearch for evidence of interception, and, later, Boady instructed Nishida to search for\\n\\nevidence of child pornography. Finally, both Cravens and Nishida testified at the\\n\\nsuppression hearing that the purpose of the November 20 search was only to uncover\\n\\n\\n 10\\n\\fevidence of computer fraud, and the district court credited that testimony. Each of\\n\\nthese facts supports the district court’s determination that the agents conducted the\\n\\nfirst search solely to look for evidence of computer fraud. And we are unpersuaded\\n\\nby Loera’s only evidence of pretext, the report written three months after the\\n\\nallegedly pretextual search.2\\n\\n Thus, we conclude the FBI agents had no pretextual motivations for obtaining\\n\\nthe first warrant, and we affirm the district on this issue.\\n\\n C. Reasonableness of the First and Second Searches\\n\\n Next, we determine that the first search of Loera’s residence was reasonable\\n\\nbecause it was directed solely at uncovering the items specified in the first warrant\\n\\nboth before and after the officers discovered the child pornography evidence.\\n\\nHowever, we conclude that the second search was unreasonable because it was\\n\\ndirected at uncovering evidence of child pornography.\\n\\n 1. Relevant legal principles\\n\\n The Fourth Amendment provides:\\n\\n The right of the people to be secure in their persons, houses, papers, and\\n effects, against unreasonable searches and seizures, shall not be\\n violated, and no Warrants shall issue, but upon probable cause,\\n supported by Oath or affirmation, and particularly describing the place\\n to be searched, and the persons or things to be seized.\\n\\n\\n\\n\\n2\\n Alternatively, even if the agents had an additional motive for conducting the first\\nsearch, that argument would fail as a matter of law under Whren v. United States,\\n517 U.S. 806, 813 (1996).\\n 11\\n\\fU.S. Const. amend. IV. It is now well-recognized that “the ultimate touchstone of\\n\\nthe Fourth Amendment is ‘reasonableness.’” Brigham City v. Stuart, 547 U.S. 398,\\n\\n403 (2006). “[R]easonableness generally requires the obtaining of a judicial\\n\\nwarrant,” Riley v. California, 134 S.Ct. 2473, 2482 (2014), subject to only a few\\n\\nexceptions. The warrant must “particularly” describe “the place to be searched, and\\n\\nthe persons or things to be seized,” U.S. Const. amend. IV.\\n\\n However, obtaining a sufficiently particular warrant is just the first step to\\n\\nconducting a reasonable search. The officers tasked with executing a sufficiently\\n\\nparticular warrant must conduct their search “strictly within the bounds set by the\\n\\nwarrant.” Bivens v. Six Unknown Named Agents of Fed. Bureau of Narcotics, 403\\n\\nU.S. 388, 395 n.7 (1971) (quoting Marron, 275 U.S. at 196). The Supreme Court has\\n\\nheld that, “[i]f the scope of [a] search exceeds that permitted by the terms of a validly\\n\\nissued warrant . . . the subsequent seizure [of evidence] is unconstitutional without\\n\\nmore.” Horton v. California, 496 U.S. 128, 140 (1990).\\n\\n Determining whether a search exceeds the scope of its authorizing warrant is,\\n\\nlike most inquiries under the Fourth Amendment, an exercise in reasonableness\\n\\nassessed on a case-by-case basis. Dalia v. United States, 441 U.S. 238, 258 (1979)\\n\\n(holding that the manner of a search is subject to “later judicial review as to its\\n\\nreasonableness”). The general Fourth Amendment rule is that investigators executing\\n\\na warrant can look anywhere where evidence described in the warrant might\\n\\nconceivably be located. United States v. Ross, 456 U.S. 798, 824 (1982). For\\n\\nexample:\\n\\n 12\\n\\f Just as probable cause to believe that a stolen lawnmower may be found in\\n a garage will not support a warrant to search an upstairs bedroom, probable\\n cause to believe that undocumented aliens are being transported in a van\\n will not justify a warrantless search of a suitcase. Probable cause to believe\\n that a container placed in the trunk of a taxi contains contraband or\\n evidence does not justify a search of the entire cab.\\n\\nId. This limitation works well in the physical-search context to ensure that searches\\n\\npursuant to warrants remain narrowly tailored, but it is less effective in the electronic-\\n\\nsearch context where searches confront what one commentator has called the “needle-in-\\n\\na-haystack” problem. Orin S. Kerr, Digital Evidence and the New Criminal\\n\\nProcedure, 105 Colum. L. Rev. 279, 301 (2005). Given the enormous amount of data\\n\\nthat computers can store and the infinite places within a computer that electronic\\n\\nevidence might conceivably be located, the traditional rule risks allowing unlimited\\n\\nelectronic searches.\\n\\n To deal with this problem, rather than focusing our analysis of the\\n\\nreasonableness of an electronic search on “what” a particular warrant permitted the\\n\\ngovernment agents to search (i.e., “a computer” or “a hard drive”), we have focused\\n\\non “how” the agents carried out the search, that is, the reasonableness of the search\\n\\nmethod the government employed. See United States v. Burgess, 576 F.3d 1078\\n\\n(10th Cir. 2009); United States v. Walser, 275 F.3d 981 (10th Cir. 2001); United\\n\\nStates v. Carey, 172 F.3d 1268 (10th Cir. 1999). Our electronic search precedents\\n\\ndemonstrate a shift away from considering what digital location was searched and\\n\\ntoward considering whether the forensic steps of the search process were reasonably\\n\\ndirected at uncovering the evidence specified in the search warrant. Shifting our\\n\\n\\n 13\\n\\ffocus in this way is necessary in the electronic search context because search\\n\\nwarrants typically contain few—if any—restrictions on where within a computer or\\n\\nother electronic storage device the government is permitted to search. See United\\n\\nStates v. Christie, 717 F.3d 1156, 1165 (10th Cir. 2013) (holding that, so long as an\\n\\nelectronic search warrant requires the government to “direct all of its search efforts”\\n\\ntoward evidence relating to a specific crime, the warrant is sufficiently particular,\\n\\neven where it permits the government to search a “computer” for “all records”\\n\\nrelating to the crimes of “murder, neglect, and abuse”). Because it is “unrealistic to\\n\\nexpect a warrant prospectively [to] restrict the scope of a search by directory,\\n\\nfilename or extension or to attempt to structure search methods,” Burgess, 576 F.3d\\n\\nat 1093 (alteration added), our ex post assessment of the propriety of a government\\n\\nsearch is essential to ensuring that the Fourth Amendment’s protections are realized\\n\\nin this context. Our precedent of Carey, Burgess, and Walser, to which we turn next,\\n\\nare instructive as to what constitutes a reasonable electronic search pursuant to a\\n\\nvalid warrant.\\n\\n Carey is the only case in which we invalidated an electronic search for\\n\\nexceeding the scope of its authorizing warrant. See 172 F.3d at 1276. There, a\\n\\npolice officer obtained a warrant to search files on the defendant’s computer for\\n\\nevidence “pertaining to the sale and distribution of controlled substances.” Id. at\\n\\n1270. Prior to searching the computer, the officer first viewed the computer’s file\\n\\ndirectory, which showed numerous “JPG” files with sexually suggestive titles. Id.\\n\\nDuring his search, the officer came across a number of files that he did not recognize\\n\\n 14\\n\\fand that he was unable to view on the computer that he was using. Id. at 1271. To\\n\\nview the files, the officer downloaded them onto a separate disk, inserted that disk\\n\\ninto another computer, and then was immediately able to view a “JPG file” that\\n\\ndepicted child pornography. Id. Rather than navigating away from the\\n\\nnonresponsive material, the officer “downloaded approximately two hundred forty-\\n\\nfour” more JPG files and then transferred them to nineteen disks, viewing five to\\n\\nseven images on each disk to determine that they all contained child pornography.\\n\\nId. The whole process took about five hours. Id. at 1273. After he had catalogued\\n\\nthe child pornography images in this manner, he then “returned” to his “original task\\n\\nof looking for evidence of drug transactions.” Id. at 1271.\\n\\n The Carey court held that this was an unlawful, general exploratory search\\n\\nbecause, although it was permissible for the officer to open the first JPG file to see if\\n\\nit was responsive to the warrant, id. at 1273 n.4, his opening of the remaining files\\n\\nexceeded the bounds of the authorizing warrant, id. at 1276. The Carey court’s\\n\\nholding turned on four facts: (1) the officer spent five hours, a significant amount of\\n\\ntime, specifically perusing the trove of nonresponsive material, id. at 1273; (2) the\\n\\nnonresponsive files were characteristically distinct and set apart from the other files\\n\\non the computer (such that they could have been avoided) because each file was\\n\\nlabeled “JPG,” many had sexually suggestive titles, and the officer had to download\\n\\nthem to open them, id. at 1274; (3) the officer did not discover the files inadvertently\\n\\n(at least after his first look), id. at 1273; and (4) a more narrowly tailored search was\\n\\npossible—the officer could have gone back to searching for drug-related documents\\n\\n 15\\n\\fmuch sooner than he did, id. at 1273. Importantly, we did not condemn the officer’s\\n\\ndecision to return to searching for drug-related documents after discovering the child\\n\\npornography, but, instead, we condemned his “temporar[y] abandon[ment]” of the\\n\\noriginal search to conduct a “five hour search of the child pornography files.” Id. at\\n\\n1273.\\n\\n Next, we turn to Walser and Burgess, both of which upheld electronic searches\\n\\nin which the investigator discovered incriminating, nonresponsive material while\\n\\nexecuting a search warrant but then navigated away from it. In United States v.\\n\\nWalser, the police obtained a warrant to search the defendant’s hotel room for\\n\\nelectronically stored records of “evidence of the possession of controlled\\n\\nsubstances.” 275 F.3d 981, 983–84 (10th Cir. 2001). A police officer searched the\\n\\nroom pursuant to the warrant and found a laptop and a digital camera. Id. at 984.\\n\\nThe agent seized the laptop, removed it from the hotel room, and then conducted a\\n\\ndrug-specific search of the laptop, looking for “ledgers of drug transactions or images\\n\\nof drug use.” Id. In order to find those things, the agent employed a particularized\\n\\nsearch method that “selectively proceeded to the ‘Microsoft Works’ sub-folder on the\\n\\npremise that[,] because Works is a spreadsheet program, that folder would be most\\n\\nlikely to contain records relating to the business of drug trafficking.” Id. at 986. It\\n\\nwas while searching the contents of the Works folder that the officer came across a\\n\\nfile labeled “bstfit.avi” and opened it. Id. at 984. When he viewed the contents, he\\n\\ndiscovered that the file contained child pornography images. Id. at 986–87. He then\\n\\nimmediately ceased his search. Id.\\n\\n 16\\n\\f We upheld the officer’s search as reasonable because we determined that, by\\n\\nusing a particularized search method, the officer avoided conducting the kind of\\n\\n“sweeping, comprehensive search of a computer’s hard drive” that Carey prohibited.\\n\\nId. at 986. The defendant in Walser argued that the agent exceeded the scope of the\\n\\nwarrant by opening the “AVI file,” a video file, because “it could not possibly have\\n\\ncontained the type of evidence the [a]gent was authorized to search for, namely,\\n\\nrecords of drug transactions or still images of drug use.” Id. at 987. We rejected that\\n\\nargument by interpreting Carey to excuse an officer’s discovery of child pornography\\n\\nduring a search for “relevant records in places where such records might logically be\\n\\nfound” so long as the officer does not conduct a supervening search specifically\\n\\ndirected at finding pornography evidence. Id. at 986. Applying that rule, we held in\\n\\nWalser that the officer’s opening the “bstfit.avi” file was permissible because (1) he\\n\\nwas looking in a folder that was “most likely to contain records relating to the\\n\\nbusiness of drug trafficking” when he opened it, and (2) he did not conduct an\\n\\nintervening search directly focused on child pornography like the agent in Carey. Id.\\n\\nBased on those facts, we concluded that the “search was reasonable and within the\\n\\nparameters of the search warrant” and that the evidence found as a result of it did not\\n\\nneed to be suppressed. Id. at 987.\\n\\n Finally, in United States v. Burgess, 576 F.3d 1078 (10th Cir. 2009), we again\\n\\nupheld an electronic search that uncovered evidence of child pornography as\\n\\nreasonable and within the scope of its authorizing warrant. There, police obtained a\\n\\nwarrant to search a motorhome for, among other things, “computer records” that\\n\\n 17\\n\\fwould tend to show “conspiracy to sell drugs.” Id. at 1083. The warrant\\n\\nincorporated the affidavit on which it was based, which stated that the affiant “knows\\n\\nthat persons involved in trafficking or the use of narcotics often keep photographs of\\n\\ncoconspirators or photographs of illegal narcotics in their vehicle.” Id.\\n\\n Based on the warrant, officers searched two hard drives and a laptop found in\\n\\nthe motorhome. Id. An agent searched one of the hard drives by using a program\\n\\ncalled EnCase, which copies the contents of a hard drive over to a computer to\\n\\nprevent file corruption. Id. at 1083–84. EnCase allows an investigator to “preview”\\n\\nreduced-sized photos of each image file as they are being copied. Id. at 1084, 1094.\\n\\nThe agent took advantage of this feature and viewed each image file on the hard drive\\n\\nas it was being copied. Id. at 1084. After viewing 200-300 digital images, mostly\\n\\npersonal photos, the agent saw an image that looked like child sexual exploitation.\\n\\nId. He then closed the preview program and sought a warrant to search all of the\\n\\ndefendant’s electronic storage devices for evidence of child pornography. Id. Upon\\n\\nconducting that search, the agent found more than one hundred thousand illegal\\n\\nimages. Id.\\n\\n The defendant asked the district court to suppress the child pornography\\n\\nevidence because, he argued, the agent’s use of the “preview” program exceeded the\\n\\nscope of the warrant because he did not employ a particularized search method like\\n\\nthe agent in Walser but instead looked through each image file contained on the hard\\n\\ndrive. We determined that the agent’s use of the “preview” program was reasonable\\n\\nand did not exceed the scope of the warrant for two reasons. First, we noted that,\\n\\n 18\\n\\fbecause the warrant did not expressly limit the file types that the agent was allowed\\n\\nto search, for example, by limiting the search to text files (.doc, .wpd, .txt, etc.), the\\n\\nagent was well within the scope of the warrant when he decided to view all of the\\n\\nimage files on the hard drive using the preview program. Id. at 1092. Second, we\\n\\ndetermined that there was no reasonable way for the agent to conduct a more\\n\\nnarrowly tailored search because, when the object of a search is likely to be an image\\n\\nfile, as it was in Burgess, “there may be no practical substitute for actually looking in\\n\\nmany (perhaps all) folders and sometimes at the documents contained within those\\n\\nfolders.” Id. at 1094.\\n\\n Reading these cases together, we determine that four features of the\\n\\nunconstitutional search in Carey demonstrate that it was unreasonably directed at\\n\\nuncovering evidence of child pornography, rather than directed at the evidence\\n\\nspecified in the warrant, and distinguish it from the reasonable searches in Walser\\n\\nand Burgess: (1) the length of time the searching officer spent looking at the\\n\\nincriminating, nonresponsive evidence (five hours in Carey versus less than one\\n\\nminute in Walser and Burgess); (2) the fact that the nonresponsive files were set apart\\n\\nfrom the responsive files saved on the storage device (JPG files downloaded onto\\n\\nseparate disks in Carey versus generic files intermingled all in one place in Burgess);\\n\\n(3) the manner in which the evidence was discovered (purposefully in Carey versus\\n\\ninadvertently in Walser and Burgess);3 and (4) the breadth of the search method\\n\\n\\n3\\n We acknowledge that in Horton v. California, 496 U.S. 128, 130 (1990), the\\nSupreme Court held that, in physical searches, “even though inadvertence is a\\n 19\\n\\femployed (the wide detour in Carey versus the narrowly tailored search in Walser).\\n\\nContrary to Loera’s assertion, these cases do not require that officers stop searching\\n\\nupon discovering evidence of a crime outside the scope of the warrant. Such a rule\\n\\nwould prohibit what the Fourth Amendment expressly permits—reasonable searches\\n\\nbased upon a warrant supported by probable cause. We have never required that.\\n\\n This conclusion brings us in line with every circuit that has confronted this\\n\\nissue. See United States v. Stabile, 633 F.3d 219, 240 (3d Cir. 2011) (upholding\\n\\ndenial of motion to suppress where officers continued warrant-authorized search of\\n\\nthe defendant’s computer for financial crimes after discovering child pornography);\\n\\nUnited States v. Williams, 592 F.3d 511, 521–24 (4th Cir. 2010) (upholding search\\n\\nwhere the officer continued his warrant-authorized search of the defendant’s\\n\\ncomputer for evidence of “making threats and computer harassment” after\\n\\ndiscovering child pornography); United States v. Miranda, 325 F.App’x 858, 859–60\\n\\n(11th Cir. 2009) (per curiam) (unpublished) (upholding search where officer\\n\\ncontinued his warrant-authorized search for evidence of counterfeit software after\\n\\ndiscovering child pornography); United States v. Wong, 334 F.3d 831, 834 (9th Cir.\\n\\n\\ncharacteristic of most legitimate ‘plain view’ seizures, it is not a necessary\\ncondition.” However, because Carey, Walser, and Burgess, each of which succeeded\\nHorton in time, considered the subjective intentions of the searching officers where\\nthat information was available, we continue to include inadvertence as a factor to\\nconsider when deciding whether an electronic search fell within the scope of its\\nauthorizing warrant or outside of it. The fundamental differences between electronic\\nsearches and physical searches, including the fact that electronic search warrants are\\nless likely prospectively to restrict the scope of the search, justify our inclusion of\\nthat factor. See Horton, 496 U.S. at 139 (abandoning inadvertence as a necessary\\ncondition for a legitimate plain view seizure).\\n 20\\n\\f2003) (upholding denial of motion to suppress where the officer continued his\\n\\nwarrant-authorized search of the defendant’s computer for, among other things,\\n\\n“[a]ny maps, receipts, or writings, depicting Churchill County Nevada” after\\n\\ndiscovering child pornography).\\n\\n Although officers do not have to stop executing a search warrant when they\\n\\nrun across evidence outside the warrant’s scope, they must nevertheless reasonably\\n\\ndirect their search toward evidence specified in the warrant. What that looks like\\n\\ndepends on the particular facts of a given case. Narrowly tailored search methods\\n\\nthat begin looking “in the most obvious places and [then] progressively move from the\\n\\nobvious to the obscure,” Burgess, 576 F.3d at 1094, should be used where possible but\\n\\nare not necessary in every case. In cases like this one, where the electronic storage\\n\\ndevice is not well-organized and the most practical way to search it is through an item-\\n\\nby-item review, “there may be no practical substitute for actually looking in many\\n\\n(perhaps all) folders and sometimes at the documents contained within those folders.”\\n\\nId. In such a case, however, the searching officer must respond appropriately to what\\n\\nhe or she sees. The reasonableness of a search evolves as the search progresses and\\n\\nas the searching officer learns more about the files on the device that he or she is\\n\\nsearching.\\n\\n An analogy to the physical realm is helpful here. Imagine a warrant authorizes\\n\\npolice officers to search a “residence” for evidence of “firearms and ammunition.”\\n\\nUnder that warrant, it would be reasonable for a police officer to search the medicine\\n\\ncabinet in the bathroom for a minute or two to see if a small gun or ammunition is\\n\\n 21\\n\\fhidden there, however, it would be unreasonable for the officer to spend two hours\\n\\nreading the labels on each bottle of medicine in the cabinet. On the other hand, if the\\n\\nwarrant had authorized the officer to search the residence for evidence of “illegal\\n\\ndrug trafficking and manufacture,” an intensive search of the medicine cabinet would\\n\\nbe reasonable. In both cases, the medicine cabinet is fair game to search, but the\\n\\nintensity level of the permitted search differs depending on the evidence to be seized.\\n\\nThe same is true for electronic searches. While in some cases many (perhaps all)\\n\\nelectronic areas of a computer will be fair game to search, the level of intensity that\\n\\nofficers are permitted to spend searching those areas will differ depending on\\n\\nwhether the area appears to contain responsive material. This is true even when\\n\\nofficers come across evidence of incriminating, nonresponsive material. In all cases,\\n\\nthe ultimate test is the one mandated by the Fourth Amendment: whether the search\\n\\nwas “reasonable” under the circumstances. In the case of a computer search,\\n\\n“reasonableness” requires officers to take into account the flexibility of computers\\n\\nand the multiple configurations to which they may be adapted. As the computer\\n\\nsearch continues and as the executing officer obtains more information about how a\\n\\nsuspect used his computer, that too may inform the reasonableness of the continuing\\n\\nsearch.\\n\\n We now apply these principles to the November 20 and 27 searches conducted\\n\\nin this case.\\n\\n\\n\\n\\n 22\\n\\f 2. November 20 search was reasonable\\n\\n Loera argues that, although the first warrant permitted the FBI agents to search his\\n\\nCDs for evidence of computer fraud, the officers’ search exceeded the scope of the first\\n\\nwarrant when they continued searching after discovering evidence of child pornography.\\n\\nWe disagree. The searches that Agent Cravens and Agent Nishida each conducted of\\n\\nLoera’s CDs on November 20 were reasonable and conducted within the scope of the\\n\\nfirst warrant because at all times each was reasonably directed at discovering evidence of\\n\\ncomputer fraud. Therefore, the first search did not violate the Fourth Amendment and\\n\\nthus did not warrant suppression of the evidence discovered during that search.\\n\\n The agents’ searches on November 20 resemble the searches in Walser and\\n\\nBurgess more than they resemble the search in Carey, both before and after they\\n\\ndiscovered the child pornography evidence. First, both agents here spent very little\\n\\ntime looking at the child pornography images they discovered. They noticed them,\\n\\nalerted a supervisor, and then moved on to the rest of the images on the same CD (in\\n\\nNishida’s case), or the other CDs (in Cravens’ case), looking for evidence of\\n\\ncomputer fraud. Both responses were reasonable because, as mentioned above, the\\n\\nagents were not required to stop searching altogether. And both responses\\n\\ndemonstrate an effort to navigate away from the nonresponsive material and toward\\n\\nfiles that they believed were more likely to contain material responsive to the\\n\\nwarrant. Second, the files on the CDs that the agents previewed were not\\n\\ncharacteristically distinct or set apart from the other files, in contrast to Carey. Agent\\n\\nCravens testified that, when he put a CD into his computer to see the files that it\\n\\n 23\\n\\fcontained, the computer pulled up a generic list of those files. The record does not\\n\\nindicate that there were any folders or distinctive titles setting clearly apart the\\n\\nnonresponsive child pornography files from the other files on the disk. Loera bears\\n\\nthe burden of proof on his suppression motion, and he has offered no evidence on this\\n\\npoint. Third, the agents discovered the child pornography files inadvertently on\\n\\nNovember 20. Fourth, both agents’ search methods were reasonably narrow under\\n\\nthe circumstances, considering the fact that the CDs did not seem particularly\\n\\norganized. Given that the warrant permitted the agents to search the CDs for\\n\\n“photographs,” “documents,” and “configuration files,” it was reasonable for Nishida and\\n\\nCravens to search all file types on the CDs (image, video, and text) for evidence of\\n\\ncomputer fraud rather than to narrow that search to one particular file type. The agents’\\n\\nsearches on November 20 were reasonable because they fell within the scope of the\\n\\nfirst warrant both before and after they discovered the child pornography evidence. We\\n\\nreverse the district court’s ruling to the contrary.\\n\\n 3. November 27 search was unreasonable\\n\\n Loera also argues that Agent Cravens’ subsequent search on November 27,\\n\\n2012, of the four seized CDs that contained child pornography violated the Fourth\\n\\nAmendment because Cravens was “[i]ntentionally searching for evidence of a crime\\n\\noutside the scope of the [f]irst [w]arrant prior to obtaining a new warrant.” Aplt. Br. 29.\\n\\nIn making this argument, Loera accepts that the first warrant permitted the government to\\n\\nseize the four CDs that were found to contain some child pornography and to search them\\n\\nfor evidence of computer fraud. Therefore, Loera challenges Cravens’ November 27\\n\\n 24\\n\\fsearch only for exceeding that permission. Accordingly, we confine our analysis to\\n\\nwhether the second search exceeded the scope of the first warrant. The district court\\n\\nconcluded that it did and that neither exigent circumstances nor any other exception to\\n\\nthe warrant requirement justified that search. We agree and conclude that the district\\n\\ncourt correctly excised the evidence obtained during the November 27th search from\\n\\nCravens’ affidavit for the second warrant. Several of the district court’s factual findings\\n\\nsupport that result.\\n\\n The district court found that “Cravens was not searching for evidence of\\n\\nelectronic fraud” on November 27 but instead was searching for child pornography.\\n\\nDist. Ct. Op. at 144. The district court based this finding on Cravens’ testimony at the\\n\\nsuppression hearing that he reopened Loera’s CDs on November 27 specifically “[t]o\\n\\nwrite a description of an image on the disc” so that he could “obtain a second warrant\\n\\nfor child pornography.” ROA Vol. II at 72. That admission is the most probative\\n\\nfact in the record that Cravens’ search was directed at finding child pornography.\\n\\nThe district court also found that Cravens had the four CDs for a total of two-and-a-\\n\\nhalf hours that day, during which time he searched the CDs and drafted the second\\n\\naffidavit. Although the record does not indicate how long Cravens searched the CDs,\\n\\nhe testified at the suppression hearing that he looked at several images on each CD—\\n\\n“more than just a couple” but “[m]ost likely less than a dozen.” ROA Vol. II at 143.\\n\\nWhatever the amount of time, Cravens’ devoted it exclusively to nonresponsive\\n\\nmaterial. Rather than navigate away from the child pornography images when he found\\n\\nthem, Cravens explicitly navigated toward such images. Based on these findings, we\\n\\n 25\\n\\fagree with the district court that, in contrast with the agents’ searches on November\\n\\n20, Agent Cravens’ search on November 27 was unreasonable because it was directed\\n\\nat uncovering evidence of child pornography.\\n\\n The government argues that two exceptions save Cravens’ search from\\n\\nviolating the Fourth Amendment: the plain view doctrine and the foregone-\\n\\nconclusion exception. We disagree. For its plain view argument, the government\\n\\nasserts that the law permitted Agent Cravens to take a “second look” at the child\\n\\npornography images on Loera’s CDs because members of the FBI had already seen\\n\\nthe images in plain view during a lawful search, and, therefore, his “second look”\\n\\nwas no further invasion of Loera’s privacy than the initial, lawful viewing. The\\n\\ngovernment points to a Fourth Circuit case, United States v. Jackson, 131 F.3d 1105\\n\\n(4th Cir. 1997), where a law enforcement officer had consent to search a residence for a\\n\\nfugitive. Id. at 1107. While looking for the fugitive in the basement, the officer observed\\n\\nsome suspicious metal items on the floor. Id. He did not pause to examine those items at\\n\\nthat time, but he instead proceeded to finish his sweep for the fugitive. Id. Once\\n\\nfinished, he went back to take a closer look at the objects on the floor, this time\\n\\nrecognizing them as drug paraphernalia. Id. More officers arrived and took a look at the\\n\\nparaphernalia, eventually using the presence of those items to obtain a search warrant for\\n\\nthe house, which uncovered a gun and large quantities of drugs. Id. at 1108. That further\\n\\nsearch was held to have been constitutional under the plain-view doctrine. Id.\\n\\n There are too many factual distinctions between Jackson and this case to permit\\n\\nCravens’ second look under the plain view doctrine. First, as government counsel\\n\\n 26\\n\\fadmitted at oral argument, there is no evidence in the record that Cravens looked at the\\n\\nsame photos on November 27 that the officers viewed on November 20. Second, seven\\n\\ndays elapsed between the first and second searches in this case, not a matter of minutes.\\n\\nThird, Cravens’ “second look” led him to peruse more than just the child pornography\\n\\nimages, so we cannot say that the November 27 search did not cause a further invasion\\n\\nof Loera’s privacy. The plain view doctrine permits the warrantless seizure of\\n\\nevidence of criminal activity when police officers observe the evidence during a\\n\\nlawful search. United States v. Naugle, 997 F.2d 819, 822 (10th Cir. 1993). That\\n\\ndoctrine cannot be used to justify Cravens’ November 27 search.\\n\\n The government also argues that Cravens’ “second look” was justified under\\n\\nwhat it has termed the “foregone-conclusion exception” to the warrant requirement.\\n\\nThis doctrine comes from several of our plain view cases where we have permitted\\n\\nthe warrantless search of containers in plain view whose contents “are a foregone\\n\\nconclusion” because the container is “not closed,” “transparent,” or, if it is closed,\\n\\n“its ‘distinctive configuration . . . proclaims its contents’” nonetheless. United States\\n\\nv. Corral, 970 F.2d 719, 725 (10th Cir. 1992). We have also held that the doctrine\\n\\napplies “where the police have already seen the contents of a seized container prior to\\n\\nconducting the search, [because] there is no significant additional invasion of privacy\\n\\ninvolved in searching the container.” Id. at 725. We reject this argument for the\\n\\nsame reasons as the government’s plain view argument. Here, Cravens knew to a\\n\\nnear certainty that the seized and re-searched CDs contained some child pornography,\\n\\nbut he had no idea what else they contained. And, again, there is no evidence that\\n\\n 27\\n\\fCravens had previously seen the child pornography images that he viewed on\\n\\nNovember 27.\\n\\n Thus, Cravens’ November 27 search was unlawful because it exceeded the scope\\n\\nof the first warrant and none of the exceptions to the warrant requirement apply.\\n\\n D. Reasonableness of the Searches Conducted Under the Second Warrant\\n\\n Additionally, Loera argues that the child pornography evidence that Agent\\n\\nNishida discovered when he executed the second warrant should have been\\n\\nsuppressed because the second warrant was not supported by probable cause and no\\n\\nexceptions to the warrant requirement apply. We agree that the second warrant was\\n\\nnot supported by probable cause and that the good faith exception is inapplicable\\n\\nhere. However, the inevitable discovery doctrine supports the district court’s denial\\n\\nof Loera’s motion to suppress, and we affirm on that basis.\\n\\n 1. Second warrant was not supported by probable cause\\n\\n We review whether a magistrate properly issued a search warrant by determining\\n\\nwhether there was a “substantial basis” for probable cause in the affidavit submitted in\\n\\nsupport of the warrant. Illinois v. Gates, 462 U.S. 213, 236 (1983). Because we find\\n\\nthat the November 27 search was unlawful, we must excise from the affidavit that\\n\\nCravens filed in support of the second warrant all of the descriptions of child\\n\\npornography that he unlawfully obtained during the second search and then\\n\\ndetermine whether “there was probable cause absent that information.” United States\\n\\nv. Sims, 428 F.3d 945, 954 (10th Cir. 2005). The district court determined that the\\n\\n\\n\\n 28\\n\\fsecond warrant remained supported by probable cause without the tainted\\n\\ndescriptions. We disagree.\\n\\n While “probable cause does not demand the certainty we associate with formal\\n\\ntrials,” Gates, 462 U.S. at 246, “[s]ufficient information must be presented to the\\n\\nmagistrate to allow that official to determine probable cause; his action cannot be a mere\\n\\nratification of the bare conclusions of others,” id. at 239 (emphasis added). For example,\\n\\n“[a] sworn statement of an affiant that ‘he has cause to suspect and does believe that’\\n\\nliquor illegally brought into the United States is located on certain premises” is not\\n\\nsufficient to support a finding that probable cause exists to search the premises. Id.\\n\\n The child pornography descriptions that Agent Cravens obtained during the\\n\\nunlawful second search appear in paragraphs 24-27 of Cravens’ affidavit. Once we\\n\\nexcise those descriptions, all that remains substantively is Cravens statement that,\\n\\n“During the preview, the examiners identified four writable CDs which appeared to\\n\\ncontain images of child pornography.” ROA Vol. I at 120. This sentence does not\\n\\nsupport a finding of probable cause.\\n\\n In United States v. Pavulak, the Third Circuit reviewed an affidavit to support\\n\\na warrant to search for child pornography that contained language very similar to the\\n\\nbare-bones description left in the affidavit in our case, 700 F.3d 651, 661 (3d Cir.\\n\\n2012). The warrant affidavit in Pavulak stated that an informant had seen the\\n\\ndefendant “viewing child pornography” of females “between 16 and 18 years old,”\\n\\nwithout providing any further details about what the images depicted. Id. at 657.\\n\\nThe Third Circuit held that the affidavit lacked probable cause because it did not\\n\\n 29\\n\\fallow the magistrate judge “to independently evaluate whether the contents of the\\n\\nalleged images [met] the legal definition of child pornography.” Id. at 661. We find\\n\\nthat analysis persuasive here. Agent Cravens’ remaining statement that the CDs\\n\\n“appeared to contain images of child pornography” provides no detailed description\\n\\nof what the images depicted such that a magistrate could independently assess\\n\\nwhether the images meet the legal definition of child pornography. ROA Vol. I at\\n\\n120.\\n\\n Therefore, the affidavit supporting the second warrant lacked probable cause\\n\\nabsent the tainted information. We reverse the district court’s contrary conclusion.\\n\\n 2. Good-faith exception inapplicable to these facts\\n\\n Next, we consider whether the good faith exception to the exclusionary rule\\n\\nfrom United States v. Leon, 468 U.S. 897, 918 (1984), applies when police execute a\\n\\nsearch warrant that is based on information obtained through an unlawful predicate\\n\\nsearch. Disagreeing with the district court, we conclude that it does not. The\\n\\nSupreme Court’s opinion in Leon and our opinion in United States v. Scales, 903\\n\\nF.2d 765, 768 (10th Cir. 1990), dictate that the good faith exception does not apply in\\n\\na case like the one before us because the illegality at issue stems from unlawful\\n\\npolice conduct, rather than magistrate error, and therefore the deterrence purposes of\\n\\nthe Fourth Amendment are best served by applying the exclusionary rule.\\n\\n In United States v. Leon, the Supreme Court modified the exclusionary rule\\n\\n“so as not to bar the use in the prosecution’s case in chief of evidence obtained by\\n\\nofficers acting in reasonable reliance on a search warrant issued by a detached and\\n\\n 30\\n\\fneutral magistrate but ultimately found to be unsupported by probable cause,” 468\\n\\nU.S. at 900. The Court reasoned that the purpose of the exclusionary rule is to deter\\n\\npolice misconduct and in such a case “there is no police illegality and thus nothing to\\n\\ndeter.” Id. at 920. In this circuit, “Leon’s good faith exception applies only narrowly,\\n\\nand ordinarily only when an officer relies, in an objectively reasonable manner, on a\\n\\nmistake made by someone other than the officer.” United States v. Cos, 498 F.3d 1115,\\n\\n1132 (10th Cir. 2007) (declining to apply good faith exception to warrantless search of\\n\\napartment where officers mistakenly believed the person that consented to the search had\\n\\nthe authority to do so); United States v. Herrera, 444 F.3d 1238, 1251 (10th Cir. 2006)\\n\\n(declining to apply good faith exception to state trooper who conducted a warrantless\\n\\ninspection of a truck based on the officer’s mistaken belief the truck was a commercial\\n\\nvehicle subject to such inspection). Thus, Leon is inapplicable here where the\\n\\nmistake—the unconstitutional second search—was the fault of the officer, not the\\n\\nmagistrate.\\n\\n We considered whether Leon applied to a warrant affidavit based on tainted\\n\\nevidence in Scales, 903 F.2d at 768. There, we held that Leon did not apply to\\n\\nexcuse a law enforcement officer’s reliance on a search warrant where the facts in the\\n\\nwarrant affidavit were obtained through an unlawful predicate seizure. In that case,\\n\\nDEA agents seized a suitcase that they believed contained drugs. Id. at 767. Then,\\n\\nthey took the suitcase to a drug-sniffing canine team that signaled the suitcase did\\n\\ncontain drugs. Id. Finally, after having had the suitcase in their possession for\\n\\ntwenty-four hours, the agents applied for and obtained a warrant to search the\\n\\n 31\\n\\fsuitcase based on the probable cause provided by the canine alert. Id. Upon\\n\\nconducting the search, the agents discovered more than 2,000 grams of cocaine in the\\n\\nsuitcase. Id. The defendant moved to suppress the cocaine evidence, arguing that the\\n\\nagents’ initial seizure of the suitcase was unlawful because it was unsupported by\\n\\nprobable cause. Id. at 767.\\n\\n The district court in Scales denied the motion, finding that, even if the seizure\\n\\nof the suitcase was unlawful, the good faith exception ratified the agents’ behavior.\\n\\nId. We reversed, holding that Leon was inapplicable “[b]ecause the DEA agents\\n\\nwere not acting in reliance on a search warrant when they seized the luggage and held\\n\\nit for more than twenty-four hours.” Id. at 768. Our holding was informed by the\\n\\nreasoning in Leon that “Penalizing the officer for the magistrate’s error, rather than\\n\\nhis [or her] own, cannot logically contribute to the deterrence of Fourth Amendment\\n\\nviolations.” Id. at 768 (quoting Leon, 468 U.S. at 921) (alteration in original).\\n\\nBecause the contraposition is also true—that penalizing an officer for his or her own\\n\\nerror does contribute to deterrence—we determined that the exclusionary rule must\\n\\napply to the agents’ unlawful pre-warrant seizure of the suitcase. Id.\\n\\n Scales and Leon control our outcome here. Cravens conducted an unlawful\\n\\nsearch of Loera’s CDs on November 27 in the absence of a warrant. He included the\\n\\ntainted fruit that he uncovered during that search in the affidavit that he submitted in\\n\\nsupport of the second warrant. Cravens’ warrant affidavit was facially valid, and\\n\\ntherefore the magistrate did not error by issuing a warrant based upon it. Instead, the\\n\\nconstitutional error came from Agent Cravens.\\n\\n 32\\n\\f The government argues that Cravens acted in good faith because he\\n\\n“transparently informed the magistrate judge of the steps he had taken to obtain the\\n\\ndescriptions he included in his affidavit.” Aple. Br. at 40. Cravens’ affidavit\\n\\nprovided some information about the first search. It explained that, while executing\\n\\nthe first search warrant, the FBI agents identified four CDs that contained child\\n\\npornography and seized them. Then, Cravens wrote:\\n\\n On November 27, 2012, the writer, an FBI certified CART Technician,\\n reviewed the four CDs, each of which are designated in attachment A,\\n that were believed to contain child pornography. During the review of\\n the CDs, the writer observed multiple pictures of children many of\\n which are in various state of dress including the following images . . . .\\n\\nROA Vol. I at 50. However, that information was not sufficient to allow the\\n\\nmagistrate to determine the constitutionality of the second search such that the\\n\\nmagistrate can be said to have endorsed Cravens’ pre-warrant conduct. Furthermore,\\n\\neven if it was, that would not affect our outcome. Tenth Circuit precedent dictates\\n\\nthat the good faith exception does not apply at all when a warrant affidavit is based\\n\\non tainted evidence from a prior, unlawful search.\\n\\n Four other circuits have likewise concluded that Leon is inapplicable when an\\n\\nofficer executes in good faith a search warrant that is based on unlawfully-obtained\\n\\nevidence. United States v. Scott, 731 F.3d 659, 664 (7th Cir. 2013) (holding that\\n\\nevidence discovered pursuant to a warrant based on illegally-obtained evidence will\\n\\nbe inadmissible unless other, untainted information in the affidavit establishes\\n\\nprobable cause); United States v. Mowatt, 513 F.3d 395, 405 (4th Cir. 2008) (holding\\n\\nthat “Leon only prohibits penalizing officers for their good-faith reliance on\\n\\n 33\\n\\fmagistrates’ probable cause determinations” and that the exclusionary rule operates\\n\\nto penalize officers for any unconstitutional conduct preceding a magistrate’s\\n\\ninvolvement); United States v. McGough, 412 F.3d 1232 (11th Cir. 2005) (refusing\\n\\nto apply good faith exception where an unlawful entry into the defendant’s apartment\\n\\nled to the officer’s request for a search warrant); United States v. Vasey, 834 F.2d\\n\\n782, 789 (9th Cir. 1987) (holding that good faith exception did not apply to a warrant\\n\\nthat was based on information obtained in an illegal warrantless search because “[t]he\\n\\nconstitutional error was made by the officer . . ., not by the magistrate”). At least two\\n\\ncommentators support this analysis as well. See Wayne R. LaFave, Search &\\n\\nSeizure: A Treatise on the Fourth Amendment § 1.3(f) (5th ed. 2016) (explaining\\n\\nthat, because courts rarely require affiants to prove that they obtained the evidence\\n\\nlisted in an affidavit lawfully, “there is no reason why that process should, via Leon,\\n\\nshield that activity from full scrutiny at the suppression hearing”); Craig M.\\n\\nBradley, The “Good Faith Exception” Cases: Reasonable Exercise in Futility, 60 Ind.\\n\\nL.J. 287, 302 (1985) (quoting Leon, 468 U.S. at 914) (“When the magistrate issued\\n\\nthe warrant, he did not endorse past activity; he only authorized future activity. . . .\\n\\n[T]he function of the magistrate is to determine ‘whether a particular affidavit\\n\\nestablishes probable cause,’ not whether the methods used to obtain the information\\n\\nin that affidavit were legal.”).\\n\\n However, five other circuits have concluded that the good faith exception can\\n\\napply where an affidavit supporting a search warrant is tainted by illegally-obtained\\n\\nevidence in at least some limited circumstances. Three of those circuits apply the\\n\\n 34\\n\\fgood faith exception if the predicate search, although ultimately determined to be\\n\\nunlawful, was arguably lawful under the binding precedent in effect at the time of the\\n\\nsearch. United States v Bain, 874 F.3d 1, 22–23 (1st Cir. 2017) (applying good faith\\n\\nexception because binding precedent did not “clearly classify” as unlawful the\\n\\nconduct that invalidated the predicate search); United States v. Hopkins, 824 F.3d\\n\\n726 (8th Cir. 2016) (applying good faith exception because the reasonableness of the\\n\\nillegal predicate search was “close enough to the line of validity” to make an\\n\\nofficer’s belief in the validity of the warrant objectively reasonable); United States v.\\n\\nHolley, 831 F.3d 322, 326–27 (5th Cir. 2016) (also applying “close enough to the\\n\\nline of validity” test). Two other circuits apply the good faith exception in these\\n\\ntypes of cases when (1) the predicate search was arguably reasonable and (2) the\\n\\nwarrant affidavit truthfully conveyed the circumstances of the illegal predicate search\\n\\nto the magistrate judge. United States v. McClain, 444 F.3d 556, 566 (6th Cir. 2005)\\n\\n(applying Leon because the reasonableness of the predicate search was a close call\\n\\nand the warrant affidavit “fully disclosed” the circumstances surrounding the initial\\n\\nwarrantless search); United States v. Thomas, 757 F.2d 1359 (2d Cir. 1985) (applying\\n\\ngood faith exception because officer’s affidavit fully described the unlawful, pre-\\n\\nwarrant canine sniff that supplied probable cause for the warrant and there was\\n\\n“nothing more the officer could have or should have done” to be sure his search was\\n\\nlegal). We cannot read Leon or Scales to support the rules adopted by these courts.\\n\\nWhen a magistrate issues a warrant based on illegally obtained evidence, typically the\\n\\nmanner in which the affidavit evidence is obtained is not before the magistrate, and the\\n\\n 35\\n\\fmagistrate is not asked explicitly to endorse the evidence-gathering procedure. Even\\n\\nthough some disclosure of the evidence-gathering technique may have occurred, that is\\n\\nnot ordinarily the focus of an application for a warrant. Thus, we are unwilling to read a\\n\\nwarrant as ratifying the information-gathering process of a search that preceded it. In any\\n\\nevent, we are bound by Scales, which appears to us to have been correctly decided.\\n\\n Therefore, the district court erred by finding that the good faith doctrine applied to\\n\\nthe searches Agent Nishida conducted in execution of the second warrant.\\n\\n 3. Inevitable discovery doctrine supports denial of Loera’s motion\\n\\n Finally, we consider whether the government would have inevitably discovered\\n\\nthe child pornography evidence on Loera’s electronic devices. Loera argues that, because\\n\\nthere was no probable cause to support the second warrant, all evidence discovered as a\\n\\nresult of the execution of the second warrant should have been suppressed. The issue\\n\\nbefore us, then, is whether the FBI agents would have inevitably discovered the roughly\\n\\n330 child pornography images on Loera’s CDs and 730 child pornography images on\\n\\nLoera’s laptop that Nishida found when he executed the second warrant. We conclude\\n\\nthat they would have. Accordingly, we affirm the district court’s denial of Loera’s\\n\\nmotion to suppress.\\n\\n When evidence is obtained in violation of the Fourth Amendment, that\\n\\nevidence need not be suppressed if agents inevitably would have discovered it\\n\\nthrough lawful means independent from the unconstitutional search. United States v.\\n\\nChristy, 739 F.3d 534, 540 (10th Cir. 2014). The government is required to prove by a\\n\\npreponderance of the evidence that the unlawfully-obtained evidence would have been\\n\\n 36\\n\\fdiscovered through lawful means. Id. The “lawful means” need not be a second,\\n\\nindependent investigation. Id. Rather, the inevitable discovery doctrine will apply if\\n\\nthere was “one line of investigation that would have led inevitably to the obtaining of a\\n\\nsearch warrant by independent lawful means but was halted prematurely by a search\\n\\nsubsequently contended to be illegal.” Id. (citations omitted). The key to applying this\\n\\ndoctrine is to place the government officers in the “same positions they would have\\n\\nbeen in had the impermissible conduct not taken place,” and, from that vantage point,\\n\\nto ask whether the government would have inevitably discovered the evidence\\n\\nlawfully. Nix v. Williams, 467 U.S. 431, 447 (1984).\\n\\n Here, the district court’s supportable findings demonstrate by a preponderance of\\n\\nthe evidence that the FBI would have inevitably discovered the child pornography\\n\\nevidence on Loera’s electronic devices through lawful means independent from Agent\\n\\nCravens’ unlawful second search. On November 26 (the day before the second search),\\n\\nthe government lawfully had in its possession Loera’s computers, external hard drives,\\n\\niPhone, iPad, and thirteen CDs (nine without child pornography and four with child\\n\\npornography).4 The government had the authority under the first warrant to search\\n\\nLoera’s electronic devices—most importantly his laptop and CDs—for evidence of\\n\\ncomputer fraud. The district court issued an explicit factual finding that, had the\\n\\nsecond warrant never been obtained, Agent Nishida would “have searched [Loera’s\\n\\n\\n\\n4\\n As mentioned above, although Loera challenges the first search of these four CDs,\\nhe does not separately challenge their seizure were we to determine, as we have, that\\nthe first search was constitutional.\\n 37\\n\\flaptop] for evidence of electronic mail hijacking and computer fraud pursuant to the\\n\\n[f]irst [w]arrant.” Dist. Ct. Op. at 24. The district court further found that, as part of\\n\\nthat search, lawfully conducted pursuant to the parameters of the first warrant, Agent\\n\\nNishida would have searched the electronic folders where he discovered child\\n\\npornography when he executed the second warrant, including, the “My Documents”\\n\\nfolder, the “Bookmarks” tab of Loera’s internet browser, and a folder saved on the\\n\\nDesktop titled “Allmyfiles.txt.” Id. at 24–25. The district court also accepted\\n\\nNishida’s statement that, had he found child pornography images on the laptop\\n\\nduring a search conducted solely pursuant to the first warrant, he would have “alerted\\n\\nthe case agent so that [he] could get a search warrant for child pornography.” Id. at\\n\\n25.\\n\\n The laptop, including the specific files referenced above, contained over 730\\n\\nimages and 40 movies involving child pornography. Id. at 24. To take one specific\\n\\nexample, the “Allmyfiles.txt” file, which the district court found Nishida would have\\n\\nlawfully opened pursuant to the first warrant, contained files called “Spycam 9yr\\n\\nUndress.” Id. Such information would have been sufficient to establish probable\\n\\ncause to support a warrant to search all of the electronic devices belonging to Loera\\n\\nthat the government had in its possession, including the four CDs that Agent Cravens\\n\\nsearched unlawfully on November 27. That fact, combined with Agent Nishida’s\\n\\nindication that he would have sought a warrant, allows us to conclude that the\\n\\ninevitable discovery doctrine applies in this case such that the evidence discovered\\n\\npursuant to the second warrant did not need to be suppressed.\\n\\n 38\\n\\f III. CONCLUSION\\n\\n For the foregoing reasons, we AFFIRM the orders of the district court denying\\n\\nthe defendant’s motion to suppress and motion for reconsideration.\\n\\n\\n\\n\\n 39\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4396329/\", \"author_raw\": \"EBEL, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"LUCERO"},"judge2":{"kind":"string","value":"EBEL"},"judge3":{"kind":"string","value":"PHILLIPS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4619076/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America Plaintiff - Appellee, v. Jason LOERA, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-13\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 13, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\n UNITED STATES OF AMERICA\n\n Plaintiff - Appellee,\n\n v. No. 17-2180\n\n JASON LOERA,\n\n Defendant - Appellant.\n _________________________________\n\n Appeal from the United States District Court\n for the District of New Mexico\n (D.C. No. 1:13-CR-01876-JB-1)\n _________________________________\n\nJerry A. Walz, Walz and Associates, P.C., Albuquerque, New Mexico for Defendant-\nAppellant.\n\nKristopher N. Houghton, Assistant United States Attorney (John C. Anderson, United\nStates Attorney, with him on the brief), Albuquerque, New Mexico for Plaintiff-\nAppellee.\n _________________________________\n\nBefore LUCERO, EBEL, and PHILLIPS, Circuit Judges.\n _________________________________\n\nEBEL, Circuit Judge.\n _________________________________\n\n This appeal requires us to apply Fourth Amendment principles to a situation\n\nwhere a police officer executing a warrant to search an electronic storage device for\n\nevidence of one crime discovers evidence of other criminal activity. Here, while\n\fexecuting a warrant to search Jason Loera’s home for evidence of computer fraud,\n\nFBI agents discovered child pornography on four of Loera’s CDs. Despite\n\ndiscovering the pornography, the agents continued their search for evidence of\n\ncomputer fraud—one agent continued to search the CDs that were found to contain\n\nsome child pornography and a second agent searched other electronic devices\n\nbelonging to Loera, not including those particular CDs (Search 1). After the agents\n\nfinished their on-site search, they seized a number of electronic devices that appeared\n\nto contain evidence of computer fraud, plus the four CDs that were found to contain\n\nchild pornography, and then brought the seized items back to their office. One week\n\nlater, one of the agents reopened the CDs that he knew contained some child\n\npornography so that he could describe a few pornographic images in an affidavit\n\nrequesting a (second) warrant to search all of the seized electronic devices for child\n\npornography (Search 2). A magistrate judge issued the warrant, and, upon executing\n\nit through two searches, the agents found more child pornography.\n\n In the subsequent prosecution against him for possessing child pornography,\n\nLoera filed a motion to suppress the evidence seized pursuant to each search, arguing\n\nthat the searches violated the Fourth Amendment. On denial of his motion, Loera\n\npled guilty to receipt of child pornography but preserved his right to appeal that\n\ndenial. Exercising jurisdiction under 28 U.S.C. § 1291, we affirm the denial of\n\nLoera’s motion to suppress. We hold, among other things, that the Fourth\n\nAmendment does not require police officers to stop executing an electronic search\n\nwarrant when they discover evidence of an ongoing crime outside the scope of the\n\n 2\n\fwarrant, so long as their search remains directed at uncovering evidence specified in\n\nthat warrant.\n\n I. BACKGROUND\n\n This case involves several police searches governed by the Fourth\n\nAmendment. The Fourth Amendment protects “the right of the people to be secure in\n\ntheir persons, houses, papers, and effects, against unreasonable searches and\n\nseizures.” U.S. Const. amend. IV. Generally, for a search to be reasonable, it must\n\nbe authorized by a warrant that “particularly” describes “the place to be searched, and\n\nthe persons or things to be seized.” U.S. Const. amend. IV. Once officers obtain a\n\nsufficiently particular warrant, they must execute it according to the warrant’s terms.\n\nHorton v. California, 496 U.S. 128, 140 (1990). The following undisputed facts\n\nexplain how the warrant-based searches in this case arose.\n\n In 2012, the FBI began investigating Jason Loera for illegally intercepting e-\n\nmails intended for then-sitting New Mexico Governor Susana Martinez and her staff\n\nin violation of 18 U.S.C. § 2511 (illegal interception) and 18 U.S.C. § 1030\n\n(computer fraud) [collectively, “computer fraud”]. As part of that investigation\n\n(more details of which can be found in the district court’s opinion United States v.\n\nLoera, 59 F. Supp. 3d 1089, 1095–1108 (D.N.M. 2014)), FBI agents applied for and\n\nreceived a warrant to search Loera’s residence for computer fraud, including any\n\nsuch evidence residing on electronic devices or storage media (“the first warrant”).\n\n The first warrant authorized FBI agents to search and seize, in relevant part,\n\n“All records, in any form, relating to violations of [computer fraud], involving Jason\n\n 3\n\fLoera.” ROA Vol. I at 37. The warrant defined the terms “records” and “information”\n\nas including: “all of the foregoing items of evidence in whatever forms and by whatever\n\nmeans they may have been created or stored, including any form of computer or\n\nelectronic storage (such as hard disks or other media that can store data).” Id. at 39. In a\n\nseparate provision, the warrant sought “Any computers, cell phones, and/or electronic\n\nmedia that could have been used as a means to commit the offenses described on the\n\nwarrant.” Id. at 87. Finally, for any electronic device, whether it was used to commit the\n\noffenses or simply had relevant records stored on it, the warrant permitted the agents to\n\nsearch and seize evidence of who used, owned, or controlled the device, such as\n\n“configuration files . . . documents, browsing history . . . photographs, and\n\ncorrespondence . . . .” Id. at 38.\n\n A. The First Search\n\n On November 20, 2012, FBI agents including Agent Aaron Cravens and\n\nSpecial Agent Brian Nishida executed the first search warrant. They discovered a\n\nlarge volume of electronic media in Loera’s residence, including CDs, DVDs, laptop\n\ncomputers, external hard drives, a USB flash drive, an iPhone, and an iPad. Cravens\n\nand Nishida were responsible for “previewing” the CDs at Loera’s residence to\n\nensure that the FBI seized only those CDs that contained information relevant to the\n\nauthorized investigation. ROA Vol. II at 53, 58. The two agents split up the CDs\n\nbetween themselves and searched them separately.\n\n Cravens tried to view the files of the first CD using a program called FTK\n\nImager, which would have allowed Cravens to limit his search to a particular type of\n\n 4\n\ffile, for example, only image, text, or audio files. However, the program did not\n\nwork. Consequently, Cravens opened the CD on a computer and used the “thumbnail\n\nview” to preview the files stored on it, meaning, he saw small images of the files, the\n\nfile names, and the file types in a vertical list that he had to scroll through to see in\n\nits entirety. Although Cravens believed he had authority under the first warrant to view\n\nthe entire contents of the CD, Cravens used the thumbnail-image view to fast-track his\n\nsearch. He would scroll past irrelevant files but “click[] on anything that didn’t appear\n\ncorrect, or any documents” to open them. Id. at 92. While Cravens was “scrolling\n\ndown through the images or files . . . on the CDs, [he] found what looked like a nude\n\nchild.” Id. at 60. He opened the file to confirm that it was an image of child\n\npornography. After determining that it was, Cravens ejected the CD from his\n\ncomputer, set it aside, and alerted Agent Nishida and the FBI agent in charge of\n\nLoera’s case. Then, Cravens searched the rest of the CDs assigned to him for\n\nevidence of computer fraud. Cravens later found a child pornography image on a\n\nsecond CD. Just as he did with the first, Cravens set the CD aside after discovering the\n\nillegal images and did not open any other files on that CD.\n\n Agent Nishida took a different approach to his search. He previewed the files\n\non his assigned CDs using the “details view” of Windows Explorer, meaning that he\n\nsaw a list of files, file names, and last-modified dates of those files, but not pictures\n\nassociated with the files. Id. at 157. For his search of the CDs, or “triage,” as he called\n\nit, Nishida would open two or three files on each CD and then determine from that\n\nsample whether the CD should be seized pursuant to the warrant. Id. at 160. If Nishida\n\n 5\n\ffound something he believed might be responsive to the warrant in the files that he\n\nsampled, he would set the CD aside to be reviewed off-site. As he was sampling files,\n\nNishida found child pornography on two CDs. Unlike Cravens, Nishida did not cease his\n\nsearch of those CDs after discovering child pornography; he continued sampling files on\n\nthe CDs to determine if they contained information that was responsive to the warrant.\n\n The FBI seized thirteen CDs in total from Loera’s residence: four contained child\n\npornography images and nine contained evidence of computer fraud.1 In addition to the\n\nthirteen CDs, the FBI seized computers, external hard drives, an iPhone, and an iPad.\n\n B. The Second Search\n\n One week later, on November 27, 2012, Cravens decided to apply for a search\n\nwarrant to search the items seized from Loera’s residence for child pornography.\n\nCravens wanted to include in his warrant affidavit a detailed description of one child\n\npornography image from each of the four CDs on which he and Nishida had found child\n\npornography during their on-site preview. Consequently, Cravens opened each of the\n\nfour CDs, viewing several images on each, to find child pornography images that he\n\ncould accurately describe. Viewing the photos and drafting the affidavit took a total of\n\ntwo-and-a-half hours. However, Cravens testified before the district court that he did not\n\nspend “anywhere near the two-and-a-half hours” actually looking at photos on the CDs.\n\nId. at 74-75.\n\n\n\n1\n There is no indication in the record whether the four CDs that contained child\npornography also contained evidence responsive to the warrant. However, Loera does\nnot challenge the FBI’s seizure of those CDs pursuant to the first warrant.\n 6\n\f Cravens’ affidavit included two sections. In Section I, Cravens described his\n\ntraining and experience with computers and child pornography. In Section II, Cravens\n\nexplained the details of the FBI’s investigation of Loera that led to the agent’s discovery\n\nof child pornography on the CDs in Loera’s residence. In particular, paragraph 21\n\ndescribed in general terms how Cravens discovered the child pornography:\n\n 21. In the process of executing this warrant, an FBI certified computer\n forensic examiner and a computer analysis response team (CART)\n technician previewed the loose media located during the search (e.g.,\n thumb drives, CD-Rs, DVD-Rs, memory cards, etc.) for evidence\n relevant to the original unrelated investigation. During the preview, the\n examiners identified four writable CDs which appeared to contain\n images of child pornography. The CDs were seized and placed in the\n evidence control room at the local FBI office.\n\nROA Vol. I at 120. In paragraph 23, Cravens explained that on November 27, 2012,\n\nhe “reviewed the four CDs . . . that were believed to contain child pornography,” id.\n\nat 121, and that “[d]uring the review of the CDs, [he] observed multiple pictures of\n\nchildren many of which are in various states of dress,” id. Then, in paragraphs\n\n24-27, Cravens provided a detailed description of one image from each CD that\n\ndepicted a minor engaged in sexually explicit conduct. Cravens’ descriptions\n\nincluded the apparent age of the minor and the conduct depicted. On November 29,\n\n2012, based on Cravens’ affidavit, a federal magistrate judge approved a warrant to\n\nsearch the thirteen CDs and six other electronic devices that were seized from Loera’s\n\nresidence for child pornography (“the second warrant”).\n\n\n\n\n 7\n\f C. Searches Pursuant to the Second Warrant\n\n Agent Nishida executed the second warrant on two separate dates. In December\n\n2012, Nishida searched Loera’s laptop pursuant to both the first and second warrants,\n\nlooking for evidence of computer fraud and child pornography. He discovered more than\n\n730 child pornography images on Loera’s laptop. In April 2013, Nishida searched the\n\nfour CDs seized from Loera’s residence for child pornography pursuant to the second\n\nwarrant. He discovered approximately 330 images and two movies of child pornography\n\non those CDs.\n\n D. Proceedings Below\n\n A federal grand jury indicted Loera on several counts of possessing child\n\npornography that implicated the images found on both his laptop and his CDs. Loera\n\nfiled a motion to suppress that child pornography evidence, and the district court\n\ndenied the motion. Loera filed a motion for reconsideration, which the district court\n\nalso denied. Following that denial, Loera pled guilty to one count of knowingly\n\nreceiving child pornography in violation of 18 U.S.C. §§ 2252(a)(2), 2252(b)(1), and\n\n2256, pursuant to a plea agreement, but he reserved the right to appeal the denial of\n\nhis motions.\n\n On appeal, Loera argues that the district court should have suppressed the\n\nchild pornography evidence discovered during the first search, the second search, and\n\nthe searches conducted pursuant to the second warrant because, according to Loera,\n\neach search was unlawful. Loera argues that the first search exceeded the scope of\n\nthe first warrant, the second search exceeded the scope of the first warrant, and the\n\n 8\n\flast two searches, while authorized by the second warrant, were unlawful because\n\nthat warrant was invalid. Additionally, Loera maintains that none of the exceptions\n\nto the warrant requirement apply to the searches in this case. We conclude that the\n\nfirst search was lawful, but we agree with Loera that the remaining searches were\n\nunlawful. Nevertheless, we AFFIRM the district court’s denial of Loera’s motion to\n\nsuppress and motion to reconsider under the inevitable discovery doctrine.\n\n II. DISCUSSION\n\n A. Standard of Review\n\n “When reviewing the district court’s denial of a motion to suppress, we view\n\nthe evidence in the light most favorable to the government and accept the district\n\ncourt’s factual findings unless they are clearly erroneous,” United States v. Grimmett,\n\n439 F.3d 1263, 1268 (10th Cir. 2006), but “[t]he ultimate question of reasonableness\n\nunder the Fourth Amendment is a legal conclusion that we review de novo.” Id.\n\nAccordingly, de novo review applies to the issues we address in this opinion,\n\nincluding, the scope of a search warrant, United States v. Angelos, 433 F.3d 738, 745\n\n(10th Cir. 2006), the sufficiency of a search warrant, United States v. Danhauer, 229\n\nF.3d 1002, 1005 (10th Cir. 2000), the applicability of the good-faith exception, id.,\n\nand the applicability of the inevitable discovery doctrine, United States v. Christy, 739\n\nF.3d 534, 540 (10th Cir. 2014).\n\n B. Validity of the Government’s Application for the First Warrant\n\n First, Loera argues that the FBI agents obtained the initial warrant to search\n\nhis residence for evidence of computer fraud as a pretext to search instead for\n\n 9\n\fevidence of child pornography. The district court disagreed, finding that the sole\n\npurpose of the first search was to uncover evidence of computer fraud. We affirm\n\nthat conclusion.\n\n Loera’s pretext argument is based on a statement that Agent Nishida made in a\n\nreport dated February 28, 2013, three months after the first and second searches were\n\nconducted. In that report, Nishida wrote:\n\n On November 14, 2012, SA Michael Boady requested that the above\n listed specimen or specimens be examined for evidence of intercepting a\n communication. For example, e-mail messages to or from the domain\n Susanna2010.com. In addition, SA Boady requested that the evidence\n also be examined for evidence of child pornography possession and\n receipt.\n\nROA Vol. II at 191–92. Loera argues that this report proves that on November 14,\n\n2012, six days before the first search, Agent Nishida received instructions to search\n\nLoera’s home and effects for evidence of child pornography.\n\n The district court made explicit factual findings to the contrary, which are\n\nsupported by the record. First, the district court found that, had the FBI agents had\n\nsuspicions that Loera possessed child pornography, agents would have included that\n\ninformation in their application for the first warrant. Second, Agent Nishida testified\n\nat the suppression hearing that the February 2013 report summarized two separate\n\ninstructions from SA Boady: on November 14, 2012, Boady instructed Nishida to\n\nsearch for evidence of interception, and, later, Boady instructed Nishida to search for\n\nevidence of child pornography. Finally, both Cravens and Nishida testified at the\n\nsuppression hearing that the purpose of the November 20 search was only to uncover\n\n\n 10\n\fevidence of computer fraud, and the district court credited that testimony. Each of\n\nthese facts supports the district court’s determination that the agents conducted the\n\nfirst search solely to look for evidence of computer fraud. And we are unpersuaded\n\nby Loera’s only evidence of pretext, the report written three months after the\n\nallegedly pretextual search.2\n\n Thus, we conclude the FBI agents had no pretextual motivations for obtaining\n\nthe first warrant, and we affirm the district on this issue.\n\n C. Reasonableness of the First and Second Searches\n\n Next, we determine that the first search of Loera’s residence was reasonable\n\nbecause it was directed solely at uncovering the items specified in the first warrant\n\nboth before and after the officers discovered the child pornography evidence.\n\nHowever, we conclude that the second search was unreasonable because it was\n\ndirected at uncovering evidence of child pornography.\n\n 1. Relevant legal principles\n\n The Fourth Amendment provides:\n\n The right of the people to be secure in their persons, houses, papers, and\n effects, against unreasonable searches and seizures, shall not be\n violated, and no Warrants shall issue, but upon probable cause,\n supported by Oath or affirmation, and particularly describing the place\n to be searched, and the persons or things to be seized.\n\n\n\n\n2\n Alternatively, even if the agents had an additional motive for conducting the first\nsearch, that argument would fail as a matter of law under Whren v. United States,\n517 U.S. 806, 813 (1996).\n 11\n\fU.S. Const. amend. IV. It is now well-recognized that “the ultimate touchstone of\n\nthe Fourth Amendment is ‘reasonableness.’” Brigham City v. Stuart, 547 U.S. 398,\n\n403 (2006). “[R]easonableness generally requires the obtaining of a judicial\n\nwarrant,” Riley v. California, 134 S.Ct. 2473, 2482 (2014), subject to only a few\n\nexceptions. The warrant must “particularly” describe “the place to be searched, and\n\nthe persons or things to be seized,” U.S. Const. amend. IV.\n\n However, obtaining a sufficiently particular warrant is just the first step to\n\nconducting a reasonable search. The officers tasked with executing a sufficiently\n\nparticular warrant must conduct their search “strictly within the bounds set by the\n\nwarrant.” Bivens v. Six Unknown Named Agents of Fed. Bureau of Narcotics, 403\n\nU.S. 388, 395 n.7 (1971) (quoting Marron, 275 U.S. at 196). The Supreme Court has\n\nheld that, “[i]f the scope of [a] search exceeds that permitted by the terms of a validly\n\nissued warrant . . . the subsequent seizure [of evidence] is unconstitutional without\n\nmore.” Horton v. California, 496 U.S. 128, 140 (1990).\n\n Determining whether a search exceeds the scope of its authorizing warrant is,\n\nlike most inquiries under the Fourth Amendment, an exercise in reasonableness\n\nassessed on a case-by-case basis. Dalia v. United States, 441 U.S. 238, 258 (1979)\n\n(holding that the manner of a search is subject to “later judicial review as to its\n\nreasonableness”). The general Fourth Amendment rule is that investigators executing\n\na warrant can look anywhere where evidence described in the warrant might\n\nconceivably be located. United States v. Ross, 456 U.S. 798, 824 (1982). For\n\nexample:\n\n 12\n\f Just as probable cause to believe that a stolen lawnmower may be found in\n a garage will not support a warrant to search an upstairs bedroom, probable\n cause to believe that undocumented aliens are being transported in a van\n will not justify a warrantless search of a suitcase. Probable cause to believe\n that a container placed in the trunk of a taxi contains contraband or\n evidence does not justify a search of the entire cab.\n\nId. This limitation works well in the physical-search context to ensure that searches\n\npursuant to warrants remain narrowly tailored, but it is less effective in the electronic-\n\nsearch context where searches confront what one commentator has called the “needle-in-\n\na-haystack” problem. Orin S. Kerr, Digital Evidence and the New Criminal\n\nProcedure, 105 Colum. L. Rev. 279, 301 (2005). Given the enormous amount of data\n\nthat computers can store and the infinite places within a computer that electronic\n\nevidence might conceivably be located, the traditional rule risks allowing unlimited\n\nelectronic searches.\n\n To deal with this problem, rather than focusing our analysis of the\n\nreasonableness of an electronic search on “what” a particular warrant permitted the\n\ngovernment agents to search (i.e., “a computer” or “a hard drive”), we have focused\n\non “how” the agents carried out the search, that is, the reasonableness of the search\n\nmethod the government employed. See United States v. Burgess, 576 F.3d 1078\n\n(10th Cir. 2009); United States v. Walser, 275 F.3d 981 (10th Cir. 2001); United\n\nStates v. Carey, 172 F.3d 1268 (10th Cir. 1999). Our electronic search precedents\n\ndemonstrate a shift away from considering what digital location was searched and\n\ntoward considering whether the forensic steps of the search process were reasonably\n\ndirected at uncovering the evidence specified in the search warrant. Shifting our\n\n\n 13\n\ffocus in this way is necessary in the electronic search context because search\n\nwarrants typically contain few—if any—restrictions on where within a computer or\n\nother electronic storage device the government is permitted to search. See United\n\nStates v. Christie, 717 F.3d 1156, 1165 (10th Cir. 2013) (holding that, so long as an\n\nelectronic search warrant requires the government to “direct all of its search efforts”\n\ntoward evidence relating to a specific crime, the warrant is sufficiently particular,\n\neven where it permits the government to search a “computer” for “all records”\n\nrelating to the crimes of “murder, neglect, and abuse”). Because it is “unrealistic to\n\nexpect a warrant prospectively [to] restrict the scope of a search by directory,\n\nfilename or extension or to attempt to structure search methods,” Burgess, 576 F.3d\n\nat 1093 (alteration added), our ex post assessment of the propriety of a government\n\nsearch is essential to ensuring that the Fourth Amendment’s protections are realized\n\nin this context. Our precedent of Carey, Burgess, and Walser, to which we turn next,\n\nare instructive as to what constitutes a reasonable electronic search pursuant to a\n\nvalid warrant.\n\n Carey is the only case in which we invalidated an electronic search for\n\nexceeding the scope of its authorizing warrant. See 172 F.3d at 1276. There, a\n\npolice officer obtained a warrant to search files on the defendant’s computer for\n\nevidence “pertaining to the sale and distribution of controlled substances.” Id. at\n\n1270. Prior to searching the computer, the officer first viewed the computer’s file\n\ndirectory, which showed numerous “JPG” files with sexually suggestive titles. Id.\n\nDuring his search, the officer came across a number of files that he did not recognize\n\n 14\n\fand that he was unable to view on the computer that he was using. Id. at 1271. To\n\nview the files, the officer downloaded them onto a separate disk, inserted that disk\n\ninto another computer, and then was immediately able to view a “JPG file” that\n\ndepicted child pornography. Id. Rather than navigating away from the\n\nnonresponsive material, the officer “downloaded approximately two hundred forty-\n\nfour” more JPG files and then transferred them to nineteen disks, viewing five to\n\nseven images on each disk to determine that they all contained child pornography.\n\nId. The whole process took about five hours. Id. at 1273. After he had catalogued\n\nthe child pornography images in this manner, he then “returned” to his “original task\n\nof looking for evidence of drug transactions.” Id. at 1271.\n\n The Carey court held that this was an unlawful, general exploratory search\n\nbecause, although it was permissible for the officer to open the first JPG file to see if\n\nit was responsive to the warrant, id. at 1273 n.4, his opening of the remaining files\n\nexceeded the bounds of the authorizing warrant, id. at 1276. The Carey court’s\n\nholding turned on four facts: (1) the officer spent five hours, a significant amount of\n\ntime, specifically perusing the trove of nonresponsive material, id. at 1273; (2) the\n\nnonresponsive files were characteristically distinct and set apart from the other files\n\non the computer (such that they could have been avoided) because each file was\n\nlabeled “JPG,” many had sexually suggestive titles, and the officer had to download\n\nthem to open them, id. at 1274; (3) the officer did not discover the files inadvertently\n\n(at least after his first look), id. at 1273; and (4) a more narrowly tailored search was\n\npossible—the officer could have gone back to searching for drug-related documents\n\n 15\n\fmuch sooner than he did, id. at 1273. Importantly, we did not condemn the officer’s\n\ndecision to return to searching for drug-related documents after discovering the child\n\npornography, but, instead, we condemned his “temporar[y] abandon[ment]” of the\n\noriginal search to conduct a “five hour search of the child pornography files.” Id. at\n\n1273.\n\n Next, we turn to Walser and Burgess, both of which upheld electronic searches\n\nin which the investigator discovered incriminating, nonresponsive material while\n\nexecuting a search warrant but then navigated away from it. In United States v.\n\nWalser, the police obtained a warrant to search the defendant’s hotel room for\n\nelectronically stored records of “evidence of the possession of controlled\n\nsubstances.” 275 F.3d 981, 983–84 (10th Cir. 2001). A police officer searched the\n\nroom pursuant to the warrant and found a laptop and a digital camera. Id. at 984.\n\nThe agent seized the laptop, removed it from the hotel room, and then conducted a\n\ndrug-specific search of the laptop, looking for “ledgers of drug transactions or images\n\nof drug use.” Id. In order to find those things, the agent employed a particularized\n\nsearch method that “selectively proceeded to the ‘Microsoft Works’ sub-folder on the\n\npremise that[,] because Works is a spreadsheet program, that folder would be most\n\nlikely to contain records relating to the business of drug trafficking.” Id. at 986. It\n\nwas while searching the contents of the Works folder that the officer came across a\n\nfile labeled “bstfit.avi” and opened it. Id. at 984. When he viewed the contents, he\n\ndiscovered that the file contained child pornography images. Id. at 986–87. He then\n\nimmediately ceased his search. Id.\n\n 16\n\f We upheld the officer’s search as reasonable because we determined that, by\n\nusing a particularized search method, the officer avoided conducting the kind of\n\n“sweeping, comprehensive search of a computer’s hard drive” that Carey prohibited.\n\nId. at 986. The defendant in Walser argued that the agent exceeded the scope of the\n\nwarrant by opening the “AVI file,” a video file, because “it could not possibly have\n\ncontained the type of evidence the [a]gent was authorized to search for, namely,\n\nrecords of drug transactions or still images of drug use.” Id. at 987. We rejected that\n\nargument by interpreting Carey to excuse an officer’s discovery of child pornography\n\nduring a search for “relevant records in places where such records might logically be\n\nfound” so long as the officer does not conduct a supervening search specifically\n\ndirected at finding pornography evidence. Id. at 986. Applying that rule, we held in\n\nWalser that the officer’s opening the “bstfit.avi” file was permissible because (1) he\n\nwas looking in a folder that was “most likely to contain records relating to the\n\nbusiness of drug trafficking” when he opened it, and (2) he did not conduct an\n\nintervening search directly focused on child pornography like the agent in Carey. Id.\n\nBased on those facts, we concluded that the “search was reasonable and within the\n\nparameters of the search warrant” and that the evidence found as a result of it did not\n\nneed to be suppressed. Id. at 987.\n\n Finally, in United States v. Burgess, 576 F.3d 1078 (10th Cir. 2009), we again\n\nupheld an electronic search that uncovered evidence of child pornography as\n\nreasonable and within the scope of its authorizing warrant. There, police obtained a\n\nwarrant to search a motorhome for, among other things, “computer records” that\n\n 17\n\fwould tend to show “conspiracy to sell drugs.” Id. at 1083. The warrant\n\nincorporated the affidavit on which it was based, which stated that the affiant “knows\n\nthat persons involved in trafficking or the use of narcotics often keep photographs of\n\ncoconspirators or photographs of illegal narcotics in their vehicle.” Id.\n\n Based on the warrant, officers searched two hard drives and a laptop found in\n\nthe motorhome. Id. An agent searched one of the hard drives by using a program\n\ncalled EnCase, which copies the contents of a hard drive over to a computer to\n\nprevent file corruption. Id. at 1083–84. EnCase allows an investigator to “preview”\n\nreduced-sized photos of each image file as they are being copied. Id. at 1084, 1094.\n\nThe agent took advantage of this feature and viewed each image file on the hard drive\n\nas it was being copied. Id. at 1084. After viewing 200-300 digital images, mostly\n\npersonal photos, the agent saw an image that looked like child sexual exploitation.\n\nId. He then closed the preview program and sought a warrant to search all of the\n\ndefendant’s electronic storage devices for evidence of child pornography. Id. Upon\n\nconducting that search, the agent found more than one hundred thousand illegal\n\nimages. Id.\n\n The defendant asked the district court to suppress the child pornography\n\nevidence because, he argued, the agent’s use of the “preview” program exceeded the\n\nscope of the warrant because he did not employ a particularized search method like\n\nthe agent in Walser but instead looked through each image file contained on the hard\n\ndrive. We determined that the agent’s use of the “preview” program was reasonable\n\nand did not exceed the scope of the warrant for two reasons. First, we noted that,\n\n 18\n\fbecause the warrant did not expressly limit the file types that the agent was allowed\n\nto search, for example, by limiting the search to text files (.doc, .wpd, .txt, etc.), the\n\nagent was well within the scope of the warrant when he decided to view all of the\n\nimage files on the hard drive using the preview program. Id. at 1092. Second, we\n\ndetermined that there was no reasonable way for the agent to conduct a more\n\nnarrowly tailored search because, when the object of a search is likely to be an image\n\nfile, as it was in Burgess, “there may be no practical substitute for actually looking in\n\nmany (perhaps all) folders and sometimes at the documents contained within those\n\nfolders.” Id. at 1094.\n\n Reading these cases together, we determine that four features of the\n\nunconstitutional search in Carey demonstrate that it was unreasonably directed at\n\nuncovering evidence of child pornography, rather than directed at the evidence\n\nspecified in the warrant, and distinguish it from the reasonable searches in Walser\n\nand Burgess: (1) the length of time the searching officer spent looking at the\n\nincriminating, nonresponsive evidence (five hours in Carey versus less than one\n\nminute in Walser and Burgess); (2) the fact that the nonresponsive files were set apart\n\nfrom the responsive files saved on the storage device (JPG files downloaded onto\n\nseparate disks in Carey versus generic files intermingled all in one place in Burgess);\n\n(3) the manner in which the evidence was discovered (purposefully in Carey versus\n\ninadvertently in Walser and Burgess);3 and (4) the breadth of the search method\n\n\n3\n We acknowledge that in Horton v. California, 496 U.S. 128, 130 (1990), the\nSupreme Court held that, in physical searches, “even though inadvertence is a\n 19\n\femployed (the wide detour in Carey versus the narrowly tailored search in Walser).\n\nContrary to Loera’s assertion, these cases do not require that officers stop searching\n\nupon discovering evidence of a crime outside the scope of the warrant. Such a rule\n\nwould prohibit what the Fourth Amendment expressly permits—reasonable searches\n\nbased upon a warrant supported by probable cause. We have never required that.\n\n This conclusion brings us in line with every circuit that has confronted this\n\nissue. See United States v. Stabile, 633 F.3d 219, 240 (3d Cir. 2011) (upholding\n\ndenial of motion to suppress where officers continued warrant-authorized search of\n\nthe defendant’s computer for financial crimes after discovering child pornography);\n\nUnited States v. Williams, 592 F.3d 511, 521–24 (4th Cir. 2010) (upholding search\n\nwhere the officer continued his warrant-authorized search of the defendant’s\n\ncomputer for evidence of “making threats and computer harassment” after\n\ndiscovering child pornography); United States v. Miranda, 325 F.App’x 858, 859–60\n\n(11th Cir. 2009) (per curiam) (unpublished) (upholding search where officer\n\ncontinued his warrant-authorized search for evidence of counterfeit software after\n\ndiscovering child pornography); United States v. Wong, 334 F.3d 831, 834 (9th Cir.\n\n\ncharacteristic of most legitimate ‘plain view’ seizures, it is not a necessary\ncondition.” However, because Carey, Walser, and Burgess, each of which succeeded\nHorton in time, considered the subjective intentions of the searching officers where\nthat information was available, we continue to include inadvertence as a factor to\nconsider when deciding whether an electronic search fell within the scope of its\nauthorizing warrant or outside of it. The fundamental differences between electronic\nsearches and physical searches, including the fact that electronic search warrants are\nless likely prospectively to restrict the scope of the search, justify our inclusion of\nthat factor. See Horton, 496 U.S. at 139 (abandoning inadvertence as a necessary\ncondition for a legitimate plain view seizure).\n 20\n\f2003) (upholding denial of motion to suppress where the officer continued his\n\nwarrant-authorized search of the defendant’s computer for, among other things,\n\n“[a]ny maps, receipts, or writings, depicting Churchill County Nevada” after\n\ndiscovering child pornography).\n\n Although officers do not have to stop executing a search warrant when they\n\nrun across evidence outside the warrant’s scope, they must nevertheless reasonably\n\ndirect their search toward evidence specified in the warrant. What that looks like\n\ndepends on the particular facts of a given case. Narrowly tailored search methods\n\nthat begin looking “in the most obvious places and [then] progressively move from the\n\nobvious to the obscure,” Burgess, 576 F.3d at 1094, should be used where possible but\n\nare not necessary in every case. In cases like this one, where the electronic storage\n\ndevice is not well-organized and the most practical way to search it is through an item-\n\nby-item review, “there may be no practical substitute for actually looking in many\n\n(perhaps all) folders and sometimes at the documents contained within those folders.”\n\nId. In such a case, however, the searching officer must respond appropriately to what\n\nhe or she sees. The reasonableness of a search evolves as the search progresses and\n\nas the searching officer learns more about the files on the device that he or she is\n\nsearching.\n\n An analogy to the physical realm is helpful here. Imagine a warrant authorizes\n\npolice officers to search a “residence” for evidence of “firearms and ammunition.”\n\nUnder that warrant, it would be reasonable for a police officer to search the medicine\n\ncabinet in the bathroom for a minute or two to see if a small gun or ammunition is\n\n 21\n\fhidden there, however, it would be unreasonable for the officer to spend two hours\n\nreading the labels on each bottle of medicine in the cabinet. On the other hand, if the\n\nwarrant had authorized the officer to search the residence for evidence of “illegal\n\ndrug trafficking and manufacture,” an intensive search of the medicine cabinet would\n\nbe reasonable. In both cases, the medicine cabinet is fair game to search, but the\n\nintensity level of the permitted search differs depending on the evidence to be seized.\n\nThe same is true for electronic searches. While in some cases many (perhaps all)\n\nelectronic areas of a computer will be fair game to search, the level of intensity that\n\nofficers are permitted to spend searching those areas will differ depending on\n\nwhether the area appears to contain responsive material. This is true even when\n\nofficers come across evidence of incriminating, nonresponsive material. In all cases,\n\nthe ultimate test is the one mandated by the Fourth Amendment: whether the search\n\nwas “reasonable” under the circumstances. In the case of a computer search,\n\n“reasonableness” requires officers to take into account the flexibility of computers\n\nand the multiple configurations to which they may be adapted. As the computer\n\nsearch continues and as the executing officer obtains more information about how a\n\nsuspect used his computer, that too may inform the reasonableness of the continuing\n\nsearch.\n\n We now apply these principles to the November 20 and 27 searches conducted\n\nin this case.\n\n\n\n\n 22\n\f 2. November 20 search was reasonable\n\n Loera argues that, although the first warrant permitted the FBI agents to search his\n\nCDs for evidence of computer fraud, the officers’ search exceeded the scope of the first\n\nwarrant when they continued searching after discovering evidence of child pornography.\n\nWe disagree. The searches that Agent Cravens and Agent Nishida each conducted of\n\nLoera’s CDs on November 20 were reasonable and conducted within the scope of the\n\nfirst warrant because at all times each was reasonably directed at discovering evidence of\n\ncomputer fraud. Therefore, the first search did not violate the Fourth Amendment and\n\nthus did not warrant suppression of the evidence discovered during that search.\n\n The agents’ searches on November 20 resemble the searches in Walser and\n\nBurgess more than they resemble the search in Carey, both before and after they\n\ndiscovered the child pornography evidence. First, both agents here spent very little\n\ntime looking at the child pornography images they discovered. They noticed them,\n\nalerted a supervisor, and then moved on to the rest of the images on the same CD (in\n\nNishida’s case), or the other CDs (in Cravens’ case), looking for evidence of\n\ncomputer fraud. Both responses were reasonable because, as mentioned above, the\n\nagents were not required to stop searching altogether. And both responses\n\ndemonstrate an effort to navigate away from the nonresponsive material and toward\n\nfiles that they believed were more likely to contain material responsive to the\n\nwarrant. Second, the files on the CDs that the agents previewed were not\n\ncharacteristically distinct or set apart from the other files, in contrast to Carey. Agent\n\nCravens testified that, when he put a CD into his computer to see the files that it\n\n 23\n\fcontained, the computer pulled up a generic list of those files. The record does not\n\nindicate that there were any folders or distinctive titles setting clearly apart the\n\nnonresponsive child pornography files from the other files on the disk. Loera bears\n\nthe burden of proof on his suppression motion, and he has offered no evidence on this\n\npoint. Third, the agents discovered the child pornography files inadvertently on\n\nNovember 20. Fourth, both agents’ search methods were reasonably narrow under\n\nthe circumstances, considering the fact that the CDs did not seem particularly\n\norganized. Given that the warrant permitted the agents to search the CDs for\n\n“photographs,” “documents,” and “configuration files,” it was reasonable for Nishida and\n\nCravens to search all file types on the CDs (image, video, and text) for evidence of\n\ncomputer fraud rather than to narrow that search to one particular file type. The agents’\n\nsearches on November 20 were reasonable because they fell within the scope of the\n\nfirst warrant both before and after they discovered the child pornography evidence. We\n\nreverse the district court’s ruling to the contrary.\n\n 3. November 27 search was unreasonable\n\n Loera also argues that Agent Cravens’ subsequent search on November 27,\n\n2012, of the four seized CDs that contained child pornography violated the Fourth\n\nAmendment because Cravens was “[i]ntentionally searching for evidence of a crime\n\noutside the scope of the [f]irst [w]arrant prior to obtaining a new warrant.” Aplt. Br. 29.\n\nIn making this argument, Loera accepts that the first warrant permitted the government to\n\nseize the four CDs that were found to contain some child pornography and to search them\n\nfor evidence of computer fraud. Therefore, Loera challenges Cravens’ November 27\n\n 24\n\fsearch only for exceeding that permission. Accordingly, we confine our analysis to\n\nwhether the second search exceeded the scope of the first warrant. The district court\n\nconcluded that it did and that neither exigent circumstances nor any other exception to\n\nthe warrant requirement justified that search. We agree and conclude that the district\n\ncourt correctly excised the evidence obtained during the November 27th search from\n\nCravens’ affidavit for the second warrant. Several of the district court’s factual findings\n\nsupport that result.\n\n The district court found that “Cravens was not searching for evidence of\n\nelectronic fraud” on November 27 but instead was searching for child pornography.\n\nDist. Ct. Op. at 144. The district court based this finding on Cravens’ testimony at the\n\nsuppression hearing that he reopened Loera’s CDs on November 27 specifically “[t]o\n\nwrite a description of an image on the disc” so that he could “obtain a second warrant\n\nfor child pornography.” ROA Vol. II at 72. That admission is the most probative\n\nfact in the record that Cravens’ search was directed at finding child pornography.\n\nThe district court also found that Cravens had the four CDs for a total of two-and-a-\n\nhalf hours that day, during which time he searched the CDs and drafted the second\n\naffidavit. Although the record does not indicate how long Cravens searched the CDs,\n\nhe testified at the suppression hearing that he looked at several images on each CD—\n\n“more than just a couple” but “[m]ost likely less than a dozen.” ROA Vol. II at 143.\n\nWhatever the amount of time, Cravens’ devoted it exclusively to nonresponsive\n\nmaterial. Rather than navigate away from the child pornography images when he found\n\nthem, Cravens explicitly navigated toward such images. Based on these findings, we\n\n 25\n\fagree with the district court that, in contrast with the agents’ searches on November\n\n20, Agent Cravens’ search on November 27 was unreasonable because it was directed\n\nat uncovering evidence of child pornography.\n\n The government argues that two exceptions save Cravens’ search from\n\nviolating the Fourth Amendment: the plain view doctrine and the foregone-\n\nconclusion exception. We disagree. For its plain view argument, the government\n\nasserts that the law permitted Agent Cravens to take a “second look” at the child\n\npornography images on Loera’s CDs because members of the FBI had already seen\n\nthe images in plain view during a lawful search, and, therefore, his “second look”\n\nwas no further invasion of Loera’s privacy than the initial, lawful viewing. The\n\ngovernment points to a Fourth Circuit case, United States v. Jackson, 131 F.3d 1105\n\n(4th Cir. 1997), where a law enforcement officer had consent to search a residence for a\n\nfugitive. Id. at 1107. While looking for the fugitive in the basement, the officer observed\n\nsome suspicious metal items on the floor. Id. He did not pause to examine those items at\n\nthat time, but he instead proceeded to finish his sweep for the fugitive. Id. Once\n\nfinished, he went back to take a closer look at the objects on the floor, this time\n\nrecognizing them as drug paraphernalia. Id. More officers arrived and took a look at the\n\nparaphernalia, eventually using the presence of those items to obtain a search warrant for\n\nthe house, which uncovered a gun and large quantities of drugs. Id. at 1108. That further\n\nsearch was held to have been constitutional under the plain-view doctrine. Id.\n\n There are too many factual distinctions between Jackson and this case to permit\n\nCravens’ second look under the plain view doctrine. First, as government counsel\n\n 26\n\fadmitted at oral argument, there is no evidence in the record that Cravens looked at the\n\nsame photos on November 27 that the officers viewed on November 20. Second, seven\n\ndays elapsed between the first and second searches in this case, not a matter of minutes.\n\nThird, Cravens’ “second look” led him to peruse more than just the child pornography\n\nimages, so we cannot say that the November 27 search did not cause a further invasion\n\nof Loera’s privacy. The plain view doctrine permits the warrantless seizure of\n\nevidence of criminal activity when police officers observe the evidence during a\n\nlawful search. United States v. Naugle, 997 F.2d 819, 822 (10th Cir. 1993). That\n\ndoctrine cannot be used to justify Cravens’ November 27 search.\n\n The government also argues that Cravens’ “second look” was justified under\n\nwhat it has termed the “foregone-conclusion exception” to the warrant requirement.\n\nThis doctrine comes from several of our plain view cases where we have permitted\n\nthe warrantless search of containers in plain view whose contents “are a foregone\n\nconclusion” because the container is “not closed,” “transparent,” or, if it is closed,\n\n“its ‘distinctive configuration . . . proclaims its contents’” nonetheless. United States\n\nv. Corral, 970 F.2d 719, 725 (10th Cir. 1992). We have also held that the doctrine\n\napplies “where the police have already seen the contents of a seized container prior to\n\nconducting the search, [because] there is no significant additional invasion of privacy\n\ninvolved in searching the container.” Id. at 725. We reject this argument for the\n\nsame reasons as the government’s plain view argument. Here, Cravens knew to a\n\nnear certainty that the seized and re-searched CDs contained some child pornography,\n\nbut he had no idea what else they contained. And, again, there is no evidence that\n\n 27\n\fCravens had previously seen the child pornography images that he viewed on\n\nNovember 27.\n\n Thus, Cravens’ November 27 search was unlawful because it exceeded the scope\n\nof the first warrant and none of the exceptions to the warrant requirement apply.\n\n D. Reasonableness of the Searches Conducted Under the Second Warrant\n\n Additionally, Loera argues that the child pornography evidence that Agent\n\nNishida discovered when he executed the second warrant should have been\n\nsuppressed because the second warrant was not supported by probable cause and no\n\nexceptions to the warrant requirement apply. We agree that the second warrant was\n\nnot supported by probable cause and that the good faith exception is inapplicable\n\nhere. However, the inevitable discovery doctrine supports the district court’s denial\n\nof Loera’s motion to suppress, and we affirm on that basis.\n\n 1. Second warrant was not supported by probable cause\n\n We review whether a magistrate properly issued a search warrant by determining\n\nwhether there was a “substantial basis” for probable cause in the affidavit submitted in\n\nsupport of the warrant. Illinois v. Gates, 462 U.S. 213, 236 (1983). Because we find\n\nthat the November 27 search was unlawful, we must excise from the affidavit that\n\nCravens filed in support of the second warrant all of the descriptions of child\n\npornography that he unlawfully obtained during the second search and then\n\ndetermine whether “there was probable cause absent that information.” United States\n\nv. Sims, 428 F.3d 945, 954 (10th Cir. 2005). The district court determined that the\n\n\n\n 28\n\fsecond warrant remained supported by probable cause without the tainted\n\ndescriptions. We disagree.\n\n While “probable cause does not demand the certainty we associate with formal\n\ntrials,” Gates, 462 U.S. at 246, “[s]ufficient information must be presented to the\n\nmagistrate to allow that official to determine probable cause; his action cannot be a mere\n\nratification of the bare conclusions of others,” id. at 239 (emphasis added). For example,\n\n“[a] sworn statement of an affiant that ‘he has cause to suspect and does believe that’\n\nliquor illegally brought into the United States is located on certain premises” is not\n\nsufficient to support a finding that probable cause exists to search the premises. Id.\n\n The child pornography descriptions that Agent Cravens obtained during the\n\nunlawful second search appear in paragraphs 24-27 of Cravens’ affidavit. Once we\n\nexcise those descriptions, all that remains substantively is Cravens statement that,\n\n“During the preview, the examiners identified four writable CDs which appeared to\n\ncontain images of child pornography.” ROA Vol. I at 120. This sentence does not\n\nsupport a finding of probable cause.\n\n In United States v. Pavulak, the Third Circuit reviewed an affidavit to support\n\na warrant to search for child pornography that contained language very similar to the\n\nbare-bones description left in the affidavit in our case, 700 F.3d 651, 661 (3d Cir.\n\n2012). The warrant affidavit in Pavulak stated that an informant had seen the\n\ndefendant “viewing child pornography” of females “between 16 and 18 years old,”\n\nwithout providing any further details about what the images depicted. Id. at 657.\n\nThe Third Circuit held that the affidavit lacked probable cause because it did not\n\n 29\n\fallow the magistrate judge “to independently evaluate whether the contents of the\n\nalleged images [met] the legal definition of child pornography.” Id. at 661. We find\n\nthat analysis persuasive here. Agent Cravens’ remaining statement that the CDs\n\n“appeared to contain images of child pornography” provides no detailed description\n\nof what the images depicted such that a magistrate could independently assess\n\nwhether the images meet the legal definition of child pornography. ROA Vol. I at\n\n120.\n\n Therefore, the affidavit supporting the second warrant lacked probable cause\n\nabsent the tainted information. We reverse the district court’s contrary conclusion.\n\n 2. Good-faith exception inapplicable to these facts\n\n Next, we consider whether the good faith exception to the exclusionary rule\n\nfrom United States v. Leon, 468 U.S. 897, 918 (1984), applies when police execute a\n\nsearch warrant that is based on information obtained through an unlawful predicate\n\nsearch. Disagreeing with the district court, we conclude that it does not. The\n\nSupreme Court’s opinion in Leon and our opinion in United States v. Scales, 903\n\nF.2d 765, 768 (10th Cir. 1990), dictate that the good faith exception does not apply in\n\na case like the one before us because the illegality at issue stems from unlawful\n\npolice conduct, rather than magistrate error, and therefore the deterrence purposes of\n\nthe Fourth Amendment are best served by applying the exclusionary rule.\n\n In United States v. Leon, the Supreme Court modified the exclusionary rule\n\n“so as not to bar the use in the prosecution’s case in chief of evidence obtained by\n\nofficers acting in reasonable reliance on a search warrant issued by a detached and\n\n 30\n\fneutral magistrate but ultimately found to be unsupported by probable cause,” 468\n\nU.S. at 900. The Court reasoned that the purpose of the exclusionary rule is to deter\n\npolice misconduct and in such a case “there is no police illegality and thus nothing to\n\ndeter.” Id. at 920. In this circuit, “Leon’s good faith exception applies only narrowly,\n\nand ordinarily only when an officer relies, in an objectively reasonable manner, on a\n\nmistake made by someone other than the officer.” United States v. Cos, 498 F.3d 1115,\n\n1132 (10th Cir. 2007) (declining to apply good faith exception to warrantless search of\n\napartment where officers mistakenly believed the person that consented to the search had\n\nthe authority to do so); United States v. Herrera, 444 F.3d 1238, 1251 (10th Cir. 2006)\n\n(declining to apply good faith exception to state trooper who conducted a warrantless\n\ninspection of a truck based on the officer’s mistaken belief the truck was a commercial\n\nvehicle subject to such inspection). Thus, Leon is inapplicable here where the\n\nmistake—the unconstitutional second search—was the fault of the officer, not the\n\nmagistrate.\n\n We considered whether Leon applied to a warrant affidavit based on tainted\n\nevidence in Scales, 903 F.2d at 768. There, we held that Leon did not apply to\n\nexcuse a law enforcement officer’s reliance on a search warrant where the facts in the\n\nwarrant affidavit were obtained through an unlawful predicate seizure. In that case,\n\nDEA agents seized a suitcase that they believed contained drugs. Id. at 767. Then,\n\nthey took the suitcase to a drug-sniffing canine team that signaled the suitcase did\n\ncontain drugs. Id. Finally, after having had the suitcase in their possession for\n\ntwenty-four hours, the agents applied for and obtained a warrant to search the\n\n 31\n\fsuitcase based on the probable cause provided by the canine alert. Id. Upon\n\nconducting the search, the agents discovered more than 2,000 grams of cocaine in the\n\nsuitcase. Id. The defendant moved to suppress the cocaine evidence, arguing that the\n\nagents’ initial seizure of the suitcase was unlawful because it was unsupported by\n\nprobable cause. Id. at 767.\n\n The district court in Scales denied the motion, finding that, even if the seizure\n\nof the suitcase was unlawful, the good faith exception ratified the agents’ behavior.\n\nId. We reversed, holding that Leon was inapplicable “[b]ecause the DEA agents\n\nwere not acting in reliance on a search warrant when they seized the luggage and held\n\nit for more than twenty-four hours.” Id. at 768. Our holding was informed by the\n\nreasoning in Leon that “Penalizing the officer for the magistrate’s error, rather than\n\nhis [or her] own, cannot logically contribute to the deterrence of Fourth Amendment\n\nviolations.” Id. at 768 (quoting Leon, 468 U.S. at 921) (alteration in original).\n\nBecause the contraposition is also true—that penalizing an officer for his or her own\n\nerror does contribute to deterrence—we determined that the exclusionary rule must\n\napply to the agents’ unlawful pre-warrant seizure of the suitcase. Id.\n\n Scales and Leon control our outcome here. Cravens conducted an unlawful\n\nsearch of Loera’s CDs on November 27 in the absence of a warrant. He included the\n\ntainted fruit that he uncovered during that search in the affidavit that he submitted in\n\nsupport of the second warrant. Cravens’ warrant affidavit was facially valid, and\n\ntherefore the magistrate did not error by issuing a warrant based upon it. Instead, the\n\nconstitutional error came from Agent Cravens.\n\n 32\n\f The government argues that Cravens acted in good faith because he\n\n“transparently informed the magistrate judge of the steps he had taken to obtain the\n\ndescriptions he included in his affidavit.” Aple. Br. at 40. Cravens’ affidavit\n\nprovided some information about the first search. It explained that, while executing\n\nthe first search warrant, the FBI agents identified four CDs that contained child\n\npornography and seized them. Then, Cravens wrote:\n\n On November 27, 2012, the writer, an FBI certified CART Technician,\n reviewed the four CDs, each of which are designated in attachment A,\n that were believed to contain child pornography. During the review of\n the CDs, the writer observed multiple pictures of children many of\n which are in various state of dress including the following images . . . .\n\nROA Vol. I at 50. However, that information was not sufficient to allow the\n\nmagistrate to determine the constitutionality of the second search such that the\n\nmagistrate can be said to have endorsed Cravens’ pre-warrant conduct. Furthermore,\n\neven if it was, that would not affect our outcome. Tenth Circuit precedent dictates\n\nthat the good faith exception does not apply at all when a warrant affidavit is based\n\non tainted evidence from a prior, unlawful search.\n\n Four other circuits have likewise concluded that Leon is inapplicable when an\n\nofficer executes in good faith a search warrant that is based on unlawfully-obtained\n\nevidence. United States v. Scott, 731 F.3d 659, 664 (7th Cir. 2013) (holding that\n\nevidence discovered pursuant to a warrant based on illegally-obtained evidence will\n\nbe inadmissible unless other, untainted information in the affidavit establishes\n\nprobable cause); United States v. Mowatt, 513 F.3d 395, 405 (4th Cir. 2008) (holding\n\nthat “Leon only prohibits penalizing officers for their good-faith reliance on\n\n 33\n\fmagistrates’ probable cause determinations” and that the exclusionary rule operates\n\nto penalize officers for any unconstitutional conduct preceding a magistrate’s\n\ninvolvement); United States v. McGough, 412 F.3d 1232 (11th Cir. 2005) (refusing\n\nto apply good faith exception where an unlawful entry into the defendant’s apartment\n\nled to the officer’s request for a search warrant); United States v. Vasey, 834 F.2d\n\n782, 789 (9th Cir. 1987) (holding that good faith exception did not apply to a warrant\n\nthat was based on information obtained in an illegal warrantless search because “[t]he\n\nconstitutional error was made by the officer . . ., not by the magistrate”). At least two\n\ncommentators support this analysis as well. See Wayne R. LaFave, Search &\n\nSeizure: A Treatise on the Fourth Amendment § 1.3(f) (5th ed. 2016) (explaining\n\nthat, because courts rarely require affiants to prove that they obtained the evidence\n\nlisted in an affidavit lawfully, “there is no reason why that process should, via Leon,\n\nshield that activity from full scrutiny at the suppression hearing”); Craig M.\n\nBradley, The “Good Faith Exception” Cases: Reasonable Exercise in Futility, 60 Ind.\n\nL.J. 287, 302 (1985) (quoting Leon, 468 U.S. at 914) (“When the magistrate issued\n\nthe warrant, he did not endorse past activity; he only authorized future activity. . . .\n\n[T]he function of the magistrate is to determine ‘whether a particular affidavit\n\nestablishes probable cause,’ not whether the methods used to obtain the information\n\nin that affidavit were legal.”).\n\n However, five other circuits have concluded that the good faith exception can\n\napply where an affidavit supporting a search warrant is tainted by illegally-obtained\n\nevidence in at least some limited circumstances. Three of those circuits apply the\n\n 34\n\fgood faith exception if the predicate search, although ultimately determined to be\n\nunlawful, was arguably lawful under the binding precedent in effect at the time of the\n\nsearch. United States v Bain, 874 F.3d 1, 22–23 (1st Cir. 2017) (applying good faith\n\nexception because binding precedent did not “clearly classify” as unlawful the\n\nconduct that invalidated the predicate search); United States v. Hopkins, 824 F.3d\n\n726 (8th Cir. 2016) (applying good faith exception because the reasonableness of the\n\nillegal predicate search was “close enough to the line of validity” to make an\n\nofficer’s belief in the validity of the warrant objectively reasonable); United States v.\n\nHolley, 831 F.3d 322, 326–27 (5th Cir. 2016) (also applying “close enough to the\n\nline of validity” test). Two other circuits apply the good faith exception in these\n\ntypes of cases when (1) the predicate search was arguably reasonable and (2) the\n\nwarrant affidavit truthfully conveyed the circumstances of the illegal predicate search\n\nto the magistrate judge. United States v. McClain, 444 F.3d 556, 566 (6th Cir. 2005)\n\n(applying Leon because the reasonableness of the predicate search was a close call\n\nand the warrant affidavit “fully disclosed” the circumstances surrounding the initial\n\nwarrantless search); United States v. Thomas, 757 F.2d 1359 (2d Cir. 1985) (applying\n\ngood faith exception because officer’s affidavit fully described the unlawful, pre-\n\nwarrant canine sniff that supplied probable cause for the warrant and there was\n\n“nothing more the officer could have or should have done” to be sure his search was\n\nlegal). We cannot read Leon or Scales to support the rules adopted by these courts.\n\nWhen a magistrate issues a warrant based on illegally obtained evidence, typically the\n\nmanner in which the affidavit evidence is obtained is not before the magistrate, and the\n\n 35\n\fmagistrate is not asked explicitly to endorse the evidence-gathering procedure. Even\n\nthough some disclosure of the evidence-gathering technique may have occurred, that is\n\nnot ordinarily the focus of an application for a warrant. Thus, we are unwilling to read a\n\nwarrant as ratifying the information-gathering process of a search that preceded it. In any\n\nevent, we are bound by Scales, which appears to us to have been correctly decided.\n\n Therefore, the district court erred by finding that the good faith doctrine applied to\n\nthe searches Agent Nishida conducted in execution of the second warrant.\n\n 3. Inevitable discovery doctrine supports denial of Loera’s motion\n\n Finally, we consider whether the government would have inevitably discovered\n\nthe child pornography evidence on Loera’s electronic devices. Loera argues that, because\n\nthere was no probable cause to support the second warrant, all evidence discovered as a\n\nresult of the execution of the second warrant should have been suppressed. The issue\n\nbefore us, then, is whether the FBI agents would have inevitably discovered the roughly\n\n330 child pornography images on Loera’s CDs and 730 child pornography images on\n\nLoera’s laptop that Nishida found when he executed the second warrant. We conclude\n\nthat they would have. Accordingly, we affirm the district court’s denial of Loera’s\n\nmotion to suppress.\n\n When evidence is obtained in violation of the Fourth Amendment, that\n\nevidence need not be suppressed if agents inevitably would have discovered it\n\nthrough lawful means independent from the unconstitutional search. United States v.\n\nChristy, 739 F.3d 534, 540 (10th Cir. 2014). The government is required to prove by a\n\npreponderance of the evidence that the unlawfully-obtained evidence would have been\n\n 36\n\fdiscovered through lawful means. Id. The “lawful means” need not be a second,\n\nindependent investigation. Id. Rather, the inevitable discovery doctrine will apply if\n\nthere was “one line of investigation that would have led inevitably to the obtaining of a\n\nsearch warrant by independent lawful means but was halted prematurely by a search\n\nsubsequently contended to be illegal.” Id. (citations omitted). The key to applying this\n\ndoctrine is to place the government officers in the “same positions they would have\n\nbeen in had the impermissible conduct not taken place,” and, from that vantage point,\n\nto ask whether the government would have inevitably discovered the evidence\n\nlawfully. Nix v. Williams, 467 U.S. 431, 447 (1984).\n\n Here, the district court’s supportable findings demonstrate by a preponderance of\n\nthe evidence that the FBI would have inevitably discovered the child pornography\n\nevidence on Loera’s electronic devices through lawful means independent from Agent\n\nCravens’ unlawful second search. On November 26 (the day before the second search),\n\nthe government lawfully had in its possession Loera’s computers, external hard drives,\n\niPhone, iPad, and thirteen CDs (nine without child pornography and four with child\n\npornography).4 The government had the authority under the first warrant to search\n\nLoera’s electronic devices—most importantly his laptop and CDs—for evidence of\n\ncomputer fraud. The district court issued an explicit factual finding that, had the\n\nsecond warrant never been obtained, Agent Nishida would “have searched [Loera’s\n\n\n\n4\n As mentioned above, although Loera challenges the first search of these four CDs,\nhe does not separately challenge their seizure were we to determine, as we have, that\nthe first search was constitutional.\n 37\n\flaptop] for evidence of electronic mail hijacking and computer fraud pursuant to the\n\n[f]irst [w]arrant.” Dist. Ct. Op. at 24. The district court further found that, as part of\n\nthat search, lawfully conducted pursuant to the parameters of the first warrant, Agent\n\nNishida would have searched the electronic folders where he discovered child\n\npornography when he executed the second warrant, including, the “My Documents”\n\nfolder, the “Bookmarks” tab of Loera’s internet browser, and a folder saved on the\n\nDesktop titled “Allmyfiles.txt.” Id. at 24–25. The district court also accepted\n\nNishida’s statement that, had he found child pornography images on the laptop\n\nduring a search conducted solely pursuant to the first warrant, he would have “alerted\n\nthe case agent so that [he] could get a search warrant for child pornography.” Id. at\n\n25.\n\n The laptop, including the specific files referenced above, contained over 730\n\nimages and 40 movies involving child pornography. Id. at 24. To take one specific\n\nexample, the “Allmyfiles.txt” file, which the district court found Nishida would have\n\nlawfully opened pursuant to the first warrant, contained files called “Spycam 9yr\n\nUndress.” Id. Such information would have been sufficient to establish probable\n\ncause to support a warrant to search all of the electronic devices belonging to Loera\n\nthat the government had in its possession, including the four CDs that Agent Cravens\n\nsearched unlawfully on November 27. That fact, combined with Agent Nishida’s\n\nindication that he would have sought a warrant, allows us to conclude that the\n\ninevitable discovery doctrine applies in this case such that the evidence discovered\n\npursuant to the second warrant did not need to be suppressed.\n\n 38\n\f III. CONCLUSION\n\n For the foregoing reasons, we AFFIRM the orders of the district court denying\n\nthe defendant’s motion to suppress and motion for reconsideration.\n\n\n\n\n 39\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America Plaintiff - Appellee, v. Jason LOERA, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-13\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 13, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n UNITED STATES OF AMERICA\\n\\n Plaintiff - Appellee,\\n\\n v. No. 17-2180\\n\\n JASON LOERA,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of New Mexico\\n (D.C. No. 1:13-CR-01876-JB-1)\\n _________________________________\\n\\nJerry A. Walz, Walz and Associates, P.C., Albuquerque, New Mexico for Defendant-\\nAppellant.\\n\\nKristopher N. Houghton, Assistant United States Attorney (John C. Anderson, United\\nStates Attorney, with him on the brief), Albuquerque, New Mexico for Plaintiff-\\nAppellee.\\n _________________________________\\n\\nBefore LUCERO, EBEL, and PHILLIPS, Circuit Judges.\\n _________________________________\\n\\nEBEL, Circuit Judge.\\n _________________________________\\n\\n This appeal requires us to apply Fourth Amendment principles to a situation\\n\\nwhere a police officer executing a warrant to search an electronic storage device for\\n\\nevidence of one crime discovers evidence of other criminal activity. Here, while\\n\\fexecuting a warrant to search Jason Loera’s home for evidence of computer fraud,\\n\\nFBI agents discovered child pornography on four of Loera’s CDs. Despite\\n\\ndiscovering the pornography, the agents continued their search for evidence of\\n\\ncomputer fraud—one agent continued to search the CDs that were found to contain\\n\\nsome child pornography and a second agent searched other electronic devices\\n\\nbelonging to Loera, not including those particular CDs (Search 1). After the agents\\n\\nfinished their on-site search, they seized a number of electronic devices that appeared\\n\\nto contain evidence of computer fraud, plus the four CDs that were found to contain\\n\\nchild pornography, and then brought the seized items back to their office. One week\\n\\nlater, one of the agents reopened the CDs that he knew contained some child\\n\\npornography so that he could describe a few pornographic images in an affidavit\\n\\nrequesting a (second) warrant to search all of the seized electronic devices for child\\n\\npornography (Search 2). A magistrate judge issued the warrant, and, upon executing\\n\\nit through two searches, the agents found more child pornography.\\n\\n In the subsequent prosecution against him for possessing child pornography,\\n\\nLoera filed a motion to suppress the evidence seized pursuant to each search, arguing\\n\\nthat the searches violated the Fourth Amendment. On denial of his motion, Loera\\n\\npled guilty to receipt of child pornography but preserved his right to appeal that\\n\\ndenial. Exercising jurisdiction under 28 U.S.C. § 1291, we affirm the denial of\\n\\nLoera’s motion to suppress. We hold, among other things, that the Fourth\\n\\nAmendment does not require police officers to stop executing an electronic search\\n\\nwarrant when they discover evidence of an ongoing crime outside the scope of the\\n\\n 2\\n\\fwarrant, so long as their search remains directed at uncovering evidence specified in\\n\\nthat warrant.\\n\\n I. BACKGROUND\\n\\n This case involves several police searches governed by the Fourth\\n\\nAmendment. The Fourth Amendment protects “the right of the people to be secure in\\n\\ntheir persons, houses, papers, and effects, against unreasonable searches and\\n\\nseizures.” U.S. Const. amend. IV. Generally, for a search to be reasonable, it must\\n\\nbe authorized by a warrant that “particularly” describes “the place to be searched, and\\n\\nthe persons or things to be seized.” U.S. Const. amend. IV. Once officers obtain a\\n\\nsufficiently particular warrant, they must execute it according to the warrant’s terms.\\n\\nHorton v. California, 496 U.S. 128, 140 (1990). The following undisputed facts\\n\\nexplain how the warrant-based searches in this case arose.\\n\\n In 2012, the FBI began investigating Jason Loera for illegally intercepting e-\\n\\nmails intended for then-sitting New Mexico Governor Susana Martinez and her staff\\n\\nin violation of 18 U.S.C. § 2511 (illegal interception) and 18 U.S.C. § 1030\\n\\n(computer fraud) [collectively, “computer fraud”]. As part of that investigation\\n\\n(more details of which can be found in the district court’s opinion United States v.\\n\\nLoera, 59 F. Supp. 3d 1089, 1095–1108 (D.N.M. 2014)), FBI agents applied for and\\n\\nreceived a warrant to search Loera’s residence for computer fraud, including any\\n\\nsuch evidence residing on electronic devices or storage media (“the first warrant”).\\n\\n The first warrant authorized FBI agents to search and seize, in relevant part,\\n\\n“All records, in any form, relating to violations of [computer fraud], involving Jason\\n\\n 3\\n\\fLoera.” ROA Vol. I at 37. The warrant defined the terms “records” and “information”\\n\\nas including: “all of the foregoing items of evidence in whatever forms and by whatever\\n\\nmeans they may have been created or stored, including any form of computer or\\n\\nelectronic storage (such as hard disks or other media that can store data).” Id. at 39. In a\\n\\nseparate provision, the warrant sought “Any computers, cell phones, and/or electronic\\n\\nmedia that could have been used as a means to commit the offenses described on the\\n\\nwarrant.” Id. at 87. Finally, for any electronic device, whether it was used to commit the\\n\\noffenses or simply had relevant records stored on it, the warrant permitted the agents to\\n\\nsearch and seize evidence of who used, owned, or controlled the device, such as\\n\\n“configuration files . . . documents, browsing history . . . photographs, and\\n\\ncorrespondence . . . .” Id. at 38.\\n\\n A. The First Search\\n\\n On November 20, 2012, FBI agents including Agent Aaron Cravens and\\n\\nSpecial Agent Brian Nishida executed the first search warrant. They discovered a\\n\\nlarge volume of electronic media in Loera’s residence, including CDs, DVDs, laptop\\n\\ncomputers, external hard drives, a USB flash drive, an iPhone, and an iPad. Cravens\\n\\nand Nishida were responsible for “previewing” the CDs at Loera’s residence to\\n\\nensure that the FBI seized only those CDs that contained information relevant to the\\n\\nauthorized investigation. ROA Vol. II at 53, 58. The two agents split up the CDs\\n\\nbetween themselves and searched them separately.\\n\\n Cravens tried to view the files of the first CD using a program called FTK\\n\\nImager, which would have allowed Cravens to limit his search to a particular type of\\n\\n 4\\n\\ffile, for example, only image, text, or audio files. However, the program did not\\n\\nwork. Consequently, Cravens opened the CD on a computer and used the “thumbnail\\n\\nview” to preview the files stored on it, meaning, he saw small images of the files, the\\n\\nfile names, and the file types in a vertical list that he had to scroll through to see in\\n\\nits entirety. Although Cravens believed he had authority under the first warrant to view\\n\\nthe entire contents of the CD, Cravens used the thumbnail-image view to fast-track his\\n\\nsearch. He would scroll past irrelevant files but “click[] on anything that didn’t appear\\n\\ncorrect, or any documents” to open them. Id. at 92. While Cravens was “scrolling\\n\\ndown through the images or files . . . on the CDs, [he] found what looked like a nude\\n\\nchild.” Id. at 60. He opened the file to confirm that it was an image of child\\n\\npornography. After determining that it was, Cravens ejected the CD from his\\n\\ncomputer, set it aside, and alerted Agent Nishida and the FBI agent in charge of\\n\\nLoera’s case. Then, Cravens searched the rest of the CDs assigned to him for\\n\\nevidence of computer fraud. Cravens later found a child pornography image on a\\n\\nsecond CD. Just as he did with the first, Cravens set the CD aside after discovering the\\n\\nillegal images and did not open any other files on that CD.\\n\\n Agent Nishida took a different approach to his search. He previewed the files\\n\\non his assigned CDs using the “details view” of Windows Explorer, meaning that he\\n\\nsaw a list of files, file names, and last-modified dates of those files, but not pictures\\n\\nassociated with the files. Id. at 157. For his search of the CDs, or “triage,” as he called\\n\\nit, Nishida would open two or three files on each CD and then determine from that\\n\\nsample whether the CD should be seized pursuant to the warrant. Id. at 160. If Nishida\\n\\n 5\\n\\ffound something he believed might be responsive to the warrant in the files that he\\n\\nsampled, he would set the CD aside to be reviewed off-site. As he was sampling files,\\n\\nNishida found child pornography on two CDs. Unlike Cravens, Nishida did not cease his\\n\\nsearch of those CDs after discovering child pornography; he continued sampling files on\\n\\nthe CDs to determine if they contained information that was responsive to the warrant.\\n\\n The FBI seized thirteen CDs in total from Loera’s residence: four contained child\\n\\npornography images and nine contained evidence of computer fraud.1 In addition to the\\n\\nthirteen CDs, the FBI seized computers, external hard drives, an iPhone, and an iPad.\\n\\n B. The Second Search\\n\\n One week later, on November 27, 2012, Cravens decided to apply for a search\\n\\nwarrant to search the items seized from Loera’s residence for child pornography.\\n\\nCravens wanted to include in his warrant affidavit a detailed description of one child\\n\\npornography image from each of the four CDs on which he and Nishida had found child\\n\\npornography during their on-site preview. Consequently, Cravens opened each of the\\n\\nfour CDs, viewing several images on each, to find child pornography images that he\\n\\ncould accurately describe. Viewing the photos and drafting the affidavit took a total of\\n\\ntwo-and-a-half hours. However, Cravens testified before the district court that he did not\\n\\nspend “anywhere near the two-and-a-half hours” actually looking at photos on the CDs.\\n\\nId. at 74-75.\\n\\n\\n\\n1\\n There is no indication in the record whether the four CDs that contained child\\npornography also contained evidence responsive to the warrant. However, Loera does\\nnot challenge the FBI’s seizure of those CDs pursuant to the first warrant.\\n 6\\n\\f Cravens’ affidavit included two sections. In Section I, Cravens described his\\n\\ntraining and experience with computers and child pornography. In Section II, Cravens\\n\\nexplained the details of the FBI’s investigation of Loera that led to the agent’s discovery\\n\\nof child pornography on the CDs in Loera’s residence. In particular, paragraph 21\\n\\ndescribed in general terms how Cravens discovered the child pornography:\\n\\n 21. In the process of executing this warrant, an FBI certified computer\\n forensic examiner and a computer analysis response team (CART)\\n technician previewed the loose media located during the search (e.g.,\\n thumb drives, CD-Rs, DVD-Rs, memory cards, etc.) for evidence\\n relevant to the original unrelated investigation. During the preview, the\\n examiners identified four writable CDs which appeared to contain\\n images of child pornography. The CDs were seized and placed in the\\n evidence control room at the local FBI office.\\n\\nROA Vol. I at 120. In paragraph 23, Cravens explained that on November 27, 2012,\\n\\nhe “reviewed the four CDs . . . that were believed to contain child pornography,” id.\\n\\nat 121, and that “[d]uring the review of the CDs, [he] observed multiple pictures of\\n\\nchildren many of which are in various states of dress,” id. Then, in paragraphs\\n\\n24-27, Cravens provided a detailed description of one image from each CD that\\n\\ndepicted a minor engaged in sexually explicit conduct. Cravens’ descriptions\\n\\nincluded the apparent age of the minor and the conduct depicted. On November 29,\\n\\n2012, based on Cravens’ affidavit, a federal magistrate judge approved a warrant to\\n\\nsearch the thirteen CDs and six other electronic devices that were seized from Loera’s\\n\\nresidence for child pornography (“the second warrant”).\\n\\n\\n\\n\\n 7\\n\\f C. Searches Pursuant to the Second Warrant\\n\\n Agent Nishida executed the second warrant on two separate dates. In December\\n\\n2012, Nishida searched Loera’s laptop pursuant to both the first and second warrants,\\n\\nlooking for evidence of computer fraud and child pornography. He discovered more than\\n\\n730 child pornography images on Loera’s laptop. In April 2013, Nishida searched the\\n\\nfour CDs seized from Loera’s residence for child pornography pursuant to the second\\n\\nwarrant. He discovered approximately 330 images and two movies of child pornography\\n\\non those CDs.\\n\\n D. Proceedings Below\\n\\n A federal grand jury indicted Loera on several counts of possessing child\\n\\npornography that implicated the images found on both his laptop and his CDs. Loera\\n\\nfiled a motion to suppress that child pornography evidence, and the district court\\n\\ndenied the motion. Loera filed a motion for reconsideration, which the district court\\n\\nalso denied. Following that denial, Loera pled guilty to one count of knowingly\\n\\nreceiving child pornography in violation of 18 U.S.C. §§ 2252(a)(2), 2252(b)(1), and\\n\\n2256, pursuant to a plea agreement, but he reserved the right to appeal the denial of\\n\\nhis motions.\\n\\n On appeal, Loera argues that the district court should have suppressed the\\n\\nchild pornography evidence discovered during the first search, the second search, and\\n\\nthe searches conducted pursuant to the second warrant because, according to Loera,\\n\\neach search was unlawful. Loera argues that the first search exceeded the scope of\\n\\nthe first warrant, the second search exceeded the scope of the first warrant, and the\\n\\n 8\\n\\flast two searches, while authorized by the second warrant, were unlawful because\\n\\nthat warrant was invalid. Additionally, Loera maintains that none of the exceptions\\n\\nto the warrant requirement apply to the searches in this case. We conclude that the\\n\\nfirst search was lawful, but we agree with Loera that the remaining searches were\\n\\nunlawful. Nevertheless, we AFFIRM the district court’s denial of Loera’s motion to\\n\\nsuppress and motion to reconsider under the inevitable discovery doctrine.\\n\\n II. DISCUSSION\\n\\n A. Standard of Review\\n\\n “When reviewing the district court’s denial of a motion to suppress, we view\\n\\nthe evidence in the light most favorable to the government and accept the district\\n\\ncourt’s factual findings unless they are clearly erroneous,” United States v. Grimmett,\\n\\n439 F.3d 1263, 1268 (10th Cir. 2006), but “[t]he ultimate question of reasonableness\\n\\nunder the Fourth Amendment is a legal conclusion that we review de novo.” Id.\\n\\nAccordingly, de novo review applies to the issues we address in this opinion,\\n\\nincluding, the scope of a search warrant, United States v. Angelos, 433 F.3d 738, 745\\n\\n(10th Cir. 2006), the sufficiency of a search warrant, United States v. Danhauer, 229\\n\\nF.3d 1002, 1005 (10th Cir. 2000), the applicability of the good-faith exception, id.,\\n\\nand the applicability of the inevitable discovery doctrine, United States v. Christy, 739\\n\\nF.3d 534, 540 (10th Cir. 2014).\\n\\n B. Validity of the Government’s Application for the First Warrant\\n\\n First, Loera argues that the FBI agents obtained the initial warrant to search\\n\\nhis residence for evidence of computer fraud as a pretext to search instead for\\n\\n 9\\n\\fevidence of child pornography. The district court disagreed, finding that the sole\\n\\npurpose of the first search was to uncover evidence of computer fraud. We affirm\\n\\nthat conclusion.\\n\\n Loera’s pretext argument is based on a statement that Agent Nishida made in a\\n\\nreport dated February 28, 2013, three months after the first and second searches were\\n\\nconducted. In that report, Nishida wrote:\\n\\n On November 14, 2012, SA Michael Boady requested that the above\\n listed specimen or specimens be examined for evidence of intercepting a\\n communication. For example, e-mail messages to or from the domain\\n Susanna2010.com. In addition, SA Boady requested that the evidence\\n also be examined for evidence of child pornography possession and\\n receipt.\\n\\nROA Vol. II at 191–92. Loera argues that this report proves that on November 14,\\n\\n2012, six days before the first search, Agent Nishida received instructions to search\\n\\nLoera’s home and effects for evidence of child pornography.\\n\\n The district court made explicit factual findings to the contrary, which are\\n\\nsupported by the record. First, the district court found that, had the FBI agents had\\n\\nsuspicions that Loera possessed child pornography, agents would have included that\\n\\ninformation in their application for the first warrant. Second, Agent Nishida testified\\n\\nat the suppression hearing that the February 2013 report summarized two separate\\n\\ninstructions from SA Boady: on November 14, 2012, Boady instructed Nishida to\\n\\nsearch for evidence of interception, and, later, Boady instructed Nishida to search for\\n\\nevidence of child pornography. Finally, both Cravens and Nishida testified at the\\n\\nsuppression hearing that the purpose of the November 20 search was only to uncover\\n\\n\\n 10\\n\\fevidence of computer fraud, and the district court credited that testimony. Each of\\n\\nthese facts supports the district court’s determination that the agents conducted the\\n\\nfirst search solely to look for evidence of computer fraud. And we are unpersuaded\\n\\nby Loera’s only evidence of pretext, the report written three months after the\\n\\nallegedly pretextual search.2\\n\\n Thus, we conclude the FBI agents had no pretextual motivations for obtaining\\n\\nthe first warrant, and we affirm the district on this issue.\\n\\n C. Reasonableness of the First and Second Searches\\n\\n Next, we determine that the first search of Loera’s residence was reasonable\\n\\nbecause it was directed solely at uncovering the items specified in the first warrant\\n\\nboth before and after the officers discovered the child pornography evidence.\\n\\nHowever, we conclude that the second search was unreasonable because it was\\n\\ndirected at uncovering evidence of child pornography.\\n\\n 1. Relevant legal principles\\n\\n The Fourth Amendment provides:\\n\\n The right of the people to be secure in their persons, houses, papers, and\\n effects, against unreasonable searches and seizures, shall not be\\n violated, and no Warrants shall issue, but upon probable cause,\\n supported by Oath or affirmation, and particularly describing the place\\n to be searched, and the persons or things to be seized.\\n\\n\\n\\n\\n2\\n Alternatively, even if the agents had an additional motive for conducting the first\\nsearch, that argument would fail as a matter of law under Whren v. United States,\\n517 U.S. 806, 813 (1996).\\n 11\\n\\fU.S. Const. amend. IV. It is now well-recognized that “the ultimate touchstone of\\n\\nthe Fourth Amendment is ‘reasonableness.’” Brigham City v. Stuart, 547 U.S. 398,\\n\\n403 (2006). “[R]easonableness generally requires the obtaining of a judicial\\n\\nwarrant,” Riley v. California, 134 S.Ct. 2473, 2482 (2014), subject to only a few\\n\\nexceptions. The warrant must “particularly” describe “the place to be searched, and\\n\\nthe persons or things to be seized,” U.S. Const. amend. IV.\\n\\n However, obtaining a sufficiently particular warrant is just the first step to\\n\\nconducting a reasonable search. The officers tasked with executing a sufficiently\\n\\nparticular warrant must conduct their search “strictly within the bounds set by the\\n\\nwarrant.” Bivens v. Six Unknown Named Agents of Fed. Bureau of Narcotics, 403\\n\\nU.S. 388, 395 n.7 (1971) (quoting Marron, 275 U.S. at 196). The Supreme Court has\\n\\nheld that, “[i]f the scope of [a] search exceeds that permitted by the terms of a validly\\n\\nissued warrant . . . the subsequent seizure [of evidence] is unconstitutional without\\n\\nmore.” Horton v. California, 496 U.S. 128, 140 (1990).\\n\\n Determining whether a search exceeds the scope of its authorizing warrant is,\\n\\nlike most inquiries under the Fourth Amendment, an exercise in reasonableness\\n\\nassessed on a case-by-case basis. Dalia v. United States, 441 U.S. 238, 258 (1979)\\n\\n(holding that the manner of a search is subject to “later judicial review as to its\\n\\nreasonableness”). The general Fourth Amendment rule is that investigators executing\\n\\na warrant can look anywhere where evidence described in the warrant might\\n\\nconceivably be located. United States v. Ross, 456 U.S. 798, 824 (1982). For\\n\\nexample:\\n\\n 12\\n\\f Just as probable cause to believe that a stolen lawnmower may be found in\\n a garage will not support a warrant to search an upstairs bedroom, probable\\n cause to believe that undocumented aliens are being transported in a van\\n will not justify a warrantless search of a suitcase. Probable cause to believe\\n that a container placed in the trunk of a taxi contains contraband or\\n evidence does not justify a search of the entire cab.\\n\\nId. This limitation works well in the physical-search context to ensure that searches\\n\\npursuant to warrants remain narrowly tailored, but it is less effective in the electronic-\\n\\nsearch context where searches confront what one commentator has called the “needle-in-\\n\\na-haystack” problem. Orin S. Kerr, Digital Evidence and the New Criminal\\n\\nProcedure, 105 Colum. L. Rev. 279, 301 (2005). Given the enormous amount of data\\n\\nthat computers can store and the infinite places within a computer that electronic\\n\\nevidence might conceivably be located, the traditional rule risks allowing unlimited\\n\\nelectronic searches.\\n\\n To deal with this problem, rather than focusing our analysis of the\\n\\nreasonableness of an electronic search on “what” a particular warrant permitted the\\n\\ngovernment agents to search (i.e., “a computer” or “a hard drive”), we have focused\\n\\non “how” the agents carried out the search, that is, the reasonableness of the search\\n\\nmethod the government employed. See United States v. Burgess, 576 F.3d 1078\\n\\n(10th Cir. 2009); United States v. Walser, 275 F.3d 981 (10th Cir. 2001); United\\n\\nStates v. Carey, 172 F.3d 1268 (10th Cir. 1999). Our electronic search precedents\\n\\ndemonstrate a shift away from considering what digital location was searched and\\n\\ntoward considering whether the forensic steps of the search process were reasonably\\n\\ndirected at uncovering the evidence specified in the search warrant. Shifting our\\n\\n\\n 13\\n\\ffocus in this way is necessary in the electronic search context because search\\n\\nwarrants typically contain few—if any—restrictions on where within a computer or\\n\\nother electronic storage device the government is permitted to search. See United\\n\\nStates v. Christie, 717 F.3d 1156, 1165 (10th Cir. 2013) (holding that, so long as an\\n\\nelectronic search warrant requires the government to “direct all of its search efforts”\\n\\ntoward evidence relating to a specific crime, the warrant is sufficiently particular,\\n\\neven where it permits the government to search a “computer” for “all records”\\n\\nrelating to the crimes of “murder, neglect, and abuse”). Because it is “unrealistic to\\n\\nexpect a warrant prospectively [to] restrict the scope of a search by directory,\\n\\nfilename or extension or to attempt to structure search methods,” Burgess, 576 F.3d\\n\\nat 1093 (alteration added), our ex post assessment of the propriety of a government\\n\\nsearch is essential to ensuring that the Fourth Amendment’s protections are realized\\n\\nin this context. Our precedent of Carey, Burgess, and Walser, to which we turn next,\\n\\nare instructive as to what constitutes a reasonable electronic search pursuant to a\\n\\nvalid warrant.\\n\\n Carey is the only case in which we invalidated an electronic search for\\n\\nexceeding the scope of its authorizing warrant. See 172 F.3d at 1276. There, a\\n\\npolice officer obtained a warrant to search files on the defendant’s computer for\\n\\nevidence “pertaining to the sale and distribution of controlled substances.” Id. at\\n\\n1270. Prior to searching the computer, the officer first viewed the computer’s file\\n\\ndirectory, which showed numerous “JPG” files with sexually suggestive titles. Id.\\n\\nDuring his search, the officer came across a number of files that he did not recognize\\n\\n 14\\n\\fand that he was unable to view on the computer that he was using. Id. at 1271. To\\n\\nview the files, the officer downloaded them onto a separate disk, inserted that disk\\n\\ninto another computer, and then was immediately able to view a “JPG file” that\\n\\ndepicted child pornography. Id. Rather than navigating away from the\\n\\nnonresponsive material, the officer “downloaded approximately two hundred forty-\\n\\nfour” more JPG files and then transferred them to nineteen disks, viewing five to\\n\\nseven images on each disk to determine that they all contained child pornography.\\n\\nId. The whole process took about five hours. Id. at 1273. After he had catalogued\\n\\nthe child pornography images in this manner, he then “returned” to his “original task\\n\\nof looking for evidence of drug transactions.” Id. at 1271.\\n\\n The Carey court held that this was an unlawful, general exploratory search\\n\\nbecause, although it was permissible for the officer to open the first JPG file to see if\\n\\nit was responsive to the warrant, id. at 1273 n.4, his opening of the remaining files\\n\\nexceeded the bounds of the authorizing warrant, id. at 1276. The Carey court’s\\n\\nholding turned on four facts: (1) the officer spent five hours, a significant amount of\\n\\ntime, specifically perusing the trove of nonresponsive material, id. at 1273; (2) the\\n\\nnonresponsive files were characteristically distinct and set apart from the other files\\n\\non the computer (such that they could have been avoided) because each file was\\n\\nlabeled “JPG,” many had sexually suggestive titles, and the officer had to download\\n\\nthem to open them, id. at 1274; (3) the officer did not discover the files inadvertently\\n\\n(at least after his first look), id. at 1273; and (4) a more narrowly tailored search was\\n\\npossible—the officer could have gone back to searching for drug-related documents\\n\\n 15\\n\\fmuch sooner than he did, id. at 1273. Importantly, we did not condemn the officer’s\\n\\ndecision to return to searching for drug-related documents after discovering the child\\n\\npornography, but, instead, we condemned his “temporar[y] abandon[ment]” of the\\n\\noriginal search to conduct a “five hour search of the child pornography files.” Id. at\\n\\n1273.\\n\\n Next, we turn to Walser and Burgess, both of which upheld electronic searches\\n\\nin which the investigator discovered incriminating, nonresponsive material while\\n\\nexecuting a search warrant but then navigated away from it. In United States v.\\n\\nWalser, the police obtained a warrant to search the defendant’s hotel room for\\n\\nelectronically stored records of “evidence of the possession of controlled\\n\\nsubstances.” 275 F.3d 981, 983–84 (10th Cir. 2001). A police officer searched the\\n\\nroom pursuant to the warrant and found a laptop and a digital camera. Id. at 984.\\n\\nThe agent seized the laptop, removed it from the hotel room, and then conducted a\\n\\ndrug-specific search of the laptop, looking for “ledgers of drug transactions or images\\n\\nof drug use.” Id. In order to find those things, the agent employed a particularized\\n\\nsearch method that “selectively proceeded to the ‘Microsoft Works’ sub-folder on the\\n\\npremise that[,] because Works is a spreadsheet program, that folder would be most\\n\\nlikely to contain records relating to the business of drug trafficking.” Id. at 986. It\\n\\nwas while searching the contents of the Works folder that the officer came across a\\n\\nfile labeled “bstfit.avi” and opened it. Id. at 984. When he viewed the contents, he\\n\\ndiscovered that the file contained child pornography images. Id. at 986–87. He then\\n\\nimmediately ceased his search. Id.\\n\\n 16\\n\\f We upheld the officer’s search as reasonable because we determined that, by\\n\\nusing a particularized search method, the officer avoided conducting the kind of\\n\\n“sweeping, comprehensive search of a computer’s hard drive” that Carey prohibited.\\n\\nId. at 986. The defendant in Walser argued that the agent exceeded the scope of the\\n\\nwarrant by opening the “AVI file,” a video file, because “it could not possibly have\\n\\ncontained the type of evidence the [a]gent was authorized to search for, namely,\\n\\nrecords of drug transactions or still images of drug use.” Id. at 987. We rejected that\\n\\nargument by interpreting Carey to excuse an officer’s discovery of child pornography\\n\\nduring a search for “relevant records in places where such records might logically be\\n\\nfound” so long as the officer does not conduct a supervening search specifically\\n\\ndirected at finding pornography evidence. Id. at 986. Applying that rule, we held in\\n\\nWalser that the officer’s opening the “bstfit.avi” file was permissible because (1) he\\n\\nwas looking in a folder that was “most likely to contain records relating to the\\n\\nbusiness of drug trafficking” when he opened it, and (2) he did not conduct an\\n\\nintervening search directly focused on child pornography like the agent in Carey. Id.\\n\\nBased on those facts, we concluded that the “search was reasonable and within the\\n\\nparameters of the search warrant” and that the evidence found as a result of it did not\\n\\nneed to be suppressed. Id. at 987.\\n\\n Finally, in United States v. Burgess, 576 F.3d 1078 (10th Cir. 2009), we again\\n\\nupheld an electronic search that uncovered evidence of child pornography as\\n\\nreasonable and within the scope of its authorizing warrant. There, police obtained a\\n\\nwarrant to search a motorhome for, among other things, “computer records” that\\n\\n 17\\n\\fwould tend to show “conspiracy to sell drugs.” Id. at 1083. The warrant\\n\\nincorporated the affidavit on which it was based, which stated that the affiant “knows\\n\\nthat persons involved in trafficking or the use of narcotics often keep photographs of\\n\\ncoconspirators or photographs of illegal narcotics in their vehicle.” Id.\\n\\n Based on the warrant, officers searched two hard drives and a laptop found in\\n\\nthe motorhome. Id. An agent searched one of the hard drives by using a program\\n\\ncalled EnCase, which copies the contents of a hard drive over to a computer to\\n\\nprevent file corruption. Id. at 1083–84. EnCase allows an investigator to “preview”\\n\\nreduced-sized photos of each image file as they are being copied. Id. at 1084, 1094.\\n\\nThe agent took advantage of this feature and viewed each image file on the hard drive\\n\\nas it was being copied. Id. at 1084. After viewing 200-300 digital images, mostly\\n\\npersonal photos, the agent saw an image that looked like child sexual exploitation.\\n\\nId. He then closed the preview program and sought a warrant to search all of the\\n\\ndefendant’s electronic storage devices for evidence of child pornography. Id. Upon\\n\\nconducting that search, the agent found more than one hundred thousand illegal\\n\\nimages. Id.\\n\\n The defendant asked the district court to suppress the child pornography\\n\\nevidence because, he argued, the agent’s use of the “preview” program exceeded the\\n\\nscope of the warrant because he did not employ a particularized search method like\\n\\nthe agent in Walser but instead looked through each image file contained on the hard\\n\\ndrive. We determined that the agent’s use of the “preview” program was reasonable\\n\\nand did not exceed the scope of the warrant for two reasons. First, we noted that,\\n\\n 18\\n\\fbecause the warrant did not expressly limit the file types that the agent was allowed\\n\\nto search, for example, by limiting the search to text files (.doc, .wpd, .txt, etc.), the\\n\\nagent was well within the scope of the warrant when he decided to view all of the\\n\\nimage files on the hard drive using the preview program. Id. at 1092. Second, we\\n\\ndetermined that there was no reasonable way for the agent to conduct a more\\n\\nnarrowly tailored search because, when the object of a search is likely to be an image\\n\\nfile, as it was in Burgess, “there may be no practical substitute for actually looking in\\n\\nmany (perhaps all) folders and sometimes at the documents contained within those\\n\\nfolders.” Id. at 1094.\\n\\n Reading these cases together, we determine that four features of the\\n\\nunconstitutional search in Carey demonstrate that it was unreasonably directed at\\n\\nuncovering evidence of child pornography, rather than directed at the evidence\\n\\nspecified in the warrant, and distinguish it from the reasonable searches in Walser\\n\\nand Burgess: (1) the length of time the searching officer spent looking at the\\n\\nincriminating, nonresponsive evidence (five hours in Carey versus less than one\\n\\nminute in Walser and Burgess); (2) the fact that the nonresponsive files were set apart\\n\\nfrom the responsive files saved on the storage device (JPG files downloaded onto\\n\\nseparate disks in Carey versus generic files intermingled all in one place in Burgess);\\n\\n(3) the manner in which the evidence was discovered (purposefully in Carey versus\\n\\ninadvertently in Walser and Burgess);3 and (4) the breadth of the search method\\n\\n\\n3\\n We acknowledge that in Horton v. California, 496 U.S. 128, 130 (1990), the\\nSupreme Court held that, in physical searches, “even though inadvertence is a\\n 19\\n\\femployed (the wide detour in Carey versus the narrowly tailored search in Walser).\\n\\nContrary to Loera’s assertion, these cases do not require that officers stop searching\\n\\nupon discovering evidence of a crime outside the scope of the warrant. Such a rule\\n\\nwould prohibit what the Fourth Amendment expressly permits—reasonable searches\\n\\nbased upon a warrant supported by probable cause. We have never required that.\\n\\n This conclusion brings us in line with every circuit that has confronted this\\n\\nissue. See United States v. Stabile, 633 F.3d 219, 240 (3d Cir. 2011) (upholding\\n\\ndenial of motion to suppress where officers continued warrant-authorized search of\\n\\nthe defendant’s computer for financial crimes after discovering child pornography);\\n\\nUnited States v. Williams, 592 F.3d 511, 521–24 (4th Cir. 2010) (upholding search\\n\\nwhere the officer continued his warrant-authorized search of the defendant’s\\n\\ncomputer for evidence of “making threats and computer harassment” after\\n\\ndiscovering child pornography); United States v. Miranda, 325 F.App’x 858, 859–60\\n\\n(11th Cir. 2009) (per curiam) (unpublished) (upholding search where officer\\n\\ncontinued his warrant-authorized search for evidence of counterfeit software after\\n\\ndiscovering child pornography); United States v. Wong, 334 F.3d 831, 834 (9th Cir.\\n\\n\\ncharacteristic of most legitimate ‘plain view’ seizures, it is not a necessary\\ncondition.” However, because Carey, Walser, and Burgess, each of which succeeded\\nHorton in time, considered the subjective intentions of the searching officers where\\nthat information was available, we continue to include inadvertence as a factor to\\nconsider when deciding whether an electronic search fell within the scope of its\\nauthorizing warrant or outside of it. The fundamental differences between electronic\\nsearches and physical searches, including the fact that electronic search warrants are\\nless likely prospectively to restrict the scope of the search, justify our inclusion of\\nthat factor. See Horton, 496 U.S. at 139 (abandoning inadvertence as a necessary\\ncondition for a legitimate plain view seizure).\\n 20\\n\\f2003) (upholding denial of motion to suppress where the officer continued his\\n\\nwarrant-authorized search of the defendant’s computer for, among other things,\\n\\n“[a]ny maps, receipts, or writings, depicting Churchill County Nevada” after\\n\\ndiscovering child pornography).\\n\\n Although officers do not have to stop executing a search warrant when they\\n\\nrun across evidence outside the warrant’s scope, they must nevertheless reasonably\\n\\ndirect their search toward evidence specified in the warrant. What that looks like\\n\\ndepends on the particular facts of a given case. Narrowly tailored search methods\\n\\nthat begin looking “in the most obvious places and [then] progressively move from the\\n\\nobvious to the obscure,” Burgess, 576 F.3d at 1094, should be used where possible but\\n\\nare not necessary in every case. In cases like this one, where the electronic storage\\n\\ndevice is not well-organized and the most practical way to search it is through an item-\\n\\nby-item review, “there may be no practical substitute for actually looking in many\\n\\n(perhaps all) folders and sometimes at the documents contained within those folders.”\\n\\nId. In such a case, however, the searching officer must respond appropriately to what\\n\\nhe or she sees. The reasonableness of a search evolves as the search progresses and\\n\\nas the searching officer learns more about the files on the device that he or she is\\n\\nsearching.\\n\\n An analogy to the physical realm is helpful here. Imagine a warrant authorizes\\n\\npolice officers to search a “residence” for evidence of “firearms and ammunition.”\\n\\nUnder that warrant, it would be reasonable for a police officer to search the medicine\\n\\ncabinet in the bathroom for a minute or two to see if a small gun or ammunition is\\n\\n 21\\n\\fhidden there, however, it would be unreasonable for the officer to spend two hours\\n\\nreading the labels on each bottle of medicine in the cabinet. On the other hand, if the\\n\\nwarrant had authorized the officer to search the residence for evidence of “illegal\\n\\ndrug trafficking and manufacture,” an intensive search of the medicine cabinet would\\n\\nbe reasonable. In both cases, the medicine cabinet is fair game to search, but the\\n\\nintensity level of the permitted search differs depending on the evidence to be seized.\\n\\nThe same is true for electronic searches. While in some cases many (perhaps all)\\n\\nelectronic areas of a computer will be fair game to search, the level of intensity that\\n\\nofficers are permitted to spend searching those areas will differ depending on\\n\\nwhether the area appears to contain responsive material. This is true even when\\n\\nofficers come across evidence of incriminating, nonresponsive material. In all cases,\\n\\nthe ultimate test is the one mandated by the Fourth Amendment: whether the search\\n\\nwas “reasonable” under the circumstances. In the case of a computer search,\\n\\n“reasonableness” requires officers to take into account the flexibility of computers\\n\\nand the multiple configurations to which they may be adapted. As the computer\\n\\nsearch continues and as the executing officer obtains more information about how a\\n\\nsuspect used his computer, that too may inform the reasonableness of the continuing\\n\\nsearch.\\n\\n We now apply these principles to the November 20 and 27 searches conducted\\n\\nin this case.\\n\\n\\n\\n\\n 22\\n\\f 2. November 20 search was reasonable\\n\\n Loera argues that, although the first warrant permitted the FBI agents to search his\\n\\nCDs for evidence of computer fraud, the officers’ search exceeded the scope of the first\\n\\nwarrant when they continued searching after discovering evidence of child pornography.\\n\\nWe disagree. The searches that Agent Cravens and Agent Nishida each conducted of\\n\\nLoera’s CDs on November 20 were reasonable and conducted within the scope of the\\n\\nfirst warrant because at all times each was reasonably directed at discovering evidence of\\n\\ncomputer fraud. Therefore, the first search did not violate the Fourth Amendment and\\n\\nthus did not warrant suppression of the evidence discovered during that search.\\n\\n The agents’ searches on November 20 resemble the searches in Walser and\\n\\nBurgess more than they resemble the search in Carey, both before and after they\\n\\ndiscovered the child pornography evidence. First, both agents here spent very little\\n\\ntime looking at the child pornography images they discovered. They noticed them,\\n\\nalerted a supervisor, and then moved on to the rest of the images on the same CD (in\\n\\nNishida’s case), or the other CDs (in Cravens’ case), looking for evidence of\\n\\ncomputer fraud. Both responses were reasonable because, as mentioned above, the\\n\\nagents were not required to stop searching altogether. And both responses\\n\\ndemonstrate an effort to navigate away from the nonresponsive material and toward\\n\\nfiles that they believed were more likely to contain material responsive to the\\n\\nwarrant. Second, the files on the CDs that the agents previewed were not\\n\\ncharacteristically distinct or set apart from the other files, in contrast to Carey. Agent\\n\\nCravens testified that, when he put a CD into his computer to see the files that it\\n\\n 23\\n\\fcontained, the computer pulled up a generic list of those files. The record does not\\n\\nindicate that there were any folders or distinctive titles setting clearly apart the\\n\\nnonresponsive child pornography files from the other files on the disk. Loera bears\\n\\nthe burden of proof on his suppression motion, and he has offered no evidence on this\\n\\npoint. Third, the agents discovered the child pornography files inadvertently on\\n\\nNovember 20. Fourth, both agents’ search methods were reasonably narrow under\\n\\nthe circumstances, considering the fact that the CDs did not seem particularly\\n\\norganized. Given that the warrant permitted the agents to search the CDs for\\n\\n“photographs,” “documents,” and “configuration files,” it was reasonable for Nishida and\\n\\nCravens to search all file types on the CDs (image, video, and text) for evidence of\\n\\ncomputer fraud rather than to narrow that search to one particular file type. The agents’\\n\\nsearches on November 20 were reasonable because they fell within the scope of the\\n\\nfirst warrant both before and after they discovered the child pornography evidence. We\\n\\nreverse the district court’s ruling to the contrary.\\n\\n 3. November 27 search was unreasonable\\n\\n Loera also argues that Agent Cravens’ subsequent search on November 27,\\n\\n2012, of the four seized CDs that contained child pornography violated the Fourth\\n\\nAmendment because Cravens was “[i]ntentionally searching for evidence of a crime\\n\\noutside the scope of the [f]irst [w]arrant prior to obtaining a new warrant.” Aplt. Br. 29.\\n\\nIn making this argument, Loera accepts that the first warrant permitted the government to\\n\\nseize the four CDs that were found to contain some child pornography and to search them\\n\\nfor evidence of computer fraud. Therefore, Loera challenges Cravens’ November 27\\n\\n 24\\n\\fsearch only for exceeding that permission. Accordingly, we confine our analysis to\\n\\nwhether the second search exceeded the scope of the first warrant. The district court\\n\\nconcluded that it did and that neither exigent circumstances nor any other exception to\\n\\nthe warrant requirement justified that search. We agree and conclude that the district\\n\\ncourt correctly excised the evidence obtained during the November 27th search from\\n\\nCravens’ affidavit for the second warrant. Several of the district court’s factual findings\\n\\nsupport that result.\\n\\n The district court found that “Cravens was not searching for evidence of\\n\\nelectronic fraud” on November 27 but instead was searching for child pornography.\\n\\nDist. Ct. Op. at 144. The district court based this finding on Cravens’ testimony at the\\n\\nsuppression hearing that he reopened Loera’s CDs on November 27 specifically “[t]o\\n\\nwrite a description of an image on the disc” so that he could “obtain a second warrant\\n\\nfor child pornography.” ROA Vol. II at 72. That admission is the most probative\\n\\nfact in the record that Cravens’ search was directed at finding child pornography.\\n\\nThe district court also found that Cravens had the four CDs for a total of two-and-a-\\n\\nhalf hours that day, during which time he searched the CDs and drafted the second\\n\\naffidavit. Although the record does not indicate how long Cravens searched the CDs,\\n\\nhe testified at the suppression hearing that he looked at several images on each CD—\\n\\n“more than just a couple” but “[m]ost likely less than a dozen.” ROA Vol. II at 143.\\n\\nWhatever the amount of time, Cravens’ devoted it exclusively to nonresponsive\\n\\nmaterial. Rather than navigate away from the child pornography images when he found\\n\\nthem, Cravens explicitly navigated toward such images. Based on these findings, we\\n\\n 25\\n\\fagree with the district court that, in contrast with the agents’ searches on November\\n\\n20, Agent Cravens’ search on November 27 was unreasonable because it was directed\\n\\nat uncovering evidence of child pornography.\\n\\n The government argues that two exceptions save Cravens’ search from\\n\\nviolating the Fourth Amendment: the plain view doctrine and the foregone-\\n\\nconclusion exception. We disagree. For its plain view argument, the government\\n\\nasserts that the law permitted Agent Cravens to take a “second look” at the child\\n\\npornography images on Loera’s CDs because members of the FBI had already seen\\n\\nthe images in plain view during a lawful search, and, therefore, his “second look”\\n\\nwas no further invasion of Loera’s privacy than the initial, lawful viewing. The\\n\\ngovernment points to a Fourth Circuit case, United States v. Jackson, 131 F.3d 1105\\n\\n(4th Cir. 1997), where a law enforcement officer had consent to search a residence for a\\n\\nfugitive. Id. at 1107. While looking for the fugitive in the basement, the officer observed\\n\\nsome suspicious metal items on the floor. Id. He did not pause to examine those items at\\n\\nthat time, but he instead proceeded to finish his sweep for the fugitive. Id. Once\\n\\nfinished, he went back to take a closer look at the objects on the floor, this time\\n\\nrecognizing them as drug paraphernalia. Id. More officers arrived and took a look at the\\n\\nparaphernalia, eventually using the presence of those items to obtain a search warrant for\\n\\nthe house, which uncovered a gun and large quantities of drugs. Id. at 1108. That further\\n\\nsearch was held to have been constitutional under the plain-view doctrine. Id.\\n\\n There are too many factual distinctions between Jackson and this case to permit\\n\\nCravens’ second look under the plain view doctrine. First, as government counsel\\n\\n 26\\n\\fadmitted at oral argument, there is no evidence in the record that Cravens looked at the\\n\\nsame photos on November 27 that the officers viewed on November 20. Second, seven\\n\\ndays elapsed between the first and second searches in this case, not a matter of minutes.\\n\\nThird, Cravens’ “second look” led him to peruse more than just the child pornography\\n\\nimages, so we cannot say that the November 27 search did not cause a further invasion\\n\\nof Loera’s privacy. The plain view doctrine permits the warrantless seizure of\\n\\nevidence of criminal activity when police officers observe the evidence during a\\n\\nlawful search. United States v. Naugle, 997 F.2d 819, 822 (10th Cir. 1993). That\\n\\ndoctrine cannot be used to justify Cravens’ November 27 search.\\n\\n The government also argues that Cravens’ “second look” was justified under\\n\\nwhat it has termed the “foregone-conclusion exception” to the warrant requirement.\\n\\nThis doctrine comes from several of our plain view cases where we have permitted\\n\\nthe warrantless search of containers in plain view whose contents “are a foregone\\n\\nconclusion” because the container is “not closed,” “transparent,” or, if it is closed,\\n\\n“its ‘distinctive configuration . . . proclaims its contents’” nonetheless. United States\\n\\nv. Corral, 970 F.2d 719, 725 (10th Cir. 1992). We have also held that the doctrine\\n\\napplies “where the police have already seen the contents of a seized container prior to\\n\\nconducting the search, [because] there is no significant additional invasion of privacy\\n\\ninvolved in searching the container.” Id. at 725. We reject this argument for the\\n\\nsame reasons as the government’s plain view argument. Here, Cravens knew to a\\n\\nnear certainty that the seized and re-searched CDs contained some child pornography,\\n\\nbut he had no idea what else they contained. And, again, there is no evidence that\\n\\n 27\\n\\fCravens had previously seen the child pornography images that he viewed on\\n\\nNovember 27.\\n\\n Thus, Cravens’ November 27 search was unlawful because it exceeded the scope\\n\\nof the first warrant and none of the exceptions to the warrant requirement apply.\\n\\n D. Reasonableness of the Searches Conducted Under the Second Warrant\\n\\n Additionally, Loera argues that the child pornography evidence that Agent\\n\\nNishida discovered when he executed the second warrant should have been\\n\\nsuppressed because the second warrant was not supported by probable cause and no\\n\\nexceptions to the warrant requirement apply. We agree that the second warrant was\\n\\nnot supported by probable cause and that the good faith exception is inapplicable\\n\\nhere. However, the inevitable discovery doctrine supports the district court’s denial\\n\\nof Loera’s motion to suppress, and we affirm on that basis.\\n\\n 1. Second warrant was not supported by probable cause\\n\\n We review whether a magistrate properly issued a search warrant by determining\\n\\nwhether there was a “substantial basis” for probable cause in the affidavit submitted in\\n\\nsupport of the warrant. Illinois v. Gates, 462 U.S. 213, 236 (1983). Because we find\\n\\nthat the November 27 search was unlawful, we must excise from the affidavit that\\n\\nCravens filed in support of the second warrant all of the descriptions of child\\n\\npornography that he unlawfully obtained during the second search and then\\n\\ndetermine whether “there was probable cause absent that information.” United States\\n\\nv. Sims, 428 F.3d 945, 954 (10th Cir. 2005). The district court determined that the\\n\\n\\n\\n 28\\n\\fsecond warrant remained supported by probable cause without the tainted\\n\\ndescriptions. We disagree.\\n\\n While “probable cause does not demand the certainty we associate with formal\\n\\ntrials,” Gates, 462 U.S. at 246, “[s]ufficient information must be presented to the\\n\\nmagistrate to allow that official to determine probable cause; his action cannot be a mere\\n\\nratification of the bare conclusions of others,” id. at 239 (emphasis added). For example,\\n\\n“[a] sworn statement of an affiant that ‘he has cause to suspect and does believe that’\\n\\nliquor illegally brought into the United States is located on certain premises” is not\\n\\nsufficient to support a finding that probable cause exists to search the premises. Id.\\n\\n The child pornography descriptions that Agent Cravens obtained during the\\n\\nunlawful second search appear in paragraphs 24-27 of Cravens’ affidavit. Once we\\n\\nexcise those descriptions, all that remains substantively is Cravens statement that,\\n\\n“During the preview, the examiners identified four writable CDs which appeared to\\n\\ncontain images of child pornography.” ROA Vol. I at 120. This sentence does not\\n\\nsupport a finding of probable cause.\\n\\n In United States v. Pavulak, the Third Circuit reviewed an affidavit to support\\n\\na warrant to search for child pornography that contained language very similar to the\\n\\nbare-bones description left in the affidavit in our case, 700 F.3d 651, 661 (3d Cir.\\n\\n2012). The warrant affidavit in Pavulak stated that an informant had seen the\\n\\ndefendant “viewing child pornography” of females “between 16 and 18 years old,”\\n\\nwithout providing any further details about what the images depicted. Id. at 657.\\n\\nThe Third Circuit held that the affidavit lacked probable cause because it did not\\n\\n 29\\n\\fallow the magistrate judge “to independently evaluate whether the contents of the\\n\\nalleged images [met] the legal definition of child pornography.” Id. at 661. We find\\n\\nthat analysis persuasive here. Agent Cravens’ remaining statement that the CDs\\n\\n“appeared to contain images of child pornography” provides no detailed description\\n\\nof what the images depicted such that a magistrate could independently assess\\n\\nwhether the images meet the legal definition of child pornography. ROA Vol. I at\\n\\n120.\\n\\n Therefore, the affidavit supporting the second warrant lacked probable cause\\n\\nabsent the tainted information. We reverse the district court’s contrary conclusion.\\n\\n 2. Good-faith exception inapplicable to these facts\\n\\n Next, we consider whether the good faith exception to the exclusionary rule\\n\\nfrom United States v. Leon, 468 U.S. 897, 918 (1984), applies when police execute a\\n\\nsearch warrant that is based on information obtained through an unlawful predicate\\n\\nsearch. Disagreeing with the district court, we conclude that it does not. The\\n\\nSupreme Court’s opinion in Leon and our opinion in United States v. Scales, 903\\n\\nF.2d 765, 768 (10th Cir. 1990), dictate that the good faith exception does not apply in\\n\\na case like the one before us because the illegality at issue stems from unlawful\\n\\npolice conduct, rather than magistrate error, and therefore the deterrence purposes of\\n\\nthe Fourth Amendment are best served by applying the exclusionary rule.\\n\\n In United States v. Leon, the Supreme Court modified the exclusionary rule\\n\\n“so as not to bar the use in the prosecution’s case in chief of evidence obtained by\\n\\nofficers acting in reasonable reliance on a search warrant issued by a detached and\\n\\n 30\\n\\fneutral magistrate but ultimately found to be unsupported by probable cause,” 468\\n\\nU.S. at 900. The Court reasoned that the purpose of the exclusionary rule is to deter\\n\\npolice misconduct and in such a case “there is no police illegality and thus nothing to\\n\\ndeter.” Id. at 920. In this circuit, “Leon’s good faith exception applies only narrowly,\\n\\nand ordinarily only when an officer relies, in an objectively reasonable manner, on a\\n\\nmistake made by someone other than the officer.” United States v. Cos, 498 F.3d 1115,\\n\\n1132 (10th Cir. 2007) (declining to apply good faith exception to warrantless search of\\n\\napartment where officers mistakenly believed the person that consented to the search had\\n\\nthe authority to do so); United States v. Herrera, 444 F.3d 1238, 1251 (10th Cir. 2006)\\n\\n(declining to apply good faith exception to state trooper who conducted a warrantless\\n\\ninspection of a truck based on the officer’s mistaken belief the truck was a commercial\\n\\nvehicle subject to such inspection). Thus, Leon is inapplicable here where the\\n\\nmistake—the unconstitutional second search—was the fault of the officer, not the\\n\\nmagistrate.\\n\\n We considered whether Leon applied to a warrant affidavit based on tainted\\n\\nevidence in Scales, 903 F.2d at 768. There, we held that Leon did not apply to\\n\\nexcuse a law enforcement officer’s reliance on a search warrant where the facts in the\\n\\nwarrant affidavit were obtained through an unlawful predicate seizure. In that case,\\n\\nDEA agents seized a suitcase that they believed contained drugs. Id. at 767. Then,\\n\\nthey took the suitcase to a drug-sniffing canine team that signaled the suitcase did\\n\\ncontain drugs. Id. Finally, after having had the suitcase in their possession for\\n\\ntwenty-four hours, the agents applied for and obtained a warrant to search the\\n\\n 31\\n\\fsuitcase based on the probable cause provided by the canine alert. Id. Upon\\n\\nconducting the search, the agents discovered more than 2,000 grams of cocaine in the\\n\\nsuitcase. Id. The defendant moved to suppress the cocaine evidence, arguing that the\\n\\nagents’ initial seizure of the suitcase was unlawful because it was unsupported by\\n\\nprobable cause. Id. at 767.\\n\\n The district court in Scales denied the motion, finding that, even if the seizure\\n\\nof the suitcase was unlawful, the good faith exception ratified the agents’ behavior.\\n\\nId. We reversed, holding that Leon was inapplicable “[b]ecause the DEA agents\\n\\nwere not acting in reliance on a search warrant when they seized the luggage and held\\n\\nit for more than twenty-four hours.” Id. at 768. Our holding was informed by the\\n\\nreasoning in Leon that “Penalizing the officer for the magistrate’s error, rather than\\n\\nhis [or her] own, cannot logically contribute to the deterrence of Fourth Amendment\\n\\nviolations.” Id. at 768 (quoting Leon, 468 U.S. at 921) (alteration in original).\\n\\nBecause the contraposition is also true—that penalizing an officer for his or her own\\n\\nerror does contribute to deterrence—we determined that the exclusionary rule must\\n\\napply to the agents’ unlawful pre-warrant seizure of the suitcase. Id.\\n\\n Scales and Leon control our outcome here. Cravens conducted an unlawful\\n\\nsearch of Loera’s CDs on November 27 in the absence of a warrant. He included the\\n\\ntainted fruit that he uncovered during that search in the affidavit that he submitted in\\n\\nsupport of the second warrant. Cravens’ warrant affidavit was facially valid, and\\n\\ntherefore the magistrate did not error by issuing a warrant based upon it. Instead, the\\n\\nconstitutional error came from Agent Cravens.\\n\\n 32\\n\\f The government argues that Cravens acted in good faith because he\\n\\n“transparently informed the magistrate judge of the steps he had taken to obtain the\\n\\ndescriptions he included in his affidavit.” Aple. Br. at 40. Cravens’ affidavit\\n\\nprovided some information about the first search. It explained that, while executing\\n\\nthe first search warrant, the FBI agents identified four CDs that contained child\\n\\npornography and seized them. Then, Cravens wrote:\\n\\n On November 27, 2012, the writer, an FBI certified CART Technician,\\n reviewed the four CDs, each of which are designated in attachment A,\\n that were believed to contain child pornography. During the review of\\n the CDs, the writer observed multiple pictures of children many of\\n which are in various state of dress including the following images . . . .\\n\\nROA Vol. I at 50. However, that information was not sufficient to allow the\\n\\nmagistrate to determine the constitutionality of the second search such that the\\n\\nmagistrate can be said to have endorsed Cravens’ pre-warrant conduct. Furthermore,\\n\\neven if it was, that would not affect our outcome. Tenth Circuit precedent dictates\\n\\nthat the good faith exception does not apply at all when a warrant affidavit is based\\n\\non tainted evidence from a prior, unlawful search.\\n\\n Four other circuits have likewise concluded that Leon is inapplicable when an\\n\\nofficer executes in good faith a search warrant that is based on unlawfully-obtained\\n\\nevidence. United States v. Scott, 731 F.3d 659, 664 (7th Cir. 2013) (holding that\\n\\nevidence discovered pursuant to a warrant based on illegally-obtained evidence will\\n\\nbe inadmissible unless other, untainted information in the affidavit establishes\\n\\nprobable cause); United States v. Mowatt, 513 F.3d 395, 405 (4th Cir. 2008) (holding\\n\\nthat “Leon only prohibits penalizing officers for their good-faith reliance on\\n\\n 33\\n\\fmagistrates’ probable cause determinations” and that the exclusionary rule operates\\n\\nto penalize officers for any unconstitutional conduct preceding a magistrate’s\\n\\ninvolvement); United States v. McGough, 412 F.3d 1232 (11th Cir. 2005) (refusing\\n\\nto apply good faith exception where an unlawful entry into the defendant’s apartment\\n\\nled to the officer’s request for a search warrant); United States v. Vasey, 834 F.2d\\n\\n782, 789 (9th Cir. 1987) (holding that good faith exception did not apply to a warrant\\n\\nthat was based on information obtained in an illegal warrantless search because “[t]he\\n\\nconstitutional error was made by the officer . . ., not by the magistrate”). At least two\\n\\ncommentators support this analysis as well. See Wayne R. LaFave, Search &\\n\\nSeizure: A Treatise on the Fourth Amendment § 1.3(f) (5th ed. 2016) (explaining\\n\\nthat, because courts rarely require affiants to prove that they obtained the evidence\\n\\nlisted in an affidavit lawfully, “there is no reason why that process should, via Leon,\\n\\nshield that activity from full scrutiny at the suppression hearing”); Craig M.\\n\\nBradley, The “Good Faith Exception” Cases: Reasonable Exercise in Futility, 60 Ind.\\n\\nL.J. 287, 302 (1985) (quoting Leon, 468 U.S. at 914) (“When the magistrate issued\\n\\nthe warrant, he did not endorse past activity; he only authorized future activity. . . .\\n\\n[T]he function of the magistrate is to determine ‘whether a particular affidavit\\n\\nestablishes probable cause,’ not whether the methods used to obtain the information\\n\\nin that affidavit were legal.”).\\n\\n However, five other circuits have concluded that the good faith exception can\\n\\napply where an affidavit supporting a search warrant is tainted by illegally-obtained\\n\\nevidence in at least some limited circumstances. Three of those circuits apply the\\n\\n 34\\n\\fgood faith exception if the predicate search, although ultimately determined to be\\n\\nunlawful, was arguably lawful under the binding precedent in effect at the time of the\\n\\nsearch. United States v Bain, 874 F.3d 1, 22–23 (1st Cir. 2017) (applying good faith\\n\\nexception because binding precedent did not “clearly classify” as unlawful the\\n\\nconduct that invalidated the predicate search); United States v. Hopkins, 824 F.3d\\n\\n726 (8th Cir. 2016) (applying good faith exception because the reasonableness of the\\n\\nillegal predicate search was “close enough to the line of validity” to make an\\n\\nofficer’s belief in the validity of the warrant objectively reasonable); United States v.\\n\\nHolley, 831 F.3d 322, 326–27 (5th Cir. 2016) (also applying “close enough to the\\n\\nline of validity” test). Two other circuits apply the good faith exception in these\\n\\ntypes of cases when (1) the predicate search was arguably reasonable and (2) the\\n\\nwarrant affidavit truthfully conveyed the circumstances of the illegal predicate search\\n\\nto the magistrate judge. United States v. McClain, 444 F.3d 556, 566 (6th Cir. 2005)\\n\\n(applying Leon because the reasonableness of the predicate search was a close call\\n\\nand the warrant affidavit “fully disclosed” the circumstances surrounding the initial\\n\\nwarrantless search); United States v. Thomas, 757 F.2d 1359 (2d Cir. 1985) (applying\\n\\ngood faith exception because officer’s affidavit fully described the unlawful, pre-\\n\\nwarrant canine sniff that supplied probable cause for the warrant and there was\\n\\n“nothing more the officer could have or should have done” to be sure his search was\\n\\nlegal). We cannot read Leon or Scales to support the rules adopted by these courts.\\n\\nWhen a magistrate issues a warrant based on illegally obtained evidence, typically the\\n\\nmanner in which the affidavit evidence is obtained is not before the magistrate, and the\\n\\n 35\\n\\fmagistrate is not asked explicitly to endorse the evidence-gathering procedure. Even\\n\\nthough some disclosure of the evidence-gathering technique may have occurred, that is\\n\\nnot ordinarily the focus of an application for a warrant. Thus, we are unwilling to read a\\n\\nwarrant as ratifying the information-gathering process of a search that preceded it. In any\\n\\nevent, we are bound by Scales, which appears to us to have been correctly decided.\\n\\n Therefore, the district court erred by finding that the good faith doctrine applied to\\n\\nthe searches Agent Nishida conducted in execution of the second warrant.\\n\\n 3. Inevitable discovery doctrine supports denial of Loera’s motion\\n\\n Finally, we consider whether the government would have inevitably discovered\\n\\nthe child pornography evidence on Loera’s electronic devices. Loera argues that, because\\n\\nthere was no probable cause to support the second warrant, all evidence discovered as a\\n\\nresult of the execution of the second warrant should have been suppressed. The issue\\n\\nbefore us, then, is whether the FBI agents would have inevitably discovered the roughly\\n\\n330 child pornography images on Loera’s CDs and 730 child pornography images on\\n\\nLoera’s laptop that Nishida found when he executed the second warrant. We conclude\\n\\nthat they would have. Accordingly, we affirm the district court’s denial of Loera’s\\n\\nmotion to suppress.\\n\\n When evidence is obtained in violation of the Fourth Amendment, that\\n\\nevidence need not be suppressed if agents inevitably would have discovered it\\n\\nthrough lawful means independent from the unconstitutional search. United States v.\\n\\nChristy, 739 F.3d 534, 540 (10th Cir. 2014). The government is required to prove by a\\n\\npreponderance of the evidence that the unlawfully-obtained evidence would have been\\n\\n 36\\n\\fdiscovered through lawful means. Id. The “lawful means” need not be a second,\\n\\nindependent investigation. Id. Rather, the inevitable discovery doctrine will apply if\\n\\nthere was “one line of investigation that would have led inevitably to the obtaining of a\\n\\nsearch warrant by independent lawful means but was halted prematurely by a search\\n\\nsubsequently contended to be illegal.” Id. (citations omitted). The key to applying this\\n\\ndoctrine is to place the government officers in the “same positions they would have\\n\\nbeen in had the impermissible conduct not taken place,” and, from that vantage point,\\n\\nto ask whether the government would have inevitably discovered the evidence\\n\\nlawfully. Nix v. Williams, 467 U.S. 431, 447 (1984).\\n\\n Here, the district court’s supportable findings demonstrate by a preponderance of\\n\\nthe evidence that the FBI would have inevitably discovered the child pornography\\n\\nevidence on Loera’s electronic devices through lawful means independent from Agent\\n\\nCravens’ unlawful second search. On November 26 (the day before the second search),\\n\\nthe government lawfully had in its possession Loera’s computers, external hard drives,\\n\\niPhone, iPad, and thirteen CDs (nine without child pornography and four with child\\n\\npornography).4 The government had the authority under the first warrant to search\\n\\nLoera’s electronic devices—most importantly his laptop and CDs—for evidence of\\n\\ncomputer fraud. The district court issued an explicit factual finding that, had the\\n\\nsecond warrant never been obtained, Agent Nishida would “have searched [Loera’s\\n\\n\\n\\n4\\n As mentioned above, although Loera challenges the first search of these four CDs,\\nhe does not separately challenge their seizure were we to determine, as we have, that\\nthe first search was constitutional.\\n 37\\n\\flaptop] for evidence of electronic mail hijacking and computer fraud pursuant to the\\n\\n[f]irst [w]arrant.” Dist. Ct. Op. at 24. The district court further found that, as part of\\n\\nthat search, lawfully conducted pursuant to the parameters of the first warrant, Agent\\n\\nNishida would have searched the electronic folders where he discovered child\\n\\npornography when he executed the second warrant, including, the “My Documents”\\n\\nfolder, the “Bookmarks” tab of Loera’s internet browser, and a folder saved on the\\n\\nDesktop titled “Allmyfiles.txt.” Id. at 24–25. The district court also accepted\\n\\nNishida’s statement that, had he found child pornography images on the laptop\\n\\nduring a search conducted solely pursuant to the first warrant, he would have “alerted\\n\\nthe case agent so that [he] could get a search warrant for child pornography.” Id. at\\n\\n25.\\n\\n The laptop, including the specific files referenced above, contained over 730\\n\\nimages and 40 movies involving child pornography. Id. at 24. To take one specific\\n\\nexample, the “Allmyfiles.txt” file, which the district court found Nishida would have\\n\\nlawfully opened pursuant to the first warrant, contained files called “Spycam 9yr\\n\\nUndress.” Id. Such information would have been sufficient to establish probable\\n\\ncause to support a warrant to search all of the electronic devices belonging to Loera\\n\\nthat the government had in its possession, including the four CDs that Agent Cravens\\n\\nsearched unlawfully on November 27. That fact, combined with Agent Nishida’s\\n\\nindication that he would have sought a warrant, allows us to conclude that the\\n\\ninevitable discovery doctrine applies in this case such that the evidence discovered\\n\\npursuant to the second warrant did not need to be suppressed.\\n\\n 38\\n\\f III. CONCLUSION\\n\\n For the foregoing reasons, we AFFIRM the orders of the district court denying\\n\\nthe defendant’s motion to suppress and motion for reconsideration.\\n\\n\\n\\n\\n 39\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2262,"cells":{"id":{"kind":"number","value":4619689,"string":"4,619,689"},"name":{"kind":"string","value":"Steven M. PETERSEN ; Pauline Petersen, Petitioners - Appellants, v. COMMISSIONER OF INTERNAL REVENUE, Respondent - Appellee. John E. Johnstun; Larue A. Johnstun, Petitioners - Appellants, v. Commissioner of Internal Revenue, Respondent - Appellee."},"name_abbreviation":{"kind":"string","value":"Petersen v. Comm'r of Internal Revenue"},"decision_date":{"kind":"string","value":"2019-05-15"},"docket_number":{"kind":"string","value":"17-9003; 17-9004"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Hartz, Phillips, Eid\", \"parties\": \"\", \"opinions\": [{\"author\": \"HARTZ, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 15, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n STEVEN M. PETERSEN; PAULINE\\n PETERSEN,\\n\\n Petitioners - Appellants,\\n\\n v. No. 17-9003\\n\\n COMMISSIONER OF INTERNAL\\n REVENUE,\\n\\n Respondent - Appellee.\\n\\n –––––––––––––––––––––––––––––––––––\\n\\n JOHN E. JOHNSTUN; LARUE A.\\n JOHNSTUN,\\n\\n Petitioners - Appellants,\\n\\n v. No. 17-9004\\n\\n COMMISSIONER OF INTERNAL\\n REVENUE,\\n\\n Respondent - Appellee.\\n _________________________________\\n\\n Appeal from the United States Tax Court\\n (CIR Nos. 015184-14 & 015185-14)\\n _________________________________\\n\\nMichael C. Walch, Kirton McConkie, Lehi, Utah, for Petitioners-Appellants.\\n\\nJennifer M. Rubin (Bruce R. Ellisen, with her on the brief), Department of Justice, Tax\\nDivision, Washington, D.C., for Respondent-Appellee.\\n _________________________________\\n\\fBefore HARTZ, PHILLIPS, and EID, Circuit Judges.\\n _________________________________\\n\\nHARTZ, Circuit Judge.\\n _________________________________\\n\\n This appeal concerns the propriety of the timing of deductions by a Subchapter S\\n\\ncorporation for expenses paid to employees who participate in the corporation’s\\n\\nemployee stock ownership plan (ESOP). Stephen and Pauline Petersen and John and\\n\\nLarue Johnstun (Taxpayers) appeal the decision of the United States Tax Court holding\\n\\nthem liable for past-due taxes arising out of errors in their income-tax returns caused by\\n\\npremature deductions for expenses paid to their Corporation’s ESOP. Taxpayers contend\\n\\nthat the Tax Court misinterpreted the Internal Revenue Code (IRC) and, even if its\\n\\ninterpretation was correct, miscalculated the amounts of alleged deficiencies. The\\n\\nCommissioner agrees that a recalculation is necessary. Exercising jurisdiction under 26\\n\\nU.S.C. § 7482(a), we affirm Taxpayers’ liability but remand for recalculation of the\\n\\ndeficiencies.\\n\\n I. BACKGROUND\\n\\n Taxpayers were majority shareholders in Petersen Inc. (the Corporation), a\\n\\nSubchapter S corporation.1 The disputed liabilities arise from Taxpayers’ income-tax\\n\\nreturns for 2009 (offset in small part by corrections in their favor for their 2010 returns).\\n\\nBecause the Corporation is a Subchapter S corporation, it is a pass-through entity for\\n\\nincome-tax purposes—that is, the Corporation does not itself pay income taxes, but its\\n\\n\\n1\\n Larue Johnstun was not a shareholder in the Corporation, but is a party in this case\\nbecause she filed her income-tax return jointly with her husband John.\\n\\n 2\\n\\ftaxable income, deductions, and losses are passed through to its shareholders. See 26\\n\\nU.S.C. § 1366. For 2009 and most of 2010, Taxpayers owned 79.6% of the\\n\\nCorporation’s stock. The remaining stock was held by the Corporation’s ESOP. In\\n\\nOctober 2010 the ESOP acquired all of Taxpayers’ stock, becoming the 100% owner.\\n\\n The ESOP is an employee-benefit plan governed by the Employee Retirement\\n\\nIncome Security Act (ERISA). Employee-benefit plans that qualify under the detailed\\n\\nrequirements of ERISA, see 26 U.S.C. § 401(a), are exempt from income taxes, see id.\\n\\n§ 501. An ESOP is a type of qualified employee-benefit plan in which an employer\\n\\ncontributes shares of its own stock, or cash to purchase shares of its stock, into a trust,\\n\\nand those shares are allocated to individual employee accounts. See 26 U.S.C. § 4975\\n\\n(e)(7); 29 U.S.C. § 1107(d)(6); Donovan v. Cunningham, 716 F.2d 1455, 1459 (5th Cir.\\n\\n1983). ESOPs provide employee participants the opportunity to gain ownership in shares\\n\\nof the employer corporation. As the Supreme Court has recently noted:\\n\\n “The Congress, in a series of laws [including ERISA] has made clear its\\n interest in encouraging [ESOPs] as a bold and innovative method of\\n strengthening the free private enterprise system which will solve the dual\\n problems of securing capital funds for necessary capital growth and of\\n bringing about stock ownership by all corporate employees.”\\n\\nFifth Third Bancorp v. Dudenhoeffer, 573 U.S. 409, 416 (2014) (quoting Tax Reform Act\\n\\nof 1976, § 803(h), 90 Stat. 1590 (brackets added by Supreme Court)). A corporation’s\\n\\ncontributions paid to its ESOP are tax deductible. See 26 U.S.C. § 404(a)(3); Brindle v.\\n\\nWilmington Trust, N.A., 919 F.3d 763, 769 (4th Cir. 2019). There is no dispute that the\\n\\nCorporation’s ESOP is qualified under ERISA.\\n\\n\\n\\n\\n 3\\n\\f The Corporation is an accrual-basis taxpayer and its ESOP-participant employees\\n\\nare cash-basis taxpayers. As a general rule, an accrual-basis taxpayer may deduct\\n\\nordinary and necessary business expenses in the year when “all events have occurred\\n\\nwhich determine the fact of liability and the amount of such liability can be determined\\n\\nwith reasonable accuracy.” 26 U.S.C. § 461(h)(4). But § 267 of the IRC restricts the\\n\\ntiming of deductibility when the accrued expense is to be paid to a cash-basis taxpayer\\n\\nthat is “related to” the taxpayer. See id. § 267(a)(2). Such expenses cannot be deducted\\n\\nuntil the amount of the payment becomes gross income of the related taxpayer. See id.\\n\\nConsider, for example, an employee on the Corporation’s payroll who is “related to” the\\n\\nCorporation (we will call such employees “related employees”), works during the last\\n\\neight days of the calendar year, but does not receive a paycheck until early the following\\n\\nyear. Although the Corporation accrues the payroll expense in the year that the employee\\n\\nworked the eight days, it must delay the deduction until the next year, when the related\\n\\nemployee receives the payment of wages.\\n\\n Here, the Corporation deducted expenses for ESOP participants in the year that the\\n\\nexpenses accrued even though it did not pay the expenses until the next year. Among\\n\\nthose accrued expenses were wages and salaries (paid every second Friday) and unused\\n\\nvacation time rolled over by employees from one year to the next. If a payday fell early\\n\\nin January 2010, the Corporation could accrue during 2009 up to two weeks of unpaid\\n\\npayroll that the employee would not receive until 2010; and the expense of vacation days\\n\\ncould be accrued many months before the employee used the benefit. These accrued but\\n\\n\\n\\n\\n 4\\n\\funpaid expenses should not have been deducted by the Corporation at the time of accrual\\n\\nif the payment would go to a related employee.\\n\\n The Internal Revenue Service (IRS) audited Taxpayers and decided that\\n\\nemployees of the Corporation who participated in its ESOP were related to the\\n\\nCorporation. It therefore disallowed deductions taken for the 2009 tax year based on\\n\\nexpenses accrued in that year but not paid to the related employees until 2010.\\n\\nTaxpayers unsuccessfully contested the alleged deficiencies in the United States Tax\\n\\nCourt and now appeal to this court.\\n\\n II. DISCUSSION\\n\\n “We review tax court decisions in the same manner and to the same extent as\\n\\ndecisions of the district courts in civil actions tried without a jury. The Tax Court’s legal\\n\\nconclusions are subject to de novo review, and its factual findings can be set aside only if\\n\\nclearly erroneous.” Katz v. C.I.R., 335 F.3d 1121, 1125–26 (10th Cir. 2003) (citation and\\n\\ninternal quotation marks omitted). We proceed to discuss the applicable statutory\\n\\nprovisions and explain why the challenges by Taxpayers are unpersuasive.\\n\\n A. IRC § 267\\n\\n We begin with IRC § 267. Paragraph 267(a)(2) is entitled “Matching of deduction\\n\\nand payee income item in the case of expenses and interest.” It provides that if the\\n\\ntaxpayer and a person to whom the taxpayer is to make a payment are related—that is,\\n\\n“are persons specified in any of the paragraphs of subsection (b) [of § 267],” id.\\n\\n§ 267(a)(1) (emphasis added)—then the amount of the payment cannot be deducted until\\n\\n\\n\\n\\n 5\\n\\fit is paid or is includible in the recipient’s gross income, see id. § 267(a)(2)2. This\\n\\nprovision keeps taxpayers from exploiting differences in accounting methods between the\\n\\npayer (who deducts the payment) and the recipient (who treats the payment as income) to\\n\\nartificially evade, or at least delay, income taxes. It was enacted “to require related\\n\\npersons ‘to use the same accounting method with respect to transactions between\\n\\nthemselves in order to prevent the allowance of a deduction without the corresponding\\n\\ninclusion in income.’” Tate & Lyle, Inc. v. C.I.R., 87 F.3d 99, 103 (3d Cir. 1996) (quoting\\n\\nH.R. Supp. Rep. 998-432, Part 2, at 1578, reprinted in 1984 U.S.C.C.A.N. 697, 1205)\\n\\n(House Report); see also House Report at 1578–79 (“The failure to use the same\\n\\naccounting method with respect to one transaction involves unwarranted tax benefits,\\n\\nespecially where payments are delayed for a long period of time, and in fact may never\\n\\n\\n\\n\\n2\\n The pertinent part of § 267(a)(2) states:\\n\\nIf--\\n\\n(A) by reason of the method of accounting of the person to whom the payment is to be\\nmade, the amount thereof is not (unless paid) includible in the gross income of such\\nperson, and\\n\\n(B) at the close of the taxable year of the taxpayer for which (but for this paragraph) the\\namount would be deductible under this chapter, both the taxpayer and the person to\\nwhom the payment is to be made are persons specified in any of the paragraphs of\\nsubsection (b),\\n\\nthen any deduction allowable under this chapter in respect of such amount shall be\\nallowable as of the day as of which such amount is includible in the gross income of the\\nperson to whom the payment is made (or, if later, as of the day on which it would be so\\nallowable but for this paragraph). . . .\\n\\n\\n 6\\n\\fbe paid.”); Metzger Trust v. C.I.R., 76 T.C. 42, 75 (1981) (Congress enacted § 267 “to\\n\\nprevent the use of differing methods of reporting income for Federal income tax purposes\\n\\nin order to obtain artificial deductions for interest and business expenses.”). For example,\\n\\nabsent the limitations of § 267, an accrual-basis taxpayer indebted to a closely related\\n\\ncash-basis taxpayer could, as interest became due on the debt, report the interest as a\\n\\ndeduction without making the payment to the cash-basis taxpayer, who would report no\\n\\nincome at the time and might never report income if payment was arranged to arrive\\n\\nwhen the cash-basis taxpayer had offsetting losses. See Metzger Trust, 76 T.C. at 75.\\n\\n Subsection 267(b), entitled “Relationships,” lists a number of relationships\\n\\ncovered by this provision of the statute, such as “[m]embers of a family” and “[a] grantor\\n\\nand a fiduciary of any trust,” 26 U.S.C. § 267(b)(1), (4). Relevant here, however, is\\n\\nsubsection (e), which provides “[s]pecial rules for pass-thru entities.” It states that “an S\\n\\ncorporation [and] any person who owns (directly or indirectly) any of the stock of such\\n\\ncorporation” are to be “treated as persons specified in a paragraph of subsection (b).”\\n\\n26 U.S.C. § 267(e)(1) (emphasis added)3. In other words, an S corporation and a\\n\\n\\n\\n3\\n § 267(e) states in full:\\n\\nSpecial rules for pass-thru entities.--\\n\\n(1) In general.--In the case of any amount paid or incurred by, to, or on behalf of, a pass-\\nthru entity, for purposes of applying subsection (a)(2)--\\n\\n(A) such entity,\\n\\n(B) in the case of--\\n\\n\\n 7\\n\\fshareholder of that S corporation are related to one another for purposes of § 267.\\n\\nBecause the Corporation ESOP owned much—later, all—of the shares of the\\n\\nCorporation, the Corporation and the Corporation ESOP were related.\\n\\n Also relevant here is § 267(c), entitled “Constructive ownership of stock.” It\\n\\nprovides, “For purposes of determining, in applying subsection (b), the ownership of\\n\\nstock—(1) Stock owned, directly or indirectly, by or for a corporation, partnership, state,\\n\\nor trust shall be considered as being owned proportionately by or for its shareholders,\\n\\npartners, or beneficiaries.” 26 U.S.C. § 267(c)(1) (emphasis added). If the stock held by\\n\\nan ESOP is held in a trust within the meaning of § 267(c)(1), and if the employees\\n\\nparticipating in the ESOP are beneficiaries of that trust, then the Corporation employees\\n\\n\\n\\n(i) a partnership, any person who owns (directly or indirectly) any capital interest or\\nprofits interest of such partnership, or\\n\\n(ii) an S corporation, any person who owns (directly or indirectly) any of the stock of\\nsuch corporation,\\n\\n(C) any person who owns (directly or indirectly) any capital interest or profits interest of\\na partnership in which such entity owns (directly or indirectly) any capital interest or\\nprofits interest, and\\n\\n(D) any person related (within the meaning of subsection (b) of this section or section\\n707(b)(1)) to a person described in subparagraph (B) or (C),\\n\\nshall be treated as persons specified in a paragraph of subsection (b). Subparagraph (C)\\nshall apply to a transaction only if such transaction is related either to the operations of\\nthe partnership described in such subparagraph or to an interest in such partnership.\\n(2) Pass-thru entity.ab--For purposes of this section, the term “pass-thru entity” means--\\n(A) a partnership, and\\n\\n(B) an S corporation.\\n\\n(Emphasis added.)\\n\\n 8\\n\\fparticipating in the ESOP must be considered owners of stock of the Corporation under\\n\\n§ 267(c). In our view, both of those conditions are met. To support that conclusion, we\\n\\nneed to examine both trust law and ERISA.\\n\\n B. Trust Law and ERISA\\n\\n The term trust is not defined in § 267. The Restatement (Third) of Trusts § 2\\n\\n(2003) (hereinafter Restatement Third) broadly defines the term as “a fiduciary\\n\\nrelationship with respect to property, arising from a manifestation of intention to create\\n\\nthat relationship and subjecting the person who holds title to the property to duties to deal\\n\\nwith it for the benefit of charity or for one or more persons, at least one of whom is not\\n\\nthe sole trustee.” A trust generally has the following elements: (1) trust property (real or\\n\\npersonal, tangible or intangible) which the trustee holds subject to the rights of another,\\n\\n(2) a trustee (an individual or entity charged with holding the trust property for the\\n\\nbenefit of another), and (3) a beneficiary (the person for whose benefit the trustee holds\\n\\nthe trust property). See Amy M. Hess et al., Bogert’s Trust and Trustees § 1 (2018)\\n\\n(Bogert). Essentially the same concept is reflected in the IRC regulations: “Generally\\n\\nspeaking, an arrangement will be treated as a trust under the Internal Revenue Code if it\\n\\ncan be shown that the purpose of the arrangement is to vest in trustees responsibility for\\n\\nthe protection and conservation of property for beneficiaries who cannot share in the\\n\\ndischarge of this responsibility and, therefore, are not associates in a joint enterprise for\\n\\nthe conduct of business for profit.” 26 C.F.R. § 301.7701-4(a).\\n\\n One purpose of ERISA is to protect employees from abuse and mismanagement of\\n\\nfunds designated for employee-benefit plans. See Massachusetts v. Morash, 490 U.S.\\n\\n\\n 9\\n\\f107, 112 (1989) (“ERISA was passed . . . to safeguard employees from the abuse and\\n\\nmismanagement of funds that had been accumulated to finance various types of employee\\n\\nbenefits.”); Firestone Tire and Rubber Co. v. Bruch, 489 U.S. 101, 113 (1989). To this\\n\\nend, ERISA establishes minimum standards for benefit plans by “imposing reporting and\\n\\ndisclosure mandates, participation and vesting requirements, funding standards, and\\n\\nfiduciary responsibilities for plan administrators. It envisions administrative oversight,\\n\\nimposes criminal sanctions, and establishes a comprehensive civil enforcement scheme.”\\n\\nNew York State Conference of Blue Cross & Blue Shield Plans v. Travelers Ins. Co., 514\\n\\nU.S. 645, 651 (1995) (citations omitted). The safeguard relevant here is that it mandates\\n\\nthat assets of employee-benefit plans be held in trust. See 29 U.S.C. § 1103(a) (absent\\n\\nexceptions not relevant here, “all assets of an employee benefit plan shall be held in trust\\n\\nby one or more trustees”); Restatement Third § 2 cmt. a (“The term ‘trust’ . . . includes\\n\\n. . . private pension-fund arrangements in trust form.”).\\n\\n Although ERISA trusts are not governed by the common law of trusts established\\n\\nby state law, see Shaw v. Delta Air Lines, Inc., 463 U.S. 85, 104 (1983) (“Congress\\n\\napplied the principle of pre-emption in its broadest sense to foreclose any non-Federal\\n\\nregulation of employee benefit plans, creating only very limited exceptions . . . .”\\n\\n(internal quotation marks omitted)), the federal statutory requirements mirror the law\\n\\nregarding a common-law trust. The trust property consists of all the assets of the\\n\\nemployee-benefit plan. The trust must have trustees. See 29 U.S.C. § 1103(a). The trust\\n\\nproperty must be managed for the exclusive benefit of plan participants and beneficiaries.\\n\\nSee 29 U.S.C. § 1103(c)(1) (absent exceptions not relevant here, “the assets of a plan\\n\\n\\n 10\\n\\fshall never inure to the benefit of any employer and shall be held for the exclusive\\n\\npurposes of providing benefits to participants in the plan and their beneficiaries and\\n\\ndefraying reasonable expenses of administering the plan.”). Indeed, citing the provision\\n\\nthat “assets of an employee benefit plan shall be held in trust,” 29 U.S.C. § 1103(a), the\\n\\nSupreme Court observed that “rather than explicitly enumerating all of the powers and\\n\\nduties of trustees and other fiduciaries, Congress invoked the common law of trust to\\n\\ndefine the general scope of their authority and responsibility.” Central States, Southeast\\n\\nand Southwest Areas Pension Fund v. Central Transport, Inc., 472 U.S. 559, 570 (1985);\\n\\nsee also Firestone, 489 U.S. at 110 (“ERISA abounds with the language and terminology\\n\\nof trust law.”). Also, although a participant or beneficiary of an ERISA plan cannot seek\\n\\nrelief under state trust law, see Pilot Life Ins. Co. v. Dedeaux, 481 U.S. 41, 54 (1987)\\n\\n(ERISA’s civil enforcement remedies are exclusive; remedies under state law are not\\n\\navailable.), ERISA itself provides robust remedies for violations of fiduciary duties, see\\n\\nVarity Corp. v. Howe, 516 U.S. 489 (1996) (construing 29 U.S.C. § 1132, entitled “Civil\\n\\nenforcement”); see also Garratt v. Walker, 164 F.3d 1249, 1253 (10th Cir. 1998) (“The\\n\\ncivil enforcement mechanism . . . of ERISA, specifically 29 U.S.C. § 1132(a)(1)(B),\\n\\nallows a plan participant to bring a civil action not only for recovery of plan benefits and\\n\\nenforcement of plan rights, but also to clarify his rights to future benefits under the terms\\n\\nof the plan.”).\\n\\n To be sure, although courts in the ERISA context “are to apply common-law trust\\n\\nstandards, [they must] bear[] in mind the special nature and purpose of employee benefit\\n\\nplans.” Varity, 516 U.S. at 506 (internal quotation marks omitted). But that does not\\n\\n\\n 11\\n\\fchange the essential nature of an ERISA trust as a trust. After all, even common-law\\n\\ntrusts regularly contain provisions departing from the default common-law standards.\\n\\nSee Restatement Third § 4 cmt. a(1) (“[M]ost (but not all) of trust law consists of ‘default\\n\\nrules,’ as opposed to mandatory or restrictive rules . . . .”) Here, Congress authorizes the\\n\\ncourts to recognize the need for special standards in this context.\\n\\n We therefore conclude that the Corporation’s ESOP trust is a trust within the\\n\\nmeaning of § 267 and that the Commissioner properly applied that section to Taxpayers.\\n\\nTaxpayers’ brief has a jumble of arguments that an ESOP trust is not a “trust” within the\\n\\nmeaning of the term in IRC § 267. But to the extent that we can understand these\\n\\narguments, they are unconvincing. We consider them in turn.\\n\\n Taxpayers argue that an ERISA trust is distinguishable from a common-law trust\\n\\n(and thus is not covered by § 267) because it protects the interests of “participants,” who\\n\\nare distinguished from “beneficiaries” in ERISA. But this argument relies on semantics\\n\\nrather than substance. As previously noted, a beneficiary “is the person for whose benefit\\n\\nthe trustee holds the trust property.” Bogert § 1. The property in an ERISA trust “shall\\n\\nbe held for the exclusive purposes of providing benefits to participants in the plan and\\n\\ntheir beneficiaries and defraying reasonable expenses of administering the plan.”\\n\\n29 U.S.C. § 1103(c)(1). Both participants in the plan and their beneficiaries satisfy the\\n\\ndefinition of beneficiary in trust law. All ERISA does is use different terminology to\\n\\ndescribe two distinct classes of beneficiaries—those employees or former employees who\\n\\nparticipate in the plan, and the beneficiaries whose interests derive from a participant.\\n\\nSee 29 U.S.C. § 1002(7) (defining participant), (8) (defining beneficiary as “a person\\n\\n\\n 12\\n\\fdesignated by a participant, or by terms of an employee benefit plan, who is or may\\n\\nbecome entitled to a benefit thereunder.”). The common law of trusts allows for different\\n\\nbeneficiaries “whose interests may be enjoyable concurrently or successively.”\\n\\nRestatement Third § 44 cmt. a. ERISA’s use of the term participant to describe certain\\n\\nbeneficiaries does not remove ERISA trusts from the IRC definition of trusts. The term\\n\\nbeneficiary in § 267 has been interpreted quite broadly, see Wyly v. United States, 662\\n\\nF.2d 397, 402 (5th Cir. 1981) (taxpayers were beneficiaries of trust even though they\\n\\nwould receive nothing unless their four children died without issue); and in any event,\\n\\nthere is no need for such a broad construction here, since every participant easily satisfies\\n\\nthe common-law definition of beneficiary.\\n\\n Taxpayers also argue that ERISA trusts are not true trusts because they are called\\n\\n“qualified trusts.” They cite various provisions of the Internal Revenue Code that do not\\n\\ntreat ESOPs the same way as they treat other trusts. But all that shows is that an ESOP\\n\\ntrust is a special type of trust, with special tax consequences for which it “qualifies.” For\\n\\nexample, such a trust pays no income tax. See 26 U.S.C. § 501(a). The very reason why\\n\\nthe term trust is preceded by the adjective “qualified” is that special conditions must be\\n\\nmet for the trust to qualify. That adjective does not signal that the entity is not a true\\n\\ntrust; the term is not “quasi-trust.” To say that calling the entity a “qualified trust” means\\n\\nthat it is not a true “trust” would be like saying that an All Star baseball player is not a\\n\\nreal baseball player. We reject Taxpayers’ suggestion that when the IRC uses the stand-\\n\\nalone term trust, it intends to exclude ESOP “qualified trusts.”\\n\\n\\n\\n\\n 13\\n\\f Taxpayers further contend that an ESOP trust does not satisfy the IRS definition of\\n\\ntrust in 26 C.F.R. § 301.7701–4(a). They point to the following sentence in the\\n\\nregulation:\\n\\n In general, the term “trust” as used in the Internal Revenue Code refers to\\n an arrangement created either by a will or by an inter vivos declaration\\n whereby trustees take title to property for the purpose of protecting or\\n conserving it for the beneficiaries under the ordinary rules applied in\\n chancery or probate courts . . . .\\n\\n26 C.F.R. § 301.7701–4(a). As they see it, an ESOP trust is distinct from the trusts\\n\\ndescribed in that sentence because it is not created by a will or an inter vivos declaration\\n\\nand is not “generally subject to the rules of chancery or probate courts.” Aplt. Br. at 20.\\n\\n But Taxpayers ignore the words “[i]n general” at the beginning of the quoted\\n\\nsentence; the language that follows those words is clearly intended to be illustrative, not\\n\\nexhaustive. And they ignore the language three sentences later in the regulation:\\n\\n“Generally speaking, an arrangement will be treated as a trust under the Internal Revenue\\n\\nCode if it can be shown that the purpose of the arrangement is to vest in trustees\\n\\nresponsibility for the protection and conservation of property for beneficiaries who\\n\\ncannot share in the discharge of this responsibility and, therefore, are not associates in a\\n\\njoint enterprise for the conduct of business for profit.” 26 C.F.R. § 301.7701–4(a). We\\n\\nhave already explained how ERISA trusts fulfill those requirements. One should not\\n\\nmake too much of the statement that trusts generally are created “either by will or by an\\n\\ninter vivos declaration” (which apparently does not include trusts created by\\n\\ncorporations). Id. Similar language appears in the Restatement Third. Section 3(1)\\n\\nstates: “The person who creates a trust is the settlor,” and comment a to the section\\n\\n\\n 14\\n\\fstates: “The term ‘settlor’ includes a person who creates a trust by will as well as a\\n\\nperson who creates a trust inter vivos.” But that language does not exclude trusts created\\n\\nby others, such as corporations. Comment e to § 3 states, “The term ‘person’ includes\\n\\ncorporations and unincorporated associations.” Cf. Restatement Third § 10 cmt. b. (“A\\n\\ntrust may also be created by statute.”).\\n\\n Nor is it material that the terms of an ERISA trust cannot be enforced in chancery\\n\\nor probate courts. Federal-court remedies provided in ERISA itself reflect the common\\n\\nlaw of trusts and are an adequate substitute. Besides, the regulation does not say that the\\n\\nrules governing a trust must be enforced in chancery or probate courts; it just says that\\n\\nsuch a trust should be subject to the “ordinary rules applied” in those courts. 26 C.F.R.\\n\\n§ 301.7701–4(a). Also, we think it informative that the regulation notes certain entities\\n\\n(but notably not ERISA trusts) that are known as trusts but not treated as trusts for\\n\\npurposes of the IRC because they do not satisfy the requirements of an ordinary trust.\\n\\nSee id. § 301.7701–4(b) (business trusts), (c) (investment trusts). We are confident that\\n\\nan ERISA trust satisfies the requirements of the regulation.\\n\\n Taxpayers also claim support in Revenue Ruling 89-52, which includes the\\n\\nstatement, “The term ‘trust’ is not a term of art or of fixed content, and its meaning for\\n\\nthe purposes of employee trusts under section 401(a) of the Code [which sets forth the\\n\\nrequirements for an employee-benefit trust to qualify for exemption from taxation under\\n\\n26 U.S.C. § 501(a)] is not necessarily the same as under state law or as under other\\n\\nsections of the Internal Revenue Code.” See Rev. Rul. 89-52, 1989-1 C.B. 110. But read\\n\\nin the context of the entire ruling, the point of the sentence is that additional requirements\\n\\n\\n 15\\n\\fmay be imposed on employee trusts that are not imposed on trusts in general. The next\\n\\nparagraph of the Ruling makes this clear:\\n\\n Generally, for a trust to be qualified under section 401(a) of the Code, the\\n trust must be a valid trust under the law of the jurisdiction in which the trust\\n is located. However, even if the trust is valid under local law, the\\n arrangement may be required to satisfy certain other requirements in order\\n to be considered a trust for purposes of section 401(a).\\n\\nRev. Rul. 89-52, 1989-1 C.B. 110 (citation omitted). In the trust at issue in the Ruling,\\n\\nthe trust was not qualified as an employee trust because the elements of a trust\\n\\nrelationship were not present. See id. (“[P]articipants [in the trust at issue] have the right\\n\\nto acquire, hold and dispose of an amount attributable to their account balances in the\\n\\nplan.”). If anything, the Ruling supports the proposition that a “qualified trust” must be a\\n\\n“trust” and also meet certain other requirements.4\\n\\n Taxpayers’ final argument against treating the ESOP trust as a “trust” under § 267\\n\\n is a puzzling one. It relies on 29 U.S.C. § 1132(d), which states that “[a]n employee\\n\\n benefit plan may sue or be sued [under ERISA] as an entity” and that “[a]ny money\\n\\n judgment under [ERISA] against an employee benefit plan shall be enforceable only\\n\\n against the plan as an entity and shall not be enforceable against any other person unless\\n\\n\\n\\n4\\n The sentence in the Ruling relied on by Taxpayers cites to Tavannes Watch Co. v.\\nCommissioner, 176 F.2d 211, 215 (2d Cir. 1949). In that case the court held that an\\nentity was a trust that satisfied the requirements for an employer profit-sharing plan even\\nthough it was not formally a trust. We do not think that this opinion helps Taxpayers\\neither. The court was dealing with a transitional provision for employee-benefit plans\\nthat predated a new statute and did not comply with the new requirements. The court\\nruled that the entity should be treated as qualifying during the transition period because\\nits essential nature was that of a trust. See id. at 214–16. No such special circumstances\\nare present here.\\n\\n 16\\n\\fliability against such person is established in his individual capacity under [ERISA].”\\n\\nThey conclude from this language that “it is the plan which is the legal entity, and not\\n\\nthe trust which is a part of that plan.” Aplt. Br. at 11. Are they suggesting that the\\n\\nESOP trust is a nonentity? The essential facts for application of § 267 are that the assets\\n\\nof the plan are held in a trust and the participants in the plan are beneficiaries of the\\n\\ntrust. Taxpayers do not explain the relevance of statutory provisions concerning who\\n\\ncan sue whom. And anyway they admit that trustees of an ESOP trust can be sued,\\n\\nalthough they assert, without citing authority, that in that event the trustees “are sued as\\n\\nagents of the plan, not of the trust.” Id.\\n\\n In addition to arguing that the ESOP trust is not a “trust” within the meaning of\\n\\n§ 267, Taxpayers raise several objections to applying that section to an ESOP trust on the\\n\\nground that this would conflict with other provisions of the IRC. First they claim that\\n\\n§ 267 cannot apply because it is within Subchapter B (of chapter 1 of subtitle A of the\\n\\nIRC), which covers “Computation of Taxable Income,” whereas ESOPs are formed and\\n\\ngoverned by the provisions in Subchapter D, which addresses “Deferred Compensation.”\\n\\nBut they do not point to any requirement in Subchapter D that conflicts with § 267, and\\n\\nwe perceive no conflict. What is before us to resolve is the taxation of the shareholders\\n\\nof a Subchapter S corporation, who are subject to Subchapter B. The constructive\\n\\nownership rules of § 267(c) explicitly apply to transactions with corporations,\\n\\npartnerships, estates, and trusts, see 26 U.S.C. § 267(c), all of which are also subject to\\n\\nprovisions in other subchapters of the IRC. See 26 U.S.C. §§ 301 et seq. (Subchapter C-\\n\\nCorporate Distributions and Adjustments); §§ 641 et seq. (Subchapter J-Estates, Trusts,\\n\\n\\n 17\\n\\fBeneficiaries, and Decedents); §§ 701 et seq. (Subchapter K-Partners and Partnerships).\\n\\nThere is no reason to treat a Subchapter D trust differently.\\n\\n Taxpayers similarly argue that applying the attribution rules in § 267 to trusts like\\n\\nan ESOP trust would be absurd because ESOP participants would be taxed on their share\\n\\nof ESOP income, as would beneficiaries of charitable trusts and the like. But § 267 does\\n\\nnot impose taxes on any person or entity that would not otherwise be taxed. It simply\\n\\nsays, roughly speaking, that deductions taken by those who are taxed may have to be\\n\\ndelayed—in particular, an accrual-basis taxpayer cannot deduct an accrued expense\\n\\npayable to a related person (not necessarily a taxpayer) in a tax year before the tax year in\\n\\nwhich the related person receives the payment. The tax liability of the related person is\\n\\nnot affected. Taxpayers’ various references to the nontaxation of ESOPs are therefore\\n\\nbeside the point. Of course, if a particular provision of Subchapter D explicitly overrides\\n\\n§ 267 (as Taxpayers contend is true of 26 U.S.C. § 404(a), although we note that the\\n\\nCommissioner disputes the contention), then the Subchapter D provision may well\\n\\nprevail. But Taxpayers do not suggest that any provision of Subchapter D addresses their\\n\\nsituation.\\n\\n Another of Taxpayers’ statutory arguments relies on 26 U.S.C. § 318, which, in\\n\\nour view, actually supports the Commissioner. Titled “Constructive ownership of stock,”\\n\\n§ 318 sets forth attribution rules for transactions by Subchapter C Corporations for such\\n\\npurposes as determining whether a transaction is treated as a dividend or a sale of stock.\\n\\nSee Bittker & Eustice, Fed. Income Taxation of Corp. and S’holders, ¶¶ 9.02–9.05, Mar.\\n\\n2019; S. Rep. 83-1622, at 45, 252-53 (1954) reprinted in 1954; U.S.C.C.A.N 4621, 4676,\\n\\n\\n 18\\n\\f4890–92. Taxpayers point to § 318(a)(2)(B)(i), which excludes employee-benefit trusts\\n\\nfrom the § 318 constructive-ownership rules. It states: “Stock owned, directly or\\n\\nindirectly, by or for a trust (other than an employees’ trust described in section 401(a)\\n\\nwhich is exempt from tax under section 501(a)) shall be considered as owned by its\\n\\nbeneficiaries in proportion to the actuarial interest of such beneficiaries in such trust.”\\n\\n(Emphasis added.) In particular, stock owned by an ESOP trust would not be considered\\n\\nas owned by its “beneficiaries” (presumably including the participants). Applying that\\n\\nexception to the present case, Taxpayers contend that the Corporation stock owned by its\\n\\nESOP should not be considered to be owned by the Corporation employees who\\n\\nparticipate in the plan.\\n\\n The argument may look persuasive, but there is a fatal flaw. The language\\n\\nintroducing this provision is crucial. The relevant language of § 318 is:\\n\\n (a) General rule. – For purposes of those provisions of this subchapter to which\\n the rules contained in this subsection are expressly made applicable\\n ...\\n (2) Attribution from partnerships, estates, trusts, and corporations. –\\n ...\\n (B) From trusts. –\\n (i) Stock owned, directly or indirectly by or for a trust (other than an\\n employees’ trust described in section 401(a) which is exempt from\\n tax under section 501(a)) shall be considered as owned by its\\n beneficiaries in proportion to the actuarial interest of such\\n beneficiaries in such trust.\\n\\n26 U.S.C. § 318(a)(2)(B)(i) (emphasis added). Consequently, this provision cannot\\n\\nexclude ESOP trusts from the meaning of trust in § 267 for two independently sufficient\\n\\nreasons: (1) § 267 is not in the same subchapter as § 318 (which is in Subchapter C), and\\n\\n(2) § 267 does not even mention § 318, much less make it “expressly . . . applicable.”\\n\\n\\n 19\\n\\fIndeed, rather than supporting Taxpayers’ argument, § 318 undermines it because the\\n\\nsection implicitly assumes that an “employees’ trust described in section 401(a)” would\\n\\nbe considered a “trust” governed by that section if it were not expressly excluded. Thus,\\n\\nthe failure to explicitly exclude employee trusts in § 267 strongly indicates that such\\n\\ntrusts are included.\\n\\n Taxpayers cite to Boise Cascade Corp. v. United States, 329 F.3d 751, 755 (9th\\n\\nCir. 2003), where § 318 was applied. But their reliance on that decision is misplaced.\\n\\nThe court applied § 318 to 26 U.S.C. § 302, entitled “Distributions in redemption of\\n\\nstock.” Section 302, however, satisfies the conditions for application of § 318. It appears\\n\\nin Subchapter C and it explicitly states that “section 318(a) shall apply in determining the\\n\\nownership of stock for purposes of this section.” 26 U.S.C. § 302(c)(1); see also\\n\\n26 U.S.C. 318(b) (cross referencing § 302 as a provision to which § 318(a) applies).\\n\\n Finally, Taxpayers, rather than analyzing the language of § 267, simply argue that\\n\\nit is inconsistent with some other provisions of the IRC and that if it were intended to\\n\\napply to Subchapter S corporation ESOPs, it would have said so explicitly. We are not\\n\\npersuaded. Applying § 267 to the circumstances here does not contradict any other\\n\\nprovision of the IRC, and the language of § 267 quite clearly applies in this context.\\n\\n III. CONCLUSION\\n\\n We AFFIRM the decision of the Tax Court except that we REMAND for\\n\\nrecalculation of the correct amounts of the deficiencies.\\n\\n\\n\\n\\n 20\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4396942/\", \"author_raw\": \"HARTZ, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"HARTZ"},"judge2":{"kind":"string","value":"PHILLIPS"},"judge3":{"kind":"string","value":"EID"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4619689/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Steven M. PETERSEN ; Pauline Petersen, Petitioners - Appellants, v. COMMISSIONER OF INTERNAL REVENUE, Respondent - Appellee. John E. Johnstun; Larue A. Johnstun, Petitioners - Appellants, v. Commissioner of Internal Revenue, Respondent - Appellee.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-15\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 15, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\n STEVEN M. PETERSEN; PAULINE\n PETERSEN,\n\n Petitioners - Appellants,\n\n v. No. 17-9003\n\n COMMISSIONER OF INTERNAL\n REVENUE,\n\n Respondent - Appellee.\n\n –––––––––––––––––––––––––––––––––––\n\n JOHN E. JOHNSTUN; LARUE A.\n JOHNSTUN,\n\n Petitioners - Appellants,\n\n v. No. 17-9004\n\n COMMISSIONER OF INTERNAL\n REVENUE,\n\n Respondent - Appellee.\n _________________________________\n\n Appeal from the United States Tax Court\n (CIR Nos. 015184-14 & 015185-14)\n _________________________________\n\nMichael C. Walch, Kirton McConkie, Lehi, Utah, for Petitioners-Appellants.\n\nJennifer M. Rubin (Bruce R. Ellisen, with her on the brief), Department of Justice, Tax\nDivision, Washington, D.C., for Respondent-Appellee.\n _________________________________\n\fBefore HARTZ, PHILLIPS, and EID, Circuit Judges.\n _________________________________\n\nHARTZ, Circuit Judge.\n _________________________________\n\n This appeal concerns the propriety of the timing of deductions by a Subchapter S\n\ncorporation for expenses paid to employees who participate in the corporation’s\n\nemployee stock ownership plan (ESOP). Stephen and Pauline Petersen and John and\n\nLarue Johnstun (Taxpayers) appeal the decision of the United States Tax Court holding\n\nthem liable for past-due taxes arising out of errors in their income-tax returns caused by\n\npremature deductions for expenses paid to their Corporation’s ESOP. Taxpayers contend\n\nthat the Tax Court misinterpreted the Internal Revenue Code (IRC) and, even if its\n\ninterpretation was correct, miscalculated the amounts of alleged deficiencies. The\n\nCommissioner agrees that a recalculation is necessary. Exercising jurisdiction under 26\n\nU.S.C. § 7482(a), we affirm Taxpayers’ liability but remand for recalculation of the\n\ndeficiencies.\n\n I. BACKGROUND\n\n Taxpayers were majority shareholders in Petersen Inc. (the Corporation), a\n\nSubchapter S corporation.1 The disputed liabilities arise from Taxpayers’ income-tax\n\nreturns for 2009 (offset in small part by corrections in their favor for their 2010 returns).\n\nBecause the Corporation is a Subchapter S corporation, it is a pass-through entity for\n\nincome-tax purposes—that is, the Corporation does not itself pay income taxes, but its\n\n\n1\n Larue Johnstun was not a shareholder in the Corporation, but is a party in this case\nbecause she filed her income-tax return jointly with her husband John.\n\n 2\n\ftaxable income, deductions, and losses are passed through to its shareholders. See 26\n\nU.S.C. § 1366. For 2009 and most of 2010, Taxpayers owned 79.6% of the\n\nCorporation’s stock. The remaining stock was held by the Corporation’s ESOP. In\n\nOctober 2010 the ESOP acquired all of Taxpayers’ stock, becoming the 100% owner.\n\n The ESOP is an employee-benefit plan governed by the Employee Retirement\n\nIncome Security Act (ERISA). Employee-benefit plans that qualify under the detailed\n\nrequirements of ERISA, see 26 U.S.C. § 401(a), are exempt from income taxes, see id.\n\n§ 501. An ESOP is a type of qualified employee-benefit plan in which an employer\n\ncontributes shares of its own stock, or cash to purchase shares of its stock, into a trust,\n\nand those shares are allocated to individual employee accounts. See 26 U.S.C. § 4975\n\n(e)(7); 29 U.S.C. § 1107(d)(6); Donovan v. Cunningham, 716 F.2d 1455, 1459 (5th Cir.\n\n1983). ESOPs provide employee participants the opportunity to gain ownership in shares\n\nof the employer corporation. As the Supreme Court has recently noted:\n\n “The Congress, in a series of laws [including ERISA] has made clear its\n interest in encouraging [ESOPs] as a bold and innovative method of\n strengthening the free private enterprise system which will solve the dual\n problems of securing capital funds for necessary capital growth and of\n bringing about stock ownership by all corporate employees.”\n\nFifth Third Bancorp v. Dudenhoeffer, 573 U.S. 409, 416 (2014) (quoting Tax Reform Act\n\nof 1976, § 803(h), 90 Stat. 1590 (brackets added by Supreme Court)). A corporation’s\n\ncontributions paid to its ESOP are tax deductible. See 26 U.S.C. § 404(a)(3); Brindle v.\n\nWilmington Trust, N.A., 919 F.3d 763, 769 (4th Cir. 2019). There is no dispute that the\n\nCorporation’s ESOP is qualified under ERISA.\n\n\n\n\n 3\n\f The Corporation is an accrual-basis taxpayer and its ESOP-participant employees\n\nare cash-basis taxpayers. As a general rule, an accrual-basis taxpayer may deduct\n\nordinary and necessary business expenses in the year when “all events have occurred\n\nwhich determine the fact of liability and the amount of such liability can be determined\n\nwith reasonable accuracy.” 26 U.S.C. § 461(h)(4). But § 267 of the IRC restricts the\n\ntiming of deductibility when the accrued expense is to be paid to a cash-basis taxpayer\n\nthat is “related to” the taxpayer. See id. § 267(a)(2). Such expenses cannot be deducted\n\nuntil the amount of the payment becomes gross income of the related taxpayer. See id.\n\nConsider, for example, an employee on the Corporation’s payroll who is “related to” the\n\nCorporation (we will call such employees “related employees”), works during the last\n\neight days of the calendar year, but does not receive a paycheck until early the following\n\nyear. Although the Corporation accrues the payroll expense in the year that the employee\n\nworked the eight days, it must delay the deduction until the next year, when the related\n\nemployee receives the payment of wages.\n\n Here, the Corporation deducted expenses for ESOP participants in the year that the\n\nexpenses accrued even though it did not pay the expenses until the next year. Among\n\nthose accrued expenses were wages and salaries (paid every second Friday) and unused\n\nvacation time rolled over by employees from one year to the next. If a payday fell early\n\nin January 2010, the Corporation could accrue during 2009 up to two weeks of unpaid\n\npayroll that the employee would not receive until 2010; and the expense of vacation days\n\ncould be accrued many months before the employee used the benefit. These accrued but\n\n\n\n\n 4\n\funpaid expenses should not have been deducted by the Corporation at the time of accrual\n\nif the payment would go to a related employee.\n\n The Internal Revenue Service (IRS) audited Taxpayers and decided that\n\nemployees of the Corporation who participated in its ESOP were related to the\n\nCorporation. It therefore disallowed deductions taken for the 2009 tax year based on\n\nexpenses accrued in that year but not paid to the related employees until 2010.\n\nTaxpayers unsuccessfully contested the alleged deficiencies in the United States Tax\n\nCourt and now appeal to this court.\n\n II. DISCUSSION\n\n “We review tax court decisions in the same manner and to the same extent as\n\ndecisions of the district courts in civil actions tried without a jury. The Tax Court’s legal\n\nconclusions are subject to de novo review, and its factual findings can be set aside only if\n\nclearly erroneous.” Katz v. C.I.R., 335 F.3d 1121, 1125–26 (10th Cir. 2003) (citation and\n\ninternal quotation marks omitted). We proceed to discuss the applicable statutory\n\nprovisions and explain why the challenges by Taxpayers are unpersuasive.\n\n A. IRC § 267\n\n We begin with IRC § 267. Paragraph 267(a)(2) is entitled “Matching of deduction\n\nand payee income item in the case of expenses and interest.” It provides that if the\n\ntaxpayer and a person to whom the taxpayer is to make a payment are related—that is,\n\n“are persons specified in any of the paragraphs of subsection (b) [of § 267],” id.\n\n§ 267(a)(1) (emphasis added)—then the amount of the payment cannot be deducted until\n\n\n\n\n 5\n\fit is paid or is includible in the recipient’s gross income, see id. § 267(a)(2)2. This\n\nprovision keeps taxpayers from exploiting differences in accounting methods between the\n\npayer (who deducts the payment) and the recipient (who treats the payment as income) to\n\nartificially evade, or at least delay, income taxes. It was enacted “to require related\n\npersons ‘to use the same accounting method with respect to transactions between\n\nthemselves in order to prevent the allowance of a deduction without the corresponding\n\ninclusion in income.’” Tate & Lyle, Inc. v. C.I.R., 87 F.3d 99, 103 (3d Cir. 1996) (quoting\n\nH.R. Supp. Rep. 998-432, Part 2, at 1578, reprinted in 1984 U.S.C.C.A.N. 697, 1205)\n\n(House Report); see also House Report at 1578–79 (“The failure to use the same\n\naccounting method with respect to one transaction involves unwarranted tax benefits,\n\nespecially where payments are delayed for a long period of time, and in fact may never\n\n\n\n\n2\n The pertinent part of § 267(a)(2) states:\n\nIf--\n\n(A) by reason of the method of accounting of the person to whom the payment is to be\nmade, the amount thereof is not (unless paid) includible in the gross income of such\nperson, and\n\n(B) at the close of the taxable year of the taxpayer for which (but for this paragraph) the\namount would be deductible under this chapter, both the taxpayer and the person to\nwhom the payment is to be made are persons specified in any of the paragraphs of\nsubsection (b),\n\nthen any deduction allowable under this chapter in respect of such amount shall be\nallowable as of the day as of which such amount is includible in the gross income of the\nperson to whom the payment is made (or, if later, as of the day on which it would be so\nallowable but for this paragraph). . . .\n\n\n 6\n\fbe paid.”); Metzger Trust v. C.I.R., 76 T.C. 42, 75 (1981) (Congress enacted § 267 “to\n\nprevent the use of differing methods of reporting income for Federal income tax purposes\n\nin order to obtain artificial deductions for interest and business expenses.”). For example,\n\nabsent the limitations of § 267, an accrual-basis taxpayer indebted to a closely related\n\ncash-basis taxpayer could, as interest became due on the debt, report the interest as a\n\ndeduction without making the payment to the cash-basis taxpayer, who would report no\n\nincome at the time and might never report income if payment was arranged to arrive\n\nwhen the cash-basis taxpayer had offsetting losses. See Metzger Trust, 76 T.C. at 75.\n\n Subsection 267(b), entitled “Relationships,” lists a number of relationships\n\ncovered by this provision of the statute, such as “[m]embers of a family” and “[a] grantor\n\nand a fiduciary of any trust,” 26 U.S.C. § 267(b)(1), (4). Relevant here, however, is\n\nsubsection (e), which provides “[s]pecial rules for pass-thru entities.” It states that “an S\n\ncorporation [and] any person who owns (directly or indirectly) any of the stock of such\n\ncorporation” are to be “treated as persons specified in a paragraph of subsection (b).”\n\n26 U.S.C. § 267(e)(1) (emphasis added)3. In other words, an S corporation and a\n\n\n\n3\n § 267(e) states in full:\n\nSpecial rules for pass-thru entities.--\n\n(1) In general.--In the case of any amount paid or incurred by, to, or on behalf of, a pass-\nthru entity, for purposes of applying subsection (a)(2)--\n\n(A) such entity,\n\n(B) in the case of--\n\n\n 7\n\fshareholder of that S corporation are related to one another for purposes of § 267.\n\nBecause the Corporation ESOP owned much—later, all—of the shares of the\n\nCorporation, the Corporation and the Corporation ESOP were related.\n\n Also relevant here is § 267(c), entitled “Constructive ownership of stock.” It\n\nprovides, “For purposes of determining, in applying subsection (b), the ownership of\n\nstock—(1) Stock owned, directly or indirectly, by or for a corporation, partnership, state,\n\nor trust shall be considered as being owned proportionately by or for its shareholders,\n\npartners, or beneficiaries.” 26 U.S.C. § 267(c)(1) (emphasis added). If the stock held by\n\nan ESOP is held in a trust within the meaning of § 267(c)(1), and if the employees\n\nparticipating in the ESOP are beneficiaries of that trust, then the Corporation employees\n\n\n\n(i) a partnership, any person who owns (directly or indirectly) any capital interest or\nprofits interest of such partnership, or\n\n(ii) an S corporation, any person who owns (directly or indirectly) any of the stock of\nsuch corporation,\n\n(C) any person who owns (directly or indirectly) any capital interest or profits interest of\na partnership in which such entity owns (directly or indirectly) any capital interest or\nprofits interest, and\n\n(D) any person related (within the meaning of subsection (b) of this section or section\n707(b)(1)) to a person described in subparagraph (B) or (C),\n\nshall be treated as persons specified in a paragraph of subsection (b). Subparagraph (C)\nshall apply to a transaction only if such transaction is related either to the operations of\nthe partnership described in such subparagraph or to an interest in such partnership.\n(2) Pass-thru entity.ab--For purposes of this section, the term “pass-thru entity” means--\n(A) a partnership, and\n\n(B) an S corporation.\n\n(Emphasis added.)\n\n 8\n\fparticipating in the ESOP must be considered owners of stock of the Corporation under\n\n§ 267(c). In our view, both of those conditions are met. To support that conclusion, we\n\nneed to examine both trust law and ERISA.\n\n B. Trust Law and ERISA\n\n The term trust is not defined in § 267. The Restatement (Third) of Trusts § 2\n\n(2003) (hereinafter Restatement Third) broadly defines the term as “a fiduciary\n\nrelationship with respect to property, arising from a manifestation of intention to create\n\nthat relationship and subjecting the person who holds title to the property to duties to deal\n\nwith it for the benefit of charity or for one or more persons, at least one of whom is not\n\nthe sole trustee.” A trust generally has the following elements: (1) trust property (real or\n\npersonal, tangible or intangible) which the trustee holds subject to the rights of another,\n\n(2) a trustee (an individual or entity charged with holding the trust property for the\n\nbenefit of another), and (3) a beneficiary (the person for whose benefit the trustee holds\n\nthe trust property). See Amy M. Hess et al., Bogert’s Trust and Trustees § 1 (2018)\n\n(Bogert). Essentially the same concept is reflected in the IRC regulations: “Generally\n\nspeaking, an arrangement will be treated as a trust under the Internal Revenue Code if it\n\ncan be shown that the purpose of the arrangement is to vest in trustees responsibility for\n\nthe protection and conservation of property for beneficiaries who cannot share in the\n\ndischarge of this responsibility and, therefore, are not associates in a joint enterprise for\n\nthe conduct of business for profit.” 26 C.F.R. § 301.7701-4(a).\n\n One purpose of ERISA is to protect employees from abuse and mismanagement of\n\nfunds designated for employee-benefit plans. See Massachusetts v. Morash, 490 U.S.\n\n\n 9\n\f107, 112 (1989) (“ERISA was passed . . . to safeguard employees from the abuse and\n\nmismanagement of funds that had been accumulated to finance various types of employee\n\nbenefits.”); Firestone Tire and Rubber Co. v. Bruch, 489 U.S. 101, 113 (1989). To this\n\nend, ERISA establishes minimum standards for benefit plans by “imposing reporting and\n\ndisclosure mandates, participation and vesting requirements, funding standards, and\n\nfiduciary responsibilities for plan administrators. It envisions administrative oversight,\n\nimposes criminal sanctions, and establishes a comprehensive civil enforcement scheme.”\n\nNew York State Conference of Blue Cross & Blue Shield Plans v. Travelers Ins. Co., 514\n\nU.S. 645, 651 (1995) (citations omitted). The safeguard relevant here is that it mandates\n\nthat assets of employee-benefit plans be held in trust. See 29 U.S.C. § 1103(a) (absent\n\nexceptions not relevant here, “all assets of an employee benefit plan shall be held in trust\n\nby one or more trustees”); Restatement Third § 2 cmt. a (“The term ‘trust’ . . . includes\n\n. . . private pension-fund arrangements in trust form.”).\n\n Although ERISA trusts are not governed by the common law of trusts established\n\nby state law, see Shaw v. Delta Air Lines, Inc., 463 U.S. 85, 104 (1983) (“Congress\n\napplied the principle of pre-emption in its broadest sense to foreclose any non-Federal\n\nregulation of employee benefit plans, creating only very limited exceptions . . . .”\n\n(internal quotation marks omitted)), the federal statutory requirements mirror the law\n\nregarding a common-law trust. The trust property consists of all the assets of the\n\nemployee-benefit plan. The trust must have trustees. See 29 U.S.C. § 1103(a). The trust\n\nproperty must be managed for the exclusive benefit of plan participants and beneficiaries.\n\nSee 29 U.S.C. § 1103(c)(1) (absent exceptions not relevant here, “the assets of a plan\n\n\n 10\n\fshall never inure to the benefit of any employer and shall be held for the exclusive\n\npurposes of providing benefits to participants in the plan and their beneficiaries and\n\ndefraying reasonable expenses of administering the plan.”). Indeed, citing the provision\n\nthat “assets of an employee benefit plan shall be held in trust,” 29 U.S.C. § 1103(a), the\n\nSupreme Court observed that “rather than explicitly enumerating all of the powers and\n\nduties of trustees and other fiduciaries, Congress invoked the common law of trust to\n\ndefine the general scope of their authority and responsibility.” Central States, Southeast\n\nand Southwest Areas Pension Fund v. Central Transport, Inc., 472 U.S. 559, 570 (1985);\n\nsee also Firestone, 489 U.S. at 110 (“ERISA abounds with the language and terminology\n\nof trust law.”). Also, although a participant or beneficiary of an ERISA plan cannot seek\n\nrelief under state trust law, see Pilot Life Ins. Co. v. Dedeaux, 481 U.S. 41, 54 (1987)\n\n(ERISA’s civil enforcement remedies are exclusive; remedies under state law are not\n\navailable.), ERISA itself provides robust remedies for violations of fiduciary duties, see\n\nVarity Corp. v. Howe, 516 U.S. 489 (1996) (construing 29 U.S.C. § 1132, entitled “Civil\n\nenforcement”); see also Garratt v. Walker, 164 F.3d 1249, 1253 (10th Cir. 1998) (“The\n\ncivil enforcement mechanism . . . of ERISA, specifically 29 U.S.C. § 1132(a)(1)(B),\n\nallows a plan participant to bring a civil action not only for recovery of plan benefits and\n\nenforcement of plan rights, but also to clarify his rights to future benefits under the terms\n\nof the plan.”).\n\n To be sure, although courts in the ERISA context “are to apply common-law trust\n\nstandards, [they must] bear[] in mind the special nature and purpose of employee benefit\n\nplans.” Varity, 516 U.S. at 506 (internal quotation marks omitted). But that does not\n\n\n 11\n\fchange the essential nature of an ERISA trust as a trust. After all, even common-law\n\ntrusts regularly contain provisions departing from the default common-law standards.\n\nSee Restatement Third § 4 cmt. a(1) (“[M]ost (but not all) of trust law consists of ‘default\n\nrules,’ as opposed to mandatory or restrictive rules . . . .”) Here, Congress authorizes the\n\ncourts to recognize the need for special standards in this context.\n\n We therefore conclude that the Corporation’s ESOP trust is a trust within the\n\nmeaning of § 267 and that the Commissioner properly applied that section to Taxpayers.\n\nTaxpayers’ brief has a jumble of arguments that an ESOP trust is not a “trust” within the\n\nmeaning of the term in IRC § 267. But to the extent that we can understand these\n\narguments, they are unconvincing. We consider them in turn.\n\n Taxpayers argue that an ERISA trust is distinguishable from a common-law trust\n\n(and thus is not covered by § 267) because it protects the interests of “participants,” who\n\nare distinguished from “beneficiaries” in ERISA. But this argument relies on semantics\n\nrather than substance. As previously noted, a beneficiary “is the person for whose benefit\n\nthe trustee holds the trust property.” Bogert § 1. The property in an ERISA trust “shall\n\nbe held for the exclusive purposes of providing benefits to participants in the plan and\n\ntheir beneficiaries and defraying reasonable expenses of administering the plan.”\n\n29 U.S.C. § 1103(c)(1). Both participants in the plan and their beneficiaries satisfy the\n\ndefinition of beneficiary in trust law. All ERISA does is use different terminology to\n\ndescribe two distinct classes of beneficiaries—those employees or former employees who\n\nparticipate in the plan, and the beneficiaries whose interests derive from a participant.\n\nSee 29 U.S.C. § 1002(7) (defining participant), (8) (defining beneficiary as “a person\n\n\n 12\n\fdesignated by a participant, or by terms of an employee benefit plan, who is or may\n\nbecome entitled to a benefit thereunder.”). The common law of trusts allows for different\n\nbeneficiaries “whose interests may be enjoyable concurrently or successively.”\n\nRestatement Third § 44 cmt. a. ERISA’s use of the term participant to describe certain\n\nbeneficiaries does not remove ERISA trusts from the IRC definition of trusts. The term\n\nbeneficiary in § 267 has been interpreted quite broadly, see Wyly v. United States, 662\n\nF.2d 397, 402 (5th Cir. 1981) (taxpayers were beneficiaries of trust even though they\n\nwould receive nothing unless their four children died without issue); and in any event,\n\nthere is no need for such a broad construction here, since every participant easily satisfies\n\nthe common-law definition of beneficiary.\n\n Taxpayers also argue that ERISA trusts are not true trusts because they are called\n\n“qualified trusts.” They cite various provisions of the Internal Revenue Code that do not\n\ntreat ESOPs the same way as they treat other trusts. But all that shows is that an ESOP\n\ntrust is a special type of trust, with special tax consequences for which it “qualifies.” For\n\nexample, such a trust pays no income tax. See 26 U.S.C. § 501(a). The very reason why\n\nthe term trust is preceded by the adjective “qualified” is that special conditions must be\n\nmet for the trust to qualify. That adjective does not signal that the entity is not a true\n\ntrust; the term is not “quasi-trust.” To say that calling the entity a “qualified trust” means\n\nthat it is not a true “trust” would be like saying that an All Star baseball player is not a\n\nreal baseball player. We reject Taxpayers’ suggestion that when the IRC uses the stand-\n\nalone term trust, it intends to exclude ESOP “qualified trusts.”\n\n\n\n\n 13\n\f Taxpayers further contend that an ESOP trust does not satisfy the IRS definition of\n\ntrust in 26 C.F.R. § 301.7701–4(a). They point to the following sentence in the\n\nregulation:\n\n In general, the term “trust” as used in the Internal Revenue Code refers to\n an arrangement created either by a will or by an inter vivos declaration\n whereby trustees take title to property for the purpose of protecting or\n conserving it for the beneficiaries under the ordinary rules applied in\n chancery or probate courts . . . .\n\n26 C.F.R. § 301.7701–4(a). As they see it, an ESOP trust is distinct from the trusts\n\ndescribed in that sentence because it is not created by a will or an inter vivos declaration\n\nand is not “generally subject to the rules of chancery or probate courts.” Aplt. Br. at 20.\n\n But Taxpayers ignore the words “[i]n general” at the beginning of the quoted\n\nsentence; the language that follows those words is clearly intended to be illustrative, not\n\nexhaustive. And they ignore the language three sentences later in the regulation:\n\n“Generally speaking, an arrangement will be treated as a trust under the Internal Revenue\n\nCode if it can be shown that the purpose of the arrangement is to vest in trustees\n\nresponsibility for the protection and conservation of property for beneficiaries who\n\ncannot share in the discharge of this responsibility and, therefore, are not associates in a\n\njoint enterprise for the conduct of business for profit.” 26 C.F.R. § 301.7701–4(a). We\n\nhave already explained how ERISA trusts fulfill those requirements. One should not\n\nmake too much of the statement that trusts generally are created “either by will or by an\n\ninter vivos declaration” (which apparently does not include trusts created by\n\ncorporations). Id. Similar language appears in the Restatement Third. Section 3(1)\n\nstates: “The person who creates a trust is the settlor,” and comment a to the section\n\n\n 14\n\fstates: “The term ‘settlor’ includes a person who creates a trust by will as well as a\n\nperson who creates a trust inter vivos.” But that language does not exclude trusts created\n\nby others, such as corporations. Comment e to § 3 states, “The term ‘person’ includes\n\ncorporations and unincorporated associations.” Cf. Restatement Third § 10 cmt. b. (“A\n\ntrust may also be created by statute.”).\n\n Nor is it material that the terms of an ERISA trust cannot be enforced in chancery\n\nor probate courts. Federal-court remedies provided in ERISA itself reflect the common\n\nlaw of trusts and are an adequate substitute. Besides, the regulation does not say that the\n\nrules governing a trust must be enforced in chancery or probate courts; it just says that\n\nsuch a trust should be subject to the “ordinary rules applied” in those courts. 26 C.F.R.\n\n§ 301.7701–4(a). Also, we think it informative that the regulation notes certain entities\n\n(but notably not ERISA trusts) that are known as trusts but not treated as trusts for\n\npurposes of the IRC because they do not satisfy the requirements of an ordinary trust.\n\nSee id. § 301.7701–4(b) (business trusts), (c) (investment trusts). We are confident that\n\nan ERISA trust satisfies the requirements of the regulation.\n\n Taxpayers also claim support in Revenue Ruling 89-52, which includes the\n\nstatement, “The term ‘trust’ is not a term of art or of fixed content, and its meaning for\n\nthe purposes of employee trusts under section 401(a) of the Code [which sets forth the\n\nrequirements for an employee-benefit trust to qualify for exemption from taxation under\n\n26 U.S.C. § 501(a)] is not necessarily the same as under state law or as under other\n\nsections of the Internal Revenue Code.” See Rev. Rul. 89-52, 1989-1 C.B. 110. But read\n\nin the context of the entire ruling, the point of the sentence is that additional requirements\n\n\n 15\n\fmay be imposed on employee trusts that are not imposed on trusts in general. The next\n\nparagraph of the Ruling makes this clear:\n\n Generally, for a trust to be qualified under section 401(a) of the Code, the\n trust must be a valid trust under the law of the jurisdiction in which the trust\n is located. However, even if the trust is valid under local law, the\n arrangement may be required to satisfy certain other requirements in order\n to be considered a trust for purposes of section 401(a).\n\nRev. Rul. 89-52, 1989-1 C.B. 110 (citation omitted). In the trust at issue in the Ruling,\n\nthe trust was not qualified as an employee trust because the elements of a trust\n\nrelationship were not present. See id. (“[P]articipants [in the trust at issue] have the right\n\nto acquire, hold and dispose of an amount attributable to their account balances in the\n\nplan.”). If anything, the Ruling supports the proposition that a “qualified trust” must be a\n\n“trust” and also meet certain other requirements.4\n\n Taxpayers’ final argument against treating the ESOP trust as a “trust” under § 267\n\n is a puzzling one. It relies on 29 U.S.C. § 1132(d), which states that “[a]n employee\n\n benefit plan may sue or be sued [under ERISA] as an entity” and that “[a]ny money\n\n judgment under [ERISA] against an employee benefit plan shall be enforceable only\n\n against the plan as an entity and shall not be enforceable against any other person unless\n\n\n\n4\n The sentence in the Ruling relied on by Taxpayers cites to Tavannes Watch Co. v.\nCommissioner, 176 F.2d 211, 215 (2d Cir. 1949). In that case the court held that an\nentity was a trust that satisfied the requirements for an employer profit-sharing plan even\nthough it was not formally a trust. We do not think that this opinion helps Taxpayers\neither. The court was dealing with a transitional provision for employee-benefit plans\nthat predated a new statute and did not comply with the new requirements. The court\nruled that the entity should be treated as qualifying during the transition period because\nits essential nature was that of a trust. See id. at 214–16. No such special circumstances\nare present here.\n\n 16\n\fliability against such person is established in his individual capacity under [ERISA].”\n\nThey conclude from this language that “it is the plan which is the legal entity, and not\n\nthe trust which is a part of that plan.” Aplt. Br. at 11. Are they suggesting that the\n\nESOP trust is a nonentity? The essential facts for application of § 267 are that the assets\n\nof the plan are held in a trust and the participants in the plan are beneficiaries of the\n\ntrust. Taxpayers do not explain the relevance of statutory provisions concerning who\n\ncan sue whom. And anyway they admit that trustees of an ESOP trust can be sued,\n\nalthough they assert, without citing authority, that in that event the trustees “are sued as\n\nagents of the plan, not of the trust.” Id.\n\n In addition to arguing that the ESOP trust is not a “trust” within the meaning of\n\n§ 267, Taxpayers raise several objections to applying that section to an ESOP trust on the\n\nground that this would conflict with other provisions of the IRC. First they claim that\n\n§ 267 cannot apply because it is within Subchapter B (of chapter 1 of subtitle A of the\n\nIRC), which covers “Computation of Taxable Income,” whereas ESOPs are formed and\n\ngoverned by the provisions in Subchapter D, which addresses “Deferred Compensation.”\n\nBut they do not point to any requirement in Subchapter D that conflicts with § 267, and\n\nwe perceive no conflict. What is before us to resolve is the taxation of the shareholders\n\nof a Subchapter S corporation, who are subject to Subchapter B. The constructive\n\nownership rules of § 267(c) explicitly apply to transactions with corporations,\n\npartnerships, estates, and trusts, see 26 U.S.C. § 267(c), all of which are also subject to\n\nprovisions in other subchapters of the IRC. See 26 U.S.C. §§ 301 et seq. (Subchapter C-\n\nCorporate Distributions and Adjustments); §§ 641 et seq. (Subchapter J-Estates, Trusts,\n\n\n 17\n\fBeneficiaries, and Decedents); §§ 701 et seq. (Subchapter K-Partners and Partnerships).\n\nThere is no reason to treat a Subchapter D trust differently.\n\n Taxpayers similarly argue that applying the attribution rules in § 267 to trusts like\n\nan ESOP trust would be absurd because ESOP participants would be taxed on their share\n\nof ESOP income, as would beneficiaries of charitable trusts and the like. But § 267 does\n\nnot impose taxes on any person or entity that would not otherwise be taxed. It simply\n\nsays, roughly speaking, that deductions taken by those who are taxed may have to be\n\ndelayed—in particular, an accrual-basis taxpayer cannot deduct an accrued expense\n\npayable to a related person (not necessarily a taxpayer) in a tax year before the tax year in\n\nwhich the related person receives the payment. The tax liability of the related person is\n\nnot affected. Taxpayers’ various references to the nontaxation of ESOPs are therefore\n\nbeside the point. Of course, if a particular provision of Subchapter D explicitly overrides\n\n§ 267 (as Taxpayers contend is true of 26 U.S.C. § 404(a), although we note that the\n\nCommissioner disputes the contention), then the Subchapter D provision may well\n\nprevail. But Taxpayers do not suggest that any provision of Subchapter D addresses their\n\nsituation.\n\n Another of Taxpayers’ statutory arguments relies on 26 U.S.C. § 318, which, in\n\nour view, actually supports the Commissioner. Titled “Constructive ownership of stock,”\n\n§ 318 sets forth attribution rules for transactions by Subchapter C Corporations for such\n\npurposes as determining whether a transaction is treated as a dividend or a sale of stock.\n\nSee Bittker & Eustice, Fed. Income Taxation of Corp. and S’holders, ¶¶ 9.02–9.05, Mar.\n\n2019; S. Rep. 83-1622, at 45, 252-53 (1954) reprinted in 1954; U.S.C.C.A.N 4621, 4676,\n\n\n 18\n\f4890–92. Taxpayers point to § 318(a)(2)(B)(i), which excludes employee-benefit trusts\n\nfrom the § 318 constructive-ownership rules. It states: “Stock owned, directly or\n\nindirectly, by or for a trust (other than an employees’ trust described in section 401(a)\n\nwhich is exempt from tax under section 501(a)) shall be considered as owned by its\n\nbeneficiaries in proportion to the actuarial interest of such beneficiaries in such trust.”\n\n(Emphasis added.) In particular, stock owned by an ESOP trust would not be considered\n\nas owned by its “beneficiaries” (presumably including the participants). Applying that\n\nexception to the present case, Taxpayers contend that the Corporation stock owned by its\n\nESOP should not be considered to be owned by the Corporation employees who\n\nparticipate in the plan.\n\n The argument may look persuasive, but there is a fatal flaw. The language\n\nintroducing this provision is crucial. The relevant language of § 318 is:\n\n (a) General rule. – For purposes of those provisions of this subchapter to which\n the rules contained in this subsection are expressly made applicable\n ...\n (2) Attribution from partnerships, estates, trusts, and corporations. –\n ...\n (B) From trusts. –\n (i) Stock owned, directly or indirectly by or for a trust (other than an\n employees’ trust described in section 401(a) which is exempt from\n tax under section 501(a)) shall be considered as owned by its\n beneficiaries in proportion to the actuarial interest of such\n beneficiaries in such trust.\n\n26 U.S.C. § 318(a)(2)(B)(i) (emphasis added). Consequently, this provision cannot\n\nexclude ESOP trusts from the meaning of trust in § 267 for two independently sufficient\n\nreasons: (1) § 267 is not in the same subchapter as § 318 (which is in Subchapter C), and\n\n(2) § 267 does not even mention § 318, much less make it “expressly . . . applicable.”\n\n\n 19\n\fIndeed, rather than supporting Taxpayers’ argument, § 318 undermines it because the\n\nsection implicitly assumes that an “employees’ trust described in section 401(a)” would\n\nbe considered a “trust” governed by that section if it were not expressly excluded. Thus,\n\nthe failure to explicitly exclude employee trusts in § 267 strongly indicates that such\n\ntrusts are included.\n\n Taxpayers cite to Boise Cascade Corp. v. United States, 329 F.3d 751, 755 (9th\n\nCir. 2003), where § 318 was applied. But their reliance on that decision is misplaced.\n\nThe court applied § 318 to 26 U.S.C. § 302, entitled “Distributions in redemption of\n\nstock.” Section 302, however, satisfies the conditions for application of § 318. It appears\n\nin Subchapter C and it explicitly states that “section 318(a) shall apply in determining the\n\nownership of stock for purposes of this section.” 26 U.S.C. § 302(c)(1); see also\n\n26 U.S.C. 318(b) (cross referencing § 302 as a provision to which § 318(a) applies).\n\n Finally, Taxpayers, rather than analyzing the language of § 267, simply argue that\n\nit is inconsistent with some other provisions of the IRC and that if it were intended to\n\napply to Subchapter S corporation ESOPs, it would have said so explicitly. We are not\n\npersuaded. Applying § 267 to the circumstances here does not contradict any other\n\nprovision of the IRC, and the language of § 267 quite clearly applies in this context.\n\n III. CONCLUSION\n\n We AFFIRM the decision of the Tax Court except that we REMAND for\n\nrecalculation of the correct amounts of the deficiencies.\n\n\n\n\n 20\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Steven M. PETERSEN ; Pauline Petersen, Petitioners - Appellants, v. COMMISSIONER OF INTERNAL REVENUE, Respondent - Appellee. John E. Johnstun; Larue A. Johnstun, Petitioners - Appellants, v. Commissioner of Internal Revenue, Respondent - Appellee.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-15\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 15, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n STEVEN M. PETERSEN; PAULINE\\n PETERSEN,\\n\\n Petitioners - Appellants,\\n\\n v. No. 17-9003\\n\\n COMMISSIONER OF INTERNAL\\n REVENUE,\\n\\n Respondent - Appellee.\\n\\n –––––––––––––––––––––––––––––––––––\\n\\n JOHN E. JOHNSTUN; LARUE A.\\n JOHNSTUN,\\n\\n Petitioners - Appellants,\\n\\n v. No. 17-9004\\n\\n COMMISSIONER OF INTERNAL\\n REVENUE,\\n\\n Respondent - Appellee.\\n _________________________________\\n\\n Appeal from the United States Tax Court\\n (CIR Nos. 015184-14 & 015185-14)\\n _________________________________\\n\\nMichael C. Walch, Kirton McConkie, Lehi, Utah, for Petitioners-Appellants.\\n\\nJennifer M. Rubin (Bruce R. Ellisen, with her on the brief), Department of Justice, Tax\\nDivision, Washington, D.C., for Respondent-Appellee.\\n _________________________________\\n\\fBefore HARTZ, PHILLIPS, and EID, Circuit Judges.\\n _________________________________\\n\\nHARTZ, Circuit Judge.\\n _________________________________\\n\\n This appeal concerns the propriety of the timing of deductions by a Subchapter S\\n\\ncorporation for expenses paid to employees who participate in the corporation’s\\n\\nemployee stock ownership plan (ESOP). Stephen and Pauline Petersen and John and\\n\\nLarue Johnstun (Taxpayers) appeal the decision of the United States Tax Court holding\\n\\nthem liable for past-due taxes arising out of errors in their income-tax returns caused by\\n\\npremature deductions for expenses paid to their Corporation’s ESOP. Taxpayers contend\\n\\nthat the Tax Court misinterpreted the Internal Revenue Code (IRC) and, even if its\\n\\ninterpretation was correct, miscalculated the amounts of alleged deficiencies. The\\n\\nCommissioner agrees that a recalculation is necessary. Exercising jurisdiction under 26\\n\\nU.S.C. § 7482(a), we affirm Taxpayers’ liability but remand for recalculation of the\\n\\ndeficiencies.\\n\\n I. BACKGROUND\\n\\n Taxpayers were majority shareholders in Petersen Inc. (the Corporation), a\\n\\nSubchapter S corporation.1 The disputed liabilities arise from Taxpayers’ income-tax\\n\\nreturns for 2009 (offset in small part by corrections in their favor for their 2010 returns).\\n\\nBecause the Corporation is a Subchapter S corporation, it is a pass-through entity for\\n\\nincome-tax purposes—that is, the Corporation does not itself pay income taxes, but its\\n\\n\\n1\\n Larue Johnstun was not a shareholder in the Corporation, but is a party in this case\\nbecause she filed her income-tax return jointly with her husband John.\\n\\n 2\\n\\ftaxable income, deductions, and losses are passed through to its shareholders. See 26\\n\\nU.S.C. § 1366. For 2009 and most of 2010, Taxpayers owned 79.6% of the\\n\\nCorporation’s stock. The remaining stock was held by the Corporation’s ESOP. In\\n\\nOctober 2010 the ESOP acquired all of Taxpayers’ stock, becoming the 100% owner.\\n\\n The ESOP is an employee-benefit plan governed by the Employee Retirement\\n\\nIncome Security Act (ERISA). Employee-benefit plans that qualify under the detailed\\n\\nrequirements of ERISA, see 26 U.S.C. § 401(a), are exempt from income taxes, see id.\\n\\n§ 501. An ESOP is a type of qualified employee-benefit plan in which an employer\\n\\ncontributes shares of its own stock, or cash to purchase shares of its stock, into a trust,\\n\\nand those shares are allocated to individual employee accounts. See 26 U.S.C. § 4975\\n\\n(e)(7); 29 U.S.C. § 1107(d)(6); Donovan v. Cunningham, 716 F.2d 1455, 1459 (5th Cir.\\n\\n1983). ESOPs provide employee participants the opportunity to gain ownership in shares\\n\\nof the employer corporation. As the Supreme Court has recently noted:\\n\\n “The Congress, in a series of laws [including ERISA] has made clear its\\n interest in encouraging [ESOPs] as a bold and innovative method of\\n strengthening the free private enterprise system which will solve the dual\\n problems of securing capital funds for necessary capital growth and of\\n bringing about stock ownership by all corporate employees.”\\n\\nFifth Third Bancorp v. Dudenhoeffer, 573 U.S. 409, 416 (2014) (quoting Tax Reform Act\\n\\nof 1976, § 803(h), 90 Stat. 1590 (brackets added by Supreme Court)). A corporation’s\\n\\ncontributions paid to its ESOP are tax deductible. See 26 U.S.C. § 404(a)(3); Brindle v.\\n\\nWilmington Trust, N.A., 919 F.3d 763, 769 (4th Cir. 2019). There is no dispute that the\\n\\nCorporation’s ESOP is qualified under ERISA.\\n\\n\\n\\n\\n 3\\n\\f The Corporation is an accrual-basis taxpayer and its ESOP-participant employees\\n\\nare cash-basis taxpayers. As a general rule, an accrual-basis taxpayer may deduct\\n\\nordinary and necessary business expenses in the year when “all events have occurred\\n\\nwhich determine the fact of liability and the amount of such liability can be determined\\n\\nwith reasonable accuracy.” 26 U.S.C. § 461(h)(4). But § 267 of the IRC restricts the\\n\\ntiming of deductibility when the accrued expense is to be paid to a cash-basis taxpayer\\n\\nthat is “related to” the taxpayer. See id. § 267(a)(2). Such expenses cannot be deducted\\n\\nuntil the amount of the payment becomes gross income of the related taxpayer. See id.\\n\\nConsider, for example, an employee on the Corporation’s payroll who is “related to” the\\n\\nCorporation (we will call such employees “related employees”), works during the last\\n\\neight days of the calendar year, but does not receive a paycheck until early the following\\n\\nyear. Although the Corporation accrues the payroll expense in the year that the employee\\n\\nworked the eight days, it must delay the deduction until the next year, when the related\\n\\nemployee receives the payment of wages.\\n\\n Here, the Corporation deducted expenses for ESOP participants in the year that the\\n\\nexpenses accrued even though it did not pay the expenses until the next year. Among\\n\\nthose accrued expenses were wages and salaries (paid every second Friday) and unused\\n\\nvacation time rolled over by employees from one year to the next. If a payday fell early\\n\\nin January 2010, the Corporation could accrue during 2009 up to two weeks of unpaid\\n\\npayroll that the employee would not receive until 2010; and the expense of vacation days\\n\\ncould be accrued many months before the employee used the benefit. These accrued but\\n\\n\\n\\n\\n 4\\n\\funpaid expenses should not have been deducted by the Corporation at the time of accrual\\n\\nif the payment would go to a related employee.\\n\\n The Internal Revenue Service (IRS) audited Taxpayers and decided that\\n\\nemployees of the Corporation who participated in its ESOP were related to the\\n\\nCorporation. It therefore disallowed deductions taken for the 2009 tax year based on\\n\\nexpenses accrued in that year but not paid to the related employees until 2010.\\n\\nTaxpayers unsuccessfully contested the alleged deficiencies in the United States Tax\\n\\nCourt and now appeal to this court.\\n\\n II. DISCUSSION\\n\\n “We review tax court decisions in the same manner and to the same extent as\\n\\ndecisions of the district courts in civil actions tried without a jury. The Tax Court’s legal\\n\\nconclusions are subject to de novo review, and its factual findings can be set aside only if\\n\\nclearly erroneous.” Katz v. C.I.R., 335 F.3d 1121, 1125–26 (10th Cir. 2003) (citation and\\n\\ninternal quotation marks omitted). We proceed to discuss the applicable statutory\\n\\nprovisions and explain why the challenges by Taxpayers are unpersuasive.\\n\\n A. IRC § 267\\n\\n We begin with IRC § 267. Paragraph 267(a)(2) is entitled “Matching of deduction\\n\\nand payee income item in the case of expenses and interest.” It provides that if the\\n\\ntaxpayer and a person to whom the taxpayer is to make a payment are related—that is,\\n\\n“are persons specified in any of the paragraphs of subsection (b) [of § 267],” id.\\n\\n§ 267(a)(1) (emphasis added)—then the amount of the payment cannot be deducted until\\n\\n\\n\\n\\n 5\\n\\fit is paid or is includible in the recipient’s gross income, see id. § 267(a)(2)2. This\\n\\nprovision keeps taxpayers from exploiting differences in accounting methods between the\\n\\npayer (who deducts the payment) and the recipient (who treats the payment as income) to\\n\\nartificially evade, or at least delay, income taxes. It was enacted “to require related\\n\\npersons ‘to use the same accounting method with respect to transactions between\\n\\nthemselves in order to prevent the allowance of a deduction without the corresponding\\n\\ninclusion in income.’” Tate & Lyle, Inc. v. C.I.R., 87 F.3d 99, 103 (3d Cir. 1996) (quoting\\n\\nH.R. Supp. Rep. 998-432, Part 2, at 1578, reprinted in 1984 U.S.C.C.A.N. 697, 1205)\\n\\n(House Report); see also House Report at 1578–79 (“The failure to use the same\\n\\naccounting method with respect to one transaction involves unwarranted tax benefits,\\n\\nespecially where payments are delayed for a long period of time, and in fact may never\\n\\n\\n\\n\\n2\\n The pertinent part of § 267(a)(2) states:\\n\\nIf--\\n\\n(A) by reason of the method of accounting of the person to whom the payment is to be\\nmade, the amount thereof is not (unless paid) includible in the gross income of such\\nperson, and\\n\\n(B) at the close of the taxable year of the taxpayer for which (but for this paragraph) the\\namount would be deductible under this chapter, both the taxpayer and the person to\\nwhom the payment is to be made are persons specified in any of the paragraphs of\\nsubsection (b),\\n\\nthen any deduction allowable under this chapter in respect of such amount shall be\\nallowable as of the day as of which such amount is includible in the gross income of the\\nperson to whom the payment is made (or, if later, as of the day on which it would be so\\nallowable but for this paragraph). . . .\\n\\n\\n 6\\n\\fbe paid.”); Metzger Trust v. C.I.R., 76 T.C. 42, 75 (1981) (Congress enacted § 267 “to\\n\\nprevent the use of differing methods of reporting income for Federal income tax purposes\\n\\nin order to obtain artificial deductions for interest and business expenses.”). For example,\\n\\nabsent the limitations of § 267, an accrual-basis taxpayer indebted to a closely related\\n\\ncash-basis taxpayer could, as interest became due on the debt, report the interest as a\\n\\ndeduction without making the payment to the cash-basis taxpayer, who would report no\\n\\nincome at the time and might never report income if payment was arranged to arrive\\n\\nwhen the cash-basis taxpayer had offsetting losses. See Metzger Trust, 76 T.C. at 75.\\n\\n Subsection 267(b), entitled “Relationships,” lists a number of relationships\\n\\ncovered by this provision of the statute, such as “[m]embers of a family” and “[a] grantor\\n\\nand a fiduciary of any trust,” 26 U.S.C. § 267(b)(1), (4). Relevant here, however, is\\n\\nsubsection (e), which provides “[s]pecial rules for pass-thru entities.” It states that “an S\\n\\ncorporation [and] any person who owns (directly or indirectly) any of the stock of such\\n\\ncorporation” are to be “treated as persons specified in a paragraph of subsection (b).”\\n\\n26 U.S.C. § 267(e)(1) (emphasis added)3. In other words, an S corporation and a\\n\\n\\n\\n3\\n § 267(e) states in full:\\n\\nSpecial rules for pass-thru entities.--\\n\\n(1) In general.--In the case of any amount paid or incurred by, to, or on behalf of, a pass-\\nthru entity, for purposes of applying subsection (a)(2)--\\n\\n(A) such entity,\\n\\n(B) in the case of--\\n\\n\\n 7\\n\\fshareholder of that S corporation are related to one another for purposes of § 267.\\n\\nBecause the Corporation ESOP owned much—later, all—of the shares of the\\n\\nCorporation, the Corporation and the Corporation ESOP were related.\\n\\n Also relevant here is § 267(c), entitled “Constructive ownership of stock.” It\\n\\nprovides, “For purposes of determining, in applying subsection (b), the ownership of\\n\\nstock—(1) Stock owned, directly or indirectly, by or for a corporation, partnership, state,\\n\\nor trust shall be considered as being owned proportionately by or for its shareholders,\\n\\npartners, or beneficiaries.” 26 U.S.C. § 267(c)(1) (emphasis added). If the stock held by\\n\\nan ESOP is held in a trust within the meaning of § 267(c)(1), and if the employees\\n\\nparticipating in the ESOP are beneficiaries of that trust, then the Corporation employees\\n\\n\\n\\n(i) a partnership, any person who owns (directly or indirectly) any capital interest or\\nprofits interest of such partnership, or\\n\\n(ii) an S corporation, any person who owns (directly or indirectly) any of the stock of\\nsuch corporation,\\n\\n(C) any person who owns (directly or indirectly) any capital interest or profits interest of\\na partnership in which such entity owns (directly or indirectly) any capital interest or\\nprofits interest, and\\n\\n(D) any person related (within the meaning of subsection (b) of this section or section\\n707(b)(1)) to a person described in subparagraph (B) or (C),\\n\\nshall be treated as persons specified in a paragraph of subsection (b). Subparagraph (C)\\nshall apply to a transaction only if such transaction is related either to the operations of\\nthe partnership described in such subparagraph or to an interest in such partnership.\\n(2) Pass-thru entity.ab--For purposes of this section, the term “pass-thru entity” means--\\n(A) a partnership, and\\n\\n(B) an S corporation.\\n\\n(Emphasis added.)\\n\\n 8\\n\\fparticipating in the ESOP must be considered owners of stock of the Corporation under\\n\\n§ 267(c). In our view, both of those conditions are met. To support that conclusion, we\\n\\nneed to examine both trust law and ERISA.\\n\\n B. Trust Law and ERISA\\n\\n The term trust is not defined in § 267. The Restatement (Third) of Trusts § 2\\n\\n(2003) (hereinafter Restatement Third) broadly defines the term as “a fiduciary\\n\\nrelationship with respect to property, arising from a manifestation of intention to create\\n\\nthat relationship and subjecting the person who holds title to the property to duties to deal\\n\\nwith it for the benefit of charity or for one or more persons, at least one of whom is not\\n\\nthe sole trustee.” A trust generally has the following elements: (1) trust property (real or\\n\\npersonal, tangible or intangible) which the trustee holds subject to the rights of another,\\n\\n(2) a trustee (an individual or entity charged with holding the trust property for the\\n\\nbenefit of another), and (3) a beneficiary (the person for whose benefit the trustee holds\\n\\nthe trust property). See Amy M. Hess et al., Bogert’s Trust and Trustees § 1 (2018)\\n\\n(Bogert). Essentially the same concept is reflected in the IRC regulations: “Generally\\n\\nspeaking, an arrangement will be treated as a trust under the Internal Revenue Code if it\\n\\ncan be shown that the purpose of the arrangement is to vest in trustees responsibility for\\n\\nthe protection and conservation of property for beneficiaries who cannot share in the\\n\\ndischarge of this responsibility and, therefore, are not associates in a joint enterprise for\\n\\nthe conduct of business for profit.” 26 C.F.R. § 301.7701-4(a).\\n\\n One purpose of ERISA is to protect employees from abuse and mismanagement of\\n\\nfunds designated for employee-benefit plans. See Massachusetts v. Morash, 490 U.S.\\n\\n\\n 9\\n\\f107, 112 (1989) (“ERISA was passed . . . to safeguard employees from the abuse and\\n\\nmismanagement of funds that had been accumulated to finance various types of employee\\n\\nbenefits.”); Firestone Tire and Rubber Co. v. Bruch, 489 U.S. 101, 113 (1989). To this\\n\\nend, ERISA establishes minimum standards for benefit plans by “imposing reporting and\\n\\ndisclosure mandates, participation and vesting requirements, funding standards, and\\n\\nfiduciary responsibilities for plan administrators. It envisions administrative oversight,\\n\\nimposes criminal sanctions, and establishes a comprehensive civil enforcement scheme.”\\n\\nNew York State Conference of Blue Cross & Blue Shield Plans v. Travelers Ins. Co., 514\\n\\nU.S. 645, 651 (1995) (citations omitted). The safeguard relevant here is that it mandates\\n\\nthat assets of employee-benefit plans be held in trust. See 29 U.S.C. § 1103(a) (absent\\n\\nexceptions not relevant here, “all assets of an employee benefit plan shall be held in trust\\n\\nby one or more trustees”); Restatement Third § 2 cmt. a (“The term ‘trust’ . . . includes\\n\\n. . . private pension-fund arrangements in trust form.”).\\n\\n Although ERISA trusts are not governed by the common law of trusts established\\n\\nby state law, see Shaw v. Delta Air Lines, Inc., 463 U.S. 85, 104 (1983) (“Congress\\n\\napplied the principle of pre-emption in its broadest sense to foreclose any non-Federal\\n\\nregulation of employee benefit plans, creating only very limited exceptions . . . .”\\n\\n(internal quotation marks omitted)), the federal statutory requirements mirror the law\\n\\nregarding a common-law trust. The trust property consists of all the assets of the\\n\\nemployee-benefit plan. The trust must have trustees. See 29 U.S.C. § 1103(a). The trust\\n\\nproperty must be managed for the exclusive benefit of plan participants and beneficiaries.\\n\\nSee 29 U.S.C. § 1103(c)(1) (absent exceptions not relevant here, “the assets of a plan\\n\\n\\n 10\\n\\fshall never inure to the benefit of any employer and shall be held for the exclusive\\n\\npurposes of providing benefits to participants in the plan and their beneficiaries and\\n\\ndefraying reasonable expenses of administering the plan.”). Indeed, citing the provision\\n\\nthat “assets of an employee benefit plan shall be held in trust,” 29 U.S.C. § 1103(a), the\\n\\nSupreme Court observed that “rather than explicitly enumerating all of the powers and\\n\\nduties of trustees and other fiduciaries, Congress invoked the common law of trust to\\n\\ndefine the general scope of their authority and responsibility.” Central States, Southeast\\n\\nand Southwest Areas Pension Fund v. Central Transport, Inc., 472 U.S. 559, 570 (1985);\\n\\nsee also Firestone, 489 U.S. at 110 (“ERISA abounds with the language and terminology\\n\\nof trust law.”). Also, although a participant or beneficiary of an ERISA plan cannot seek\\n\\nrelief under state trust law, see Pilot Life Ins. Co. v. Dedeaux, 481 U.S. 41, 54 (1987)\\n\\n(ERISA’s civil enforcement remedies are exclusive; remedies under state law are not\\n\\navailable.), ERISA itself provides robust remedies for violations of fiduciary duties, see\\n\\nVarity Corp. v. Howe, 516 U.S. 489 (1996) (construing 29 U.S.C. § 1132, entitled “Civil\\n\\nenforcement”); see also Garratt v. Walker, 164 F.3d 1249, 1253 (10th Cir. 1998) (“The\\n\\ncivil enforcement mechanism . . . of ERISA, specifically 29 U.S.C. § 1132(a)(1)(B),\\n\\nallows a plan participant to bring a civil action not only for recovery of plan benefits and\\n\\nenforcement of plan rights, but also to clarify his rights to future benefits under the terms\\n\\nof the plan.”).\\n\\n To be sure, although courts in the ERISA context “are to apply common-law trust\\n\\nstandards, [they must] bear[] in mind the special nature and purpose of employee benefit\\n\\nplans.” Varity, 516 U.S. at 506 (internal quotation marks omitted). But that does not\\n\\n\\n 11\\n\\fchange the essential nature of an ERISA trust as a trust. After all, even common-law\\n\\ntrusts regularly contain provisions departing from the default common-law standards.\\n\\nSee Restatement Third § 4 cmt. a(1) (“[M]ost (but not all) of trust law consists of ‘default\\n\\nrules,’ as opposed to mandatory or restrictive rules . . . .”) Here, Congress authorizes the\\n\\ncourts to recognize the need for special standards in this context.\\n\\n We therefore conclude that the Corporation’s ESOP trust is a trust within the\\n\\nmeaning of § 267 and that the Commissioner properly applied that section to Taxpayers.\\n\\nTaxpayers’ brief has a jumble of arguments that an ESOP trust is not a “trust” within the\\n\\nmeaning of the term in IRC § 267. But to the extent that we can understand these\\n\\narguments, they are unconvincing. We consider them in turn.\\n\\n Taxpayers argue that an ERISA trust is distinguishable from a common-law trust\\n\\n(and thus is not covered by § 267) because it protects the interests of “participants,” who\\n\\nare distinguished from “beneficiaries” in ERISA. But this argument relies on semantics\\n\\nrather than substance. As previously noted, a beneficiary “is the person for whose benefit\\n\\nthe trustee holds the trust property.” Bogert § 1. The property in an ERISA trust “shall\\n\\nbe held for the exclusive purposes of providing benefits to participants in the plan and\\n\\ntheir beneficiaries and defraying reasonable expenses of administering the plan.”\\n\\n29 U.S.C. § 1103(c)(1). Both participants in the plan and their beneficiaries satisfy the\\n\\ndefinition of beneficiary in trust law. All ERISA does is use different terminology to\\n\\ndescribe two distinct classes of beneficiaries—those employees or former employees who\\n\\nparticipate in the plan, and the beneficiaries whose interests derive from a participant.\\n\\nSee 29 U.S.C. § 1002(7) (defining participant), (8) (defining beneficiary as “a person\\n\\n\\n 12\\n\\fdesignated by a participant, or by terms of an employee benefit plan, who is or may\\n\\nbecome entitled to a benefit thereunder.”). The common law of trusts allows for different\\n\\nbeneficiaries “whose interests may be enjoyable concurrently or successively.”\\n\\nRestatement Third § 44 cmt. a. ERISA’s use of the term participant to describe certain\\n\\nbeneficiaries does not remove ERISA trusts from the IRC definition of trusts. The term\\n\\nbeneficiary in § 267 has been interpreted quite broadly, see Wyly v. United States, 662\\n\\nF.2d 397, 402 (5th Cir. 1981) (taxpayers were beneficiaries of trust even though they\\n\\nwould receive nothing unless their four children died without issue); and in any event,\\n\\nthere is no need for such a broad construction here, since every participant easily satisfies\\n\\nthe common-law definition of beneficiary.\\n\\n Taxpayers also argue that ERISA trusts are not true trusts because they are called\\n\\n“qualified trusts.” They cite various provisions of the Internal Revenue Code that do not\\n\\ntreat ESOPs the same way as they treat other trusts. But all that shows is that an ESOP\\n\\ntrust is a special type of trust, with special tax consequences for which it “qualifies.” For\\n\\nexample, such a trust pays no income tax. See 26 U.S.C. § 501(a). The very reason why\\n\\nthe term trust is preceded by the adjective “qualified” is that special conditions must be\\n\\nmet for the trust to qualify. That adjective does not signal that the entity is not a true\\n\\ntrust; the term is not “quasi-trust.” To say that calling the entity a “qualified trust” means\\n\\nthat it is not a true “trust” would be like saying that an All Star baseball player is not a\\n\\nreal baseball player. We reject Taxpayers’ suggestion that when the IRC uses the stand-\\n\\nalone term trust, it intends to exclude ESOP “qualified trusts.”\\n\\n\\n\\n\\n 13\\n\\f Taxpayers further contend that an ESOP trust does not satisfy the IRS definition of\\n\\ntrust in 26 C.F.R. § 301.7701–4(a). They point to the following sentence in the\\n\\nregulation:\\n\\n In general, the term “trust” as used in the Internal Revenue Code refers to\\n an arrangement created either by a will or by an inter vivos declaration\\n whereby trustees take title to property for the purpose of protecting or\\n conserving it for the beneficiaries under the ordinary rules applied in\\n chancery or probate courts . . . .\\n\\n26 C.F.R. § 301.7701–4(a). As they see it, an ESOP trust is distinct from the trusts\\n\\ndescribed in that sentence because it is not created by a will or an inter vivos declaration\\n\\nand is not “generally subject to the rules of chancery or probate courts.” Aplt. Br. at 20.\\n\\n But Taxpayers ignore the words “[i]n general” at the beginning of the quoted\\n\\nsentence; the language that follows those words is clearly intended to be illustrative, not\\n\\nexhaustive. And they ignore the language three sentences later in the regulation:\\n\\n“Generally speaking, an arrangement will be treated as a trust under the Internal Revenue\\n\\nCode if it can be shown that the purpose of the arrangement is to vest in trustees\\n\\nresponsibility for the protection and conservation of property for beneficiaries who\\n\\ncannot share in the discharge of this responsibility and, therefore, are not associates in a\\n\\njoint enterprise for the conduct of business for profit.” 26 C.F.R. § 301.7701–4(a). We\\n\\nhave already explained how ERISA trusts fulfill those requirements. One should not\\n\\nmake too much of the statement that trusts generally are created “either by will or by an\\n\\ninter vivos declaration” (which apparently does not include trusts created by\\n\\ncorporations). Id. Similar language appears in the Restatement Third. Section 3(1)\\n\\nstates: “The person who creates a trust is the settlor,” and comment a to the section\\n\\n\\n 14\\n\\fstates: “The term ‘settlor’ includes a person who creates a trust by will as well as a\\n\\nperson who creates a trust inter vivos.” But that language does not exclude trusts created\\n\\nby others, such as corporations. Comment e to § 3 states, “The term ‘person’ includes\\n\\ncorporations and unincorporated associations.” Cf. Restatement Third § 10 cmt. b. (“A\\n\\ntrust may also be created by statute.”).\\n\\n Nor is it material that the terms of an ERISA trust cannot be enforced in chancery\\n\\nor probate courts. Federal-court remedies provided in ERISA itself reflect the common\\n\\nlaw of trusts and are an adequate substitute. Besides, the regulation does not say that the\\n\\nrules governing a trust must be enforced in chancery or probate courts; it just says that\\n\\nsuch a trust should be subject to the “ordinary rules applied” in those courts. 26 C.F.R.\\n\\n§ 301.7701–4(a). Also, we think it informative that the regulation notes certain entities\\n\\n(but notably not ERISA trusts) that are known as trusts but not treated as trusts for\\n\\npurposes of the IRC because they do not satisfy the requirements of an ordinary trust.\\n\\nSee id. § 301.7701–4(b) (business trusts), (c) (investment trusts). We are confident that\\n\\nan ERISA trust satisfies the requirements of the regulation.\\n\\n Taxpayers also claim support in Revenue Ruling 89-52, which includes the\\n\\nstatement, “The term ‘trust’ is not a term of art or of fixed content, and its meaning for\\n\\nthe purposes of employee trusts under section 401(a) of the Code [which sets forth the\\n\\nrequirements for an employee-benefit trust to qualify for exemption from taxation under\\n\\n26 U.S.C. § 501(a)] is not necessarily the same as under state law or as under other\\n\\nsections of the Internal Revenue Code.” See Rev. Rul. 89-52, 1989-1 C.B. 110. But read\\n\\nin the context of the entire ruling, the point of the sentence is that additional requirements\\n\\n\\n 15\\n\\fmay be imposed on employee trusts that are not imposed on trusts in general. The next\\n\\nparagraph of the Ruling makes this clear:\\n\\n Generally, for a trust to be qualified under section 401(a) of the Code, the\\n trust must be a valid trust under the law of the jurisdiction in which the trust\\n is located. However, even if the trust is valid under local law, the\\n arrangement may be required to satisfy certain other requirements in order\\n to be considered a trust for purposes of section 401(a).\\n\\nRev. Rul. 89-52, 1989-1 C.B. 110 (citation omitted). In the trust at issue in the Ruling,\\n\\nthe trust was not qualified as an employee trust because the elements of a trust\\n\\nrelationship were not present. See id. (“[P]articipants [in the trust at issue] have the right\\n\\nto acquire, hold and dispose of an amount attributable to their account balances in the\\n\\nplan.”). If anything, the Ruling supports the proposition that a “qualified trust” must be a\\n\\n“trust” and also meet certain other requirements.4\\n\\n Taxpayers’ final argument against treating the ESOP trust as a “trust” under § 267\\n\\n is a puzzling one. It relies on 29 U.S.C. § 1132(d), which states that “[a]n employee\\n\\n benefit plan may sue or be sued [under ERISA] as an entity” and that “[a]ny money\\n\\n judgment under [ERISA] against an employee benefit plan shall be enforceable only\\n\\n against the plan as an entity and shall not be enforceable against any other person unless\\n\\n\\n\\n4\\n The sentence in the Ruling relied on by Taxpayers cites to Tavannes Watch Co. v.\\nCommissioner, 176 F.2d 211, 215 (2d Cir. 1949). In that case the court held that an\\nentity was a trust that satisfied the requirements for an employer profit-sharing plan even\\nthough it was not formally a trust. We do not think that this opinion helps Taxpayers\\neither. The court was dealing with a transitional provision for employee-benefit plans\\nthat predated a new statute and did not comply with the new requirements. The court\\nruled that the entity should be treated as qualifying during the transition period because\\nits essential nature was that of a trust. See id. at 214–16. No such special circumstances\\nare present here.\\n\\n 16\\n\\fliability against such person is established in his individual capacity under [ERISA].”\\n\\nThey conclude from this language that “it is the plan which is the legal entity, and not\\n\\nthe trust which is a part of that plan.” Aplt. Br. at 11. Are they suggesting that the\\n\\nESOP trust is a nonentity? The essential facts for application of § 267 are that the assets\\n\\nof the plan are held in a trust and the participants in the plan are beneficiaries of the\\n\\ntrust. Taxpayers do not explain the relevance of statutory provisions concerning who\\n\\ncan sue whom. And anyway they admit that trustees of an ESOP trust can be sued,\\n\\nalthough they assert, without citing authority, that in that event the trustees “are sued as\\n\\nagents of the plan, not of the trust.” Id.\\n\\n In addition to arguing that the ESOP trust is not a “trust” within the meaning of\\n\\n§ 267, Taxpayers raise several objections to applying that section to an ESOP trust on the\\n\\nground that this would conflict with other provisions of the IRC. First they claim that\\n\\n§ 267 cannot apply because it is within Subchapter B (of chapter 1 of subtitle A of the\\n\\nIRC), which covers “Computation of Taxable Income,” whereas ESOPs are formed and\\n\\ngoverned by the provisions in Subchapter D, which addresses “Deferred Compensation.”\\n\\nBut they do not point to any requirement in Subchapter D that conflicts with § 267, and\\n\\nwe perceive no conflict. What is before us to resolve is the taxation of the shareholders\\n\\nof a Subchapter S corporation, who are subject to Subchapter B. The constructive\\n\\nownership rules of § 267(c) explicitly apply to transactions with corporations,\\n\\npartnerships, estates, and trusts, see 26 U.S.C. § 267(c), all of which are also subject to\\n\\nprovisions in other subchapters of the IRC. See 26 U.S.C. §§ 301 et seq. (Subchapter C-\\n\\nCorporate Distributions and Adjustments); §§ 641 et seq. (Subchapter J-Estates, Trusts,\\n\\n\\n 17\\n\\fBeneficiaries, and Decedents); §§ 701 et seq. (Subchapter K-Partners and Partnerships).\\n\\nThere is no reason to treat a Subchapter D trust differently.\\n\\n Taxpayers similarly argue that applying the attribution rules in § 267 to trusts like\\n\\nan ESOP trust would be absurd because ESOP participants would be taxed on their share\\n\\nof ESOP income, as would beneficiaries of charitable trusts and the like. But § 267 does\\n\\nnot impose taxes on any person or entity that would not otherwise be taxed. It simply\\n\\nsays, roughly speaking, that deductions taken by those who are taxed may have to be\\n\\ndelayed—in particular, an accrual-basis taxpayer cannot deduct an accrued expense\\n\\npayable to a related person (not necessarily a taxpayer) in a tax year before the tax year in\\n\\nwhich the related person receives the payment. The tax liability of the related person is\\n\\nnot affected. Taxpayers’ various references to the nontaxation of ESOPs are therefore\\n\\nbeside the point. Of course, if a particular provision of Subchapter D explicitly overrides\\n\\n§ 267 (as Taxpayers contend is true of 26 U.S.C. § 404(a), although we note that the\\n\\nCommissioner disputes the contention), then the Subchapter D provision may well\\n\\nprevail. But Taxpayers do not suggest that any provision of Subchapter D addresses their\\n\\nsituation.\\n\\n Another of Taxpayers’ statutory arguments relies on 26 U.S.C. § 318, which, in\\n\\nour view, actually supports the Commissioner. Titled “Constructive ownership of stock,”\\n\\n§ 318 sets forth attribution rules for transactions by Subchapter C Corporations for such\\n\\npurposes as determining whether a transaction is treated as a dividend or a sale of stock.\\n\\nSee Bittker & Eustice, Fed. Income Taxation of Corp. and S’holders, ¶¶ 9.02–9.05, Mar.\\n\\n2019; S. Rep. 83-1622, at 45, 252-53 (1954) reprinted in 1954; U.S.C.C.A.N 4621, 4676,\\n\\n\\n 18\\n\\f4890–92. Taxpayers point to § 318(a)(2)(B)(i), which excludes employee-benefit trusts\\n\\nfrom the § 318 constructive-ownership rules. It states: “Stock owned, directly or\\n\\nindirectly, by or for a trust (other than an employees’ trust described in section 401(a)\\n\\nwhich is exempt from tax under section 501(a)) shall be considered as owned by its\\n\\nbeneficiaries in proportion to the actuarial interest of such beneficiaries in such trust.”\\n\\n(Emphasis added.) In particular, stock owned by an ESOP trust would not be considered\\n\\nas owned by its “beneficiaries” (presumably including the participants). Applying that\\n\\nexception to the present case, Taxpayers contend that the Corporation stock owned by its\\n\\nESOP should not be considered to be owned by the Corporation employees who\\n\\nparticipate in the plan.\\n\\n The argument may look persuasive, but there is a fatal flaw. The language\\n\\nintroducing this provision is crucial. The relevant language of § 318 is:\\n\\n (a) General rule. – For purposes of those provisions of this subchapter to which\\n the rules contained in this subsection are expressly made applicable\\n ...\\n (2) Attribution from partnerships, estates, trusts, and corporations. –\\n ...\\n (B) From trusts. –\\n (i) Stock owned, directly or indirectly by or for a trust (other than an\\n employees’ trust described in section 401(a) which is exempt from\\n tax under section 501(a)) shall be considered as owned by its\\n beneficiaries in proportion to the actuarial interest of such\\n beneficiaries in such trust.\\n\\n26 U.S.C. § 318(a)(2)(B)(i) (emphasis added). Consequently, this provision cannot\\n\\nexclude ESOP trusts from the meaning of trust in § 267 for two independently sufficient\\n\\nreasons: (1) § 267 is not in the same subchapter as § 318 (which is in Subchapter C), and\\n\\n(2) § 267 does not even mention § 318, much less make it “expressly . . . applicable.”\\n\\n\\n 19\\n\\fIndeed, rather than supporting Taxpayers’ argument, § 318 undermines it because the\\n\\nsection implicitly assumes that an “employees’ trust described in section 401(a)” would\\n\\nbe considered a “trust” governed by that section if it were not expressly excluded. Thus,\\n\\nthe failure to explicitly exclude employee trusts in § 267 strongly indicates that such\\n\\ntrusts are included.\\n\\n Taxpayers cite to Boise Cascade Corp. v. United States, 329 F.3d 751, 755 (9th\\n\\nCir. 2003), where § 318 was applied. But their reliance on that decision is misplaced.\\n\\nThe court applied § 318 to 26 U.S.C. § 302, entitled “Distributions in redemption of\\n\\nstock.” Section 302, however, satisfies the conditions for application of § 318. It appears\\n\\nin Subchapter C and it explicitly states that “section 318(a) shall apply in determining the\\n\\nownership of stock for purposes of this section.” 26 U.S.C. § 302(c)(1); see also\\n\\n26 U.S.C. 318(b) (cross referencing § 302 as a provision to which § 318(a) applies).\\n\\n Finally, Taxpayers, rather than analyzing the language of § 267, simply argue that\\n\\nit is inconsistent with some other provisions of the IRC and that if it were intended to\\n\\napply to Subchapter S corporation ESOPs, it would have said so explicitly. We are not\\n\\npersuaded. Applying § 267 to the circumstances here does not contradict any other\\n\\nprovision of the IRC, and the language of § 267 quite clearly applies in this context.\\n\\n III. CONCLUSION\\n\\n We AFFIRM the decision of the Tax Court except that we REMAND for\\n\\nrecalculation of the correct amounts of the deficiencies.\\n\\n\\n\\n\\n 20\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2263,"cells":{"id":{"kind":"number","value":4619690,"string":"4,619,690"},"name":{"kind":"string","value":"Stephen HAMER, Plaintiff - Appellant, v. CITY OF TRINIDAD, Defendant - Appellee. Colorado Municipal League, Amicus Curiae."},"name_abbreviation":{"kind":"string","value":"Hamer v. City of Trinidad"},"decision_date":{"kind":"string","value":"2019-05-15"},"docket_number":{"kind":"string","value":"17-1456"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Briscoe, Bacharach, Carson\", \"parties\": \"\", \"opinions\": [{\"author\": \"CARSON, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 15, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n STEPHEN HAMER,\\n\\n Plaintiff - Appellant,\\n\\n v. No. 17-1456\\n\\n CITY OF TRINIDAD,\\n\\n Defendant - Appellee.\\n\\n ------------------------------\\n\\n COLORADO MUNICIPAL LEAGUE,\\n\\n Amicus Curiae.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:16-CV-02545-NYM-KMT)\\n _________________________________\\n\\nGarrett S. DeReus (Andrew D. Bizer with him on the briefs), Bizer & DeReus, New\\nOrleans, Louisiana, for Plaintiff-Appellant.\\n\\nMarni Nathan Kloster (Nicholas C. Poppe with her on the brief), Nathan Dumm & Mayer\\nP.C., Denver, Colorado, for Defendant-Appellee.\\n\\nWynetta P. Massey and Lindsay M. Rose, Special Counsel for Colorado Municipal\\nLeague, Office of the City Attorney, Colorado Springs, Colorado, and Dianne M.\\nCriswell, Attorney for Colorado Municipal League, Denver, Colorado, filed a brief for\\nAmicus Curiae in support of Defendant-Appellee.\\n _________________________________\\n\\nBefore BRISCOE, BACHARACH, and CARSON, Circuit Judges.\\n _________________________________\\n\\fCARSON, Circuit Judge.\\n _________________________________\\n\\n Title II of the Americans with Disabilities Act (“ADA”) mandates that “no\\n\\nqualified individual with a disability shall, by reason of such disability, be excluded\\n\\nfrom participation in or be denied the benefits of the services, programs, or activities\\n\\nof a public entity, or be subjected to discrimination by any such entity.” 42 U.S.C.\\n\\n§ 12132. Similarly, section 504 of the Rehabilitation Act of 1973 (“RA”) mandates\\n\\nin part that “[n]o otherwise qualified individual with a disability in the United\\n\\nStates . . . shall, solely by reason of her or his disability, be excluded from the\\n\\nparticipation in, be denied the benefits of, or be subjected to discrimination under any\\n\\nprogram or activity receiving Federal financial assistance.” 29 U.S.C. § 794(a).\\n\\n Today we consider exactly when and how a public entity violates these two\\n\\nstatutes.1 The answer, in turn, affects how the applicable statutes of limitations\\n\\noperate. Does a public entity violate Title II and section 504 only when it initially\\n\\nconstructs or creates a non-compliant service, program, or activity? If so, a single\\n\\nstatute of limitations accrues from the day a qualified individual with a disability first\\n\\ndiscovers he or she has been injured by the service, program, or activity. The statute\\n\\nof limitations, in this scenario, would bar any lawsuit brought after the limitations\\n\\nperiod ends.\\n\\n\\n\\n\\n 1\\n Unless we say otherwise, when we use the term “public entity,” we are\\nreferring to both public entities under Title II and programs or activities that receive\\nfederal financial assistance under section 504.\\n 2\\n\\f Or does a public entity violate Title II and section 504 repeatedly until it\\n\\naffirmatively acts to remedy the non-compliant service, program, or activity? In that\\n\\nsituation, a qualified individual’s initial discovery that he or she has been injured\\n\\ndoes not trigger just one statute of limitations that bars any lawsuit brought after the\\n\\nlimitations period ends. Rather, because the public entity commits a new violation\\n\\n(and the qualified individual experiences a new injury) each day that it fails to act,\\n\\nthe statute of limitations effectively functions as a “look-back period,” Burlington N.\\n\\n& Santa Fe Ry. Co. v. Grant, 505 F.3d 1013, 1028–29 (10th Cir. 2007), restricting an\\n\\nindividual’s right to relief to those injuries suffered (1) during the limitations period\\n\\nimmediately prior to filing suit and (2) while the suit is pending.\\n\\n We hold that a public entity violates Title II of the Americans with Disabilities\\n\\nAct and section 504 of the Rehabilitation Act each day that it fails to remedy a non-\\n\\ncompliant service, program, or activity. As a result, the applicable statute of\\n\\nlimitations does not operate in its usual capacity as a firm bar to an untimely lawsuit.\\n\\nInstead, it constrains a plaintiff’s right to relief to injuries sustained during the\\n\\nlimitations period counting backwards from the day he or she files the lawsuit and\\n\\ninjuries sustained while the lawsuit is pending. Because the district court applied a\\n\\ndifferent and incorrect standard, we reverse and remand for further proceedings.\\n\\n I.\\n\\n Plaintiff Stephen Hamer resides in Trinidad, Colorado; is confined to a\\n\\nmotorized wheelchair due to what he characterizes as “severe bilateral ankle\\n\\nproblems”; and, for purposes of this appeal, is a qualified individual with a disability\\n\\n 3\\n\\funder Title II of the ADA and section 504 of the RA. He does not own a car or\\n\\notherwise use public transportation. Instead, he primarily utilizes the City of\\n\\nTrinidad’s public sidewalks to move about in his wheelchair.\\n\\n Plaintiff contends many of the City’s sidewalks and the curb cuts allowing\\n\\naccess onto those sidewalks do not comply with Title II of the ADA and section 504\\n\\nof the RA. Indeed, at a City Council meeting he attended in April 2014, Plaintiff\\n\\ninformed City officials that he had personally counted seventy-nine non-compliant\\n\\nsidewalks and curb cuts throughout the city. Further, at the end of that same month,\\n\\nPlaintiff filed an ADA complaint with the United States Department of Justice\\n\\n(“DOJ”) informing the government about the state of the City’s sidewalks and curb\\n\\ncuts.\\n\\n Plaintiff continued to lodge informal ADA and RA complaints at City Council\\n\\nmeetings over the next few months. And at some point after he lodged his ADA\\n\\ncomplaint with the DOJ, the DOJ audited the City and discovered multiple non-\\n\\ncompliant sidewalks and curb ramps. Apparently in response to Plaintiff’s multiple\\n\\ncomplaints and the results of the DOJ’s audit, City officials actively began repairing\\n\\nand amassing funding to further repair non-compliant sidewalks and curb cuts.\\n\\n Even so, Plaintiff nonetheless filed the present lawsuit against the City on\\n\\nOctober 12, 2016, for violations of Title II of the ADA and section 504 of the RA.\\n\\nLike the complaint he filed with the DOJ, Plaintiff complains of the City’s allegedly\\n\\ndeficient sidewalks and curb cuts. He thus seeks a declaratory judgment that the\\n\\nCity’s sidewalks and curb cuts violate the ADA and RA, injunctive relief requiring\\n\\n 4\\n\\fCity officials to remedy the City’s non-compliant sidewalks and curb cuts, monetary\\n\\ndamages, attorneys’ fees, and costs.\\n\\n The district court granted summary judgment to the City on statute-of-\\n\\nlimitations grounds. The district court first observed that because neither Title II nor\\n\\nsection 504 explicitly provided for a statute of limitations, Colorado’s general two-\\n\\nyear statute of limitations governed Plaintiff’s claims. See E.E.O.C. v. W.H. Braum,\\n\\nInc., 347 F.3d 1192, 1197 (10th Cir. 2003) (“Where Congress creates a cause of\\n\\naction without specifying the time period within which it may be brought, courts may\\n\\ninfer that Congress intended the most analogous state statute of limitations to\\n\\napply.”); see also Colo. Rev. Stat. § 13-80-102 (establishing Colorado’s general two-\\n\\nyear statute of limitations). The district court then noted the general rule in federal\\n\\ncourt that “[t]he statute of limitations begins to run when the plaintiff knows or has\\n\\nreason to know of the existence and cause of the injury which is the basis of his\\n\\naction.” Alexander v. Oklahoma, 382 F.3d 1206, 1215 (10th Cir. 2004) (alteration in\\n\\noriginal) (quoting Indus. Constructors Corp. v. U.S. Bureau of Reclamation, 15 F.3d\\n\\n963, 969 (10th Cir. 1994)). With that rule in mind, the district court concluded that\\n\\nPlaintiff must have “discovered” or “encountered” the City’s non-compliant\\n\\nsidewalks and curb cuts no earlier than October 12, 2014—i.e., two years before the\\n\\nday he filed his lawsuit—to survive summary judgment.\\n\\n The district court determined, however, that Plaintiff’s claims most likely\\n\\naccrued in April 2014 when Plaintiff first raised his concerns about the City’s\\n\\nsidewalks and curb cuts at the City Council meeting and with the DOJ. In any event,\\n\\n 5\\n\\fthe district court also determined that Plaintiff’s claims must have begun to accrue\\n\\n“at the very latest[] in August 2014” when he raised his concerns at a City Council\\n\\nmeeting for the final time. At one of these two points—either April or August\\n\\n2014—Plaintiff was undoubtedly “aware of the nature and extent of the City’s\\n\\ndiscrimination.” Thus, because both of these dates occurred before October 12,\\n\\n2014, the district court held that the two-year statute of limitations barred Plaintiff’s\\n\\nTitle II and section 504 claims.\\n\\n The district court explicitly rejected Plaintiff’s argument that the continuing\\n\\nviolation doctrine could salvage his claims from being untimely. This doctrine\\n\\napplies “‘when the plaintiff’s claim seeks redress for injuries resulting from a series\\n\\nof separate acts that collectively constitute one unlawful act,’ as opposed to ‘conduct\\n\\nthat is a discrete unlawful act.’” Sierra Club v. Okla. Gas & Elec. Co., 816 F.3d 666,\\n\\n672 (10th Cir. 2016) (quoting Shomo v. City of New York, 579 F.3d 176, 181 (2d\\n\\nCir. 2009)). Stated differently, “one violation continues when ‘the conduct as a\\n\\nwhole can be considered as a single course of conduct.’” Id. (quoting Birkelbach v.\\n\\nSEC, 751 F.3d 472, 479 n.7 (7th Cir. 2014)). The utility of the continuing violation\\n\\ndoctrine lies in the fact that as long as one of the separate wrongful acts contributing\\n\\nto the collective conduct “occurs within the filing period,” a court may consider “the\\n\\nentire time period”—including those separate acts falling outside the filing period—\\n\\n“for the purposes of determining liability.” Nat’l R.R. Passenger Corp. v. Morgan,\\n\\n536 U.S. 101, 117 (2002) (emphasis added).\\n\\n\\n\\n 6\\n\\f An important caveat to the continuing violation doctrine, however, is that it “is\\n\\ntriggered ‘by continual unlawful acts, not by continual ill effects from the original\\n\\nviolation.’” Mata v. Anderson, 635 F.3d 1250, 1253 (10th Cir. 2011) (quoting\\n\\nParkhurst v. Lampert, 264 F. App’x 748, 749 (10th Cir. 2008) (unpublished)). And\\n\\naccording to the district court, the allegedly unlawful acts at issue in Plaintiff’s\\n\\nlawsuit—“the construction and alleged lack of maintenance of noncompliant\\n\\nsidewalks and curb cuts”—were discrete, as opposed to continual, acts. As a result,\\n\\nthe district court concluded that “any subsequent injury caused by the City’s failure to\\n\\nremediate these issues” after Plaintiff discovered or encountered them simply amounted\\n\\nto “continual ill effects” of those original violations. Thus, the district court reasoned that\\n\\nthe continuing violation doctrine could not apply to Plaintiff’s claims.\\n\\n The district court also denied Plaintiff’s additional argument that, regardless of\\n\\nwhether the continuing violation doctrine applied, his claims remained timely because the\\n\\nCity “violate[d] both statutes each day” that it failed to remedy its non-compliant\\n\\nsidewalks and curb cuts. In Plaintiff’s opinion, such repeated violations meant that he\\n\\nsuffered injuries each day he was unable to access the sidewalks and curb cuts until the\\n\\nday he filed suit. Under this theory, the two-year statute of limitations did not bar\\n\\nPlaintiff’s suit completely. Instead, he could obtain relief for injuries he suffered after\\n\\nOctober 12, 2014, but not for any injuries he suffered before that day.\\n\\n The district court rejected Plaintiff’s argument, concluding that “it [was]\\n\\ninsufficient to rely solely on the continued inaccessibility of the City’s sidewalks and\\n\\ncurb cuts” for Plaintiff to show he suffered an injury or injuries after October 12, 2014.\\n\\n 7\\n\\fIndeed, the district court again characterized the continued inaccessibility as “continued\\n\\nill effects” of Plaintiff’s original encounters or discoveries of the City’s alleged\\n\\ndiscrimination. The district court therefore reaffirmed its belief that Plaintiff needed to\\n\\npoint to “discrete acts of discrimination he encountered since October 12, 2014,” to\\n\\nsurvive summary judgment. And because Plaintiff had not directed the district court to\\n\\nany evidence suggesting that he encountered or discovered any new, non-compliant\\n\\nsidewalks and curb cuts after October 12, 2014, the district court stood firm in its\\n\\nconclusion that Plaintiff’s Title II and section 504 claims were untimely.\\n\\n Plaintiff now appeals the district court’s ruling that Colorado’s two-year\\n\\nstatute of limitations bars his Title II and section 504 claims.2 Our jurisdiction arises\\n\\nunder 28 U.S.C. § 1291, and our review is de novo. Sierra Club, 816 F.3d at 671.\\n\\nFurther, because Title II and section 504 essentially “involve the same substantive\\n\\nstandards, we analyze them together.” Miller ex rel. S.M. v. Bd. of Educ. of\\n\\nAlbuquerque Pub. Sch., 565 F.3d 1232, 1245 (10th Cir. 2009).\\n\\n II.\\n\\n Before launching into our analysis, we first take a moment to explain in more\\n\\ndetail the difference between the two arguments Plaintiff made in the district court\\n\\nand how that difference affects our ultimate disposition of his appeal.\\n\\n\\n\\n\\n 2\\n Neither party disputes that the applicable limitations period is two years in\\nlength or that it derives from section 13-80-102 of the Colorado Revised Statutes.\\nWe thus assume the same for purposes of this appeal.\\n\\n 8\\n\\f As discussed above, the “continuing violation” doctrine—Plaintiff’s first\\n\\nargument to the district court—tethers conduct from both inside and outside the\\n\\nlimitations period into one single violation that, taken as a whole, satisfies the\\n\\napplicable statute of limitations.3 Sierra Club, 816 F.3d at 672. To help illustrate\\n\\nthis concept, we borrow a useful visual aid from attorney Kyle Graham’s law review\\n\\narticle “The Continuing Violations Doctrine”:\\n\\n\\n\\n\\nThis figure “illustrates how [the continuing violation doctrine] combines otherwise\\n\\ndiscrete occurrences A through E, of which only D and E occurred within the limitations\\n\\nperiod, into a single, timely claim A.” Kyle Graham, The Continuing Violations\\n\\nDoctrine, 43 Gonz. L. Rev. 271, 280 (2008).\\n\\n\\n\\n\\n 3\\n Unlike the typical custom in our circuit, other courts and scholars have\\nsometimes added a word and referred to this doctrine as the “pure” continuing\\nviolation doctrine. See, e.g., White v. Mercury Marine, Div. of Brunswick, Inc., 129\\nF.3d 1428, 1430 (11th Cir. 1997); Kyle Graham, The Continuing Violations\\nDoctrine, 43 Gonz. L. Rev. 271, 283 (2008).\\n\\n 9\\n\\f By contrast, we have referred to the second argument Plaintiff made to the\\n\\ndistrict court as the “repeated violations” doctrine.4 Sierra Club, 816 F.3d at 671.\\n\\nUnlike the continuing violation doctrine, the repeated violations doctrine “divides\\n\\nwhat might otherwise represent a single, time-barred cause of action into several\\n\\nseparate claims, at least one of which accrues within the limitations period prior to\\n\\nsuit.” Graham, supra, at 275 (emphasis added). That division, in turn, “allows\\n\\nrecovery for only that part of the injury the plaintiff suffered during the limitations\\n\\nperiod”; recovery for the part of the injury suffered outside of the limitations period,\\n\\nhowever, remains unavailable. White v. Mercury Marine, Div. of Brunswick, Inc.,\\n\\n129 F.3d 1428, 1430 (11th Cir. 1997); see also, e.g., Figueroa v. D.C. Metro. Police\\n\\nDep’t, 633 F.3d 1129, 1135 (D.C. Cir. 2011) (addressing how repeated violations\\n\\ninfluence the statute of limitations); Provident Mut. Life Ins. Co. of Phila. v. City of\\n\\nAtlanta, 864 F. Supp. 1274, 1284–85 (N.D. Ga. 1994) (describing an instance of the\\n\\nrepeated violations doctrine at work and observing that the plaintiff “may secure only\\n\\nactual damages incurred within the [limitations period] preceding the date upon\\n\\nwhich the action was filed”); Russo Farms, Inc. v. Vineland Bd. of Educ., 675 A.2d\\n\\n1077, 1084 (N.J. 1996) (same). Mr. Graham again provides a useful visual aid that\\n\\nillustrates just how this doctrine operates. As shown below, the repeated violations\\n\\ndoctrine “transforms what would otherwise represent a single, time-barred claim A\\n\\n\\n\\n 4\\n Other courts and scholars have sometimes referred to this doctrine as the\\n“modified” continuing violation doctrine. See, e.g., White, 129 F.3d at 1430;\\nGraham, supra, at 283.\\n 10\\n\\finto a series of fresh claims, identified as claims B, C, D, etc.” Graham, supra, at\\n\\n281.\\n\\n\\n\\n\\n Notably, although Plaintiff argued in the district court that both the continuing\\n\\nviolation doctrine and the repeated violations doctrine could make timely his claims\\n\\nunder Title II of the ADA and section 504 of the RA, on appeal he argues only for\\n\\napplication of the repeated violations doctrine.5 Indeed, in his Opening Brief,\\n\\nPlaintiff argues that\\n\\n [e]ach time [he] was denied access to [the sidewalks and curb cuts], the\\n City of Trinidad committed discrimination within the meaning of the\\n ADA/§504 and a claim for damages arose under the statute. [Plaintiff]\\n experienced recurrent discrimination by the City of Trinidad both inside\\n and outside of the statute of limitations period. Accordingly, [Plaintiff]\\n had some claims that are timely and some that are time barred.\\n\\n\\n\\n\\n 5\\n Plaintiff, in other words, abandoned his continuing violations argument on\\nappeal. We thus do not consider it. See United States v. Yelloweagle, 643 F.3d\\n1275, 1280 (10th Cir. 2011) (“[W]here [an appellant] raises an issue before the\\ndistrict court but does not pursue it on appeal, we ordinarily consider the issue\\nwaived.”).\\n 11\\n\\fPl.’s Opening Br. 7 (emphases added). This language is a clear reference to the\\n\\nrepeated violations doctrine.\\n\\n Although Plaintiff abandons the continuing violation doctrine on appeal, the\\n\\nCity continues to view the case in that context. In the City’s view, the Supreme\\n\\nCourt’s analysis of the continuing violation doctrine in National Railroad Passenger\\n\\nCorp. v. Morgan, 536 U.S. 101 (2002), is controlling. In Morgan, the Supreme Court\\n\\nconsidered how statutes of limitations apply to various claims under Title VII of the\\n\\nCivil Rights Act of 1964. For hostile work environment claims, the Supreme Court\\n\\nheld that “consideration of the entire scope of [the] claim, including behavior alleged\\n\\noutside the statutory time period, is permissible for the purposes of assessing\\n\\nliability, so long as an act contributing to that hostile environment takes place within\\n\\nthe statutory time period.” Id. at 105. The Supreme Court reasoned that hostile work\\n\\nenvironment claims “cannot be said to occur on any particular day” and instead\\n\\n“occur[] over a series of days or perhaps years.” Id. at 115. Because “[s]uch claims\\n\\nare based on the cumulative effect of individual acts,” “[i]t does not matter . . . that\\n\\nsome of the component acts of the hostile work environment fall outside the statutory\\n\\ntime period.” Id. at 115, 117.\\n\\n The City argues that Morgan precludes us from applying the continuing\\n\\nviolation doctrine to Plaintiff’s Title II and section 504 claims because the City\\n\\nsubjected him to only “discrete acts of discrimination” that “did not require proof” of\\n\\nthe cumulative effect of individual acts. Def.’s Resp. Br. 11. Although that\\n\\nargument is correct, it misses the mark insofar as it assails an argument Plaintiff does\\n\\n 12\\n\\fnot make on appeal. Contrary to the way the City frames the issue, Plaintiff does not\\n\\ncontend that he should be able to aggregate separate acts into one single,\\n\\ncomprehensive violation. Instead, he argues that he may recover for injuries he\\n\\nsuffered inside of the limitations period but not for injuries he suffered outside of the\\n\\nlimitations period—that is, he is arguing for application of the repeated violations\\n\\ndoctrine. Morgan, therefore, is inapposite to this appeal because it did not involve\\n\\nthe repeated violations doctrine. Indeed, the language of that case—e.g., that hostile\\n\\nwork environments are made up of “component acts” and “are based on the\\n\\ncumulative effect of individual acts”—makes it clear it was immediately concerned\\n\\nwith interpreting and applying the continuing violation doctrine.\\n\\n The City further relies on our unpublished decision in Rhodes v. Langston\\n\\nUniversity, 462 F. App’x 773 (10th Cir. 2011). In Rhodes, the plaintiff argued that\\n\\nthe alleged Title II and section 504 violations at issue could not “be tied to specific\\n\\ndates as all were on-going events.” Id. at 780. He thus argued that the district court\\n\\nerred in concluding that the applicable two-year statute of limitations barred any of\\n\\nhis claims—including those based on acts that occurred outside of the limitations\\n\\nperiod—because they amounted to “a continuation . . . of related and repetitive\\n\\nunlawful acts or practices” that only concluded within that two-year period. Id.\\n\\nAlthough we ultimately determined that the plaintiff’s argument had no merit, that\\n\\ndetermination does not bear upon the outcome of Plaintiff’s current appeal before us\\n\\ntoday. Like the Supreme Court’s language in Morgan, our language in Rhodes shows\\n\\nthat we were concerned in that case with whether the continuing violation doctrine,\\n\\n 13\\n\\fnot the repeated violations doctrine, applied to Title II and section 504 claims. Thus,\\n\\nthe City’s attempt to analogize Plaintiff’s arguments to Rhodes is equally\\n\\nunconvincing.\\n\\n Finally, the City directs us to Foster v. Morris, 208 F. App’x 174 (3d Cir.\\n\\n2006) (unpublished). In that case, the Third Circuit concluded that the continuing\\n\\nviolation doctrine, not the repeated violations doctrine, does not apply to Title II\\n\\nclaims. See, e.g., id. at 177 (“The continuing violations doctrine is an equitable\\n\\nexception to a strict application of a statute of limitations where the conduct\\n\\ncomplained of consists of a pattern that has only become cognizable as illegal over\\n\\ntime.”); id. at 177–78 (“When a defendant’s conduct is part of a continuing practice,\\n\\nan action is timely so long as the last act evidencing the continuing practice falls\\n\\nwithin the limitations period; in such an instance, the court will grant relief for the\\n\\nearlier related acts that would otherwise be time barred.” (internal quotation marks\\n\\nand alterations omitted)). And interestingly enough, although Foster did not address\\n\\nthe repeated violations doctrine outright, Foster’s underlying reasoning actually\\n\\nsupports—or, at the very least, leaves room open for—that doctrine in the Title II and\\n\\nSection 504 context. Indeed, the Third Circuit concluded that the plaintiff in that\\n\\ncase was “still entitled to recover for any violations that occurred during” the\\n\\nlimitations period even though he could not recover for any violations that occurred\\n\\n\\n\\n\\n 14\\n\\foutside that period. Id. at 178. That logic is perfectly consistent with the repeated\\n\\nviolations doctrine. So no matter how we slice it, Foster cannot help the City.6\\n\\n Because none of the cases the City cites resolve whether the repeated\\n\\nviolations doctrine applies to Plaintiff’s claims under Title II and section 504, we\\n\\nturn to the statutory text to decide this matter of first impression in our circuit.\\n\\n III.\\n\\n We hold that the repeated violations doctrine applies to claims under Title II of\\n\\nthe Americans with Disabilities Act and section 504 of the Rehabilitation Act of\\n\\n1973. As we explain below, a public entity repeatedly violates those two statutes\\n\\neach day that it fails to remedy a non-compliant service, program, or activity.\\n\\nAccordingly, a qualified individual with a disability is excluded from the\\n\\nparticipation in, denied the benefits of, and subjected to discrimination under the\\n\\nservice, program, or activity each day that she is deterred from utilizing it due to its\\n\\nnon-compliance. She stops suffering a daily injury only when the public entity\\n\\n\\n 6\\n Although neither party cites it, we also note that the Fifth Circuit’s decision\\nin Frame v. City of Arlington, 657 F.3d 215 (5th Cir. 2011) (en banc), does not bear\\non Plaintiff’s present appeal. The Frame court held that a single cause of action\\naccrues under Title II and section 504 when the plaintiff “has sufficient information\\nto know that he has been denied the benefits of a service, program, or activity of a\\npublic entity.” Id. at 238. One may think that holding amounts to a rejection of the\\nrepeated violations doctrine. But the question whether the repeated violations\\ndoctrine applies to Title II claims was not before the court in Frame. Indeed, Frame\\nonly considered whether a Title II cause of action accrues when the plaintiff\\ndiscovers he has been injured or when the public entity engaged in the wrongful act\\nthat caused the injury. Id. at 238–40. Nothing in its holding rejects or is inconsistent\\nwith the repeated violations doctrine. Thus, for our purposes today, Frame is of\\nlimited value.\\n\\n 15\\n\\fremedies the non-compliant service, program, or activity or when she no longer\\n\\nevinces an intent to utilize it. The practical effect is that, once the individual sues\\n\\nunder Title II or section 504, the statute of limitations bars recovery only for those\\n\\ninjuries she incurred outside of the limitations period immediately preceding the day\\n\\nof suit; it does not, however, bar recovery for injuries she incurred within that\\n\\nlimitations period or after she files suit.\\n\\n A.\\n\\n Our starting point is the plain language of Title II and section 504. See\\n\\nLevorsen v. Octapharma Plasma, Inc., 828 F.3d 1227, 1231 (10th Cir. 2016). If that\\n\\nlanguage is “clear and unambiguous,” then “our duty is simply to enforce the statute\\n\\nthat Congress has drafted.” United States v. Brown, 529 F.3d 1260, 1264 (10th Cir.\\n\\n2008) (quoting United States v. Ortiz, 427 F.3d 1278, 1282 (10th Cir. 2005)).\\n\\nSignificantly, though, “the meaning of statutory language, plain or not, depends on\\n\\ncontext.” First Nat’l Bank of Durango v. Woods (In re Woods), 743 F.3d 689, 694\\n\\n(10th Cir. 2014) (quoting United States v. Villa, 589 F.3d 1334, 1343 (10th Cir.\\n\\n2009)). We thus need not constrain ourselves to the “language itself” in determining\\n\\nwhether Title II and section 504 clearly and unambiguously convey when and how\\n\\noften a public entity violates these two statutes. Salazar v. Butterball, LLC, 644 F.3d\\n\\n1130, 1137 (10th Cir. 2011) (quoting Robinson v. Shell Oil Co., 519 U.S. 337, 340\\n\\n(1997)). Rather, we may also look to “the specific context in which that language is\\n\\nused” and “the broader context of the statute as a whole.” Id. (quoting Robinson, 519\\n\\nU.S. at 340). Both the text and structure of the statutes guide our decision today.\\n\\n 16\\n\\f Consider first the specific language. Title II mandates that “no qualified\\n\\nindividual with a disability shall, by reason of such disability, be excluded from\\n\\nparticipation in or be denied the benefits of the services, programs, or activities of a\\n\\npublic entity, or be subjected to discrimination by any such entity.” 42 U.S.C.\\n\\n§ 12132. Likewise, section 504 mandates in part that “[n]o otherwise qualified\\n\\nindividual with a disability in the United States . . . shall, solely by reason of her or\\n\\nhis disability, be excluded from the participation in, be denied the benefits of, or be\\n\\nsubjected to discrimination under any program or activity receiving Federal financial\\n\\nassistance.” 29 U.S.C. § 794(a).\\n\\n Obviously, neither of these statutes state outright when or how often a public\\n\\nentity violates them. They simply command that no qualified individual may “be\\n\\nexcluded” from, “be denied” the benefits of, or “be subjected” to discrimination\\n\\nunder a service, program, or activity. With that said, that language is phrased in the\\n\\npresent tense (albeit in the passive voice), which suggests that a qualified individual\\n\\nwho currently experiences discrimination under Title II or section 504 suffers an\\n\\ninjury. And so the same language also suggests that a qualified individual suffers\\n\\nnew discrimination and a new injury each day that she cannot utilize a non-compliant\\n\\nservice, program, or activity—even if the barriers giving rise to her claim were ones\\n\\nshe encountered before. After all, if sidewalks and curb cuts actually do constitute a\\n\\nservice, program, or activity of a public entity—a question that we express no\\n\\nopinion on today—a qualified individual with a disability would still “be excluded”\\n\\nfrom utilizing any given sidewalk or curb cut each day that it remained non-\\n\\n 17\\n\\fcompliant.7 Likewise, that same individual would still “be denied” the benefits of\\n\\nthat sidewalk or curb cut when she encountered it a day ago just as much as when she\\n\\nfirst encountered it a year ago. Cf. Pickern v. Holiday Quality Foods Inc., 293 F.3d\\n\\n1133, 1136 (9th Cir. 2002) (interpreting the phrases “is being subjected to” and “is\\n\\nabout to be subjected to” in the enforcement provision of Title III of the ADA and\\n\\nconcluding that they “make[] clear that either a continuing or a threatened violation\\n\\nof the ADA is an injury within the meaning of the Act”); Scherr v. Marriott Int’l,\\n\\nInc., 703 F.3d 1069, 1075–76 (7th Cir. 2013) (relying on Pickern and concluding the\\n\\nsame).\\n\\n To the extent any real or perceived gaps remain in the statutory text, the\\n\\nSupreme Court’s Title II jurisprudence fills them. In Tennessee v. Lane, 541 U.S.\\n\\n509 (2004), the Supreme Court recognized “that failure to accommodate persons with\\n\\ndisabilities will often have the same practical effect as outright exclusion.” Id. at 531\\n\\n(citing 42 U.S.C. § 12131(2)). Title II therefore imposes “an affirmative obligation\\n\\nto accommodate persons with disabilities.” Id. at 533.8\\n\\n\\n 7\\n We assume only for the purposes of this appeal that sidewalks and curb cuts\\nconstitute a service, program, or activity.\\n 8\\n As Plaintiff points out, numerous regulations implementing the ADA reflect\\nthis principle. See, e.g., 28 C.F.R. § 35.133(a) (“A public entity shall maintain in\\noperable working condition those features of facilities and equipment that are\\nrequired to be readily accessible to and usable by persons with disabilities . . . .”\\n(emphasis added)); id. § 35.150(a) (“A public entity shall operate each service,\\nprogram, or activity so that the service, program, or activity, when viewed in its\\nentirety, is readily accessible to and usable by individuals with disabilities.”\\n(emphasis added)); id. § 35.150(d) (allowing public entities to create a multi-year\\nplan to remove existing barriers); id. § 35.151(b)(1) (“Each facility or part of a\\n 18\\n\\f This “duty to accommodate,” id. at 532, solidifies that Title II (and, by\\n\\nextension, section 504) clearly and unambiguously conveys that a non-compliant\\n\\nservice, program, or activity gives rise to repeated violations.9 Failing to act in the\\n\\nface of an affirmative duty to do so axiomatically gives rise to liability. Cf., e.g.,\\n\\nRestatement (First) of Torts § 284 (1934) (“Negligent conduct may be . . . a failure to\\n\\ndo an act which is necessary for the . . . assistance of another and which the actor is\\n\\nunder a duty to do.”); Restatement (Second) of Torts § 824 (1979) (“The conduct\\n\\nnecessary to make the actor liable for . . . nuisance may consist of . . . a failure to act\\n\\nunder circumstances in which the actor is under a duty to take positive action . . . .”).\\n\\nFurther, if the actor under the affirmative duty keeps failing to act while the\\n\\nunderlying problem remains unremedied, then every day’s inaction amounts to a new\\n\\nviolation. Cf., e.g., Grant, 505 F.3d at 1028 (observing that continuing temporary\\n\\nnuisances “give[] rise over and over to new causes of action” until they are abated\\n\\n(internal quotation marks and alteration omitted)). Thus, even though “adverse\\n\\neffects resulting from” a single, original violation do not trigger the repeated\\n\\n\\nfacility . . . shall . . . be altered in such manner that the altered portion of the facility\\nis readily accessible to and usable by individuals with disabilities.” (emphases\\nadded)).\\n 9\\n In addition to the fact that we analyze Title II and section 504 claims\\ntogether, Miller ex rel. S.M., 565 F.3d at 1245, the language of the RA itself also\\nsuggests an affirmative duty to accommodate. See, e.g., 29 U.S.C. § 701(c)(2)\\n(requiring “the use of accessible formats” for qualified individuals with disabilities);\\nsee also Alexander v. Choate, 469 U.S. 287, 301 (1985) (observing that qualified\\nindividuals with disabilities under the RA are entitled to “meaningful access” and\\n“reasonable accommodations”).\\n\\n 19\\n\\fviolations doctrine when they do not constitute violations in their own right,\\n\\nLedbetter v. Goodyear Tire & Rubber Co., 550 U.S. 618, 628 (2007), overturned on\\n\\nother grounds by The Lilly Ledbetter Fair Pay Act of 2009, Pub. L. No. 111–2, 123\\n\\nStat. 5 (2009), claims under Title II (and section 504 by extension) do not fit that\\n\\nrubric. Rather, a public entity does commit a “new violation” each day that it fails to\\n\\nremedy a non-compliant service, program, or activity. The affirmative, ongoing duty\\n\\nthat Title II and section 504 place upon it mandates as much. Id. 10,11\\n\\n\\n 10\\n The City notes and relies on the Fourth Circuit’s opinion in A Society\\nWithout A Name v. Virginia, 655 F.3d 342 (4th Cir. 2011), which concluded that a\\nclaim under Title II did not trigger the principles of the repeated violations doctrine\\nbecause that claim only gave rise to “the continuing ill effects of [one] original\\nviolation.” Id. at 348–49. We do not find that case persuasive, however, because it\\nnever factored in the mandate that Title II imposes an affirmative duty to\\naccommodate. See id.\\n 11\\n At this point, we believe that an analogy to temporary nuisance claims—one\\nof the “touchstone” instances of the repeated violations doctrine at work, Graham,\\nsupra, at 308—can further illustrate our rationale. A temporary nuisance exists\\n“[w]here the injury from the alleged nuisance . . . is of a continuing or recurring\\ncharacter.” 58 Am. Jur. 2d Nuisances § 221 (2018). “In such a case, every day’s\\ncontinuance is a new nuisance,” id., that “gives rise over and over to new causes of\\naction,” Grant, 505 F.3d at 1028 (internal quotation marks and alteration omitted).\\nThe practical effect is that “a new statute of limitations begins to run . . . after each\\nnew injury,” 58 Am. Jur. 2d Nuisances § 253 (2018) (emphasis added), and the final\\nstatute of limitations accrues only when the temporary nuisance is remedied once and\\nfor all. See Grant, 505 F.3d at 1028. Thus, so long as the temporary nuisance\\ncontinues unabated, a plaintiff bringing suit is effectively doing so on “day one” of a\\nnew limitations period, which enables her to seek damages for past injuries sustained\\n“within the limitations period immediately prior to suit.” Id. (internal quotation\\nmarks omitted).\\n So too here. Each time a qualified individual with a disability is excluded\\nfrom, denied the benefits of, or subjected to discrimination under a service, program,\\nor activity, he suffers an injury under Title II and section 504. For the reasons we\\nexplained above, this injury is not a one-time event; rather, it repeatedly occurs so\\nlong as the service, program, or activity remains non-compliant and the qualified\\n 20\\n\\f The broader statutory context of the ADA and RA bolsters this conclusion.\\n\\nConsider, for example, 42 U.S.C. § 12101, which outlines Congress’s express\\n\\nstatutory purposes for enacting the ADA. There, Congress noted that “the Nation’s\\n\\nproper goals regarding individuals with disabilities are to assure . . . full\\n\\nparticipation . . . for such individuals.” 42 U.S.C. § 12101(a)(7). Congress made a\\n\\nsimilar conclusion earlier when it enacted 29 U.S.C. § 701, which lists the purposes\\n\\nof the RA. In that statute, Congress noted that it hoped to achieve “full inclusion and\\n\\nintegration in society” for individuals with disabilities and that an entity charged with\\n\\ncarrying out the RA should always consider “the principle[] of . . . full participation\\n\\nof the individuals.” 29 U.S.C. § 701(a)(6)(B), (c)(3).\\n\\n Congress’s goals of full participation, inclusion, and integration for qualified\\n\\nindividuals with disabilities are consistent with and suggestive of the repeated\\n\\nviolations doctrine. A qualified individual is not a full participant or fully included\\n\\nin a service, program, or activity if she cannot utilize it in a similar way as persons\\n\\nwithout disabilities, and that does not change simply because she was deterred from\\n\\nutilizing the service, program, or activity many times before. What matters is\\n\\nwhether the individual can fully participate now in the service, program, or activity.\\n\\nThe repeated violations doctrine, in turn, accounts for that reality—and, for that\\n\\nmatter, encourages public entities to comply with their affirmative and ongoing\\n\\n\\n\\nindividual is aware of that and deterred from utilizing it. So when a Title II or\\nsection 504 plaintiff brings suit, he is essentially doing so on the first day of a new\\nlimitations period.\\n 21\\n\\fobligations to accommodate—by giving a qualified individual an avenue for relief\\n\\nany moment that he or she cannot fully participate or is not fully included in a\\n\\nservice, program, or activity.\\n\\n Congress further observed in enacting the ADA that “the continuing existence\\n\\nof unfair and unnecessary discrimination and prejudice denies people with disabilities\\n\\nthe opportunity to compete on an equal basis and to pursue those opportunities for\\n\\nwhich our free society is justifiably famous . . . .” 42 U.S.C. § 12101(a)(8) (emphasis\\n\\nadded). It also noted that it hoped “to address the major areas of discrimination faced\\n\\nday-to-day by people with disabilities.” Id. § 12101(b)(4) (emphasis added).\\n\\nSimilarly, when it previously enacted the RA, Congress had discerned that\\n\\n“individuals with disabilities continually encounter various forms of discrimination.”\\n\\n29 U.S.C. § 701(a)(5) (emphasis added). This language demonstrates that Congress\\n\\nunderstood that a public entity could repeatedly cause a qualified individual with a\\n\\ndisability to suffer an injury from the same service, program, or activity. Certainly,\\n\\nnothing in the text of Title II or section 504 suggests otherwise.\\n\\n The statutory text and the Supreme Court’s pronouncements make one thing\\n\\nclear: Congress did not design the ADA or the RA so that a public entity could\\n\\nforever prevent a qualified individual with a disability from utilizing a service,\\n\\nprogram, or activity. Yet the City argues for that exact result. The City contends\\n\\nthat because Plaintiff filed suit more than two years after he first encountered the\\n\\nallegedly non-compliant sidewalks and curb cuts, the statute of limitations forever\\n\\nbars him from forcing the City to live up to its affirmative duty and correct those\\n\\n 22\\n\\fbarriers. That proposition simply cannot fit within the language, structure, and\\n\\npurpose of the ADA or the RA.\\n\\n In conclusion, based on the plain language of Title II of the ADA and section\\n\\n504 of the RA, Supreme Court jurisprudence interpreting Title II, and Congress’s\\n\\nexpress statutory purposes in enacting the ADA and RA, we hold that Title II and\\n\\nsection 504 clearly and unambiguously require us to acknowledge they are subject to\\n\\nthe repeated violations doctrine.12 Accordingly, each time a qualified individual with\\n\\na disability encounters or “actually become[s] aware of” a non-compliant service,\\n\\nprogram, or activity “and is thereby deterred” from utilizing that service, program, or\\n\\nactivity, he or she suffers discrimination and a cognizable injury. Pickern, 293 F.3d\\n\\n\\n 12\\n Because Title II and section 504 are unambiguous in this regard, we have no\\nreason to consider “the underlying public policy” of either statute. United States v.\\nManning, 526 F.3d 611, 614 (10th Cir. 2008) (quoting United States v. LaHue, 170\\nF.3d 1026, 1028 (10th Cir. 1999)); see also id. (“If the statutory language is clear, our\\nanalysis ordinarily ends.”). Even so, we observe as a side note that applying the\\nrepeated violations doctrine to claims under Title II and section 504 serves the\\ninterests of efficiency. In Title II and section 504 cases, “more than just the rights of\\nthe plaintiff before the court are at stake.” Graham, supra, at 321. Indeed, many\\nother qualified individuals with disabilities also benefit from a ruling favorable to the\\nplaintiff. To use this case as an example, if Plaintiff were to succeed in requiring the\\nCity of Trinidad to further remedy its sidewalks and curb cuts, other individuals who\\nuse wheelchairs would likewise reap the rewards. So if we were not to apply the\\nrepeated violations doctrine to Plaintiff’s claims and therefore forever bar those\\nclaims on statute of limitations grounds, “a substantively similar but timely suit\\nbrought by a different plaintiff”—namely, another qualified individual unable to\\nutilize the City’s sidewalks and curb cuts—“could land in [this Court’s] lap soon\\nthereafter.” Id. Thus, although the clear and unambiguous language of these two\\nstatutes carries the day, we note the inherent good sense in “entertaining the claim[s]\\nat hand” but limiting Title II and section 504 plaintiffs “to only those damages\\nsuffered within the limitations period and, perhaps more important, to injunctive\\nrelief.” Id.\\n\\n 23\\n\\fat 1136–37. So long as the service, program, or activity remains non-compliant, “and\\n\\nso long as a plaintiff is aware of [that] and remains deterred,” the qualified\\n\\nindividual’s injury repeats. Id. at 1137. A defendant, therefore, cannot brandish the\\n\\nstatute of limitations in its usual manner as a shield that fully protects he, she, or it\\n\\nfrom suit. But the defendant can wield the statute of limitations as a sword that\\n\\nchops off damages arising before the limitations period comes into play.\\n\\n B.\\n\\n The City of Trinidad and the Colorado Municipal League (“the League”) as\\n\\namicus curiae both claim that our ruling today will effectively “nullify the statute of\\n\\nlimitations.” Def.’s Resp. Br. 24.\\n\\n Not so for several reasons. For starters, both the City and the League conflate\\n\\nthe repeated violations doctrine and continuing violation doctrine—or at least\\n\\nconflate which of the two Plaintiff is arguing for on appeal—which likely has\\n\\ncontributed to that belief. See supra. But setting that point aside, we “will look\\n\\nbeyond the plain language of a statute only if the result is an absurd application of the\\n\\nlaw.” Brown, 529 F.3d at 1265 (emphasis in original). Observing that the repeated\\n\\nviolations doctrine applies to Title II and section 504 claims, however, does not result\\n\\nin any absurd statute-of-limitations outcomes. Indeed, the statute of limitations still\\n\\nhas an important role to play even when the repeated violations doctrine applies to a\\n\\nclaim. Namely, although the statute of limitations does not bar an untimely lawsuit\\n\\nin its entirety in such an instance, it nonetheless limits the plaintiff’s ability to\\n\\nrecover damages to only those injuries incurred during the limitations period\\n\\n 24\\n\\fimmediately preceding suit (the plaintiff, of course, can also recover damages for any\\n\\ninjuries incurred after filing suit).13 White, 129 F.3d at 1430. By contrast, the\\n\\nrepeated violations doctrine prevents a plaintiff from recovering damages for every\\n\\ninjury she suffered throughout history that relates to the non-compliant service,\\n\\nprogram, or activity.14 Cf., e.g., Foster, 208 F. App’x at 178. If Plaintiff, for\\n\\nexample, had first discovered the City’s non-compliant sidewalks and curb cuts in\\n\\n1996 but still brought suit in 2016, he would not be able to recover damages for\\n\\nevery injury he sustained throughout those twenty years; he would be restricted to\\n\\nthose injuries he suffered after October 12, 2014. This in itself substantially limits a\\n\\npublic entity’s liability under Title II and section 504.\\n\\n\\n 13\\n Theoretically, the statute of limitations could still function as a complete bar\\nto an untimely lawsuit even when the repeated violations doctrine applies. Suppose,\\nfor instance, a plaintiff was first deterred from utilizing a service, program, or\\nactivity in 2009 and tries to bring a lawsuit in 2019 for violations of Title II and\\nsection 504 against the public entity responsible. But also suppose the plaintiff\\nconcedes that in 2016 the public entity completely and entirely remedied the non-\\ncompliant service, program, or activity. Assuming a two-year statute of limitations\\napplies, it would entirely bar the plaintiff’s claims even though the repeated\\nviolations doctrine also applies to his claims. Indeed, the public entity’s last possible\\nrepeated violation (and the plaintiff’s last possible injury) would have occurred in\\n2016 before the remedy went into place, which means that the statute of limitations\\nwould have run at some point in 2018. Accordingly, the 2019 lawsuit would be\\nuntimely because the plaintiff could not point to a violation or injury that occurred in\\nthe two years prior to the day he files suit.\\n We mention this scenario only to illustrate that it is possible. Our immediate\\nconcern, however, is with cases where the public entity has not remedied the non-\\ncompliant service, program, or activity. In such instances, the public entity is still\\ncommitting violations, and the qualified individual with a disability is still suffering\\ninjuries.\\n 14\\n The continuing violation doctrine would allow for such a recovery. See\\nMorgan, 536 U.S. at 105.\\n 25\\n\\f What’s more, Title II and section 504 plaintiffs are able to recover damages\\n\\nonly in the unusual case. Our circuit requires proof of intentional discrimination\\n\\nbefore a plaintiff can recover compensatory damages under section 504, Havens v.\\n\\nColo. Dep’t of Corr., 897 F.3d 1250, 1263 (10th Cir. 2018), and we have suggested\\n\\nthat as much is required under Title II, Moseley v. Bd. of Educ. of Albuquerque Pub.\\n\\nSch., 483 F.3d 689, 693 (10th Cir. 2007) (noting that Tenth Circuit precedent\\n\\nsuggests, but does not explicitly hold, “that proof of intentional discrimination is\\n\\nrequired for compensatory damages under Title II”); see also Miraglia v. Bd. of\\n\\nSupervisors of La. State Museum, 901 F.3d 565, 574 (5th Cir. 2018) (“To recover\\n\\ncompensatory damages for disability discrimination under Title II of the ADA, a\\n\\nplaintiff must also show that the discrimination was intentional.” (emphasis added)\\n\\n(internal quotation marks omitted)). And punitive damages are categorically\\n\\nunavailable for suits under Title II and section 504. Barnes v. Gorman, 536 U.S. 181,\\n\\n189 (2002). So Title II and section 504 plaintiffs are hard-pressed to receive any\\n\\nmonetary damages unless they can prove that a service, program, or activity is\\n\\nintentionally discriminatory toward individuals with disabilities, which is surely the\\n\\nexception rather than the rule. This stands as an additional limitation of a public\\n\\nentity’s liability under Title II and section 504.\\n\\n We agree with the City and the League, though, that the repeated violations\\n\\ndoctrine will manifest itself by keeping public entities on the hook for injunctive\\n\\nrelief as the years go by. After all, if a court grants an injunction requiring a public\\n\\nentity to remedy a program, service, or activity, we have a difficult time seeing just\\n\\n 26\\n\\fhow the court or public entity could divvy that injunction up in a way that limits it to\\n\\ninjuries the plaintiff incurred within the limitations period. See Holmberg v.\\n\\nAmbrecht, 327 U.S. 392, 396 (1946) (observing that equitable relief “eschews\\n\\nmechanical rules”).\\n\\n But the availability of injunctive relief itself does not raise any red flags. As\\n\\nwe described above, when Congress outlined its purposes and goals in enacting the\\n\\nADA and RA, it expressly noted that it sought full participation, inclusion, and\\n\\nintegration in society for individuals with disabilities. By remaining on the hook for\\n\\ninjunctive relief—as its affirmative obligation to accommodate requires—a public\\n\\nentity is incentivized to remedy non-compliant services, programs, or activities in a\\n\\nreasonable yet efficient manner to ensure that full participation. And along those\\n\\nsame lines, Plaintiff makes an excellent point: “public entities . . . have the ultimate\\n\\noption to avoid liability” by “simply mak[ing] their programs, services, and activities\\n\\naccessible for persons with disabilities.” Pl.’s Opening Br. 30; see also Frame v. City\\n\\nof Arlington, 657 F.3d 215, 239 (5th Cir. 2011) (en banc) (“The City may avoid\\n\\nliability whenever it chooses simply by building sidewalks right the first time, or by\\n\\nfixing its original unlawful construction. In other words, the City is not liable\\n\\nforever; it is responsible only for correcting its own mistakes.”).\\n\\n Further, as far as injunctive relief is concerned, we note that a qualified\\n\\nindividual with a disability no longer suffers an injury once he stops “assert[ing] an\\n\\nintent to return to the particular place (or places) where the violations are alleged to\\n\\nbe occurring.” Scherr, 703 F.3d at 1074, 1076; see also Frame, 657 F.3d at 238 (“[A]\\n\\n 27\\n\\fdisabled individual has no standing to challenge an inaccessible sidewalk until he can\\n\\nshow actual, concrete plans to use that sidewalk.” (internal quotation marks\\n\\nomitted)); Barney v. Pulsipher, 143 F.3d 1299, 1306 n.3 (10th Cir. 1998) (“A\\n\\n‘plaintiff cannot maintain a declaratory or injunctive action unless he or she can\\n\\ndemonstrate a good chance of being likewise injured in the future.’” (quoting Facio\\n\\nv. Jones, 929 F.2d 541, 544 (10th Cir. 1991))). Although this implicates Article III\\n\\nstanding, Scherr, 703 F.3d at 1073–76, the practical effect of that lack of intent\\n\\nwould insulate a public entity from a Title II or section 504 lawsuit seeking\\n\\nprospective injunctive relief. To use an extreme example, if Plaintiff were to move\\n\\naway from the City of Trinidad and had no intent to return, he would no longer be\\n\\nsuffering any injury—and, consequently, would lack standing to bring a suit for\\n\\nprospective injunctive relief—regardless of whether the City remedied the sidewalks\\n\\nand curb cuts that allegedly injured him in the past. And even if a qualified\\n\\nindividual still suffers an injury after many years, we note that at some point the\\n\\ndoctrine of laches may come into play. See SCA Hygiene Prods. Aktiebolag v. First\\n\\nQuality Baby Prods., LLC, 137 S. Ct. 954, 960 (2017) (“Laches is ‘a defense\\n\\ndeveloped by courts of equity’ to protect defendants against ‘unreasonable,\\n\\nprejudicial delay in commencing suit.’” (quoting Petrella v. Metro-Goldwyn-Mayer,\\n\\nInc., 572 U.S. 663, 667, 678 (2014)). This further cuts against the City’s and the\\n\\nLeague’s arguments that public entities will be exposed to unlimited liability.\\n\\n As a final note, we are not unsympathetic to the City’s and the League’s\\n\\narguments that public entities are constrained by limited budgets that do not easily\\n\\n 28\\n\\flend themselves to the constant ability to remedy ADA and RA issues.15 But again,\\n\\nliability for monetary damages is infrequent, which significantly softens the impact\\n\\nof our ruling today. See supra. And if a public entity truly is not liable, or if that\\n\\nentity has already taken significant steps to remedy or can establish that it has multi-\\n\\nyear plans in place to remedy a non-compliant service, program, or activity—as the\\n\\nCity has apparently done in this case—a factfinder will be able to ferret that out when\\n\\ndeciding the merits of any given case. See, e.g., Rife v. Okla. Dep’t of Pub. Safety,\\n\\n854 F.3d 637, 643 (10th Cir. 2017) (observing that factfinders find facts weighing on\\n\\nliability). Indeed, at least two other circuits have endorsed either the repeated\\n\\nviolations doctrine or continuing violation doctrine in the context of ADA Title III\\n\\nclaims, but neither the City nor the League have directed us to any evidence\\n\\nsuggesting that places of public accommodation located in those circuits have faced\\n\\nsignificant hardship by the courts’ respective applications of the doctrines. See\\n\\nPickern, 293 F.3d at 1136–37; Scherr, 703 F.3d at 1075–76.\\n\\n Thus, the City’s and the League’s concerns are unsubstantiated.\\n\\n IV.\\n\\n The district court did not recognize the impact of the repeated violations\\n\\ndoctrine on Plaintiff’s claims under Title II of the ADA and section 504 of the RA.\\n\\n\\n 15\\n The City contends that adopting the repeated violations doctrine will cause\\nthis inability to remedy ADA and RA issues, but it is mistaken. Even without the\\nrepeated violations doctrine, qualified individuals with disabilities who have\\nencountered the City’s non-compliant services, programs, or activities within the past\\ntwo years could just as easily bring lawsuits against the City. So the danger about\\nwhich the City complains exists even under their own interpretation of the law.\\n 29\\n\\fInstead, it concluded that Plaintiff could not “rely solely on the continued\\n\\ninaccessibility of the City’s sidewalks and curb cuts” to survive dismissal under\\n\\nColorado’s two-year statute of limitations.\\n\\n This was error. Because the district court applied an incorrect standard, it\\n\\ncould not determine under the proper framework how the two-year statute of\\n\\nlimitations affected Plaintiff’s claims. As a court of review, we will not decide that\\n\\ninquiry for the first time on appeal. Pignanelli v. Pueblo Sch. Dist. No. 60, 540 F.3d\\n\\n1213, 1218 (10th Cir. 2008). We thus remand the case to the district court to decide\\n\\nin the first instance under the framework set forth in this opinion which of Plaintiff’s\\n\\ninjuries he may seek relief for and which of those he may not. In so doing, the\\n\\ndistrict court will necessarily need to determine which of the City’s sidewalks and\\n\\ncurb cuts Plaintiff has actually been deterred from utilizing.16\\n\\n For the reasons set forth above, we REVERSE and REMAND for further\\n\\nproceedings consistent with this opinion.\\n\\n\\n\\n\\n 16\\n In issuing these instructions on remand, we emphasize once again that we\\ntake no stance on the question whether sidewalks and curb cuts qualify as a service,\\nprogram, or activity of a public entity. We also issue these instructions cognizant of\\nthe fact that the district court assumed—much like we did—that sidewalks and curb\\ncuts qualify as a service, program, or activity of a public entity so that it could reach\\nthe “narrower” and “dispositive” statute of limitations question. For those reasons,\\nthe district court may now find it necessary to definitively decide on remand whether\\nsidewalks and curb cuts qualify as a service, program, or activity of a public entity,\\nand it should not read anything in this opinion as preventing it from doing so.\\n 30\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4396943/\", \"author_raw\": \"CARSON, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"BRISCOE"},"judge2":{"kind":"string","value":"BACHARACH"},"judge3":{"kind":"string","value":"CARSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4619690/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Stephen HAMER, Plaintiff - Appellant, v. CITY OF TRINIDAD, Defendant - Appellee. Colorado Municipal League, Amicus Curiae.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-15\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 15, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\n STEPHEN HAMER,\n\n Plaintiff - Appellant,\n\n v. No. 17-1456\n\n CITY OF TRINIDAD,\n\n Defendant - Appellee.\n\n ------------------------------\n\n COLORADO MUNICIPAL LEAGUE,\n\n Amicus Curiae.\n _________________________________\n\n Appeal from the United States District Court\n for the District of Colorado\n (D.C. No. 1:16-CV-02545-NYM-KMT)\n _________________________________\n\nGarrett S. DeReus (Andrew D. Bizer with him on the briefs), Bizer & DeReus, New\nOrleans, Louisiana, for Plaintiff-Appellant.\n\nMarni Nathan Kloster (Nicholas C. Poppe with her on the brief), Nathan Dumm & Mayer\nP.C., Denver, Colorado, for Defendant-Appellee.\n\nWynetta P. Massey and Lindsay M. Rose, Special Counsel for Colorado Municipal\nLeague, Office of the City Attorney, Colorado Springs, Colorado, and Dianne M.\nCriswell, Attorney for Colorado Municipal League, Denver, Colorado, filed a brief for\nAmicus Curiae in support of Defendant-Appellee.\n _________________________________\n\nBefore BRISCOE, BACHARACH, and CARSON, Circuit Judges.\n _________________________________\n\fCARSON, Circuit Judge.\n _________________________________\n\n Title II of the Americans with Disabilities Act (“ADA”) mandates that “no\n\nqualified individual with a disability shall, by reason of such disability, be excluded\n\nfrom participation in or be denied the benefits of the services, programs, or activities\n\nof a public entity, or be subjected to discrimination by any such entity.” 42 U.S.C.\n\n§ 12132. Similarly, section 504 of the Rehabilitation Act of 1973 (“RA”) mandates\n\nin part that “[n]o otherwise qualified individual with a disability in the United\n\nStates . . . shall, solely by reason of her or his disability, be excluded from the\n\nparticipation in, be denied the benefits of, or be subjected to discrimination under any\n\nprogram or activity receiving Federal financial assistance.” 29 U.S.C. § 794(a).\n\n Today we consider exactly when and how a public entity violates these two\n\nstatutes.1 The answer, in turn, affects how the applicable statutes of limitations\n\noperate. Does a public entity violate Title II and section 504 only when it initially\n\nconstructs or creates a non-compliant service, program, or activity? If so, a single\n\nstatute of limitations accrues from the day a qualified individual with a disability first\n\ndiscovers he or she has been injured by the service, program, or activity. The statute\n\nof limitations, in this scenario, would bar any lawsuit brought after the limitations\n\nperiod ends.\n\n\n\n\n 1\n Unless we say otherwise, when we use the term “public entity,” we are\nreferring to both public entities under Title II and programs or activities that receive\nfederal financial assistance under section 504.\n 2\n\f Or does a public entity violate Title II and section 504 repeatedly until it\n\naffirmatively acts to remedy the non-compliant service, program, or activity? In that\n\nsituation, a qualified individual’s initial discovery that he or she has been injured\n\ndoes not trigger just one statute of limitations that bars any lawsuit brought after the\n\nlimitations period ends. Rather, because the public entity commits a new violation\n\n(and the qualified individual experiences a new injury) each day that it fails to act,\n\nthe statute of limitations effectively functions as a “look-back period,” Burlington N.\n\n& Santa Fe Ry. Co. v. Grant, 505 F.3d 1013, 1028–29 (10th Cir. 2007), restricting an\n\nindividual’s right to relief to those injuries suffered (1) during the limitations period\n\nimmediately prior to filing suit and (2) while the suit is pending.\n\n We hold that a public entity violates Title II of the Americans with Disabilities\n\nAct and section 504 of the Rehabilitation Act each day that it fails to remedy a non-\n\ncompliant service, program, or activity. As a result, the applicable statute of\n\nlimitations does not operate in its usual capacity as a firm bar to an untimely lawsuit.\n\nInstead, it constrains a plaintiff’s right to relief to injuries sustained during the\n\nlimitations period counting backwards from the day he or she files the lawsuit and\n\ninjuries sustained while the lawsuit is pending. Because the district court applied a\n\ndifferent and incorrect standard, we reverse and remand for further proceedings.\n\n I.\n\n Plaintiff Stephen Hamer resides in Trinidad, Colorado; is confined to a\n\nmotorized wheelchair due to what he characterizes as “severe bilateral ankle\n\nproblems”; and, for purposes of this appeal, is a qualified individual with a disability\n\n 3\n\funder Title II of the ADA and section 504 of the RA. He does not own a car or\n\notherwise use public transportation. Instead, he primarily utilizes the City of\n\nTrinidad’s public sidewalks to move about in his wheelchair.\n\n Plaintiff contends many of the City’s sidewalks and the curb cuts allowing\n\naccess onto those sidewalks do not comply with Title II of the ADA and section 504\n\nof the RA. Indeed, at a City Council meeting he attended in April 2014, Plaintiff\n\ninformed City officials that he had personally counted seventy-nine non-compliant\n\nsidewalks and curb cuts throughout the city. Further, at the end of that same month,\n\nPlaintiff filed an ADA complaint with the United States Department of Justice\n\n(“DOJ”) informing the government about the state of the City’s sidewalks and curb\n\ncuts.\n\n Plaintiff continued to lodge informal ADA and RA complaints at City Council\n\nmeetings over the next few months. And at some point after he lodged his ADA\n\ncomplaint with the DOJ, the DOJ audited the City and discovered multiple non-\n\ncompliant sidewalks and curb ramps. Apparently in response to Plaintiff’s multiple\n\ncomplaints and the results of the DOJ’s audit, City officials actively began repairing\n\nand amassing funding to further repair non-compliant sidewalks and curb cuts.\n\n Even so, Plaintiff nonetheless filed the present lawsuit against the City on\n\nOctober 12, 2016, for violations of Title II of the ADA and section 504 of the RA.\n\nLike the complaint he filed with the DOJ, Plaintiff complains of the City’s allegedly\n\ndeficient sidewalks and curb cuts. He thus seeks a declaratory judgment that the\n\nCity’s sidewalks and curb cuts violate the ADA and RA, injunctive relief requiring\n\n 4\n\fCity officials to remedy the City’s non-compliant sidewalks and curb cuts, monetary\n\ndamages, attorneys’ fees, and costs.\n\n The district court granted summary judgment to the City on statute-of-\n\nlimitations grounds. The district court first observed that because neither Title II nor\n\nsection 504 explicitly provided for a statute of limitations, Colorado’s general two-\n\nyear statute of limitations governed Plaintiff’s claims. See E.E.O.C. v. W.H. Braum,\n\nInc., 347 F.3d 1192, 1197 (10th Cir. 2003) (“Where Congress creates a cause of\n\naction without specifying the time period within which it may be brought, courts may\n\ninfer that Congress intended the most analogous state statute of limitations to\n\napply.”); see also Colo. Rev. Stat. § 13-80-102 (establishing Colorado’s general two-\n\nyear statute of limitations). The district court then noted the general rule in federal\n\ncourt that “[t]he statute of limitations begins to run when the plaintiff knows or has\n\nreason to know of the existence and cause of the injury which is the basis of his\n\naction.” Alexander v. Oklahoma, 382 F.3d 1206, 1215 (10th Cir. 2004) (alteration in\n\noriginal) (quoting Indus. Constructors Corp. v. U.S. Bureau of Reclamation, 15 F.3d\n\n963, 969 (10th Cir. 1994)). With that rule in mind, the district court concluded that\n\nPlaintiff must have “discovered” or “encountered” the City’s non-compliant\n\nsidewalks and curb cuts no earlier than October 12, 2014—i.e., two years before the\n\nday he filed his lawsuit—to survive summary judgment.\n\n The district court determined, however, that Plaintiff’s claims most likely\n\naccrued in April 2014 when Plaintiff first raised his concerns about the City’s\n\nsidewalks and curb cuts at the City Council meeting and with the DOJ. In any event,\n\n 5\n\fthe district court also determined that Plaintiff’s claims must have begun to accrue\n\n“at the very latest[] in August 2014” when he raised his concerns at a City Council\n\nmeeting for the final time. At one of these two points—either April or August\n\n2014—Plaintiff was undoubtedly “aware of the nature and extent of the City’s\n\ndiscrimination.” Thus, because both of these dates occurred before October 12,\n\n2014, the district court held that the two-year statute of limitations barred Plaintiff’s\n\nTitle II and section 504 claims.\n\n The district court explicitly rejected Plaintiff’s argument that the continuing\n\nviolation doctrine could salvage his claims from being untimely. This doctrine\n\napplies “‘when the plaintiff’s claim seeks redress for injuries resulting from a series\n\nof separate acts that collectively constitute one unlawful act,’ as opposed to ‘conduct\n\nthat is a discrete unlawful act.’” Sierra Club v. Okla. Gas & Elec. Co., 816 F.3d 666,\n\n672 (10th Cir. 2016) (quoting Shomo v. City of New York, 579 F.3d 176, 181 (2d\n\nCir. 2009)). Stated differently, “one violation continues when ‘the conduct as a\n\nwhole can be considered as a single course of conduct.’” Id. (quoting Birkelbach v.\n\nSEC, 751 F.3d 472, 479 n.7 (7th Cir. 2014)). The utility of the continuing violation\n\ndoctrine lies in the fact that as long as one of the separate wrongful acts contributing\n\nto the collective conduct “occurs within the filing period,” a court may consider “the\n\nentire time period”—including those separate acts falling outside the filing period—\n\n“for the purposes of determining liability.” Nat’l R.R. Passenger Corp. v. Morgan,\n\n536 U.S. 101, 117 (2002) (emphasis added).\n\n\n\n 6\n\f An important caveat to the continuing violation doctrine, however, is that it “is\n\ntriggered ‘by continual unlawful acts, not by continual ill effects from the original\n\nviolation.’” Mata v. Anderson, 635 F.3d 1250, 1253 (10th Cir. 2011) (quoting\n\nParkhurst v. Lampert, 264 F. App’x 748, 749 (10th Cir. 2008) (unpublished)). And\n\naccording to the district court, the allegedly unlawful acts at issue in Plaintiff’s\n\nlawsuit—“the construction and alleged lack of maintenance of noncompliant\n\nsidewalks and curb cuts”—were discrete, as opposed to continual, acts. As a result,\n\nthe district court concluded that “any subsequent injury caused by the City’s failure to\n\nremediate these issues” after Plaintiff discovered or encountered them simply amounted\n\nto “continual ill effects” of those original violations. Thus, the district court reasoned that\n\nthe continuing violation doctrine could not apply to Plaintiff’s claims.\n\n The district court also denied Plaintiff’s additional argument that, regardless of\n\nwhether the continuing violation doctrine applied, his claims remained timely because the\n\nCity “violate[d] both statutes each day” that it failed to remedy its non-compliant\n\nsidewalks and curb cuts. In Plaintiff’s opinion, such repeated violations meant that he\n\nsuffered injuries each day he was unable to access the sidewalks and curb cuts until the\n\nday he filed suit. Under this theory, the two-year statute of limitations did not bar\n\nPlaintiff’s suit completely. Instead, he could obtain relief for injuries he suffered after\n\nOctober 12, 2014, but not for any injuries he suffered before that day.\n\n The district court rejected Plaintiff’s argument, concluding that “it [was]\n\ninsufficient to rely solely on the continued inaccessibility of the City’s sidewalks and\n\ncurb cuts” for Plaintiff to show he suffered an injury or injuries after October 12, 2014.\n\n 7\n\fIndeed, the district court again characterized the continued inaccessibility as “continued\n\nill effects” of Plaintiff’s original encounters or discoveries of the City’s alleged\n\ndiscrimination. The district court therefore reaffirmed its belief that Plaintiff needed to\n\npoint to “discrete acts of discrimination he encountered since October 12, 2014,” to\n\nsurvive summary judgment. And because Plaintiff had not directed the district court to\n\nany evidence suggesting that he encountered or discovered any new, non-compliant\n\nsidewalks and curb cuts after October 12, 2014, the district court stood firm in its\n\nconclusion that Plaintiff’s Title II and section 504 claims were untimely.\n\n Plaintiff now appeals the district court’s ruling that Colorado’s two-year\n\nstatute of limitations bars his Title II and section 504 claims.2 Our jurisdiction arises\n\nunder 28 U.S.C. § 1291, and our review is de novo. Sierra Club, 816 F.3d at 671.\n\nFurther, because Title II and section 504 essentially “involve the same substantive\n\nstandards, we analyze them together.” Miller ex rel. S.M. v. Bd. of Educ. of\n\nAlbuquerque Pub. Sch., 565 F.3d 1232, 1245 (10th Cir. 2009).\n\n II.\n\n Before launching into our analysis, we first take a moment to explain in more\n\ndetail the difference between the two arguments Plaintiff made in the district court\n\nand how that difference affects our ultimate disposition of his appeal.\n\n\n\n\n 2\n Neither party disputes that the applicable limitations period is two years in\nlength or that it derives from section 13-80-102 of the Colorado Revised Statutes.\nWe thus assume the same for purposes of this appeal.\n\n 8\n\f As discussed above, the “continuing violation” doctrine—Plaintiff’s first\n\nargument to the district court—tethers conduct from both inside and outside the\n\nlimitations period into one single violation that, taken as a whole, satisfies the\n\napplicable statute of limitations.3 Sierra Club, 816 F.3d at 672. To help illustrate\n\nthis concept, we borrow a useful visual aid from attorney Kyle Graham’s law review\n\narticle “The Continuing Violations Doctrine”:\n\n\n\n\nThis figure “illustrates how [the continuing violation doctrine] combines otherwise\n\ndiscrete occurrences A through E, of which only D and E occurred within the limitations\n\nperiod, into a single, timely claim A.” Kyle Graham, The Continuing Violations\n\nDoctrine, 43 Gonz. L. Rev. 271, 280 (2008).\n\n\n\n\n 3\n Unlike the typical custom in our circuit, other courts and scholars have\nsometimes added a word and referred to this doctrine as the “pure” continuing\nviolation doctrine. See, e.g., White v. Mercury Marine, Div. of Brunswick, Inc., 129\nF.3d 1428, 1430 (11th Cir. 1997); Kyle Graham, The Continuing Violations\nDoctrine, 43 Gonz. L. Rev. 271, 283 (2008).\n\n 9\n\f By contrast, we have referred to the second argument Plaintiff made to the\n\ndistrict court as the “repeated violations” doctrine.4 Sierra Club, 816 F.3d at 671.\n\nUnlike the continuing violation doctrine, the repeated violations doctrine “divides\n\nwhat might otherwise represent a single, time-barred cause of action into several\n\nseparate claims, at least one of which accrues within the limitations period prior to\n\nsuit.” Graham, supra, at 275 (emphasis added). That division, in turn, “allows\n\nrecovery for only that part of the injury the plaintiff suffered during the limitations\n\nperiod”; recovery for the part of the injury suffered outside of the limitations period,\n\nhowever, remains unavailable. White v. Mercury Marine, Div. of Brunswick, Inc.,\n\n129 F.3d 1428, 1430 (11th Cir. 1997); see also, e.g., Figueroa v. D.C. Metro. Police\n\nDep’t, 633 F.3d 1129, 1135 (D.C. Cir. 2011) (addressing how repeated violations\n\ninfluence the statute of limitations); Provident Mut. Life Ins. Co. of Phila. v. City of\n\nAtlanta, 864 F. Supp. 1274, 1284–85 (N.D. Ga. 1994) (describing an instance of the\n\nrepeated violations doctrine at work and observing that the plaintiff “may secure only\n\nactual damages incurred within the [limitations period] preceding the date upon\n\nwhich the action was filed”); Russo Farms, Inc. v. Vineland Bd. of Educ., 675 A.2d\n\n1077, 1084 (N.J. 1996) (same). Mr. Graham again provides a useful visual aid that\n\nillustrates just how this doctrine operates. As shown below, the repeated violations\n\ndoctrine “transforms what would otherwise represent a single, time-barred claim A\n\n\n\n 4\n Other courts and scholars have sometimes referred to this doctrine as the\n“modified” continuing violation doctrine. See, e.g., White, 129 F.3d at 1430;\nGraham, supra, at 283.\n 10\n\finto a series of fresh claims, identified as claims B, C, D, etc.” Graham, supra, at\n\n281.\n\n\n\n\n Notably, although Plaintiff argued in the district court that both the continuing\n\nviolation doctrine and the repeated violations doctrine could make timely his claims\n\nunder Title II of the ADA and section 504 of the RA, on appeal he argues only for\n\napplication of the repeated violations doctrine.5 Indeed, in his Opening Brief,\n\nPlaintiff argues that\n\n [e]ach time [he] was denied access to [the sidewalks and curb cuts], the\n City of Trinidad committed discrimination within the meaning of the\n ADA/§504 and a claim for damages arose under the statute. [Plaintiff]\n experienced recurrent discrimination by the City of Trinidad both inside\n and outside of the statute of limitations period. Accordingly, [Plaintiff]\n had some claims that are timely and some that are time barred.\n\n\n\n\n 5\n Plaintiff, in other words, abandoned his continuing violations argument on\nappeal. We thus do not consider it. See United States v. Yelloweagle, 643 F.3d\n1275, 1280 (10th Cir. 2011) (“[W]here [an appellant] raises an issue before the\ndistrict court but does not pursue it on appeal, we ordinarily consider the issue\nwaived.”).\n 11\n\fPl.’s Opening Br. 7 (emphases added). This language is a clear reference to the\n\nrepeated violations doctrine.\n\n Although Plaintiff abandons the continuing violation doctrine on appeal, the\n\nCity continues to view the case in that context. In the City’s view, the Supreme\n\nCourt’s analysis of the continuing violation doctrine in National Railroad Passenger\n\nCorp. v. Morgan, 536 U.S. 101 (2002), is controlling. In Morgan, the Supreme Court\n\nconsidered how statutes of limitations apply to various claims under Title VII of the\n\nCivil Rights Act of 1964. For hostile work environment claims, the Supreme Court\n\nheld that “consideration of the entire scope of [the] claim, including behavior alleged\n\noutside the statutory time period, is permissible for the purposes of assessing\n\nliability, so long as an act contributing to that hostile environment takes place within\n\nthe statutory time period.” Id. at 105. The Supreme Court reasoned that hostile work\n\nenvironment claims “cannot be said to occur on any particular day” and instead\n\n“occur[] over a series of days or perhaps years.” Id. at 115. Because “[s]uch claims\n\nare based on the cumulative effect of individual acts,” “[i]t does not matter . . . that\n\nsome of the component acts of the hostile work environment fall outside the statutory\n\ntime period.” Id. at 115, 117.\n\n The City argues that Morgan precludes us from applying the continuing\n\nviolation doctrine to Plaintiff’s Title II and section 504 claims because the City\n\nsubjected him to only “discrete acts of discrimination” that “did not require proof” of\n\nthe cumulative effect of individual acts. Def.’s Resp. Br. 11. Although that\n\nargument is correct, it misses the mark insofar as it assails an argument Plaintiff does\n\n 12\n\fnot make on appeal. Contrary to the way the City frames the issue, Plaintiff does not\n\ncontend that he should be able to aggregate separate acts into one single,\n\ncomprehensive violation. Instead, he argues that he may recover for injuries he\n\nsuffered inside of the limitations period but not for injuries he suffered outside of the\n\nlimitations period—that is, he is arguing for application of the repeated violations\n\ndoctrine. Morgan, therefore, is inapposite to this appeal because it did not involve\n\nthe repeated violations doctrine. Indeed, the language of that case—e.g., that hostile\n\nwork environments are made up of “component acts” and “are based on the\n\ncumulative effect of individual acts”—makes it clear it was immediately concerned\n\nwith interpreting and applying the continuing violation doctrine.\n\n The City further relies on our unpublished decision in Rhodes v. Langston\n\nUniversity, 462 F. App’x 773 (10th Cir. 2011). In Rhodes, the plaintiff argued that\n\nthe alleged Title II and section 504 violations at issue could not “be tied to specific\n\ndates as all were on-going events.” Id. at 780. He thus argued that the district court\n\nerred in concluding that the applicable two-year statute of limitations barred any of\n\nhis claims—including those based on acts that occurred outside of the limitations\n\nperiod—because they amounted to “a continuation . . . of related and repetitive\n\nunlawful acts or practices” that only concluded within that two-year period. Id.\n\nAlthough we ultimately determined that the plaintiff’s argument had no merit, that\n\ndetermination does not bear upon the outcome of Plaintiff’s current appeal before us\n\ntoday. Like the Supreme Court’s language in Morgan, our language in Rhodes shows\n\nthat we were concerned in that case with whether the continuing violation doctrine,\n\n 13\n\fnot the repeated violations doctrine, applied to Title II and section 504 claims. Thus,\n\nthe City’s attempt to analogize Plaintiff’s arguments to Rhodes is equally\n\nunconvincing.\n\n Finally, the City directs us to Foster v. Morris, 208 F. App’x 174 (3d Cir.\n\n2006) (unpublished). In that case, the Third Circuit concluded that the continuing\n\nviolation doctrine, not the repeated violations doctrine, does not apply to Title II\n\nclaims. See, e.g., id. at 177 (“The continuing violations doctrine is an equitable\n\nexception to a strict application of a statute of limitations where the conduct\n\ncomplained of consists of a pattern that has only become cognizable as illegal over\n\ntime.”); id. at 177–78 (“When a defendant’s conduct is part of a continuing practice,\n\nan action is timely so long as the last act evidencing the continuing practice falls\n\nwithin the limitations period; in such an instance, the court will grant relief for the\n\nearlier related acts that would otherwise be time barred.” (internal quotation marks\n\nand alterations omitted)). And interestingly enough, although Foster did not address\n\nthe repeated violations doctrine outright, Foster’s underlying reasoning actually\n\nsupports—or, at the very least, leaves room open for—that doctrine in the Title II and\n\nSection 504 context. Indeed, the Third Circuit concluded that the plaintiff in that\n\ncase was “still entitled to recover for any violations that occurred during” the\n\nlimitations period even though he could not recover for any violations that occurred\n\n\n\n\n 14\n\foutside that period. Id. at 178. That logic is perfectly consistent with the repeated\n\nviolations doctrine. So no matter how we slice it, Foster cannot help the City.6\n\n Because none of the cases the City cites resolve whether the repeated\n\nviolations doctrine applies to Plaintiff’s claims under Title II and section 504, we\n\nturn to the statutory text to decide this matter of first impression in our circuit.\n\n III.\n\n We hold that the repeated violations doctrine applies to claims under Title II of\n\nthe Americans with Disabilities Act and section 504 of the Rehabilitation Act of\n\n1973. As we explain below, a public entity repeatedly violates those two statutes\n\neach day that it fails to remedy a non-compliant service, program, or activity.\n\nAccordingly, a qualified individual with a disability is excluded from the\n\nparticipation in, denied the benefits of, and subjected to discrimination under the\n\nservice, program, or activity each day that she is deterred from utilizing it due to its\n\nnon-compliance. She stops suffering a daily injury only when the public entity\n\n\n 6\n Although neither party cites it, we also note that the Fifth Circuit’s decision\nin Frame v. City of Arlington, 657 F.3d 215 (5th Cir. 2011) (en banc), does not bear\non Plaintiff’s present appeal. The Frame court held that a single cause of action\naccrues under Title II and section 504 when the plaintiff “has sufficient information\nto know that he has been denied the benefits of a service, program, or activity of a\npublic entity.” Id. at 238. One may think that holding amounts to a rejection of the\nrepeated violations doctrine. But the question whether the repeated violations\ndoctrine applies to Title II claims was not before the court in Frame. Indeed, Frame\nonly considered whether a Title II cause of action accrues when the plaintiff\ndiscovers he has been injured or when the public entity engaged in the wrongful act\nthat caused the injury. Id. at 238–40. Nothing in its holding rejects or is inconsistent\nwith the repeated violations doctrine. Thus, for our purposes today, Frame is of\nlimited value.\n\n 15\n\fremedies the non-compliant service, program, or activity or when she no longer\n\nevinces an intent to utilize it. The practical effect is that, once the individual sues\n\nunder Title II or section 504, the statute of limitations bars recovery only for those\n\ninjuries she incurred outside of the limitations period immediately preceding the day\n\nof suit; it does not, however, bar recovery for injuries she incurred within that\n\nlimitations period or after she files suit.\n\n A.\n\n Our starting point is the plain language of Title II and section 504. See\n\nLevorsen v. Octapharma Plasma, Inc., 828 F.3d 1227, 1231 (10th Cir. 2016). If that\n\nlanguage is “clear and unambiguous,” then “our duty is simply to enforce the statute\n\nthat Congress has drafted.” United States v. Brown, 529 F.3d 1260, 1264 (10th Cir.\n\n2008) (quoting United States v. Ortiz, 427 F.3d 1278, 1282 (10th Cir. 2005)).\n\nSignificantly, though, “the meaning of statutory language, plain or not, depends on\n\ncontext.” First Nat’l Bank of Durango v. Woods (In re Woods), 743 F.3d 689, 694\n\n(10th Cir. 2014) (quoting United States v. Villa, 589 F.3d 1334, 1343 (10th Cir.\n\n2009)). We thus need not constrain ourselves to the “language itself” in determining\n\nwhether Title II and section 504 clearly and unambiguously convey when and how\n\noften a public entity violates these two statutes. Salazar v. Butterball, LLC, 644 F.3d\n\n1130, 1137 (10th Cir. 2011) (quoting Robinson v. Shell Oil Co., 519 U.S. 337, 340\n\n(1997)). Rather, we may also look to “the specific context in which that language is\n\nused” and “the broader context of the statute as a whole.” Id. (quoting Robinson, 519\n\nU.S. at 340). Both the text and structure of the statutes guide our decision today.\n\n 16\n\f Consider first the specific language. Title II mandates that “no qualified\n\nindividual with a disability shall, by reason of such disability, be excluded from\n\nparticipation in or be denied the benefits of the services, programs, or activities of a\n\npublic entity, or be subjected to discrimination by any such entity.” 42 U.S.C.\n\n§ 12132. Likewise, section 504 mandates in part that “[n]o otherwise qualified\n\nindividual with a disability in the United States . . . shall, solely by reason of her or\n\nhis disability, be excluded from the participation in, be denied the benefits of, or be\n\nsubjected to discrimination under any program or activity receiving Federal financial\n\nassistance.” 29 U.S.C. § 794(a).\n\n Obviously, neither of these statutes state outright when or how often a public\n\nentity violates them. They simply command that no qualified individual may “be\n\nexcluded” from, “be denied” the benefits of, or “be subjected” to discrimination\n\nunder a service, program, or activity. With that said, that language is phrased in the\n\npresent tense (albeit in the passive voice), which suggests that a qualified individual\n\nwho currently experiences discrimination under Title II or section 504 suffers an\n\ninjury. And so the same language also suggests that a qualified individual suffers\n\nnew discrimination and a new injury each day that she cannot utilize a non-compliant\n\nservice, program, or activity—even if the barriers giving rise to her claim were ones\n\nshe encountered before. After all, if sidewalks and curb cuts actually do constitute a\n\nservice, program, or activity of a public entity—a question that we express no\n\nopinion on today—a qualified individual with a disability would still “be excluded”\n\nfrom utilizing any given sidewalk or curb cut each day that it remained non-\n\n 17\n\fcompliant.7 Likewise, that same individual would still “be denied” the benefits of\n\nthat sidewalk or curb cut when she encountered it a day ago just as much as when she\n\nfirst encountered it a year ago. Cf. Pickern v. Holiday Quality Foods Inc., 293 F.3d\n\n1133, 1136 (9th Cir. 2002) (interpreting the phrases “is being subjected to” and “is\n\nabout to be subjected to” in the enforcement provision of Title III of the ADA and\n\nconcluding that they “make[] clear that either a continuing or a threatened violation\n\nof the ADA is an injury within the meaning of the Act”); Scherr v. Marriott Int’l,\n\nInc., 703 F.3d 1069, 1075–76 (7th Cir. 2013) (relying on Pickern and concluding the\n\nsame).\n\n To the extent any real or perceived gaps remain in the statutory text, the\n\nSupreme Court’s Title II jurisprudence fills them. In Tennessee v. Lane, 541 U.S.\n\n509 (2004), the Supreme Court recognized “that failure to accommodate persons with\n\ndisabilities will often have the same practical effect as outright exclusion.” Id. at 531\n\n(citing 42 U.S.C. § 12131(2)). Title II therefore imposes “an affirmative obligation\n\nto accommodate persons with disabilities.” Id. at 533.8\n\n\n 7\n We assume only for the purposes of this appeal that sidewalks and curb cuts\nconstitute a service, program, or activity.\n 8\n As Plaintiff points out, numerous regulations implementing the ADA reflect\nthis principle. See, e.g., 28 C.F.R. § 35.133(a) (“A public entity shall maintain in\noperable working condition those features of facilities and equipment that are\nrequired to be readily accessible to and usable by persons with disabilities . . . .”\n(emphasis added)); id. § 35.150(a) (“A public entity shall operate each service,\nprogram, or activity so that the service, program, or activity, when viewed in its\nentirety, is readily accessible to and usable by individuals with disabilities.”\n(emphasis added)); id. § 35.150(d) (allowing public entities to create a multi-year\nplan to remove existing barriers); id. § 35.151(b)(1) (“Each facility or part of a\n 18\n\f This “duty to accommodate,” id. at 532, solidifies that Title II (and, by\n\nextension, section 504) clearly and unambiguously conveys that a non-compliant\n\nservice, program, or activity gives rise to repeated violations.9 Failing to act in the\n\nface of an affirmative duty to do so axiomatically gives rise to liability. Cf., e.g.,\n\nRestatement (First) of Torts § 284 (1934) (“Negligent conduct may be . . . a failure to\n\ndo an act which is necessary for the . . . assistance of another and which the actor is\n\nunder a duty to do.”); Restatement (Second) of Torts § 824 (1979) (“The conduct\n\nnecessary to make the actor liable for . . . nuisance may consist of . . . a failure to act\n\nunder circumstances in which the actor is under a duty to take positive action . . . .”).\n\nFurther, if the actor under the affirmative duty keeps failing to act while the\n\nunderlying problem remains unremedied, then every day’s inaction amounts to a new\n\nviolation. Cf., e.g., Grant, 505 F.3d at 1028 (observing that continuing temporary\n\nnuisances “give[] rise over and over to new causes of action” until they are abated\n\n(internal quotation marks and alteration omitted)). Thus, even though “adverse\n\neffects resulting from” a single, original violation do not trigger the repeated\n\n\nfacility . . . shall . . . be altered in such manner that the altered portion of the facility\nis readily accessible to and usable by individuals with disabilities.” (emphases\nadded)).\n 9\n In addition to the fact that we analyze Title II and section 504 claims\ntogether, Miller ex rel. S.M., 565 F.3d at 1245, the language of the RA itself also\nsuggests an affirmative duty to accommodate. See, e.g., 29 U.S.C. § 701(c)(2)\n(requiring “the use of accessible formats” for qualified individuals with disabilities);\nsee also Alexander v. Choate, 469 U.S. 287, 301 (1985) (observing that qualified\nindividuals with disabilities under the RA are entitled to “meaningful access” and\n“reasonable accommodations”).\n\n 19\n\fviolations doctrine when they do not constitute violations in their own right,\n\nLedbetter v. Goodyear Tire & Rubber Co., 550 U.S. 618, 628 (2007), overturned on\n\nother grounds by The Lilly Ledbetter Fair Pay Act of 2009, Pub. L. No. 111–2, 123\n\nStat. 5 (2009), claims under Title II (and section 504 by extension) do not fit that\n\nrubric. Rather, a public entity does commit a “new violation” each day that it fails to\n\nremedy a non-compliant service, program, or activity. The affirmative, ongoing duty\n\nthat Title II and section 504 place upon it mandates as much. Id. 10,11\n\n\n 10\n The City notes and relies on the Fourth Circuit’s opinion in A Society\nWithout A Name v. Virginia, 655 F.3d 342 (4th Cir. 2011), which concluded that a\nclaim under Title II did not trigger the principles of the repeated violations doctrine\nbecause that claim only gave rise to “the continuing ill effects of [one] original\nviolation.” Id. at 348–49. We do not find that case persuasive, however, because it\nnever factored in the mandate that Title II imposes an affirmative duty to\naccommodate. See id.\n 11\n At this point, we believe that an analogy to temporary nuisance claims—one\nof the “touchstone” instances of the repeated violations doctrine at work, Graham,\nsupra, at 308—can further illustrate our rationale. A temporary nuisance exists\n“[w]here the injury from the alleged nuisance . . . is of a continuing or recurring\ncharacter.” 58 Am. Jur. 2d Nuisances § 221 (2018). “In such a case, every day’s\ncontinuance is a new nuisance,” id., that “gives rise over and over to new causes of\naction,” Grant, 505 F.3d at 1028 (internal quotation marks and alteration omitted).\nThe practical effect is that “a new statute of limitations begins to run . . . after each\nnew injury,” 58 Am. Jur. 2d Nuisances § 253 (2018) (emphasis added), and the final\nstatute of limitations accrues only when the temporary nuisance is remedied once and\nfor all. See Grant, 505 F.3d at 1028. Thus, so long as the temporary nuisance\ncontinues unabated, a plaintiff bringing suit is effectively doing so on “day one” of a\nnew limitations period, which enables her to seek damages for past injuries sustained\n“within the limitations period immediately prior to suit.” Id. (internal quotation\nmarks omitted).\n So too here. Each time a qualified individual with a disability is excluded\nfrom, denied the benefits of, or subjected to discrimination under a service, program,\nor activity, he suffers an injury under Title II and section 504. For the reasons we\nexplained above, this injury is not a one-time event; rather, it repeatedly occurs so\nlong as the service, program, or activity remains non-compliant and the qualified\n 20\n\f The broader statutory context of the ADA and RA bolsters this conclusion.\n\nConsider, for example, 42 U.S.C. § 12101, which outlines Congress’s express\n\nstatutory purposes for enacting the ADA. There, Congress noted that “the Nation’s\n\nproper goals regarding individuals with disabilities are to assure . . . full\n\nparticipation . . . for such individuals.” 42 U.S.C. § 12101(a)(7). Congress made a\n\nsimilar conclusion earlier when it enacted 29 U.S.C. § 701, which lists the purposes\n\nof the RA. In that statute, Congress noted that it hoped to achieve “full inclusion and\n\nintegration in society” for individuals with disabilities and that an entity charged with\n\ncarrying out the RA should always consider “the principle[] of . . . full participation\n\nof the individuals.” 29 U.S.C. § 701(a)(6)(B), (c)(3).\n\n Congress’s goals of full participation, inclusion, and integration for qualified\n\nindividuals with disabilities are consistent with and suggestive of the repeated\n\nviolations doctrine. A qualified individual is not a full participant or fully included\n\nin a service, program, or activity if she cannot utilize it in a similar way as persons\n\nwithout disabilities, and that does not change simply because she was deterred from\n\nutilizing the service, program, or activity many times before. What matters is\n\nwhether the individual can fully participate now in the service, program, or activity.\n\nThe repeated violations doctrine, in turn, accounts for that reality—and, for that\n\nmatter, encourages public entities to comply with their affirmative and ongoing\n\n\n\nindividual is aware of that and deterred from utilizing it. So when a Title II or\nsection 504 plaintiff brings suit, he is essentially doing so on the first day of a new\nlimitations period.\n 21\n\fobligations to accommodate—by giving a qualified individual an avenue for relief\n\nany moment that he or she cannot fully participate or is not fully included in a\n\nservice, program, or activity.\n\n Congress further observed in enacting the ADA that “the continuing existence\n\nof unfair and unnecessary discrimination and prejudice denies people with disabilities\n\nthe opportunity to compete on an equal basis and to pursue those opportunities for\n\nwhich our free society is justifiably famous . . . .” 42 U.S.C. § 12101(a)(8) (emphasis\n\nadded). It also noted that it hoped “to address the major areas of discrimination faced\n\nday-to-day by people with disabilities.” Id. § 12101(b)(4) (emphasis added).\n\nSimilarly, when it previously enacted the RA, Congress had discerned that\n\n“individuals with disabilities continually encounter various forms of discrimination.”\n\n29 U.S.C. § 701(a)(5) (emphasis added). This language demonstrates that Congress\n\nunderstood that a public entity could repeatedly cause a qualified individual with a\n\ndisability to suffer an injury from the same service, program, or activity. Certainly,\n\nnothing in the text of Title II or section 504 suggests otherwise.\n\n The statutory text and the Supreme Court’s pronouncements make one thing\n\nclear: Congress did not design the ADA or the RA so that a public entity could\n\nforever prevent a qualified individual with a disability from utilizing a service,\n\nprogram, or activity. Yet the City argues for that exact result. The City contends\n\nthat because Plaintiff filed suit more than two years after he first encountered the\n\nallegedly non-compliant sidewalks and curb cuts, the statute of limitations forever\n\nbars him from forcing the City to live up to its affirmative duty and correct those\n\n 22\n\fbarriers. That proposition simply cannot fit within the language, structure, and\n\npurpose of the ADA or the RA.\n\n In conclusion, based on the plain language of Title II of the ADA and section\n\n504 of the RA, Supreme Court jurisprudence interpreting Title II, and Congress’s\n\nexpress statutory purposes in enacting the ADA and RA, we hold that Title II and\n\nsection 504 clearly and unambiguously require us to acknowledge they are subject to\n\nthe repeated violations doctrine.12 Accordingly, each time a qualified individual with\n\na disability encounters or “actually become[s] aware of” a non-compliant service,\n\nprogram, or activity “and is thereby deterred” from utilizing that service, program, or\n\nactivity, he or she suffers discrimination and a cognizable injury. Pickern, 293 F.3d\n\n\n 12\n Because Title II and section 504 are unambiguous in this regard, we have no\nreason to consider “the underlying public policy” of either statute. United States v.\nManning, 526 F.3d 611, 614 (10th Cir. 2008) (quoting United States v. LaHue, 170\nF.3d 1026, 1028 (10th Cir. 1999)); see also id. (“If the statutory language is clear, our\nanalysis ordinarily ends.”). Even so, we observe as a side note that applying the\nrepeated violations doctrine to claims under Title II and section 504 serves the\ninterests of efficiency. In Title II and section 504 cases, “more than just the rights of\nthe plaintiff before the court are at stake.” Graham, supra, at 321. Indeed, many\nother qualified individuals with disabilities also benefit from a ruling favorable to the\nplaintiff. To use this case as an example, if Plaintiff were to succeed in requiring the\nCity of Trinidad to further remedy its sidewalks and curb cuts, other individuals who\nuse wheelchairs would likewise reap the rewards. So if we were not to apply the\nrepeated violations doctrine to Plaintiff’s claims and therefore forever bar those\nclaims on statute of limitations grounds, “a substantively similar but timely suit\nbrought by a different plaintiff”—namely, another qualified individual unable to\nutilize the City’s sidewalks and curb cuts—“could land in [this Court’s] lap soon\nthereafter.” Id. Thus, although the clear and unambiguous language of these two\nstatutes carries the day, we note the inherent good sense in “entertaining the claim[s]\nat hand” but limiting Title II and section 504 plaintiffs “to only those damages\nsuffered within the limitations period and, perhaps more important, to injunctive\nrelief.” Id.\n\n 23\n\fat 1136–37. So long as the service, program, or activity remains non-compliant, “and\n\nso long as a plaintiff is aware of [that] and remains deterred,” the qualified\n\nindividual’s injury repeats. Id. at 1137. A defendant, therefore, cannot brandish the\n\nstatute of limitations in its usual manner as a shield that fully protects he, she, or it\n\nfrom suit. But the defendant can wield the statute of limitations as a sword that\n\nchops off damages arising before the limitations period comes into play.\n\n B.\n\n The City of Trinidad and the Colorado Municipal League (“the League”) as\n\namicus curiae both claim that our ruling today will effectively “nullify the statute of\n\nlimitations.” Def.’s Resp. Br. 24.\n\n Not so for several reasons. For starters, both the City and the League conflate\n\nthe repeated violations doctrine and continuing violation doctrine—or at least\n\nconflate which of the two Plaintiff is arguing for on appeal—which likely has\n\ncontributed to that belief. See supra. But setting that point aside, we “will look\n\nbeyond the plain language of a statute only if the result is an absurd application of the\n\nlaw.” Brown, 529 F.3d at 1265 (emphasis in original). Observing that the repeated\n\nviolations doctrine applies to Title II and section 504 claims, however, does not result\n\nin any absurd statute-of-limitations outcomes. Indeed, the statute of limitations still\n\nhas an important role to play even when the repeated violations doctrine applies to a\n\nclaim. Namely, although the statute of limitations does not bar an untimely lawsuit\n\nin its entirety in such an instance, it nonetheless limits the plaintiff’s ability to\n\nrecover damages to only those injuries incurred during the limitations period\n\n 24\n\fimmediately preceding suit (the plaintiff, of course, can also recover damages for any\n\ninjuries incurred after filing suit).13 White, 129 F.3d at 1430. By contrast, the\n\nrepeated violations doctrine prevents a plaintiff from recovering damages for every\n\ninjury she suffered throughout history that relates to the non-compliant service,\n\nprogram, or activity.14 Cf., e.g., Foster, 208 F. App’x at 178. If Plaintiff, for\n\nexample, had first discovered the City’s non-compliant sidewalks and curb cuts in\n\n1996 but still brought suit in 2016, he would not be able to recover damages for\n\nevery injury he sustained throughout those twenty years; he would be restricted to\n\nthose injuries he suffered after October 12, 2014. This in itself substantially limits a\n\npublic entity’s liability under Title II and section 504.\n\n\n 13\n Theoretically, the statute of limitations could still function as a complete bar\nto an untimely lawsuit even when the repeated violations doctrine applies. Suppose,\nfor instance, a plaintiff was first deterred from utilizing a service, program, or\nactivity in 2009 and tries to bring a lawsuit in 2019 for violations of Title II and\nsection 504 against the public entity responsible. But also suppose the plaintiff\nconcedes that in 2016 the public entity completely and entirely remedied the non-\ncompliant service, program, or activity. Assuming a two-year statute of limitations\napplies, it would entirely bar the plaintiff’s claims even though the repeated\nviolations doctrine also applies to his claims. Indeed, the public entity’s last possible\nrepeated violation (and the plaintiff’s last possible injury) would have occurred in\n2016 before the remedy went into place, which means that the statute of limitations\nwould have run at some point in 2018. Accordingly, the 2019 lawsuit would be\nuntimely because the plaintiff could not point to a violation or injury that occurred in\nthe two years prior to the day he files suit.\n We mention this scenario only to illustrate that it is possible. Our immediate\nconcern, however, is with cases where the public entity has not remedied the non-\ncompliant service, program, or activity. In such instances, the public entity is still\ncommitting violations, and the qualified individual with a disability is still suffering\ninjuries.\n 14\n The continuing violation doctrine would allow for such a recovery. See\nMorgan, 536 U.S. at 105.\n 25\n\f What’s more, Title II and section 504 plaintiffs are able to recover damages\n\nonly in the unusual case. Our circuit requires proof of intentional discrimination\n\nbefore a plaintiff can recover compensatory damages under section 504, Havens v.\n\nColo. Dep’t of Corr., 897 F.3d 1250, 1263 (10th Cir. 2018), and we have suggested\n\nthat as much is required under Title II, Moseley v. Bd. of Educ. of Albuquerque Pub.\n\nSch., 483 F.3d 689, 693 (10th Cir. 2007) (noting that Tenth Circuit precedent\n\nsuggests, but does not explicitly hold, “that proof of intentional discrimination is\n\nrequired for compensatory damages under Title II”); see also Miraglia v. Bd. of\n\nSupervisors of La. State Museum, 901 F.3d 565, 574 (5th Cir. 2018) (“To recover\n\ncompensatory damages for disability discrimination under Title II of the ADA, a\n\nplaintiff must also show that the discrimination was intentional.” (emphasis added)\n\n(internal quotation marks omitted)). And punitive damages are categorically\n\nunavailable for suits under Title II and section 504. Barnes v. Gorman, 536 U.S. 181,\n\n189 (2002). So Title II and section 504 plaintiffs are hard-pressed to receive any\n\nmonetary damages unless they can prove that a service, program, or activity is\n\nintentionally discriminatory toward individuals with disabilities, which is surely the\n\nexception rather than the rule. This stands as an additional limitation of a public\n\nentity’s liability under Title II and section 504.\n\n We agree with the City and the League, though, that the repeated violations\n\ndoctrine will manifest itself by keeping public entities on the hook for injunctive\n\nrelief as the years go by. After all, if a court grants an injunction requiring a public\n\nentity to remedy a program, service, or activity, we have a difficult time seeing just\n\n 26\n\fhow the court or public entity could divvy that injunction up in a way that limits it to\n\ninjuries the plaintiff incurred within the limitations period. See Holmberg v.\n\nAmbrecht, 327 U.S. 392, 396 (1946) (observing that equitable relief “eschews\n\nmechanical rules”).\n\n But the availability of injunctive relief itself does not raise any red flags. As\n\nwe described above, when Congress outlined its purposes and goals in enacting the\n\nADA and RA, it expressly noted that it sought full participation, inclusion, and\n\nintegration in society for individuals with disabilities. By remaining on the hook for\n\ninjunctive relief—as its affirmative obligation to accommodate requires—a public\n\nentity is incentivized to remedy non-compliant services, programs, or activities in a\n\nreasonable yet efficient manner to ensure that full participation. And along those\n\nsame lines, Plaintiff makes an excellent point: “public entities . . . have the ultimate\n\noption to avoid liability” by “simply mak[ing] their programs, services, and activities\n\naccessible for persons with disabilities.” Pl.’s Opening Br. 30; see also Frame v. City\n\nof Arlington, 657 F.3d 215, 239 (5th Cir. 2011) (en banc) (“The City may avoid\n\nliability whenever it chooses simply by building sidewalks right the first time, or by\n\nfixing its original unlawful construction. In other words, the City is not liable\n\nforever; it is responsible only for correcting its own mistakes.”).\n\n Further, as far as injunctive relief is concerned, we note that a qualified\n\nindividual with a disability no longer suffers an injury once he stops “assert[ing] an\n\nintent to return to the particular place (or places) where the violations are alleged to\n\nbe occurring.” Scherr, 703 F.3d at 1074, 1076; see also Frame, 657 F.3d at 238 (“[A]\n\n 27\n\fdisabled individual has no standing to challenge an inaccessible sidewalk until he can\n\nshow actual, concrete plans to use that sidewalk.” (internal quotation marks\n\nomitted)); Barney v. Pulsipher, 143 F.3d 1299, 1306 n.3 (10th Cir. 1998) (“A\n\n‘plaintiff cannot maintain a declaratory or injunctive action unless he or she can\n\ndemonstrate a good chance of being likewise injured in the future.’” (quoting Facio\n\nv. Jones, 929 F.2d 541, 544 (10th Cir. 1991))). Although this implicates Article III\n\nstanding, Scherr, 703 F.3d at 1073–76, the practical effect of that lack of intent\n\nwould insulate a public entity from a Title II or section 504 lawsuit seeking\n\nprospective injunctive relief. To use an extreme example, if Plaintiff were to move\n\naway from the City of Trinidad and had no intent to return, he would no longer be\n\nsuffering any injury—and, consequently, would lack standing to bring a suit for\n\nprospective injunctive relief—regardless of whether the City remedied the sidewalks\n\nand curb cuts that allegedly injured him in the past. And even if a qualified\n\nindividual still suffers an injury after many years, we note that at some point the\n\ndoctrine of laches may come into play. See SCA Hygiene Prods. Aktiebolag v. First\n\nQuality Baby Prods., LLC, 137 S. Ct. 954, 960 (2017) (“Laches is ‘a defense\n\ndeveloped by courts of equity’ to protect defendants against ‘unreasonable,\n\nprejudicial delay in commencing suit.’” (quoting Petrella v. Metro-Goldwyn-Mayer,\n\nInc., 572 U.S. 663, 667, 678 (2014)). This further cuts against the City’s and the\n\nLeague’s arguments that public entities will be exposed to unlimited liability.\n\n As a final note, we are not unsympathetic to the City’s and the League’s\n\narguments that public entities are constrained by limited budgets that do not easily\n\n 28\n\flend themselves to the constant ability to remedy ADA and RA issues.15 But again,\n\nliability for monetary damages is infrequent, which significantly softens the impact\n\nof our ruling today. See supra. And if a public entity truly is not liable, or if that\n\nentity has already taken significant steps to remedy or can establish that it has multi-\n\nyear plans in place to remedy a non-compliant service, program, or activity—as the\n\nCity has apparently done in this case—a factfinder will be able to ferret that out when\n\ndeciding the merits of any given case. See, e.g., Rife v. Okla. Dep’t of Pub. Safety,\n\n854 F.3d 637, 643 (10th Cir. 2017) (observing that factfinders find facts weighing on\n\nliability). Indeed, at least two other circuits have endorsed either the repeated\n\nviolations doctrine or continuing violation doctrine in the context of ADA Title III\n\nclaims, but neither the City nor the League have directed us to any evidence\n\nsuggesting that places of public accommodation located in those circuits have faced\n\nsignificant hardship by the courts’ respective applications of the doctrines. See\n\nPickern, 293 F.3d at 1136–37; Scherr, 703 F.3d at 1075–76.\n\n Thus, the City’s and the League’s concerns are unsubstantiated.\n\n IV.\n\n The district court did not recognize the impact of the repeated violations\n\ndoctrine on Plaintiff’s claims under Title II of the ADA and section 504 of the RA.\n\n\n 15\n The City contends that adopting the repeated violations doctrine will cause\nthis inability to remedy ADA and RA issues, but it is mistaken. Even without the\nrepeated violations doctrine, qualified individuals with disabilities who have\nencountered the City’s non-compliant services, programs, or activities within the past\ntwo years could just as easily bring lawsuits against the City. So the danger about\nwhich the City complains exists even under their own interpretation of the law.\n 29\n\fInstead, it concluded that Plaintiff could not “rely solely on the continued\n\ninaccessibility of the City’s sidewalks and curb cuts” to survive dismissal under\n\nColorado’s two-year statute of limitations.\n\n This was error. Because the district court applied an incorrect standard, it\n\ncould not determine under the proper framework how the two-year statute of\n\nlimitations affected Plaintiff’s claims. As a court of review, we will not decide that\n\ninquiry for the first time on appeal. Pignanelli v. Pueblo Sch. Dist. No. 60, 540 F.3d\n\n1213, 1218 (10th Cir. 2008). We thus remand the case to the district court to decide\n\nin the first instance under the framework set forth in this opinion which of Plaintiff’s\n\ninjuries he may seek relief for and which of those he may not. In so doing, the\n\ndistrict court will necessarily need to determine which of the City’s sidewalks and\n\ncurb cuts Plaintiff has actually been deterred from utilizing.16\n\n For the reasons set forth above, we REVERSE and REMAND for further\n\nproceedings consistent with this opinion.\n\n\n\n\n 16\n In issuing these instructions on remand, we emphasize once again that we\ntake no stance on the question whether sidewalks and curb cuts qualify as a service,\nprogram, or activity of a public entity. We also issue these instructions cognizant of\nthe fact that the district court assumed—much like we did—that sidewalks and curb\ncuts qualify as a service, program, or activity of a public entity so that it could reach\nthe “narrower” and “dispositive” statute of limitations question. For those reasons,\nthe district court may now find it necessary to definitively decide on remand whether\nsidewalks and curb cuts qualify as a service, program, or activity of a public entity,\nand it should not read anything in this opinion as preventing it from doing so.\n 30\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Stephen HAMER, Plaintiff - Appellant, v. CITY OF TRINIDAD, Defendant - Appellee. Colorado Municipal League, Amicus Curiae.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-15\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 15, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n STEPHEN HAMER,\\n\\n Plaintiff - Appellant,\\n\\n v. No. 17-1456\\n\\n CITY OF TRINIDAD,\\n\\n Defendant - Appellee.\\n\\n ------------------------------\\n\\n COLORADO MUNICIPAL LEAGUE,\\n\\n Amicus Curiae.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:16-CV-02545-NYM-KMT)\\n _________________________________\\n\\nGarrett S. DeReus (Andrew D. Bizer with him on the briefs), Bizer & DeReus, New\\nOrleans, Louisiana, for Plaintiff-Appellant.\\n\\nMarni Nathan Kloster (Nicholas C. Poppe with her on the brief), Nathan Dumm & Mayer\\nP.C., Denver, Colorado, for Defendant-Appellee.\\n\\nWynetta P. Massey and Lindsay M. Rose, Special Counsel for Colorado Municipal\\nLeague, Office of the City Attorney, Colorado Springs, Colorado, and Dianne M.\\nCriswell, Attorney for Colorado Municipal League, Denver, Colorado, filed a brief for\\nAmicus Curiae in support of Defendant-Appellee.\\n _________________________________\\n\\nBefore BRISCOE, BACHARACH, and CARSON, Circuit Judges.\\n _________________________________\\n\\fCARSON, Circuit Judge.\\n _________________________________\\n\\n Title II of the Americans with Disabilities Act (“ADA”) mandates that “no\\n\\nqualified individual with a disability shall, by reason of such disability, be excluded\\n\\nfrom participation in or be denied the benefits of the services, programs, or activities\\n\\nof a public entity, or be subjected to discrimination by any such entity.” 42 U.S.C.\\n\\n§ 12132. Similarly, section 504 of the Rehabilitation Act of 1973 (“RA”) mandates\\n\\nin part that “[n]o otherwise qualified individual with a disability in the United\\n\\nStates . . . shall, solely by reason of her or his disability, be excluded from the\\n\\nparticipation in, be denied the benefits of, or be subjected to discrimination under any\\n\\nprogram or activity receiving Federal financial assistance.” 29 U.S.C. § 794(a).\\n\\n Today we consider exactly when and how a public entity violates these two\\n\\nstatutes.1 The answer, in turn, affects how the applicable statutes of limitations\\n\\noperate. Does a public entity violate Title II and section 504 only when it initially\\n\\nconstructs or creates a non-compliant service, program, or activity? If so, a single\\n\\nstatute of limitations accrues from the day a qualified individual with a disability first\\n\\ndiscovers he or she has been injured by the service, program, or activity. The statute\\n\\nof limitations, in this scenario, would bar any lawsuit brought after the limitations\\n\\nperiod ends.\\n\\n\\n\\n\\n 1\\n Unless we say otherwise, when we use the term “public entity,” we are\\nreferring to both public entities under Title II and programs or activities that receive\\nfederal financial assistance under section 504.\\n 2\\n\\f Or does a public entity violate Title II and section 504 repeatedly until it\\n\\naffirmatively acts to remedy the non-compliant service, program, or activity? In that\\n\\nsituation, a qualified individual’s initial discovery that he or she has been injured\\n\\ndoes not trigger just one statute of limitations that bars any lawsuit brought after the\\n\\nlimitations period ends. Rather, because the public entity commits a new violation\\n\\n(and the qualified individual experiences a new injury) each day that it fails to act,\\n\\nthe statute of limitations effectively functions as a “look-back period,” Burlington N.\\n\\n& Santa Fe Ry. Co. v. Grant, 505 F.3d 1013, 1028–29 (10th Cir. 2007), restricting an\\n\\nindividual’s right to relief to those injuries suffered (1) during the limitations period\\n\\nimmediately prior to filing suit and (2) while the suit is pending.\\n\\n We hold that a public entity violates Title II of the Americans with Disabilities\\n\\nAct and section 504 of the Rehabilitation Act each day that it fails to remedy a non-\\n\\ncompliant service, program, or activity. As a result, the applicable statute of\\n\\nlimitations does not operate in its usual capacity as a firm bar to an untimely lawsuit.\\n\\nInstead, it constrains a plaintiff’s right to relief to injuries sustained during the\\n\\nlimitations period counting backwards from the day he or she files the lawsuit and\\n\\ninjuries sustained while the lawsuit is pending. Because the district court applied a\\n\\ndifferent and incorrect standard, we reverse and remand for further proceedings.\\n\\n I.\\n\\n Plaintiff Stephen Hamer resides in Trinidad, Colorado; is confined to a\\n\\nmotorized wheelchair due to what he characterizes as “severe bilateral ankle\\n\\nproblems”; and, for purposes of this appeal, is a qualified individual with a disability\\n\\n 3\\n\\funder Title II of the ADA and section 504 of the RA. He does not own a car or\\n\\notherwise use public transportation. Instead, he primarily utilizes the City of\\n\\nTrinidad’s public sidewalks to move about in his wheelchair.\\n\\n Plaintiff contends many of the City’s sidewalks and the curb cuts allowing\\n\\naccess onto those sidewalks do not comply with Title II of the ADA and section 504\\n\\nof the RA. Indeed, at a City Council meeting he attended in April 2014, Plaintiff\\n\\ninformed City officials that he had personally counted seventy-nine non-compliant\\n\\nsidewalks and curb cuts throughout the city. Further, at the end of that same month,\\n\\nPlaintiff filed an ADA complaint with the United States Department of Justice\\n\\n(“DOJ”) informing the government about the state of the City’s sidewalks and curb\\n\\ncuts.\\n\\n Plaintiff continued to lodge informal ADA and RA complaints at City Council\\n\\nmeetings over the next few months. And at some point after he lodged his ADA\\n\\ncomplaint with the DOJ, the DOJ audited the City and discovered multiple non-\\n\\ncompliant sidewalks and curb ramps. Apparently in response to Plaintiff’s multiple\\n\\ncomplaints and the results of the DOJ’s audit, City officials actively began repairing\\n\\nand amassing funding to further repair non-compliant sidewalks and curb cuts.\\n\\n Even so, Plaintiff nonetheless filed the present lawsuit against the City on\\n\\nOctober 12, 2016, for violations of Title II of the ADA and section 504 of the RA.\\n\\nLike the complaint he filed with the DOJ, Plaintiff complains of the City’s allegedly\\n\\ndeficient sidewalks and curb cuts. He thus seeks a declaratory judgment that the\\n\\nCity’s sidewalks and curb cuts violate the ADA and RA, injunctive relief requiring\\n\\n 4\\n\\fCity officials to remedy the City’s non-compliant sidewalks and curb cuts, monetary\\n\\ndamages, attorneys’ fees, and costs.\\n\\n The district court granted summary judgment to the City on statute-of-\\n\\nlimitations grounds. The district court first observed that because neither Title II nor\\n\\nsection 504 explicitly provided for a statute of limitations, Colorado’s general two-\\n\\nyear statute of limitations governed Plaintiff’s claims. See E.E.O.C. v. W.H. Braum,\\n\\nInc., 347 F.3d 1192, 1197 (10th Cir. 2003) (“Where Congress creates a cause of\\n\\naction without specifying the time period within which it may be brought, courts may\\n\\ninfer that Congress intended the most analogous state statute of limitations to\\n\\napply.”); see also Colo. Rev. Stat. § 13-80-102 (establishing Colorado’s general two-\\n\\nyear statute of limitations). The district court then noted the general rule in federal\\n\\ncourt that “[t]he statute of limitations begins to run when the plaintiff knows or has\\n\\nreason to know of the existence and cause of the injury which is the basis of his\\n\\naction.” Alexander v. Oklahoma, 382 F.3d 1206, 1215 (10th Cir. 2004) (alteration in\\n\\noriginal) (quoting Indus. Constructors Corp. v. U.S. Bureau of Reclamation, 15 F.3d\\n\\n963, 969 (10th Cir. 1994)). With that rule in mind, the district court concluded that\\n\\nPlaintiff must have “discovered” or “encountered” the City’s non-compliant\\n\\nsidewalks and curb cuts no earlier than October 12, 2014—i.e., two years before the\\n\\nday he filed his lawsuit—to survive summary judgment.\\n\\n The district court determined, however, that Plaintiff’s claims most likely\\n\\naccrued in April 2014 when Plaintiff first raised his concerns about the City’s\\n\\nsidewalks and curb cuts at the City Council meeting and with the DOJ. In any event,\\n\\n 5\\n\\fthe district court also determined that Plaintiff’s claims must have begun to accrue\\n\\n“at the very latest[] in August 2014” when he raised his concerns at a City Council\\n\\nmeeting for the final time. At one of these two points—either April or August\\n\\n2014—Plaintiff was undoubtedly “aware of the nature and extent of the City’s\\n\\ndiscrimination.” Thus, because both of these dates occurred before October 12,\\n\\n2014, the district court held that the two-year statute of limitations barred Plaintiff’s\\n\\nTitle II and section 504 claims.\\n\\n The district court explicitly rejected Plaintiff’s argument that the continuing\\n\\nviolation doctrine could salvage his claims from being untimely. This doctrine\\n\\napplies “‘when the plaintiff’s claim seeks redress for injuries resulting from a series\\n\\nof separate acts that collectively constitute one unlawful act,’ as opposed to ‘conduct\\n\\nthat is a discrete unlawful act.’” Sierra Club v. Okla. Gas & Elec. Co., 816 F.3d 666,\\n\\n672 (10th Cir. 2016) (quoting Shomo v. City of New York, 579 F.3d 176, 181 (2d\\n\\nCir. 2009)). Stated differently, “one violation continues when ‘the conduct as a\\n\\nwhole can be considered as a single course of conduct.’” Id. (quoting Birkelbach v.\\n\\nSEC, 751 F.3d 472, 479 n.7 (7th Cir. 2014)). The utility of the continuing violation\\n\\ndoctrine lies in the fact that as long as one of the separate wrongful acts contributing\\n\\nto the collective conduct “occurs within the filing period,” a court may consider “the\\n\\nentire time period”—including those separate acts falling outside the filing period—\\n\\n“for the purposes of determining liability.” Nat’l R.R. Passenger Corp. v. Morgan,\\n\\n536 U.S. 101, 117 (2002) (emphasis added).\\n\\n\\n\\n 6\\n\\f An important caveat to the continuing violation doctrine, however, is that it “is\\n\\ntriggered ‘by continual unlawful acts, not by continual ill effects from the original\\n\\nviolation.’” Mata v. Anderson, 635 F.3d 1250, 1253 (10th Cir. 2011) (quoting\\n\\nParkhurst v. Lampert, 264 F. App’x 748, 749 (10th Cir. 2008) (unpublished)). And\\n\\naccording to the district court, the allegedly unlawful acts at issue in Plaintiff’s\\n\\nlawsuit—“the construction and alleged lack of maintenance of noncompliant\\n\\nsidewalks and curb cuts”—were discrete, as opposed to continual, acts. As a result,\\n\\nthe district court concluded that “any subsequent injury caused by the City’s failure to\\n\\nremediate these issues” after Plaintiff discovered or encountered them simply amounted\\n\\nto “continual ill effects” of those original violations. Thus, the district court reasoned that\\n\\nthe continuing violation doctrine could not apply to Plaintiff’s claims.\\n\\n The district court also denied Plaintiff’s additional argument that, regardless of\\n\\nwhether the continuing violation doctrine applied, his claims remained timely because the\\n\\nCity “violate[d] both statutes each day” that it failed to remedy its non-compliant\\n\\nsidewalks and curb cuts. In Plaintiff’s opinion, such repeated violations meant that he\\n\\nsuffered injuries each day he was unable to access the sidewalks and curb cuts until the\\n\\nday he filed suit. Under this theory, the two-year statute of limitations did not bar\\n\\nPlaintiff’s suit completely. Instead, he could obtain relief for injuries he suffered after\\n\\nOctober 12, 2014, but not for any injuries he suffered before that day.\\n\\n The district court rejected Plaintiff’s argument, concluding that “it [was]\\n\\ninsufficient to rely solely on the continued inaccessibility of the City’s sidewalks and\\n\\ncurb cuts” for Plaintiff to show he suffered an injury or injuries after October 12, 2014.\\n\\n 7\\n\\fIndeed, the district court again characterized the continued inaccessibility as “continued\\n\\nill effects” of Plaintiff’s original encounters or discoveries of the City’s alleged\\n\\ndiscrimination. The district court therefore reaffirmed its belief that Plaintiff needed to\\n\\npoint to “discrete acts of discrimination he encountered since October 12, 2014,” to\\n\\nsurvive summary judgment. And because Plaintiff had not directed the district court to\\n\\nany evidence suggesting that he encountered or discovered any new, non-compliant\\n\\nsidewalks and curb cuts after October 12, 2014, the district court stood firm in its\\n\\nconclusion that Plaintiff’s Title II and section 504 claims were untimely.\\n\\n Plaintiff now appeals the district court’s ruling that Colorado’s two-year\\n\\nstatute of limitations bars his Title II and section 504 claims.2 Our jurisdiction arises\\n\\nunder 28 U.S.C. § 1291, and our review is de novo. Sierra Club, 816 F.3d at 671.\\n\\nFurther, because Title II and section 504 essentially “involve the same substantive\\n\\nstandards, we analyze them together.” Miller ex rel. S.M. v. Bd. of Educ. of\\n\\nAlbuquerque Pub. Sch., 565 F.3d 1232, 1245 (10th Cir. 2009).\\n\\n II.\\n\\n Before launching into our analysis, we first take a moment to explain in more\\n\\ndetail the difference between the two arguments Plaintiff made in the district court\\n\\nand how that difference affects our ultimate disposition of his appeal.\\n\\n\\n\\n\\n 2\\n Neither party disputes that the applicable limitations period is two years in\\nlength or that it derives from section 13-80-102 of the Colorado Revised Statutes.\\nWe thus assume the same for purposes of this appeal.\\n\\n 8\\n\\f As discussed above, the “continuing violation” doctrine—Plaintiff’s first\\n\\nargument to the district court—tethers conduct from both inside and outside the\\n\\nlimitations period into one single violation that, taken as a whole, satisfies the\\n\\napplicable statute of limitations.3 Sierra Club, 816 F.3d at 672. To help illustrate\\n\\nthis concept, we borrow a useful visual aid from attorney Kyle Graham’s law review\\n\\narticle “The Continuing Violations Doctrine”:\\n\\n\\n\\n\\nThis figure “illustrates how [the continuing violation doctrine] combines otherwise\\n\\ndiscrete occurrences A through E, of which only D and E occurred within the limitations\\n\\nperiod, into a single, timely claim A.” Kyle Graham, The Continuing Violations\\n\\nDoctrine, 43 Gonz. L. Rev. 271, 280 (2008).\\n\\n\\n\\n\\n 3\\n Unlike the typical custom in our circuit, other courts and scholars have\\nsometimes added a word and referred to this doctrine as the “pure” continuing\\nviolation doctrine. See, e.g., White v. Mercury Marine, Div. of Brunswick, Inc., 129\\nF.3d 1428, 1430 (11th Cir. 1997); Kyle Graham, The Continuing Violations\\nDoctrine, 43 Gonz. L. Rev. 271, 283 (2008).\\n\\n 9\\n\\f By contrast, we have referred to the second argument Plaintiff made to the\\n\\ndistrict court as the “repeated violations” doctrine.4 Sierra Club, 816 F.3d at 671.\\n\\nUnlike the continuing violation doctrine, the repeated violations doctrine “divides\\n\\nwhat might otherwise represent a single, time-barred cause of action into several\\n\\nseparate claims, at least one of which accrues within the limitations period prior to\\n\\nsuit.” Graham, supra, at 275 (emphasis added). That division, in turn, “allows\\n\\nrecovery for only that part of the injury the plaintiff suffered during the limitations\\n\\nperiod”; recovery for the part of the injury suffered outside of the limitations period,\\n\\nhowever, remains unavailable. White v. Mercury Marine, Div. of Brunswick, Inc.,\\n\\n129 F.3d 1428, 1430 (11th Cir. 1997); see also, e.g., Figueroa v. D.C. Metro. Police\\n\\nDep’t, 633 F.3d 1129, 1135 (D.C. Cir. 2011) (addressing how repeated violations\\n\\ninfluence the statute of limitations); Provident Mut. Life Ins. Co. of Phila. v. City of\\n\\nAtlanta, 864 F. Supp. 1274, 1284–85 (N.D. Ga. 1994) (describing an instance of the\\n\\nrepeated violations doctrine at work and observing that the plaintiff “may secure only\\n\\nactual damages incurred within the [limitations period] preceding the date upon\\n\\nwhich the action was filed”); Russo Farms, Inc. v. Vineland Bd. of Educ., 675 A.2d\\n\\n1077, 1084 (N.J. 1996) (same). Mr. Graham again provides a useful visual aid that\\n\\nillustrates just how this doctrine operates. As shown below, the repeated violations\\n\\ndoctrine “transforms what would otherwise represent a single, time-barred claim A\\n\\n\\n\\n 4\\n Other courts and scholars have sometimes referred to this doctrine as the\\n“modified” continuing violation doctrine. See, e.g., White, 129 F.3d at 1430;\\nGraham, supra, at 283.\\n 10\\n\\finto a series of fresh claims, identified as claims B, C, D, etc.” Graham, supra, at\\n\\n281.\\n\\n\\n\\n\\n Notably, although Plaintiff argued in the district court that both the continuing\\n\\nviolation doctrine and the repeated violations doctrine could make timely his claims\\n\\nunder Title II of the ADA and section 504 of the RA, on appeal he argues only for\\n\\napplication of the repeated violations doctrine.5 Indeed, in his Opening Brief,\\n\\nPlaintiff argues that\\n\\n [e]ach time [he] was denied access to [the sidewalks and curb cuts], the\\n City of Trinidad committed discrimination within the meaning of the\\n ADA/§504 and a claim for damages arose under the statute. [Plaintiff]\\n experienced recurrent discrimination by the City of Trinidad both inside\\n and outside of the statute of limitations period. Accordingly, [Plaintiff]\\n had some claims that are timely and some that are time barred.\\n\\n\\n\\n\\n 5\\n Plaintiff, in other words, abandoned his continuing violations argument on\\nappeal. We thus do not consider it. See United States v. Yelloweagle, 643 F.3d\\n1275, 1280 (10th Cir. 2011) (“[W]here [an appellant] raises an issue before the\\ndistrict court but does not pursue it on appeal, we ordinarily consider the issue\\nwaived.”).\\n 11\\n\\fPl.’s Opening Br. 7 (emphases added). This language is a clear reference to the\\n\\nrepeated violations doctrine.\\n\\n Although Plaintiff abandons the continuing violation doctrine on appeal, the\\n\\nCity continues to view the case in that context. In the City’s view, the Supreme\\n\\nCourt’s analysis of the continuing violation doctrine in National Railroad Passenger\\n\\nCorp. v. Morgan, 536 U.S. 101 (2002), is controlling. In Morgan, the Supreme Court\\n\\nconsidered how statutes of limitations apply to various claims under Title VII of the\\n\\nCivil Rights Act of 1964. For hostile work environment claims, the Supreme Court\\n\\nheld that “consideration of the entire scope of [the] claim, including behavior alleged\\n\\noutside the statutory time period, is permissible for the purposes of assessing\\n\\nliability, so long as an act contributing to that hostile environment takes place within\\n\\nthe statutory time period.” Id. at 105. The Supreme Court reasoned that hostile work\\n\\nenvironment claims “cannot be said to occur on any particular day” and instead\\n\\n“occur[] over a series of days or perhaps years.” Id. at 115. Because “[s]uch claims\\n\\nare based on the cumulative effect of individual acts,” “[i]t does not matter . . . that\\n\\nsome of the component acts of the hostile work environment fall outside the statutory\\n\\ntime period.” Id. at 115, 117.\\n\\n The City argues that Morgan precludes us from applying the continuing\\n\\nviolation doctrine to Plaintiff’s Title II and section 504 claims because the City\\n\\nsubjected him to only “discrete acts of discrimination” that “did not require proof” of\\n\\nthe cumulative effect of individual acts. Def.’s Resp. Br. 11. Although that\\n\\nargument is correct, it misses the mark insofar as it assails an argument Plaintiff does\\n\\n 12\\n\\fnot make on appeal. Contrary to the way the City frames the issue, Plaintiff does not\\n\\ncontend that he should be able to aggregate separate acts into one single,\\n\\ncomprehensive violation. Instead, he argues that he may recover for injuries he\\n\\nsuffered inside of the limitations period but not for injuries he suffered outside of the\\n\\nlimitations period—that is, he is arguing for application of the repeated violations\\n\\ndoctrine. Morgan, therefore, is inapposite to this appeal because it did not involve\\n\\nthe repeated violations doctrine. Indeed, the language of that case—e.g., that hostile\\n\\nwork environments are made up of “component acts” and “are based on the\\n\\ncumulative effect of individual acts”—makes it clear it was immediately concerned\\n\\nwith interpreting and applying the continuing violation doctrine.\\n\\n The City further relies on our unpublished decision in Rhodes v. Langston\\n\\nUniversity, 462 F. App’x 773 (10th Cir. 2011). In Rhodes, the plaintiff argued that\\n\\nthe alleged Title II and section 504 violations at issue could not “be tied to specific\\n\\ndates as all were on-going events.” Id. at 780. He thus argued that the district court\\n\\nerred in concluding that the applicable two-year statute of limitations barred any of\\n\\nhis claims—including those based on acts that occurred outside of the limitations\\n\\nperiod—because they amounted to “a continuation . . . of related and repetitive\\n\\nunlawful acts or practices” that only concluded within that two-year period. Id.\\n\\nAlthough we ultimately determined that the plaintiff’s argument had no merit, that\\n\\ndetermination does not bear upon the outcome of Plaintiff’s current appeal before us\\n\\ntoday. Like the Supreme Court’s language in Morgan, our language in Rhodes shows\\n\\nthat we were concerned in that case with whether the continuing violation doctrine,\\n\\n 13\\n\\fnot the repeated violations doctrine, applied to Title II and section 504 claims. Thus,\\n\\nthe City’s attempt to analogize Plaintiff’s arguments to Rhodes is equally\\n\\nunconvincing.\\n\\n Finally, the City directs us to Foster v. Morris, 208 F. App’x 174 (3d Cir.\\n\\n2006) (unpublished). In that case, the Third Circuit concluded that the continuing\\n\\nviolation doctrine, not the repeated violations doctrine, does not apply to Title II\\n\\nclaims. See, e.g., id. at 177 (“The continuing violations doctrine is an equitable\\n\\nexception to a strict application of a statute of limitations where the conduct\\n\\ncomplained of consists of a pattern that has only become cognizable as illegal over\\n\\ntime.”); id. at 177–78 (“When a defendant’s conduct is part of a continuing practice,\\n\\nan action is timely so long as the last act evidencing the continuing practice falls\\n\\nwithin the limitations period; in such an instance, the court will grant relief for the\\n\\nearlier related acts that would otherwise be time barred.” (internal quotation marks\\n\\nand alterations omitted)). And interestingly enough, although Foster did not address\\n\\nthe repeated violations doctrine outright, Foster’s underlying reasoning actually\\n\\nsupports—or, at the very least, leaves room open for—that doctrine in the Title II and\\n\\nSection 504 context. Indeed, the Third Circuit concluded that the plaintiff in that\\n\\ncase was “still entitled to recover for any violations that occurred during” the\\n\\nlimitations period even though he could not recover for any violations that occurred\\n\\n\\n\\n\\n 14\\n\\foutside that period. Id. at 178. That logic is perfectly consistent with the repeated\\n\\nviolations doctrine. So no matter how we slice it, Foster cannot help the City.6\\n\\n Because none of the cases the City cites resolve whether the repeated\\n\\nviolations doctrine applies to Plaintiff’s claims under Title II and section 504, we\\n\\nturn to the statutory text to decide this matter of first impression in our circuit.\\n\\n III.\\n\\n We hold that the repeated violations doctrine applies to claims under Title II of\\n\\nthe Americans with Disabilities Act and section 504 of the Rehabilitation Act of\\n\\n1973. As we explain below, a public entity repeatedly violates those two statutes\\n\\neach day that it fails to remedy a non-compliant service, program, or activity.\\n\\nAccordingly, a qualified individual with a disability is excluded from the\\n\\nparticipation in, denied the benefits of, and subjected to discrimination under the\\n\\nservice, program, or activity each day that she is deterred from utilizing it due to its\\n\\nnon-compliance. She stops suffering a daily injury only when the public entity\\n\\n\\n 6\\n Although neither party cites it, we also note that the Fifth Circuit’s decision\\nin Frame v. City of Arlington, 657 F.3d 215 (5th Cir. 2011) (en banc), does not bear\\non Plaintiff’s present appeal. The Frame court held that a single cause of action\\naccrues under Title II and section 504 when the plaintiff “has sufficient information\\nto know that he has been denied the benefits of a service, program, or activity of a\\npublic entity.” Id. at 238. One may think that holding amounts to a rejection of the\\nrepeated violations doctrine. But the question whether the repeated violations\\ndoctrine applies to Title II claims was not before the court in Frame. Indeed, Frame\\nonly considered whether a Title II cause of action accrues when the plaintiff\\ndiscovers he has been injured or when the public entity engaged in the wrongful act\\nthat caused the injury. Id. at 238–40. Nothing in its holding rejects or is inconsistent\\nwith the repeated violations doctrine. Thus, for our purposes today, Frame is of\\nlimited value.\\n\\n 15\\n\\fremedies the non-compliant service, program, or activity or when she no longer\\n\\nevinces an intent to utilize it. The practical effect is that, once the individual sues\\n\\nunder Title II or section 504, the statute of limitations bars recovery only for those\\n\\ninjuries she incurred outside of the limitations period immediately preceding the day\\n\\nof suit; it does not, however, bar recovery for injuries she incurred within that\\n\\nlimitations period or after she files suit.\\n\\n A.\\n\\n Our starting point is the plain language of Title II and section 504. See\\n\\nLevorsen v. Octapharma Plasma, Inc., 828 F.3d 1227, 1231 (10th Cir. 2016). If that\\n\\nlanguage is “clear and unambiguous,” then “our duty is simply to enforce the statute\\n\\nthat Congress has drafted.” United States v. Brown, 529 F.3d 1260, 1264 (10th Cir.\\n\\n2008) (quoting United States v. Ortiz, 427 F.3d 1278, 1282 (10th Cir. 2005)).\\n\\nSignificantly, though, “the meaning of statutory language, plain or not, depends on\\n\\ncontext.” First Nat’l Bank of Durango v. Woods (In re Woods), 743 F.3d 689, 694\\n\\n(10th Cir. 2014) (quoting United States v. Villa, 589 F.3d 1334, 1343 (10th Cir.\\n\\n2009)). We thus need not constrain ourselves to the “language itself” in determining\\n\\nwhether Title II and section 504 clearly and unambiguously convey when and how\\n\\noften a public entity violates these two statutes. Salazar v. Butterball, LLC, 644 F.3d\\n\\n1130, 1137 (10th Cir. 2011) (quoting Robinson v. Shell Oil Co., 519 U.S. 337, 340\\n\\n(1997)). Rather, we may also look to “the specific context in which that language is\\n\\nused” and “the broader context of the statute as a whole.” Id. (quoting Robinson, 519\\n\\nU.S. at 340). Both the text and structure of the statutes guide our decision today.\\n\\n 16\\n\\f Consider first the specific language. Title II mandates that “no qualified\\n\\nindividual with a disability shall, by reason of such disability, be excluded from\\n\\nparticipation in or be denied the benefits of the services, programs, or activities of a\\n\\npublic entity, or be subjected to discrimination by any such entity.” 42 U.S.C.\\n\\n§ 12132. Likewise, section 504 mandates in part that “[n]o otherwise qualified\\n\\nindividual with a disability in the United States . . . shall, solely by reason of her or\\n\\nhis disability, be excluded from the participation in, be denied the benefits of, or be\\n\\nsubjected to discrimination under any program or activity receiving Federal financial\\n\\nassistance.” 29 U.S.C. § 794(a).\\n\\n Obviously, neither of these statutes state outright when or how often a public\\n\\nentity violates them. They simply command that no qualified individual may “be\\n\\nexcluded” from, “be denied” the benefits of, or “be subjected” to discrimination\\n\\nunder a service, program, or activity. With that said, that language is phrased in the\\n\\npresent tense (albeit in the passive voice), which suggests that a qualified individual\\n\\nwho currently experiences discrimination under Title II or section 504 suffers an\\n\\ninjury. And so the same language also suggests that a qualified individual suffers\\n\\nnew discrimination and a new injury each day that she cannot utilize a non-compliant\\n\\nservice, program, or activity—even if the barriers giving rise to her claim were ones\\n\\nshe encountered before. After all, if sidewalks and curb cuts actually do constitute a\\n\\nservice, program, or activity of a public entity—a question that we express no\\n\\nopinion on today—a qualified individual with a disability would still “be excluded”\\n\\nfrom utilizing any given sidewalk or curb cut each day that it remained non-\\n\\n 17\\n\\fcompliant.7 Likewise, that same individual would still “be denied” the benefits of\\n\\nthat sidewalk or curb cut when she encountered it a day ago just as much as when she\\n\\nfirst encountered it a year ago. Cf. Pickern v. Holiday Quality Foods Inc., 293 F.3d\\n\\n1133, 1136 (9th Cir. 2002) (interpreting the phrases “is being subjected to” and “is\\n\\nabout to be subjected to” in the enforcement provision of Title III of the ADA and\\n\\nconcluding that they “make[] clear that either a continuing or a threatened violation\\n\\nof the ADA is an injury within the meaning of the Act”); Scherr v. Marriott Int’l,\\n\\nInc., 703 F.3d 1069, 1075–76 (7th Cir. 2013) (relying on Pickern and concluding the\\n\\nsame).\\n\\n To the extent any real or perceived gaps remain in the statutory text, the\\n\\nSupreme Court’s Title II jurisprudence fills them. In Tennessee v. Lane, 541 U.S.\\n\\n509 (2004), the Supreme Court recognized “that failure to accommodate persons with\\n\\ndisabilities will often have the same practical effect as outright exclusion.” Id. at 531\\n\\n(citing 42 U.S.C. § 12131(2)). Title II therefore imposes “an affirmative obligation\\n\\nto accommodate persons with disabilities.” Id. at 533.8\\n\\n\\n 7\\n We assume only for the purposes of this appeal that sidewalks and curb cuts\\nconstitute a service, program, or activity.\\n 8\\n As Plaintiff points out, numerous regulations implementing the ADA reflect\\nthis principle. See, e.g., 28 C.F.R. § 35.133(a) (“A public entity shall maintain in\\noperable working condition those features of facilities and equipment that are\\nrequired to be readily accessible to and usable by persons with disabilities . . . .”\\n(emphasis added)); id. § 35.150(a) (“A public entity shall operate each service,\\nprogram, or activity so that the service, program, or activity, when viewed in its\\nentirety, is readily accessible to and usable by individuals with disabilities.”\\n(emphasis added)); id. § 35.150(d) (allowing public entities to create a multi-year\\nplan to remove existing barriers); id. § 35.151(b)(1) (“Each facility or part of a\\n 18\\n\\f This “duty to accommodate,” id. at 532, solidifies that Title II (and, by\\n\\nextension, section 504) clearly and unambiguously conveys that a non-compliant\\n\\nservice, program, or activity gives rise to repeated violations.9 Failing to act in the\\n\\nface of an affirmative duty to do so axiomatically gives rise to liability. Cf., e.g.,\\n\\nRestatement (First) of Torts § 284 (1934) (“Negligent conduct may be . . . a failure to\\n\\ndo an act which is necessary for the . . . assistance of another and which the actor is\\n\\nunder a duty to do.”); Restatement (Second) of Torts § 824 (1979) (“The conduct\\n\\nnecessary to make the actor liable for . . . nuisance may consist of . . . a failure to act\\n\\nunder circumstances in which the actor is under a duty to take positive action . . . .”).\\n\\nFurther, if the actor under the affirmative duty keeps failing to act while the\\n\\nunderlying problem remains unremedied, then every day’s inaction amounts to a new\\n\\nviolation. Cf., e.g., Grant, 505 F.3d at 1028 (observing that continuing temporary\\n\\nnuisances “give[] rise over and over to new causes of action” until they are abated\\n\\n(internal quotation marks and alteration omitted)). Thus, even though “adverse\\n\\neffects resulting from” a single, original violation do not trigger the repeated\\n\\n\\nfacility . . . shall . . . be altered in such manner that the altered portion of the facility\\nis readily accessible to and usable by individuals with disabilities.” (emphases\\nadded)).\\n 9\\n In addition to the fact that we analyze Title II and section 504 claims\\ntogether, Miller ex rel. S.M., 565 F.3d at 1245, the language of the RA itself also\\nsuggests an affirmative duty to accommodate. See, e.g., 29 U.S.C. § 701(c)(2)\\n(requiring “the use of accessible formats” for qualified individuals with disabilities);\\nsee also Alexander v. Choate, 469 U.S. 287, 301 (1985) (observing that qualified\\nindividuals with disabilities under the RA are entitled to “meaningful access” and\\n“reasonable accommodations”).\\n\\n 19\\n\\fviolations doctrine when they do not constitute violations in their own right,\\n\\nLedbetter v. Goodyear Tire & Rubber Co., 550 U.S. 618, 628 (2007), overturned on\\n\\nother grounds by The Lilly Ledbetter Fair Pay Act of 2009, Pub. L. No. 111–2, 123\\n\\nStat. 5 (2009), claims under Title II (and section 504 by extension) do not fit that\\n\\nrubric. Rather, a public entity does commit a “new violation” each day that it fails to\\n\\nremedy a non-compliant service, program, or activity. The affirmative, ongoing duty\\n\\nthat Title II and section 504 place upon it mandates as much. Id. 10,11\\n\\n\\n 10\\n The City notes and relies on the Fourth Circuit’s opinion in A Society\\nWithout A Name v. Virginia, 655 F.3d 342 (4th Cir. 2011), which concluded that a\\nclaim under Title II did not trigger the principles of the repeated violations doctrine\\nbecause that claim only gave rise to “the continuing ill effects of [one] original\\nviolation.” Id. at 348–49. We do not find that case persuasive, however, because it\\nnever factored in the mandate that Title II imposes an affirmative duty to\\naccommodate. See id.\\n 11\\n At this point, we believe that an analogy to temporary nuisance claims—one\\nof the “touchstone” instances of the repeated violations doctrine at work, Graham,\\nsupra, at 308—can further illustrate our rationale. A temporary nuisance exists\\n“[w]here the injury from the alleged nuisance . . . is of a continuing or recurring\\ncharacter.” 58 Am. Jur. 2d Nuisances § 221 (2018). “In such a case, every day’s\\ncontinuance is a new nuisance,” id., that “gives rise over and over to new causes of\\naction,” Grant, 505 F.3d at 1028 (internal quotation marks and alteration omitted).\\nThe practical effect is that “a new statute of limitations begins to run . . . after each\\nnew injury,” 58 Am. Jur. 2d Nuisances § 253 (2018) (emphasis added), and the final\\nstatute of limitations accrues only when the temporary nuisance is remedied once and\\nfor all. See Grant, 505 F.3d at 1028. Thus, so long as the temporary nuisance\\ncontinues unabated, a plaintiff bringing suit is effectively doing so on “day one” of a\\nnew limitations period, which enables her to seek damages for past injuries sustained\\n“within the limitations period immediately prior to suit.” Id. (internal quotation\\nmarks omitted).\\n So too here. Each time a qualified individual with a disability is excluded\\nfrom, denied the benefits of, or subjected to discrimination under a service, program,\\nor activity, he suffers an injury under Title II and section 504. For the reasons we\\nexplained above, this injury is not a one-time event; rather, it repeatedly occurs so\\nlong as the service, program, or activity remains non-compliant and the qualified\\n 20\\n\\f The broader statutory context of the ADA and RA bolsters this conclusion.\\n\\nConsider, for example, 42 U.S.C. § 12101, which outlines Congress’s express\\n\\nstatutory purposes for enacting the ADA. There, Congress noted that “the Nation’s\\n\\nproper goals regarding individuals with disabilities are to assure . . . full\\n\\nparticipation . . . for such individuals.” 42 U.S.C. § 12101(a)(7). Congress made a\\n\\nsimilar conclusion earlier when it enacted 29 U.S.C. § 701, which lists the purposes\\n\\nof the RA. In that statute, Congress noted that it hoped to achieve “full inclusion and\\n\\nintegration in society” for individuals with disabilities and that an entity charged with\\n\\ncarrying out the RA should always consider “the principle[] of . . . full participation\\n\\nof the individuals.” 29 U.S.C. § 701(a)(6)(B), (c)(3).\\n\\n Congress’s goals of full participation, inclusion, and integration for qualified\\n\\nindividuals with disabilities are consistent with and suggestive of the repeated\\n\\nviolations doctrine. A qualified individual is not a full participant or fully included\\n\\nin a service, program, or activity if she cannot utilize it in a similar way as persons\\n\\nwithout disabilities, and that does not change simply because she was deterred from\\n\\nutilizing the service, program, or activity many times before. What matters is\\n\\nwhether the individual can fully participate now in the service, program, or activity.\\n\\nThe repeated violations doctrine, in turn, accounts for that reality—and, for that\\n\\nmatter, encourages public entities to comply with their affirmative and ongoing\\n\\n\\n\\nindividual is aware of that and deterred from utilizing it. So when a Title II or\\nsection 504 plaintiff brings suit, he is essentially doing so on the first day of a new\\nlimitations period.\\n 21\\n\\fobligations to accommodate—by giving a qualified individual an avenue for relief\\n\\nany moment that he or she cannot fully participate or is not fully included in a\\n\\nservice, program, or activity.\\n\\n Congress further observed in enacting the ADA that “the continuing existence\\n\\nof unfair and unnecessary discrimination and prejudice denies people with disabilities\\n\\nthe opportunity to compete on an equal basis and to pursue those opportunities for\\n\\nwhich our free society is justifiably famous . . . .” 42 U.S.C. § 12101(a)(8) (emphasis\\n\\nadded). It also noted that it hoped “to address the major areas of discrimination faced\\n\\nday-to-day by people with disabilities.” Id. § 12101(b)(4) (emphasis added).\\n\\nSimilarly, when it previously enacted the RA, Congress had discerned that\\n\\n“individuals with disabilities continually encounter various forms of discrimination.”\\n\\n29 U.S.C. § 701(a)(5) (emphasis added). This language demonstrates that Congress\\n\\nunderstood that a public entity could repeatedly cause a qualified individual with a\\n\\ndisability to suffer an injury from the same service, program, or activity. Certainly,\\n\\nnothing in the text of Title II or section 504 suggests otherwise.\\n\\n The statutory text and the Supreme Court’s pronouncements make one thing\\n\\nclear: Congress did not design the ADA or the RA so that a public entity could\\n\\nforever prevent a qualified individual with a disability from utilizing a service,\\n\\nprogram, or activity. Yet the City argues for that exact result. The City contends\\n\\nthat because Plaintiff filed suit more than two years after he first encountered the\\n\\nallegedly non-compliant sidewalks and curb cuts, the statute of limitations forever\\n\\nbars him from forcing the City to live up to its affirmative duty and correct those\\n\\n 22\\n\\fbarriers. That proposition simply cannot fit within the language, structure, and\\n\\npurpose of the ADA or the RA.\\n\\n In conclusion, based on the plain language of Title II of the ADA and section\\n\\n504 of the RA, Supreme Court jurisprudence interpreting Title II, and Congress’s\\n\\nexpress statutory purposes in enacting the ADA and RA, we hold that Title II and\\n\\nsection 504 clearly and unambiguously require us to acknowledge they are subject to\\n\\nthe repeated violations doctrine.12 Accordingly, each time a qualified individual with\\n\\na disability encounters or “actually become[s] aware of” a non-compliant service,\\n\\nprogram, or activity “and is thereby deterred” from utilizing that service, program, or\\n\\nactivity, he or she suffers discrimination and a cognizable injury. Pickern, 293 F.3d\\n\\n\\n 12\\n Because Title II and section 504 are unambiguous in this regard, we have no\\nreason to consider “the underlying public policy” of either statute. United States v.\\nManning, 526 F.3d 611, 614 (10th Cir. 2008) (quoting United States v. LaHue, 170\\nF.3d 1026, 1028 (10th Cir. 1999)); see also id. (“If the statutory language is clear, our\\nanalysis ordinarily ends.”). Even so, we observe as a side note that applying the\\nrepeated violations doctrine to claims under Title II and section 504 serves the\\ninterests of efficiency. In Title II and section 504 cases, “more than just the rights of\\nthe plaintiff before the court are at stake.” Graham, supra, at 321. Indeed, many\\nother qualified individuals with disabilities also benefit from a ruling favorable to the\\nplaintiff. To use this case as an example, if Plaintiff were to succeed in requiring the\\nCity of Trinidad to further remedy its sidewalks and curb cuts, other individuals who\\nuse wheelchairs would likewise reap the rewards. So if we were not to apply the\\nrepeated violations doctrine to Plaintiff’s claims and therefore forever bar those\\nclaims on statute of limitations grounds, “a substantively similar but timely suit\\nbrought by a different plaintiff”—namely, another qualified individual unable to\\nutilize the City’s sidewalks and curb cuts—“could land in [this Court’s] lap soon\\nthereafter.” Id. Thus, although the clear and unambiguous language of these two\\nstatutes carries the day, we note the inherent good sense in “entertaining the claim[s]\\nat hand” but limiting Title II and section 504 plaintiffs “to only those damages\\nsuffered within the limitations period and, perhaps more important, to injunctive\\nrelief.” Id.\\n\\n 23\\n\\fat 1136–37. So long as the service, program, or activity remains non-compliant, “and\\n\\nso long as a plaintiff is aware of [that] and remains deterred,” the qualified\\n\\nindividual’s injury repeats. Id. at 1137. A defendant, therefore, cannot brandish the\\n\\nstatute of limitations in its usual manner as a shield that fully protects he, she, or it\\n\\nfrom suit. But the defendant can wield the statute of limitations as a sword that\\n\\nchops off damages arising before the limitations period comes into play.\\n\\n B.\\n\\n The City of Trinidad and the Colorado Municipal League (“the League”) as\\n\\namicus curiae both claim that our ruling today will effectively “nullify the statute of\\n\\nlimitations.” Def.’s Resp. Br. 24.\\n\\n Not so for several reasons. For starters, both the City and the League conflate\\n\\nthe repeated violations doctrine and continuing violation doctrine—or at least\\n\\nconflate which of the two Plaintiff is arguing for on appeal—which likely has\\n\\ncontributed to that belief. See supra. But setting that point aside, we “will look\\n\\nbeyond the plain language of a statute only if the result is an absurd application of the\\n\\nlaw.” Brown, 529 F.3d at 1265 (emphasis in original). Observing that the repeated\\n\\nviolations doctrine applies to Title II and section 504 claims, however, does not result\\n\\nin any absurd statute-of-limitations outcomes. Indeed, the statute of limitations still\\n\\nhas an important role to play even when the repeated violations doctrine applies to a\\n\\nclaim. Namely, although the statute of limitations does not bar an untimely lawsuit\\n\\nin its entirety in such an instance, it nonetheless limits the plaintiff’s ability to\\n\\nrecover damages to only those injuries incurred during the limitations period\\n\\n 24\\n\\fimmediately preceding suit (the plaintiff, of course, can also recover damages for any\\n\\ninjuries incurred after filing suit).13 White, 129 F.3d at 1430. By contrast, the\\n\\nrepeated violations doctrine prevents a plaintiff from recovering damages for every\\n\\ninjury she suffered throughout history that relates to the non-compliant service,\\n\\nprogram, or activity.14 Cf., e.g., Foster, 208 F. App’x at 178. If Plaintiff, for\\n\\nexample, had first discovered the City’s non-compliant sidewalks and curb cuts in\\n\\n1996 but still brought suit in 2016, he would not be able to recover damages for\\n\\nevery injury he sustained throughout those twenty years; he would be restricted to\\n\\nthose injuries he suffered after October 12, 2014. This in itself substantially limits a\\n\\npublic entity’s liability under Title II and section 504.\\n\\n\\n 13\\n Theoretically, the statute of limitations could still function as a complete bar\\nto an untimely lawsuit even when the repeated violations doctrine applies. Suppose,\\nfor instance, a plaintiff was first deterred from utilizing a service, program, or\\nactivity in 2009 and tries to bring a lawsuit in 2019 for violations of Title II and\\nsection 504 against the public entity responsible. But also suppose the plaintiff\\nconcedes that in 2016 the public entity completely and entirely remedied the non-\\ncompliant service, program, or activity. Assuming a two-year statute of limitations\\napplies, it would entirely bar the plaintiff’s claims even though the repeated\\nviolations doctrine also applies to his claims. Indeed, the public entity’s last possible\\nrepeated violation (and the plaintiff’s last possible injury) would have occurred in\\n2016 before the remedy went into place, which means that the statute of limitations\\nwould have run at some point in 2018. Accordingly, the 2019 lawsuit would be\\nuntimely because the plaintiff could not point to a violation or injury that occurred in\\nthe two years prior to the day he files suit.\\n We mention this scenario only to illustrate that it is possible. Our immediate\\nconcern, however, is with cases where the public entity has not remedied the non-\\ncompliant service, program, or activity. In such instances, the public entity is still\\ncommitting violations, and the qualified individual with a disability is still suffering\\ninjuries.\\n 14\\n The continuing violation doctrine would allow for such a recovery. See\\nMorgan, 536 U.S. at 105.\\n 25\\n\\f What’s more, Title II and section 504 plaintiffs are able to recover damages\\n\\nonly in the unusual case. Our circuit requires proof of intentional discrimination\\n\\nbefore a plaintiff can recover compensatory damages under section 504, Havens v.\\n\\nColo. Dep’t of Corr., 897 F.3d 1250, 1263 (10th Cir. 2018), and we have suggested\\n\\nthat as much is required under Title II, Moseley v. Bd. of Educ. of Albuquerque Pub.\\n\\nSch., 483 F.3d 689, 693 (10th Cir. 2007) (noting that Tenth Circuit precedent\\n\\nsuggests, but does not explicitly hold, “that proof of intentional discrimination is\\n\\nrequired for compensatory damages under Title II”); see also Miraglia v. Bd. of\\n\\nSupervisors of La. State Museum, 901 F.3d 565, 574 (5th Cir. 2018) (“To recover\\n\\ncompensatory damages for disability discrimination under Title II of the ADA, a\\n\\nplaintiff must also show that the discrimination was intentional.” (emphasis added)\\n\\n(internal quotation marks omitted)). And punitive damages are categorically\\n\\nunavailable for suits under Title II and section 504. Barnes v. Gorman, 536 U.S. 181,\\n\\n189 (2002). So Title II and section 504 plaintiffs are hard-pressed to receive any\\n\\nmonetary damages unless they can prove that a service, program, or activity is\\n\\nintentionally discriminatory toward individuals with disabilities, which is surely the\\n\\nexception rather than the rule. This stands as an additional limitation of a public\\n\\nentity’s liability under Title II and section 504.\\n\\n We agree with the City and the League, though, that the repeated violations\\n\\ndoctrine will manifest itself by keeping public entities on the hook for injunctive\\n\\nrelief as the years go by. After all, if a court grants an injunction requiring a public\\n\\nentity to remedy a program, service, or activity, we have a difficult time seeing just\\n\\n 26\\n\\fhow the court or public entity could divvy that injunction up in a way that limits it to\\n\\ninjuries the plaintiff incurred within the limitations period. See Holmberg v.\\n\\nAmbrecht, 327 U.S. 392, 396 (1946) (observing that equitable relief “eschews\\n\\nmechanical rules”).\\n\\n But the availability of injunctive relief itself does not raise any red flags. As\\n\\nwe described above, when Congress outlined its purposes and goals in enacting the\\n\\nADA and RA, it expressly noted that it sought full participation, inclusion, and\\n\\nintegration in society for individuals with disabilities. By remaining on the hook for\\n\\ninjunctive relief—as its affirmative obligation to accommodate requires—a public\\n\\nentity is incentivized to remedy non-compliant services, programs, or activities in a\\n\\nreasonable yet efficient manner to ensure that full participation. And along those\\n\\nsame lines, Plaintiff makes an excellent point: “public entities . . . have the ultimate\\n\\noption to avoid liability” by “simply mak[ing] their programs, services, and activities\\n\\naccessible for persons with disabilities.” Pl.’s Opening Br. 30; see also Frame v. City\\n\\nof Arlington, 657 F.3d 215, 239 (5th Cir. 2011) (en banc) (“The City may avoid\\n\\nliability whenever it chooses simply by building sidewalks right the first time, or by\\n\\nfixing its original unlawful construction. In other words, the City is not liable\\n\\nforever; it is responsible only for correcting its own mistakes.”).\\n\\n Further, as far as injunctive relief is concerned, we note that a qualified\\n\\nindividual with a disability no longer suffers an injury once he stops “assert[ing] an\\n\\nintent to return to the particular place (or places) where the violations are alleged to\\n\\nbe occurring.” Scherr, 703 F.3d at 1074, 1076; see also Frame, 657 F.3d at 238 (“[A]\\n\\n 27\\n\\fdisabled individual has no standing to challenge an inaccessible sidewalk until he can\\n\\nshow actual, concrete plans to use that sidewalk.” (internal quotation marks\\n\\nomitted)); Barney v. Pulsipher, 143 F.3d 1299, 1306 n.3 (10th Cir. 1998) (“A\\n\\n‘plaintiff cannot maintain a declaratory or injunctive action unless he or she can\\n\\ndemonstrate a good chance of being likewise injured in the future.’” (quoting Facio\\n\\nv. Jones, 929 F.2d 541, 544 (10th Cir. 1991))). Although this implicates Article III\\n\\nstanding, Scherr, 703 F.3d at 1073–76, the practical effect of that lack of intent\\n\\nwould insulate a public entity from a Title II or section 504 lawsuit seeking\\n\\nprospective injunctive relief. To use an extreme example, if Plaintiff were to move\\n\\naway from the City of Trinidad and had no intent to return, he would no longer be\\n\\nsuffering any injury—and, consequently, would lack standing to bring a suit for\\n\\nprospective injunctive relief—regardless of whether the City remedied the sidewalks\\n\\nand curb cuts that allegedly injured him in the past. And even if a qualified\\n\\nindividual still suffers an injury after many years, we note that at some point the\\n\\ndoctrine of laches may come into play. See SCA Hygiene Prods. Aktiebolag v. First\\n\\nQuality Baby Prods., LLC, 137 S. Ct. 954, 960 (2017) (“Laches is ‘a defense\\n\\ndeveloped by courts of equity’ to protect defendants against ‘unreasonable,\\n\\nprejudicial delay in commencing suit.’” (quoting Petrella v. Metro-Goldwyn-Mayer,\\n\\nInc., 572 U.S. 663, 667, 678 (2014)). This further cuts against the City’s and the\\n\\nLeague’s arguments that public entities will be exposed to unlimited liability.\\n\\n As a final note, we are not unsympathetic to the City’s and the League’s\\n\\narguments that public entities are constrained by limited budgets that do not easily\\n\\n 28\\n\\flend themselves to the constant ability to remedy ADA and RA issues.15 But again,\\n\\nliability for monetary damages is infrequent, which significantly softens the impact\\n\\nof our ruling today. See supra. And if a public entity truly is not liable, or if that\\n\\nentity has already taken significant steps to remedy or can establish that it has multi-\\n\\nyear plans in place to remedy a non-compliant service, program, or activity—as the\\n\\nCity has apparently done in this case—a factfinder will be able to ferret that out when\\n\\ndeciding the merits of any given case. See, e.g., Rife v. Okla. Dep’t of Pub. Safety,\\n\\n854 F.3d 637, 643 (10th Cir. 2017) (observing that factfinders find facts weighing on\\n\\nliability). Indeed, at least two other circuits have endorsed either the repeated\\n\\nviolations doctrine or continuing violation doctrine in the context of ADA Title III\\n\\nclaims, but neither the City nor the League have directed us to any evidence\\n\\nsuggesting that places of public accommodation located in those circuits have faced\\n\\nsignificant hardship by the courts’ respective applications of the doctrines. See\\n\\nPickern, 293 F.3d at 1136–37; Scherr, 703 F.3d at 1075–76.\\n\\n Thus, the City’s and the League’s concerns are unsubstantiated.\\n\\n IV.\\n\\n The district court did not recognize the impact of the repeated violations\\n\\ndoctrine on Plaintiff’s claims under Title II of the ADA and section 504 of the RA.\\n\\n\\n 15\\n The City contends that adopting the repeated violations doctrine will cause\\nthis inability to remedy ADA and RA issues, but it is mistaken. Even without the\\nrepeated violations doctrine, qualified individuals with disabilities who have\\nencountered the City’s non-compliant services, programs, or activities within the past\\ntwo years could just as easily bring lawsuits against the City. So the danger about\\nwhich the City complains exists even under their own interpretation of the law.\\n 29\\n\\fInstead, it concluded that Plaintiff could not “rely solely on the continued\\n\\ninaccessibility of the City’s sidewalks and curb cuts” to survive dismissal under\\n\\nColorado’s two-year statute of limitations.\\n\\n This was error. Because the district court applied an incorrect standard, it\\n\\ncould not determine under the proper framework how the two-year statute of\\n\\nlimitations affected Plaintiff’s claims. As a court of review, we will not decide that\\n\\ninquiry for the first time on appeal. Pignanelli v. Pueblo Sch. Dist. No. 60, 540 F.3d\\n\\n1213, 1218 (10th Cir. 2008). We thus remand the case to the district court to decide\\n\\nin the first instance under the framework set forth in this opinion which of Plaintiff’s\\n\\ninjuries he may seek relief for and which of those he may not. In so doing, the\\n\\ndistrict court will necessarily need to determine which of the City’s sidewalks and\\n\\ncurb cuts Plaintiff has actually been deterred from utilizing.16\\n\\n For the reasons set forth above, we REVERSE and REMAND for further\\n\\nproceedings consistent with this opinion.\\n\\n\\n\\n\\n 16\\n In issuing these instructions on remand, we emphasize once again that we\\ntake no stance on the question whether sidewalks and curb cuts qualify as a service,\\nprogram, or activity of a public entity. We also issue these instructions cognizant of\\nthe fact that the district court assumed—much like we did—that sidewalks and curb\\ncuts qualify as a service, program, or activity of a public entity so that it could reach\\nthe “narrower” and “dispositive” statute of limitations question. For those reasons,\\nthe district court may now find it necessary to definitively decide on remand whether\\nsidewalks and curb cuts qualify as a service, program, or activity of a public entity,\\nand it should not read anything in this opinion as preventing it from doing so.\\n 30\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2264,"cells":{"id":{"kind":"number","value":4620920,"string":"4,620,920"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Armando MENDEZ, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Mendez"},"decision_date":{"kind":"string","value":"2019-05-17"},"docket_number":{"kind":"string","value":"18-1259"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Hartz, Seymour, Holmes\", \"parties\": \"\", \"opinions\": [{\"author\": \"SEYMOUR, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 17, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n UNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v. No. 18-1259\\n\\n ARMANDO MENDEZ,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:17-CR-00434-RM-1)\\n _________________________________\\n\\nHoward A. Pincus, Office of the Federal Public Defender, Denver Colorado, for\\nDefendant-Appellant.\\n\\nPaul Farley, Assistant United States Attorney, (Jason R. Dunn, United States Attorney,\\nwith him on the brief), Office of the United States Attorney, Denver, Colorado, for\\nPlaintiff-Appellee.\\n _________________________________\\n\\nBefore HARTZ, SEYMOUR, and HOLMES, Circuit Judges.\\n _________________________________\\n\\nSEYMOUR, Circuit Judge.\\n _________________________________\\n\\n\\n\\n\\n Armando Mendez appeals the sentence imposed after he pled guilty in 2018 to\\n\\nviolating 18 U.S.C. § 922(g)(1), which prohibits felons from possessing firearms. On\\n\\fappeal, he contends his sentence was improperly inflated because the district court\\n\\nheld that a prior conviction for attempted robbery in Colorado qualified as a “crime\\n\\nof violence” under § 4B1.2(a) of the United States Sentencing Guidelines\\n\\n(“U.S.S.G.” or “the guidelines”). We affirm.\\n\\n\\n\\n I.\\n\\n Mr. Mendez entered an unconditional guilty plea but objected to the probation\\n\\nofficer’s presentence report, which calculated a recommended sentence of 30-37\\n\\nmonths under the sentencing guidelines. Specifically, Mr. Mendez disputed the\\n\\ndetermination that a 2001 conviction for attempted robbery in Colorado qualified as a\\n\\nprior “crime of violence,” which resulted in an enhanced base offense level of 20\\n\\nunder U.S.S.G. § 2K2.1(a)(4)(A). Arguing that the conviction did not qualify, Mr.\\n\\nMendez asked the court to impose a sentence of 15-21 months using a base offense\\n\\nlevel of 14, the level applicable to Mr. Mendez absent the crime-of-violence\\n\\nenhancement. After briefing and oral argument on the matter, the district court\\n\\nimposed a sentence of 30 months, holding that Mr. Mendez’s 2001 conviction was a\\n\\ncrime of violence.\\n\\n\\n II.\\n\\n Whether a prior conviction qualifies as a crime of violence for purposes of the\\n\\nsentencing guidelines is a matter of statutory interpretation. United States v. Charles,\\n\\n576 F.3d 1060, 1066 (10th Cir. 2009). Accordingly, our review is de novo. Id.\\n\\n 2\\n\\f We apply a categorical approach to determine whether a prior conviction falls\\n\\nwithin U.S.S.G. § 4B1.2(a),1 which provides that an offense is a “crime of violence”\\n\\nif (1) its elements include “the use, attempted use, or threatened use of physical force\\n\\nagainst the person of another”, or (2) the offense is any of several crimes enumerated\\n\\nin the guideline itself. See United States v. O’Connor, 874 F.3d 1147, 1151–52 (10th\\n\\nCir. 2017). Under the categorical approach, it is not the particular defendant’s\\n\\nconduct that counts but the scope of conduct that may be prosecuted under the statute\\n\\nof his conviction. Id. at 1151. Violation of the underlying statute must categorically\\n\\nconstitute a crime of violence for the enhancement to apply. If a course of conduct\\n\\nwould be criminal under the statute but the same conduct would not satisfy either\\n\\nprong of § 4B1.2(a), then no conviction under the statute will serve as a predicate.\\n\\nThe test is all or nothing. O’Connor, 874 F.3d at 1151.\\n\\n This case appears, on first blush, deceptively easy to resolve. The application\\n\\nnote appended to the guideline defining “crime of violence” clarifies that the term\\n\\nincludes “attempting to commit” such a crime. § 4B1.2 cmt. n.1. Moreover, we have\\n\\npreviously held that Colorado’s definition of robbery is a crime of violence under §\\n\\n4B1.2 because it involves the use or threatened use of physical force. See United\\n\\nStates v. Crump, 674 Fed. Appx. 802 (10th Cir. 2017) (unpublished); cf. United\\n\\nStates v. Harris, 844 F.3d 1260 (10th Cir. 2017) (holding that a conviction under\\n\\n\\n 1\\n The guideline governing the applicable base offense level for unlawful\\npossession of a firearm incorporates by reference the definition of “crime of\\nviolence” in § 4B1.2(a) and Application Note 1 of the commentary to § 4B1.2.\\nU.S.S.G. § 2K2.1 cmt. n.1.\\n 3\\n\\fColorado’s robbery statute triggers enhancement under 18 U.S.C. § 924(e)(1)). This,\\n\\nhowever, does not end our enquiry.\\n\\n Section 4B1.2 offers no definition of what constitutes “attempt.” If criminal\\n\\nattempt as defined by Colorado law covers a broader scope of conduct than “attempt”\\n\\nfor the purposes of the guidelines, then attempted robbery under Colorado law is not\\n\\ncategorically a crime of violence and Mr. Mendez is not subject to the enhancement.\\n\\nThe operative portion of Colorado’s criminal-attempt statute provides as follows:\\n\\n A person commits criminal attempt if, acting with the kind of culpability\\n otherwise required for commission of an offense, he engages in conduct\\n constituting a substantial step toward the commission of the offense. A\\n substantial step is any conduct . . . which is strongly corroborative of the\\n firmness of the actor’s purpose to complete the commission of the offense.\\n\\nColo. Rev. Stat. § 18-2-101(1). Because § 4B1.2 does not define attempt, we\\n\\ncompare Colorado’s law to a generic definition, which can be formulated by looking\\n\\nto “a wide range of sources . . . , including federal and state statutes, the Model Penal\\n\\nCode, dictionaries, and treatises.” See O’Connor, 874 F.3d at 1151. Here, both\\n\\nparties construct their arguments by comparing Colorado attempt to attempt under the\\n\\nModel Penal Code. We therefore see no reason to do otherwise.\\n\\n The Model Penal Code definition of attempt shares the same basic\\n\\nrequirements as Colorado’s definition, providing in relevant part that a person is\\n\\nguilty of criminal attempt when, acting with the required kind of culpability, he\\n\\nmakes a “a substantial step in a course of conduct planned to culminate in his\\n\\ncommission of the crime.” Model Penal Code § 5.01(1)(c). Conduct is not a\\n\\n\\n 4\\n\\fsubstantial step “unless it is strongly corroborative of the actor’s criminal purpose.”\\n\\nId. § 5.01(2).\\n\\n Mr. Mendez attempts to create some daylight between the two formulations by\\n\\ncrafting an argument based on formal logic. While Colorado and the Model Penal\\n\\nCode both require a substantial step, Mr. Mendez argues, they differ as to what\\n\\nconduct will qualify. Under the Model Penal Code, an act is not a substantial step\\n\\nunless the “strongly corroborative” element is met, but that does not necessarily\\n\\nmean that all “strongly corroborative” conduct will be a substantial step. See Aplt.\\n\\nBr. at 15–20. The Colorado formulation, by contrast, provides that “any conduct . . .\\n\\nwhich is strongly corroborative” will be a substantial step. Colo. Rev. Stat. § 18-2-\\n\\n101(1) (emphasis added). Because showing conduct “strongly corroborative” of\\n\\ncriminal intent is sufficient to prove a substantial step under Colorado law, Mr.\\n\\nMendez argues that Colorado criminalizes some conduct that the Model Penal Code\\n\\ndoes not. Therefore, he contends, a conviction for attempted robbery in Colorado is\\n\\nnot categorically a “crime of violence” for the purposes of the guidelines. We are not\\n\\nconvinced.\\n\\n Mr. Mendez’s hairsplitting focus on formal logic loses sight of the categorical\\n\\napproach’s purpose, which is to carry out congressional intent by giving a word its\\n\\ncommonly understood meaning when the statute itself leaves the term undefined. See\\n\\ngenerally Taylor v. United States, 495 U.S. 575, 597 (1990). A statute that mirrors\\n\\nthe generic definition of an offense but makes minor variations in terminology will\\n\\nsuffice if it “corresponds in substance to the generic meaning.” See id. at 599\\n\\n 5\\n\\f(applying a categorical analysis to a state’s burglary statute). Colorado’s definition\\n\\nof attempt hews closely to that of the Model Penal Code. Both require a substantial\\n\\nstep and both define substantial step by reference to the act’s probative value\\n\\nregarding the defendant’s criminal intent.\\n\\n Mr. Mendez points to People v. Lehnert, 163 P.3d 1111 (Colo. 2007), as\\n\\nevidence that the Colorado Supreme Court views the statute’s departure from the\\n\\nModel Penal Code as significant, implying that Colorado’s statute would now\\n\\ncriminalize “mere preparation.” See Aplt. Br. at 19–20; Aplt. Reply Br. at 3. His\\n\\nargument significantly overstates the court’s conclusions. In Lehnert, the Colorado\\n\\nSupreme Court traced the evolution of Colorado’s treatment of attempt. Id. The\\n\\ncourt explained that the emphasis of the current Colorado statute, like the Model\\n\\nPenal Code, is on the degree to which the defendant’s conduct corroborates his\\n\\ncriminal intent. Id. at 1114–15. Nothing in Lehnert supports the proposition that\\n\\nColorado’s statute would criminalize “mere preparation,” which the Lehnert court\\n\\nactually recognized as “a useful way of describing conduct falling short of a\\n\\n‘substantial step’” under the current statute. Id. at 1114.\\n\\n Significantly, Mr. Mendez’s assertion that Colorado criminalizes conduct that\\n\\nwould not qualify as an attempted robbery elsewhere is purely speculative. The\\n\\ncategorical approach focuses on the minimum conduct criminalized by the state\\n\\nstatute, but this “is not an invitation to apply ‘legal imagination’ to the state offense;\\n\\nthere must be ‘a realistic probability, not a theoretical possibility, that the State\\n\\nwould apply its statute to conduct that falls outside the generic definition of a\\n\\n 6\\n\\fcrime.’” Moncrieffe v. Holder, 569 U.S. 184, 191 (2013) (quoting Gonzales v.\\n\\nDuenas-Alvarez, 549 U.S. 183, 193 (2007)). Where a statute does not on its face\\n\\ncriminalize conduct outside the generic definition of the offense, it is not enough to\\n\\nargue that a state could interpret its statute to criminalize such conduct; the defendant\\n\\nmust show that the state has actually done so. See United States v. Titties, 852 F.3d\\n\\n1257, 1275 (10th Cir. 2017); see also Moncrieffe, 569 U.S. at 191. “[H]e must at\\n\\nleast point to his own case or other cases in which the state courts in fact did apply\\n\\nthe statute in the special (nongeneric) manner for which he argues.” Duenas-Alvarez,\\n\\n549 U.S. at 193; see also United States v. Alexander, 809 F.3d 1029, 1033 (8th Cir.\\n\\n2016) (rejecting categorical challenge to state attempt statute based on a lack of case\\n\\nlaw construing attempt overinclusively); United States v. Havis, 907 F.3d 439, 446\\n\\n(6th Cir. 2018) (same); United States v. Garcia-Figueroa, 753 F.3d 179, 189 (5th Cir.\\n\\n2014) (same).\\n\\n Mr. Mendez does no more than offer theoretical grounds on which some\\n\\nconduct might constitute criminal attempt in Colorado but not under the generic\\n\\ndefinition of the term. He offers no cases to demonstrate that the state has actually\\n\\nprosecuted anyone under his broader definition. He does not even offer a\\n\\nhypothetical course of conduct where it might. For the foregoing reasons, we agree\\n\\nwith the district court that attempted robbery as defined in Colorado law is a crime of\\n\\nviolence for the purposes of § 4B1.2(a). Accordingly, we AFFIRM Mr. Mendez’s\\n\\nsentence.\\n\\n\\n\\n 7\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4398173/\", \"author_raw\": \"SEYMOUR, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"HARTZ"},"judge2":{"kind":"string","value":"SEYMOUR"},"judge3":{"kind":"string","value":"HOLMES"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4620920/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Armando MENDEZ, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-17\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 17, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\n UNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\n v. No. 18-1259\n\n ARMANDO MENDEZ,\n\n Defendant - Appellant.\n _________________________________\n\n Appeal from the United States District Court\n for the District of Colorado\n (D.C. No. 1:17-CR-00434-RM-1)\n _________________________________\n\nHoward A. Pincus, Office of the Federal Public Defender, Denver Colorado, for\nDefendant-Appellant.\n\nPaul Farley, Assistant United States Attorney, (Jason R. Dunn, United States Attorney,\nwith him on the brief), Office of the United States Attorney, Denver, Colorado, for\nPlaintiff-Appellee.\n _________________________________\n\nBefore HARTZ, SEYMOUR, and HOLMES, Circuit Judges.\n _________________________________\n\nSEYMOUR, Circuit Judge.\n _________________________________\n\n\n\n\n Armando Mendez appeals the sentence imposed after he pled guilty in 2018 to\n\nviolating 18 U.S.C. § 922(g)(1), which prohibits felons from possessing firearms. On\n\fappeal, he contends his sentence was improperly inflated because the district court\n\nheld that a prior conviction for attempted robbery in Colorado qualified as a “crime\n\nof violence” under § 4B1.2(a) of the United States Sentencing Guidelines\n\n(“U.S.S.G.” or “the guidelines”). We affirm.\n\n\n\n I.\n\n Mr. Mendez entered an unconditional guilty plea but objected to the probation\n\nofficer’s presentence report, which calculated a recommended sentence of 30-37\n\nmonths under the sentencing guidelines. Specifically, Mr. Mendez disputed the\n\ndetermination that a 2001 conviction for attempted robbery in Colorado qualified as a\n\nprior “crime of violence,” which resulted in an enhanced base offense level of 20\n\nunder U.S.S.G. § 2K2.1(a)(4)(A). Arguing that the conviction did not qualify, Mr.\n\nMendez asked the court to impose a sentence of 15-21 months using a base offense\n\nlevel of 14, the level applicable to Mr. Mendez absent the crime-of-violence\n\nenhancement. After briefing and oral argument on the matter, the district court\n\nimposed a sentence of 30 months, holding that Mr. Mendez’s 2001 conviction was a\n\ncrime of violence.\n\n\n II.\n\n Whether a prior conviction qualifies as a crime of violence for purposes of the\n\nsentencing guidelines is a matter of statutory interpretation. United States v. Charles,\n\n576 F.3d 1060, 1066 (10th Cir. 2009). Accordingly, our review is de novo. Id.\n\n 2\n\f We apply a categorical approach to determine whether a prior conviction falls\n\nwithin U.S.S.G. § 4B1.2(a),1 which provides that an offense is a “crime of violence”\n\nif (1) its elements include “the use, attempted use, or threatened use of physical force\n\nagainst the person of another”, or (2) the offense is any of several crimes enumerated\n\nin the guideline itself. See United States v. O’Connor, 874 F.3d 1147, 1151–52 (10th\n\nCir. 2017). Under the categorical approach, it is not the particular defendant’s\n\nconduct that counts but the scope of conduct that may be prosecuted under the statute\n\nof his conviction. Id. at 1151. Violation of the underlying statute must categorically\n\nconstitute a crime of violence for the enhancement to apply. If a course of conduct\n\nwould be criminal under the statute but the same conduct would not satisfy either\n\nprong of § 4B1.2(a), then no conviction under the statute will serve as a predicate.\n\nThe test is all or nothing. O’Connor, 874 F.3d at 1151.\n\n This case appears, on first blush, deceptively easy to resolve. The application\n\nnote appended to the guideline defining “crime of violence” clarifies that the term\n\nincludes “attempting to commit” such a crime. § 4B1.2 cmt. n.1. Moreover, we have\n\npreviously held that Colorado’s definition of robbery is a crime of violence under §\n\n4B1.2 because it involves the use or threatened use of physical force. See United\n\nStates v. Crump, 674 Fed. Appx. 802 (10th Cir. 2017) (unpublished); cf. United\n\nStates v. Harris, 844 F.3d 1260 (10th Cir. 2017) (holding that a conviction under\n\n\n 1\n The guideline governing the applicable base offense level for unlawful\npossession of a firearm incorporates by reference the definition of “crime of\nviolence” in § 4B1.2(a) and Application Note 1 of the commentary to § 4B1.2.\nU.S.S.G. § 2K2.1 cmt. n.1.\n 3\n\fColorado’s robbery statute triggers enhancement under 18 U.S.C. § 924(e)(1)). This,\n\nhowever, does not end our enquiry.\n\n Section 4B1.2 offers no definition of what constitutes “attempt.” If criminal\n\nattempt as defined by Colorado law covers a broader scope of conduct than “attempt”\n\nfor the purposes of the guidelines, then attempted robbery under Colorado law is not\n\ncategorically a crime of violence and Mr. Mendez is not subject to the enhancement.\n\nThe operative portion of Colorado’s criminal-attempt statute provides as follows:\n\n A person commits criminal attempt if, acting with the kind of culpability\n otherwise required for commission of an offense, he engages in conduct\n constituting a substantial step toward the commission of the offense. A\n substantial step is any conduct . . . which is strongly corroborative of the\n firmness of the actor’s purpose to complete the commission of the offense.\n\nColo. Rev. Stat. § 18-2-101(1). Because § 4B1.2 does not define attempt, we\n\ncompare Colorado’s law to a generic definition, which can be formulated by looking\n\nto “a wide range of sources . . . , including federal and state statutes, the Model Penal\n\nCode, dictionaries, and treatises.” See O’Connor, 874 F.3d at 1151. Here, both\n\nparties construct their arguments by comparing Colorado attempt to attempt under the\n\nModel Penal Code. We therefore see no reason to do otherwise.\n\n The Model Penal Code definition of attempt shares the same basic\n\nrequirements as Colorado’s definition, providing in relevant part that a person is\n\nguilty of criminal attempt when, acting with the required kind of culpability, he\n\nmakes a “a substantial step in a course of conduct planned to culminate in his\n\ncommission of the crime.” Model Penal Code § 5.01(1)(c). Conduct is not a\n\n\n 4\n\fsubstantial step “unless it is strongly corroborative of the actor’s criminal purpose.”\n\nId. § 5.01(2).\n\n Mr. Mendez attempts to create some daylight between the two formulations by\n\ncrafting an argument based on formal logic. While Colorado and the Model Penal\n\nCode both require a substantial step, Mr. Mendez argues, they differ as to what\n\nconduct will qualify. Under the Model Penal Code, an act is not a substantial step\n\nunless the “strongly corroborative” element is met, but that does not necessarily\n\nmean that all “strongly corroborative” conduct will be a substantial step. See Aplt.\n\nBr. at 15–20. The Colorado formulation, by contrast, provides that “any conduct . . .\n\nwhich is strongly corroborative” will be a substantial step. Colo. Rev. Stat. § 18-2-\n\n101(1) (emphasis added). Because showing conduct “strongly corroborative” of\n\ncriminal intent is sufficient to prove a substantial step under Colorado law, Mr.\n\nMendez argues that Colorado criminalizes some conduct that the Model Penal Code\n\ndoes not. Therefore, he contends, a conviction for attempted robbery in Colorado is\n\nnot categorically a “crime of violence” for the purposes of the guidelines. We are not\n\nconvinced.\n\n Mr. Mendez’s hairsplitting focus on formal logic loses sight of the categorical\n\napproach’s purpose, which is to carry out congressional intent by giving a word its\n\ncommonly understood meaning when the statute itself leaves the term undefined. See\n\ngenerally Taylor v. United States, 495 U.S. 575, 597 (1990). A statute that mirrors\n\nthe generic definition of an offense but makes minor variations in terminology will\n\nsuffice if it “corresponds in substance to the generic meaning.” See id. at 599\n\n 5\n\f(applying a categorical analysis to a state’s burglary statute). Colorado’s definition\n\nof attempt hews closely to that of the Model Penal Code. Both require a substantial\n\nstep and both define substantial step by reference to the act’s probative value\n\nregarding the defendant’s criminal intent.\n\n Mr. Mendez points to People v. Lehnert, 163 P.3d 1111 (Colo. 2007), as\n\nevidence that the Colorado Supreme Court views the statute’s departure from the\n\nModel Penal Code as significant, implying that Colorado’s statute would now\n\ncriminalize “mere preparation.” See Aplt. Br. at 19–20; Aplt. Reply Br. at 3. His\n\nargument significantly overstates the court’s conclusions. In Lehnert, the Colorado\n\nSupreme Court traced the evolution of Colorado’s treatment of attempt. Id. The\n\ncourt explained that the emphasis of the current Colorado statute, like the Model\n\nPenal Code, is on the degree to which the defendant’s conduct corroborates his\n\ncriminal intent. Id. at 1114–15. Nothing in Lehnert supports the proposition that\n\nColorado’s statute would criminalize “mere preparation,” which the Lehnert court\n\nactually recognized as “a useful way of describing conduct falling short of a\n\n‘substantial step’” under the current statute. Id. at 1114.\n\n Significantly, Mr. Mendez’s assertion that Colorado criminalizes conduct that\n\nwould not qualify as an attempted robbery elsewhere is purely speculative. The\n\ncategorical approach focuses on the minimum conduct criminalized by the state\n\nstatute, but this “is not an invitation to apply ‘legal imagination’ to the state offense;\n\nthere must be ‘a realistic probability, not a theoretical possibility, that the State\n\nwould apply its statute to conduct that falls outside the generic definition of a\n\n 6\n\fcrime.’” Moncrieffe v. Holder, 569 U.S. 184, 191 (2013) (quoting Gonzales v.\n\nDuenas-Alvarez, 549 U.S. 183, 193 (2007)). Where a statute does not on its face\n\ncriminalize conduct outside the generic definition of the offense, it is not enough to\n\nargue that a state could interpret its statute to criminalize such conduct; the defendant\n\nmust show that the state has actually done so. See United States v. Titties, 852 F.3d\n\n1257, 1275 (10th Cir. 2017); see also Moncrieffe, 569 U.S. at 191. “[H]e must at\n\nleast point to his own case or other cases in which the state courts in fact did apply\n\nthe statute in the special (nongeneric) manner for which he argues.” Duenas-Alvarez,\n\n549 U.S. at 193; see also United States v. Alexander, 809 F.3d 1029, 1033 (8th Cir.\n\n2016) (rejecting categorical challenge to state attempt statute based on a lack of case\n\nlaw construing attempt overinclusively); United States v. Havis, 907 F.3d 439, 446\n\n(6th Cir. 2018) (same); United States v. Garcia-Figueroa, 753 F.3d 179, 189 (5th Cir.\n\n2014) (same).\n\n Mr. Mendez does no more than offer theoretical grounds on which some\n\nconduct might constitute criminal attempt in Colorado but not under the generic\n\ndefinition of the term. He offers no cases to demonstrate that the state has actually\n\nprosecuted anyone under his broader definition. He does not even offer a\n\nhypothetical course of conduct where it might. For the foregoing reasons, we agree\n\nwith the district court that attempted robbery as defined in Colorado law is a crime of\n\nviolence for the purposes of § 4B1.2(a). Accordingly, we AFFIRM Mr. Mendez’s\n\nsentence.\n\n\n\n 7\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Armando MENDEZ, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-17\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 17, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n UNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\n v. No. 18-1259\\n\\n ARMANDO MENDEZ,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:17-CR-00434-RM-1)\\n _________________________________\\n\\nHoward A. Pincus, Office of the Federal Public Defender, Denver Colorado, for\\nDefendant-Appellant.\\n\\nPaul Farley, Assistant United States Attorney, (Jason R. Dunn, United States Attorney,\\nwith him on the brief), Office of the United States Attorney, Denver, Colorado, for\\nPlaintiff-Appellee.\\n _________________________________\\n\\nBefore HARTZ, SEYMOUR, and HOLMES, Circuit Judges.\\n _________________________________\\n\\nSEYMOUR, Circuit Judge.\\n _________________________________\\n\\n\\n\\n\\n Armando Mendez appeals the sentence imposed after he pled guilty in 2018 to\\n\\nviolating 18 U.S.C. § 922(g)(1), which prohibits felons from possessing firearms. On\\n\\fappeal, he contends his sentence was improperly inflated because the district court\\n\\nheld that a prior conviction for attempted robbery in Colorado qualified as a “crime\\n\\nof violence” under § 4B1.2(a) of the United States Sentencing Guidelines\\n\\n(“U.S.S.G.” or “the guidelines”). We affirm.\\n\\n\\n\\n I.\\n\\n Mr. Mendez entered an unconditional guilty plea but objected to the probation\\n\\nofficer’s presentence report, which calculated a recommended sentence of 30-37\\n\\nmonths under the sentencing guidelines. Specifically, Mr. Mendez disputed the\\n\\ndetermination that a 2001 conviction for attempted robbery in Colorado qualified as a\\n\\nprior “crime of violence,” which resulted in an enhanced base offense level of 20\\n\\nunder U.S.S.G. § 2K2.1(a)(4)(A). Arguing that the conviction did not qualify, Mr.\\n\\nMendez asked the court to impose a sentence of 15-21 months using a base offense\\n\\nlevel of 14, the level applicable to Mr. Mendez absent the crime-of-violence\\n\\nenhancement. After briefing and oral argument on the matter, the district court\\n\\nimposed a sentence of 30 months, holding that Mr. Mendez’s 2001 conviction was a\\n\\ncrime of violence.\\n\\n\\n II.\\n\\n Whether a prior conviction qualifies as a crime of violence for purposes of the\\n\\nsentencing guidelines is a matter of statutory interpretation. United States v. Charles,\\n\\n576 F.3d 1060, 1066 (10th Cir. 2009). Accordingly, our review is de novo. Id.\\n\\n 2\\n\\f We apply a categorical approach to determine whether a prior conviction falls\\n\\nwithin U.S.S.G. § 4B1.2(a),1 which provides that an offense is a “crime of violence”\\n\\nif (1) its elements include “the use, attempted use, or threatened use of physical force\\n\\nagainst the person of another”, or (2) the offense is any of several crimes enumerated\\n\\nin the guideline itself. See United States v. O’Connor, 874 F.3d 1147, 1151–52 (10th\\n\\nCir. 2017). Under the categorical approach, it is not the particular defendant’s\\n\\nconduct that counts but the scope of conduct that may be prosecuted under the statute\\n\\nof his conviction. Id. at 1151. Violation of the underlying statute must categorically\\n\\nconstitute a crime of violence for the enhancement to apply. If a course of conduct\\n\\nwould be criminal under the statute but the same conduct would not satisfy either\\n\\nprong of § 4B1.2(a), then no conviction under the statute will serve as a predicate.\\n\\nThe test is all or nothing. O’Connor, 874 F.3d at 1151.\\n\\n This case appears, on first blush, deceptively easy to resolve. The application\\n\\nnote appended to the guideline defining “crime of violence” clarifies that the term\\n\\nincludes “attempting to commit” such a crime. § 4B1.2 cmt. n.1. Moreover, we have\\n\\npreviously held that Colorado’s definition of robbery is a crime of violence under §\\n\\n4B1.2 because it involves the use or threatened use of physical force. See United\\n\\nStates v. Crump, 674 Fed. Appx. 802 (10th Cir. 2017) (unpublished); cf. United\\n\\nStates v. Harris, 844 F.3d 1260 (10th Cir. 2017) (holding that a conviction under\\n\\n\\n 1\\n The guideline governing the applicable base offense level for unlawful\\npossession of a firearm incorporates by reference the definition of “crime of\\nviolence” in § 4B1.2(a) and Application Note 1 of the commentary to § 4B1.2.\\nU.S.S.G. § 2K2.1 cmt. n.1.\\n 3\\n\\fColorado’s robbery statute triggers enhancement under 18 U.S.C. § 924(e)(1)). This,\\n\\nhowever, does not end our enquiry.\\n\\n Section 4B1.2 offers no definition of what constitutes “attempt.” If criminal\\n\\nattempt as defined by Colorado law covers a broader scope of conduct than “attempt”\\n\\nfor the purposes of the guidelines, then attempted robbery under Colorado law is not\\n\\ncategorically a crime of violence and Mr. Mendez is not subject to the enhancement.\\n\\nThe operative portion of Colorado’s criminal-attempt statute provides as follows:\\n\\n A person commits criminal attempt if, acting with the kind of culpability\\n otherwise required for commission of an offense, he engages in conduct\\n constituting a substantial step toward the commission of the offense. A\\n substantial step is any conduct . . . which is strongly corroborative of the\\n firmness of the actor’s purpose to complete the commission of the offense.\\n\\nColo. Rev. Stat. § 18-2-101(1). Because § 4B1.2 does not define attempt, we\\n\\ncompare Colorado’s law to a generic definition, which can be formulated by looking\\n\\nto “a wide range of sources . . . , including federal and state statutes, the Model Penal\\n\\nCode, dictionaries, and treatises.” See O’Connor, 874 F.3d at 1151. Here, both\\n\\nparties construct their arguments by comparing Colorado attempt to attempt under the\\n\\nModel Penal Code. We therefore see no reason to do otherwise.\\n\\n The Model Penal Code definition of attempt shares the same basic\\n\\nrequirements as Colorado’s definition, providing in relevant part that a person is\\n\\nguilty of criminal attempt when, acting with the required kind of culpability, he\\n\\nmakes a “a substantial step in a course of conduct planned to culminate in his\\n\\ncommission of the crime.” Model Penal Code § 5.01(1)(c). Conduct is not a\\n\\n\\n 4\\n\\fsubstantial step “unless it is strongly corroborative of the actor’s criminal purpose.”\\n\\nId. § 5.01(2).\\n\\n Mr. Mendez attempts to create some daylight between the two formulations by\\n\\ncrafting an argument based on formal logic. While Colorado and the Model Penal\\n\\nCode both require a substantial step, Mr. Mendez argues, they differ as to what\\n\\nconduct will qualify. Under the Model Penal Code, an act is not a substantial step\\n\\nunless the “strongly corroborative” element is met, but that does not necessarily\\n\\nmean that all “strongly corroborative” conduct will be a substantial step. See Aplt.\\n\\nBr. at 15–20. The Colorado formulation, by contrast, provides that “any conduct . . .\\n\\nwhich is strongly corroborative” will be a substantial step. Colo. Rev. Stat. § 18-2-\\n\\n101(1) (emphasis added). Because showing conduct “strongly corroborative” of\\n\\ncriminal intent is sufficient to prove a substantial step under Colorado law, Mr.\\n\\nMendez argues that Colorado criminalizes some conduct that the Model Penal Code\\n\\ndoes not. Therefore, he contends, a conviction for attempted robbery in Colorado is\\n\\nnot categorically a “crime of violence” for the purposes of the guidelines. We are not\\n\\nconvinced.\\n\\n Mr. Mendez’s hairsplitting focus on formal logic loses sight of the categorical\\n\\napproach’s purpose, which is to carry out congressional intent by giving a word its\\n\\ncommonly understood meaning when the statute itself leaves the term undefined. See\\n\\ngenerally Taylor v. United States, 495 U.S. 575, 597 (1990). A statute that mirrors\\n\\nthe generic definition of an offense but makes minor variations in terminology will\\n\\nsuffice if it “corresponds in substance to the generic meaning.” See id. at 599\\n\\n 5\\n\\f(applying a categorical analysis to a state’s burglary statute). Colorado’s definition\\n\\nof attempt hews closely to that of the Model Penal Code. Both require a substantial\\n\\nstep and both define substantial step by reference to the act’s probative value\\n\\nregarding the defendant’s criminal intent.\\n\\n Mr. Mendez points to People v. Lehnert, 163 P.3d 1111 (Colo. 2007), as\\n\\nevidence that the Colorado Supreme Court views the statute’s departure from the\\n\\nModel Penal Code as significant, implying that Colorado’s statute would now\\n\\ncriminalize “mere preparation.” See Aplt. Br. at 19–20; Aplt. Reply Br. at 3. His\\n\\nargument significantly overstates the court’s conclusions. In Lehnert, the Colorado\\n\\nSupreme Court traced the evolution of Colorado’s treatment of attempt. Id. The\\n\\ncourt explained that the emphasis of the current Colorado statute, like the Model\\n\\nPenal Code, is on the degree to which the defendant’s conduct corroborates his\\n\\ncriminal intent. Id. at 1114–15. Nothing in Lehnert supports the proposition that\\n\\nColorado’s statute would criminalize “mere preparation,” which the Lehnert court\\n\\nactually recognized as “a useful way of describing conduct falling short of a\\n\\n‘substantial step’” under the current statute. Id. at 1114.\\n\\n Significantly, Mr. Mendez’s assertion that Colorado criminalizes conduct that\\n\\nwould not qualify as an attempted robbery elsewhere is purely speculative. The\\n\\ncategorical approach focuses on the minimum conduct criminalized by the state\\n\\nstatute, but this “is not an invitation to apply ‘legal imagination’ to the state offense;\\n\\nthere must be ‘a realistic probability, not a theoretical possibility, that the State\\n\\nwould apply its statute to conduct that falls outside the generic definition of a\\n\\n 6\\n\\fcrime.’” Moncrieffe v. Holder, 569 U.S. 184, 191 (2013) (quoting Gonzales v.\\n\\nDuenas-Alvarez, 549 U.S. 183, 193 (2007)). Where a statute does not on its face\\n\\ncriminalize conduct outside the generic definition of the offense, it is not enough to\\n\\nargue that a state could interpret its statute to criminalize such conduct; the defendant\\n\\nmust show that the state has actually done so. See United States v. Titties, 852 F.3d\\n\\n1257, 1275 (10th Cir. 2017); see also Moncrieffe, 569 U.S. at 191. “[H]e must at\\n\\nleast point to his own case or other cases in which the state courts in fact did apply\\n\\nthe statute in the special (nongeneric) manner for which he argues.” Duenas-Alvarez,\\n\\n549 U.S. at 193; see also United States v. Alexander, 809 F.3d 1029, 1033 (8th Cir.\\n\\n2016) (rejecting categorical challenge to state attempt statute based on a lack of case\\n\\nlaw construing attempt overinclusively); United States v. Havis, 907 F.3d 439, 446\\n\\n(6th Cir. 2018) (same); United States v. Garcia-Figueroa, 753 F.3d 179, 189 (5th Cir.\\n\\n2014) (same).\\n\\n Mr. Mendez does no more than offer theoretical grounds on which some\\n\\nconduct might constitute criminal attempt in Colorado but not under the generic\\n\\ndefinition of the term. He offers no cases to demonstrate that the state has actually\\n\\nprosecuted anyone under his broader definition. He does not even offer a\\n\\nhypothetical course of conduct where it might. For the foregoing reasons, we agree\\n\\nwith the district court that attempted robbery as defined in Colorado law is a crime of\\n\\nviolence for the purposes of § 4B1.2(a). Accordingly, we AFFIRM Mr. Mendez’s\\n\\nsentence.\\n\\n\\n\\n 7\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2265,"cells":{"id":{"kind":"number","value":4620922,"string":"4,620,922"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Gale v. City and County of Denver"},"decision_date":{"kind":"string","value":"2019-05-17"},"docket_number":{"kind":"string","value":"18-1269"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"\", \"parties\": \"\", \"opinions\": [{\"author\": \"Honorable Philip A. Brimmer, Chief Judge\", \"type\": \"010combined\", \"text\": \"United States Court of Appeals\\n Tenth Circuit\\n Office of the Clerk\\n Byron White United States Courthouse\\n 1823 Stout Street\\n Denver, Colorado 80257\\n (303) 844-3157\\n\\nElisabeth A. Shumaker Chris Wolpert\\nClerk of Court Chief Deputy Clerk\\n\\n May 17, 2019\\n\\n\\nHonorable Philip A. Brimmer, Chief Judge\\nHonorable Christine M. Arguello\\nHonorable William J. Martinez\\nHonorable R. Brook Jackson\\nHonorable Raymond P. Moore\\nHonorable Daniel D. Domenico\\n\\n\\n Re: Certification of State Law\\n Gale v. City and County of Denver, No. 18-1269\\n (D. Ct. No. 1:16-CV-02436-MSK-KMT)\\n\\nDear Judges:\\n\\n The court has certified a question of state law to the Colorado Supreme Court in Gale v.\\nCity and County of Denver, No. 18-1269, D. Ct. No. 1:16-CV-02436-MSK-KMT.\\n\\n Attached for your information is a copy of the court’s certification order.\\n\\n Very truly yours,\\n ELISABETH A. SHUMAKER, Clerk\\n\\n\\n Kevin Schwalbe\\n Deputy Clerk\\n\\nEAS/ks\\n\\nEnclosures\\n\\ncc: All Tenth Circuit Judges\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4398175/\"}]}"},"judge1":{"kind":"string","value":""},"judge2":{"kind":"string","value":""},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4620922/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Gale v. City and County of Denver\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-17\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nUnited States Court of Appeals\n Tenth Circuit\n Office of the Clerk\n Byron White United States Courthouse\n 1823 Stout Street\n Denver, Colorado 80257\n (303) 844-3157\n\nElisabeth A. Shumaker Chris Wolpert\nClerk of Court Chief Deputy Clerk\n\n May 17, 2019\n\n\nHonorable Philip A. Brimmer, Chief Judge\nHonorable Christine M. Arguello\nHonorable William J. Martinez\nHonorable R. Brook Jackson\nHonorable Raymond P. Moore\nHonorable Daniel D. Domenico\n\n\n Re: Certification of State Law\n Gale v. City and County of Denver, No. 18-1269\n (D. Ct. No. 1:16-CV-02436-MSK-KMT)\n\nDear Judges:\n\n The court has certified a question of state law to the Colorado Supreme Court in Gale v.\nCity and County of Denver, No. 18-1269, D. Ct. No. 1:16-CV-02436-MSK-KMT.\n\n Attached for your information is a copy of the court’s certification order.\n\n Very truly yours,\n ELISABETH A. SHUMAKER, Clerk\n\n\n Kevin Schwalbe\n Deputy Clerk\n\nEAS/ks\n\nEnclosures\n\ncc: All Tenth Circuit Judges\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Gale v. City and County of Denver\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-17\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nUnited States Court of Appeals\\n Tenth Circuit\\n Office of the Clerk\\n Byron White United States Courthouse\\n 1823 Stout Street\\n Denver, Colorado 80257\\n (303) 844-3157\\n\\nElisabeth A. Shumaker Chris Wolpert\\nClerk of Court Chief Deputy Clerk\\n\\n May 17, 2019\\n\\n\\nHonorable Philip A. Brimmer, Chief Judge\\nHonorable Christine M. Arguello\\nHonorable William J. Martinez\\nHonorable R. Brook Jackson\\nHonorable Raymond P. Moore\\nHonorable Daniel D. Domenico\\n\\n\\n Re: Certification of State Law\\n Gale v. City and County of Denver, No. 18-1269\\n (D. Ct. No. 1:16-CV-02436-MSK-KMT)\\n\\nDear Judges:\\n\\n The court has certified a question of state law to the Colorado Supreme Court in Gale v.\\nCity and County of Denver, No. 18-1269, D. Ct. No. 1:16-CV-02436-MSK-KMT.\\n\\n Attached for your information is a copy of the court’s certification order.\\n\\n Very truly yours,\\n ELISABETH A. SHUMAKER, Clerk\\n\\n\\n Kevin Schwalbe\\n Deputy Clerk\\n\\nEAS/ks\\n\\nEnclosures\\n\\ncc: All Tenth Circuit Judges\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2266,"cells":{"id":{"kind":"number","value":4620969,"string":"4,620,969"},"name":{"kind":"string","value":"Franklin GALE, Plaintiff-Appellant, v. the CITY AND COUNTY OF DENVER, Defendant-Appellee."},"name_abbreviation":{"kind":"string","value":"Gale v. City and County of Denver"},"decision_date":{"kind":"string","value":"2019-05-17"},"docket_number":{"kind":"string","value":"18-1269"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Tymkovich, Bacharach, Moritz\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n Tenth Circuit\\n\\n May 17, 2019\\n PUBLISH\\n Elisabeth A. Shumaker\\n Clerk of Court\\n UNITED STATES COURT OF APPEALS\\n\\n TENTH CIRCUIT\\n\\n\\n\\n FRANKLIN GALE,\\n\\n Plaintiff-Appellant,\\n v. No. 18-1269\\n (D.C. No. 1:16-CV-02436-MSK-KMT)\\n THE CITY AND COUNTY OF (D. Colo.)\\n DENVER,\\n\\n Defendant-Appellee.\\n\\n\\n CERTIFICATION OF QUESTION OF STATE LAW\\n\\n\\nBefore TYMKOVICH, Chief Judge, BACHARACH, and MORITZ, Circuit\\nJudges.\\n\\n\\n The United States Court of Appeals for the Tenth Circuit, acting under\\n\\nTenth Circuit Rule 27.2, asks the Supreme Court of Colorado to exercise its\\n\\ndiscretion under Colorado Appellate Rule 21.1 to accept the following certified\\n\\nquestion of Colorado law:\\n\\n Has the Colorado Supreme Court crafted an exception to the doctrine\\n of res judicata such that a prior action under Colorado Rule of Civil\\n Procedure 106(a)(4) cannot preclude 42 U.S.C. § 1983 claims brought\\n in federal court, even though such claims could have been brought in\\n the prior state action?\\n\\f The controlling precedent from the Colorado Supreme Court is unclear, and\\n\\nthe answer to this question will be determinative of the appeal now pending in\\n\\nthis court. The court may reformulate this question as it sees fit.\\n\\n I. Background\\n\\n In January 2015, the Denver Sheriff Department terminated Deputy Sheriff\\n\\nFrank Gale. Denver alleged Gale violated career service rules and then engaged\\n\\nin deceptive acts to hide purported misbehavior. For his part, Gale alleged\\n\\nDenver terminated his employment in retaliation for his outspoken union\\n\\norganizing activities.\\n\\n Gale challenged his termination in an administrative proceeding that was\\n\\nsubsequently affirmed by the Denver Career Services Board. Pursuant to\\n\\nColorado Rule of Civil Procedure 106(a)(4), Gale appealed the administrative\\n\\ndecision in state district court. The court affirmed the administrative\\n\\ndetermination, as did the Colorado Court of Appeals. The Colorado Supreme\\n\\nCourt denied review.\\n\\n Shortly after filing his Rule 106(a)(4) appeal in state court but before the\\n\\nstate courts had resolved the appeal, Gale brought constitutional claims in federal\\n\\ndistrict court under 42 U.S.C. § 1983, alleging retaliation for his exercise of\\n\\nassociation and speech rights in violation of the First Amendment. Once the state\\n\\ncourt judgment became final, Denver amended its answer to include defenses of\\n\\n\\n\\n -2-\\n\\fres judicata and collateral estoppel. The federal district court granted summary\\n\\njudgment to Denver based on res judicata, and Gale appealed to our court.\\n\\n II. Analysis\\n\\n Res judicata, or claim preclusion, “precludes the parties or their privies\\n\\nfrom relitigating issues that were or could have been raised in the prior action.”\\n\\nWilkes v. Wyo. Dep’t of Emp’t, 314 F.3d 501, 503 (10th Cir. 2002). Colorado\\n\\npreclusion law applies because Denver asserted the preclusive effect of a\\n\\njudgment rendered by a Colorado court. See Nichols v. Bd. of Cty. Comm’rs, 506\\n\\nF.3d 962, 967 (10th Cir. 2007) (“In determining the preclusive effect of a state\\n\\ncourt judgment, the full faith and credit statute, 28 U.S.C. § 1738, directs a\\n\\nfederal court to refer to the preclusion law of the State in which judgment was\\n\\nrendered.” (internal quotation marks omitted)), abrogated on other grounds as\\n\\nrecognized by Onyx Properties LLC v. Bd. of Cnty. Comm’rs, 838 F.3d 1039,\\n\\n1043 n.2 (10th Cir. 2016).\\n\\n Under Colorado law, res judicata bars a claim in a current proceeding when\\n\\nfour elements are met: “(1) the judgment in the prior proceeding was final; (2) the\\n\\nprior and current proceeding involved identical subject matter; (3) the prior and\\n\\ncurrent proceeding involved identical claims for relief; and (4) the parties to both\\n\\nproceedings were identical or in privity with one another.” Foster v. Plock, 394\\n\\nP.3d 1119, 1123 (Colo. 2017) (internal quotation marks omitted).\\n\\n\\n\\n -3-\\n\\f The question presented in this certification request concerns the third\\n\\nelement of res judicata—identity of claims. Identity of claims exists when “the\\n\\nclaim at issue in the second proceeding is the same claim that was (or could have\\n\\nbeen) brought in the first proceeding.” Foster, 394 P.3d at 1127. Colorado\\n\\n“disregard[s] the form of the action and instead look[s] at the actual injury\\n\\nunderlying the first proceeding” using a transactional analysis to determine\\n\\nwhether the claims “seek redress for essentially the same basic wrong, and rest on\\n\\nthe same or a substantially similar factual basis.” Id. (internal quotation marks\\n\\nomitted). Gale’s previous state Rule 106 action and this federal § 1983 action\\n\\nboth arise from the same injury, namely, the termination of Gale’s employment.\\n\\nGale’s § 1983 claims could have been brought in the first proceeding. See Colo.\\n\\nR. Civ. P. 106(a)(4)(VI) (permitting joinder of claims).\\n\\n Colorado courts have held generally that “when a party files an action\\n\\nunder Colo. R. Civ. P. 106(a)(4) to review an administrative\\n\\ndetermination. . . Colorado ‘public policy requires the joinder of all of the\\n\\npetitioner’s claims in one action.’” Bolling v. City of Denver, 790 F.2d 67, 68\\n\\n(10th Cir. 1986) (quoting Powers v. Bd. of Cty. Comm’rs, 651 P.2d 463, 464\\n\\n(Colo. App. 1982)); see also Norby v. City of Boulder, 577 P.2d 277, 281 (Colo.\\n\\n1981). This rule reflects the strong public policy interest in judicial economy and\\n\\nefficiency.\\n\\n\\n\\n -4-\\n\\f Nevertheless, Gale relies on Board of County Commissioners v. Sundheim,\\n\\n926 P.2d 545 (Colo. 1996), and State Board of Chiropractic Examiners v.\\n\\nStjernholm, 935 P.2d 959 (Colo. 1997), to argue the Colorado Supreme Court has\\n\\ncrafted an exception to this rule. Gale says these cases establish that a Rule 106\\n\\naction in which § 1983 claims could have been brought—but are not—cannot\\n\\npreclude a plaintiff from later bringing those same claims separately in federal\\n\\ncourt.\\n\\n In Sundheim, the Board of County Commissioners denied plaintiffs’\\n\\napplication to continue a horse-boarding and training business on their property.\\n\\n926 P.2d at 547. The Sundheims never filed a Rule 106(a)(4) action challenging\\n\\nthe board’s determination, but they did commence a state court action alleging\\n\\nclaims under § 1983. Even though the Sundheims filed suit within the two-year\\n\\nstatute of limitations for § 1983 claims, the trial court dismissed the case because\\n\\nit was filed after the thirty-day deadline for bringing claims under Rule\\n\\n106(a)(4). 1\\n\\n The Colorado Supreme Court reversed. The court recognized Rule\\n\\n106(a)(4) “provides the exclusive remedy for reviewing a quasi-judicial decision\\n\\nmade by a government entity” and that a Rule 106(a)(4) “complaint must include\\n\\nall causes of action, including constitutional claims, in a single C.R.C.P.\\n\\n\\n 1\\n Rule 106 has since been amended to require filing within twenty-eight\\ndays of a final administrative determination. See Colo. R. Civ. P. 106(b).\\n\\n -5-\\n\\f106(a)(4) action.” 926 P.2d at 548. But the court went on to explain that\\n\\n“because claims under § 1983 exist as a uniquely federal remedy that is to be\\n\\naccorded a sweep as broad as its language” “[t]he analysis shifts . . . when a\\n\\ncomplainant asserts a claim for money damages under § 1983.” Id. (cleaned up).\\n\\nThe court therefore affirmed “that a § 1983 damages claim may exist separately\\n\\nfrom a C.R.C.P. 106(a)(4) action.” Id. at 549.\\n\\n Sundheim thus stands only for the noncontroversial proposition that\\n\\nplaintiffs need not forfeit their § 1983 claims simply because they choose not to\\n\\npursue a Rule 106(a)(4) action. A state procedural deadline for filing Rule\\n\\n106(a)(4) actions cannot bar a § 1983 claim properly filed within the two-year\\n\\nstatute of limitations.\\n\\n One year after deciding Sundheim, the Colorado Supreme Court deemed res\\n\\njudicata inapplicable to a § 1983 suit against the State Board of Chiropractic\\n\\nExaminers in Stjernholm. In a previous action, Stjernholm challenged the board’s\\n\\nsuspension of his license in the court of appeals, as required by the Chiropractic\\n\\nAct. See Stjernholm, 935 P.2d at 964–66; see also Colo. Rev. Stat. § 12-33-121\\n\\n(granting initial jurisdiction to the court of appeals to review Chiropractic Board\\n\\ndeterminations). Taking note of that prior appeal, the Colorado Supreme Court\\n\\napplied Sundheim to the § 1983 case before it, observing that the § 1983 case\\n\\ncould not have been resolved in an appellate tribunal because “Section 1983 suits\\n\\ninvolve evidentiary presentation to and fact finding by a district court.” Id. at\\n\\n -6-\\n\\f967. The court therefore concluded the court of appeals “did not err in refusing,\\n\\nas a general matter, to employ res judicata to preclude section 1983 litigation in\\n\\nthe [state] district court.” Id.\\n\\n It is obvious that a complainant such as Stjernholm bringing a Chiropractic\\n\\nAct challenge before the court of appeals in the first instance cannot raise § 1983\\n\\nclaims at that juncture. This is unlike the procedures available under a Rule\\n\\n106(a)(4) appeal in state district court. Parties cannot add and litigate new claims\\n\\nfor relief—which often will require discovery and trial—initially in the court of\\n\\nappeals. The court of appeals is simply a reviewing body, undertaking a record\\n\\nreview as set forth in the Colorado Administrative Procedure Act, Colo. Rev. Stat.\\n\\n§ 24-4-106(11).\\n\\n But it is equally obvious a complainant bringing an APA challenge before\\n\\nthe district court can raise and litigate such claims. See Crocog Co. v. Reeves,\\n\\n992 F.2d 267, 269–70 (10th Cir. 1993) (granting res judicata against plaintiff’s\\n\\n§ 1983 claim because it could have joined that claim in state district court under\\n\\n§ 24-4-106(6)). Thus, Stjernholm applies Sundheim to Chiropractic Act appeals\\n\\nin which the complainant could not have brought his § 1983 claims in the prior\\n\\nproceeding before the court of appeals. Accord id. at 269 (“Plaintiff argues that\\n\\nthe Colorado courts would not have permitted the joinder of its § 1983 claim to\\n\\nthe review of the administrative proceeding. Under Colorado law, such an\\n\\n\\n\\n -7-\\n\\fargument, if true, would defeat claim preclusion.” (citing Carpenter v. Young,\\n\\n773 P.2d 561, 565 n.5 (Colo. 1989))).\\n\\n Taken together, Sundheim and Stjernholm are best read as holding that if a\\n\\nplaintiff cannot join § 1983 claims to an administrative challenge or chooses not\\n\\nto bring an administrative challenge, then the plaintiff is not precluded from\\n\\nraising § 1983 claims in a free standing action. If one does bring an\\n\\nadministrative challenge in state district court under Rule 106(a)(4), however, the\\n\\nstate’s interest in judicial efficiency kicks in and any § 1983 claims not joined\\n\\nmay be claim-precluded in the future.\\n\\n On the contrary, Gale argues Sundheim and Stjernholm establish a blanket\\n\\n§ 1983 exception from the Bolling/Norby rule requiring joinder of all claims in a\\n\\nRule 106(a)(4) proceeding. A putative plaintiff can hold onto his § 1983 claim\\n\\nregardless of whether he is pursuing relief for the same claim in state courts.\\n\\n Because the central issue before our court is the extent to which a prior\\n\\nRule 106(a)(4) action would preclude Gale’s federal action under Colorado law,\\n\\nthe Colorado Supreme Court is the best venue to resolve any uncertainty as to\\n\\ninterpretation of controlling precedent. The certified question is a pure question\\n\\nof law and does not entail any factual disputes for the court to resolve.\\n\\nMoreover, the question of state law presented in this case involves rights and\\n\\nremedies at the intersection of state and federal jurisdiction. In furtherance of\\n\\n\\n\\n -8-\\n\\fcomity and federalism, we conclude the Colorado Supreme Court should have the\\n\\nopportunity to answer this important question in the first instance.\\n\\n We greatly appreciate the consideration of this request.\\n\\n III. Conclusion\\n\\n Gale’s motion to certify this question of state law is GRANTED. The\\n\\nappeal is therefore ABATED pending resolution of the question certified to the\\n\\nSupreme Court of Colorado. The clerk of this court shall submit to the Supreme\\n\\nCourt of Colorado a certified copy of this order, together with copies of the briefs\\n\\nfiled in this court and a copy of the judgment of the district court.\\n\\n ENTERED FOR THE COURT\\n\\n\\n\\n\\n Timothy M. Tymkovich\\n Chief Judge\\n\\n\\n\\n\\n -9-\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4398222/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"TYMKOVICH"},"judge2":{"kind":"string","value":"BACHARACH"},"judge3":{"kind":"string","value":"MORITZ"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4620969/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Franklin GALE, Plaintiff-Appellant, v. the CITY AND COUNTY OF DENVER, Defendant-Appellee.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-17\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n Tenth Circuit\n\n May 17, 2019\n PUBLISH\n Elisabeth A. Shumaker\n Clerk of Court\n UNITED STATES COURT OF APPEALS\n\n TENTH CIRCUIT\n\n\n\n FRANKLIN GALE,\n\n Plaintiff-Appellant,\n v. No. 18-1269\n (D.C. No. 1:16-CV-02436-MSK-KMT)\n THE CITY AND COUNTY OF (D. Colo.)\n DENVER,\n\n Defendant-Appellee.\n\n\n CERTIFICATION OF QUESTION OF STATE LAW\n\n\nBefore TYMKOVICH, Chief Judge, BACHARACH, and MORITZ, Circuit\nJudges.\n\n\n The United States Court of Appeals for the Tenth Circuit, acting under\n\nTenth Circuit Rule 27.2, asks the Supreme Court of Colorado to exercise its\n\ndiscretion under Colorado Appellate Rule 21.1 to accept the following certified\n\nquestion of Colorado law:\n\n Has the Colorado Supreme Court crafted an exception to the doctrine\n of res judicata such that a prior action under Colorado Rule of Civil\n Procedure 106(a)(4) cannot preclude 42 U.S.C. § 1983 claims brought\n in federal court, even though such claims could have been brought in\n the prior state action?\n\f The controlling precedent from the Colorado Supreme Court is unclear, and\n\nthe answer to this question will be determinative of the appeal now pending in\n\nthis court. The court may reformulate this question as it sees fit.\n\n I. Background\n\n In January 2015, the Denver Sheriff Department terminated Deputy Sheriff\n\nFrank Gale. Denver alleged Gale violated career service rules and then engaged\n\nin deceptive acts to hide purported misbehavior. For his part, Gale alleged\n\nDenver terminated his employment in retaliation for his outspoken union\n\norganizing activities.\n\n Gale challenged his termination in an administrative proceeding that was\n\nsubsequently affirmed by the Denver Career Services Board. Pursuant to\n\nColorado Rule of Civil Procedure 106(a)(4), Gale appealed the administrative\n\ndecision in state district court. The court affirmed the administrative\n\ndetermination, as did the Colorado Court of Appeals. The Colorado Supreme\n\nCourt denied review.\n\n Shortly after filing his Rule 106(a)(4) appeal in state court but before the\n\nstate courts had resolved the appeal, Gale brought constitutional claims in federal\n\ndistrict court under 42 U.S.C. § 1983, alleging retaliation for his exercise of\n\nassociation and speech rights in violation of the First Amendment. Once the state\n\ncourt judgment became final, Denver amended its answer to include defenses of\n\n\n\n -2-\n\fres judicata and collateral estoppel. The federal district court granted summary\n\njudgment to Denver based on res judicata, and Gale appealed to our court.\n\n II. Analysis\n\n Res judicata, or claim preclusion, “precludes the parties or their privies\n\nfrom relitigating issues that were or could have been raised in the prior action.”\n\nWilkes v. Wyo. Dep’t of Emp’t, 314 F.3d 501, 503 (10th Cir. 2002). Colorado\n\npreclusion law applies because Denver asserted the preclusive effect of a\n\njudgment rendered by a Colorado court. See Nichols v. Bd. of Cty. Comm’rs, 506\n\nF.3d 962, 967 (10th Cir. 2007) (“In determining the preclusive effect of a state\n\ncourt judgment, the full faith and credit statute, 28 U.S.C. § 1738, directs a\n\nfederal court to refer to the preclusion law of the State in which judgment was\n\nrendered.” (internal quotation marks omitted)), abrogated on other grounds as\n\nrecognized by Onyx Properties LLC v. Bd. of Cnty. Comm’rs, 838 F.3d 1039,\n\n1043 n.2 (10th Cir. 2016).\n\n Under Colorado law, res judicata bars a claim in a current proceeding when\n\nfour elements are met: “(1) the judgment in the prior proceeding was final; (2) the\n\nprior and current proceeding involved identical subject matter; (3) the prior and\n\ncurrent proceeding involved identical claims for relief; and (4) the parties to both\n\nproceedings were identical or in privity with one another.” Foster v. Plock, 394\n\nP.3d 1119, 1123 (Colo. 2017) (internal quotation marks omitted).\n\n\n\n -3-\n\f The question presented in this certification request concerns the third\n\nelement of res judicata—identity of claims. Identity of claims exists when “the\n\nclaim at issue in the second proceeding is the same claim that was (or could have\n\nbeen) brought in the first proceeding.” Foster, 394 P.3d at 1127. Colorado\n\n“disregard[s] the form of the action and instead look[s] at the actual injury\n\nunderlying the first proceeding” using a transactional analysis to determine\n\nwhether the claims “seek redress for essentially the same basic wrong, and rest on\n\nthe same or a substantially similar factual basis.” Id. (internal quotation marks\n\nomitted). Gale’s previous state Rule 106 action and this federal § 1983 action\n\nboth arise from the same injury, namely, the termination of Gale’s employment.\n\nGale’s § 1983 claims could have been brought in the first proceeding. See Colo.\n\nR. Civ. P. 106(a)(4)(VI) (permitting joinder of claims).\n\n Colorado courts have held generally that “when a party files an action\n\nunder Colo. R. Civ. P. 106(a)(4) to review an administrative\n\ndetermination. . . Colorado ‘public policy requires the joinder of all of the\n\npetitioner’s claims in one action.’” Bolling v. City of Denver, 790 F.2d 67, 68\n\n(10th Cir. 1986) (quoting Powers v. Bd. of Cty. Comm’rs, 651 P.2d 463, 464\n\n(Colo. App. 1982)); see also Norby v. City of Boulder, 577 P.2d 277, 281 (Colo.\n\n1981). This rule reflects the strong public policy interest in judicial economy and\n\nefficiency.\n\n\n\n -4-\n\f Nevertheless, Gale relies on Board of County Commissioners v. Sundheim,\n\n926 P.2d 545 (Colo. 1996), and State Board of Chiropractic Examiners v.\n\nStjernholm, 935 P.2d 959 (Colo. 1997), to argue the Colorado Supreme Court has\n\ncrafted an exception to this rule. Gale says these cases establish that a Rule 106\n\naction in which § 1983 claims could have been brought—but are not—cannot\n\npreclude a plaintiff from later bringing those same claims separately in federal\n\ncourt.\n\n In Sundheim, the Board of County Commissioners denied plaintiffs’\n\napplication to continue a horse-boarding and training business on their property.\n\n926 P.2d at 547. The Sundheims never filed a Rule 106(a)(4) action challenging\n\nthe board’s determination, but they did commence a state court action alleging\n\nclaims under § 1983. Even though the Sundheims filed suit within the two-year\n\nstatute of limitations for § 1983 claims, the trial court dismissed the case because\n\nit was filed after the thirty-day deadline for bringing claims under Rule\n\n106(a)(4). 1\n\n The Colorado Supreme Court reversed. The court recognized Rule\n\n106(a)(4) “provides the exclusive remedy for reviewing a quasi-judicial decision\n\nmade by a government entity” and that a Rule 106(a)(4) “complaint must include\n\nall causes of action, including constitutional claims, in a single C.R.C.P.\n\n\n 1\n Rule 106 has since been amended to require filing within twenty-eight\ndays of a final administrative determination. See Colo. R. Civ. P. 106(b).\n\n -5-\n\f106(a)(4) action.” 926 P.2d at 548. But the court went on to explain that\n\n“because claims under § 1983 exist as a uniquely federal remedy that is to be\n\naccorded a sweep as broad as its language” “[t]he analysis shifts . . . when a\n\ncomplainant asserts a claim for money damages under § 1983.” Id. (cleaned up).\n\nThe court therefore affirmed “that a § 1983 damages claim may exist separately\n\nfrom a C.R.C.P. 106(a)(4) action.” Id. at 549.\n\n Sundheim thus stands only for the noncontroversial proposition that\n\nplaintiffs need not forfeit their § 1983 claims simply because they choose not to\n\npursue a Rule 106(a)(4) action. A state procedural deadline for filing Rule\n\n106(a)(4) actions cannot bar a § 1983 claim properly filed within the two-year\n\nstatute of limitations.\n\n One year after deciding Sundheim, the Colorado Supreme Court deemed res\n\njudicata inapplicable to a § 1983 suit against the State Board of Chiropractic\n\nExaminers in Stjernholm. In a previous action, Stjernholm challenged the board’s\n\nsuspension of his license in the court of appeals, as required by the Chiropractic\n\nAct. See Stjernholm, 935 P.2d at 964–66; see also Colo. Rev. Stat. § 12-33-121\n\n(granting initial jurisdiction to the court of appeals to review Chiropractic Board\n\ndeterminations). Taking note of that prior appeal, the Colorado Supreme Court\n\napplied Sundheim to the § 1983 case before it, observing that the § 1983 case\n\ncould not have been resolved in an appellate tribunal because “Section 1983 suits\n\ninvolve evidentiary presentation to and fact finding by a district court.” Id. at\n\n -6-\n\f967. The court therefore concluded the court of appeals “did not err in refusing,\n\nas a general matter, to employ res judicata to preclude section 1983 litigation in\n\nthe [state] district court.” Id.\n\n It is obvious that a complainant such as Stjernholm bringing a Chiropractic\n\nAct challenge before the court of appeals in the first instance cannot raise § 1983\n\nclaims at that juncture. This is unlike the procedures available under a Rule\n\n106(a)(4) appeal in state district court. Parties cannot add and litigate new claims\n\nfor relief—which often will require discovery and trial—initially in the court of\n\nappeals. The court of appeals is simply a reviewing body, undertaking a record\n\nreview as set forth in the Colorado Administrative Procedure Act, Colo. Rev. Stat.\n\n§ 24-4-106(11).\n\n But it is equally obvious a complainant bringing an APA challenge before\n\nthe district court can raise and litigate such claims. See Crocog Co. v. Reeves,\n\n992 F.2d 267, 269–70 (10th Cir. 1993) (granting res judicata against plaintiff’s\n\n§ 1983 claim because it could have joined that claim in state district court under\n\n§ 24-4-106(6)). Thus, Stjernholm applies Sundheim to Chiropractic Act appeals\n\nin which the complainant could not have brought his § 1983 claims in the prior\n\nproceeding before the court of appeals. Accord id. at 269 (“Plaintiff argues that\n\nthe Colorado courts would not have permitted the joinder of its § 1983 claim to\n\nthe review of the administrative proceeding. Under Colorado law, such an\n\n\n\n -7-\n\fargument, if true, would defeat claim preclusion.” (citing Carpenter v. Young,\n\n773 P.2d 561, 565 n.5 (Colo. 1989))).\n\n Taken together, Sundheim and Stjernholm are best read as holding that if a\n\nplaintiff cannot join § 1983 claims to an administrative challenge or chooses not\n\nto bring an administrative challenge, then the plaintiff is not precluded from\n\nraising § 1983 claims in a free standing action. If one does bring an\n\nadministrative challenge in state district court under Rule 106(a)(4), however, the\n\nstate’s interest in judicial efficiency kicks in and any § 1983 claims not joined\n\nmay be claim-precluded in the future.\n\n On the contrary, Gale argues Sundheim and Stjernholm establish a blanket\n\n§ 1983 exception from the Bolling/Norby rule requiring joinder of all claims in a\n\nRule 106(a)(4) proceeding. A putative plaintiff can hold onto his § 1983 claim\n\nregardless of whether he is pursuing relief for the same claim in state courts.\n\n Because the central issue before our court is the extent to which a prior\n\nRule 106(a)(4) action would preclude Gale’s federal action under Colorado law,\n\nthe Colorado Supreme Court is the best venue to resolve any uncertainty as to\n\ninterpretation of controlling precedent. The certified question is a pure question\n\nof law and does not entail any factual disputes for the court to resolve.\n\nMoreover, the question of state law presented in this case involves rights and\n\nremedies at the intersection of state and federal jurisdiction. In furtherance of\n\n\n\n -8-\n\fcomity and federalism, we conclude the Colorado Supreme Court should have the\n\nopportunity to answer this important question in the first instance.\n\n We greatly appreciate the consideration of this request.\n\n III. Conclusion\n\n Gale’s motion to certify this question of state law is GRANTED. The\n\nappeal is therefore ABATED pending resolution of the question certified to the\n\nSupreme Court of Colorado. The clerk of this court shall submit to the Supreme\n\nCourt of Colorado a certified copy of this order, together with copies of the briefs\n\nfiled in this court and a copy of the judgment of the district court.\n\n ENTERED FOR THE COURT\n\n\n\n\n Timothy M. Tymkovich\n Chief Judge\n\n\n\n\n -9-\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Franklin GALE, Plaintiff-Appellant, v. the CITY AND COUNTY OF DENVER, Defendant-Appellee.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-17\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n Tenth Circuit\\n\\n May 17, 2019\\n PUBLISH\\n Elisabeth A. Shumaker\\n Clerk of Court\\n UNITED STATES COURT OF APPEALS\\n\\n TENTH CIRCUIT\\n\\n\\n\\n FRANKLIN GALE,\\n\\n Plaintiff-Appellant,\\n v. No. 18-1269\\n (D.C. No. 1:16-CV-02436-MSK-KMT)\\n THE CITY AND COUNTY OF (D. Colo.)\\n DENVER,\\n\\n Defendant-Appellee.\\n\\n\\n CERTIFICATION OF QUESTION OF STATE LAW\\n\\n\\nBefore TYMKOVICH, Chief Judge, BACHARACH, and MORITZ, Circuit\\nJudges.\\n\\n\\n The United States Court of Appeals for the Tenth Circuit, acting under\\n\\nTenth Circuit Rule 27.2, asks the Supreme Court of Colorado to exercise its\\n\\ndiscretion under Colorado Appellate Rule 21.1 to accept the following certified\\n\\nquestion of Colorado law:\\n\\n Has the Colorado Supreme Court crafted an exception to the doctrine\\n of res judicata such that a prior action under Colorado Rule of Civil\\n Procedure 106(a)(4) cannot preclude 42 U.S.C. § 1983 claims brought\\n in federal court, even though such claims could have been brought in\\n the prior state action?\\n\\f The controlling precedent from the Colorado Supreme Court is unclear, and\\n\\nthe answer to this question will be determinative of the appeal now pending in\\n\\nthis court. The court may reformulate this question as it sees fit.\\n\\n I. Background\\n\\n In January 2015, the Denver Sheriff Department terminated Deputy Sheriff\\n\\nFrank Gale. Denver alleged Gale violated career service rules and then engaged\\n\\nin deceptive acts to hide purported misbehavior. For his part, Gale alleged\\n\\nDenver terminated his employment in retaliation for his outspoken union\\n\\norganizing activities.\\n\\n Gale challenged his termination in an administrative proceeding that was\\n\\nsubsequently affirmed by the Denver Career Services Board. Pursuant to\\n\\nColorado Rule of Civil Procedure 106(a)(4), Gale appealed the administrative\\n\\ndecision in state district court. The court affirmed the administrative\\n\\ndetermination, as did the Colorado Court of Appeals. The Colorado Supreme\\n\\nCourt denied review.\\n\\n Shortly after filing his Rule 106(a)(4) appeal in state court but before the\\n\\nstate courts had resolved the appeal, Gale brought constitutional claims in federal\\n\\ndistrict court under 42 U.S.C. § 1983, alleging retaliation for his exercise of\\n\\nassociation and speech rights in violation of the First Amendment. Once the state\\n\\ncourt judgment became final, Denver amended its answer to include defenses of\\n\\n\\n\\n -2-\\n\\fres judicata and collateral estoppel. The federal district court granted summary\\n\\njudgment to Denver based on res judicata, and Gale appealed to our court.\\n\\n II. Analysis\\n\\n Res judicata, or claim preclusion, “precludes the parties or their privies\\n\\nfrom relitigating issues that were or could have been raised in the prior action.”\\n\\nWilkes v. Wyo. Dep’t of Emp’t, 314 F.3d 501, 503 (10th Cir. 2002). Colorado\\n\\npreclusion law applies because Denver asserted the preclusive effect of a\\n\\njudgment rendered by a Colorado court. See Nichols v. Bd. of Cty. Comm’rs, 506\\n\\nF.3d 962, 967 (10th Cir. 2007) (“In determining the preclusive effect of a state\\n\\ncourt judgment, the full faith and credit statute, 28 U.S.C. § 1738, directs a\\n\\nfederal court to refer to the preclusion law of the State in which judgment was\\n\\nrendered.” (internal quotation marks omitted)), abrogated on other grounds as\\n\\nrecognized by Onyx Properties LLC v. Bd. of Cnty. Comm’rs, 838 F.3d 1039,\\n\\n1043 n.2 (10th Cir. 2016).\\n\\n Under Colorado law, res judicata bars a claim in a current proceeding when\\n\\nfour elements are met: “(1) the judgment in the prior proceeding was final; (2) the\\n\\nprior and current proceeding involved identical subject matter; (3) the prior and\\n\\ncurrent proceeding involved identical claims for relief; and (4) the parties to both\\n\\nproceedings were identical or in privity with one another.” Foster v. Plock, 394\\n\\nP.3d 1119, 1123 (Colo. 2017) (internal quotation marks omitted).\\n\\n\\n\\n -3-\\n\\f The question presented in this certification request concerns the third\\n\\nelement of res judicata—identity of claims. Identity of claims exists when “the\\n\\nclaim at issue in the second proceeding is the same claim that was (or could have\\n\\nbeen) brought in the first proceeding.” Foster, 394 P.3d at 1127. Colorado\\n\\n“disregard[s] the form of the action and instead look[s] at the actual injury\\n\\nunderlying the first proceeding” using a transactional analysis to determine\\n\\nwhether the claims “seek redress for essentially the same basic wrong, and rest on\\n\\nthe same or a substantially similar factual basis.” Id. (internal quotation marks\\n\\nomitted). Gale’s previous state Rule 106 action and this federal § 1983 action\\n\\nboth arise from the same injury, namely, the termination of Gale’s employment.\\n\\nGale’s § 1983 claims could have been brought in the first proceeding. See Colo.\\n\\nR. Civ. P. 106(a)(4)(VI) (permitting joinder of claims).\\n\\n Colorado courts have held generally that “when a party files an action\\n\\nunder Colo. R. Civ. P. 106(a)(4) to review an administrative\\n\\ndetermination. . . Colorado ‘public policy requires the joinder of all of the\\n\\npetitioner’s claims in one action.’” Bolling v. City of Denver, 790 F.2d 67, 68\\n\\n(10th Cir. 1986) (quoting Powers v. Bd. of Cty. Comm’rs, 651 P.2d 463, 464\\n\\n(Colo. App. 1982)); see also Norby v. City of Boulder, 577 P.2d 277, 281 (Colo.\\n\\n1981). This rule reflects the strong public policy interest in judicial economy and\\n\\nefficiency.\\n\\n\\n\\n -4-\\n\\f Nevertheless, Gale relies on Board of County Commissioners v. Sundheim,\\n\\n926 P.2d 545 (Colo. 1996), and State Board of Chiropractic Examiners v.\\n\\nStjernholm, 935 P.2d 959 (Colo. 1997), to argue the Colorado Supreme Court has\\n\\ncrafted an exception to this rule. Gale says these cases establish that a Rule 106\\n\\naction in which § 1983 claims could have been brought—but are not—cannot\\n\\npreclude a plaintiff from later bringing those same claims separately in federal\\n\\ncourt.\\n\\n In Sundheim, the Board of County Commissioners denied plaintiffs’\\n\\napplication to continue a horse-boarding and training business on their property.\\n\\n926 P.2d at 547. The Sundheims never filed a Rule 106(a)(4) action challenging\\n\\nthe board’s determination, but they did commence a state court action alleging\\n\\nclaims under § 1983. Even though the Sundheims filed suit within the two-year\\n\\nstatute of limitations for § 1983 claims, the trial court dismissed the case because\\n\\nit was filed after the thirty-day deadline for bringing claims under Rule\\n\\n106(a)(4). 1\\n\\n The Colorado Supreme Court reversed. The court recognized Rule\\n\\n106(a)(4) “provides the exclusive remedy for reviewing a quasi-judicial decision\\n\\nmade by a government entity” and that a Rule 106(a)(4) “complaint must include\\n\\nall causes of action, including constitutional claims, in a single C.R.C.P.\\n\\n\\n 1\\n Rule 106 has since been amended to require filing within twenty-eight\\ndays of a final administrative determination. See Colo. R. Civ. P. 106(b).\\n\\n -5-\\n\\f106(a)(4) action.” 926 P.2d at 548. But the court went on to explain that\\n\\n“because claims under § 1983 exist as a uniquely federal remedy that is to be\\n\\naccorded a sweep as broad as its language” “[t]he analysis shifts . . . when a\\n\\ncomplainant asserts a claim for money damages under § 1983.” Id. (cleaned up).\\n\\nThe court therefore affirmed “that a § 1983 damages claim may exist separately\\n\\nfrom a C.R.C.P. 106(a)(4) action.” Id. at 549.\\n\\n Sundheim thus stands only for the noncontroversial proposition that\\n\\nplaintiffs need not forfeit their § 1983 claims simply because they choose not to\\n\\npursue a Rule 106(a)(4) action. A state procedural deadline for filing Rule\\n\\n106(a)(4) actions cannot bar a § 1983 claim properly filed within the two-year\\n\\nstatute of limitations.\\n\\n One year after deciding Sundheim, the Colorado Supreme Court deemed res\\n\\njudicata inapplicable to a § 1983 suit against the State Board of Chiropractic\\n\\nExaminers in Stjernholm. In a previous action, Stjernholm challenged the board’s\\n\\nsuspension of his license in the court of appeals, as required by the Chiropractic\\n\\nAct. See Stjernholm, 935 P.2d at 964–66; see also Colo. Rev. Stat. § 12-33-121\\n\\n(granting initial jurisdiction to the court of appeals to review Chiropractic Board\\n\\ndeterminations). Taking note of that prior appeal, the Colorado Supreme Court\\n\\napplied Sundheim to the § 1983 case before it, observing that the § 1983 case\\n\\ncould not have been resolved in an appellate tribunal because “Section 1983 suits\\n\\ninvolve evidentiary presentation to and fact finding by a district court.” Id. at\\n\\n -6-\\n\\f967. The court therefore concluded the court of appeals “did not err in refusing,\\n\\nas a general matter, to employ res judicata to preclude section 1983 litigation in\\n\\nthe [state] district court.” Id.\\n\\n It is obvious that a complainant such as Stjernholm bringing a Chiropractic\\n\\nAct challenge before the court of appeals in the first instance cannot raise § 1983\\n\\nclaims at that juncture. This is unlike the procedures available under a Rule\\n\\n106(a)(4) appeal in state district court. Parties cannot add and litigate new claims\\n\\nfor relief—which often will require discovery and trial—initially in the court of\\n\\nappeals. The court of appeals is simply a reviewing body, undertaking a record\\n\\nreview as set forth in the Colorado Administrative Procedure Act, Colo. Rev. Stat.\\n\\n§ 24-4-106(11).\\n\\n But it is equally obvious a complainant bringing an APA challenge before\\n\\nthe district court can raise and litigate such claims. See Crocog Co. v. Reeves,\\n\\n992 F.2d 267, 269–70 (10th Cir. 1993) (granting res judicata against plaintiff’s\\n\\n§ 1983 claim because it could have joined that claim in state district court under\\n\\n§ 24-4-106(6)). Thus, Stjernholm applies Sundheim to Chiropractic Act appeals\\n\\nin which the complainant could not have brought his § 1983 claims in the prior\\n\\nproceeding before the court of appeals. Accord id. at 269 (“Plaintiff argues that\\n\\nthe Colorado courts would not have permitted the joinder of its § 1983 claim to\\n\\nthe review of the administrative proceeding. Under Colorado law, such an\\n\\n\\n\\n -7-\\n\\fargument, if true, would defeat claim preclusion.” (citing Carpenter v. Young,\\n\\n773 P.2d 561, 565 n.5 (Colo. 1989))).\\n\\n Taken together, Sundheim and Stjernholm are best read as holding that if a\\n\\nplaintiff cannot join § 1983 claims to an administrative challenge or chooses not\\n\\nto bring an administrative challenge, then the plaintiff is not precluded from\\n\\nraising § 1983 claims in a free standing action. If one does bring an\\n\\nadministrative challenge in state district court under Rule 106(a)(4), however, the\\n\\nstate’s interest in judicial efficiency kicks in and any § 1983 claims not joined\\n\\nmay be claim-precluded in the future.\\n\\n On the contrary, Gale argues Sundheim and Stjernholm establish a blanket\\n\\n§ 1983 exception from the Bolling/Norby rule requiring joinder of all claims in a\\n\\nRule 106(a)(4) proceeding. A putative plaintiff can hold onto his § 1983 claim\\n\\nregardless of whether he is pursuing relief for the same claim in state courts.\\n\\n Because the central issue before our court is the extent to which a prior\\n\\nRule 106(a)(4) action would preclude Gale’s federal action under Colorado law,\\n\\nthe Colorado Supreme Court is the best venue to resolve any uncertainty as to\\n\\ninterpretation of controlling precedent. The certified question is a pure question\\n\\nof law and does not entail any factual disputes for the court to resolve.\\n\\nMoreover, the question of state law presented in this case involves rights and\\n\\nremedies at the intersection of state and federal jurisdiction. In furtherance of\\n\\n\\n\\n -8-\\n\\fcomity and federalism, we conclude the Colorado Supreme Court should have the\\n\\nopportunity to answer this important question in the first instance.\\n\\n We greatly appreciate the consideration of this request.\\n\\n III. Conclusion\\n\\n Gale’s motion to certify this question of state law is GRANTED. The\\n\\nappeal is therefore ABATED pending resolution of the question certified to the\\n\\nSupreme Court of Colorado. The clerk of this court shall submit to the Supreme\\n\\nCourt of Colorado a certified copy of this order, together with copies of the briefs\\n\\nfiled in this court and a copy of the judgment of the district court.\\n\\n ENTERED FOR THE COURT\\n\\n\\n\\n\\n Timothy M. Tymkovich\\n Chief Judge\\n\\n\\n\\n\\n -9-\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2267,"cells":{"id":{"kind":"number","value":4621587,"string":"4,621,587"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellee, v. Wendy Marie YUREK, Defendant-Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Yurek (Wendy)"},"decision_date":{"kind":"string","value":"2019-05-21"},"docket_number":{"kind":"string","value":"18-1134"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Bacharach, Baldock, Ebel\", \"parties\": \"\", \"opinions\": [{\"author\": \"BACHARACH, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 21, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\nv. No. 18-1134\\n\\nWENDY MARIE YUREK,\\n\\n Defendant-Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:15-CR-00394-WJM-2)\\n _________________________________\\n\\nRobert S. Jackson, Oklahoma City, Oklahoma, for Defendant-Appellant.\\n\\nPegeen D. Rhyne, Assistant United States Attorney (Jason R. Dunn, United\\nStates Attorney, with her on the brief), Denver, Colorado, for Plaintiff-\\nAppellee.\\n _________________________________\\n\\nBefore BACHARACH, BALDOCK, and EBEL, Circuit Judges.\\n _________________________________\\n\\nBACHARACH, Circuit Judge.\\n _________________________________\\n\\f Mrs. Wendy Yurek and her husband, Mr. Daryl Yurek, were charged\\n\\nwith tax evasion and bankruptcy fraud. 1 After a joint jury trial, Mrs. Yurek\\n\\nand her husband were convicted on both offenses. The district court then\\n\\nsentenced Mrs. Yurek to a prison term of 27 months, leading her to appeal\\n\\nthe conviction and sentence.\\n\\n We affirm in part and reverse in part. We affirm Mrs. Yurek’s\\n\\nconviction, but we vacate the sentence because the district court applied\\n\\nthe wrong test when deciding whether to grant a mitigating-role\\n\\nadjustment.\\n\\nI. We reject Mrs. Yurek’s challenges to the sufficiency of the\\n evidence on her conviction for tax evasion and bankruptcy fraud.\\n\\n We conclude that the evidence of Mrs. Yurek’s guilt was sufficient to\\n\\nsupport her conviction for tax evasion and bankruptcy fraud.\\n\\n A. We engage in de novo review over the sufficiency of the\\n evidence.\\n\\n In considering the sufficiency of the evidence, we engage in de novo\\n\\nreview. United States v. Ramos-Arenas, 596 F.3d 783, 786 (10th Cir.\\n\\n2010). We will reverse only if no rational factfinder could have found that\\n\\nthe government had proven all of the elements of an offense beyond a\\n\\n\\n\\n\\n1\\n Mr. Yurek was also charged with making a false statement under oath\\nin a bankruptcy proceeding and willfully making false statements to the\\nIRS under penalty of perjury.\\n\\n 2\\n\\freasonable doubt. United States v. Brown, 400 F.3d 1242, 1247 (10th Cir.\\n\\n2005).\\n\\n Under de novo review, we view the trial evidence in the light most\\n\\nfavorable to the government. United States v. Boisseau, 841 F.3d 1122,\\n\\n1125 (10th Cir. 2016). We do not reevaluate witness credibility or reweigh\\n\\nthe evidence. United States v. Smith, 133 F.3d 737, 742 (10th Cir. 1997).\\n\\n B. The evidence was sufficient to convict on tax evasion.\\n\\n Mrs. Yurek was convicted of tax evasion, which consists of\\n\\n“willfully attempt[ing] in any manner to evade or defeat any tax imposed\\n\\nby [the Internal Revenue Code] or the payment thereof.” 26 U.S.C. § 7201.\\n\\nTo obtain a conviction on this offense, the government had to prove three\\n\\nelements:\\n\\n 1. Mrs. Yurek owed a substantial tax to the IRS.\\n\\n 2. Mrs. Yurek committed “an affirmative act constituting an\\n evasion or attempted evasion” of assessment or payment of the\\n tax.\\n\\n 3. Mrs. Yurek willfully evaded or attempted to evade the\\n assessment or payment of the tax. 2\\n\\nUnited States v. Boisseau, 841 F.3d 1122, 1125 (10th Cir. 2016) (citing\\n\\nSansone v. United States, 380 U.S. 343, 351 (1965)); see United States v.\\n\\n\\n2\\n Mrs. Yurek argues that the government did not establish that she and\\nher husband had the ability to pay their IRS tax debt. But the ability to pay\\none’s taxes is not an element of tax evasion. See Boisseau, 841 F.3d at\\n1125.\\n\\n 3\\n\\fThompson, 518 F.3d 832, 850 (10th Cir. 2008) (noting that the tax liability\\n\\nmust be “substantial”).\\n\\n Mrs. Yurek challenges the sufficiency of the evidence on the second\\n\\nand third elements (an affirmative act and willfulness).\\n\\n 1. The evidence was sufficient to find an affirmative act.\\n\\n To establish an affirmative act, the government had to prove an act\\n\\ndesigned to “mislead or conceal” within the six-year period of limitations.\\n\\nUnited States v. Thompson, 518 F.3d 832, 852 (10th Cir. 2008); see United\\n\\nStates v. Anderson, 319 F.3d 1218, 1219 (10th Cir. 2003) (holding that\\n\\nwhen a defendant commits a series of affirmative acts over multiple years,\\n\\nthe six-year period of limitations for tax evasion begins with the last\\n\\naffirmative act). The government bore the burden to prove that Mrs. Yurek\\n\\nhad committed at least one affirmative act. United States v. Hoskins, 654\\n\\nF.3d 1086, 1091 (10th Cir. 2011). The jury could have reasonably found\\n\\nthat the government had satisfied this burden.\\n\\n a. “Affirmative acts” are broadly defined.\\n\\n We first consider what constitutes an affirmative act. Federal law\\n\\nsuggests an expansive definition, stating that tax evasion can be committed\\n\\nby evading taxes “in any manner.” 26 U.S.C. § 7201; see Boisseau, 841\\n\\nF.3d at 1125 (“[T]he type of affirmative conduct that can constitute an\\n\\naffirmative act of evasion is broad.”). Affirmative acts thus include\\n\\n concealing assets,\\n 4\\n\\f covering up sources of income, and\\n\\n engaging in misleading or concealing conduct.\\n\\nBoisseau, 841 F.3d at 1125. Affirmative acts may even consist of otherwise\\n\\nlawful conduct if the acts are committed with an intent to evade taxes. Id.;\\n\\nUnited States v. Gorrell, No. 18-5041, 2019 WL 1890971 at *5 (10th Cir.\\n\\nApr. 29, 2019).\\n\\n b. The evidence sufficed for a finding that Mrs. Yurek had\\n committed an affirmative act.\\n\\n Viewed in the light most favorable to the government, the trial\\n\\nevidence allowed a reasonable jury to find affirmative acts involving (1)\\n\\npayment of personal expenses from business accounts and (2) submission\\n\\nof false tax documents to the IRS.\\n\\n i. The jury could have reasonably found that Mrs. Yurek had\\n committed affirmative acts by paying her and her husband’s\\n personal expenses out of business accounts.\\n\\n Mrs. Yurek had authority to write checks on behalf of Bolder Venture\\n\\nPartners and Veracity Credit Consultants, LLC, and she used that authority\\n\\nto write business checks for her and her husband’s personal expenses. A\\n\\nfact-finder could have reasonably viewed the writing of these checks as\\n\\naffirmative acts to evade taxes.\\n\\n Some of these checks came from Bolder Venture Partners, where\\n\\nMrs. Yurek was a partner. For example, Mrs. Yurek signed a $2,309.68\\n\\n\\n\\n 5\\n\\fcheck from Bolder 3 to pay condominium-association dues for the loft where\\n\\nshe and her husband lived.\\n\\n Mrs. Yurek contends that her son, Mr. Justin Yurek, owned the loft.\\n\\nBut the trial evidence was sufficient to support findings that (1) Justin had\\n\\nbeen a “straw purchaser” and (2) Mrs. Yurek and her husband were the true\\n\\nowners of the loft. See United States v. Reese, 745 F.3d 1075, 1078 (10th\\n\\nCir. 2014) (explaining a straw purchase).\\n\\n Mrs. Yurek and her husband had been leasing the loft and living in it.\\n\\nThey had a contract to purchase the loft, but a tax lien prevented them\\n\\nfrom obtaining a mortgage. So they assigned the contract to Justin, who\\n\\npurchased the loft. Though Justin was the purchaser, Mrs. Yurek’s husband\\n\\nnegotiated the sale and used companies (over which he wielded significant\\n\\ncontrol) to fund more than $112,000 of the down payment.\\n\\n After Justin purchased the loft, Mrs. Yurek signed an affidavit on\\n\\nJustin’s behalf, stating under oath that (1) the loft would serve as Justin’s\\n\\nprimary residence and (2) Justin had no intent to lease the loft or to make\\n\\nthe purchase as an investment. 4 But Justin never lived in the loft, and Mrs.\\n\\n\\n\\n\\n3\\n Mrs. Yurek wrote the check for $2,309.68 within the six-year\\nlimitations period.\\n4\\n Despite the affidavit, Justin testified that he had bought the loft as an\\ninvestment.\\n\\n 6\\n\\fYurek and her husband continued to live there while making only\\n\\ninfrequent rental payments.\\n\\n Mrs. Yurek not only used her role at Bolder to pay condominium-\\n\\nassociation dues but also used her check-writing authority at Veracity\\n\\nCredit Consultants, LLC to pay her husband’s country-club dues and\\n\\nexpenses. For example, she signed a Veracity check for $3,403.43 to pay\\n\\nthese expenses. 5\\n\\n Veracity also paid other expenses for Mrs. Yurek and her husband.\\n\\nFor example, Veracity paid the rent on two homes that Mrs. Yurek and her\\n\\nhusband used. Veracity’s former chief financial officer, Mr. Michael\\n\\nHennigan, testified that he knew of no business purpose for these rentals or\\n\\nthe country-club dues and expenses.\\n\\n Veracity also made mortgage payments on the loft where Mrs. Yurek\\n\\nand her husband lived. The jury could reasonably infer that the Yureks\\n\\nwere trying to hide the source of these mortgage payments. For example,\\n\\nthey recorded the mortgage payments under an account designated as a\\n\\nloan account for Mrs. Yurek’s husband, but Veracity did little to collect on\\n\\nthe purported loan.\\n\\n Bolder and Veracity paid these various personal expenses for Mrs.\\n\\nYurek and her husband while they\\n\\n owed substantial taxes and penalties to the IRS and\\n\\n5\\n This check was signed within the six-year period of limitations.\\n 7\\n\\f tried to settle with the IRS based on their inability to pay what\\n they owed.\\n\\nThese payments continued through the bankruptcy proceedings, where Mrs.\\n\\nYurek and her husband tried to discharge their federal tax debt. But Mrs.\\n\\nYurek and her husband did not tell the IRS about these payments.\\n\\n Given this combination of evidence, the jury could have reasonably\\n\\nfound that Mrs. Yurek had committed an affirmative act to evade the\\n\\npayment of taxes. See United States v. Farr, 701 F.3d 1274, 1285–86 (10th\\n\\nCir. 2012) (concluding that the defendant’s use of a corporate account to\\n\\npay for personal living expenses supported a factual finding that the\\n\\ndefendant had “willfully evaded [a tax penalty] and [had taken] affirmative\\n\\nsteps to do so”).\\n\\n ii. A reasonable jury could also have found that Mrs. Yurek\\n had committed affirmative acts by submitting false tax\\n documents to the IRS.\\n\\n Along with her husband, Mrs. Yurek submitted tax forms to the IRS\\n\\nin 2009 and 2010. On these forms, Mrs. Yurek and her husband reported\\n\\nthat their gross monthly income was $7,667. But this amount didn’t include\\n\\nBolder and Veracity’s payments for personal expenses. The jury could\\n\\nreasonably have viewed these omissions as misleading or even false.\\n\\n\\n\\n\\n 8\\n\\f Mrs. Yurek’s submission of misleading or false tax documents to the\\n\\nIRS could constitute affirmative acts. 6 See Sansone v. United States, 380\\n\\nU.S. 343, 351–52 (1965) (“[I]t is undisputed that petitioner filed a tax\\n\\nreturn and that the petitioner’s filing of a false tax return constituted a\\n\\nsufficient affirmative commission to satisfy that requirement of § 7201.”);\\n\\nUnited States v. Hoskins, 654 F.3d 1086, 1091 (10th Cir. 2011)\\n\\n(concluding that submission of a false tax return “was sufficient to\\n\\nestablish an affirmative act under § 7201”).\\n\\n 2. The evidence was sufficient to find that Mrs. Yurek had\\n acted willfully.\\n\\n To satisfy the willfulness requirement, the government had to prove a\\n\\nspecific intent to evade taxes. United States v. Payne, 978 F.2d 1177, 1182\\n\\n(10th Cir. 1992); see Hoskins, 654 F.3d at 1090 (“Under § 7201,\\n\\n‘willfulness’ means the ‘voluntary, intentional violation of a known legal\\n\\nduty.’” (quoting Cheek v. United States, 498 U.S. 192, 201 (1991))).\\n\\n The government can ordinarily establish the willfulness requirement\\n\\nthrough “circumstantial evidence or inferences arising from a defendant’s\\n\\nconduct.” United States v. Boisseau, 841 F.3d 1122, 1127 (10th Cir. 2016).\\n\\nThe willfulness requirement is “closely connected” to the affirmative-act\\n\\n\\n\\n\\n6\\n The government also argues that Mrs. Yurek’s filing of the\\nbankruptcy petition constituted an affirmative act. We need not address\\nthis argument.\\n\\n 9\\n\\frequirement, for “‘[e]vidence of affirmative acts may be used to show\\n\\nwillfulness.’” Id. (quoting United States v. Romano, 938 F.2d 1569, 1572\\n\\n(2d Cir. 1991)) (alteration in original).\\n\\n Viewed in the light most favorable to the government, the trial\\n\\nevidence was sufficient in five ways to prove Mrs. Yurek’s specific intent\\n\\nto evade taxes.\\n\\n First, a reasonable jury could have found that Mrs. Yurek had known\\n\\nof her legal obligation to pay her federal tax debt. With this finding, the\\n\\njury could reasonably have concluded that Mrs. Yurek had committed the\\n\\naffirmative acts with an intent to evade payment of her tax debt.\\n\\n Second, Mrs. Yurek represented to the IRS that she and her husband\\n\\ncouldn’t pay more than $75,000 of their tax liability based on “insufficient\\n\\nassets and income” even though they had just signed a contract to pay $1.3\\n\\nmillion for a loft. Supp. R., vol. 1, at 125, 185. Given the timing of Mrs.\\n\\nYurek’s representation to the IRS and the contract to purchase the loft, a\\n\\njury could rationally have found a specific intent to evade the tax debt.\\n\\n Third, the jury could reasonably have found that Mrs. Yurek had\\n\\narranged for Justin to purchase the loft in order to conceal her financial\\n\\ninterest in it. See pp. 6–7, above.\\n\\n Fourth, Mrs. Yurek reported to the IRS that she and her husband had\\n\\na gross monthly income of $7,667 in 2009 and 2010, but Bolder and\\n\\n\\n\\n 10\\n\\fVeracity paid monthly payments of more than $7,667 for the Yureks’\\n\\npersonal expenses.\\n\\n Fifth, Mrs. Yurek told Veracity’s accountant that her husband would\\n\\nrepay his loan account every year. He didn’t, so a jury could reasonably\\n\\nhave found that (1) Mrs. Yurek was misleading the accountant about her\\n\\nhusband’s intent to repay the loans and (2) the loan account served as a\\n\\nsham to deceive the IRS.\\n\\n The jury thus could reasonably have found that Mrs. Yurek had a\\n\\nspecific intent to evade the payment of tax debt, and this finding would\\n\\nsatisfy the requirement of willfulness. See United States v. Guidry, 199\\n\\nF.3d 1150, 1157 (10th Cir. 1999) (observing that willfulness can be\\n\\ninferred from “concealment of assets or covering up sources of income”\\n\\n(quoting Spies v. United States, 317 U.S. 492, 499 (1943))).\\n\\n Despite this evidence, Mrs. Yurek argues that she lacked expertise in\\n\\ntax matters and depended on professionals. But the jury could reasonably\\n\\nhave discounted this argument and found that Mrs. Yurek had known that\\n\\nshe was giving false information to the IRS. For example, the jury could\\n\\nhave reasonably relied on Mrs. Yurek’s accounting experience, which\\n\\nincluded handling Veracity’s payroll and accounts payable and helping to\\n\\nprepare Bolder’s tax returns in 2005, 2006, and 2007. See United States v.\\n\\nGuidry, 199 F.3d 1150, 1157 (10th Cir. 1999) (treating evidence of a\\n\\ndefendant’s accounting experience as support for a finding of willfulness).\\n\\n 11\\n\\f * * *\\n\\n For these reasons, we reject Mrs. Yurek’s challenge to the\\n\\nsufficiency of the evidence for her conviction on tax evasion. 7\\n\\n C. The evidence was sufficient to convict Mrs. Yurek of\\n bankruptcy fraud.\\n\\n Mrs. Yurek was also convicted of bankruptcy fraud. This crime\\n\\ninvolves filing a bankruptcy petition with an intent to execute, conceal, or\\n\\nattempt to execute or conceal “a scheme or artifice to defraud.” 18 U.S.C.\\n\\n§ 157(1). To obtain a conviction on this offense, the government had to\\n\\nprove three elements beyond a reasonable doubt:\\n\\n 1. Mrs. Yurek had devised or intended to devise a scheme to\\n defraud or otherwise engage in a fraudulent scheme.\\n\\n 2. Mrs. Yurek had filed a bankruptcy petition with the purpose to\\n execute or conceal the scheme or attempt to do so.\\n\\n 3. Mrs. Yurek had acted with the specific intent to defraud. 8\\n7\\n Mrs. Yurek argues that her conviction cannot stand because the\\ngovernment didn’t present expert testimony on “technical concepts such as\\nincome or assets.” Appellant’s Op. Br. at 15. We disagree and conclude\\nthat expert testimony was not necessary to assist the jury in understanding\\nthe evidence.\\n8\\n In its jury instructions on the first and third elements, the district\\ncourt referred to our circuit’s pattern jury instruction for mail fraud under\\n18 U.S.C. § 1341:\\n A “scheme to defraud” is conduct intended to or reasonably\\n calculated to deceive persons of ordinary prudence or\\n comprehension and includes a scheme to deprive another of\\n money or property. An “intent to defraud” means an intent to\\n deceive or cheat someone.\\n\\n\\n 12\\n\\fSee United States v. Spurlin, 664 F.3d 954, 964 (5th Cir. 2011) (listing the\\n\\nelements that the government must prove under § 157(1) as “(1) a specific\\n\\nintent to defraud; (2) a scheme to defraud; and (3) filing a bankruptcy\\n\\npetition to conceal or execute that scheme”). Mrs. Yurek argues that the\\n\\ntrial evidence was insufficient on the elements of bankruptcy fraud. 9 We\\n\\ndisagree.\\n\\n Viewed in the light most favorable to the government, the trial\\n\\nevidence was sufficient for a jury to reasonably find satisfaction of each\\n\\nelement. That evidence showed six pertinent facts:\\n\\n 1. Mrs. Yurek and her husband had owed a substantial tax debt to\\n the IRS.\\n\\n 2. Mrs. Yurek and her husband had filed a bankruptcy petition in\\n order to discharge that debt.\\n\\n 3. When filing the bankruptcy petition, Mrs. Yurek and her\\n husband had not told the court that Bolder and Veracity were\\n paying the Yureks’ personal expenses.\\n\\n\\nR., vol. 2, at 121–22 (citing 10th Cir. Pattern Crim. Jury Instr. § 2.56 (mail\\nfraud)). As the district court noted, courts have used § 1341 for guidance\\nwhen interpreting 18 U.S.C. § 157(1). See United States v. Milwitt, 475\\nF.3d 1150, 1155 n.5 (9th Cir. 2007) (“Most of the few courts that have\\ninterpreted 18 U.S.C. § 157 have looked to 18 U.S.C. §§ 1341 and 1343 for\\nguidance.”).\\n9\\n Mrs. Yurek also relies on the fact that the IRS and the bankruptcy\\ntrustee didn’t object to discharge of the Yureks’ tax debt. According to\\nMrs. Yurek, the absence of an objection shows that the government did not\\nprove the elements of bankruptcy fraud. We disagree. The absence of an\\nobjection could conceivably affect the weight of the evidence but not its\\nsufficiency to convict.\\n\\n 13\\n\\f 4. Bolder and Veracity had continued to pay the Yureks’ personal\\n expenses during the bankruptcy proceedings, but Mrs. Yurek\\n and her husband never told the bankruptcy court about these\\n payments.\\n\\n 5. Mrs. Yurek had been a partner at Bolder and was responsible\\n for Veracity’s accounts payable and payroll.\\n\\n 6. Mrs. Yurek had participated in obtaining the checks from\\n Bolder and Veracity for personal expenses.\\n\\nGiven the evidence of these six facts, we conclude that the jury could\\n\\nreasonably have found all of the elements of bankruptcy fraud.\\n\\nII. We reject Mrs. Yurek’s challenges to the district court’s denials\\n of her motions for severance and a new trial.\\n\\n We also reject Mrs. Yurek’s arguments that the district court should\\n\\nhave (1) severed her trial from her husband’s or (2) granted her a new trial.\\n\\n A. The district court generally enjoyed discretion on these\\n matters.\\n\\n On these issues, we apply the abuse-of-discretion standard. See\\n\\nUnited States v. Pursley, 577 F.3d 1204, 1215 (10th Cir. 2009)\\n\\n(severance); United States v. Patterson, 41 F.3d 577, 579–80 (10th Cir.\\n\\n1994) (new trial). On the refusal to sever the trial, Mrs. Yurek needed to\\n\\nshow actual prejudice. See United States v. Hack, 782 F.2d 862, 870 (10th\\n\\nCir. 1986) (“To establish that a court abused its discretion, a defendant\\n\\nmust show actual prejudice to him resulting from a denial of his request for\\n\\nseverance.”).\\n\\n\\n 14\\n\\f To satisfy this burden, Mrs. Yurek needed to show a “serious risk”\\n\\nthat joinder would compromise a specific trial right or prevent a reliable\\n\\ndetermination of guilt. Pursley, 577 F.3d at 1215. Mrs. Yurek argues both,\\n\\nasserting that joinder\\n\\n created prejudice through a spillover effect from the evidence\\n of her husband’s guilt and\\n\\n violated the Sixth Amendment and created further prejudice by\\n preventing her from confronting her husband about his out-of-\\n court statement in bankruptcy court. 10\\n\\nIn our review of her Sixth Amendment theory, we engage in de novo\\n\\nreview. United States v. Clark, 717 F.3d 790, 813 (10th Cir. 2013).\\n\\n B. Mrs. Yurek has not shown actual prejudice from\\n introduction of the evidence against her husband.\\n\\n Mrs. Yurek contends that her trial should have been severed from her\\n\\nhusband’s because\\n\\n the evidence against her was slim in comparison to the\\n evidence against her husband and\\n\\n the jury could not have followed the district court’s instruction\\n to separately consider the evidence against her and her\\n husband.\\n\\n\\n10\\n In a footnote, Mrs. Yurek also suggests that the government violated\\nFederal Rule of Evidence 403 by using her husband’s out-of-court\\nstatement against her. Mrs. Yurek’s passing reference to Rule 403 does not\\nconstitute adequate briefing of a distinct issue. See Adler v. Wal-Mart\\nStores, Inc., 144 F.3d 664, 679 (10th Cir. 1998) (“Arguments inadequately\\nbriefed in the opening brief are waived.”); COPE v. Kan. State Bd. of\\nEduc., 821 F.3d 1215, 1219 n.4 (10th Cir. 2016) (concluding that “passing\\nreferences” to an issue do not constitute adequate briefing).\\n\\n 15\\n\\fWe conclude that the district court acted within its discretion by rejecting\\n\\nthese arguments.\\n\\n Federal courts generally prefer to jointly try defendants who were\\n\\nindicted together. Zafiro v. United States, 506 U.S. 534, 537 (1993). This\\n\\npreference is based on recognition that\\n\\n joint trials “promote efficiency and serve the interests of\\n justice by avoiding the scandal and inequity of inconsistent\\n verdicts” 11 and\\n\\n joint trials are ordinarily more efficient in cases where the\\n evidence against multiple defendants is “overlapping and\\n intertwined.” 12\\n\\n Mrs. Yurek tries to skirt this preference based on the alleged\\n\\nspillover of evidence against her husband. But severance is not warranted\\n\\nby “a mere allegation that defendant would have a better chance of\\n\\nacquittal in a separate trial” or “a complaint of the ‘spillover effect’ from\\n\\nthe evidence that was overwhelming or more damaging against the co-\\n\\ndefendant than that against the moving party.” United States v. Hack, 782\\n\\nF.2d 862, 870 (10th Cir. 1986); see United States v. Wardell, 591 F.3d\\n\\n1279, 1300 (10th Cir. 2009) (“[T]he nearly insuperable rule in this circuit\\n\\nis that a defendant cannot obtain severance simply by showing that the\\n\\n\\n\\n\\n11\\n Zafiro, 506 U.S. at 537 (internal quotation marks omitted).\\n12\\n United States v. Morales, 108 F.3d 1213, 1220 (10th Cir. 1997).\\n\\n\\n 16\\n\\fevidence against a co-defendant is more damaging than the evidence\\n\\nagainst herself.” (internal quotation marks omitted)). So Mrs. Yurek’s\\n\\ncomplaints about the strength of the trial evidence against her husband do\\n\\nnot warrant severance.\\n\\n Coupled with the preference for joint trials is the district court’s\\n\\nguidance to the jury. The court instructed the jury\\n\\n that it “must separately consider the evidence against each\\n defendant and return a separate verdict for each” and\\n\\n that its “verdict as to one defendant . . . should not affect [its]\\n verdict as to the other defendant.”\\n\\nR., vol. 2, at 113. These instructions, which the jury presumably followed,\\n\\nnegated the risk of prejudice to Mrs. Yurek from the joint trial. See Weeks\\n\\nv. Angelone, 528 U.S. 225, 234 (2000) (“A jury is presumed to follow its\\n\\ninstructions.”); Wardell, 591 F.3d at 1301 (noting that the district court’s\\n\\njury instruction “to give separate and individual consideration to each\\n\\ncharge against each defendant” and the district court’s other cautionary\\n\\nstatements to the jury “negated any risk of prejudice” to the defendant\\n\\nfrom the joint trial). We thus conclude that the district court acted within\\n\\nits discretion by denying Mrs. Yurek’s motions to sever the trial and to\\n\\ngrant a new trial.\\n\\n\\n\\n\\n 17\\n\\f C. The district court’s refusal to sever the trial did not violate\\n Mrs. Yurek’s right to confrontation because her husband’s\\n out-of-court statement had not been testimonial.\\n\\n Mrs. Yurek contends that the refusal to sever the trial violated her\\n\\nright to confrontation by allowing the government to use the husband’s\\n\\nout-of-court statement against her. But the Sixth Amendment applies only\\n\\nwhen the out-of-court statement is testimonial. 13 See United States v.\\n\\nClark, 717 F.3d 790, 815 (10th Cir. 2013) (observing that the Sixth\\n\\nAmendment’s Confrontation Clause applies only if a statement is\\n\\n“testimonial”). Statements in furtherance of a conspiracy are\\n\\nnontestimonial, so they are admissible even when the defendants cannot\\n\\nconfront the declarants. United States v. Patterson, 713 F.3d 1237, 1247\\n\\n(10th Cir. 2013); see Crawford v. Washington, 541 U.S. 36, 56 (2004)\\n\\n\\n13\\n We have supplied “two possible definitions” for what constitutes a\\n“testimonial” statement:\\n\\n 1. “a formal declaration made by the declarant that, when\\n objectively considered, indicates the primary purpose for which\\n the declaration was made was that of establishing or proving\\n some fact potentially relevant to a criminal prosecution” and\\n\\n 2. “[a] formal statement [such that] a reasonable person in the\\n position of the declarant would objectively foresee that the\\n primary purpose of the statement was for use in the\\n investigation or prosecution of a crime.”\\n\\nUnited States v. Clark, 717 F.3d 790, 816 (10th Cir. 2013) (alterations in\\noriginal) (quoting United States v. Smalls, 605 F.3d 765, 778 (10th Cir.\\n2010)).\\n\\n\\n 18\\n\\f(observing that statements in furtherance of a conspiracy are not\\n\\ntestimonial).\\n\\n Prior to trial, the district court concluded that Mr. Yurek’s out-of-\\n\\ncourt statement 14 was admissible against Mrs. Yurek as a statement by a\\n\\ncoconspirator. To qualify for admissibility as a coconspirator statement,\\n\\nthe statement must have been made during and in furtherance of a\\n\\nconspiracy. Fed. R. Evid. 801(d)(2)(E).\\n\\n Mrs. Yurek does not challenge the district court’s admissibility\\n\\ndetermination, so we regard the husband’s out-of-court statement as\\n\\nnontestimonial. Introduction of this nontestimonial statement against Mrs.\\n\\nYurek did not violate the Sixth Amendment. See Patterson, 713 F.3d at\\n\\n1247 (concluding that statements made in furtherance of a conspiracy were\\n\\nproperly admitted because they were nontestimonial).\\n\\n D. Mrs. Yurek has not demonstrated that her husband would\\n have been willing to testify at a severed trial.\\n\\n Mrs. Yurek also contends that if the trial had been severed, she could\\n\\nhave cross-examined her husband about his out-of-court statement. 15 But\\n\\nMrs. Yurek never presented evidence that her husband would have testified\\n\\n\\n14\\n He made the statement in bankruptcy court; but for purposes of\\nadmissibility, the pertinent court is the federal district court in Mrs.\\nYurek’s trial.\\n15\\n The parties dispute whether Mrs. Yurek preserved this argument. For\\nthe sake of argument, we assume preservation.\\n\\n 19\\n\\fat a severed trial. Indeed, Mrs. Yurek concedes that she does not know\\n\\nwhether he would have done so. Appellant’s Op. Br. at 27. The resulting\\n\\nuncertainty is fatal to Mrs. Yurek’s contention. See United States v.\\n\\nPursley, 577 F.3d 1204, 1216 (10th Cir. 2009) (upholding the denial of a\\n\\nmotion to sever because the defendant did not submit affidavits from his\\n\\nco-defendants regarding their willingness to testify at a severed trial);\\n\\nUnited States v. Dirden, 38 F.3d 1131, 1141 n.13 (10th Cir. 1994)\\n\\n(upholding the denial of the defendant’s motion to sever based on the lack\\n\\nof evidence that the co-defendant would have given exculpatory\\n\\ntestimony).\\n\\n * * *\\n\\n For these reasons, we conclude that the district court acted within its\\n\\ndiscretion in denying Mrs. Yurek’s motions for severance and a new trial.\\n\\nIII. We reject Mrs. Yurek’s challenge based on multiplicity.\\n\\n Mrs. Yurek insists that she was convicted of multiplicitous charges:\\n\\ntax evasion and bankruptcy fraud. Charges are multiplicitous when they\\n\\ncover the same criminal conduct. United States v. McCullough, 457 F.3d\\n\\n1150, 1162 (10th Cir. 2006). On challenges involving multiplicity, we\\n\\ngenerally engage in de novo review. United States v. McIntosh, 124 F.3d\\n\\n1330, 1336 (10th Cir. 1997). But Mrs. Yurek did not raise the issue in a\\n\\n\\n\\n\\n 20\\n\\fpretrial motion, so we review her argument only for plain error. Id. We\\n\\nconclude that there was no error, plain or otherwise.\\n\\n The Fifth Amendment forbids convictions on multiplicitous charges.\\n\\nMcCullough, 457 F.3d at 1162. But under the Blockburger test, the same\\n\\nconduct can trigger prosecution for multiple crimes “if each crime requires\\n\\nproof of a fact that the other does not.” United States v. Berres, 777 F.3d\\n\\n1083, 1090 (10th Cir. 2015); see Blockburger v. United States, 284 U.S.\\n\\n299, 304 (1932) (“[W]here the same act or transaction constitutes a\\n\\nviolation of two distinct statutory provisions, the test to be applied to\\n\\ndetermine whether there are two offenses or only one, is whether each\\n\\nprovision requires proof of a fact which the other does not.”). We thus\\n\\nfocus on whether the elements differ for Mrs. Yurek’s crimes of tax\\n\\nevasion and bankruptcy fraud. See Illinois v. Vitale, 447 U.S. 410, 416\\n\\n(1980) (analyzing the elements of the crimes of conviction when applying\\n\\nthe Blockburger test).\\n\\n A conviction for tax evasion requires proof of three elements:\\n\\n 1. The defendant owed a substantial tax to the IRS.\\n\\n 2. The defendant committed “an affirmative act constituting an\\n evasion or attempted evasion” of assessment or payment of the\\n tax.\\n\\n 3. The defendant willfully evaded or attempted to evade the\\n assessment or payment of the tax.\\n\\n\\n\\n\\n 21\\n\\fUnited States v. Boisseau, 841 F.3d 1122, 1125 (10th Cir. 2016) (citing\\n\\nSansone v. United States, 380 U.S. 343, 351 (1965)). A conviction for\\n\\nbankruptcy fraud also requires proof of three elements:\\n\\n 1. The defendant devised or intended to devise a scheme to\\n defraud or otherwise engage in a fraudulent scheme.\\n\\n 2. For the purpose of executing or concealing the scheme or\\n attempting to do so, the defendant filed a petition under the\\n Bankruptcy Code.\\n\\n 3. The defendant acted with the specific intent to defraud.\\n\\nUnited States v. Spurlin, 664 F.3d 954, 964 (5th Cir. 2011). As Mrs. Yurek\\n\\nadmits, each crime requires proof of an element that the other crime does\\n\\nnot. We thus would not ordinarily consider the two counts multiplicitous.\\n\\n But Mrs. Yurek argues that the government’s theory essentially\\n\\nrequired the same elements for both crimes because the government\\n\\ncharacterized the bankruptcy fraud as a scheme to evade taxes. To support\\n\\nthis argument, Mrs. Yurek points to the indictment, contending that the\\n\\nindictment shows that both counts stemmed from the same underlying\\n\\nconduct. But the Blockburger test “focuses on the proof necessary to prove\\n\\nthe statutory elements of each offense, rather than on the actual evidence\\n\\nto be presented at trial.” Illinois v Vitale, 447 U.S. 410, 416 (1980). Given\\n\\nthe focus of this test, Mrs. Yurek’s argument fails because the nature of the\\n\\ncharges does not alter the elements that the government needed to prove.\\n\\n\\n\\n\\n 22\\n\\f To argue that she was convicted of multiplicitous charges, Mrs.\\n\\nYurek also relies on United States v. McIntosh, 124 F.3d 1330 (10th Cir.\\n\\n1997). In McIntosh we acknowledged that “Congress undoubtedly may\\n\\nsubject a defendant to multiple convictions and punishments for the same\\n\\nact,” but we held that Congress did not intend to subject the defendant to\\n\\nconvictions for both 18 U.S.C. § 152(3) (making a false statement) and 18\\n\\nU.S.C. § 152(7) (concealing assets). 124 F.3d at 1336–37.\\n\\n But Mrs. Yurek was not convicted of violating either § 152(3) or\\n\\n§ 152(7), so McIntosh does not control. And unless Congress expresses a\\n\\ncontrary intent, “we presume . . . that Congress intended multiple\\n\\nconvictions and sentences for the same criminal behavior which violates\\n\\nmore than one statute when each statute requires proof of a fact that the\\n\\nother does not.” United States v. Benoit, 713 F.3d 1, 12 (10th Cir. 2013).\\n\\n Mrs. Yurek has not pointed to any evidence that Congress expressed\\n\\nan intent to preclude a conviction for both tax evasion and bankruptcy\\n\\nfraud. Mrs. Yurek’s reliance on McIntosh is thus misguided, and we\\n\\nconclude that the charges were not multiplicitous.\\n\\nIV. The district court erroneously calculated the guideline range by\\n applying the wrong test for a mitigating-role adjustment.\\n\\n Mrs. Yurek contends that the district court\\n\\n should have applied Sentencing Guideline § 2T1.1 to her\\n conviction for bankruptcy fraud,\\n\\n incorrectly calculated the loss attributable to her, and\\n 23\\n\\f applied the wrong test for a mitigating-role adjustment.\\n\\nWe agree that the district court erred in deciding whether to grant Mrs.\\n\\nYurek a mitigating-role adjustment. But the court did not otherwise err at\\n\\nsentencing.\\n\\n A. Sentencing Guideline § 2T1.1 does not apply to Mrs.\\n Yurek’s conviction for bankruptcy fraud.\\n\\n To calculate the guideline range, the district court must select the\\n\\napplicable guideline (if one exists) for the offense of conviction. U.S.S.G.\\n\\n1B1.2(a) (2016). 16 Here the parties agree that the relevant offense of\\n\\nconviction was bankruptcy fraud under 18 U.S.C. § 157(1). For this\\n\\noffense, however, the Sentencing Commission has not expressly adopted a\\n\\nguideline. When the Sentencing Commission has not specified the\\n\\napplicable guideline, the district court must “apply the most analogous\\n\\noffense guideline.” U.S.S.G. § 2X5.1 (2016). This process involves two\\n\\nsteps. The court begins by determining which guidelines are sufficiently\\n\\nanalogous; from these guidelines, the court then selects the most analogous\\n\\n\\n\\n\\n16\\n The 2016 version was in effect at the time of Mrs. Yurek’s\\nsentencing. See U.S.S.G. § 1B1.11(a) (2016) (Ordinarily, “[t]he court shall\\nuse the Guidelines Manual in effect on the date that the defendant is\\nsentenced.”).\\n\\n\\n 24\\n\\fone. 17 Id. § 2X5.1 cmt.; United States v. Nichols, 169 F.3d 1255, 1270–71\\n\\n(10th Cir. 1999).\\n\\n The district court assumed for the sake of argument that both § 2T1.1\\n\\nand § 2B1.1 were “sufficiently analogous” to bankruptcy fraud under 18\\n\\nU.S.C. § 157(1). The district court then concluded that § 2B1.1 was the\\n\\nmore analogous guideline.\\n\\n The parties agree that § 2B1.1 is sufficiently analogous to\\n\\nbankruptcy fraud under 18 U.S.C. § 157(1). 18 But the parties disagree over\\n\\nwhether § 2T1.1 is also sufficiently analogous to bankruptcy fraud. To\\n\\ndetermine whether § 2T1.1 is “sufficiently analogous” to bankruptcy fraud,\\n\\nwe compare the elements of bankruptcy fraud under 18 U.S.C. § 157(1)\\n\\n\\n\\n\\n17\\n If there is not a sufficiently analogous guideline, 18 U.S.C. § 3553\\nwould control. U.S.S.G. § 2X5.1 cmt. (2016).\\n18\\n Section 2B1.1 covers crimes of fraud and deceit. Two of the crimes\\ncovered by § 2B1.1 are mail fraud and wire fraud. See U.S.S.G. App’x A\\n(2016) (identifying 18 U.S.C. §§ 1341 and 1343 as covered by § 2B1.1).\\nThe statutes for these crimes served as the model for § 157. See United\\nStates v. Milwitt, 475 F.3d 1150, 1155 (9th Cir. 2007). Like § 157, both\\nmail fraud and wire fraud include as elements (1) a scheme or artifice to\\ndefraud and (2) the specific intent to defraud. Compare United States v.\\nSpurlin, 664 F.3d 954, 964 (5th Cir. 2011) (listing the elements for\\nbankruptcy fraud under § 157(1)), with United States v. Welch, 327 F.3d\\n1081, 1104 (10th Cir. 2003) (listing the elements for mail fraud and wire\\nfraud).\\n\\n\\n 25\\n\\fwith the elements of the offenses covered by § 2T1.1. See United States v.\\n\\nNichols, 169 F.3d 1255, 1270 (10th Cir. 1999). 19\\n\\n Section 2T1.1 relates to matters of taxation. Thus, all of the crimes\\n\\nexpressly covered by § 2T1.1 involve taxation:\\n\\n evading taxes (26 U.S.C. § 7201),\\n\\n willfully failing to file a tax return, keep records, supply\\n information, or pay a tax (26 U.S.C. § 7203),\\n\\n making false or fraudulent statements to the IRS (26 U.S.C.\\n § 7206(1), (3), (4), and (5)),\\n\\n willfully filing a fraudulent return, statement, or other\\n document (26 U.S.C. § 7207),\\n\\n making false statements to purchasers or lessees relating to a\\n tax (26 U.S.C. § 7211), and\\n\\n attempting to interfere with the administration of the tax laws\\n (26 U.S.C. § 7212(a)).\\n\\nU.S.S.G. App’x A (2016).\\n\\n Because these crimes target taxation, they contrast starkly with\\n\\nbankruptcy fraud. Bankruptcy fraud requires specific intent to defraud, 20\\n\\nand the § 2T1.1 crimes require specific intent only with regard to the tax\\n\\nlaws. For example, tax evasion under 26 U.S.C. § 7201 requires proof that\\n\\n\\n19\\n Because the district court didn’t decide this issue, we use our\\nindependent judgment on this legal issue. Cf. Nichols, 169 F.3d at 1270\\n(stating that determination of the first step is “purely legal,” requiring de\\nnovo review).\\n20\\n United States v. Spurlin, 664 F.3d 954, 964 (5th Cir. 2011).\\n\\n 26\\n\\fa defendant had the “specific intent to evade taxes.” United States v.\\n\\nPayne, 978 F.2d 1177, 1182 (10th Cir. 1992). A violation of 26 U.S.C.\\n\\n§ 7203 occurs only if a defendant “willfully fails” to pay a tax, file a\\n\\nreturn, keep tax records, or supply tax-related information. And a\\n\\nconviction under 26 U.S.C. § 7206(4) requires the government to prove\\n\\nthat a defendant hid taxable property “with intent to evade or defeat the\\n\\nassessment or collection” of a tax. So the specific-intent element for\\n\\nbankruptcy fraud sweeps beyond the specific-intent elements found in\\n\\n§ 2T1.1 crimes.\\n\\n Nor is there a match between § 2T1.1 and bankruptcy fraud’s first\\n\\nelement (scheme to defraud). See United States v. Spurlin, 664 F.3d 954,\\n\\n964 (5th Cir. 2011). It is true that many of the crimes covered by § 2T1.1\\n\\ntarget fraudulent conduct. But § 2T1.1’s fraud crimes again relate only to\\n\\nthe tax laws:\\n\\n 1. making false or fraudulent statements to the IRS (26 U.S.C.\\n § 7206(1)),\\n\\n 2. making false statements regarding a tax to purchasers or lessees\\n (26 U.S.C. § 7211),\\n\\n 3. filing false or fraudulent documents with the IRS (26 U.S.C.\\n § 7207),\\n\\n 4. concealing taxable property from the IRS (26 U.S.C.\\n §§ 7206(4) and 7206(5)), and\\n\\n 5. falsely or fraudulently executing or signing documents required\\n by the provisions of the Internal Revenue Code or regulations\\n issued under those provisions (26 U.S.C. § 7206(3)).\\n\\n 27\\n\\fSee p. 26, above. Unlike these crimes, bankruptcy fraud targets a scheme to\\n\\ndefraud unrelated to taxation or the administration of the federal tax laws.\\n\\nSo the fraudulent conducted covered by bankruptcy fraud sweeps beyond\\n\\nthe fraudulent conduct covered by § 2T1.1.\\n\\n Because the elements of § 2T1.1 crimes are narrower than and largely\\n\\nunrelated to the elements of bankruptcy fraud, we conclude that § 2T1.1 is\\n\\nnot sufficiently analogous to bankruptcy fraud. Thus the only potentially\\n\\napplicable guideline was § 2B1.1, and the district court did not err by\\n\\napplying this section.\\n\\n B. The amount of intended loss attributable to Mrs. Yurek\\n could reasonably be based on the amount of debt that Mrs.\\n Yurek had tried to discharge in bankruptcy.\\n\\n At Mrs. Yurek’s sentencing, the district court applied Sentencing\\n\\nGuideline § 2B1.1 to determine Mrs. Yurek’s base-offense level and\\n\\nspecific offense characteristics. For the specific offense characteristics,\\n\\n§ 2B1.1 allowed the court to increase the base-offense level based on the\\n\\n\\n\\n\\n 28\\n\\famount of the intended loss attributable to a defendant. 21 See U.S.S.G.\\n\\n§ 2B1.1(b)(1) (2016).\\n\\n To calculate the intended loss, the district court considered two\\n\\nmethodologies:\\n\\n 1. the amount of federal tax debt that Mrs. Yurek tried to\\n discharge in bankruptcy and\\n\\n 2. the value of the assets that Mrs. Yurek concealed from the\\n bankruptcy court.\\n\\nThe court found that under either approach, the intended loss was between\\n\\n$550,000 and $1,500,000. Given this finding, the court overruled Mrs.\\n\\nYurek’s objection to the U.S. Probation Department’s recommendation of a\\n\\n14-level enhancement.\\n\\n On appeal, Mrs. Yurek argues that the loss attributable to her was\\n\\nless than $550,000 and that the district court erred in two ways when\\n\\ncalculating the intended loss:\\n\\n 1. The amount sought to be discharged in bankruptcy did not\\n constitute an appropriate methodology.\\n\\n 2. The district court miscalculated the value of the assets that had\\n been concealed from the bankruptcy court.\\n\\n We reject Mrs. Yurek’s challenge to the district court’s methodology\\n\\nfor calculating the intended loss. Determining this methodology involves a\\n\\n\\n21\\n Under § 2B1.1, “loss is the greater of actual loss or intended loss.”\\nU.S.S.G. § 2B1.1 cmt. n.3(A) (2016). The parties agree that the applicable\\nmeasure of loss is intended loss because there was no actual loss.\\n\\n 29\\n\\flegal conclusion, so we engage in de novo review. See United States v.\\n\\nGordon, 710 F.3d 1124, 1160–61 (10th Cir. 2013) (stating that we engage\\n\\nin de novo review of the district court’s methodology for calculating loss\\n\\nunder § 2B1.1(b)). Engaging in de novo review, we start with the\\n\\napplicable guideline and related application notes. The application notes\\n\\nfor § 2B1.1 define “intended loss” as a loss that a defendant “purposely\\n\\nsought to inflict.” U.S.S.G. § 2B1.1 cmt. n.3(A)(ii)(I) (2016); see United\\n\\nStates v. Manatau, 647 F.3d 1048, 1050 (10th Cir. 2011) (Gorsuch, J.)\\n\\n(“Something is intended if it is done on purpose—not merely known,\\n\\nforeseen, or just possible or potentially contemplated.”). 22 We must follow\\n\\nthis definition of intended loss because it is not plainly erroneous,\\n\\ninconsistent with § 2B1.1, or violative of the U.S. Constitution or a federal\\n\\nstatute. United States v. Mojica, 214 F.3d 1169, 1171 (10th Cir. 2000).\\n\\n Applying this definition, we conclude that the intended loss equals\\n\\nthe monetary harm that Mrs. Yurek wanted to cause her creditors. See\\n\\nUnited States v. Holthaus, 486 F.3d 451, 455 (8th Cir. 2007) (“When\\n\\ndetermining intended loss [in the bankruptcy context], we look to the\\n\\n\\n\\n\\n22\\n In Manatau, we interpreted the phrase “intended loss” in a prior\\nversion of § 2B1.1 to mean “a loss the defendant purposely sought to\\ninflict.” Manatau, 647 F.3d at 1050 (emphasis in original). The Sentencing\\nCommission later amended § 2B1.1 to reflect this holding. See U.S.S.G.\\namend. 792 (eff. Nov. 1, 2015), available at U.S.S.G. supp. to app. C 108–\\n12 (2016 ) .\\n\\n 30\\n\\famount of loss a defendant actually intended to cause his creditors.”);\\n\\nUnited States v. Bussell, 504 F.3d 956, 962 (9th Cir. 2007) (“When\\n\\ndetermining intended loss [in the bankruptcy context], we must look to the\\n\\namount of loss that [the defendant] intended to cause her creditors.”).\\n\\n These creditors included the IRS, so the intended loss includes the\\n\\namount of federal tax debt that Mrs. Yurek tried to discharge in\\n\\nbankruptcy. That discharge would have extinguished Mrs. Yurek’s federal\\n\\ntax debt, causing a loss to the IRS. See United States v. Mutuc, 349 F.3d\\n\\n930, 937 (7th Cir. 2003) (“A successful discharge in bankruptcy would\\n\\nhave left the creditors without recourse against Mutuc; it follows that\\n\\nMutuc intended a loss equal to the amount to be discharged in\\n\\nbankruptcy.”).\\n\\n In similar circumstances, other circuits have ordinarily allowed\\n\\ncalculation of the intended loss based on the amount of debt that the\\n\\ndefendant was trying to discharge, though the circuits have taken somewhat\\n\\ndifferent approaches. For example, the Seventh Circuit has flatly stated\\n\\nthat it allows measurement of the intended loss based on the amount that\\n\\nthe defendant sought to discharge in bankruptcy. See United States v.\\n\\nArthur, 582 F.3d 713, 720–21 (7th Cir. 2009); United States v. Mutuc, 349\\n\\nF.3d 930, 936–37 (7th Cir. 2003); United States v. Holland, 160 F.3d 377,\\n\\n381 (7th Cir. 1998). On the other hand, the Ninth Circuit allows the district\\n\\ncourt to consider the economic realities in each case and use discretion in\\n\\n 31\\n\\fdetermining whether to calculate the intended loss based on the entire\\n\\namount to be discharged or the value of concealed assets. See United States\\n\\nv. Bussell, 504 F.3d 956, 961–62 (9th Cir. 2007). And the Eighth Circuit\\n\\nhas suggested that the intended loss can equal the entire amount that the\\n\\ndefendants are trying to discharge only if the fraud had created the illusion\\n\\nof dischargeability. See United States v. Holthaus, 486 F.3d 451, 455 (8th\\n\\nCir. 2007).\\n\\n All of these approaches support the district court’s decision to\\n\\ncalculate the intended loss attributable to Mrs. Yurek based on the amount\\n\\nof tax debt ($1.2 million) that Mrs. Yurek was trying to discharge in\\n\\nbankruptcy. So regardless of whether we consider the economic realities or\\n\\nthe illusion of dischargeability, the district court did not err in calculating\\n\\nthe intended loss based on the amount that Mrs. Yurek had tried to\\n\\ndischarge in bankruptcy.\\n\\n Of course, Mrs. Yurek couldn’t succeed in causing this loss because\\n\\nonce she committed tax evasion, the entire tax debt became\\n\\nnondischargeable. See 18 U.S.C. § 523(a)(1)(C). But a loss can be intended\\n\\neven when it is improbable or impossible. U.S.S.G. § 2B1.1 cmt. n.3(A)(ii)\\n\\n(2016). 23\\n\\n\\n23\\n We have stated that a loss is intended only if (1) “the defendant\\nrealistically intended a particular loss” or (2) such a loss was probable.\\nUnited States v. Swanson, 360 F.3d 1155, 1168 (10th Cir. 2004); United\\n\\n 32\\n\\f Mrs. Yurek disagrees, relying on United States v. Holthaus, 486 F.3d\\n\\n451 (8th Cir. 2002). There, however, the Eighth Circuit expressly\\n\\ndisavowed a blanket prohibition against calculation of intended loss based\\n\\non the amount that the defendant had tried to discharge in bankruptcy.\\n\\nHolthaus, 486 F.3d at 455; see p. 32, above. Given the pinpoint citation in\\n\\nMrs. Yurek’s opening appeal brief, Mrs. Yurek is apparently intending to\\n\\nrely on the Holthaus panel’s discussion of a prior opinion, United States v.\\n\\nWheeldon, 313 F.3d 1070 (8th Cir. 2002). There the Eighth Circuit\\n\\naddressed the proper method for calculating intended loss when the amount\\n\\nof the attempted discharge exceeds the value of the concealed assets.\\n\\nWheeldon, 313 F.3d at 1072. Applying the 2000 version of the U.S.\\n\\nSentencing Guidelines, the Eighth Circuit concluded that this situation\\n\\nrequired the district court to calculate the intended loss based on the value\\n\\nof the concealed assets. Id.\\n\\n In reaching this conclusion, the Eighth Circuit didn’t apply the term\\n\\n“intended loss;” the court instead applied the term “probable intended\\n\\n\\n\\n\\nStates v. Schild, 269 F.3d 1198, 1200 (10th Cir. 2001). We later\\ncharacterized the reference to “probable” loss as “dicta” based on\\n“questionable authority.” United States v. Baum, 555 F.3d 1129, 1134\\n(10th Cir. 2009). That “questionable authority” was United States v. Smith,\\n951 F.2d 1164 (10th Cir. 1991), which had relied on guideline language\\nthat was later deleted. See Baum, 555 F.3d at 1134–35 (discussing the\\norigin of the language in Swanson and Schild and later changes to the\\nsentencing guidelines) .\\n\\n 33\\n\\floss.” Id. But the Sentencing Commission amended the applicable\\n\\ndefinition of “intended loss” in 2001, providing that a loss can be intended\\n\\neven when it is unlikely or impossible. U.S.S.G. amend. 617 (eff. Nov. 1,\\n\\n2001), available at U.S.S.G. app. C vol. II at 117 (2016) (“The amendment\\n\\nresolves the conflict to provide that intended loss includes unlikely or\\n\\nimpossible losses that are intended, because their inclusion better reflects\\n\\nthe culpability of the offender.”); see p. 32 & note 23, above. Given the\\n\\nchange in definition, the nondischargeability of Mrs. Yurek’s tax debt does\\n\\nnot affect the available methods to calculate intended loss.\\n\\n Mrs. Yurek listed a tax debt of $1.2 million in her bankruptcy\\n\\npetition, requesting that it be discharged. And her husband, who also\\n\\nsigned the bankruptcy petition, stated in bankruptcy court that he and his\\n\\nwife had filed the bankruptcy petition in order to discharge their $1.2\\n\\nmillion tax debt. Given this evidence, the court could calculate the\\n\\nintended loss attributable to Mrs. Yurek based on the amount of tax debt\\n\\nthat she had tried to discharge.\\n\\n * * *\\n\\n We conclude that the district court appropriately calculated the\\n\\nintended loss attributable to Mrs. Yurek based on the amount of tax debt\\n\\nthat she had tried to discharge in bankruptcy. Thus, the district court did\\n\\nnot err in applying the 14-level sentencing enhancement.\\n\\n\\n\\n 34\\n\\f C. The district court plainly erred by applying the wrong test\\n for a mitigating-role adjustment.\\n\\n Mrs. Yurek also argues that the district court applied the wrong test\\n\\nwhen deciding not to grant a downward adjustment for a mitigating role.\\n\\nWe agree.\\n\\n 1. Preservation and the Argument for Plain Error\\n\\n The government contends that Mrs. Yurek did not preserve the issue\\n\\nfor appeal. We agree.\\n\\n To preserve an appellate issue involving the district court’s\\n\\nexplanation for a sentence, the defendant must lodge a “contemporaneous\\n\\nobjection.” United States v. Romero, 491 F.3d 1173, 1177 (10th Cir. 2007);\\n\\nsee United States v. Lopez-Flores, 444 F.3d 1218, 1221 (10th Cir. 2006)\\n\\n(“[T]he usual reasons for requiring a contemporaneous objection apply to\\n\\nchallenges to the district court’s method of arriving at a sentence.”). At\\n\\nsentencing, the district court explained that it would deny Mrs. Yurek a\\n\\nmitigating-role adjustment because her participation in tax evasion and\\n\\nbankruptcy fraud had been “central and necessary for both . . . crimes to\\n\\ntake place.” R., vol. 5, at 1925; see also id. at 1925–26 (finding “ample\\n\\ngrounds to conclude that Ms. Yurek’s participation in these criminal\\n\\nschemes was central and necessary and that her husband could not have\\n\\nproceeded with either the tax evasion or the bankruptcy fraud without\\n\\nher”).\\n\\n\\n 35\\n\\f Mrs. Yurek argues that the district court applied the wrong test. She\\n\\nbases her argument on the district court’s explanation for denying a\\n\\nmitigating-role adjustment, but she did not raise this issue in district court.\\n\\nAccording to Mrs. Yurek, she preserved the issue by objecting to the\\n\\npresentence report. But she is alleging an error in the district court’s\\n\\nexplanation, not in the content of the presentence report. So objecting to\\n\\nthe presentence report would not have alerted the district court to an error\\n\\nin its explanation. See United States v. Mendoza, 543 F.3d 1186, 1195\\n\\n(10th Cir. 2008); 24 see also United States v. Chavez-Morales, 894 F.3d\\n\\n1206, 1213 (10th Cir. 2018) (concluding that a defendant’s sentencing\\n\\nmemorandum did not preserve an issue involving the adequacy of the\\n\\ndistrict court’s explanation). Because Mrs. Yurek did not preserve her\\n\\nargument involving correctness of the legal standard for a mitigating-role\\n\\n\\n\\n\\n24\\n In Mendoza, the government appealed the sentence, arguing that the\\ndistrict court failed to provide written reasons for its downward variance.\\n543 F.3d at 1186. We concluded that the government had forfeited this\\nappeal point by failing to alert the district court to its failure to provide\\nwritten reasons. Id. at 1195. An objection to the presentence report didn’t\\nsuffice for preservation: “Unlike other forms of sentencing error, which\\ncan be preserved for appellate review through written objections to the\\n[presentence report] or an oral objection during the sentencing hearing,\\nfailure to enter a written statement of reasons becomes apparent to the\\nparties only after the court enters its final judgment regarding the sentence\\nimposed.” Id.\\n\\n\\n 36\\n\\fadjustment, any review would be confined to the plain-error standard.\\n\\nRomero, 491 F.3d at 1178. 25\\n\\n But the government argues that Mrs. Yurek lost her opportunity to\\n\\nurge plain error by waiting until her reply brief to do so. We disagree. Mrs.\\n\\nYurek appeared to assume in her opening brief that she had preserved her\\n\\nchallenge to the denial of a mitigating-role adjustment. After the\\n\\ngovernment challenged preservation, Mrs. Yurek argued in her reply brief\\n\\nthat the error would be considered plain even if she had forfeited the issue.\\n\\nThis approach was a permissible way to invoke plain-error review. See\\n\\nUnited States v. Zander, 794 F.3d 1220, 1232 n.5 (10th Cir. 2015) (“We\\n\\nhold that Defendant adequately addressed the issue of plain error review in\\n\\nhis reply to the government’s brief, after arguing in his opening brief that\\n\\nhis objections below were sufficiently raised to be preserved for review on\\n\\nappeal.”). We thus apply the standard for plain error.\\n\\n 2. Mrs. Yurek is entitled to relief under the plain-error\\n standard.\\n\\n For Mrs. Yurek to prevail under the plain-error test, she must show\\n\\n 1. that an error took place,\\n\\n\\n\\n\\n25\\n Mrs. Yurek contends that the government induced the error by\\narguing that she had played a central and necessary role in the crimes. But\\nthe government never suggested to the district court that it apply the wrong\\nlegal test. The government simply argued against a mitigating-role\\nadjustment. Presentation of this argument did not induce the court’s error.\\n\\n 37\\n\\f 2. that the error was plain,\\n\\n 3. that it affected her substantive rights, and\\n\\n 4. that the error “seriously affects the fairness, integrity, or public\\n reputation of judicial proceedings.”\\n\\nUnited States v. Bustamante-Conchas, 850 F.3d 1130, 1137 (10th Cir.\\n\\n2017) (en banc). Mrs. Yurek has satisfied each of these prongs.\\n\\n a. The government properly conceded the first and second\\n prongs.\\n\\n The government concedes the first two prongs of the plain-error test.\\n\\nWe agree that the first two prongs are satisfied.\\n\\n A defendant who was a minimal or minor participant in criminal\\n\\nactivity is eligible for a downward adjustment. See U.S.S.G. § 3B1.2\\n\\n(2016). Finding that a defendant performed an “essential or indispensable\\n\\nrole . . . is not determinative” of eligibility for this adjustment. Id. § 3B1.2\\n\\ncmt. n.3(C). The court instead must focus on whether the defendant “is\\n\\nsubstantially less culpable than the average participant in the criminal\\n\\nactivity.” Id.; see United States v. Salazar-Samaniega, 361 F.3d 1271,\\n\\n1277 (10th Cir. 2004) (noting that a § 3B1.2 reduction is available only for\\n\\n“a defendant who plays a part in committing the offense that makes him\\n\\nsubstantially less culpable than the average participant”); United States v.\\n\\nAyers, 84 F.3d 382, 383 (10th Cir. 1996) (“Section 3B1.2 vests the district\\n\\ncourt with discretion to grant a base-offense level reduction if it finds a\\n\\n\\n\\n 38\\n\\fdefendant is less culpable relative to other participants in a given offense.”\\n\\n(internal quotation marks omitted)).\\n\\n But the district court did not consider Mrs. Yurek’s culpability\\n\\nrelative to other participants in the scheme. 26 The court instead found that\\n\\nMrs. Yurek’s role had been essential to the crimes and treated that finding\\n\\nas determinative. By failing to consider Mrs. Yurek’s relative culpability,\\n\\nthe district court applied the wrong test when denying a mitigating-role\\n\\nadjustment. As the government admits, the district court’s application of\\n\\nthe wrong test constitutes an error that was plain. Mrs. Yurek has thus\\n\\nsatisfied both the first and second prongs of the plain-error standard.\\n\\n\\n\\n\\n26\\n In the criminal scheme, only two persons were named: Mrs. Yurek\\nand her husband. But the husband was not an “average participant” because\\nhe had obtained a two-level enhancement for a leadership role in the\\ncrimes. So in this scheme, it is impossible to compare Mrs. Yurek’s\\nculpability to another “average” participant.\\n\\n Given the absence of another “average” participant in this scheme,\\nthe sentencing court must focus on (1) the degree of Mrs. Yurek’s\\nculpability relative to her husband’s and (2) the scope of the criminal\\nscheme. See United States v. Lopez, 545 F.3d 515, 517 (7th Cir. 2008)\\n(“[I]n situations where criminal activity involves only two participants\\n(and thus it is impossible to ascertain the culpability of an ‘average’\\nparticipant), the key inquiry is the degree of the defendant’s culpability\\nrelative to the other participant’s and the scope of the criminal\\nenterprise.”). With this dual focus, the court should determine whether\\nMrs. Yurek bore substantially less culpability than her husband. See id.;\\nsee also United States v. Tholl, 895 F.2d 178, 1185–86 (7th Cir. 1990)\\n(concluding that under § 3B1.2, it was not enough for the defendant to\\nprove less culpability than the sole other participant, who had been the\\n“mastermind” behind the criminal scheme).\\n 39\\n\\f b. Mrs. Yurek has satisfied the third prong of the plain-error\\n test.\\n\\n Mrs. Yurek has also satisfied the third prong of the plain-error test.\\n\\nUnder this prong, Mrs. Yurek bears the burden to show prejudice. United\\n\\nStates v. Gonzales-Huerta, 403 F.3d 727, 732–33 (10th Cir. 2005). To\\n\\nsatisfy this burden, Mrs. Yurek must show a reasonable probability\\n\\nsufficient to undermine confidence in the outcome at her sentencing.\\n\\nUnited States v Bustamante-Conchas, 850 F.3d 1130, 1138 (10th Cir. 2017)\\n\\n(en banc). Confidence in the outcome can be undermined even if Mrs.\\n\\nYurek’s showing would not satisfy the preponderance-of-the-evidence\\n\\nstandard. United States v. Dominguez Benitez, 542 U.S. 74, 83 n.9 (2004).\\n\\n Mrs. Yurek has shown prejudice from the district court’s application\\n\\nof the wrong test. The crux of § 3B1.2 is a defendant’s relative culpability.\\n\\nSee pp. 38–39, above. After denying a mitigating-role adjustment to Mrs.\\n\\nYurek, the court considered her relative culpability and downplayed her\\n\\nrole in the scheme:\\n\\n It is true that the trial evidence established that the\\n defendants used accountants and attorneys as tools to accomplish\\n the bankruptcy fraud and tax evasion schemes for which they\\n were convicted, but in the mitigation for this defendant, these\\n accountants and attorneys unambiguously testified at trial that it\\n was always Mr. Yurek, as opposed to his wife, who took the lead\\n in communicating and strategizing with them in the perpetuation\\n of these schemes.\\n\\n While it does not absolve her from her culpability for her\\n crimes, in my judgment fairness requires me to temper the\\n sentence I will impose on Ms. Yurek to reflect her passive and,\\n\\n 40\\n\\f to some degree, submissive personality when compared to her\\n husband, at least insofar as matters such as the complex criminal\\n schemes in this case are concerned.\\n\\nR., vol. 5, at 1969–70 (emphasis added). Given Mrs. Yurek’s lesser role in\\n\\nthe scheme, the district court varied downward to 27 months from the\\n\\nguideline range of 41–51 months.\\n\\n The district court justified the downward variance based in part on\\n\\nits view that Mrs. Yurek bore less culpability than her husband. If a\\n\\ndistrict court finds that a defendant is less culpable relative to other\\n\\nparticipants in a crime and varies downward from the advisory guideline\\n\\nrange based partly on that determination, a reasonable probability exists\\n\\nthat the district court would have granted a mitigating-role adjustment\\n\\nunder the correct test. See United States v. Trujillo-Terrazas, 405 F.3d\\n\\n814, 820 (10th Cir. 2005) (considering a district court’s comments at\\n\\nsentencing when determining whether the plain error prejudiced the\\n\\ndefendant); see also United States v. Sierra-Castillo, 405 F.3d 932, 942\\n\\n(10th Cir. 2005) (noting that a district court’s comments at sentencing can\\n\\nhelp a defendant satisfy the third prong of the plain-error test).\\n\\n And if the district court had granted Mrs. Yurek a mitigating-role\\n\\nadjustment, the district court’s starting point (the guideline range) would\\n\\nhave been lower. “When the court’s starting point is skewed a ‘reasonable\\n\\nprobability’ exists that its final sentence is skewed too.” United States v.\\n\\n\\n\\n 41\\n\\fSabillon-Umana, 772 F.3d 1328, 1333 (10th Cir. 2014) (Gorsuch, J.). Mrs.\\n\\nYurek has thus satisfied the third prong of the plain-error test.\\n\\n c. The fourth prong was also satisfied.\\n\\n To satisfy the fourth prong, Mrs. Yurek must show that the district\\n\\ncourt’s error “seriously affects the fairness, integrity, or public reputation\\n\\nof judicial proceedings.” United States v. Bustamante-Conchas, 850 F.3d\\n\\n1130, 1137 (10th Cir. 2017) (en banc). We conclude that Mrs. Yurek has\\n\\nmet this burden.\\n\\n When an error affects the calculation of a defendant’s guideline\\n\\nrange, the fourth prong is ordinarily satisfied when the first three prongs\\n\\nare satisfied. Rosales-Mireles v. United States, 138 S. Ct. 1897, 1908\\n\\n(2018). After all, “what reasonable citizen wouldn’t bear a rightly\\n\\ndiminished view of the judicial process and its integrity if courts refused to\\n\\ncorrect obvious errors of their own devise that threaten to require\\n\\nindividuals to linger longer in federal prison than the law demands?” Id.\\n\\n(quoting United States v. Sabillon-Umana, 772 F.3d 1328, 1333–34 (10th\\n\\nCir. 2014) (Gorsuch, J.)).\\n\\n * * *\\n\\n We conclude that the district court plainly erred by applying the\\n\\nwrong test for a mitigating-role adjustment.\\n\\n\\n\\n\\n 42\\n\\fV. Conclusion\\n\\n We affirm Ms. Yurek’s conviction, but we vacate her sentence and\\n\\nremand for resentencing. At resentencing, the district court must\\n\\nreconsider the possibility of a mitigating-role adjustment.\\n\\n\\n\\n\\n 43\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4398840/\", \"author_raw\": \"BACHARACH, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"BACHARACH"},"judge2":{"kind":"string","value":"BALDOCK"},"judge3":{"kind":"string","value":"EBEL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4621587/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Wendy Marie YUREK, Defendant-Appellant.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-21\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 21, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\nUNITED STATES OF AMERICA,\n\n Plaintiff-Appellee,\n\nv. No. 18-1134\n\nWENDY MARIE YUREK,\n\n Defendant-Appellant.\n _________________________________\n\n Appeal from the United States District Court\n for the District of Colorado\n (D.C. No. 1:15-CR-00394-WJM-2)\n _________________________________\n\nRobert S. Jackson, Oklahoma City, Oklahoma, for Defendant-Appellant.\n\nPegeen D. Rhyne, Assistant United States Attorney (Jason R. Dunn, United\nStates Attorney, with her on the brief), Denver, Colorado, for Plaintiff-\nAppellee.\n _________________________________\n\nBefore BACHARACH, BALDOCK, and EBEL, Circuit Judges.\n _________________________________\n\nBACHARACH, Circuit Judge.\n _________________________________\n\f Mrs. Wendy Yurek and her husband, Mr. Daryl Yurek, were charged\n\nwith tax evasion and bankruptcy fraud. 1 After a joint jury trial, Mrs. Yurek\n\nand her husband were convicted on both offenses. The district court then\n\nsentenced Mrs. Yurek to a prison term of 27 months, leading her to appeal\n\nthe conviction and sentence.\n\n We affirm in part and reverse in part. We affirm Mrs. Yurek’s\n\nconviction, but we vacate the sentence because the district court applied\n\nthe wrong test when deciding whether to grant a mitigating-role\n\nadjustment.\n\nI. We reject Mrs. Yurek’s challenges to the sufficiency of the\n evidence on her conviction for tax evasion and bankruptcy fraud.\n\n We conclude that the evidence of Mrs. Yurek’s guilt was sufficient to\n\nsupport her conviction for tax evasion and bankruptcy fraud.\n\n A. We engage in de novo review over the sufficiency of the\n evidence.\n\n In considering the sufficiency of the evidence, we engage in de novo\n\nreview. United States v. Ramos-Arenas, 596 F.3d 783, 786 (10th Cir.\n\n2010). We will reverse only if no rational factfinder could have found that\n\nthe government had proven all of the elements of an offense beyond a\n\n\n\n\n1\n Mr. Yurek was also charged with making a false statement under oath\nin a bankruptcy proceeding and willfully making false statements to the\nIRS under penalty of perjury.\n\n 2\n\freasonable doubt. United States v. Brown, 400 F.3d 1242, 1247 (10th Cir.\n\n2005).\n\n Under de novo review, we view the trial evidence in the light most\n\nfavorable to the government. United States v. Boisseau, 841 F.3d 1122,\n\n1125 (10th Cir. 2016). We do not reevaluate witness credibility or reweigh\n\nthe evidence. United States v. Smith, 133 F.3d 737, 742 (10th Cir. 1997).\n\n B. The evidence was sufficient to convict on tax evasion.\n\n Mrs. Yurek was convicted of tax evasion, which consists of\n\n“willfully attempt[ing] in any manner to evade or defeat any tax imposed\n\nby [the Internal Revenue Code] or the payment thereof.” 26 U.S.C. § 7201.\n\nTo obtain a conviction on this offense, the government had to prove three\n\nelements:\n\n 1. Mrs. Yurek owed a substantial tax to the IRS.\n\n 2. Mrs. Yurek committed “an affirmative act constituting an\n evasion or attempted evasion” of assessment or payment of the\n tax.\n\n 3. Mrs. Yurek willfully evaded or attempted to evade the\n assessment or payment of the tax. 2\n\nUnited States v. Boisseau, 841 F.3d 1122, 1125 (10th Cir. 2016) (citing\n\nSansone v. United States, 380 U.S. 343, 351 (1965)); see United States v.\n\n\n2\n Mrs. Yurek argues that the government did not establish that she and\nher husband had the ability to pay their IRS tax debt. But the ability to pay\none’s taxes is not an element of tax evasion. See Boisseau, 841 F.3d at\n1125.\n\n 3\n\fThompson, 518 F.3d 832, 850 (10th Cir. 2008) (noting that the tax liability\n\nmust be “substantial”).\n\n Mrs. Yurek challenges the sufficiency of the evidence on the second\n\nand third elements (an affirmative act and willfulness).\n\n 1. The evidence was sufficient to find an affirmative act.\n\n To establish an affirmative act, the government had to prove an act\n\ndesigned to “mislead or conceal” within the six-year period of limitations.\n\nUnited States v. Thompson, 518 F.3d 832, 852 (10th Cir. 2008); see United\n\nStates v. Anderson, 319 F.3d 1218, 1219 (10th Cir. 2003) (holding that\n\nwhen a defendant commits a series of affirmative acts over multiple years,\n\nthe six-year period of limitations for tax evasion begins with the last\n\naffirmative act). The government bore the burden to prove that Mrs. Yurek\n\nhad committed at least one affirmative act. United States v. Hoskins, 654\n\nF.3d 1086, 1091 (10th Cir. 2011). The jury could have reasonably found\n\nthat the government had satisfied this burden.\n\n a. “Affirmative acts” are broadly defined.\n\n We first consider what constitutes an affirmative act. Federal law\n\nsuggests an expansive definition, stating that tax evasion can be committed\n\nby evading taxes “in any manner.” 26 U.S.C. § 7201; see Boisseau, 841\n\nF.3d at 1125 (“[T]he type of affirmative conduct that can constitute an\n\naffirmative act of evasion is broad.”). Affirmative acts thus include\n\n concealing assets,\n 4\n\f covering up sources of income, and\n\n engaging in misleading or concealing conduct.\n\nBoisseau, 841 F.3d at 1125. Affirmative acts may even consist of otherwise\n\nlawful conduct if the acts are committed with an intent to evade taxes. Id.;\n\nUnited States v. Gorrell, No. 18-5041, 2019 WL 1890971 at *5 (10th Cir.\n\nApr. 29, 2019).\n\n b. The evidence sufficed for a finding that Mrs. Yurek had\n committed an affirmative act.\n\n Viewed in the light most favorable to the government, the trial\n\nevidence allowed a reasonable jury to find affirmative acts involving (1)\n\npayment of personal expenses from business accounts and (2) submission\n\nof false tax documents to the IRS.\n\n i. The jury could have reasonably found that Mrs. Yurek had\n committed affirmative acts by paying her and her husband’s\n personal expenses out of business accounts.\n\n Mrs. Yurek had authority to write checks on behalf of Bolder Venture\n\nPartners and Veracity Credit Consultants, LLC, and she used that authority\n\nto write business checks for her and her husband’s personal expenses. A\n\nfact-finder could have reasonably viewed the writing of these checks as\n\naffirmative acts to evade taxes.\n\n Some of these checks came from Bolder Venture Partners, where\n\nMrs. Yurek was a partner. For example, Mrs. Yurek signed a $2,309.68\n\n\n\n 5\n\fcheck from Bolder 3 to pay condominium-association dues for the loft where\n\nshe and her husband lived.\n\n Mrs. Yurek contends that her son, Mr. Justin Yurek, owned the loft.\n\nBut the trial evidence was sufficient to support findings that (1) Justin had\n\nbeen a “straw purchaser” and (2) Mrs. Yurek and her husband were the true\n\nowners of the loft. See United States v. Reese, 745 F.3d 1075, 1078 (10th\n\nCir. 2014) (explaining a straw purchase).\n\n Mrs. Yurek and her husband had been leasing the loft and living in it.\n\nThey had a contract to purchase the loft, but a tax lien prevented them\n\nfrom obtaining a mortgage. So they assigned the contract to Justin, who\n\npurchased the loft. Though Justin was the purchaser, Mrs. Yurek’s husband\n\nnegotiated the sale and used companies (over which he wielded significant\n\ncontrol) to fund more than $112,000 of the down payment.\n\n After Justin purchased the loft, Mrs. Yurek signed an affidavit on\n\nJustin’s behalf, stating under oath that (1) the loft would serve as Justin’s\n\nprimary residence and (2) Justin had no intent to lease the loft or to make\n\nthe purchase as an investment. 4 But Justin never lived in the loft, and Mrs.\n\n\n\n\n3\n Mrs. Yurek wrote the check for $2,309.68 within the six-year\nlimitations period.\n4\n Despite the affidavit, Justin testified that he had bought the loft as an\ninvestment.\n\n 6\n\fYurek and her husband continued to live there while making only\n\ninfrequent rental payments.\n\n Mrs. Yurek not only used her role at Bolder to pay condominium-\n\nassociation dues but also used her check-writing authority at Veracity\n\nCredit Consultants, LLC to pay her husband’s country-club dues and\n\nexpenses. For example, she signed a Veracity check for $3,403.43 to pay\n\nthese expenses. 5\n\n Veracity also paid other expenses for Mrs. Yurek and her husband.\n\nFor example, Veracity paid the rent on two homes that Mrs. Yurek and her\n\nhusband used. Veracity’s former chief financial officer, Mr. Michael\n\nHennigan, testified that he knew of no business purpose for these rentals or\n\nthe country-club dues and expenses.\n\n Veracity also made mortgage payments on the loft where Mrs. Yurek\n\nand her husband lived. The jury could reasonably infer that the Yureks\n\nwere trying to hide the source of these mortgage payments. For example,\n\nthey recorded the mortgage payments under an account designated as a\n\nloan account for Mrs. Yurek’s husband, but Veracity did little to collect on\n\nthe purported loan.\n\n Bolder and Veracity paid these various personal expenses for Mrs.\n\nYurek and her husband while they\n\n owed substantial taxes and penalties to the IRS and\n\n5\n This check was signed within the six-year period of limitations.\n 7\n\f tried to settle with the IRS based on their inability to pay what\n they owed.\n\nThese payments continued through the bankruptcy proceedings, where Mrs.\n\nYurek and her husband tried to discharge their federal tax debt. But Mrs.\n\nYurek and her husband did not tell the IRS about these payments.\n\n Given this combination of evidence, the jury could have reasonably\n\nfound that Mrs. Yurek had committed an affirmative act to evade the\n\npayment of taxes. See United States v. Farr, 701 F.3d 1274, 1285–86 (10th\n\nCir. 2012) (concluding that the defendant’s use of a corporate account to\n\npay for personal living expenses supported a factual finding that the\n\ndefendant had “willfully evaded [a tax penalty] and [had taken] affirmative\n\nsteps to do so”).\n\n ii. A reasonable jury could also have found that Mrs. Yurek\n had committed affirmative acts by submitting false tax\n documents to the IRS.\n\n Along with her husband, Mrs. Yurek submitted tax forms to the IRS\n\nin 2009 and 2010. On these forms, Mrs. Yurek and her husband reported\n\nthat their gross monthly income was $7,667. But this amount didn’t include\n\nBolder and Veracity’s payments for personal expenses. The jury could\n\nreasonably have viewed these omissions as misleading or even false.\n\n\n\n\n 8\n\f Mrs. Yurek’s submission of misleading or false tax documents to the\n\nIRS could constitute affirmative acts. 6 See Sansone v. United States, 380\n\nU.S. 343, 351–52 (1965) (“[I]t is undisputed that petitioner filed a tax\n\nreturn and that the petitioner’s filing of a false tax return constituted a\n\nsufficient affirmative commission to satisfy that requirement of § 7201.”);\n\nUnited States v. Hoskins, 654 F.3d 1086, 1091 (10th Cir. 2011)\n\n(concluding that submission of a false tax return “was sufficient to\n\nestablish an affirmative act under § 7201”).\n\n 2. The evidence was sufficient to find that Mrs. Yurek had\n acted willfully.\n\n To satisfy the willfulness requirement, the government had to prove a\n\nspecific intent to evade taxes. United States v. Payne, 978 F.2d 1177, 1182\n\n(10th Cir. 1992); see Hoskins, 654 F.3d at 1090 (“Under § 7201,\n\n‘willfulness’ means the ‘voluntary, intentional violation of a known legal\n\nduty.’” (quoting Cheek v. United States, 498 U.S. 192, 201 (1991))).\n\n The government can ordinarily establish the willfulness requirement\n\nthrough “circumstantial evidence or inferences arising from a defendant’s\n\nconduct.” United States v. Boisseau, 841 F.3d 1122, 1127 (10th Cir. 2016).\n\nThe willfulness requirement is “closely connected” to the affirmative-act\n\n\n\n\n6\n The government also argues that Mrs. Yurek’s filing of the\nbankruptcy petition constituted an affirmative act. We need not address\nthis argument.\n\n 9\n\frequirement, for “‘[e]vidence of affirmative acts may be used to show\n\nwillfulness.’” Id. (quoting United States v. Romano, 938 F.2d 1569, 1572\n\n(2d Cir. 1991)) (alteration in original).\n\n Viewed in the light most favorable to the government, the trial\n\nevidence was sufficient in five ways to prove Mrs. Yurek’s specific intent\n\nto evade taxes.\n\n First, a reasonable jury could have found that Mrs. Yurek had known\n\nof her legal obligation to pay her federal tax debt. With this finding, the\n\njury could reasonably have concluded that Mrs. Yurek had committed the\n\naffirmative acts with an intent to evade payment of her tax debt.\n\n Second, Mrs. Yurek represented to the IRS that she and her husband\n\ncouldn’t pay more than $75,000 of their tax liability based on “insufficient\n\nassets and income” even though they had just signed a contract to pay $1.3\n\nmillion for a loft. Supp. R., vol. 1, at 125, 185. Given the timing of Mrs.\n\nYurek’s representation to the IRS and the contract to purchase the loft, a\n\njury could rationally have found a specific intent to evade the tax debt.\n\n Third, the jury could reasonably have found that Mrs. Yurek had\n\narranged for Justin to purchase the loft in order to conceal her financial\n\ninterest in it. See pp. 6–7, above.\n\n Fourth, Mrs. Yurek reported to the IRS that she and her husband had\n\na gross monthly income of $7,667 in 2009 and 2010, but Bolder and\n\n\n\n 10\n\fVeracity paid monthly payments of more than $7,667 for the Yureks’\n\npersonal expenses.\n\n Fifth, Mrs. Yurek told Veracity’s accountant that her husband would\n\nrepay his loan account every year. He didn’t, so a jury could reasonably\n\nhave found that (1) Mrs. Yurek was misleading the accountant about her\n\nhusband’s intent to repay the loans and (2) the loan account served as a\n\nsham to deceive the IRS.\n\n The jury thus could reasonably have found that Mrs. Yurek had a\n\nspecific intent to evade the payment of tax debt, and this finding would\n\nsatisfy the requirement of willfulness. See United States v. Guidry, 199\n\nF.3d 1150, 1157 (10th Cir. 1999) (observing that willfulness can be\n\ninferred from “concealment of assets or covering up sources of income”\n\n(quoting Spies v. United States, 317 U.S. 492, 499 (1943))).\n\n Despite this evidence, Mrs. Yurek argues that she lacked expertise in\n\ntax matters and depended on professionals. But the jury could reasonably\n\nhave discounted this argument and found that Mrs. Yurek had known that\n\nshe was giving false information to the IRS. For example, the jury could\n\nhave reasonably relied on Mrs. Yurek’s accounting experience, which\n\nincluded handling Veracity’s payroll and accounts payable and helping to\n\nprepare Bolder’s tax returns in 2005, 2006, and 2007. See United States v.\n\nGuidry, 199 F.3d 1150, 1157 (10th Cir. 1999) (treating evidence of a\n\ndefendant’s accounting experience as support for a finding of willfulness).\n\n 11\n\f * * *\n\n For these reasons, we reject Mrs. Yurek’s challenge to the\n\nsufficiency of the evidence for her conviction on tax evasion. 7\n\n C. The evidence was sufficient to convict Mrs. Yurek of\n bankruptcy fraud.\n\n Mrs. Yurek was also convicted of bankruptcy fraud. This crime\n\ninvolves filing a bankruptcy petition with an intent to execute, conceal, or\n\nattempt to execute or conceal “a scheme or artifice to defraud.” 18 U.S.C.\n\n§ 157(1). To obtain a conviction on this offense, the government had to\n\nprove three elements beyond a reasonable doubt:\n\n 1. Mrs. Yurek had devised or intended to devise a scheme to\n defraud or otherwise engage in a fraudulent scheme.\n\n 2. Mrs. Yurek had filed a bankruptcy petition with the purpose to\n execute or conceal the scheme or attempt to do so.\n\n 3. Mrs. Yurek had acted with the specific intent to defraud. 8\n7\n Mrs. Yurek argues that her conviction cannot stand because the\ngovernment didn’t present expert testimony on “technical concepts such as\nincome or assets.” Appellant’s Op. Br. at 15. We disagree and conclude\nthat expert testimony was not necessary to assist the jury in understanding\nthe evidence.\n8\n In its jury instructions on the first and third elements, the district\ncourt referred to our circuit’s pattern jury instruction for mail fraud under\n18 U.S.C. § 1341:\n A “scheme to defraud” is conduct intended to or reasonably\n calculated to deceive persons of ordinary prudence or\n comprehension and includes a scheme to deprive another of\n money or property. An “intent to defraud” means an intent to\n deceive or cheat someone.\n\n\n 12\n\fSee United States v. Spurlin, 664 F.3d 954, 964 (5th Cir. 2011) (listing the\n\nelements that the government must prove under § 157(1) as “(1) a specific\n\nintent to defraud; (2) a scheme to defraud; and (3) filing a bankruptcy\n\npetition to conceal or execute that scheme”). Mrs. Yurek argues that the\n\ntrial evidence was insufficient on the elements of bankruptcy fraud. 9 We\n\ndisagree.\n\n Viewed in the light most favorable to the government, the trial\n\nevidence was sufficient for a jury to reasonably find satisfaction of each\n\nelement. That evidence showed six pertinent facts:\n\n 1. Mrs. Yurek and her husband had owed a substantial tax debt to\n the IRS.\n\n 2. Mrs. Yurek and her husband had filed a bankruptcy petition in\n order to discharge that debt.\n\n 3. When filing the bankruptcy petition, Mrs. Yurek and her\n husband had not told the court that Bolder and Veracity were\n paying the Yureks’ personal expenses.\n\n\nR., vol. 2, at 121–22 (citing 10th Cir. Pattern Crim. Jury Instr. § 2.56 (mail\nfraud)). As the district court noted, courts have used § 1341 for guidance\nwhen interpreting 18 U.S.C. § 157(1). See United States v. Milwitt, 475\nF.3d 1150, 1155 n.5 (9th Cir. 2007) (“Most of the few courts that have\ninterpreted 18 U.S.C. § 157 have looked to 18 U.S.C. §§ 1341 and 1343 for\nguidance.”).\n9\n Mrs. Yurek also relies on the fact that the IRS and the bankruptcy\ntrustee didn’t object to discharge of the Yureks’ tax debt. According to\nMrs. Yurek, the absence of an objection shows that the government did not\nprove the elements of bankruptcy fraud. We disagree. The absence of an\nobjection could conceivably affect the weight of the evidence but not its\nsufficiency to convict.\n\n 13\n\f 4. Bolder and Veracity had continued to pay the Yureks’ personal\n expenses during the bankruptcy proceedings, but Mrs. Yurek\n and her husband never told the bankruptcy court about these\n payments.\n\n 5. Mrs. Yurek had been a partner at Bolder and was responsible\n for Veracity’s accounts payable and payroll.\n\n 6. Mrs. Yurek had participated in obtaining the checks from\n Bolder and Veracity for personal expenses.\n\nGiven the evidence of these six facts, we conclude that the jury could\n\nreasonably have found all of the elements of bankruptcy fraud.\n\nII. We reject Mrs. Yurek’s challenges to the district court’s denials\n of her motions for severance and a new trial.\n\n We also reject Mrs. Yurek’s arguments that the district court should\n\nhave (1) severed her trial from her husband’s or (2) granted her a new trial.\n\n A. The district court generally enjoyed discretion on these\n matters.\n\n On these issues, we apply the abuse-of-discretion standard. See\n\nUnited States v. Pursley, 577 F.3d 1204, 1215 (10th Cir. 2009)\n\n(severance); United States v. Patterson, 41 F.3d 577, 579–80 (10th Cir.\n\n1994) (new trial). On the refusal to sever the trial, Mrs. Yurek needed to\n\nshow actual prejudice. See United States v. Hack, 782 F.2d 862, 870 (10th\n\nCir. 1986) (“To establish that a court abused its discretion, a defendant\n\nmust show actual prejudice to him resulting from a denial of his request for\n\nseverance.”).\n\n\n 14\n\f To satisfy this burden, Mrs. Yurek needed to show a “serious risk”\n\nthat joinder would compromise a specific trial right or prevent a reliable\n\ndetermination of guilt. Pursley, 577 F.3d at 1215. Mrs. Yurek argues both,\n\nasserting that joinder\n\n created prejudice through a spillover effect from the evidence\n of her husband’s guilt and\n\n violated the Sixth Amendment and created further prejudice by\n preventing her from confronting her husband about his out-of-\n court statement in bankruptcy court. 10\n\nIn our review of her Sixth Amendment theory, we engage in de novo\n\nreview. United States v. Clark, 717 F.3d 790, 813 (10th Cir. 2013).\n\n B. Mrs. Yurek has not shown actual prejudice from\n introduction of the evidence against her husband.\n\n Mrs. Yurek contends that her trial should have been severed from her\n\nhusband’s because\n\n the evidence against her was slim in comparison to the\n evidence against her husband and\n\n the jury could not have followed the district court’s instruction\n to separately consider the evidence against her and her\n husband.\n\n\n10\n In a footnote, Mrs. Yurek also suggests that the government violated\nFederal Rule of Evidence 403 by using her husband’s out-of-court\nstatement against her. Mrs. Yurek’s passing reference to Rule 403 does not\nconstitute adequate briefing of a distinct issue. See Adler v. Wal-Mart\nStores, Inc., 144 F.3d 664, 679 (10th Cir. 1998) (“Arguments inadequately\nbriefed in the opening brief are waived.”); COPE v. Kan. State Bd. of\nEduc., 821 F.3d 1215, 1219 n.4 (10th Cir. 2016) (concluding that “passing\nreferences” to an issue do not constitute adequate briefing).\n\n 15\n\fWe conclude that the district court acted within its discretion by rejecting\n\nthese arguments.\n\n Federal courts generally prefer to jointly try defendants who were\n\nindicted together. Zafiro v. United States, 506 U.S. 534, 537 (1993). This\n\npreference is based on recognition that\n\n joint trials “promote efficiency and serve the interests of\n justice by avoiding the scandal and inequity of inconsistent\n verdicts” 11 and\n\n joint trials are ordinarily more efficient in cases where the\n evidence against multiple defendants is “overlapping and\n intertwined.” 12\n\n Mrs. Yurek tries to skirt this preference based on the alleged\n\nspillover of evidence against her husband. But severance is not warranted\n\nby “a mere allegation that defendant would have a better chance of\n\nacquittal in a separate trial” or “a complaint of the ‘spillover effect’ from\n\nthe evidence that was overwhelming or more damaging against the co-\n\ndefendant than that against the moving party.” United States v. Hack, 782\n\nF.2d 862, 870 (10th Cir. 1986); see United States v. Wardell, 591 F.3d\n\n1279, 1300 (10th Cir. 2009) (“[T]he nearly insuperable rule in this circuit\n\nis that a defendant cannot obtain severance simply by showing that the\n\n\n\n\n11\n Zafiro, 506 U.S. at 537 (internal quotation marks omitted).\n12\n United States v. Morales, 108 F.3d 1213, 1220 (10th Cir. 1997).\n\n\n 16\n\fevidence against a co-defendant is more damaging than the evidence\n\nagainst herself.” (internal quotation marks omitted)). So Mrs. Yurek’s\n\ncomplaints about the strength of the trial evidence against her husband do\n\nnot warrant severance.\n\n Coupled with the preference for joint trials is the district court’s\n\nguidance to the jury. The court instructed the jury\n\n that it “must separately consider the evidence against each\n defendant and return a separate verdict for each” and\n\n that its “verdict as to one defendant . . . should not affect [its]\n verdict as to the other defendant.”\n\nR., vol. 2, at 113. These instructions, which the jury presumably followed,\n\nnegated the risk of prejudice to Mrs. Yurek from the joint trial. See Weeks\n\nv. Angelone, 528 U.S. 225, 234 (2000) (“A jury is presumed to follow its\n\ninstructions.”); Wardell, 591 F.3d at 1301 (noting that the district court’s\n\njury instruction “to give separate and individual consideration to each\n\ncharge against each defendant” and the district court’s other cautionary\n\nstatements to the jury “negated any risk of prejudice” to the defendant\n\nfrom the joint trial). We thus conclude that the district court acted within\n\nits discretion by denying Mrs. Yurek’s motions to sever the trial and to\n\ngrant a new trial.\n\n\n\n\n 17\n\f C. The district court’s refusal to sever the trial did not violate\n Mrs. Yurek’s right to confrontation because her husband’s\n out-of-court statement had not been testimonial.\n\n Mrs. Yurek contends that the refusal to sever the trial violated her\n\nright to confrontation by allowing the government to use the husband’s\n\nout-of-court statement against her. But the Sixth Amendment applies only\n\nwhen the out-of-court statement is testimonial. 13 See United States v.\n\nClark, 717 F.3d 790, 815 (10th Cir. 2013) (observing that the Sixth\n\nAmendment’s Confrontation Clause applies only if a statement is\n\n“testimonial”). Statements in furtherance of a conspiracy are\n\nnontestimonial, so they are admissible even when the defendants cannot\n\nconfront the declarants. United States v. Patterson, 713 F.3d 1237, 1247\n\n(10th Cir. 2013); see Crawford v. Washington, 541 U.S. 36, 56 (2004)\n\n\n13\n We have supplied “two possible definitions” for what constitutes a\n“testimonial” statement:\n\n 1. “a formal declaration made by the declarant that, when\n objectively considered, indicates the primary purpose for which\n the declaration was made was that of establishing or proving\n some fact potentially relevant to a criminal prosecution” and\n\n 2. “[a] formal statement [such that] a reasonable person in the\n position of the declarant would objectively foresee that the\n primary purpose of the statement was for use in the\n investigation or prosecution of a crime.”\n\nUnited States v. Clark, 717 F.3d 790, 816 (10th Cir. 2013) (alterations in\noriginal) (quoting United States v. Smalls, 605 F.3d 765, 778 (10th Cir.\n2010)).\n\n\n 18\n\f(observing that statements in furtherance of a conspiracy are not\n\ntestimonial).\n\n Prior to trial, the district court concluded that Mr. Yurek’s out-of-\n\ncourt statement 14 was admissible against Mrs. Yurek as a statement by a\n\ncoconspirator. To qualify for admissibility as a coconspirator statement,\n\nthe statement must have been made during and in furtherance of a\n\nconspiracy. Fed. R. Evid. 801(d)(2)(E).\n\n Mrs. Yurek does not challenge the district court’s admissibility\n\ndetermination, so we regard the husband’s out-of-court statement as\n\nnontestimonial. Introduction of this nontestimonial statement against Mrs.\n\nYurek did not violate the Sixth Amendment. See Patterson, 713 F.3d at\n\n1247 (concluding that statements made in furtherance of a conspiracy were\n\nproperly admitted because they were nontestimonial).\n\n D. Mrs. Yurek has not demonstrated that her husband would\n have been willing to testify at a severed trial.\n\n Mrs. Yurek also contends that if the trial had been severed, she could\n\nhave cross-examined her husband about his out-of-court statement. 15 But\n\nMrs. Yurek never presented evidence that her husband would have testified\n\n\n14\n He made the statement in bankruptcy court; but for purposes of\nadmissibility, the pertinent court is the federal district court in Mrs.\nYurek’s trial.\n15\n The parties dispute whether Mrs. Yurek preserved this argument. For\nthe sake of argument, we assume preservation.\n\n 19\n\fat a severed trial. Indeed, Mrs. Yurek concedes that she does not know\n\nwhether he would have done so. Appellant’s Op. Br. at 27. The resulting\n\nuncertainty is fatal to Mrs. Yurek’s contention. See United States v.\n\nPursley, 577 F.3d 1204, 1216 (10th Cir. 2009) (upholding the denial of a\n\nmotion to sever because the defendant did not submit affidavits from his\n\nco-defendants regarding their willingness to testify at a severed trial);\n\nUnited States v. Dirden, 38 F.3d 1131, 1141 n.13 (10th Cir. 1994)\n\n(upholding the denial of the defendant’s motion to sever based on the lack\n\nof evidence that the co-defendant would have given exculpatory\n\ntestimony).\n\n * * *\n\n For these reasons, we conclude that the district court acted within its\n\ndiscretion in denying Mrs. Yurek’s motions for severance and a new trial.\n\nIII. We reject Mrs. Yurek’s challenge based on multiplicity.\n\n Mrs. Yurek insists that she was convicted of multiplicitous charges:\n\ntax evasion and bankruptcy fraud. Charges are multiplicitous when they\n\ncover the same criminal conduct. United States v. McCullough, 457 F.3d\n\n1150, 1162 (10th Cir. 2006). On challenges involving multiplicity, we\n\ngenerally engage in de novo review. United States v. McIntosh, 124 F.3d\n\n1330, 1336 (10th Cir. 1997). But Mrs. Yurek did not raise the issue in a\n\n\n\n\n 20\n\fpretrial motion, so we review her argument only for plain error. Id. We\n\nconclude that there was no error, plain or otherwise.\n\n The Fifth Amendment forbids convictions on multiplicitous charges.\n\nMcCullough, 457 F.3d at 1162. But under the Blockburger test, the same\n\nconduct can trigger prosecution for multiple crimes “if each crime requires\n\nproof of a fact that the other does not.” United States v. Berres, 777 F.3d\n\n1083, 1090 (10th Cir. 2015); see Blockburger v. United States, 284 U.S.\n\n299, 304 (1932) (“[W]here the same act or transaction constitutes a\n\nviolation of two distinct statutory provisions, the test to be applied to\n\ndetermine whether there are two offenses or only one, is whether each\n\nprovision requires proof of a fact which the other does not.”). We thus\n\nfocus on whether the elements differ for Mrs. Yurek’s crimes of tax\n\nevasion and bankruptcy fraud. See Illinois v. Vitale, 447 U.S. 410, 416\n\n(1980) (analyzing the elements of the crimes of conviction when applying\n\nthe Blockburger test).\n\n A conviction for tax evasion requires proof of three elements:\n\n 1. The defendant owed a substantial tax to the IRS.\n\n 2. The defendant committed “an affirmative act constituting an\n evasion or attempted evasion” of assessment or payment of the\n tax.\n\n 3. The defendant willfully evaded or attempted to evade the\n assessment or payment of the tax.\n\n\n\n\n 21\n\fUnited States v. Boisseau, 841 F.3d 1122, 1125 (10th Cir. 2016) (citing\n\nSansone v. United States, 380 U.S. 343, 351 (1965)). A conviction for\n\nbankruptcy fraud also requires proof of three elements:\n\n 1. The defendant devised or intended to devise a scheme to\n defraud or otherwise engage in a fraudulent scheme.\n\n 2. For the purpose of executing or concealing the scheme or\n attempting to do so, the defendant filed a petition under the\n Bankruptcy Code.\n\n 3. The defendant acted with the specific intent to defraud.\n\nUnited States v. Spurlin, 664 F.3d 954, 964 (5th Cir. 2011). As Mrs. Yurek\n\nadmits, each crime requires proof of an element that the other crime does\n\nnot. We thus would not ordinarily consider the two counts multiplicitous.\n\n But Mrs. Yurek argues that the government’s theory essentially\n\nrequired the same elements for both crimes because the government\n\ncharacterized the bankruptcy fraud as a scheme to evade taxes. To support\n\nthis argument, Mrs. Yurek points to the indictment, contending that the\n\nindictment shows that both counts stemmed from the same underlying\n\nconduct. But the Blockburger test “focuses on the proof necessary to prove\n\nthe statutory elements of each offense, rather than on the actual evidence\n\nto be presented at trial.” Illinois v Vitale, 447 U.S. 410, 416 (1980). Given\n\nthe focus of this test, Mrs. Yurek’s argument fails because the nature of the\n\ncharges does not alter the elements that the government needed to prove.\n\n\n\n\n 22\n\f To argue that she was convicted of multiplicitous charges, Mrs.\n\nYurek also relies on United States v. McIntosh, 124 F.3d 1330 (10th Cir.\n\n1997). In McIntosh we acknowledged that “Congress undoubtedly may\n\nsubject a defendant to multiple convictions and punishments for the same\n\nact,” but we held that Congress did not intend to subject the defendant to\n\nconvictions for both 18 U.S.C. § 152(3) (making a false statement) and 18\n\nU.S.C. § 152(7) (concealing assets). 124 F.3d at 1336–37.\n\n But Mrs. Yurek was not convicted of violating either § 152(3) or\n\n§ 152(7), so McIntosh does not control. And unless Congress expresses a\n\ncontrary intent, “we presume . . . that Congress intended multiple\n\nconvictions and sentences for the same criminal behavior which violates\n\nmore than one statute when each statute requires proof of a fact that the\n\nother does not.” United States v. Benoit, 713 F.3d 1, 12 (10th Cir. 2013).\n\n Mrs. Yurek has not pointed to any evidence that Congress expressed\n\nan intent to preclude a conviction for both tax evasion and bankruptcy\n\nfraud. Mrs. Yurek’s reliance on McIntosh is thus misguided, and we\n\nconclude that the charges were not multiplicitous.\n\nIV. The district court erroneously calculated the guideline range by\n applying the wrong test for a mitigating-role adjustment.\n\n Mrs. Yurek contends that the district court\n\n should have applied Sentencing Guideline § 2T1.1 to her\n conviction for bankruptcy fraud,\n\n incorrectly calculated the loss attributable to her, and\n 23\n\f applied the wrong test for a mitigating-role adjustment.\n\nWe agree that the district court erred in deciding whether to grant Mrs.\n\nYurek a mitigating-role adjustment. But the court did not otherwise err at\n\nsentencing.\n\n A. Sentencing Guideline § 2T1.1 does not apply to Mrs.\n Yurek’s conviction for bankruptcy fraud.\n\n To calculate the guideline range, the district court must select the\n\napplicable guideline (if one exists) for the offense of conviction. U.S.S.G.\n\n1B1.2(a) (2016). 16 Here the parties agree that the relevant offense of\n\nconviction was bankruptcy fraud under 18 U.S.C. § 157(1). For this\n\noffense, however, the Sentencing Commission has not expressly adopted a\n\nguideline. When the Sentencing Commission has not specified the\n\napplicable guideline, the district court must “apply the most analogous\n\noffense guideline.” U.S.S.G. § 2X5.1 (2016). This process involves two\n\nsteps. The court begins by determining which guidelines are sufficiently\n\nanalogous; from these guidelines, the court then selects the most analogous\n\n\n\n\n16\n The 2016 version was in effect at the time of Mrs. Yurek’s\nsentencing. See U.S.S.G. § 1B1.11(a) (2016) (Ordinarily, “[t]he court shall\nuse the Guidelines Manual in effect on the date that the defendant is\nsentenced.”).\n\n\n 24\n\fone. 17 Id. § 2X5.1 cmt.; United States v. Nichols, 169 F.3d 1255, 1270–71\n\n(10th Cir. 1999).\n\n The district court assumed for the sake of argument that both § 2T1.1\n\nand § 2B1.1 were “sufficiently analogous” to bankruptcy fraud under 18\n\nU.S.C. § 157(1). The district court then concluded that § 2B1.1 was the\n\nmore analogous guideline.\n\n The parties agree that § 2B1.1 is sufficiently analogous to\n\nbankruptcy fraud under 18 U.S.C. § 157(1). 18 But the parties disagree over\n\nwhether § 2T1.1 is also sufficiently analogous to bankruptcy fraud. To\n\ndetermine whether § 2T1.1 is “sufficiently analogous” to bankruptcy fraud,\n\nwe compare the elements of bankruptcy fraud under 18 U.S.C. § 157(1)\n\n\n\n\n17\n If there is not a sufficiently analogous guideline, 18 U.S.C. § 3553\nwould control. U.S.S.G. § 2X5.1 cmt. (2016).\n18\n Section 2B1.1 covers crimes of fraud and deceit. Two of the crimes\ncovered by § 2B1.1 are mail fraud and wire fraud. See U.S.S.G. App’x A\n(2016) (identifying 18 U.S.C. §§ 1341 and 1343 as covered by § 2B1.1).\nThe statutes for these crimes served as the model for § 157. See United\nStates v. Milwitt, 475 F.3d 1150, 1155 (9th Cir. 2007). Like § 157, both\nmail fraud and wire fraud include as elements (1) a scheme or artifice to\ndefraud and (2) the specific intent to defraud. Compare United States v.\nSpurlin, 664 F.3d 954, 964 (5th Cir. 2011) (listing the elements for\nbankruptcy fraud under § 157(1)), with United States v. Welch, 327 F.3d\n1081, 1104 (10th Cir. 2003) (listing the elements for mail fraud and wire\nfraud).\n\n\n 25\n\fwith the elements of the offenses covered by § 2T1.1. See United States v.\n\nNichols, 169 F.3d 1255, 1270 (10th Cir. 1999). 19\n\n Section 2T1.1 relates to matters of taxation. Thus, all of the crimes\n\nexpressly covered by § 2T1.1 involve taxation:\n\n evading taxes (26 U.S.C. § 7201),\n\n willfully failing to file a tax return, keep records, supply\n information, or pay a tax (26 U.S.C. § 7203),\n\n making false or fraudulent statements to the IRS (26 U.S.C.\n § 7206(1), (3), (4), and (5)),\n\n willfully filing a fraudulent return, statement, or other\n document (26 U.S.C. § 7207),\n\n making false statements to purchasers or lessees relating to a\n tax (26 U.S.C. § 7211), and\n\n attempting to interfere with the administration of the tax laws\n (26 U.S.C. § 7212(a)).\n\nU.S.S.G. App’x A (2016).\n\n Because these crimes target taxation, they contrast starkly with\n\nbankruptcy fraud. Bankruptcy fraud requires specific intent to defraud, 20\n\nand the § 2T1.1 crimes require specific intent only with regard to the tax\n\nlaws. For example, tax evasion under 26 U.S.C. § 7201 requires proof that\n\n\n19\n Because the district court didn’t decide this issue, we use our\nindependent judgment on this legal issue. Cf. Nichols, 169 F.3d at 1270\n(stating that determination of the first step is “purely legal,” requiring de\nnovo review).\n20\n United States v. Spurlin, 664 F.3d 954, 964 (5th Cir. 2011).\n\n 26\n\fa defendant had the “specific intent to evade taxes.” United States v.\n\nPayne, 978 F.2d 1177, 1182 (10th Cir. 1992). A violation of 26 U.S.C.\n\n§ 7203 occurs only if a defendant “willfully fails” to pay a tax, file a\n\nreturn, keep tax records, or supply tax-related information. And a\n\nconviction under 26 U.S.C. § 7206(4) requires the government to prove\n\nthat a defendant hid taxable property “with intent to evade or defeat the\n\nassessment or collection” of a tax. So the specific-intent element for\n\nbankruptcy fraud sweeps beyond the specific-intent elements found in\n\n§ 2T1.1 crimes.\n\n Nor is there a match between § 2T1.1 and bankruptcy fraud’s first\n\nelement (scheme to defraud). See United States v. Spurlin, 664 F.3d 954,\n\n964 (5th Cir. 2011). It is true that many of the crimes covered by § 2T1.1\n\ntarget fraudulent conduct. But § 2T1.1’s fraud crimes again relate only to\n\nthe tax laws:\n\n 1. making false or fraudulent statements to the IRS (26 U.S.C.\n § 7206(1)),\n\n 2. making false statements regarding a tax to purchasers or lessees\n (26 U.S.C. § 7211),\n\n 3. filing false or fraudulent documents with the IRS (26 U.S.C.\n § 7207),\n\n 4. concealing taxable property from the IRS (26 U.S.C.\n §§ 7206(4) and 7206(5)), and\n\n 5. falsely or fraudulently executing or signing documents required\n by the provisions of the Internal Revenue Code or regulations\n issued under those provisions (26 U.S.C. § 7206(3)).\n\n 27\n\fSee p. 26, above. Unlike these crimes, bankruptcy fraud targets a scheme to\n\ndefraud unrelated to taxation or the administration of the federal tax laws.\n\nSo the fraudulent conducted covered by bankruptcy fraud sweeps beyond\n\nthe fraudulent conduct covered by § 2T1.1.\n\n Because the elements of § 2T1.1 crimes are narrower than and largely\n\nunrelated to the elements of bankruptcy fraud, we conclude that § 2T1.1 is\n\nnot sufficiently analogous to bankruptcy fraud. Thus the only potentially\n\napplicable guideline was § 2B1.1, and the district court did not err by\n\napplying this section.\n\n B. The amount of intended loss attributable to Mrs. Yurek\n could reasonably be based on the amount of debt that Mrs.\n Yurek had tried to discharge in bankruptcy.\n\n At Mrs. Yurek’s sentencing, the district court applied Sentencing\n\nGuideline § 2B1.1 to determine Mrs. Yurek’s base-offense level and\n\nspecific offense characteristics. For the specific offense characteristics,\n\n§ 2B1.1 allowed the court to increase the base-offense level based on the\n\n\n\n\n 28\n\famount of the intended loss attributable to a defendant. 21 See U.S.S.G.\n\n§ 2B1.1(b)(1) (2016).\n\n To calculate the intended loss, the district court considered two\n\nmethodologies:\n\n 1. the amount of federal tax debt that Mrs. Yurek tried to\n discharge in bankruptcy and\n\n 2. the value of the assets that Mrs. Yurek concealed from the\n bankruptcy court.\n\nThe court found that under either approach, the intended loss was between\n\n$550,000 and $1,500,000. Given this finding, the court overruled Mrs.\n\nYurek’s objection to the U.S. Probation Department’s recommendation of a\n\n14-level enhancement.\n\n On appeal, Mrs. Yurek argues that the loss attributable to her was\n\nless than $550,000 and that the district court erred in two ways when\n\ncalculating the intended loss:\n\n 1. The amount sought to be discharged in bankruptcy did not\n constitute an appropriate methodology.\n\n 2. The district court miscalculated the value of the assets that had\n been concealed from the bankruptcy court.\n\n We reject Mrs. Yurek’s challenge to the district court’s methodology\n\nfor calculating the intended loss. Determining this methodology involves a\n\n\n21\n Under § 2B1.1, “loss is the greater of actual loss or intended loss.”\nU.S.S.G. § 2B1.1 cmt. n.3(A) (2016). The parties agree that the applicable\nmeasure of loss is intended loss because there was no actual loss.\n\n 29\n\flegal conclusion, so we engage in de novo review. See United States v.\n\nGordon, 710 F.3d 1124, 1160–61 (10th Cir. 2013) (stating that we engage\n\nin de novo review of the district court’s methodology for calculating loss\n\nunder § 2B1.1(b)). Engaging in de novo review, we start with the\n\napplicable guideline and related application notes. The application notes\n\nfor § 2B1.1 define “intended loss” as a loss that a defendant “purposely\n\nsought to inflict.” U.S.S.G. § 2B1.1 cmt. n.3(A)(ii)(I) (2016); see United\n\nStates v. Manatau, 647 F.3d 1048, 1050 (10th Cir. 2011) (Gorsuch, J.)\n\n(“Something is intended if it is done on purpose—not merely known,\n\nforeseen, or just possible or potentially contemplated.”). 22 We must follow\n\nthis definition of intended loss because it is not plainly erroneous,\n\ninconsistent with § 2B1.1, or violative of the U.S. Constitution or a federal\n\nstatute. United States v. Mojica, 214 F.3d 1169, 1171 (10th Cir. 2000).\n\n Applying this definition, we conclude that the intended loss equals\n\nthe monetary harm that Mrs. Yurek wanted to cause her creditors. See\n\nUnited States v. Holthaus, 486 F.3d 451, 455 (8th Cir. 2007) (“When\n\ndetermining intended loss [in the bankruptcy context], we look to the\n\n\n\n\n22\n In Manatau, we interpreted the phrase “intended loss” in a prior\nversion of § 2B1.1 to mean “a loss the defendant purposely sought to\ninflict.” Manatau, 647 F.3d at 1050 (emphasis in original). The Sentencing\nCommission later amended § 2B1.1 to reflect this holding. See U.S.S.G.\namend. 792 (eff. Nov. 1, 2015), available at U.S.S.G. supp. to app. C 108–\n12 (2016 ) .\n\n 30\n\famount of loss a defendant actually intended to cause his creditors.”);\n\nUnited States v. Bussell, 504 F.3d 956, 962 (9th Cir. 2007) (“When\n\ndetermining intended loss [in the bankruptcy context], we must look to the\n\namount of loss that [the defendant] intended to cause her creditors.”).\n\n These creditors included the IRS, so the intended loss includes the\n\namount of federal tax debt that Mrs. Yurek tried to discharge in\n\nbankruptcy. That discharge would have extinguished Mrs. Yurek’s federal\n\ntax debt, causing a loss to the IRS. See United States v. Mutuc, 349 F.3d\n\n930, 937 (7th Cir. 2003) (“A successful discharge in bankruptcy would\n\nhave left the creditors without recourse against Mutuc; it follows that\n\nMutuc intended a loss equal to the amount to be discharged in\n\nbankruptcy.”).\n\n In similar circumstances, other circuits have ordinarily allowed\n\ncalculation of the intended loss based on the amount of debt that the\n\ndefendant was trying to discharge, though the circuits have taken somewhat\n\ndifferent approaches. For example, the Seventh Circuit has flatly stated\n\nthat it allows measurement of the intended loss based on the amount that\n\nthe defendant sought to discharge in bankruptcy. See United States v.\n\nArthur, 582 F.3d 713, 720–21 (7th Cir. 2009); United States v. Mutuc, 349\n\nF.3d 930, 936–37 (7th Cir. 2003); United States v. Holland, 160 F.3d 377,\n\n381 (7th Cir. 1998). On the other hand, the Ninth Circuit allows the district\n\ncourt to consider the economic realities in each case and use discretion in\n\n 31\n\fdetermining whether to calculate the intended loss based on the entire\n\namount to be discharged or the value of concealed assets. See United States\n\nv. Bussell, 504 F.3d 956, 961–62 (9th Cir. 2007). And the Eighth Circuit\n\nhas suggested that the intended loss can equal the entire amount that the\n\ndefendants are trying to discharge only if the fraud had created the illusion\n\nof dischargeability. See United States v. Holthaus, 486 F.3d 451, 455 (8th\n\nCir. 2007).\n\n All of these approaches support the district court’s decision to\n\ncalculate the intended loss attributable to Mrs. Yurek based on the amount\n\nof tax debt ($1.2 million) that Mrs. Yurek was trying to discharge in\n\nbankruptcy. So regardless of whether we consider the economic realities or\n\nthe illusion of dischargeability, the district court did not err in calculating\n\nthe intended loss based on the amount that Mrs. Yurek had tried to\n\ndischarge in bankruptcy.\n\n Of course, Mrs. Yurek couldn’t succeed in causing this loss because\n\nonce she committed tax evasion, the entire tax debt became\n\nnondischargeable. See 18 U.S.C. § 523(a)(1)(C). But a loss can be intended\n\neven when it is improbable or impossible. U.S.S.G. § 2B1.1 cmt. n.3(A)(ii)\n\n(2016). 23\n\n\n23\n We have stated that a loss is intended only if (1) “the defendant\nrealistically intended a particular loss” or (2) such a loss was probable.\nUnited States v. Swanson, 360 F.3d 1155, 1168 (10th Cir. 2004); United\n\n 32\n\f Mrs. Yurek disagrees, relying on United States v. Holthaus, 486 F.3d\n\n451 (8th Cir. 2002). There, however, the Eighth Circuit expressly\n\ndisavowed a blanket prohibition against calculation of intended loss based\n\non the amount that the defendant had tried to discharge in bankruptcy.\n\nHolthaus, 486 F.3d at 455; see p. 32, above. Given the pinpoint citation in\n\nMrs. Yurek’s opening appeal brief, Mrs. Yurek is apparently intending to\n\nrely on the Holthaus panel’s discussion of a prior opinion, United States v.\n\nWheeldon, 313 F.3d 1070 (8th Cir. 2002). There the Eighth Circuit\n\naddressed the proper method for calculating intended loss when the amount\n\nof the attempted discharge exceeds the value of the concealed assets.\n\nWheeldon, 313 F.3d at 1072. Applying the 2000 version of the U.S.\n\nSentencing Guidelines, the Eighth Circuit concluded that this situation\n\nrequired the district court to calculate the intended loss based on the value\n\nof the concealed assets. Id.\n\n In reaching this conclusion, the Eighth Circuit didn’t apply the term\n\n“intended loss;” the court instead applied the term “probable intended\n\n\n\n\nStates v. Schild, 269 F.3d 1198, 1200 (10th Cir. 2001). We later\ncharacterized the reference to “probable” loss as “dicta” based on\n“questionable authority.” United States v. Baum, 555 F.3d 1129, 1134\n(10th Cir. 2009). That “questionable authority” was United States v. Smith,\n951 F.2d 1164 (10th Cir. 1991), which had relied on guideline language\nthat was later deleted. See Baum, 555 F.3d at 1134–35 (discussing the\norigin of the language in Swanson and Schild and later changes to the\nsentencing guidelines) .\n\n 33\n\floss.” Id. But the Sentencing Commission amended the applicable\n\ndefinition of “intended loss” in 2001, providing that a loss can be intended\n\neven when it is unlikely or impossible. U.S.S.G. amend. 617 (eff. Nov. 1,\n\n2001), available at U.S.S.G. app. C vol. II at 117 (2016) (“The amendment\n\nresolves the conflict to provide that intended loss includes unlikely or\n\nimpossible losses that are intended, because their inclusion better reflects\n\nthe culpability of the offender.”); see p. 32 & note 23, above. Given the\n\nchange in definition, the nondischargeability of Mrs. Yurek’s tax debt does\n\nnot affect the available methods to calculate intended loss.\n\n Mrs. Yurek listed a tax debt of $1.2 million in her bankruptcy\n\npetition, requesting that it be discharged. And her husband, who also\n\nsigned the bankruptcy petition, stated in bankruptcy court that he and his\n\nwife had filed the bankruptcy petition in order to discharge their $1.2\n\nmillion tax debt. Given this evidence, the court could calculate the\n\nintended loss attributable to Mrs. Yurek based on the amount of tax debt\n\nthat she had tried to discharge.\n\n * * *\n\n We conclude that the district court appropriately calculated the\n\nintended loss attributable to Mrs. Yurek based on the amount of tax debt\n\nthat she had tried to discharge in bankruptcy. Thus, the district court did\n\nnot err in applying the 14-level sentencing enhancement.\n\n\n\n 34\n\f C. The district court plainly erred by applying the wrong test\n for a mitigating-role adjustment.\n\n Mrs. Yurek also argues that the district court applied the wrong test\n\nwhen deciding not to grant a downward adjustment for a mitigating role.\n\nWe agree.\n\n 1. Preservation and the Argument for Plain Error\n\n The government contends that Mrs. Yurek did not preserve the issue\n\nfor appeal. We agree.\n\n To preserve an appellate issue involving the district court’s\n\nexplanation for a sentence, the defendant must lodge a “contemporaneous\n\nobjection.” United States v. Romero, 491 F.3d 1173, 1177 (10th Cir. 2007);\n\nsee United States v. Lopez-Flores, 444 F.3d 1218, 1221 (10th Cir. 2006)\n\n(“[T]he usual reasons for requiring a contemporaneous objection apply to\n\nchallenges to the district court’s method of arriving at a sentence.”). At\n\nsentencing, the district court explained that it would deny Mrs. Yurek a\n\nmitigating-role adjustment because her participation in tax evasion and\n\nbankruptcy fraud had been “central and necessary for both . . . crimes to\n\ntake place.” R., vol. 5, at 1925; see also id. at 1925–26 (finding “ample\n\ngrounds to conclude that Ms. Yurek’s participation in these criminal\n\nschemes was central and necessary and that her husband could not have\n\nproceeded with either the tax evasion or the bankruptcy fraud without\n\nher”).\n\n\n 35\n\f Mrs. Yurek argues that the district court applied the wrong test. She\n\nbases her argument on the district court’s explanation for denying a\n\nmitigating-role adjustment, but she did not raise this issue in district court.\n\nAccording to Mrs. Yurek, she preserved the issue by objecting to the\n\npresentence report. But she is alleging an error in the district court’s\n\nexplanation, not in the content of the presentence report. So objecting to\n\nthe presentence report would not have alerted the district court to an error\n\nin its explanation. See United States v. Mendoza, 543 F.3d 1186, 1195\n\n(10th Cir. 2008); 24 see also United States v. Chavez-Morales, 894 F.3d\n\n1206, 1213 (10th Cir. 2018) (concluding that a defendant’s sentencing\n\nmemorandum did not preserve an issue involving the adequacy of the\n\ndistrict court’s explanation). Because Mrs. Yurek did not preserve her\n\nargument involving correctness of the legal standard for a mitigating-role\n\n\n\n\n24\n In Mendoza, the government appealed the sentence, arguing that the\ndistrict court failed to provide written reasons for its downward variance.\n543 F.3d at 1186. We concluded that the government had forfeited this\nappeal point by failing to alert the district court to its failure to provide\nwritten reasons. Id. at 1195. An objection to the presentence report didn’t\nsuffice for preservation: “Unlike other forms of sentencing error, which\ncan be preserved for appellate review through written objections to the\n[presentence report] or an oral objection during the sentencing hearing,\nfailure to enter a written statement of reasons becomes apparent to the\nparties only after the court enters its final judgment regarding the sentence\nimposed.” Id.\n\n\n 36\n\fadjustment, any review would be confined to the plain-error standard.\n\nRomero, 491 F.3d at 1178. 25\n\n But the government argues that Mrs. Yurek lost her opportunity to\n\nurge plain error by waiting until her reply brief to do so. We disagree. Mrs.\n\nYurek appeared to assume in her opening brief that she had preserved her\n\nchallenge to the denial of a mitigating-role adjustment. After the\n\ngovernment challenged preservation, Mrs. Yurek argued in her reply brief\n\nthat the error would be considered plain even if she had forfeited the issue.\n\nThis approach was a permissible way to invoke plain-error review. See\n\nUnited States v. Zander, 794 F.3d 1220, 1232 n.5 (10th Cir. 2015) (“We\n\nhold that Defendant adequately addressed the issue of plain error review in\n\nhis reply to the government’s brief, after arguing in his opening brief that\n\nhis objections below were sufficiently raised to be preserved for review on\n\nappeal.”). We thus apply the standard for plain error.\n\n 2. Mrs. Yurek is entitled to relief under the plain-error\n standard.\n\n For Mrs. Yurek to prevail under the plain-error test, she must show\n\n 1. that an error took place,\n\n\n\n\n25\n Mrs. Yurek contends that the government induced the error by\narguing that she had played a central and necessary role in the crimes. But\nthe government never suggested to the district court that it apply the wrong\nlegal test. The government simply argued against a mitigating-role\nadjustment. Presentation of this argument did not induce the court’s error.\n\n 37\n\f 2. that the error was plain,\n\n 3. that it affected her substantive rights, and\n\n 4. that the error “seriously affects the fairness, integrity, or public\n reputation of judicial proceedings.”\n\nUnited States v. Bustamante-Conchas, 850 F.3d 1130, 1137 (10th Cir.\n\n2017) (en banc). Mrs. Yurek has satisfied each of these prongs.\n\n a. The government properly conceded the first and second\n prongs.\n\n The government concedes the first two prongs of the plain-error test.\n\nWe agree that the first two prongs are satisfied.\n\n A defendant who was a minimal or minor participant in criminal\n\nactivity is eligible for a downward adjustment. See U.S.S.G. § 3B1.2\n\n(2016). Finding that a defendant performed an “essential or indispensable\n\nrole . . . is not determinative” of eligibility for this adjustment. Id. § 3B1.2\n\ncmt. n.3(C). The court instead must focus on whether the defendant “is\n\nsubstantially less culpable than the average participant in the criminal\n\nactivity.” Id.; see United States v. Salazar-Samaniega, 361 F.3d 1271,\n\n1277 (10th Cir. 2004) (noting that a § 3B1.2 reduction is available only for\n\n“a defendant who plays a part in committing the offense that makes him\n\nsubstantially less culpable than the average participant”); United States v.\n\nAyers, 84 F.3d 382, 383 (10th Cir. 1996) (“Section 3B1.2 vests the district\n\ncourt with discretion to grant a base-offense level reduction if it finds a\n\n\n\n 38\n\fdefendant is less culpable relative to other participants in a given offense.”\n\n(internal quotation marks omitted)).\n\n But the district court did not consider Mrs. Yurek’s culpability\n\nrelative to other participants in the scheme. 26 The court instead found that\n\nMrs. Yurek’s role had been essential to the crimes and treated that finding\n\nas determinative. By failing to consider Mrs. Yurek’s relative culpability,\n\nthe district court applied the wrong test when denying a mitigating-role\n\nadjustment. As the government admits, the district court’s application of\n\nthe wrong test constitutes an error that was plain. Mrs. Yurek has thus\n\nsatisfied both the first and second prongs of the plain-error standard.\n\n\n\n\n26\n In the criminal scheme, only two persons were named: Mrs. Yurek\nand her husband. But the husband was not an “average participant” because\nhe had obtained a two-level enhancement for a leadership role in the\ncrimes. So in this scheme, it is impossible to compare Mrs. Yurek’s\nculpability to another “average” participant.\n\n Given the absence of another “average” participant in this scheme,\nthe sentencing court must focus on (1) the degree of Mrs. Yurek’s\nculpability relative to her husband’s and (2) the scope of the criminal\nscheme. See United States v. Lopez, 545 F.3d 515, 517 (7th Cir. 2008)\n(“[I]n situations where criminal activity involves only two participants\n(and thus it is impossible to ascertain the culpability of an ‘average’\nparticipant), the key inquiry is the degree of the defendant’s culpability\nrelative to the other participant’s and the scope of the criminal\nenterprise.”). With this dual focus, the court should determine whether\nMrs. Yurek bore substantially less culpability than her husband. See id.;\nsee also United States v. Tholl, 895 F.2d 178, 1185–86 (7th Cir. 1990)\n(concluding that under § 3B1.2, it was not enough for the defendant to\nprove less culpability than the sole other participant, who had been the\n“mastermind” behind the criminal scheme).\n 39\n\f b. Mrs. Yurek has satisfied the third prong of the plain-error\n test.\n\n Mrs. Yurek has also satisfied the third prong of the plain-error test.\n\nUnder this prong, Mrs. Yurek bears the burden to show prejudice. United\n\nStates v. Gonzales-Huerta, 403 F.3d 727, 732–33 (10th Cir. 2005). To\n\nsatisfy this burden, Mrs. Yurek must show a reasonable probability\n\nsufficient to undermine confidence in the outcome at her sentencing.\n\nUnited States v Bustamante-Conchas, 850 F.3d 1130, 1138 (10th Cir. 2017)\n\n(en banc). Confidence in the outcome can be undermined even if Mrs.\n\nYurek’s showing would not satisfy the preponderance-of-the-evidence\n\nstandard. United States v. Dominguez Benitez, 542 U.S. 74, 83 n.9 (2004).\n\n Mrs. Yurek has shown prejudice from the district court’s application\n\nof the wrong test. The crux of § 3B1.2 is a defendant’s relative culpability.\n\nSee pp. 38–39, above. After denying a mitigating-role adjustment to Mrs.\n\nYurek, the court considered her relative culpability and downplayed her\n\nrole in the scheme:\n\n It is true that the trial evidence established that the\n defendants used accountants and attorneys as tools to accomplish\n the bankruptcy fraud and tax evasion schemes for which they\n were convicted, but in the mitigation for this defendant, these\n accountants and attorneys unambiguously testified at trial that it\n was always Mr. Yurek, as opposed to his wife, who took the lead\n in communicating and strategizing with them in the perpetuation\n of these schemes.\n\n While it does not absolve her from her culpability for her\n crimes, in my judgment fairness requires me to temper the\n sentence I will impose on Ms. Yurek to reflect her passive and,\n\n 40\n\f to some degree, submissive personality when compared to her\n husband, at least insofar as matters such as the complex criminal\n schemes in this case are concerned.\n\nR., vol. 5, at 1969–70 (emphasis added). Given Mrs. Yurek’s lesser role in\n\nthe scheme, the district court varied downward to 27 months from the\n\nguideline range of 41–51 months.\n\n The district court justified the downward variance based in part on\n\nits view that Mrs. Yurek bore less culpability than her husband. If a\n\ndistrict court finds that a defendant is less culpable relative to other\n\nparticipants in a crime and varies downward from the advisory guideline\n\nrange based partly on that determination, a reasonable probability exists\n\nthat the district court would have granted a mitigating-role adjustment\n\nunder the correct test. See United States v. Trujillo-Terrazas, 405 F.3d\n\n814, 820 (10th Cir. 2005) (considering a district court’s comments at\n\nsentencing when determining whether the plain error prejudiced the\n\ndefendant); see also United States v. Sierra-Castillo, 405 F.3d 932, 942\n\n(10th Cir. 2005) (noting that a district court’s comments at sentencing can\n\nhelp a defendant satisfy the third prong of the plain-error test).\n\n And if the district court had granted Mrs. Yurek a mitigating-role\n\nadjustment, the district court’s starting point (the guideline range) would\n\nhave been lower. “When the court’s starting point is skewed a ‘reasonable\n\nprobability’ exists that its final sentence is skewed too.” United States v.\n\n\n\n 41\n\fSabillon-Umana, 772 F.3d 1328, 1333 (10th Cir. 2014) (Gorsuch, J.). Mrs.\n\nYurek has thus satisfied the third prong of the plain-error test.\n\n c. The fourth prong was also satisfied.\n\n To satisfy the fourth prong, Mrs. Yurek must show that the district\n\ncourt’s error “seriously affects the fairness, integrity, or public reputation\n\nof judicial proceedings.” United States v. Bustamante-Conchas, 850 F.3d\n\n1130, 1137 (10th Cir. 2017) (en banc). We conclude that Mrs. Yurek has\n\nmet this burden.\n\n When an error affects the calculation of a defendant’s guideline\n\nrange, the fourth prong is ordinarily satisfied when the first three prongs\n\nare satisfied. Rosales-Mireles v. United States, 138 S. Ct. 1897, 1908\n\n(2018). After all, “what reasonable citizen wouldn’t bear a rightly\n\ndiminished view of the judicial process and its integrity if courts refused to\n\ncorrect obvious errors of their own devise that threaten to require\n\nindividuals to linger longer in federal prison than the law demands?” Id.\n\n(quoting United States v. Sabillon-Umana, 772 F.3d 1328, 1333–34 (10th\n\nCir. 2014) (Gorsuch, J.)).\n\n * * *\n\n We conclude that the district court plainly erred by applying the\n\nwrong test for a mitigating-role adjustment.\n\n\n\n\n 42\n\fV. Conclusion\n\n We affirm Ms. Yurek’s conviction, but we vacate her sentence and\n\nremand for resentencing. At resentencing, the district court must\n\nreconsider the possibility of a mitigating-role adjustment.\n\n\n\n\n 43\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Wendy Marie YUREK, Defendant-Appellant.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-21\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 21, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\nv. No. 18-1134\\n\\nWENDY MARIE YUREK,\\n\\n Defendant-Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:15-CR-00394-WJM-2)\\n _________________________________\\n\\nRobert S. Jackson, Oklahoma City, Oklahoma, for Defendant-Appellant.\\n\\nPegeen D. Rhyne, Assistant United States Attorney (Jason R. Dunn, United\\nStates Attorney, with her on the brief), Denver, Colorado, for Plaintiff-\\nAppellee.\\n _________________________________\\n\\nBefore BACHARACH, BALDOCK, and EBEL, Circuit Judges.\\n _________________________________\\n\\nBACHARACH, Circuit Judge.\\n _________________________________\\n\\f Mrs. Wendy Yurek and her husband, Mr. Daryl Yurek, were charged\\n\\nwith tax evasion and bankruptcy fraud. 1 After a joint jury trial, Mrs. Yurek\\n\\nand her husband were convicted on both offenses. The district court then\\n\\nsentenced Mrs. Yurek to a prison term of 27 months, leading her to appeal\\n\\nthe conviction and sentence.\\n\\n We affirm in part and reverse in part. We affirm Mrs. Yurek’s\\n\\nconviction, but we vacate the sentence because the district court applied\\n\\nthe wrong test when deciding whether to grant a mitigating-role\\n\\nadjustment.\\n\\nI. We reject Mrs. Yurek’s challenges to the sufficiency of the\\n evidence on her conviction for tax evasion and bankruptcy fraud.\\n\\n We conclude that the evidence of Mrs. Yurek’s guilt was sufficient to\\n\\nsupport her conviction for tax evasion and bankruptcy fraud.\\n\\n A. We engage in de novo review over the sufficiency of the\\n evidence.\\n\\n In considering the sufficiency of the evidence, we engage in de novo\\n\\nreview. United States v. Ramos-Arenas, 596 F.3d 783, 786 (10th Cir.\\n\\n2010). We will reverse only if no rational factfinder could have found that\\n\\nthe government had proven all of the elements of an offense beyond a\\n\\n\\n\\n\\n1\\n Mr. Yurek was also charged with making a false statement under oath\\nin a bankruptcy proceeding and willfully making false statements to the\\nIRS under penalty of perjury.\\n\\n 2\\n\\freasonable doubt. United States v. Brown, 400 F.3d 1242, 1247 (10th Cir.\\n\\n2005).\\n\\n Under de novo review, we view the trial evidence in the light most\\n\\nfavorable to the government. United States v. Boisseau, 841 F.3d 1122,\\n\\n1125 (10th Cir. 2016). We do not reevaluate witness credibility or reweigh\\n\\nthe evidence. United States v. Smith, 133 F.3d 737, 742 (10th Cir. 1997).\\n\\n B. The evidence was sufficient to convict on tax evasion.\\n\\n Mrs. Yurek was convicted of tax evasion, which consists of\\n\\n“willfully attempt[ing] in any manner to evade or defeat any tax imposed\\n\\nby [the Internal Revenue Code] or the payment thereof.” 26 U.S.C. § 7201.\\n\\nTo obtain a conviction on this offense, the government had to prove three\\n\\nelements:\\n\\n 1. Mrs. Yurek owed a substantial tax to the IRS.\\n\\n 2. Mrs. Yurek committed “an affirmative act constituting an\\n evasion or attempted evasion” of assessment or payment of the\\n tax.\\n\\n 3. Mrs. Yurek willfully evaded or attempted to evade the\\n assessment or payment of the tax. 2\\n\\nUnited States v. Boisseau, 841 F.3d 1122, 1125 (10th Cir. 2016) (citing\\n\\nSansone v. United States, 380 U.S. 343, 351 (1965)); see United States v.\\n\\n\\n2\\n Mrs. Yurek argues that the government did not establish that she and\\nher husband had the ability to pay their IRS tax debt. But the ability to pay\\none’s taxes is not an element of tax evasion. See Boisseau, 841 F.3d at\\n1125.\\n\\n 3\\n\\fThompson, 518 F.3d 832, 850 (10th Cir. 2008) (noting that the tax liability\\n\\nmust be “substantial”).\\n\\n Mrs. Yurek challenges the sufficiency of the evidence on the second\\n\\nand third elements (an affirmative act and willfulness).\\n\\n 1. The evidence was sufficient to find an affirmative act.\\n\\n To establish an affirmative act, the government had to prove an act\\n\\ndesigned to “mislead or conceal” within the six-year period of limitations.\\n\\nUnited States v. Thompson, 518 F.3d 832, 852 (10th Cir. 2008); see United\\n\\nStates v. Anderson, 319 F.3d 1218, 1219 (10th Cir. 2003) (holding that\\n\\nwhen a defendant commits a series of affirmative acts over multiple years,\\n\\nthe six-year period of limitations for tax evasion begins with the last\\n\\naffirmative act). The government bore the burden to prove that Mrs. Yurek\\n\\nhad committed at least one affirmative act. United States v. Hoskins, 654\\n\\nF.3d 1086, 1091 (10th Cir. 2011). The jury could have reasonably found\\n\\nthat the government had satisfied this burden.\\n\\n a. “Affirmative acts” are broadly defined.\\n\\n We first consider what constitutes an affirmative act. Federal law\\n\\nsuggests an expansive definition, stating that tax evasion can be committed\\n\\nby evading taxes “in any manner.” 26 U.S.C. § 7201; see Boisseau, 841\\n\\nF.3d at 1125 (“[T]he type of affirmative conduct that can constitute an\\n\\naffirmative act of evasion is broad.”). Affirmative acts thus include\\n\\n concealing assets,\\n 4\\n\\f covering up sources of income, and\\n\\n engaging in misleading or concealing conduct.\\n\\nBoisseau, 841 F.3d at 1125. Affirmative acts may even consist of otherwise\\n\\nlawful conduct if the acts are committed with an intent to evade taxes. Id.;\\n\\nUnited States v. Gorrell, No. 18-5041, 2019 WL 1890971 at *5 (10th Cir.\\n\\nApr. 29, 2019).\\n\\n b. The evidence sufficed for a finding that Mrs. Yurek had\\n committed an affirmative act.\\n\\n Viewed in the light most favorable to the government, the trial\\n\\nevidence allowed a reasonable jury to find affirmative acts involving (1)\\n\\npayment of personal expenses from business accounts and (2) submission\\n\\nof false tax documents to the IRS.\\n\\n i. The jury could have reasonably found that Mrs. Yurek had\\n committed affirmative acts by paying her and her husband’s\\n personal expenses out of business accounts.\\n\\n Mrs. Yurek had authority to write checks on behalf of Bolder Venture\\n\\nPartners and Veracity Credit Consultants, LLC, and she used that authority\\n\\nto write business checks for her and her husband’s personal expenses. A\\n\\nfact-finder could have reasonably viewed the writing of these checks as\\n\\naffirmative acts to evade taxes.\\n\\n Some of these checks came from Bolder Venture Partners, where\\n\\nMrs. Yurek was a partner. For example, Mrs. Yurek signed a $2,309.68\\n\\n\\n\\n 5\\n\\fcheck from Bolder 3 to pay condominium-association dues for the loft where\\n\\nshe and her husband lived.\\n\\n Mrs. Yurek contends that her son, Mr. Justin Yurek, owned the loft.\\n\\nBut the trial evidence was sufficient to support findings that (1) Justin had\\n\\nbeen a “straw purchaser” and (2) Mrs. Yurek and her husband were the true\\n\\nowners of the loft. See United States v. Reese, 745 F.3d 1075, 1078 (10th\\n\\nCir. 2014) (explaining a straw purchase).\\n\\n Mrs. Yurek and her husband had been leasing the loft and living in it.\\n\\nThey had a contract to purchase the loft, but a tax lien prevented them\\n\\nfrom obtaining a mortgage. So they assigned the contract to Justin, who\\n\\npurchased the loft. Though Justin was the purchaser, Mrs. Yurek’s husband\\n\\nnegotiated the sale and used companies (over which he wielded significant\\n\\ncontrol) to fund more than $112,000 of the down payment.\\n\\n After Justin purchased the loft, Mrs. Yurek signed an affidavit on\\n\\nJustin’s behalf, stating under oath that (1) the loft would serve as Justin’s\\n\\nprimary residence and (2) Justin had no intent to lease the loft or to make\\n\\nthe purchase as an investment. 4 But Justin never lived in the loft, and Mrs.\\n\\n\\n\\n\\n3\\n Mrs. Yurek wrote the check for $2,309.68 within the six-year\\nlimitations period.\\n4\\n Despite the affidavit, Justin testified that he had bought the loft as an\\ninvestment.\\n\\n 6\\n\\fYurek and her husband continued to live there while making only\\n\\ninfrequent rental payments.\\n\\n Mrs. Yurek not only used her role at Bolder to pay condominium-\\n\\nassociation dues but also used her check-writing authority at Veracity\\n\\nCredit Consultants, LLC to pay her husband’s country-club dues and\\n\\nexpenses. For example, she signed a Veracity check for $3,403.43 to pay\\n\\nthese expenses. 5\\n\\n Veracity also paid other expenses for Mrs. Yurek and her husband.\\n\\nFor example, Veracity paid the rent on two homes that Mrs. Yurek and her\\n\\nhusband used. Veracity’s former chief financial officer, Mr. Michael\\n\\nHennigan, testified that he knew of no business purpose for these rentals or\\n\\nthe country-club dues and expenses.\\n\\n Veracity also made mortgage payments on the loft where Mrs. Yurek\\n\\nand her husband lived. The jury could reasonably infer that the Yureks\\n\\nwere trying to hide the source of these mortgage payments. For example,\\n\\nthey recorded the mortgage payments under an account designated as a\\n\\nloan account for Mrs. Yurek’s husband, but Veracity did little to collect on\\n\\nthe purported loan.\\n\\n Bolder and Veracity paid these various personal expenses for Mrs.\\n\\nYurek and her husband while they\\n\\n owed substantial taxes and penalties to the IRS and\\n\\n5\\n This check was signed within the six-year period of limitations.\\n 7\\n\\f tried to settle with the IRS based on their inability to pay what\\n they owed.\\n\\nThese payments continued through the bankruptcy proceedings, where Mrs.\\n\\nYurek and her husband tried to discharge their federal tax debt. But Mrs.\\n\\nYurek and her husband did not tell the IRS about these payments.\\n\\n Given this combination of evidence, the jury could have reasonably\\n\\nfound that Mrs. Yurek had committed an affirmative act to evade the\\n\\npayment of taxes. See United States v. Farr, 701 F.3d 1274, 1285–86 (10th\\n\\nCir. 2012) (concluding that the defendant’s use of a corporate account to\\n\\npay for personal living expenses supported a factual finding that the\\n\\ndefendant had “willfully evaded [a tax penalty] and [had taken] affirmative\\n\\nsteps to do so”).\\n\\n ii. A reasonable jury could also have found that Mrs. Yurek\\n had committed affirmative acts by submitting false tax\\n documents to the IRS.\\n\\n Along with her husband, Mrs. Yurek submitted tax forms to the IRS\\n\\nin 2009 and 2010. On these forms, Mrs. Yurek and her husband reported\\n\\nthat their gross monthly income was $7,667. But this amount didn’t include\\n\\nBolder and Veracity’s payments for personal expenses. The jury could\\n\\nreasonably have viewed these omissions as misleading or even false.\\n\\n\\n\\n\\n 8\\n\\f Mrs. Yurek’s submission of misleading or false tax documents to the\\n\\nIRS could constitute affirmative acts. 6 See Sansone v. United States, 380\\n\\nU.S. 343, 351–52 (1965) (“[I]t is undisputed that petitioner filed a tax\\n\\nreturn and that the petitioner’s filing of a false tax return constituted a\\n\\nsufficient affirmative commission to satisfy that requirement of § 7201.”);\\n\\nUnited States v. Hoskins, 654 F.3d 1086, 1091 (10th Cir. 2011)\\n\\n(concluding that submission of a false tax return “was sufficient to\\n\\nestablish an affirmative act under § 7201”).\\n\\n 2. The evidence was sufficient to find that Mrs. Yurek had\\n acted willfully.\\n\\n To satisfy the willfulness requirement, the government had to prove a\\n\\nspecific intent to evade taxes. United States v. Payne, 978 F.2d 1177, 1182\\n\\n(10th Cir. 1992); see Hoskins, 654 F.3d at 1090 (“Under § 7201,\\n\\n‘willfulness’ means the ‘voluntary, intentional violation of a known legal\\n\\nduty.’” (quoting Cheek v. United States, 498 U.S. 192, 201 (1991))).\\n\\n The government can ordinarily establish the willfulness requirement\\n\\nthrough “circumstantial evidence or inferences arising from a defendant’s\\n\\nconduct.” United States v. Boisseau, 841 F.3d 1122, 1127 (10th Cir. 2016).\\n\\nThe willfulness requirement is “closely connected” to the affirmative-act\\n\\n\\n\\n\\n6\\n The government also argues that Mrs. Yurek’s filing of the\\nbankruptcy petition constituted an affirmative act. We need not address\\nthis argument.\\n\\n 9\\n\\frequirement, for “‘[e]vidence of affirmative acts may be used to show\\n\\nwillfulness.’” Id. (quoting United States v. Romano, 938 F.2d 1569, 1572\\n\\n(2d Cir. 1991)) (alteration in original).\\n\\n Viewed in the light most favorable to the government, the trial\\n\\nevidence was sufficient in five ways to prove Mrs. Yurek’s specific intent\\n\\nto evade taxes.\\n\\n First, a reasonable jury could have found that Mrs. Yurek had known\\n\\nof her legal obligation to pay her federal tax debt. With this finding, the\\n\\njury could reasonably have concluded that Mrs. Yurek had committed the\\n\\naffirmative acts with an intent to evade payment of her tax debt.\\n\\n Second, Mrs. Yurek represented to the IRS that she and her husband\\n\\ncouldn’t pay more than $75,000 of their tax liability based on “insufficient\\n\\nassets and income” even though they had just signed a contract to pay $1.3\\n\\nmillion for a loft. Supp. R., vol. 1, at 125, 185. Given the timing of Mrs.\\n\\nYurek’s representation to the IRS and the contract to purchase the loft, a\\n\\njury could rationally have found a specific intent to evade the tax debt.\\n\\n Third, the jury could reasonably have found that Mrs. Yurek had\\n\\narranged for Justin to purchase the loft in order to conceal her financial\\n\\ninterest in it. See pp. 6–7, above.\\n\\n Fourth, Mrs. Yurek reported to the IRS that she and her husband had\\n\\na gross monthly income of $7,667 in 2009 and 2010, but Bolder and\\n\\n\\n\\n 10\\n\\fVeracity paid monthly payments of more than $7,667 for the Yureks’\\n\\npersonal expenses.\\n\\n Fifth, Mrs. Yurek told Veracity’s accountant that her husband would\\n\\nrepay his loan account every year. He didn’t, so a jury could reasonably\\n\\nhave found that (1) Mrs. Yurek was misleading the accountant about her\\n\\nhusband’s intent to repay the loans and (2) the loan account served as a\\n\\nsham to deceive the IRS.\\n\\n The jury thus could reasonably have found that Mrs. Yurek had a\\n\\nspecific intent to evade the payment of tax debt, and this finding would\\n\\nsatisfy the requirement of willfulness. See United States v. Guidry, 199\\n\\nF.3d 1150, 1157 (10th Cir. 1999) (observing that willfulness can be\\n\\ninferred from “concealment of assets or covering up sources of income”\\n\\n(quoting Spies v. United States, 317 U.S. 492, 499 (1943))).\\n\\n Despite this evidence, Mrs. Yurek argues that she lacked expertise in\\n\\ntax matters and depended on professionals. But the jury could reasonably\\n\\nhave discounted this argument and found that Mrs. Yurek had known that\\n\\nshe was giving false information to the IRS. For example, the jury could\\n\\nhave reasonably relied on Mrs. Yurek’s accounting experience, which\\n\\nincluded handling Veracity’s payroll and accounts payable and helping to\\n\\nprepare Bolder’s tax returns in 2005, 2006, and 2007. See United States v.\\n\\nGuidry, 199 F.3d 1150, 1157 (10th Cir. 1999) (treating evidence of a\\n\\ndefendant’s accounting experience as support for a finding of willfulness).\\n\\n 11\\n\\f * * *\\n\\n For these reasons, we reject Mrs. Yurek’s challenge to the\\n\\nsufficiency of the evidence for her conviction on tax evasion. 7\\n\\n C. The evidence was sufficient to convict Mrs. Yurek of\\n bankruptcy fraud.\\n\\n Mrs. Yurek was also convicted of bankruptcy fraud. This crime\\n\\ninvolves filing a bankruptcy petition with an intent to execute, conceal, or\\n\\nattempt to execute or conceal “a scheme or artifice to defraud.” 18 U.S.C.\\n\\n§ 157(1). To obtain a conviction on this offense, the government had to\\n\\nprove three elements beyond a reasonable doubt:\\n\\n 1. Mrs. Yurek had devised or intended to devise a scheme to\\n defraud or otherwise engage in a fraudulent scheme.\\n\\n 2. Mrs. Yurek had filed a bankruptcy petition with the purpose to\\n execute or conceal the scheme or attempt to do so.\\n\\n 3. Mrs. Yurek had acted with the specific intent to defraud. 8\\n7\\n Mrs. Yurek argues that her conviction cannot stand because the\\ngovernment didn’t present expert testimony on “technical concepts such as\\nincome or assets.” Appellant’s Op. Br. at 15. We disagree and conclude\\nthat expert testimony was not necessary to assist the jury in understanding\\nthe evidence.\\n8\\n In its jury instructions on the first and third elements, the district\\ncourt referred to our circuit’s pattern jury instruction for mail fraud under\\n18 U.S.C. § 1341:\\n A “scheme to defraud” is conduct intended to or reasonably\\n calculated to deceive persons of ordinary prudence or\\n comprehension and includes a scheme to deprive another of\\n money or property. An “intent to defraud” means an intent to\\n deceive or cheat someone.\\n\\n\\n 12\\n\\fSee United States v. Spurlin, 664 F.3d 954, 964 (5th Cir. 2011) (listing the\\n\\nelements that the government must prove under § 157(1) as “(1) a specific\\n\\nintent to defraud; (2) a scheme to defraud; and (3) filing a bankruptcy\\n\\npetition to conceal or execute that scheme”). Mrs. Yurek argues that the\\n\\ntrial evidence was insufficient on the elements of bankruptcy fraud. 9 We\\n\\ndisagree.\\n\\n Viewed in the light most favorable to the government, the trial\\n\\nevidence was sufficient for a jury to reasonably find satisfaction of each\\n\\nelement. That evidence showed six pertinent facts:\\n\\n 1. Mrs. Yurek and her husband had owed a substantial tax debt to\\n the IRS.\\n\\n 2. Mrs. Yurek and her husband had filed a bankruptcy petition in\\n order to discharge that debt.\\n\\n 3. When filing the bankruptcy petition, Mrs. Yurek and her\\n husband had not told the court that Bolder and Veracity were\\n paying the Yureks’ personal expenses.\\n\\n\\nR., vol. 2, at 121–22 (citing 10th Cir. Pattern Crim. Jury Instr. § 2.56 (mail\\nfraud)). As the district court noted, courts have used § 1341 for guidance\\nwhen interpreting 18 U.S.C. § 157(1). See United States v. Milwitt, 475\\nF.3d 1150, 1155 n.5 (9th Cir. 2007) (“Most of the few courts that have\\ninterpreted 18 U.S.C. § 157 have looked to 18 U.S.C. §§ 1341 and 1343 for\\nguidance.”).\\n9\\n Mrs. Yurek also relies on the fact that the IRS and the bankruptcy\\ntrustee didn’t object to discharge of the Yureks’ tax debt. According to\\nMrs. Yurek, the absence of an objection shows that the government did not\\nprove the elements of bankruptcy fraud. We disagree. The absence of an\\nobjection could conceivably affect the weight of the evidence but not its\\nsufficiency to convict.\\n\\n 13\\n\\f 4. Bolder and Veracity had continued to pay the Yureks’ personal\\n expenses during the bankruptcy proceedings, but Mrs. Yurek\\n and her husband never told the bankruptcy court about these\\n payments.\\n\\n 5. Mrs. Yurek had been a partner at Bolder and was responsible\\n for Veracity’s accounts payable and payroll.\\n\\n 6. Mrs. Yurek had participated in obtaining the checks from\\n Bolder and Veracity for personal expenses.\\n\\nGiven the evidence of these six facts, we conclude that the jury could\\n\\nreasonably have found all of the elements of bankruptcy fraud.\\n\\nII. We reject Mrs. Yurek’s challenges to the district court’s denials\\n of her motions for severance and a new trial.\\n\\n We also reject Mrs. Yurek’s arguments that the district court should\\n\\nhave (1) severed her trial from her husband’s or (2) granted her a new trial.\\n\\n A. The district court generally enjoyed discretion on these\\n matters.\\n\\n On these issues, we apply the abuse-of-discretion standard. See\\n\\nUnited States v. Pursley, 577 F.3d 1204, 1215 (10th Cir. 2009)\\n\\n(severance); United States v. Patterson, 41 F.3d 577, 579–80 (10th Cir.\\n\\n1994) (new trial). On the refusal to sever the trial, Mrs. Yurek needed to\\n\\nshow actual prejudice. See United States v. Hack, 782 F.2d 862, 870 (10th\\n\\nCir. 1986) (“To establish that a court abused its discretion, a defendant\\n\\nmust show actual prejudice to him resulting from a denial of his request for\\n\\nseverance.”).\\n\\n\\n 14\\n\\f To satisfy this burden, Mrs. Yurek needed to show a “serious risk”\\n\\nthat joinder would compromise a specific trial right or prevent a reliable\\n\\ndetermination of guilt. Pursley, 577 F.3d at 1215. Mrs. Yurek argues both,\\n\\nasserting that joinder\\n\\n created prejudice through a spillover effect from the evidence\\n of her husband’s guilt and\\n\\n violated the Sixth Amendment and created further prejudice by\\n preventing her from confronting her husband about his out-of-\\n court statement in bankruptcy court. 10\\n\\nIn our review of her Sixth Amendment theory, we engage in de novo\\n\\nreview. United States v. Clark, 717 F.3d 790, 813 (10th Cir. 2013).\\n\\n B. Mrs. Yurek has not shown actual prejudice from\\n introduction of the evidence against her husband.\\n\\n Mrs. Yurek contends that her trial should have been severed from her\\n\\nhusband’s because\\n\\n the evidence against her was slim in comparison to the\\n evidence against her husband and\\n\\n the jury could not have followed the district court’s instruction\\n to separately consider the evidence against her and her\\n husband.\\n\\n\\n10\\n In a footnote, Mrs. Yurek also suggests that the government violated\\nFederal Rule of Evidence 403 by using her husband’s out-of-court\\nstatement against her. Mrs. Yurek’s passing reference to Rule 403 does not\\nconstitute adequate briefing of a distinct issue. See Adler v. Wal-Mart\\nStores, Inc., 144 F.3d 664, 679 (10th Cir. 1998) (“Arguments inadequately\\nbriefed in the opening brief are waived.”); COPE v. Kan. State Bd. of\\nEduc., 821 F.3d 1215, 1219 n.4 (10th Cir. 2016) (concluding that “passing\\nreferences” to an issue do not constitute adequate briefing).\\n\\n 15\\n\\fWe conclude that the district court acted within its discretion by rejecting\\n\\nthese arguments.\\n\\n Federal courts generally prefer to jointly try defendants who were\\n\\nindicted together. Zafiro v. United States, 506 U.S. 534, 537 (1993). This\\n\\npreference is based on recognition that\\n\\n joint trials “promote efficiency and serve the interests of\\n justice by avoiding the scandal and inequity of inconsistent\\n verdicts” 11 and\\n\\n joint trials are ordinarily more efficient in cases where the\\n evidence against multiple defendants is “overlapping and\\n intertwined.” 12\\n\\n Mrs. Yurek tries to skirt this preference based on the alleged\\n\\nspillover of evidence against her husband. But severance is not warranted\\n\\nby “a mere allegation that defendant would have a better chance of\\n\\nacquittal in a separate trial” or “a complaint of the ‘spillover effect’ from\\n\\nthe evidence that was overwhelming or more damaging against the co-\\n\\ndefendant than that against the moving party.” United States v. Hack, 782\\n\\nF.2d 862, 870 (10th Cir. 1986); see United States v. Wardell, 591 F.3d\\n\\n1279, 1300 (10th Cir. 2009) (“[T]he nearly insuperable rule in this circuit\\n\\nis that a defendant cannot obtain severance simply by showing that the\\n\\n\\n\\n\\n11\\n Zafiro, 506 U.S. at 537 (internal quotation marks omitted).\\n12\\n United States v. Morales, 108 F.3d 1213, 1220 (10th Cir. 1997).\\n\\n\\n 16\\n\\fevidence against a co-defendant is more damaging than the evidence\\n\\nagainst herself.” (internal quotation marks omitted)). So Mrs. Yurek’s\\n\\ncomplaints about the strength of the trial evidence against her husband do\\n\\nnot warrant severance.\\n\\n Coupled with the preference for joint trials is the district court’s\\n\\nguidance to the jury. The court instructed the jury\\n\\n that it “must separately consider the evidence against each\\n defendant and return a separate verdict for each” and\\n\\n that its “verdict as to one defendant . . . should not affect [its]\\n verdict as to the other defendant.”\\n\\nR., vol. 2, at 113. These instructions, which the jury presumably followed,\\n\\nnegated the risk of prejudice to Mrs. Yurek from the joint trial. See Weeks\\n\\nv. Angelone, 528 U.S. 225, 234 (2000) (“A jury is presumed to follow its\\n\\ninstructions.”); Wardell, 591 F.3d at 1301 (noting that the district court’s\\n\\njury instruction “to give separate and individual consideration to each\\n\\ncharge against each defendant” and the district court’s other cautionary\\n\\nstatements to the jury “negated any risk of prejudice” to the defendant\\n\\nfrom the joint trial). We thus conclude that the district court acted within\\n\\nits discretion by denying Mrs. Yurek’s motions to sever the trial and to\\n\\ngrant a new trial.\\n\\n\\n\\n\\n 17\\n\\f C. The district court’s refusal to sever the trial did not violate\\n Mrs. Yurek’s right to confrontation because her husband’s\\n out-of-court statement had not been testimonial.\\n\\n Mrs. Yurek contends that the refusal to sever the trial violated her\\n\\nright to confrontation by allowing the government to use the husband’s\\n\\nout-of-court statement against her. But the Sixth Amendment applies only\\n\\nwhen the out-of-court statement is testimonial. 13 See United States v.\\n\\nClark, 717 F.3d 790, 815 (10th Cir. 2013) (observing that the Sixth\\n\\nAmendment’s Confrontation Clause applies only if a statement is\\n\\n“testimonial”). Statements in furtherance of a conspiracy are\\n\\nnontestimonial, so they are admissible even when the defendants cannot\\n\\nconfront the declarants. United States v. Patterson, 713 F.3d 1237, 1247\\n\\n(10th Cir. 2013); see Crawford v. Washington, 541 U.S. 36, 56 (2004)\\n\\n\\n13\\n We have supplied “two possible definitions” for what constitutes a\\n“testimonial” statement:\\n\\n 1. “a formal declaration made by the declarant that, when\\n objectively considered, indicates the primary purpose for which\\n the declaration was made was that of establishing or proving\\n some fact potentially relevant to a criminal prosecution” and\\n\\n 2. “[a] formal statement [such that] a reasonable person in the\\n position of the declarant would objectively foresee that the\\n primary purpose of the statement was for use in the\\n investigation or prosecution of a crime.”\\n\\nUnited States v. Clark, 717 F.3d 790, 816 (10th Cir. 2013) (alterations in\\noriginal) (quoting United States v. Smalls, 605 F.3d 765, 778 (10th Cir.\\n2010)).\\n\\n\\n 18\\n\\f(observing that statements in furtherance of a conspiracy are not\\n\\ntestimonial).\\n\\n Prior to trial, the district court concluded that Mr. Yurek’s out-of-\\n\\ncourt statement 14 was admissible against Mrs. Yurek as a statement by a\\n\\ncoconspirator. To qualify for admissibility as a coconspirator statement,\\n\\nthe statement must have been made during and in furtherance of a\\n\\nconspiracy. Fed. R. Evid. 801(d)(2)(E).\\n\\n Mrs. Yurek does not challenge the district court’s admissibility\\n\\ndetermination, so we regard the husband’s out-of-court statement as\\n\\nnontestimonial. Introduction of this nontestimonial statement against Mrs.\\n\\nYurek did not violate the Sixth Amendment. See Patterson, 713 F.3d at\\n\\n1247 (concluding that statements made in furtherance of a conspiracy were\\n\\nproperly admitted because they were nontestimonial).\\n\\n D. Mrs. Yurek has not demonstrated that her husband would\\n have been willing to testify at a severed trial.\\n\\n Mrs. Yurek also contends that if the trial had been severed, she could\\n\\nhave cross-examined her husband about his out-of-court statement. 15 But\\n\\nMrs. Yurek never presented evidence that her husband would have testified\\n\\n\\n14\\n He made the statement in bankruptcy court; but for purposes of\\nadmissibility, the pertinent court is the federal district court in Mrs.\\nYurek’s trial.\\n15\\n The parties dispute whether Mrs. Yurek preserved this argument. For\\nthe sake of argument, we assume preservation.\\n\\n 19\\n\\fat a severed trial. Indeed, Mrs. Yurek concedes that she does not know\\n\\nwhether he would have done so. Appellant’s Op. Br. at 27. The resulting\\n\\nuncertainty is fatal to Mrs. Yurek’s contention. See United States v.\\n\\nPursley, 577 F.3d 1204, 1216 (10th Cir. 2009) (upholding the denial of a\\n\\nmotion to sever because the defendant did not submit affidavits from his\\n\\nco-defendants regarding their willingness to testify at a severed trial);\\n\\nUnited States v. Dirden, 38 F.3d 1131, 1141 n.13 (10th Cir. 1994)\\n\\n(upholding the denial of the defendant’s motion to sever based on the lack\\n\\nof evidence that the co-defendant would have given exculpatory\\n\\ntestimony).\\n\\n * * *\\n\\n For these reasons, we conclude that the district court acted within its\\n\\ndiscretion in denying Mrs. Yurek’s motions for severance and a new trial.\\n\\nIII. We reject Mrs. Yurek’s challenge based on multiplicity.\\n\\n Mrs. Yurek insists that she was convicted of multiplicitous charges:\\n\\ntax evasion and bankruptcy fraud. Charges are multiplicitous when they\\n\\ncover the same criminal conduct. United States v. McCullough, 457 F.3d\\n\\n1150, 1162 (10th Cir. 2006). On challenges involving multiplicity, we\\n\\ngenerally engage in de novo review. United States v. McIntosh, 124 F.3d\\n\\n1330, 1336 (10th Cir. 1997). But Mrs. Yurek did not raise the issue in a\\n\\n\\n\\n\\n 20\\n\\fpretrial motion, so we review her argument only for plain error. Id. We\\n\\nconclude that there was no error, plain or otherwise.\\n\\n The Fifth Amendment forbids convictions on multiplicitous charges.\\n\\nMcCullough, 457 F.3d at 1162. But under the Blockburger test, the same\\n\\nconduct can trigger prosecution for multiple crimes “if each crime requires\\n\\nproof of a fact that the other does not.” United States v. Berres, 777 F.3d\\n\\n1083, 1090 (10th Cir. 2015); see Blockburger v. United States, 284 U.S.\\n\\n299, 304 (1932) (“[W]here the same act or transaction constitutes a\\n\\nviolation of two distinct statutory provisions, the test to be applied to\\n\\ndetermine whether there are two offenses or only one, is whether each\\n\\nprovision requires proof of a fact which the other does not.”). We thus\\n\\nfocus on whether the elements differ for Mrs. Yurek’s crimes of tax\\n\\nevasion and bankruptcy fraud. See Illinois v. Vitale, 447 U.S. 410, 416\\n\\n(1980) (analyzing the elements of the crimes of conviction when applying\\n\\nthe Blockburger test).\\n\\n A conviction for tax evasion requires proof of three elements:\\n\\n 1. The defendant owed a substantial tax to the IRS.\\n\\n 2. The defendant committed “an affirmative act constituting an\\n evasion or attempted evasion” of assessment or payment of the\\n tax.\\n\\n 3. The defendant willfully evaded or attempted to evade the\\n assessment or payment of the tax.\\n\\n\\n\\n\\n 21\\n\\fUnited States v. Boisseau, 841 F.3d 1122, 1125 (10th Cir. 2016) (citing\\n\\nSansone v. United States, 380 U.S. 343, 351 (1965)). A conviction for\\n\\nbankruptcy fraud also requires proof of three elements:\\n\\n 1. The defendant devised or intended to devise a scheme to\\n defraud or otherwise engage in a fraudulent scheme.\\n\\n 2. For the purpose of executing or concealing the scheme or\\n attempting to do so, the defendant filed a petition under the\\n Bankruptcy Code.\\n\\n 3. The defendant acted with the specific intent to defraud.\\n\\nUnited States v. Spurlin, 664 F.3d 954, 964 (5th Cir. 2011). As Mrs. Yurek\\n\\nadmits, each crime requires proof of an element that the other crime does\\n\\nnot. We thus would not ordinarily consider the two counts multiplicitous.\\n\\n But Mrs. Yurek argues that the government’s theory essentially\\n\\nrequired the same elements for both crimes because the government\\n\\ncharacterized the bankruptcy fraud as a scheme to evade taxes. To support\\n\\nthis argument, Mrs. Yurek points to the indictment, contending that the\\n\\nindictment shows that both counts stemmed from the same underlying\\n\\nconduct. But the Blockburger test “focuses on the proof necessary to prove\\n\\nthe statutory elements of each offense, rather than on the actual evidence\\n\\nto be presented at trial.” Illinois v Vitale, 447 U.S. 410, 416 (1980). Given\\n\\nthe focus of this test, Mrs. Yurek’s argument fails because the nature of the\\n\\ncharges does not alter the elements that the government needed to prove.\\n\\n\\n\\n\\n 22\\n\\f To argue that she was convicted of multiplicitous charges, Mrs.\\n\\nYurek also relies on United States v. McIntosh, 124 F.3d 1330 (10th Cir.\\n\\n1997). In McIntosh we acknowledged that “Congress undoubtedly may\\n\\nsubject a defendant to multiple convictions and punishments for the same\\n\\nact,” but we held that Congress did not intend to subject the defendant to\\n\\nconvictions for both 18 U.S.C. § 152(3) (making a false statement) and 18\\n\\nU.S.C. § 152(7) (concealing assets). 124 F.3d at 1336–37.\\n\\n But Mrs. Yurek was not convicted of violating either § 152(3) or\\n\\n§ 152(7), so McIntosh does not control. And unless Congress expresses a\\n\\ncontrary intent, “we presume . . . that Congress intended multiple\\n\\nconvictions and sentences for the same criminal behavior which violates\\n\\nmore than one statute when each statute requires proof of a fact that the\\n\\nother does not.” United States v. Benoit, 713 F.3d 1, 12 (10th Cir. 2013).\\n\\n Mrs. Yurek has not pointed to any evidence that Congress expressed\\n\\nan intent to preclude a conviction for both tax evasion and bankruptcy\\n\\nfraud. Mrs. Yurek’s reliance on McIntosh is thus misguided, and we\\n\\nconclude that the charges were not multiplicitous.\\n\\nIV. The district court erroneously calculated the guideline range by\\n applying the wrong test for a mitigating-role adjustment.\\n\\n Mrs. Yurek contends that the district court\\n\\n should have applied Sentencing Guideline § 2T1.1 to her\\n conviction for bankruptcy fraud,\\n\\n incorrectly calculated the loss attributable to her, and\\n 23\\n\\f applied the wrong test for a mitigating-role adjustment.\\n\\nWe agree that the district court erred in deciding whether to grant Mrs.\\n\\nYurek a mitigating-role adjustment. But the court did not otherwise err at\\n\\nsentencing.\\n\\n A. Sentencing Guideline § 2T1.1 does not apply to Mrs.\\n Yurek’s conviction for bankruptcy fraud.\\n\\n To calculate the guideline range, the district court must select the\\n\\napplicable guideline (if one exists) for the offense of conviction. U.S.S.G.\\n\\n1B1.2(a) (2016). 16 Here the parties agree that the relevant offense of\\n\\nconviction was bankruptcy fraud under 18 U.S.C. § 157(1). For this\\n\\noffense, however, the Sentencing Commission has not expressly adopted a\\n\\nguideline. When the Sentencing Commission has not specified the\\n\\napplicable guideline, the district court must “apply the most analogous\\n\\noffense guideline.” U.S.S.G. § 2X5.1 (2016). This process involves two\\n\\nsteps. The court begins by determining which guidelines are sufficiently\\n\\nanalogous; from these guidelines, the court then selects the most analogous\\n\\n\\n\\n\\n16\\n The 2016 version was in effect at the time of Mrs. Yurek’s\\nsentencing. See U.S.S.G. § 1B1.11(a) (2016) (Ordinarily, “[t]he court shall\\nuse the Guidelines Manual in effect on the date that the defendant is\\nsentenced.”).\\n\\n\\n 24\\n\\fone. 17 Id. § 2X5.1 cmt.; United States v. Nichols, 169 F.3d 1255, 1270–71\\n\\n(10th Cir. 1999).\\n\\n The district court assumed for the sake of argument that both § 2T1.1\\n\\nand § 2B1.1 were “sufficiently analogous” to bankruptcy fraud under 18\\n\\nU.S.C. § 157(1). The district court then concluded that § 2B1.1 was the\\n\\nmore analogous guideline.\\n\\n The parties agree that § 2B1.1 is sufficiently analogous to\\n\\nbankruptcy fraud under 18 U.S.C. § 157(1). 18 But the parties disagree over\\n\\nwhether § 2T1.1 is also sufficiently analogous to bankruptcy fraud. To\\n\\ndetermine whether § 2T1.1 is “sufficiently analogous” to bankruptcy fraud,\\n\\nwe compare the elements of bankruptcy fraud under 18 U.S.C. § 157(1)\\n\\n\\n\\n\\n17\\n If there is not a sufficiently analogous guideline, 18 U.S.C. § 3553\\nwould control. U.S.S.G. § 2X5.1 cmt. (2016).\\n18\\n Section 2B1.1 covers crimes of fraud and deceit. Two of the crimes\\ncovered by § 2B1.1 are mail fraud and wire fraud. See U.S.S.G. App’x A\\n(2016) (identifying 18 U.S.C. §§ 1341 and 1343 as covered by § 2B1.1).\\nThe statutes for these crimes served as the model for § 157. See United\\nStates v. Milwitt, 475 F.3d 1150, 1155 (9th Cir. 2007). Like § 157, both\\nmail fraud and wire fraud include as elements (1) a scheme or artifice to\\ndefraud and (2) the specific intent to defraud. Compare United States v.\\nSpurlin, 664 F.3d 954, 964 (5th Cir. 2011) (listing the elements for\\nbankruptcy fraud under § 157(1)), with United States v. Welch, 327 F.3d\\n1081, 1104 (10th Cir. 2003) (listing the elements for mail fraud and wire\\nfraud).\\n\\n\\n 25\\n\\fwith the elements of the offenses covered by § 2T1.1. See United States v.\\n\\nNichols, 169 F.3d 1255, 1270 (10th Cir. 1999). 19\\n\\n Section 2T1.1 relates to matters of taxation. Thus, all of the crimes\\n\\nexpressly covered by § 2T1.1 involve taxation:\\n\\n evading taxes (26 U.S.C. § 7201),\\n\\n willfully failing to file a tax return, keep records, supply\\n information, or pay a tax (26 U.S.C. § 7203),\\n\\n making false or fraudulent statements to the IRS (26 U.S.C.\\n § 7206(1), (3), (4), and (5)),\\n\\n willfully filing a fraudulent return, statement, or other\\n document (26 U.S.C. § 7207),\\n\\n making false statements to purchasers or lessees relating to a\\n tax (26 U.S.C. § 7211), and\\n\\n attempting to interfere with the administration of the tax laws\\n (26 U.S.C. § 7212(a)).\\n\\nU.S.S.G. App’x A (2016).\\n\\n Because these crimes target taxation, they contrast starkly with\\n\\nbankruptcy fraud. Bankruptcy fraud requires specific intent to defraud, 20\\n\\nand the § 2T1.1 crimes require specific intent only with regard to the tax\\n\\nlaws. For example, tax evasion under 26 U.S.C. § 7201 requires proof that\\n\\n\\n19\\n Because the district court didn’t decide this issue, we use our\\nindependent judgment on this legal issue. Cf. Nichols, 169 F.3d at 1270\\n(stating that determination of the first step is “purely legal,” requiring de\\nnovo review).\\n20\\n United States v. Spurlin, 664 F.3d 954, 964 (5th Cir. 2011).\\n\\n 26\\n\\fa defendant had the “specific intent to evade taxes.” United States v.\\n\\nPayne, 978 F.2d 1177, 1182 (10th Cir. 1992). A violation of 26 U.S.C.\\n\\n§ 7203 occurs only if a defendant “willfully fails” to pay a tax, file a\\n\\nreturn, keep tax records, or supply tax-related information. And a\\n\\nconviction under 26 U.S.C. § 7206(4) requires the government to prove\\n\\nthat a defendant hid taxable property “with intent to evade or defeat the\\n\\nassessment or collection” of a tax. So the specific-intent element for\\n\\nbankruptcy fraud sweeps beyond the specific-intent elements found in\\n\\n§ 2T1.1 crimes.\\n\\n Nor is there a match between § 2T1.1 and bankruptcy fraud’s first\\n\\nelement (scheme to defraud). See United States v. Spurlin, 664 F.3d 954,\\n\\n964 (5th Cir. 2011). It is true that many of the crimes covered by § 2T1.1\\n\\ntarget fraudulent conduct. But § 2T1.1’s fraud crimes again relate only to\\n\\nthe tax laws:\\n\\n 1. making false or fraudulent statements to the IRS (26 U.S.C.\\n § 7206(1)),\\n\\n 2. making false statements regarding a tax to purchasers or lessees\\n (26 U.S.C. § 7211),\\n\\n 3. filing false or fraudulent documents with the IRS (26 U.S.C.\\n § 7207),\\n\\n 4. concealing taxable property from the IRS (26 U.S.C.\\n §§ 7206(4) and 7206(5)), and\\n\\n 5. falsely or fraudulently executing or signing documents required\\n by the provisions of the Internal Revenue Code or regulations\\n issued under those provisions (26 U.S.C. § 7206(3)).\\n\\n 27\\n\\fSee p. 26, above. Unlike these crimes, bankruptcy fraud targets a scheme to\\n\\ndefraud unrelated to taxation or the administration of the federal tax laws.\\n\\nSo the fraudulent conducted covered by bankruptcy fraud sweeps beyond\\n\\nthe fraudulent conduct covered by § 2T1.1.\\n\\n Because the elements of § 2T1.1 crimes are narrower than and largely\\n\\nunrelated to the elements of bankruptcy fraud, we conclude that § 2T1.1 is\\n\\nnot sufficiently analogous to bankruptcy fraud. Thus the only potentially\\n\\napplicable guideline was § 2B1.1, and the district court did not err by\\n\\napplying this section.\\n\\n B. The amount of intended loss attributable to Mrs. Yurek\\n could reasonably be based on the amount of debt that Mrs.\\n Yurek had tried to discharge in bankruptcy.\\n\\n At Mrs. Yurek’s sentencing, the district court applied Sentencing\\n\\nGuideline § 2B1.1 to determine Mrs. Yurek’s base-offense level and\\n\\nspecific offense characteristics. For the specific offense characteristics,\\n\\n§ 2B1.1 allowed the court to increase the base-offense level based on the\\n\\n\\n\\n\\n 28\\n\\famount of the intended loss attributable to a defendant. 21 See U.S.S.G.\\n\\n§ 2B1.1(b)(1) (2016).\\n\\n To calculate the intended loss, the district court considered two\\n\\nmethodologies:\\n\\n 1. the amount of federal tax debt that Mrs. Yurek tried to\\n discharge in bankruptcy and\\n\\n 2. the value of the assets that Mrs. Yurek concealed from the\\n bankruptcy court.\\n\\nThe court found that under either approach, the intended loss was between\\n\\n$550,000 and $1,500,000. Given this finding, the court overruled Mrs.\\n\\nYurek’s objection to the U.S. Probation Department’s recommendation of a\\n\\n14-level enhancement.\\n\\n On appeal, Mrs. Yurek argues that the loss attributable to her was\\n\\nless than $550,000 and that the district court erred in two ways when\\n\\ncalculating the intended loss:\\n\\n 1. The amount sought to be discharged in bankruptcy did not\\n constitute an appropriate methodology.\\n\\n 2. The district court miscalculated the value of the assets that had\\n been concealed from the bankruptcy court.\\n\\n We reject Mrs. Yurek’s challenge to the district court’s methodology\\n\\nfor calculating the intended loss. Determining this methodology involves a\\n\\n\\n21\\n Under § 2B1.1, “loss is the greater of actual loss or intended loss.”\\nU.S.S.G. § 2B1.1 cmt. n.3(A) (2016). The parties agree that the applicable\\nmeasure of loss is intended loss because there was no actual loss.\\n\\n 29\\n\\flegal conclusion, so we engage in de novo review. See United States v.\\n\\nGordon, 710 F.3d 1124, 1160–61 (10th Cir. 2013) (stating that we engage\\n\\nin de novo review of the district court’s methodology for calculating loss\\n\\nunder § 2B1.1(b)). Engaging in de novo review, we start with the\\n\\napplicable guideline and related application notes. The application notes\\n\\nfor § 2B1.1 define “intended loss” as a loss that a defendant “purposely\\n\\nsought to inflict.” U.S.S.G. § 2B1.1 cmt. n.3(A)(ii)(I) (2016); see United\\n\\nStates v. Manatau, 647 F.3d 1048, 1050 (10th Cir. 2011) (Gorsuch, J.)\\n\\n(“Something is intended if it is done on purpose—not merely known,\\n\\nforeseen, or just possible or potentially contemplated.”). 22 We must follow\\n\\nthis definition of intended loss because it is not plainly erroneous,\\n\\ninconsistent with § 2B1.1, or violative of the U.S. Constitution or a federal\\n\\nstatute. United States v. Mojica, 214 F.3d 1169, 1171 (10th Cir. 2000).\\n\\n Applying this definition, we conclude that the intended loss equals\\n\\nthe monetary harm that Mrs. Yurek wanted to cause her creditors. See\\n\\nUnited States v. Holthaus, 486 F.3d 451, 455 (8th Cir. 2007) (“When\\n\\ndetermining intended loss [in the bankruptcy context], we look to the\\n\\n\\n\\n\\n22\\n In Manatau, we interpreted the phrase “intended loss” in a prior\\nversion of § 2B1.1 to mean “a loss the defendant purposely sought to\\ninflict.” Manatau, 647 F.3d at 1050 (emphasis in original). The Sentencing\\nCommission later amended § 2B1.1 to reflect this holding. See U.S.S.G.\\namend. 792 (eff. Nov. 1, 2015), available at U.S.S.G. supp. to app. C 108–\\n12 (2016 ) .\\n\\n 30\\n\\famount of loss a defendant actually intended to cause his creditors.”);\\n\\nUnited States v. Bussell, 504 F.3d 956, 962 (9th Cir. 2007) (“When\\n\\ndetermining intended loss [in the bankruptcy context], we must look to the\\n\\namount of loss that [the defendant] intended to cause her creditors.”).\\n\\n These creditors included the IRS, so the intended loss includes the\\n\\namount of federal tax debt that Mrs. Yurek tried to discharge in\\n\\nbankruptcy. That discharge would have extinguished Mrs. Yurek’s federal\\n\\ntax debt, causing a loss to the IRS. See United States v. Mutuc, 349 F.3d\\n\\n930, 937 (7th Cir. 2003) (“A successful discharge in bankruptcy would\\n\\nhave left the creditors without recourse against Mutuc; it follows that\\n\\nMutuc intended a loss equal to the amount to be discharged in\\n\\nbankruptcy.”).\\n\\n In similar circumstances, other circuits have ordinarily allowed\\n\\ncalculation of the intended loss based on the amount of debt that the\\n\\ndefendant was trying to discharge, though the circuits have taken somewhat\\n\\ndifferent approaches. For example, the Seventh Circuit has flatly stated\\n\\nthat it allows measurement of the intended loss based on the amount that\\n\\nthe defendant sought to discharge in bankruptcy. See United States v.\\n\\nArthur, 582 F.3d 713, 720–21 (7th Cir. 2009); United States v. Mutuc, 349\\n\\nF.3d 930, 936–37 (7th Cir. 2003); United States v. Holland, 160 F.3d 377,\\n\\n381 (7th Cir. 1998). On the other hand, the Ninth Circuit allows the district\\n\\ncourt to consider the economic realities in each case and use discretion in\\n\\n 31\\n\\fdetermining whether to calculate the intended loss based on the entire\\n\\namount to be discharged or the value of concealed assets. See United States\\n\\nv. Bussell, 504 F.3d 956, 961–62 (9th Cir. 2007). And the Eighth Circuit\\n\\nhas suggested that the intended loss can equal the entire amount that the\\n\\ndefendants are trying to discharge only if the fraud had created the illusion\\n\\nof dischargeability. See United States v. Holthaus, 486 F.3d 451, 455 (8th\\n\\nCir. 2007).\\n\\n All of these approaches support the district court’s decision to\\n\\ncalculate the intended loss attributable to Mrs. Yurek based on the amount\\n\\nof tax debt ($1.2 million) that Mrs. Yurek was trying to discharge in\\n\\nbankruptcy. So regardless of whether we consider the economic realities or\\n\\nthe illusion of dischargeability, the district court did not err in calculating\\n\\nthe intended loss based on the amount that Mrs. Yurek had tried to\\n\\ndischarge in bankruptcy.\\n\\n Of course, Mrs. Yurek couldn’t succeed in causing this loss because\\n\\nonce she committed tax evasion, the entire tax debt became\\n\\nnondischargeable. See 18 U.S.C. § 523(a)(1)(C). But a loss can be intended\\n\\neven when it is improbable or impossible. U.S.S.G. § 2B1.1 cmt. n.3(A)(ii)\\n\\n(2016). 23\\n\\n\\n23\\n We have stated that a loss is intended only if (1) “the defendant\\nrealistically intended a particular loss” or (2) such a loss was probable.\\nUnited States v. Swanson, 360 F.3d 1155, 1168 (10th Cir. 2004); United\\n\\n 32\\n\\f Mrs. Yurek disagrees, relying on United States v. Holthaus, 486 F.3d\\n\\n451 (8th Cir. 2002). There, however, the Eighth Circuit expressly\\n\\ndisavowed a blanket prohibition against calculation of intended loss based\\n\\non the amount that the defendant had tried to discharge in bankruptcy.\\n\\nHolthaus, 486 F.3d at 455; see p. 32, above. Given the pinpoint citation in\\n\\nMrs. Yurek’s opening appeal brief, Mrs. Yurek is apparently intending to\\n\\nrely on the Holthaus panel’s discussion of a prior opinion, United States v.\\n\\nWheeldon, 313 F.3d 1070 (8th Cir. 2002). There the Eighth Circuit\\n\\naddressed the proper method for calculating intended loss when the amount\\n\\nof the attempted discharge exceeds the value of the concealed assets.\\n\\nWheeldon, 313 F.3d at 1072. Applying the 2000 version of the U.S.\\n\\nSentencing Guidelines, the Eighth Circuit concluded that this situation\\n\\nrequired the district court to calculate the intended loss based on the value\\n\\nof the concealed assets. Id.\\n\\n In reaching this conclusion, the Eighth Circuit didn’t apply the term\\n\\n“intended loss;” the court instead applied the term “probable intended\\n\\n\\n\\n\\nStates v. Schild, 269 F.3d 1198, 1200 (10th Cir. 2001). We later\\ncharacterized the reference to “probable” loss as “dicta” based on\\n“questionable authority.” United States v. Baum, 555 F.3d 1129, 1134\\n(10th Cir. 2009). That “questionable authority” was United States v. Smith,\\n951 F.2d 1164 (10th Cir. 1991), which had relied on guideline language\\nthat was later deleted. See Baum, 555 F.3d at 1134–35 (discussing the\\norigin of the language in Swanson and Schild and later changes to the\\nsentencing guidelines) .\\n\\n 33\\n\\floss.” Id. But the Sentencing Commission amended the applicable\\n\\ndefinition of “intended loss” in 2001, providing that a loss can be intended\\n\\neven when it is unlikely or impossible. U.S.S.G. amend. 617 (eff. Nov. 1,\\n\\n2001), available at U.S.S.G. app. C vol. II at 117 (2016) (“The amendment\\n\\nresolves the conflict to provide that intended loss includes unlikely or\\n\\nimpossible losses that are intended, because their inclusion better reflects\\n\\nthe culpability of the offender.”); see p. 32 & note 23, above. Given the\\n\\nchange in definition, the nondischargeability of Mrs. Yurek’s tax debt does\\n\\nnot affect the available methods to calculate intended loss.\\n\\n Mrs. Yurek listed a tax debt of $1.2 million in her bankruptcy\\n\\npetition, requesting that it be discharged. And her husband, who also\\n\\nsigned the bankruptcy petition, stated in bankruptcy court that he and his\\n\\nwife had filed the bankruptcy petition in order to discharge their $1.2\\n\\nmillion tax debt. Given this evidence, the court could calculate the\\n\\nintended loss attributable to Mrs. Yurek based on the amount of tax debt\\n\\nthat she had tried to discharge.\\n\\n * * *\\n\\n We conclude that the district court appropriately calculated the\\n\\nintended loss attributable to Mrs. Yurek based on the amount of tax debt\\n\\nthat she had tried to discharge in bankruptcy. Thus, the district court did\\n\\nnot err in applying the 14-level sentencing enhancement.\\n\\n\\n\\n 34\\n\\f C. The district court plainly erred by applying the wrong test\\n for a mitigating-role adjustment.\\n\\n Mrs. Yurek also argues that the district court applied the wrong test\\n\\nwhen deciding not to grant a downward adjustment for a mitigating role.\\n\\nWe agree.\\n\\n 1. Preservation and the Argument for Plain Error\\n\\n The government contends that Mrs. Yurek did not preserve the issue\\n\\nfor appeal. We agree.\\n\\n To preserve an appellate issue involving the district court’s\\n\\nexplanation for a sentence, the defendant must lodge a “contemporaneous\\n\\nobjection.” United States v. Romero, 491 F.3d 1173, 1177 (10th Cir. 2007);\\n\\nsee United States v. Lopez-Flores, 444 F.3d 1218, 1221 (10th Cir. 2006)\\n\\n(“[T]he usual reasons for requiring a contemporaneous objection apply to\\n\\nchallenges to the district court’s method of arriving at a sentence.”). At\\n\\nsentencing, the district court explained that it would deny Mrs. Yurek a\\n\\nmitigating-role adjustment because her participation in tax evasion and\\n\\nbankruptcy fraud had been “central and necessary for both . . . crimes to\\n\\ntake place.” R., vol. 5, at 1925; see also id. at 1925–26 (finding “ample\\n\\ngrounds to conclude that Ms. Yurek’s participation in these criminal\\n\\nschemes was central and necessary and that her husband could not have\\n\\nproceeded with either the tax evasion or the bankruptcy fraud without\\n\\nher”).\\n\\n\\n 35\\n\\f Mrs. Yurek argues that the district court applied the wrong test. She\\n\\nbases her argument on the district court’s explanation for denying a\\n\\nmitigating-role adjustment, but she did not raise this issue in district court.\\n\\nAccording to Mrs. Yurek, she preserved the issue by objecting to the\\n\\npresentence report. But she is alleging an error in the district court’s\\n\\nexplanation, not in the content of the presentence report. So objecting to\\n\\nthe presentence report would not have alerted the district court to an error\\n\\nin its explanation. See United States v. Mendoza, 543 F.3d 1186, 1195\\n\\n(10th Cir. 2008); 24 see also United States v. Chavez-Morales, 894 F.3d\\n\\n1206, 1213 (10th Cir. 2018) (concluding that a defendant’s sentencing\\n\\nmemorandum did not preserve an issue involving the adequacy of the\\n\\ndistrict court’s explanation). Because Mrs. Yurek did not preserve her\\n\\nargument involving correctness of the legal standard for a mitigating-role\\n\\n\\n\\n\\n24\\n In Mendoza, the government appealed the sentence, arguing that the\\ndistrict court failed to provide written reasons for its downward variance.\\n543 F.3d at 1186. We concluded that the government had forfeited this\\nappeal point by failing to alert the district court to its failure to provide\\nwritten reasons. Id. at 1195. An objection to the presentence report didn’t\\nsuffice for preservation: “Unlike other forms of sentencing error, which\\ncan be preserved for appellate review through written objections to the\\n[presentence report] or an oral objection during the sentencing hearing,\\nfailure to enter a written statement of reasons becomes apparent to the\\nparties only after the court enters its final judgment regarding the sentence\\nimposed.” Id.\\n\\n\\n 36\\n\\fadjustment, any review would be confined to the plain-error standard.\\n\\nRomero, 491 F.3d at 1178. 25\\n\\n But the government argues that Mrs. Yurek lost her opportunity to\\n\\nurge plain error by waiting until her reply brief to do so. We disagree. Mrs.\\n\\nYurek appeared to assume in her opening brief that she had preserved her\\n\\nchallenge to the denial of a mitigating-role adjustment. After the\\n\\ngovernment challenged preservation, Mrs. Yurek argued in her reply brief\\n\\nthat the error would be considered plain even if she had forfeited the issue.\\n\\nThis approach was a permissible way to invoke plain-error review. See\\n\\nUnited States v. Zander, 794 F.3d 1220, 1232 n.5 (10th Cir. 2015) (“We\\n\\nhold that Defendant adequately addressed the issue of plain error review in\\n\\nhis reply to the government’s brief, after arguing in his opening brief that\\n\\nhis objections below were sufficiently raised to be preserved for review on\\n\\nappeal.”). We thus apply the standard for plain error.\\n\\n 2. Mrs. Yurek is entitled to relief under the plain-error\\n standard.\\n\\n For Mrs. Yurek to prevail under the plain-error test, she must show\\n\\n 1. that an error took place,\\n\\n\\n\\n\\n25\\n Mrs. Yurek contends that the government induced the error by\\narguing that she had played a central and necessary role in the crimes. But\\nthe government never suggested to the district court that it apply the wrong\\nlegal test. The government simply argued against a mitigating-role\\nadjustment. Presentation of this argument did not induce the court’s error.\\n\\n 37\\n\\f 2. that the error was plain,\\n\\n 3. that it affected her substantive rights, and\\n\\n 4. that the error “seriously affects the fairness, integrity, or public\\n reputation of judicial proceedings.”\\n\\nUnited States v. Bustamante-Conchas, 850 F.3d 1130, 1137 (10th Cir.\\n\\n2017) (en banc). Mrs. Yurek has satisfied each of these prongs.\\n\\n a. The government properly conceded the first and second\\n prongs.\\n\\n The government concedes the first two prongs of the plain-error test.\\n\\nWe agree that the first two prongs are satisfied.\\n\\n A defendant who was a minimal or minor participant in criminal\\n\\nactivity is eligible for a downward adjustment. See U.S.S.G. § 3B1.2\\n\\n(2016). Finding that a defendant performed an “essential or indispensable\\n\\nrole . . . is not determinative” of eligibility for this adjustment. Id. § 3B1.2\\n\\ncmt. n.3(C). The court instead must focus on whether the defendant “is\\n\\nsubstantially less culpable than the average participant in the criminal\\n\\nactivity.” Id.; see United States v. Salazar-Samaniega, 361 F.3d 1271,\\n\\n1277 (10th Cir. 2004) (noting that a § 3B1.2 reduction is available only for\\n\\n“a defendant who plays a part in committing the offense that makes him\\n\\nsubstantially less culpable than the average participant”); United States v.\\n\\nAyers, 84 F.3d 382, 383 (10th Cir. 1996) (“Section 3B1.2 vests the district\\n\\ncourt with discretion to grant a base-offense level reduction if it finds a\\n\\n\\n\\n 38\\n\\fdefendant is less culpable relative to other participants in a given offense.”\\n\\n(internal quotation marks omitted)).\\n\\n But the district court did not consider Mrs. Yurek’s culpability\\n\\nrelative to other participants in the scheme. 26 The court instead found that\\n\\nMrs. Yurek’s role had been essential to the crimes and treated that finding\\n\\nas determinative. By failing to consider Mrs. Yurek’s relative culpability,\\n\\nthe district court applied the wrong test when denying a mitigating-role\\n\\nadjustment. As the government admits, the district court’s application of\\n\\nthe wrong test constitutes an error that was plain. Mrs. Yurek has thus\\n\\nsatisfied both the first and second prongs of the plain-error standard.\\n\\n\\n\\n\\n26\\n In the criminal scheme, only two persons were named: Mrs. Yurek\\nand her husband. But the husband was not an “average participant” because\\nhe had obtained a two-level enhancement for a leadership role in the\\ncrimes. So in this scheme, it is impossible to compare Mrs. Yurek’s\\nculpability to another “average” participant.\\n\\n Given the absence of another “average” participant in this scheme,\\nthe sentencing court must focus on (1) the degree of Mrs. Yurek’s\\nculpability relative to her husband’s and (2) the scope of the criminal\\nscheme. See United States v. Lopez, 545 F.3d 515, 517 (7th Cir. 2008)\\n(“[I]n situations where criminal activity involves only two participants\\n(and thus it is impossible to ascertain the culpability of an ‘average’\\nparticipant), the key inquiry is the degree of the defendant’s culpability\\nrelative to the other participant’s and the scope of the criminal\\nenterprise.”). With this dual focus, the court should determine whether\\nMrs. Yurek bore substantially less culpability than her husband. See id.;\\nsee also United States v. Tholl, 895 F.2d 178, 1185–86 (7th Cir. 1990)\\n(concluding that under § 3B1.2, it was not enough for the defendant to\\nprove less culpability than the sole other participant, who had been the\\n“mastermind” behind the criminal scheme).\\n 39\\n\\f b. Mrs. Yurek has satisfied the third prong of the plain-error\\n test.\\n\\n Mrs. Yurek has also satisfied the third prong of the plain-error test.\\n\\nUnder this prong, Mrs. Yurek bears the burden to show prejudice. United\\n\\nStates v. Gonzales-Huerta, 403 F.3d 727, 732–33 (10th Cir. 2005). To\\n\\nsatisfy this burden, Mrs. Yurek must show a reasonable probability\\n\\nsufficient to undermine confidence in the outcome at her sentencing.\\n\\nUnited States v Bustamante-Conchas, 850 F.3d 1130, 1138 (10th Cir. 2017)\\n\\n(en banc). Confidence in the outcome can be undermined even if Mrs.\\n\\nYurek’s showing would not satisfy the preponderance-of-the-evidence\\n\\nstandard. United States v. Dominguez Benitez, 542 U.S. 74, 83 n.9 (2004).\\n\\n Mrs. Yurek has shown prejudice from the district court’s application\\n\\nof the wrong test. The crux of § 3B1.2 is a defendant’s relative culpability.\\n\\nSee pp. 38–39, above. After denying a mitigating-role adjustment to Mrs.\\n\\nYurek, the court considered her relative culpability and downplayed her\\n\\nrole in the scheme:\\n\\n It is true that the trial evidence established that the\\n defendants used accountants and attorneys as tools to accomplish\\n the bankruptcy fraud and tax evasion schemes for which they\\n were convicted, but in the mitigation for this defendant, these\\n accountants and attorneys unambiguously testified at trial that it\\n was always Mr. Yurek, as opposed to his wife, who took the lead\\n in communicating and strategizing with them in the perpetuation\\n of these schemes.\\n\\n While it does not absolve her from her culpability for her\\n crimes, in my judgment fairness requires me to temper the\\n sentence I will impose on Ms. Yurek to reflect her passive and,\\n\\n 40\\n\\f to some degree, submissive personality when compared to her\\n husband, at least insofar as matters such as the complex criminal\\n schemes in this case are concerned.\\n\\nR., vol. 5, at 1969–70 (emphasis added). Given Mrs. Yurek’s lesser role in\\n\\nthe scheme, the district court varied downward to 27 months from the\\n\\nguideline range of 41–51 months.\\n\\n The district court justified the downward variance based in part on\\n\\nits view that Mrs. Yurek bore less culpability than her husband. If a\\n\\ndistrict court finds that a defendant is less culpable relative to other\\n\\nparticipants in a crime and varies downward from the advisory guideline\\n\\nrange based partly on that determination, a reasonable probability exists\\n\\nthat the district court would have granted a mitigating-role adjustment\\n\\nunder the correct test. See United States v. Trujillo-Terrazas, 405 F.3d\\n\\n814, 820 (10th Cir. 2005) (considering a district court’s comments at\\n\\nsentencing when determining whether the plain error prejudiced the\\n\\ndefendant); see also United States v. Sierra-Castillo, 405 F.3d 932, 942\\n\\n(10th Cir. 2005) (noting that a district court’s comments at sentencing can\\n\\nhelp a defendant satisfy the third prong of the plain-error test).\\n\\n And if the district court had granted Mrs. Yurek a mitigating-role\\n\\nadjustment, the district court’s starting point (the guideline range) would\\n\\nhave been lower. “When the court’s starting point is skewed a ‘reasonable\\n\\nprobability’ exists that its final sentence is skewed too.” United States v.\\n\\n\\n\\n 41\\n\\fSabillon-Umana, 772 F.3d 1328, 1333 (10th Cir. 2014) (Gorsuch, J.). Mrs.\\n\\nYurek has thus satisfied the third prong of the plain-error test.\\n\\n c. The fourth prong was also satisfied.\\n\\n To satisfy the fourth prong, Mrs. Yurek must show that the district\\n\\ncourt’s error “seriously affects the fairness, integrity, or public reputation\\n\\nof judicial proceedings.” United States v. Bustamante-Conchas, 850 F.3d\\n\\n1130, 1137 (10th Cir. 2017) (en banc). We conclude that Mrs. Yurek has\\n\\nmet this burden.\\n\\n When an error affects the calculation of a defendant’s guideline\\n\\nrange, the fourth prong is ordinarily satisfied when the first three prongs\\n\\nare satisfied. Rosales-Mireles v. United States, 138 S. Ct. 1897, 1908\\n\\n(2018). After all, “what reasonable citizen wouldn’t bear a rightly\\n\\ndiminished view of the judicial process and its integrity if courts refused to\\n\\ncorrect obvious errors of their own devise that threaten to require\\n\\nindividuals to linger longer in federal prison than the law demands?” Id.\\n\\n(quoting United States v. Sabillon-Umana, 772 F.3d 1328, 1333–34 (10th\\n\\nCir. 2014) (Gorsuch, J.)).\\n\\n * * *\\n\\n We conclude that the district court plainly erred by applying the\\n\\nwrong test for a mitigating-role adjustment.\\n\\n\\n\\n\\n 42\\n\\fV. Conclusion\\n\\n We affirm Ms. Yurek’s conviction, but we vacate her sentence and\\n\\nremand for resentencing. At resentencing, the district court must\\n\\nreconsider the possibility of a mitigating-role adjustment.\\n\\n\\n\\n\\n 43\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2268,"cells":{"id":{"kind":"number","value":4621589,"string":"4,621,589"},"name":{"kind":"string","value":"Charles FARRAR, Petitioner - Appellant, v. Rick RAEMISCH, Executive Director, Colorado Department of Corrections; Cynthia Coffman, Attorney General, State of Colorado ; James Falk, Warden, Sterling Correctional Facility, Respondents - Appellees. Scholars of Federal Habeas Corpus, Amicus Curiae."},"name_abbreviation":{"kind":"string","value":"Farrar v. Raemisch"},"decision_date":{"kind":"string","value":"2019-05-21"},"docket_number":{"kind":"string","value":"18-1005"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Bacharach, Baldock, Ebel\", \"parties\": \"\", \"opinions\": [{\"author\": \"BACHARACH, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 21, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\nCHARLES FARRAR,\\n\\n Petitioner - Appellant,\\n\\nv. No. 18-1005\\n\\nRICK RAEMISCH, Executive\\nDirector, Colorado Department of\\nCorrections; CYNTHIA COFFMAN,\\nAttorney General, State of\\nColorado; JAMES FALK, Warden,\\nSterling Correctional Facility,\\n\\n Respondents - Appellees.\\n\\n------------------------------\\n\\nSCHOLARS OF FEDERAL\\nHABEAS CORPUS,\\n\\n Amicus Curiae.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:15-CV-01425-RPM)\\n _________________________________\\n\\nGail K. Johnson, Johnson & Klein, PLLC, Boulder, Colorado, for the\\nPetitioner - Appellant.\\n\\nRyan A. Crane, Senior Assistant Attorney General, Denver, Colorado\\n(Cynthia H. Coffman, Attorney General, with him on the briefs), for\\nRespondents - Appellees.\\n\\fAurora Temple Barnes, Lewis Roca Rothgerber Christie, LLP, Denver,\\nColorado (Kenneth F. Rossman, IV, Lewis Roca Rothgerber Christie, LLP,\\nDenver, Colorado, with her on the briefs), for Amicus Curiae.\\n _________________________________\\n\\nBefore BACHARACH, BALDOCK, and EBEL, Circuit Judges.\\n _________________________________\\n\\nBACHARACH, Circuit Judge.\\n _________________________________\\n\\n Mr. Charles Farrar, a Colorado state prisoner, appeals the district\\n\\ncourt’s denial of his petition for habeas relief. In district court, Mr. Farrar\\n\\nclaimed\\n\\n actual innocence,\\n\\n deprivation of due process based on the recantation of a key\\n prosecution witness, and\\n\\n deprivation of due process based on a state appellate decision\\n establishing an overly restrictive standard for a new trial. 1\\n\\nThe district court denied relief, and we affirm based on three conclusions:\\n\\n 1. Actual innocence does not supply a freestanding basis for\\n habeas relief.\\n\\n 2. A private citizen’s false testimony does not violate the\\n Constitution unless the government knows that the testimony is\\n false.\\n\\n 3. The alleged error in the Colorado Supreme Court’s decision\\n does not justify habeas relief.\\n\\n\\n\\n\\n1\\n In district court, Mr. Farrar also presented other habeas claims that\\nare not relevant to this appeal.\\n\\n\\n 2\\n\\fI. Mr. Farrar is convicted and seeks post-conviction relief.\\n\\n Mr. Farrar’s convictions stemmed from complaints of sexual abuse.\\n\\nThe victim was Mr. Farrar’s stepdaughter, who complained of the alleged\\n\\nabuse when she was in the eighth grade. Based on the girl’s account, state\\n\\nofficials charged Mr. Farrar with over twenty counts. Mr. Farrar denied the\\n\\nallegations. At the trial, the girl’s testimony supplied the prosecution’s\\n\\nonly direct evidence of Mr. Farrar’s guilt. The jury found Mr. Farrar guilty\\n\\nof numerous counts of sexual assault and one count of child abuse, and the\\n\\nstate trial court sentenced Mr. Farrar to prison for a minimum of 145 years\\n\\nand a maximum of life.\\n\\n Mr. Farrar appealed. While the appeal was pending, the girl recanted\\n\\nher trial testimony. Given the recantation, the Colorado Court of Appeals\\n\\ngranted a limited remand to the trial court so that Mr. Farrar could move\\n\\nfor a new trial. After Mr. Farrar filed that motion, the trial court conducted\\n\\nevidentiary hearings, where the girl testified that she had fabricated her\\n\\nallegations of sexual abuse. Nonetheless, the trial court denied the motion\\n\\non the ground that the recantation was not credible. 2 Mr. Farrar appealed\\n\\n\\n2\\n For example, the court discounted some of the girl’s new version of\\nevents because it included other “unbelievable” and “far more heinous\\nallegation[s],” including coercion by prosecutors, law enforcement\\nofficers, and social workers during the trial. Appellant’s App’x, vol. I at\\n518. The trial court ultimately concluded: “Nothing that the Court heard or\\nsaw during this post-conviction proceeding persuades it that the newly\\ndiscovered evidence would produce a complete acquittal at a new trial. In\\n\\n\\n 3\\n\\fagain, and the Colorado Court of Appeals affirmed the denial of the motion\\n\\nfor a new trial. 3\\n\\n On certiorari, the Colorado Supreme Court affirmed. Farrar v.\\n\\nPeople, 208 P.3d 702, 709–10 (Colo. 2009). The court deferred to the trial\\n\\ncourt’s credibility determinations and clarified Colorado’s standard for a\\n\\nnew trial:\\n\\n Rather than merely creating reasonable doubt by demonstrating\\n that the recanting witness has given different and irreconcilable\\n testimony on different occasions, recantation can justify a new\\n trial only if it contains sufficiently significant new evidence, and\\n if it, rather than the witness’s inconsistent trial testimony, will\\n probably be believed.\\n\\nId. at 707–08 (internal citations omitted).\\n\\n Mr. Farrar then unsuccessfully sought post-conviction relief in state\\n\\ncourt, which led to this habeas case.\\n\\nII. We engage in de novo review without applying 28 U.S.C.\\n § 2254(d).\\n\\n In habeas cases, we engage in de novo review of the district court’s\\n\\nlegal ruling. Hooks v. Workman, 689 F.3d 1148, 1163 (10th Cir. 2012).\\n\\nWhen applying de novo review, however, we must consider the\\n\\napplicability of statutory deference under 28 U.S.C. § 2254(d). See id. This\\n\\n\\n\\nall probability, another jury would accept some of [the girl’s] contentions\\nand reject others.” Id. at 520.\\n3\\n Mr. Farrar also appealed his convictions and sentence. But those\\nparts of the appeal in state court are immaterial here.\\n\\n\\n 4\\n\\fprovision states that a federal court can grant habeas relief only if the state\\n\\nappeals court acts contrary to a Supreme Court precedent, unreasonably\\n\\napplies that precedent, or unreasonably determines the facts. 28 U.S.C.\\n\\n§ 2254(d)(1)–(2). If § 2254(d) applies, Mr. Farrar and the amici argue that\\n\\nit would be unconstitutional.\\n\\n Section 2254(d) does not apply. This section applies only when a\\n\\nstate appellate court has adjudicated the merits of a constitutional claim.\\n\\nByrd v. Workman, 645 F.3d 1159, 1164 n.7 (10th Cir. 2011); Hooks v.\\n\\nWard, 184 F.3d 1206, 1223 (10th Cir. 1999). But the Colorado Supreme\\n\\nCourt didn’t adjudicate the merits of Mr. Farrar’s constitutional claims.\\n\\nInstead, the court simply held that based on Colorado’s standard for\\n\\ngranting a new trial, the denial of Mr. Farrar’s motion had fallen within the\\n\\ntrial court’s discretion. Farrar v. People, 208 P.3d 702, 706–10 (Colo.\\n\\n2009). Because the Colorado Supreme Court didn’t adjudicate the merits of\\n\\nthe constitutional claims, we do not apply § 2254(d). 4 Hooks, 184 F.3d at\\n\\n1223.\\n\\nIII. Habeas relief cannot be based on actual innocence, a private\\n citizen’s false testimony, or the Colorado Supreme Court’s\\n definition of the state-law test for granting a new trial.\\n\\n Mr. Farrar argues that\\n\\n he is actually innocent,\\n\\n4\\n In its appeal brief, the State asserted a defense of procedural default.\\nIn oral argument, however, the State expressly waived this defense.\\n\\n\\n 5\\n\\f the girl’s false testimony violated his right to due process, and\\n\\n the Colorado Supreme Court committed a due-process violation\\n by establishing an overly restrictive standard for the grant of a\\n new trial.\\n\\nWe reject these arguments.\\n\\n A. Actual innocence and false testimony by a private citizen do\\n not entitle Mr. Farrar to habeas relief.\\n\\n Mr. Farrar alleges that he is actually innocent and his conviction was\\n\\nbased on false testimony. But even if these allegations are true, they would\\n\\nnot entitle Mr. Farrar to habeas relief.\\n\\n 1. Our precedents disallow habeas relief based on freestanding\\n claims of actual innocence.\\n\\n A distinction exists between claims of actual innocence used as a\\n\\ngateway and as a freestanding basis for habeas relief. As a gateway, a\\n\\nclaim of actual innocence “enable[s] habeas petitioners to overcome a\\n\\nprocedural bar” in order to assert distinct claims for constitutional\\n\\nviolations. McQuiggin v. Perkins, 569 U.S. 383, 386 (2013). 5 Because\\n\\ngateway claims are “procedural, rather than substantive,” they do not\\n\\n“provide a basis for relief.” Schlup v. Delo, 513 U.S. 298, 314–15 (1995).\\n\\n\\n\\n\\n5\\n For example, a showing of gateway actual innocence can allow an\\napplicant to file an otherwise-barred successive or abusive petition, to\\navoid a statute of limitations, to overcome a failure to develop facts or\\nobserve filing deadlines, or to assert a claim otherwise subject to\\nprocedural default. McQuiggin, 569 U.S. at 392–93.\\n\\n\\n 6\\n\\fBy contrast, a freestanding claim asserts actual innocence as a basis for\\n\\nhabeas relief. See House v. Bell, 547 U.S. 518, 554 (2006); Dist. Attorney’s\\n\\nOffice for Third Judicial Dist. v. Osborne, 557 U.S. 52, 71 (2009).\\n\\n The Supreme Court has repeatedly sanctioned gateway actual\\n\\ninnocence claims, but the Court has never recognized freestanding actual\\n\\ninnocence claims as a basis for federal habeas relief. To the contrary, the\\n\\nCourt has repeatedly rejected such claims, noting instead that “[c]laims of\\n\\nactual innocence based on newly discovered evidence have never been held\\n\\nto state a ground for federal habeas relief absent an independent\\n\\nconstitutional violation occurring in the underlying state criminal\\n\\nproceedings.” Herrera v. Collins, 506 U.S. 390, 400 (1993). In rejecting\\n\\nsuch claims, the Court has observed that “[f]ew rulings would be more\\n\\ndisruptive of our federal system than to provide for federal habeas review\\n\\nof freestanding claims of actual innocence.” Id. at 401. 6\\n\\n We have thus held that actual innocence does not constitute a\\n\\nfreestanding basis for habeas relief. See Vreeland v. Zupan, 906 F.3d 866,\\n\\n\\n6\\n The Supreme Court has hypothesized about the possibility of an\\nexception. See, e.g., Herrera, 506 U.S. at 417 (assuming, for the sake of\\nargument, that actual innocence might justify habeas relief in a capital\\ncase); House v. Bell, 547 U.S. 518, 554–55 (2006) (declining to resolve\\nthis issue in a capital case); Dist. Attorney’s Office for Third Judicial Dist.\\nv. Osborne, 557 U.S. 52, 71 (2009) (declining to resolve whether actual\\ninnocence justifies habeas relief in a non-capital case); McQuiggin v.\\nPerkins, 569 U.S. 383, 392 (2013) (again declining to resolve whether\\nactual innocence justifies habeas relief in a non-capital case).\\n\\n\\n 7\\n\\f883 n.6 (10th Cir. 2018) (denying a certificate of appealability because\\n\\nfreestanding assertions of actual innocence cannot support habeas relief);\\n\\nLaFevers v. Gibson, 238 F.3d 1263, 1265 n.4 (10th Cir. 2001) (“[A]n\\n\\nassertion of actual innocence . . . does not, standing alone, support the\\n\\ngranting of the writ of habeas corpus.”); Sellers v. Ward, 135 F.3d 1333,\\n\\n1339 (10th Cir. 1998) (“[T]he claim of innocence . . . itself is not a basis\\n\\nfor federal habeas corpus no matter how convincing the evidence.”). So\\n\\nMr. Farrar’s freestanding claim of actual innocence does not entitle him to\\n\\nhabeas relief.\\n\\n 2. The due-process claim (based on the girl’s false testimony)\\n fails because Mr. Farrar does not allege that the government\\n knew that the testimony was false.\\n\\n For habeas relief, Mr. Farrar must show a constitutional violation in\\n\\nhis conviction or sentence. 28 U.S.C. § 2241(c)(3). Here, he alleges a\\n\\ndenial of due process when he was convicted based on the girl’s false\\n\\ntestimony.\\n\\n The Fourteenth Amendment’s Due Process Clause prevents the\\n\\ngovernment from knowingly using perjured or false testimony at trial. See\\n\\nGiglio v. United States, 405 U.S. 150, 153–54 (1972); Napue v. People of\\n\\nState of Ill., 360 U.S. 264, 269 (1959). But here, Mr. Farrar does not allege\\n\\nthat the government knowingly elicited any false trial testimony.\\n\\nAccording to Mr. Farrar, the Second and Ninth Circuits have authorized\\n\\nhabeas relief even when the government unwittingly elicits false testimony.\\n\\n\\n 8\\n\\fSee, e.g., Hall v. Dir. of Corr., 343 F.3d 976, 981–85 (9th Cir. 2003). Mr.\\n\\nFarrar asks us to do the same.\\n\\n But we have rejected that approach. In our circuit, federal habeas\\n\\nrelief cannot be based on perjured testimony unless the government knew\\n\\nthat the testimony was false. 7 For example, when a witness testified that\\n\\nthe defendant had participated in a murder but the witness later recanted,\\n\\nwe rejected the viability of a constitutional claim, reasoning that the\\n\\n\\n\\n\\n7\\n See Graham v. Wilson, 828 F.2d 656, 659 (10th Cir. 1987) (“In our\\nhabeas corpus consideration of the introduction of false or mistaken\\ntestimony, the question of error turns not on the witness’ knowledge of\\nfalsity, but on the government’s knowledge.” (emphasis in original));\\nMcBride v. United States, 446 F.2d 229, 232 (10th Cir. 1971) (“While use\\nof perjured testimony to obtain a conviction may be grounds for vacation\\nof a conviction, the petitioner has the burden of establishing that . . . it\\nwas knowingly and intentionally used by the government to obtain a\\nconviction.”); Wild v. State of Okla., 187 F.2d 409, 410 (10th Cir. 1951)\\n(“[A] writ of habeas corpus should not be granted upon the grounds that\\nfalse and perjured testimony was used unless it is shown that it was\\nknowingly used against the defendant by the prosecuting officers in the\\ncriminal case.”); Hinley v. Burford, 183 F.2d 581, 581 (10th Cir. 1950)\\n(per curiam) (“[T]here is evidence to the effect that appellant was\\nconvicted on the false testimony of his daughter, the alleged rape. But . . .\\nthere is no testimony . . . that such testimony was knowingly and\\nintentionally used by the prosecution to obtain the conviction. The writ\\nmust therefore be denied.”); Tilghman v. Hunter, 167 F.2d 661, 662 (10th\\nCir. 1948) (stating that introduction of perjured testimony would not void a\\ncriminal judgment unless the government “knowingly, willfully, and\\nintentionally” used the perjured testimony).\\n\\n\\n\\n 9\\n\\fdefendant had “failed to assert any evidence indicating prosecutors knew\\n\\n[the witness’s] testimony was false.” 8\\n\\n Our circuit’s approach precludes habeas relief based on Mr. Farrar’s\\n\\nallegations. He alleges that the girl’s testimony was false, but he doesn’t\\n\\nallege that the government knew of the falsity. This omission is fatal\\n\\nbecause the government’s knowledge is required for a constitutional\\n\\nviolation. We thus reject Mr. Farrar’s due-process claim based on the use\\n\\nof false testimony at his trial.\\n\\n B. Mr. Farrar’s challenge to the Colorado Supreme Court’s\\n decision does not justify habeas relief.\\n\\n Mr. Farrar also contends that the Colorado Supreme Court erred in\\n\\ndefining the burden for obtaining a new trial based on recanted testimony.\\n\\nGiven that the Colorado Supreme Court relied on state law, 9 our first task\\n\\n\\n8\\n Romano v. Gibson, 239 F.3d 1156, 1175 (10th Cir. 2001); see also\\nUnited States v. Garcia, 793 F.3d 1194, 1207 (10th Cir. 2015) (“[T]his\\ncourt has repeatedly spoken of Napue claims as requiring perjury by the\\nwitness and the prosecutor’s knowledge of the falsity.” (internal citations\\nomitted)); United States v. Caballero, 277 F.3d 1235, 1243 (10th Cir.\\n2002) (“In order to establish a due process violation [under Napue], the\\n[defendants] must show that . . . the prosecution knew [the witness’s\\ntestimony] to be false.”).\\n9\\n In his direct appeal, Mr. Farrar relied solely on Colorado law. Thus,\\nthe court purported to rely only on Colorado law. In discussing the state’s\\nlimits on the right to a new trial, the court observed that the United States\\nSupreme Court “ha[d] never suggested that newly discovered evidence\\nimpeaching a guilty verdict implicates due process of law.” Farrar v.\\nPeople, 208 P.3d 702, 706 (Colo. 2009). But the court made this\\nobservation only in the course of stating that creation of the right to a new\\n\\n\\n 10\\n\\fis to interpret Mr. Farrar’s contention. An error in interpreting state law\\n\\ncannot support habeas relief, 10 but federal constitutional violations can\\n\\nordinarily support habeas relief. 11 We thus assume for the sake of argument\\n\\nthat Mr. Farrar is alleging a federal constitutional infirmity in the Colorado\\n\\nSupreme Court’s decision. If so, however, this allegation is insufficient\\n\\nbecause shortcomings in the Colorado Supreme Court’s application of state\\n\\nlaw would not entail a distinct constitutional violation.\\n\\n The Constitution does not require states to provide direct appeals.\\n\\nSee Abney v. United States, 431 U.S. 651, 656 (1977) (“[I]t is well settled\\n\\nthat there is no constitutional right to an appeal.”); United States v. Eggert,\\n\\n624 F.2d 973, 974 (10th Cir. 1980) (“It is well established that there is no\\n\\nconstitutional right to an appeal.”). But Colorado (like all other states) has\\n\\nprovided the opportunity to appeal. Here, the appeal involved the denial of\\n\\na new trial after a recantation of trial testimony. We thus inquire whether\\n\\nthe Constitution restricts how far states can go in restricting the grant of a\\n\\nnew trial based on recanted testimony. In this inquiry, we are guided by the\\n\\n\\n\\n\\ntrial under state law largely entails “a matter of policy” based on a\\nbalancing of the interests in finality, fairness, and accuracy. Id.\\n10\\n Estelle v. McGuire, 502 U.S. 62, 67 (1991).\\n11\\n See 28 U.S.C. § 2241(c)(3); see also Part III(A)(2), above.\\n\\n\\n 11\\n\\ftext of the Constitution and historical practice. Herrera v. Collins, 506\\n\\nU.S. 390, 407–08 (1993).\\n\\n The Constitution does not refer to new trials. See id. at 408 (“The\\n\\nConstitution itself, of course, makes no mention of new trials.”). They\\n\\nsprung from the common law, with judges ordering new trials to address\\n\\nparticular concerns, such as newly discovered evidence. See Francis\\n\\nWharton, Criminal Pleading & Practice 584–92 (8th ed. 1880).\\n\\n Despite the historical availability of new trials, restrictions existed\\n\\nunder the common law. For example, courts have long placed time\\n\\nconstraints on new-trial motions. Herrera, 506 U.S. at 408–11. And\\n\\ncourts—before and after ratification of the Fourteenth Amendment\\n\\n(1868)—have restricted appellate review for the denial of new trials based\\n\\non matters involving facts or evidence. See Parsons v. Bedford, Breedlove\\n\\n& Robeson, 28 U.S. 433, 447–48 (1830) (discussing the unavailability of\\n\\nappellate jurisdiction over the denial of a new trial, which would have\\n\\nrequired reexamination of the jury’s factual findings); Blitz v. United\\n\\nStates, 153 U.S. 308, 312 (1894) (“The overruling of the motion for new\\n\\ntrial is next assigned for error. We had supposed that it was well\\n\\nunderstood by the bar that the refusal of a court of the United States to\\n\\ngrant a new trial cannot be reviewed upon writ of error.” (citing cases));\\n\\nSparf v. United States, 156 U.S. 51, 175 (1895) (Gray, J., dissenting)\\n\\n(“[T]he granting or refusal of a new trial rest[ed] wholly in the discretion\\n\\n\\n 12\\n\\fof the court in which the trial was had, and [could not] be reviewed on\\n\\nerror.”). 12\\n\\n Given the Constitution’s silence on new trials and the historical\\n\\npractice under the common law, we conclude that the Constitution did not\\n\\nrequire Colorado to provide any mechanism for a new trial. See Lester\\n\\nOrfield, New Trial in Federal Criminal Cases, 2 Vill. L. Rev. 293, 305\\n\\n(1957) (stating that in light of the Constitution’s silence on the right to a\\n\\nnew trial in criminal cases, “there seems to be no constitutional right to a\\n\\nnew trial”). Colorado could thus limit the availability of an appeal over the\\n\\nruling on a new-trial motion. McKane v. Durston, 153 U.S. 684, 687–88\\n\\n(1894).\\n\\n Of course, once Colorado authorized procedures for appeals and new\\n\\ntrials, the state had to comport with the Fourteenth Amendment’s rights to\\n\\ndue process and equal protection. Evitts v. Lucey, 469 U.S. 387, 393\\n\\n(1985). But Colorado’s definition of its own test for a new trial cannot be\\n\\nbootstrapped into a distinct constitutional violation triggering a right to\\n\\nhabeas relief. See Herrera v. Collins, 506 U.S. 390, 407–08, 411 (1993)\\n\\n(concluding that a state’s refusal to consider newly discovered evidence\\n\\neight years after the conviction did not result in a denial of due process).\\n\\n\\n\\n12\\n In Herrera v. Collins, 506 U.S. 390 (1993), the Supreme Court relied\\nin part on Justice Gray’s dissent. See Herrera, 506 U.S. at 408.\\n\\n\\n 13\\n\\f We have addressed a similar issue with respect to applications for\\n\\npost-conviction relief. Like many circuits, we have held that irregularities\\n\\nin a state appellate court’s handling of post-conviction proceedings do not\\n\\nsupport habeas relief because there is no constitutional right to post-\\n\\nconviction proceedings. Sellers v. Ward, 135 F.3d 1333, 1339 (10th Cir.\\n\\n1998); see also Steele v. Young, 11 F.3d 1518, 1524 (10th Cir. 1993)\\n\\n(holding that a challenge to state post-conviction procedures “would fail to\\n\\nstate a federal constitutional claim cognizable in a federal habeas\\n\\nproceeding”).\\n\\n Nor is there a constitutional right to appeal the denial of a new trial.\\n\\nSee p. 13, above; see also Allen v. Nix, 55 F.3d 414, 417 n.5 (8th Cir.\\n\\n1995) (“To the extent petitioner attempts to couch his actual innocence\\n\\nclaim in terms of a due process violation based upon the state court’s\\n\\ndenial of his motion for a new trial, petitioner does not allege an\\n\\n‘independent’ constitutional violation.”). We should thus treat appeals on\\n\\nnew-trial motions in the same way than we treat post-conviction appeals.\\n\\nIn doing so, we conclude that alleged state-law errors in either kind of\\n\\nappeal would not justify habeas relief. The district court thus did not err in\\n\\nrejecting this habeas claim.\\n\\n * * *\\n\\n Mr. Farrar’s habeas claims are invalid: Actual innocence and false\\n\\ntestimony by a private citizen do not entail constitutional violations\\n\\n\\n 14\\n\\ftriggering habeas relief. Nor can habeas relief be based on the Colorado\\n\\nSupreme Court’s definition of the state’s test for granting a new trial. We\\n\\nthus affirm the denial of Mr. Farrar’s petition for habeas relief.\\n\\n\\n\\n\\n 15\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4398842/\", \"author_raw\": \"BACHARACH, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"BACHARACH"},"judge2":{"kind":"string","value":"BALDOCK"},"judge3":{"kind":"string","value":"EBEL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4621589/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Charles FARRAR, Petitioner - Appellant, v. Rick RAEMISCH, Executive Director, Colorado Department of Corrections; Cynthia Coffman, Attorney General, State of Colorado ; James Falk, Warden, Sterling Correctional Facility, Respondents - Appellees. Scholars of Federal Habeas Corpus, Amicus Curiae.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-21\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 21, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\nCHARLES FARRAR,\n\n Petitioner - Appellant,\n\nv. No. 18-1005\n\nRICK RAEMISCH, Executive\nDirector, Colorado Department of\nCorrections; CYNTHIA COFFMAN,\nAttorney General, State of\nColorado; JAMES FALK, Warden,\nSterling Correctional Facility,\n\n Respondents - Appellees.\n\n------------------------------\n\nSCHOLARS OF FEDERAL\nHABEAS CORPUS,\n\n Amicus Curiae.\n _________________________________\n\n Appeal from the United States District Court\n for the District of Colorado\n (D.C. No. 1:15-CV-01425-RPM)\n _________________________________\n\nGail K. Johnson, Johnson & Klein, PLLC, Boulder, Colorado, for the\nPetitioner - Appellant.\n\nRyan A. Crane, Senior Assistant Attorney General, Denver, Colorado\n(Cynthia H. Coffman, Attorney General, with him on the briefs), for\nRespondents - Appellees.\n\fAurora Temple Barnes, Lewis Roca Rothgerber Christie, LLP, Denver,\nColorado (Kenneth F. Rossman, IV, Lewis Roca Rothgerber Christie, LLP,\nDenver, Colorado, with her on the briefs), for Amicus Curiae.\n _________________________________\n\nBefore BACHARACH, BALDOCK, and EBEL, Circuit Judges.\n _________________________________\n\nBACHARACH, Circuit Judge.\n _________________________________\n\n Mr. Charles Farrar, a Colorado state prisoner, appeals the district\n\ncourt’s denial of his petition for habeas relief. In district court, Mr. Farrar\n\nclaimed\n\n actual innocence,\n\n deprivation of due process based on the recantation of a key\n prosecution witness, and\n\n deprivation of due process based on a state appellate decision\n establishing an overly restrictive standard for a new trial. 1\n\nThe district court denied relief, and we affirm based on three conclusions:\n\n 1. Actual innocence does not supply a freestanding basis for\n habeas relief.\n\n 2. A private citizen’s false testimony does not violate the\n Constitution unless the government knows that the testimony is\n false.\n\n 3. The alleged error in the Colorado Supreme Court’s decision\n does not justify habeas relief.\n\n\n\n\n1\n In district court, Mr. Farrar also presented other habeas claims that\nare not relevant to this appeal.\n\n\n 2\n\fI. Mr. Farrar is convicted and seeks post-conviction relief.\n\n Mr. Farrar’s convictions stemmed from complaints of sexual abuse.\n\nThe victim was Mr. Farrar’s stepdaughter, who complained of the alleged\n\nabuse when she was in the eighth grade. Based on the girl’s account, state\n\nofficials charged Mr. Farrar with over twenty counts. Mr. Farrar denied the\n\nallegations. At the trial, the girl’s testimony supplied the prosecution’s\n\nonly direct evidence of Mr. Farrar’s guilt. The jury found Mr. Farrar guilty\n\nof numerous counts of sexual assault and one count of child abuse, and the\n\nstate trial court sentenced Mr. Farrar to prison for a minimum of 145 years\n\nand a maximum of life.\n\n Mr. Farrar appealed. While the appeal was pending, the girl recanted\n\nher trial testimony. Given the recantation, the Colorado Court of Appeals\n\ngranted a limited remand to the trial court so that Mr. Farrar could move\n\nfor a new trial. After Mr. Farrar filed that motion, the trial court conducted\n\nevidentiary hearings, where the girl testified that she had fabricated her\n\nallegations of sexual abuse. Nonetheless, the trial court denied the motion\n\non the ground that the recantation was not credible. 2 Mr. Farrar appealed\n\n\n2\n For example, the court discounted some of the girl’s new version of\nevents because it included other “unbelievable” and “far more heinous\nallegation[s],” including coercion by prosecutors, law enforcement\nofficers, and social workers during the trial. Appellant’s App’x, vol. I at\n518. The trial court ultimately concluded: “Nothing that the Court heard or\nsaw during this post-conviction proceeding persuades it that the newly\ndiscovered evidence would produce a complete acquittal at a new trial. In\n\n\n 3\n\fagain, and the Colorado Court of Appeals affirmed the denial of the motion\n\nfor a new trial. 3\n\n On certiorari, the Colorado Supreme Court affirmed. Farrar v.\n\nPeople, 208 P.3d 702, 709–10 (Colo. 2009). The court deferred to the trial\n\ncourt’s credibility determinations and clarified Colorado’s standard for a\n\nnew trial:\n\n Rather than merely creating reasonable doubt by demonstrating\n that the recanting witness has given different and irreconcilable\n testimony on different occasions, recantation can justify a new\n trial only if it contains sufficiently significant new evidence, and\n if it, rather than the witness’s inconsistent trial testimony, will\n probably be believed.\n\nId. at 707–08 (internal citations omitted).\n\n Mr. Farrar then unsuccessfully sought post-conviction relief in state\n\ncourt, which led to this habeas case.\n\nII. We engage in de novo review without applying 28 U.S.C.\n § 2254(d).\n\n In habeas cases, we engage in de novo review of the district court’s\n\nlegal ruling. Hooks v. Workman, 689 F.3d 1148, 1163 (10th Cir. 2012).\n\nWhen applying de novo review, however, we must consider the\n\napplicability of statutory deference under 28 U.S.C. § 2254(d). See id. This\n\n\n\nall probability, another jury would accept some of [the girl’s] contentions\nand reject others.” Id. at 520.\n3\n Mr. Farrar also appealed his convictions and sentence. But those\nparts of the appeal in state court are immaterial here.\n\n\n 4\n\fprovision states that a federal court can grant habeas relief only if the state\n\nappeals court acts contrary to a Supreme Court precedent, unreasonably\n\napplies that precedent, or unreasonably determines the facts. 28 U.S.C.\n\n§ 2254(d)(1)–(2). If § 2254(d) applies, Mr. Farrar and the amici argue that\n\nit would be unconstitutional.\n\n Section 2254(d) does not apply. This section applies only when a\n\nstate appellate court has adjudicated the merits of a constitutional claim.\n\nByrd v. Workman, 645 F.3d 1159, 1164 n.7 (10th Cir. 2011); Hooks v.\n\nWard, 184 F.3d 1206, 1223 (10th Cir. 1999). But the Colorado Supreme\n\nCourt didn’t adjudicate the merits of Mr. Farrar’s constitutional claims.\n\nInstead, the court simply held that based on Colorado’s standard for\n\ngranting a new trial, the denial of Mr. Farrar’s motion had fallen within the\n\ntrial court’s discretion. Farrar v. People, 208 P.3d 702, 706–10 (Colo.\n\n2009). Because the Colorado Supreme Court didn’t adjudicate the merits of\n\nthe constitutional claims, we do not apply § 2254(d). 4 Hooks, 184 F.3d at\n\n1223.\n\nIII. Habeas relief cannot be based on actual innocence, a private\n citizen’s false testimony, or the Colorado Supreme Court’s\n definition of the state-law test for granting a new trial.\n\n Mr. Farrar argues that\n\n he is actually innocent,\n\n4\n In its appeal brief, the State asserted a defense of procedural default.\nIn oral argument, however, the State expressly waived this defense.\n\n\n 5\n\f the girl’s false testimony violated his right to due process, and\n\n the Colorado Supreme Court committed a due-process violation\n by establishing an overly restrictive standard for the grant of a\n new trial.\n\nWe reject these arguments.\n\n A. Actual innocence and false testimony by a private citizen do\n not entitle Mr. Farrar to habeas relief.\n\n Mr. Farrar alleges that he is actually innocent and his conviction was\n\nbased on false testimony. But even if these allegations are true, they would\n\nnot entitle Mr. Farrar to habeas relief.\n\n 1. Our precedents disallow habeas relief based on freestanding\n claims of actual innocence.\n\n A distinction exists between claims of actual innocence used as a\n\ngateway and as a freestanding basis for habeas relief. As a gateway, a\n\nclaim of actual innocence “enable[s] habeas petitioners to overcome a\n\nprocedural bar” in order to assert distinct claims for constitutional\n\nviolations. McQuiggin v. Perkins, 569 U.S. 383, 386 (2013). 5 Because\n\ngateway claims are “procedural, rather than substantive,” they do not\n\n“provide a basis for relief.” Schlup v. Delo, 513 U.S. 298, 314–15 (1995).\n\n\n\n\n5\n For example, a showing of gateway actual innocence can allow an\napplicant to file an otherwise-barred successive or abusive petition, to\navoid a statute of limitations, to overcome a failure to develop facts or\nobserve filing deadlines, or to assert a claim otherwise subject to\nprocedural default. McQuiggin, 569 U.S. at 392–93.\n\n\n 6\n\fBy contrast, a freestanding claim asserts actual innocence as a basis for\n\nhabeas relief. See House v. Bell, 547 U.S. 518, 554 (2006); Dist. Attorney’s\n\nOffice for Third Judicial Dist. v. Osborne, 557 U.S. 52, 71 (2009).\n\n The Supreme Court has repeatedly sanctioned gateway actual\n\ninnocence claims, but the Court has never recognized freestanding actual\n\ninnocence claims as a basis for federal habeas relief. To the contrary, the\n\nCourt has repeatedly rejected such claims, noting instead that “[c]laims of\n\nactual innocence based on newly discovered evidence have never been held\n\nto state a ground for federal habeas relief absent an independent\n\nconstitutional violation occurring in the underlying state criminal\n\nproceedings.” Herrera v. Collins, 506 U.S. 390, 400 (1993). In rejecting\n\nsuch claims, the Court has observed that “[f]ew rulings would be more\n\ndisruptive of our federal system than to provide for federal habeas review\n\nof freestanding claims of actual innocence.” Id. at 401. 6\n\n We have thus held that actual innocence does not constitute a\n\nfreestanding basis for habeas relief. See Vreeland v. Zupan, 906 F.3d 866,\n\n\n6\n The Supreme Court has hypothesized about the possibility of an\nexception. See, e.g., Herrera, 506 U.S. at 417 (assuming, for the sake of\nargument, that actual innocence might justify habeas relief in a capital\ncase); House v. Bell, 547 U.S. 518, 554–55 (2006) (declining to resolve\nthis issue in a capital case); Dist. Attorney’s Office for Third Judicial Dist.\nv. Osborne, 557 U.S. 52, 71 (2009) (declining to resolve whether actual\ninnocence justifies habeas relief in a non-capital case); McQuiggin v.\nPerkins, 569 U.S. 383, 392 (2013) (again declining to resolve whether\nactual innocence justifies habeas relief in a non-capital case).\n\n\n 7\n\f883 n.6 (10th Cir. 2018) (denying a certificate of appealability because\n\nfreestanding assertions of actual innocence cannot support habeas relief);\n\nLaFevers v. Gibson, 238 F.3d 1263, 1265 n.4 (10th Cir. 2001) (“[A]n\n\nassertion of actual innocence . . . does not, standing alone, support the\n\ngranting of the writ of habeas corpus.”); Sellers v. Ward, 135 F.3d 1333,\n\n1339 (10th Cir. 1998) (“[T]he claim of innocence . . . itself is not a basis\n\nfor federal habeas corpus no matter how convincing the evidence.”). So\n\nMr. Farrar’s freestanding claim of actual innocence does not entitle him to\n\nhabeas relief.\n\n 2. The due-process claim (based on the girl’s false testimony)\n fails because Mr. Farrar does not allege that the government\n knew that the testimony was false.\n\n For habeas relief, Mr. Farrar must show a constitutional violation in\n\nhis conviction or sentence. 28 U.S.C. § 2241(c)(3). Here, he alleges a\n\ndenial of due process when he was convicted based on the girl’s false\n\ntestimony.\n\n The Fourteenth Amendment’s Due Process Clause prevents the\n\ngovernment from knowingly using perjured or false testimony at trial. See\n\nGiglio v. United States, 405 U.S. 150, 153–54 (1972); Napue v. People of\n\nState of Ill., 360 U.S. 264, 269 (1959). But here, Mr. Farrar does not allege\n\nthat the government knowingly elicited any false trial testimony.\n\nAccording to Mr. Farrar, the Second and Ninth Circuits have authorized\n\nhabeas relief even when the government unwittingly elicits false testimony.\n\n\n 8\n\fSee, e.g., Hall v. Dir. of Corr., 343 F.3d 976, 981–85 (9th Cir. 2003). Mr.\n\nFarrar asks us to do the same.\n\n But we have rejected that approach. In our circuit, federal habeas\n\nrelief cannot be based on perjured testimony unless the government knew\n\nthat the testimony was false. 7 For example, when a witness testified that\n\nthe defendant had participated in a murder but the witness later recanted,\n\nwe rejected the viability of a constitutional claim, reasoning that the\n\n\n\n\n7\n See Graham v. Wilson, 828 F.2d 656, 659 (10th Cir. 1987) (“In our\nhabeas corpus consideration of the introduction of false or mistaken\ntestimony, the question of error turns not on the witness’ knowledge of\nfalsity, but on the government’s knowledge.” (emphasis in original));\nMcBride v. United States, 446 F.2d 229, 232 (10th Cir. 1971) (“While use\nof perjured testimony to obtain a conviction may be grounds for vacation\nof a conviction, the petitioner has the burden of establishing that . . . it\nwas knowingly and intentionally used by the government to obtain a\nconviction.”); Wild v. State of Okla., 187 F.2d 409, 410 (10th Cir. 1951)\n(“[A] writ of habeas corpus should not be granted upon the grounds that\nfalse and perjured testimony was used unless it is shown that it was\nknowingly used against the defendant by the prosecuting officers in the\ncriminal case.”); Hinley v. Burford, 183 F.2d 581, 581 (10th Cir. 1950)\n(per curiam) (“[T]here is evidence to the effect that appellant was\nconvicted on the false testimony of his daughter, the alleged rape. But . . .\nthere is no testimony . . . that such testimony was knowingly and\nintentionally used by the prosecution to obtain the conviction. The writ\nmust therefore be denied.”); Tilghman v. Hunter, 167 F.2d 661, 662 (10th\nCir. 1948) (stating that introduction of perjured testimony would not void a\ncriminal judgment unless the government “knowingly, willfully, and\nintentionally” used the perjured testimony).\n\n\n\n 9\n\fdefendant had “failed to assert any evidence indicating prosecutors knew\n\n[the witness’s] testimony was false.” 8\n\n Our circuit’s approach precludes habeas relief based on Mr. Farrar’s\n\nallegations. He alleges that the girl’s testimony was false, but he doesn’t\n\nallege that the government knew of the falsity. This omission is fatal\n\nbecause the government’s knowledge is required for a constitutional\n\nviolation. We thus reject Mr. Farrar’s due-process claim based on the use\n\nof false testimony at his trial.\n\n B. Mr. Farrar’s challenge to the Colorado Supreme Court’s\n decision does not justify habeas relief.\n\n Mr. Farrar also contends that the Colorado Supreme Court erred in\n\ndefining the burden for obtaining a new trial based on recanted testimony.\n\nGiven that the Colorado Supreme Court relied on state law, 9 our first task\n\n\n8\n Romano v. Gibson, 239 F.3d 1156, 1175 (10th Cir. 2001); see also\nUnited States v. Garcia, 793 F.3d 1194, 1207 (10th Cir. 2015) (“[T]his\ncourt has repeatedly spoken of Napue claims as requiring perjury by the\nwitness and the prosecutor’s knowledge of the falsity.” (internal citations\nomitted)); United States v. Caballero, 277 F.3d 1235, 1243 (10th Cir.\n2002) (“In order to establish a due process violation [under Napue], the\n[defendants] must show that . . . the prosecution knew [the witness’s\ntestimony] to be false.”).\n9\n In his direct appeal, Mr. Farrar relied solely on Colorado law. Thus,\nthe court purported to rely only on Colorado law. In discussing the state’s\nlimits on the right to a new trial, the court observed that the United States\nSupreme Court “ha[d] never suggested that newly discovered evidence\nimpeaching a guilty verdict implicates due process of law.” Farrar v.\nPeople, 208 P.3d 702, 706 (Colo. 2009). But the court made this\nobservation only in the course of stating that creation of the right to a new\n\n\n 10\n\fis to interpret Mr. Farrar’s contention. An error in interpreting state law\n\ncannot support habeas relief, 10 but federal constitutional violations can\n\nordinarily support habeas relief. 11 We thus assume for the sake of argument\n\nthat Mr. Farrar is alleging a federal constitutional infirmity in the Colorado\n\nSupreme Court’s decision. If so, however, this allegation is insufficient\n\nbecause shortcomings in the Colorado Supreme Court’s application of state\n\nlaw would not entail a distinct constitutional violation.\n\n The Constitution does not require states to provide direct appeals.\n\nSee Abney v. United States, 431 U.S. 651, 656 (1977) (“[I]t is well settled\n\nthat there is no constitutional right to an appeal.”); United States v. Eggert,\n\n624 F.2d 973, 974 (10th Cir. 1980) (“It is well established that there is no\n\nconstitutional right to an appeal.”). But Colorado (like all other states) has\n\nprovided the opportunity to appeal. Here, the appeal involved the denial of\n\na new trial after a recantation of trial testimony. We thus inquire whether\n\nthe Constitution restricts how far states can go in restricting the grant of a\n\nnew trial based on recanted testimony. In this inquiry, we are guided by the\n\n\n\n\ntrial under state law largely entails “a matter of policy” based on a\nbalancing of the interests in finality, fairness, and accuracy. Id.\n10\n Estelle v. McGuire, 502 U.S. 62, 67 (1991).\n11\n See 28 U.S.C. § 2241(c)(3); see also Part III(A)(2), above.\n\n\n 11\n\ftext of the Constitution and historical practice. Herrera v. Collins, 506\n\nU.S. 390, 407–08 (1993).\n\n The Constitution does not refer to new trials. See id. at 408 (“The\n\nConstitution itself, of course, makes no mention of new trials.”). They\n\nsprung from the common law, with judges ordering new trials to address\n\nparticular concerns, such as newly discovered evidence. See Francis\n\nWharton, Criminal Pleading & Practice 584–92 (8th ed. 1880).\n\n Despite the historical availability of new trials, restrictions existed\n\nunder the common law. For example, courts have long placed time\n\nconstraints on new-trial motions. Herrera, 506 U.S. at 408–11. And\n\ncourts—before and after ratification of the Fourteenth Amendment\n\n(1868)—have restricted appellate review for the denial of new trials based\n\non matters involving facts or evidence. See Parsons v. Bedford, Breedlove\n\n& Robeson, 28 U.S. 433, 447–48 (1830) (discussing the unavailability of\n\nappellate jurisdiction over the denial of a new trial, which would have\n\nrequired reexamination of the jury’s factual findings); Blitz v. United\n\nStates, 153 U.S. 308, 312 (1894) (“The overruling of the motion for new\n\ntrial is next assigned for error. We had supposed that it was well\n\nunderstood by the bar that the refusal of a court of the United States to\n\ngrant a new trial cannot be reviewed upon writ of error.” (citing cases));\n\nSparf v. United States, 156 U.S. 51, 175 (1895) (Gray, J., dissenting)\n\n(“[T]he granting or refusal of a new trial rest[ed] wholly in the discretion\n\n\n 12\n\fof the court in which the trial was had, and [could not] be reviewed on\n\nerror.”). 12\n\n Given the Constitution’s silence on new trials and the historical\n\npractice under the common law, we conclude that the Constitution did not\n\nrequire Colorado to provide any mechanism for a new trial. See Lester\n\nOrfield, New Trial in Federal Criminal Cases, 2 Vill. L. Rev. 293, 305\n\n(1957) (stating that in light of the Constitution’s silence on the right to a\n\nnew trial in criminal cases, “there seems to be no constitutional right to a\n\nnew trial”). Colorado could thus limit the availability of an appeal over the\n\nruling on a new-trial motion. McKane v. Durston, 153 U.S. 684, 687–88\n\n(1894).\n\n Of course, once Colorado authorized procedures for appeals and new\n\ntrials, the state had to comport with the Fourteenth Amendment’s rights to\n\ndue process and equal protection. Evitts v. Lucey, 469 U.S. 387, 393\n\n(1985). But Colorado’s definition of its own test for a new trial cannot be\n\nbootstrapped into a distinct constitutional violation triggering a right to\n\nhabeas relief. See Herrera v. Collins, 506 U.S. 390, 407–08, 411 (1993)\n\n(concluding that a state’s refusal to consider newly discovered evidence\n\neight years after the conviction did not result in a denial of due process).\n\n\n\n12\n In Herrera v. Collins, 506 U.S. 390 (1993), the Supreme Court relied\nin part on Justice Gray’s dissent. See Herrera, 506 U.S. at 408.\n\n\n 13\n\f We have addressed a similar issue with respect to applications for\n\npost-conviction relief. Like many circuits, we have held that irregularities\n\nin a state appellate court’s handling of post-conviction proceedings do not\n\nsupport habeas relief because there is no constitutional right to post-\n\nconviction proceedings. Sellers v. Ward, 135 F.3d 1333, 1339 (10th Cir.\n\n1998); see also Steele v. Young, 11 F.3d 1518, 1524 (10th Cir. 1993)\n\n(holding that a challenge to state post-conviction procedures “would fail to\n\nstate a federal constitutional claim cognizable in a federal habeas\n\nproceeding”).\n\n Nor is there a constitutional right to appeal the denial of a new trial.\n\nSee p. 13, above; see also Allen v. Nix, 55 F.3d 414, 417 n.5 (8th Cir.\n\n1995) (“To the extent petitioner attempts to couch his actual innocence\n\nclaim in terms of a due process violation based upon the state court’s\n\ndenial of his motion for a new trial, petitioner does not allege an\n\n‘independent’ constitutional violation.”). We should thus treat appeals on\n\nnew-trial motions in the same way than we treat post-conviction appeals.\n\nIn doing so, we conclude that alleged state-law errors in either kind of\n\nappeal would not justify habeas relief. The district court thus did not err in\n\nrejecting this habeas claim.\n\n * * *\n\n Mr. Farrar’s habeas claims are invalid: Actual innocence and false\n\ntestimony by a private citizen do not entail constitutional violations\n\n\n 14\n\ftriggering habeas relief. Nor can habeas relief be based on the Colorado\n\nSupreme Court’s definition of the state’s test for granting a new trial. We\n\nthus affirm the denial of Mr. Farrar’s petition for habeas relief.\n\n\n\n\n 15\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Charles FARRAR, Petitioner - Appellant, v. Rick RAEMISCH, Executive Director, Colorado Department of Corrections; Cynthia Coffman, Attorney General, State of Colorado ; James Falk, Warden, Sterling Correctional Facility, Respondents - Appellees. Scholars of Federal Habeas Corpus, Amicus Curiae.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-21\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 21, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\nCHARLES FARRAR,\\n\\n Petitioner - Appellant,\\n\\nv. No. 18-1005\\n\\nRICK RAEMISCH, Executive\\nDirector, Colorado Department of\\nCorrections; CYNTHIA COFFMAN,\\nAttorney General, State of\\nColorado; JAMES FALK, Warden,\\nSterling Correctional Facility,\\n\\n Respondents - Appellees.\\n\\n------------------------------\\n\\nSCHOLARS OF FEDERAL\\nHABEAS CORPUS,\\n\\n Amicus Curiae.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:15-CV-01425-RPM)\\n _________________________________\\n\\nGail K. Johnson, Johnson & Klein, PLLC, Boulder, Colorado, for the\\nPetitioner - Appellant.\\n\\nRyan A. Crane, Senior Assistant Attorney General, Denver, Colorado\\n(Cynthia H. Coffman, Attorney General, with him on the briefs), for\\nRespondents - Appellees.\\n\\fAurora Temple Barnes, Lewis Roca Rothgerber Christie, LLP, Denver,\\nColorado (Kenneth F. Rossman, IV, Lewis Roca Rothgerber Christie, LLP,\\nDenver, Colorado, with her on the briefs), for Amicus Curiae.\\n _________________________________\\n\\nBefore BACHARACH, BALDOCK, and EBEL, Circuit Judges.\\n _________________________________\\n\\nBACHARACH, Circuit Judge.\\n _________________________________\\n\\n Mr. Charles Farrar, a Colorado state prisoner, appeals the district\\n\\ncourt’s denial of his petition for habeas relief. In district court, Mr. Farrar\\n\\nclaimed\\n\\n actual innocence,\\n\\n deprivation of due process based on the recantation of a key\\n prosecution witness, and\\n\\n deprivation of due process based on a state appellate decision\\n establishing an overly restrictive standard for a new trial. 1\\n\\nThe district court denied relief, and we affirm based on three conclusions:\\n\\n 1. Actual innocence does not supply a freestanding basis for\\n habeas relief.\\n\\n 2. A private citizen’s false testimony does not violate the\\n Constitution unless the government knows that the testimony is\\n false.\\n\\n 3. The alleged error in the Colorado Supreme Court’s decision\\n does not justify habeas relief.\\n\\n\\n\\n\\n1\\n In district court, Mr. Farrar also presented other habeas claims that\\nare not relevant to this appeal.\\n\\n\\n 2\\n\\fI. Mr. Farrar is convicted and seeks post-conviction relief.\\n\\n Mr. Farrar’s convictions stemmed from complaints of sexual abuse.\\n\\nThe victim was Mr. Farrar’s stepdaughter, who complained of the alleged\\n\\nabuse when she was in the eighth grade. Based on the girl’s account, state\\n\\nofficials charged Mr. Farrar with over twenty counts. Mr. Farrar denied the\\n\\nallegations. At the trial, the girl’s testimony supplied the prosecution’s\\n\\nonly direct evidence of Mr. Farrar’s guilt. The jury found Mr. Farrar guilty\\n\\nof numerous counts of sexual assault and one count of child abuse, and the\\n\\nstate trial court sentenced Mr. Farrar to prison for a minimum of 145 years\\n\\nand a maximum of life.\\n\\n Mr. Farrar appealed. While the appeal was pending, the girl recanted\\n\\nher trial testimony. Given the recantation, the Colorado Court of Appeals\\n\\ngranted a limited remand to the trial court so that Mr. Farrar could move\\n\\nfor a new trial. After Mr. Farrar filed that motion, the trial court conducted\\n\\nevidentiary hearings, where the girl testified that she had fabricated her\\n\\nallegations of sexual abuse. Nonetheless, the trial court denied the motion\\n\\non the ground that the recantation was not credible. 2 Mr. Farrar appealed\\n\\n\\n2\\n For example, the court discounted some of the girl’s new version of\\nevents because it included other “unbelievable” and “far more heinous\\nallegation[s],” including coercion by prosecutors, law enforcement\\nofficers, and social workers during the trial. Appellant’s App’x, vol. I at\\n518. The trial court ultimately concluded: “Nothing that the Court heard or\\nsaw during this post-conviction proceeding persuades it that the newly\\ndiscovered evidence would produce a complete acquittal at a new trial. In\\n\\n\\n 3\\n\\fagain, and the Colorado Court of Appeals affirmed the denial of the motion\\n\\nfor a new trial. 3\\n\\n On certiorari, the Colorado Supreme Court affirmed. Farrar v.\\n\\nPeople, 208 P.3d 702, 709–10 (Colo. 2009). The court deferred to the trial\\n\\ncourt’s credibility determinations and clarified Colorado’s standard for a\\n\\nnew trial:\\n\\n Rather than merely creating reasonable doubt by demonstrating\\n that the recanting witness has given different and irreconcilable\\n testimony on different occasions, recantation can justify a new\\n trial only if it contains sufficiently significant new evidence, and\\n if it, rather than the witness’s inconsistent trial testimony, will\\n probably be believed.\\n\\nId. at 707–08 (internal citations omitted).\\n\\n Mr. Farrar then unsuccessfully sought post-conviction relief in state\\n\\ncourt, which led to this habeas case.\\n\\nII. We engage in de novo review without applying 28 U.S.C.\\n § 2254(d).\\n\\n In habeas cases, we engage in de novo review of the district court’s\\n\\nlegal ruling. Hooks v. Workman, 689 F.3d 1148, 1163 (10th Cir. 2012).\\n\\nWhen applying de novo review, however, we must consider the\\n\\napplicability of statutory deference under 28 U.S.C. § 2254(d). See id. This\\n\\n\\n\\nall probability, another jury would accept some of [the girl’s] contentions\\nand reject others.” Id. at 520.\\n3\\n Mr. Farrar also appealed his convictions and sentence. But those\\nparts of the appeal in state court are immaterial here.\\n\\n\\n 4\\n\\fprovision states that a federal court can grant habeas relief only if the state\\n\\nappeals court acts contrary to a Supreme Court precedent, unreasonably\\n\\napplies that precedent, or unreasonably determines the facts. 28 U.S.C.\\n\\n§ 2254(d)(1)–(2). If § 2254(d) applies, Mr. Farrar and the amici argue that\\n\\nit would be unconstitutional.\\n\\n Section 2254(d) does not apply. This section applies only when a\\n\\nstate appellate court has adjudicated the merits of a constitutional claim.\\n\\nByrd v. Workman, 645 F.3d 1159, 1164 n.7 (10th Cir. 2011); Hooks v.\\n\\nWard, 184 F.3d 1206, 1223 (10th Cir. 1999). But the Colorado Supreme\\n\\nCourt didn’t adjudicate the merits of Mr. Farrar’s constitutional claims.\\n\\nInstead, the court simply held that based on Colorado’s standard for\\n\\ngranting a new trial, the denial of Mr. Farrar’s motion had fallen within the\\n\\ntrial court’s discretion. Farrar v. People, 208 P.3d 702, 706–10 (Colo.\\n\\n2009). Because the Colorado Supreme Court didn’t adjudicate the merits of\\n\\nthe constitutional claims, we do not apply § 2254(d). 4 Hooks, 184 F.3d at\\n\\n1223.\\n\\nIII. Habeas relief cannot be based on actual innocence, a private\\n citizen’s false testimony, or the Colorado Supreme Court’s\\n definition of the state-law test for granting a new trial.\\n\\n Mr. Farrar argues that\\n\\n he is actually innocent,\\n\\n4\\n In its appeal brief, the State asserted a defense of procedural default.\\nIn oral argument, however, the State expressly waived this defense.\\n\\n\\n 5\\n\\f the girl’s false testimony violated his right to due process, and\\n\\n the Colorado Supreme Court committed a due-process violation\\n by establishing an overly restrictive standard for the grant of a\\n new trial.\\n\\nWe reject these arguments.\\n\\n A. Actual innocence and false testimony by a private citizen do\\n not entitle Mr. Farrar to habeas relief.\\n\\n Mr. Farrar alleges that he is actually innocent and his conviction was\\n\\nbased on false testimony. But even if these allegations are true, they would\\n\\nnot entitle Mr. Farrar to habeas relief.\\n\\n 1. Our precedents disallow habeas relief based on freestanding\\n claims of actual innocence.\\n\\n A distinction exists between claims of actual innocence used as a\\n\\ngateway and as a freestanding basis for habeas relief. As a gateway, a\\n\\nclaim of actual innocence “enable[s] habeas petitioners to overcome a\\n\\nprocedural bar” in order to assert distinct claims for constitutional\\n\\nviolations. McQuiggin v. Perkins, 569 U.S. 383, 386 (2013). 5 Because\\n\\ngateway claims are “procedural, rather than substantive,” they do not\\n\\n“provide a basis for relief.” Schlup v. Delo, 513 U.S. 298, 314–15 (1995).\\n\\n\\n\\n\\n5\\n For example, a showing of gateway actual innocence can allow an\\napplicant to file an otherwise-barred successive or abusive petition, to\\navoid a statute of limitations, to overcome a failure to develop facts or\\nobserve filing deadlines, or to assert a claim otherwise subject to\\nprocedural default. McQuiggin, 569 U.S. at 392–93.\\n\\n\\n 6\\n\\fBy contrast, a freestanding claim asserts actual innocence as a basis for\\n\\nhabeas relief. See House v. Bell, 547 U.S. 518, 554 (2006); Dist. Attorney’s\\n\\nOffice for Third Judicial Dist. v. Osborne, 557 U.S. 52, 71 (2009).\\n\\n The Supreme Court has repeatedly sanctioned gateway actual\\n\\ninnocence claims, but the Court has never recognized freestanding actual\\n\\ninnocence claims as a basis for federal habeas relief. To the contrary, the\\n\\nCourt has repeatedly rejected such claims, noting instead that “[c]laims of\\n\\nactual innocence based on newly discovered evidence have never been held\\n\\nto state a ground for federal habeas relief absent an independent\\n\\nconstitutional violation occurring in the underlying state criminal\\n\\nproceedings.” Herrera v. Collins, 506 U.S. 390, 400 (1993). In rejecting\\n\\nsuch claims, the Court has observed that “[f]ew rulings would be more\\n\\ndisruptive of our federal system than to provide for federal habeas review\\n\\nof freestanding claims of actual innocence.” Id. at 401. 6\\n\\n We have thus held that actual innocence does not constitute a\\n\\nfreestanding basis for habeas relief. See Vreeland v. Zupan, 906 F.3d 866,\\n\\n\\n6\\n The Supreme Court has hypothesized about the possibility of an\\nexception. See, e.g., Herrera, 506 U.S. at 417 (assuming, for the sake of\\nargument, that actual innocence might justify habeas relief in a capital\\ncase); House v. Bell, 547 U.S. 518, 554–55 (2006) (declining to resolve\\nthis issue in a capital case); Dist. Attorney’s Office for Third Judicial Dist.\\nv. Osborne, 557 U.S. 52, 71 (2009) (declining to resolve whether actual\\ninnocence justifies habeas relief in a non-capital case); McQuiggin v.\\nPerkins, 569 U.S. 383, 392 (2013) (again declining to resolve whether\\nactual innocence justifies habeas relief in a non-capital case).\\n\\n\\n 7\\n\\f883 n.6 (10th Cir. 2018) (denying a certificate of appealability because\\n\\nfreestanding assertions of actual innocence cannot support habeas relief);\\n\\nLaFevers v. Gibson, 238 F.3d 1263, 1265 n.4 (10th Cir. 2001) (“[A]n\\n\\nassertion of actual innocence . . . does not, standing alone, support the\\n\\ngranting of the writ of habeas corpus.”); Sellers v. Ward, 135 F.3d 1333,\\n\\n1339 (10th Cir. 1998) (“[T]he claim of innocence . . . itself is not a basis\\n\\nfor federal habeas corpus no matter how convincing the evidence.”). So\\n\\nMr. Farrar’s freestanding claim of actual innocence does not entitle him to\\n\\nhabeas relief.\\n\\n 2. The due-process claim (based on the girl’s false testimony)\\n fails because Mr. Farrar does not allege that the government\\n knew that the testimony was false.\\n\\n For habeas relief, Mr. Farrar must show a constitutional violation in\\n\\nhis conviction or sentence. 28 U.S.C. § 2241(c)(3). Here, he alleges a\\n\\ndenial of due process when he was convicted based on the girl’s false\\n\\ntestimony.\\n\\n The Fourteenth Amendment’s Due Process Clause prevents the\\n\\ngovernment from knowingly using perjured or false testimony at trial. See\\n\\nGiglio v. United States, 405 U.S. 150, 153–54 (1972); Napue v. People of\\n\\nState of Ill., 360 U.S. 264, 269 (1959). But here, Mr. Farrar does not allege\\n\\nthat the government knowingly elicited any false trial testimony.\\n\\nAccording to Mr. Farrar, the Second and Ninth Circuits have authorized\\n\\nhabeas relief even when the government unwittingly elicits false testimony.\\n\\n\\n 8\\n\\fSee, e.g., Hall v. Dir. of Corr., 343 F.3d 976, 981–85 (9th Cir. 2003). Mr.\\n\\nFarrar asks us to do the same.\\n\\n But we have rejected that approach. In our circuit, federal habeas\\n\\nrelief cannot be based on perjured testimony unless the government knew\\n\\nthat the testimony was false. 7 For example, when a witness testified that\\n\\nthe defendant had participated in a murder but the witness later recanted,\\n\\nwe rejected the viability of a constitutional claim, reasoning that the\\n\\n\\n\\n\\n7\\n See Graham v. Wilson, 828 F.2d 656, 659 (10th Cir. 1987) (“In our\\nhabeas corpus consideration of the introduction of false or mistaken\\ntestimony, the question of error turns not on the witness’ knowledge of\\nfalsity, but on the government’s knowledge.” (emphasis in original));\\nMcBride v. United States, 446 F.2d 229, 232 (10th Cir. 1971) (“While use\\nof perjured testimony to obtain a conviction may be grounds for vacation\\nof a conviction, the petitioner has the burden of establishing that . . . it\\nwas knowingly and intentionally used by the government to obtain a\\nconviction.”); Wild v. State of Okla., 187 F.2d 409, 410 (10th Cir. 1951)\\n(“[A] writ of habeas corpus should not be granted upon the grounds that\\nfalse and perjured testimony was used unless it is shown that it was\\nknowingly used against the defendant by the prosecuting officers in the\\ncriminal case.”); Hinley v. Burford, 183 F.2d 581, 581 (10th Cir. 1950)\\n(per curiam) (“[T]here is evidence to the effect that appellant was\\nconvicted on the false testimony of his daughter, the alleged rape. But . . .\\nthere is no testimony . . . that such testimony was knowingly and\\nintentionally used by the prosecution to obtain the conviction. The writ\\nmust therefore be denied.”); Tilghman v. Hunter, 167 F.2d 661, 662 (10th\\nCir. 1948) (stating that introduction of perjured testimony would not void a\\ncriminal judgment unless the government “knowingly, willfully, and\\nintentionally” used the perjured testimony).\\n\\n\\n\\n 9\\n\\fdefendant had “failed to assert any evidence indicating prosecutors knew\\n\\n[the witness’s] testimony was false.” 8\\n\\n Our circuit’s approach precludes habeas relief based on Mr. Farrar’s\\n\\nallegations. He alleges that the girl’s testimony was false, but he doesn’t\\n\\nallege that the government knew of the falsity. This omission is fatal\\n\\nbecause the government’s knowledge is required for a constitutional\\n\\nviolation. We thus reject Mr. Farrar’s due-process claim based on the use\\n\\nof false testimony at his trial.\\n\\n B. Mr. Farrar’s challenge to the Colorado Supreme Court’s\\n decision does not justify habeas relief.\\n\\n Mr. Farrar also contends that the Colorado Supreme Court erred in\\n\\ndefining the burden for obtaining a new trial based on recanted testimony.\\n\\nGiven that the Colorado Supreme Court relied on state law, 9 our first task\\n\\n\\n8\\n Romano v. Gibson, 239 F.3d 1156, 1175 (10th Cir. 2001); see also\\nUnited States v. Garcia, 793 F.3d 1194, 1207 (10th Cir. 2015) (“[T]his\\ncourt has repeatedly spoken of Napue claims as requiring perjury by the\\nwitness and the prosecutor’s knowledge of the falsity.” (internal citations\\nomitted)); United States v. Caballero, 277 F.3d 1235, 1243 (10th Cir.\\n2002) (“In order to establish a due process violation [under Napue], the\\n[defendants] must show that . . . the prosecution knew [the witness’s\\ntestimony] to be false.”).\\n9\\n In his direct appeal, Mr. Farrar relied solely on Colorado law. Thus,\\nthe court purported to rely only on Colorado law. In discussing the state’s\\nlimits on the right to a new trial, the court observed that the United States\\nSupreme Court “ha[d] never suggested that newly discovered evidence\\nimpeaching a guilty verdict implicates due process of law.” Farrar v.\\nPeople, 208 P.3d 702, 706 (Colo. 2009). But the court made this\\nobservation only in the course of stating that creation of the right to a new\\n\\n\\n 10\\n\\fis to interpret Mr. Farrar’s contention. An error in interpreting state law\\n\\ncannot support habeas relief, 10 but federal constitutional violations can\\n\\nordinarily support habeas relief. 11 We thus assume for the sake of argument\\n\\nthat Mr. Farrar is alleging a federal constitutional infirmity in the Colorado\\n\\nSupreme Court’s decision. If so, however, this allegation is insufficient\\n\\nbecause shortcomings in the Colorado Supreme Court’s application of state\\n\\nlaw would not entail a distinct constitutional violation.\\n\\n The Constitution does not require states to provide direct appeals.\\n\\nSee Abney v. United States, 431 U.S. 651, 656 (1977) (“[I]t is well settled\\n\\nthat there is no constitutional right to an appeal.”); United States v. Eggert,\\n\\n624 F.2d 973, 974 (10th Cir. 1980) (“It is well established that there is no\\n\\nconstitutional right to an appeal.”). But Colorado (like all other states) has\\n\\nprovided the opportunity to appeal. Here, the appeal involved the denial of\\n\\na new trial after a recantation of trial testimony. We thus inquire whether\\n\\nthe Constitution restricts how far states can go in restricting the grant of a\\n\\nnew trial based on recanted testimony. In this inquiry, we are guided by the\\n\\n\\n\\n\\ntrial under state law largely entails “a matter of policy” based on a\\nbalancing of the interests in finality, fairness, and accuracy. Id.\\n10\\n Estelle v. McGuire, 502 U.S. 62, 67 (1991).\\n11\\n See 28 U.S.C. § 2241(c)(3); see also Part III(A)(2), above.\\n\\n\\n 11\\n\\ftext of the Constitution and historical practice. Herrera v. Collins, 506\\n\\nU.S. 390, 407–08 (1993).\\n\\n The Constitution does not refer to new trials. See id. at 408 (“The\\n\\nConstitution itself, of course, makes no mention of new trials.”). They\\n\\nsprung from the common law, with judges ordering new trials to address\\n\\nparticular concerns, such as newly discovered evidence. See Francis\\n\\nWharton, Criminal Pleading & Practice 584–92 (8th ed. 1880).\\n\\n Despite the historical availability of new trials, restrictions existed\\n\\nunder the common law. For example, courts have long placed time\\n\\nconstraints on new-trial motions. Herrera, 506 U.S. at 408–11. And\\n\\ncourts—before and after ratification of the Fourteenth Amendment\\n\\n(1868)—have restricted appellate review for the denial of new trials based\\n\\non matters involving facts or evidence. See Parsons v. Bedford, Breedlove\\n\\n& Robeson, 28 U.S. 433, 447–48 (1830) (discussing the unavailability of\\n\\nappellate jurisdiction over the denial of a new trial, which would have\\n\\nrequired reexamination of the jury’s factual findings); Blitz v. United\\n\\nStates, 153 U.S. 308, 312 (1894) (“The overruling of the motion for new\\n\\ntrial is next assigned for error. We had supposed that it was well\\n\\nunderstood by the bar that the refusal of a court of the United States to\\n\\ngrant a new trial cannot be reviewed upon writ of error.” (citing cases));\\n\\nSparf v. United States, 156 U.S. 51, 175 (1895) (Gray, J., dissenting)\\n\\n(“[T]he granting or refusal of a new trial rest[ed] wholly in the discretion\\n\\n\\n 12\\n\\fof the court in which the trial was had, and [could not] be reviewed on\\n\\nerror.”). 12\\n\\n Given the Constitution’s silence on new trials and the historical\\n\\npractice under the common law, we conclude that the Constitution did not\\n\\nrequire Colorado to provide any mechanism for a new trial. See Lester\\n\\nOrfield, New Trial in Federal Criminal Cases, 2 Vill. L. Rev. 293, 305\\n\\n(1957) (stating that in light of the Constitution’s silence on the right to a\\n\\nnew trial in criminal cases, “there seems to be no constitutional right to a\\n\\nnew trial”). Colorado could thus limit the availability of an appeal over the\\n\\nruling on a new-trial motion. McKane v. Durston, 153 U.S. 684, 687–88\\n\\n(1894).\\n\\n Of course, once Colorado authorized procedures for appeals and new\\n\\ntrials, the state had to comport with the Fourteenth Amendment’s rights to\\n\\ndue process and equal protection. Evitts v. Lucey, 469 U.S. 387, 393\\n\\n(1985). But Colorado’s definition of its own test for a new trial cannot be\\n\\nbootstrapped into a distinct constitutional violation triggering a right to\\n\\nhabeas relief. See Herrera v. Collins, 506 U.S. 390, 407–08, 411 (1993)\\n\\n(concluding that a state’s refusal to consider newly discovered evidence\\n\\neight years after the conviction did not result in a denial of due process).\\n\\n\\n\\n12\\n In Herrera v. Collins, 506 U.S. 390 (1993), the Supreme Court relied\\nin part on Justice Gray’s dissent. See Herrera, 506 U.S. at 408.\\n\\n\\n 13\\n\\f We have addressed a similar issue with respect to applications for\\n\\npost-conviction relief. Like many circuits, we have held that irregularities\\n\\nin a state appellate court’s handling of post-conviction proceedings do not\\n\\nsupport habeas relief because there is no constitutional right to post-\\n\\nconviction proceedings. Sellers v. Ward, 135 F.3d 1333, 1339 (10th Cir.\\n\\n1998); see also Steele v. Young, 11 F.3d 1518, 1524 (10th Cir. 1993)\\n\\n(holding that a challenge to state post-conviction procedures “would fail to\\n\\nstate a federal constitutional claim cognizable in a federal habeas\\n\\nproceeding”).\\n\\n Nor is there a constitutional right to appeal the denial of a new trial.\\n\\nSee p. 13, above; see also Allen v. Nix, 55 F.3d 414, 417 n.5 (8th Cir.\\n\\n1995) (“To the extent petitioner attempts to couch his actual innocence\\n\\nclaim in terms of a due process violation based upon the state court’s\\n\\ndenial of his motion for a new trial, petitioner does not allege an\\n\\n‘independent’ constitutional violation.”). We should thus treat appeals on\\n\\nnew-trial motions in the same way than we treat post-conviction appeals.\\n\\nIn doing so, we conclude that alleged state-law errors in either kind of\\n\\nappeal would not justify habeas relief. The district court thus did not err in\\n\\nrejecting this habeas claim.\\n\\n * * *\\n\\n Mr. Farrar’s habeas claims are invalid: Actual innocence and false\\n\\ntestimony by a private citizen do not entail constitutional violations\\n\\n\\n 14\\n\\ftriggering habeas relief. Nor can habeas relief be based on the Colorado\\n\\nSupreme Court’s definition of the state’s test for granting a new trial. We\\n\\nthus affirm the denial of Mr. Farrar’s petition for habeas relief.\\n\\n\\n\\n\\n 15\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2269,"cells":{"id":{"kind":"number","value":4623646,"string":"4,623,646"},"name":{"kind":"string","value":"STEVEN R.F., a Minor BY AND THROUGH His Mother Carrie FERNANDEZ, Plaintiff-Appellee, v. HARRISON SCHOOL DISTRICT NO. 2, and Various of Its Elected and Appointed Representatives in Their Official Capacities, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"Steven R.F. by and Through Fernandez v. Harrison Sch. Dist. No. 2"},"decision_date":{"kind":"string","value":"2019-05-28"},"docket_number":{"kind":"string","value":"18-1327"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Briscoe, Lucero, Phillips\", \"parties\": \"\", \"opinions\": [{\"author\": \"BRISCOE, Circuit Judge.\", \"type\": \"010combined\", \"text\": \"FILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 28, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n STEVEN R.F., a minor by and through his\\n mother Carrie Fernandez,\\n\\n Plaintiff - Appellee,\\n\\n v. No. 18-1327\\n\\n HARRISON SCHOOL DISTRICT NO. 2,\\n and various of its elected and appointed\\n representatives in their official capacities,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:17-CV-00629-RBJ)\\n _________________________________\\n\\nJohn R. Stanek, Anderson, Dude, and Lebel, Colorado Springs, Colorado (William K.\\nDude, Anderson, Dude, and Lebel, Colorado Springs, Colorado, and W. Stuart Stuller,\\nCaplan & Ernest, LLP, Boulder, Colorado, with him on the briefs), appearing for\\nAppellant.\\n\\nMichael C. Cook, Cook Varriano, P.C., Colorado Springs, Colorado, appearing for\\nAppellee.\\n _________________________________\\n\\nBefore BRISCOE, LUCERO, and PHILLIPS, Circuit Judges.\\n _________________________________\\n\\nBRISCOE, Circuit Judge.\\n _________________________________\\n\\n In this appeal, Defendant-Appellant Harrison School District No. 2 asks us to\\n\\freverse the district court’s ruling that it violated the Individuals with Disabilities\\n\\nEducation Act (IDEA) by failing to provide Plaintiff-Appellee Steven R.F. with a free\\n\\nappropriate public education. Because we conclude that the case is moot, we dismiss this\\n\\nappeal, vacate the district court’s ruling, and remand with instructions to dismiss as moot.\\n\\n I\\n\\n The IDEA provides federal funds to states for educating children with disabilities,\\n\\nguaranteeing disabled children between the ages of three and twenty-one access to a free\\n\\nappropriate public education (FAPE). 20 U.S.C. §§ 1400(d), 1412(a)(1). A FAPE\\n\\n“emphasizes special education and related services designed to meet [the child’s] unique\\n\\nneeds.” Id. § 1400(d). A child’s individualized education program (IEP) governs how a\\n\\nschool will provide him or her a FAPE. See id. § 1414(d)(1)(A). The IEP is a written\\n\\nstatement developed in a meeting attended by the student’s parents, teacher, and a special\\n\\neducation professional that summarizes the student’s abilities, outlines goals for the\\n\\nstudent’s education, specifies the services the student will receive to achieve those goals,\\n\\nand establishes criteria to evaluate the student’s progress. Id. § 1414(d)(1).\\n\\n The IDEA also requires state and local educational agencies receiving funding\\n\\nunder the Act to “establish and maintain procedures . . . to ensure that children with\\n\\ndisabilities and their parents are guaranteed procedural safeguards with respect to the\\n\\nprovision” of a FAPE. Id. § 1415(a); see also Honig v. Doe, 484 U.S. 305, 311–12\\n\\n(1988). For example, the IDEA requires that a child’s parents be notified by the school\\n\\ndistrict of any proposed change to the child’s educational placement. 20 U.S.C.\\n\\n§ 1415(b)(3). It also requires that the parents be permitted to participate in discussions\\n\\n 2\\n\\frelating to their child’s evaluation and education. Id. § 1414(d)(1)(B)(i). And it requires\\n\\nstates to allow parents the opportunity to bring a complaint about “any matter relating to\\n\\nthe identification, evaluation, or educational placement of [their] child, or the provision\\n\\nof a [FAPE] to such child.” Id. § 1415(b)(6).\\n\\n II\\n\\n Steven R.F. is a fourteen-year-old boy with severe autism. [App., Vol. II at 438.]\\n\\nIn 2013, the District agreed to place Steven at the Alpine Autism Center, a private out-of-\\n\\ndistrict facility in Colorado Springs. [Id.]\\n\\n In 2014, the District proposed to move Steven from Alpine to a public school\\n\\ncalled the School of Excellence (SOE) for the 2014–2015 schoolyear. [Id.] Steven’s\\n\\nmother, Carrie Fernandez (Mother), objected and filed a state complaint asserting various\\n\\nIDEA violations. After an investigation, the State Complaint Officer (SCO) agreed with\\n\\nMother and issued a written decision (2014 SCO Order). As a remedy, the SCO ordered,\\n\\namong other things, that the District could not change Steven’s placement until: (1) staff\\n\\nmembers from any new placement “proposed by” the District “have observed [Steven] . .\\n\\n. at [Alpine] to understand the nature of [his] educational and behavioral functioning” and\\n\\n(2) the District “convenes an IEP meeting, facilitated by a neutral facilitator (not\\n\\nemployed by the School District) . . . and develops an IEP that includes a description of\\n\\nplacement sufficient to allow [Mother] to understand what is being proposed.” App.,\\n\\nVol. II at 618. Steven remained at Alpine for the 2014–2015 and 2015–2016\\n\\nschoolyears. [See id. at 442.]\\n\\n On March 29, 2016, and April 5, 2016, the District held Steven’s IEP meeting for\\n\\n 3\\n\\fthe 2016–2017 schoolyear. [Id. at 444.] The IEP meeting was facilitated by the\\n\\nDistrict’s school psychologist, Michelle McFall. [Id.] Toward the end of the meeting,\\n\\nafter agreeing on required aspects of the IEP, the attendants discussed what facility\\n\\nSteven would attend. [Id. at 446.] Amy Lloyd, the District’s special education\\n\\ncoordinator, proposed three alternatives: Roundup Fellowship, Alpine, and the SOE.\\n\\n[Id.] The team decided on the SOE, over Mother’s objection. [Id.] At the time of the\\n\\nIEP meeting, no staff members from either the SOE or Roundup had observed Steven at\\n\\nAlpine. [See generally id. at 446–48.]\\n\\n After the meeting, McFall prepared a “Prior Written Notice of Special Education\\n\\nAction” summarizing the IEP Team’s discussions and decisions. [Id. at 447; accord\\n\\nApp., Vol. III at 676–79.] The notice identified the SOE as Steven’s placement for\\n\\n2016–2017, but did not identify which program within the SOE Steven would attend.\\n\\n[App., Vol. III at 678.]\\n\\n The SOE is a public school operated by Pikes Peak Board of Cooperative\\n\\nEducational Services. [App., Vol. II at 447.] The SOE has two programs relevant in this\\n\\ncase: the Communication and Language program (COLA) and the Learning\\n\\nIndependence by Educating Responsible Trustworthy Youth program (LIBERTY). [Id.]\\n\\nCOLA is designed for students who have significant behavior issues and who are largely\\n\\nunable to work independently. [Id.] LIBERTY is designed for students with either an\\n\\nautism spectrum diagnosis or a dual diagnosis and who are generally able to express their\\n\\nwants and needs and are able to work in small groups. [Id.] The District believed that\\n\\neither program could have implemented Steven’s IEP. [Id.]\\n\\n 4\\n\\f On May 5, 2016, Mother filed another state complaint alleging that the District\\n\\nviolated the 2014 SCO Order by changing Steven’s educational placement and by not\\n\\nutilizing a neutral facilitator for his 2016 IEP meeting. [App., Vol. I at 60.] She also\\n\\nasserted that the District’s placement decision of the SOE was not based on Steven’s\\n\\nindividual needs, that the District wrongfully predetermined Steven’s placement, and that\\n\\nthe District did not make a written offer of educational placement. [Id.] After an\\n\\ninvestigation, the SCO ruled, as relevant, that the District had violated the 2014 SCO\\n\\nOrder by not utilizing a neutral facilitator for Steven’s 2016 IEP meeting, [id. at 70;] and\\n\\nthat the District’s decision to move Steven to the SOE was predetermined and not based\\n\\non Steven’s individual needs, [id. at 70–72].\\n\\n The District challenged the SCO decision by filing a due process complaint with\\n\\nthe Colorado Office of Administrative Courts pursuant to 20 U.S.C. § 1415(f). The\\n\\nDistrict sought a determination that its proposal to transfer Steven to the SOE for the\\n\\n2016–2017 schoolyear was an appropriate offer of FAPE. [App., Vol. II at 439.] The\\n\\nAdministrative Law Judge deciding the complaint concluded that the “District made an\\n\\noffer of FAPE, and that any procedural violations that may have occurred did not deprive\\n\\n[Steven] of FAPE or educational benefit, and did not deprive [Mother] of her right to\\n\\nmeaningfully participate in the decision-making process.” Id.\\n\\n Mother appealed the ALJ’s determination to federal district court pursuant to 20\\n\\nU.S.C. §§ 1415(i)(2)(A) and (3)(A) and 34 C.F.R. § 300.516(b) and asked the district\\n\\ncourt to find that the 2016–2017 IEP denied Steven the FAPE to which he is entitled.\\n\\nShe asserted that the District violated the IDEA by: (1) not complying with the terms of\\n\\n 5\\n\\fthe 2014 SCO Order; (2) not identifying Steven’s proposed educational placement\\n\\n(COLA or LIBERTY) in his 2016–2017 IEP; (3) predetermining Steven’s placement in\\n\\nthe SOE; and (4) creating an IEP not based on Steven’s individual needs.1 [App., Vol. I\\n\\nat 5–20.] After merits briefing, the district court concluded that the District had violated\\n\\nthe 2014 SCO Order and various procedural protections within the IDEA, and that these\\n\\nviolations amounted to the denial of a FAPE. [See App., Vol. VII at 1786–1801.]\\n\\nSpecifically, the district court ruled, as regards Steven’s 2016 IEP: (1) the District failed\\n\\nto include a specific offer of educational placement; (2) the District failed to comply with\\n\\nthe requirements of the 2014 SCO Order,2 which were designed to protect Mother’s right\\n\\n\\n\\n\\n 1\\n Mother also asserted a claim for a violation of the Rehabilitation Act, 29\\nU.S.C. § 701 et seq. [App., Vol. I at 17–18.] The district court concluded that the\\nDistrict did not violate the Rehabilitation Act, and Mother does not appeal that\\nruling.\\n 2\\n The 2014 SCO Order prohibited the District from changing Steven’s\\neducational placement until:\\n\\n a. The School District conducts [a] comprehensive evaluation[] of\\n [Steven], in accordance with the requirements of IDEA;\\n\\n b. Staff members from any new placement proposed by the School\\n District, which staff would have responsibility for providing special\\n education and related services to [Steven] have observed [him] . . . at\\n [Alpine] to understand the nature of [his] educational and behavioral\\n functioning.\\n\\n c. The School District convenes an IEP meeting, facilitated by a neutral\\n facilitator (not employed by the School District), for [Steven] that\\n complies with all procedural requirements of IDEA, particularly all\\n of the provisions that the SCO has found the School District to have\\n violated, and develops an IEP that includes a description of\\n\\n 6\\n\\fto a “fair IEP meeting,” which includes “a clear offer of educational placement” and\\n\\n“meaningful participation in the IEP process,” App., Vol. VII at 1801; and (3) taken\\n\\ntogether, those failures amounted to the denial of a FAPE. The district court ordered the\\n\\nDistrict to reimburse Mother for Steven’s tuition at Alpine for 2016–2017 and awarded\\n\\nher attorney’s fees as the prevailing party.\\n\\n III\\n\\n Mother argues that the appeal is moot, and we must address that issue first because\\n\\nArticle III limits courts to adjudicating “actual, ongoing controversies.” Honig, 484 U.S.\\n\\nat 317. To satisfy the case-or-controversy requirement of Article III, “the parties ‘must\\n\\ncontinue to have a personal stake in the outcome of the lawsuit’ throughout the various\\n\\nstages of litigation.” Garcia v. Bd. of Educ. of Albuquerque Pub. Sch., 520 F.3d 1116,\\n\\n1123 (10th Cir. 2008) (quoting Lewis v. Cont’l Bank Corp., 494 U.S. 472, 478 (1990)).\\n\\n This case concerns Steven’s 2016–2017 IEP, which governed a schoolyear that\\n\\nhas passed. Although Mother initially sought and was awarded reimbursement for\\n\\nSteven’s tuition at Alpine, the parties agree that the District paid for Steven’s enrollment\\n\\nat Alpine pursuant to the IDEA’s stay-put provision,3 and need not reimburse Mother for\\n\\n\\n\\n\\n placement sufficient to allow [Mother] to understand what is being\\n proposed.\\n\\nApp., Vol. III at 618.\\n 3\\n The stay-put provision provides that “during the pendency of any\\nproceedings conducted pursuant to [the IDEA], unless the State or local educational\\nagency and the parents otherwise agree, the child shall remain in [his] then-current\\neducational placement . . . .” 20 U.S.C. § 1415(j).\\n 7\\n\\fanything. Therefore, unless a mootness exception applies, there is no “actual, ongoing\\n\\ncontrovers[y]” before us. Honig, 484 U.S. at 317.\\n\\n The District argues that this case falls into the exception to the mootness doctrine\\n\\nfor cases “capable of repetition yet evading review.” Id. at 318 (quoting Murphy v. Hunt,\\n\\n455 U.S. 478, 482 (1982) (per curiam)). This exception, which applies only in\\n\\n“exceptional situations,” Spencer v. Kemna, 523 U.S. 1, 17 (1998), can prevent dismissal\\n\\non mootness grounds when “(1) the challenged action was in its duration too short to be\\n\\nfully litigated prior to its cessation or expiration, and (2) there [i]s a reasonable\\n\\nexpectation that the same complaining party would be subjected to the same action\\n\\nagain,” Murphy, 455 U.S. at 482 (quoting Ill. Elections Bd. v. Socialist Workers Party,\\n\\n440 U.S. 173, 187 (1979)).\\n\\n The first prong of the exception is clearly satisfied. A one-year IEP is, by its\\n\\nnature, “too short [in duration] to be fully litigated prior to its . . . expiration.” Id.; see\\n\\nalso Sch. Comm. of Town of Burlington v. Dep’t of Educ., 471 U.S. 359, 370 (1985)\\n\\n(“[T]he [IDEA] review process is ponderous. A final judicial decision on the merits of an\\n\\nIEP will in most instances come a year or more after the school term covered by that IEP\\n\\nhas passed.”).\\n\\n The pivotal issue then becomes whether the District has shown that there is a\\n\\n“reasonable expectation” that it will be subjected to the same action again. The District’s\\n\\n“reasonable expectation” must be more than “a mere physical or theoretical possibility”;\\n\\nit must be something akin to a “demonstrated probability” that the District will again be\\n\\nin this situation. Murphy, 455 U.S. at 482. The District argues that Mother “almost\\n\\n 8\\n\\fcertainly will challenge [Steven’s most recent] IEP when these proceedings have been\\n\\ncompleted,” Aplt. Reply at 5, and notes that “[a]t the end of [Steven’s December 4, 2018]\\n\\nIEP meeting, [Mother] expressed her disagreement” with the IEP team’s proposed\\n\\nplacement at Sierra High School in its The Autism Program, id. at n.2. The District\\n\\nargues a live controversy remains: whether the District will have to maintain Steven’s\\n\\nenrollment at Alpine during the pendency of any challenge by Mother to Steven’s\\n\\nDecember 4, 2018 IEP. [Aplt. Reply at 6.] Even assuming that this amounts to a\\n\\nreasonable expectation of future IDEA disputes between the District and Mother, it does\\n\\nnot satisfy the mootness exception in this case because the procedural challenges Mother\\n\\nraises are fact-specific to Steven’s 2016–2017 IEP proceedings.\\n\\n Mother relies on two cases in support of her mootness argument: Board of\\n\\nEducation of Downers Grove Grade School District No. 58 v. Steven L., 89 F.3d 464 (7th\\n\\nCir. 1996), and District of Columbia v. Jeppsen ex rel. M.J., 468 F. Supp. 2d 107 (D.D.C.\\n\\n2006). Each case involved a challenge to an IEP for a completed schoolyear and the\\n\\napplication of the stay-put provision preventing the school from implementing the\\n\\nchallenged IEP. See Steven L., 89 F.3d at 465; Jeppsen, 468 F. Supp. 2d at 109. In\\n\\nSteven L., by the time the case reached the Seventh Circuit, the child’s parents had\\n\\n“already agreed to a new IEP with a different school district.” 89 F.3d at 467. In\\n\\nJeppsen, the parents and school district had reached a settlement and agreed to the\\n\\nstudent’s educational placement for the schoolyear at issue. 468 F. Supp. 2d at 110. In\\n\\neach case, the court concluded that the case was moot. In Steven L., the court concluded\\n\\nthat the capable-of-repetition exception did not apply because\\n\\n 9\\n\\f [the student] has successfully completed grade school and is on his way to\\n high school. He will never again attend fifth grade [(the grade to which the\\n challenged IEP related)]. The IEP modification at issue . . . has been\\n replaced by an IEP for [the student]’s high school years. [The student]’s\\n parents struck this agreement with a different entity than the [Defendant\\n Board]. There is no continuing controversy. This school district has no\\n authority to modify any IEP involving [the student].\\n\\n89 F.3d at 468. In Jeppsen, the district court also concluded that the exception did not\\n\\napply, even though “it is likely both that [the district] will attempt to move [student’s]\\n\\nplacement in the future and that the change will be challenged by [parent],” because “it is\\n\\nimpossible to predict whether a hearing officer will continue to support the [challenged]\\n\\nplacement.” 468 F. Supp. 2d at 112 n.5.\\n\\n These cases support our conclusion that this case is moot. In each case, “[b]ecause\\n\\nthe status quo remained in effect from the time [the parents] challenged the school\\n\\ndistrict’s attempt to modify the IEP, they de facto received the relief they originally\\n\\nsought . . . ; the modified IEP never took effect.” Steven L., 89 F.3d at 468; accord\\n\\nJeppsen, 468 F. Supp. 2d at 111–12. And, in each case, there was no evidence that the\\n\\nasserted IDEA violation was likely to occur again. Steven L., 89 F.3d at 468 (“This\\n\\nschool district has no authority to modify any IEP involving [student].”); Jeppsen, 468 F.\\n\\nSupp. 2d at 112 n.5 (“[I]t is likely that [student’s] IEP will change in the future, thus, it is\\n\\nimpossible to predict whether a hearing officer will continue to support the [challenged]\\n\\nplacement.”).\\n\\n Each of those facts is present in this case. By operation of the stay-put provision,\\n\\nSteven remained at Alpine for the 2016–2017 schoolyear and, we assume, he has\\n\\ncontinued to remain there. And, although the District asserts that Mother “almost\\n\\n 10\\n\\fcertainly will challenge” Steven’s December 4, 2018 IEP, Aplt. Reply at 5, nothing\\n\\nindicates that, even if she does challenge it, her challenges will be of the same procedural\\n\\nnature as those she brought in this case. A discussion of Honig, on which the District\\n\\nrelies in support of its capable-of-repetition argument, clarifies this point.\\n\\n In Honig, two students eligible for special education because of emotional\\n\\ndisturbance challenged indefinite suspensions by their school district. 484 U.S. at 312–\\n\\n13. Each student had engaged in “violent and disruptive conduct,” but it was undisputed\\n\\nthat the students’ conduct was “related to their disabilities.” Id. at 312. The Supreme\\n\\nCourt concluded that the case was moot for one student, who was twenty-four and no\\n\\nlonger IDEA-eligible. Id. at 318. The other student, however, was twenty, had not\\n\\ncompleted high school, and was therefore still entitled to a FAPE. Id. The Court\\n\\nconcluded that the twenty-year-old student’s claims were not moot because of his\\n\\n“continued eligibility for educational services under [the IDEA], the nature of his\\n\\ndisability, and [the school district’s] insistence that all local school districts retain\\n\\nresidual authority to exclude disabled children for dangerous conduct.” Id. at 318–19\\n\\n(footnote omitted). This conclusion relied on the “inextricable link between the student’s\\n\\nviolent behavior and the challenged policy of exclusion.” Brown v. Bartholomew\\n\\nConsol. Sch. Corp., 442 F.3d 588, 599 (7th Cir. 2006). Given the nature of the student’s\\n\\ndisability and the school district’s assertion that it could unilaterally refuse to provide\\n\\neducational services to the student, the Supreme Court had “little difficulty concluding\\n\\nthat there [wa]s a ‘reasonable expectation,’ that [the student] would once again be\\n\\nsubjected to” the precise action challenged in that case, and it therefore concluded that his\\n\\n 11\\n\\fclaim was not moot. Honig, 484 U.S. at 319–20 (quoting Murphy, 455 U.S. at 478).\\n\\n The certainty of the continued dispute is not present here as it was in Honig. Even\\n\\nassuming the District is correct that Mother “almost certainly will challenge” Steven’s\\n\\nnew IEP, Aplt. Reply at 5, there is no reason to conclude—must less a demonstrated\\n\\nprobability—that any subsequent IDEA challenge will be premised on the same\\n\\nprocedural shortcomings by the District that Mother challenges in this case.4 Mother’s\\n\\nchallenges to Steven’s 2016–2017 IEP were based on specific actions that she alleged the\\n\\nDistrict did not take in relation to Steven’s 2016–2017 IEP. As relevant on appeal, she\\n\\nchallenged the District’s failure to (1) have a staff member from the new placements\\n\\nproposed by the District (Roundup and the SOE) observe Steven at Alpine, [App. Vol. I\\n\\nat 14,] (2) utilize a neutral facilitator for Steven’s IEP meeting, [id. at 14–15,] and (3)\\n\\nadequately identify Steven’s proposed educational placement[, id. at 15]. Nothing\\n\\nsuggests that these alleged procedural failures will be at issue in any subsequent IDEA\\n\\nchallenge Mother brings.5 If we decided now, more than three years after the challenged\\n\\n\\n 4\\n In fact, the District’s assertions about what happened in the December 2018\\nIEP meeting indicate that the challenges Mother brings to Steven’s new IEP likely\\nwill not be of the same nature as those she brought in this case. The District stated in\\nbriefing that during Steven’s 2018 IEP meeting, “[t]he IEP team determined and\\nproposed that [Steven] be educated at his neighborhood high school, Sierra High\\nSchool in its The Autism Program.” Aplt. Reply at 5. Therefore, Mother’s argument\\nin this case that the IDEA required the District to identify Steven’s placement as\\neither COLA and LIBERTY (not merely the SOE) seems unlikely to be at issue in\\nany challenge Mother may bring to Steven’s most recent IEP.\\n 5\\n It is true that the parties have been involved in IDEA-related disputes before,\\nand that Mother has consistently opposed the District’s attempts to place Steven\\nsomewhere other than Alpine. And in some circumstances, ongoing disagreement\\n\\n 12\\n\\factions, whether those alleged failures amounted to a violation of the IDEA, we “would\\n\\nbe issuing, in effect, an advisory opinion. Our decision would merely tell the parties who\\n\\nwas correct . . . . It would do nothing to define the contours of the parties’ continuing\\n\\nlegal relationship under the IDEA such that future repetitions of the injury could be\\n\\navoided.” Brown, 442 F.3d at 599–600.\\n\\n Despite arguing that the appeal is moot, Mother argues that the district court case\\n\\n“falls within the exception to the mootness doctrine.” Aplee. Br. at 6. In support, she\\n\\nasserts that “the District continues to attempt to change Steven’s educational placement in\\n\\nviolation of the IDEA.” Id. However, as discussed, the capable-of-repetition exception\\n\\nin the IDEA context looks at the likelihood that the specific IDEA violations alleged will\\n\\nbe repeated. And the record does not indicate that it is reasonably likely that the District\\n\\nwill again violate the IDEA in the specific ways that Mother alleges it did in this case.\\n\\nBecause there is no “reasonable expectation” that the IDEA violations Mother asserts are\\n\\nlikely to happen again, the capable-of-repetition exception does not prevent us from\\n\\n\\n\\n\\ncould satisfy the capable-of-repetition exception to mootness. See, e.g., Jenkins v.\\nSquillacote, 935 F.2d 303, 308 (D.C. Cir. 1991) (concluding that an IDEA claim was\\nnot moot when “both litigants readily agreed that the question of the degree of\\nspecificity required of the District in providing notice to parents under the IDEA is . .\\n. . reasonably likely to be a recurring legal question with respect to the District’s\\neducational plans for the very pupil whose parents are now before this court”). But\\nthe only IDEA claims at issue on appeal are the District’s alleged procedural\\nviolations in creating Steven’s 2016–2017 IEP. And although it is possible that the\\nDistrict might again create an IEP with the same alleged deficiencies, the record does\\nnot contain a “demonstrated probability” that it will.\\n\\n\\n 13\\n\\fconcluding that the district court action is also moot.6\\n\\n Because the case is moot, we dismiss this appeal, vacate the district court’s ruling,\\n\\nand remand with instructions to dismiss as moot. See Lewis, 494 U.S. at 482 (1990)\\n\\n(“Our ordinary practice in disposing of a case that has become moot on appeal is to\\n\\nvacate the judgment with directions to dismiss.”).7\\n\\n\\n\\n\\n 6\\n As noted, Mother asserted both substantive and procedural IDEA violations\\nin district court. As discussed, the record does not support a conclusion that the\\nprocedural violations are reasonably likely to occur again. And even if the record\\ncould support a conclusion that the substantive violations are reasonably likely to\\noccur again, Mother does not argue that distinction, pointing only to the District’s\\nalleged procedural violations.\\n 7\\n Mother’s argument that equity dictates that we affirm the district court’s\\njudgment and remand for a determination of attorney’s fees has no support in the law.\\nUnder the IDEA, only the “prevailing party” can be awarded attorney’s fees. 20\\nU.S.C. § 1415(i)(3)(B). A party can only be determined to prevail if it does so on the\\nmerits or with “the necessary judicial imprimatur,” such as through a consent decree.\\nBuckhannon Bd. & Care Home v. W. Va. Dep’t of Health & Human Res., 532 U.S.\\n598, 605 (2001). Because the case is moot, the court does not have jurisdiction to\\nmake a determination on the merits, and Mother cannot be a “prevailing party” under\\nthe IDEA.\\n Rio Grande Silvery Minnow v. Bureau of Reclamation, 601 F.3d 1096, 1129\\n(10th Cir. 2010), which Mother cites in support of her argument for attorney’s fees,\\ndoes not dictate otherwise. Silvery Minnow noted that “if the party seeking vacatur\\nhas caused mootness, generally we do not order vacatur.” Id. That is not the\\ncircumstance here. This case has become moot by the passage of time and the nature\\nof the IDEA violations at issue, not by any action by the District.\\n 14\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4400899/\", \"author_raw\": \"BRISCOE, Circuit Judge.\"}]}"},"judge1":{"kind":"string","value":"BRISCOE"},"judge2":{"kind":"string","value":"LUCERO"},"judge3":{"kind":"string","value":"PHILLIPS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4623646/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: STEVEN R.F., a Minor BY AND THROUGH His Mother Carrie FERNANDEZ, Plaintiff-Appellee, v. HARRISON SCHOOL DISTRICT NO. 2, and Various of Its Elected and Appointed Representatives in Their Official Capacities, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-28\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nFILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n UNITED STATES COURT OF APPEALS May 28, 2019\n\n Elisabeth A. Shumaker\n FOR THE TENTH CIRCUIT Clerk of Court\n _________________________________\n\n STEVEN R.F., a minor by and through his\n mother Carrie Fernandez,\n\n Plaintiff - Appellee,\n\n v. No. 18-1327\n\n HARRISON SCHOOL DISTRICT NO. 2,\n and various of its elected and appointed\n representatives in their official capacities,\n\n Defendant - Appellant.\n _________________________________\n\n Appeal from the United States District Court\n for the District of Colorado\n (D.C. No. 1:17-CV-00629-RBJ)\n _________________________________\n\nJohn R. Stanek, Anderson, Dude, and Lebel, Colorado Springs, Colorado (William K.\nDude, Anderson, Dude, and Lebel, Colorado Springs, Colorado, and W. Stuart Stuller,\nCaplan & Ernest, LLP, Boulder, Colorado, with him on the briefs), appearing for\nAppellant.\n\nMichael C. Cook, Cook Varriano, P.C., Colorado Springs, Colorado, appearing for\nAppellee.\n _________________________________\n\nBefore BRISCOE, LUCERO, and PHILLIPS, Circuit Judges.\n _________________________________\n\nBRISCOE, Circuit Judge.\n _________________________________\n\n In this appeal, Defendant-Appellant Harrison School District No. 2 asks us to\n\freverse the district court’s ruling that it violated the Individuals with Disabilities\n\nEducation Act (IDEA) by failing to provide Plaintiff-Appellee Steven R.F. with a free\n\nappropriate public education. Because we conclude that the case is moot, we dismiss this\n\nappeal, vacate the district court’s ruling, and remand with instructions to dismiss as moot.\n\n I\n\n The IDEA provides federal funds to states for educating children with disabilities,\n\nguaranteeing disabled children between the ages of three and twenty-one access to a free\n\nappropriate public education (FAPE). 20 U.S.C. §§ 1400(d), 1412(a)(1). A FAPE\n\n“emphasizes special education and related services designed to meet [the child’s] unique\n\nneeds.” Id. § 1400(d). A child’s individualized education program (IEP) governs how a\n\nschool will provide him or her a FAPE. See id. § 1414(d)(1)(A). The IEP is a written\n\nstatement developed in a meeting attended by the student’s parents, teacher, and a special\n\neducation professional that summarizes the student’s abilities, outlines goals for the\n\nstudent’s education, specifies the services the student will receive to achieve those goals,\n\nand establishes criteria to evaluate the student’s progress. Id. § 1414(d)(1).\n\n The IDEA also requires state and local educational agencies receiving funding\n\nunder the Act to “establish and maintain procedures . . . to ensure that children with\n\ndisabilities and their parents are guaranteed procedural safeguards with respect to the\n\nprovision” of a FAPE. Id. § 1415(a); see also Honig v. Doe, 484 U.S. 305, 311–12\n\n(1988). For example, the IDEA requires that a child’s parents be notified by the school\n\ndistrict of any proposed change to the child’s educational placement. 20 U.S.C.\n\n§ 1415(b)(3). It also requires that the parents be permitted to participate in discussions\n\n 2\n\frelating to their child’s evaluation and education. Id. § 1414(d)(1)(B)(i). And it requires\n\nstates to allow parents the opportunity to bring a complaint about “any matter relating to\n\nthe identification, evaluation, or educational placement of [their] child, or the provision\n\nof a [FAPE] to such child.” Id. § 1415(b)(6).\n\n II\n\n Steven R.F. is a fourteen-year-old boy with severe autism. [App., Vol. II at 438.]\n\nIn 2013, the District agreed to place Steven at the Alpine Autism Center, a private out-of-\n\ndistrict facility in Colorado Springs. [Id.]\n\n In 2014, the District proposed to move Steven from Alpine to a public school\n\ncalled the School of Excellence (SOE) for the 2014–2015 schoolyear. [Id.] Steven’s\n\nmother, Carrie Fernandez (Mother), objected and filed a state complaint asserting various\n\nIDEA violations. After an investigation, the State Complaint Officer (SCO) agreed with\n\nMother and issued a written decision (2014 SCO Order). As a remedy, the SCO ordered,\n\namong other things, that the District could not change Steven’s placement until: (1) staff\n\nmembers from any new placement “proposed by” the District “have observed [Steven] . .\n\n. at [Alpine] to understand the nature of [his] educational and behavioral functioning” and\n\n(2) the District “convenes an IEP meeting, facilitated by a neutral facilitator (not\n\nemployed by the School District) . . . and develops an IEP that includes a description of\n\nplacement sufficient to allow [Mother] to understand what is being proposed.” App.,\n\nVol. II at 618. Steven remained at Alpine for the 2014–2015 and 2015–2016\n\nschoolyears. [See id. at 442.]\n\n On March 29, 2016, and April 5, 2016, the District held Steven’s IEP meeting for\n\n 3\n\fthe 2016–2017 schoolyear. [Id. at 444.] The IEP meeting was facilitated by the\n\nDistrict’s school psychologist, Michelle McFall. [Id.] Toward the end of the meeting,\n\nafter agreeing on required aspects of the IEP, the attendants discussed what facility\n\nSteven would attend. [Id. at 446.] Amy Lloyd, the District’s special education\n\ncoordinator, proposed three alternatives: Roundup Fellowship, Alpine, and the SOE.\n\n[Id.] The team decided on the SOE, over Mother’s objection. [Id.] At the time of the\n\nIEP meeting, no staff members from either the SOE or Roundup had observed Steven at\n\nAlpine. [See generally id. at 446–48.]\n\n After the meeting, McFall prepared a “Prior Written Notice of Special Education\n\nAction” summarizing the IEP Team’s discussions and decisions. [Id. at 447; accord\n\nApp., Vol. III at 676–79.] The notice identified the SOE as Steven’s placement for\n\n2016–2017, but did not identify which program within the SOE Steven would attend.\n\n[App., Vol. III at 678.]\n\n The SOE is a public school operated by Pikes Peak Board of Cooperative\n\nEducational Services. [App., Vol. II at 447.] The SOE has two programs relevant in this\n\ncase: the Communication and Language program (COLA) and the Learning\n\nIndependence by Educating Responsible Trustworthy Youth program (LIBERTY). [Id.]\n\nCOLA is designed for students who have significant behavior issues and who are largely\n\nunable to work independently. [Id.] LIBERTY is designed for students with either an\n\nautism spectrum diagnosis or a dual diagnosis and who are generally able to express their\n\nwants and needs and are able to work in small groups. [Id.] The District believed that\n\neither program could have implemented Steven’s IEP. [Id.]\n\n 4\n\f On May 5, 2016, Mother filed another state complaint alleging that the District\n\nviolated the 2014 SCO Order by changing Steven’s educational placement and by not\n\nutilizing a neutral facilitator for his 2016 IEP meeting. [App., Vol. I at 60.] She also\n\nasserted that the District’s placement decision of the SOE was not based on Steven’s\n\nindividual needs, that the District wrongfully predetermined Steven’s placement, and that\n\nthe District did not make a written offer of educational placement. [Id.] After an\n\ninvestigation, the SCO ruled, as relevant, that the District had violated the 2014 SCO\n\nOrder by not utilizing a neutral facilitator for Steven’s 2016 IEP meeting, [id. at 70;] and\n\nthat the District’s decision to move Steven to the SOE was predetermined and not based\n\non Steven’s individual needs, [id. at 70–72].\n\n The District challenged the SCO decision by filing a due process complaint with\n\nthe Colorado Office of Administrative Courts pursuant to 20 U.S.C. § 1415(f). The\n\nDistrict sought a determination that its proposal to transfer Steven to the SOE for the\n\n2016–2017 schoolyear was an appropriate offer of FAPE. [App., Vol. II at 439.] The\n\nAdministrative Law Judge deciding the complaint concluded that the “District made an\n\noffer of FAPE, and that any procedural violations that may have occurred did not deprive\n\n[Steven] of FAPE or educational benefit, and did not deprive [Mother] of her right to\n\nmeaningfully participate in the decision-making process.” Id.\n\n Mother appealed the ALJ’s determination to federal district court pursuant to 20\n\nU.S.C. §§ 1415(i)(2)(A) and (3)(A) and 34 C.F.R. § 300.516(b) and asked the district\n\ncourt to find that the 2016–2017 IEP denied Steven the FAPE to which he is entitled.\n\nShe asserted that the District violated the IDEA by: (1) not complying with the terms of\n\n 5\n\fthe 2014 SCO Order; (2) not identifying Steven’s proposed educational placement\n\n(COLA or LIBERTY) in his 2016–2017 IEP; (3) predetermining Steven’s placement in\n\nthe SOE; and (4) creating an IEP not based on Steven’s individual needs.1 [App., Vol. I\n\nat 5–20.] After merits briefing, the district court concluded that the District had violated\n\nthe 2014 SCO Order and various procedural protections within the IDEA, and that these\n\nviolations amounted to the denial of a FAPE. [See App., Vol. VII at 1786–1801.]\n\nSpecifically, the district court ruled, as regards Steven’s 2016 IEP: (1) the District failed\n\nto include a specific offer of educational placement; (2) the District failed to comply with\n\nthe requirements of the 2014 SCO Order,2 which were designed to protect Mother’s right\n\n\n\n\n 1\n Mother also asserted a claim for a violation of the Rehabilitation Act, 29\nU.S.C. § 701 et seq. [App., Vol. I at 17–18.] The district court concluded that the\nDistrict did not violate the Rehabilitation Act, and Mother does not appeal that\nruling.\n 2\n The 2014 SCO Order prohibited the District from changing Steven’s\neducational placement until:\n\n a. The School District conducts [a] comprehensive evaluation[] of\n [Steven], in accordance with the requirements of IDEA;\n\n b. Staff members from any new placement proposed by the School\n District, which staff would have responsibility for providing special\n education and related services to [Steven] have observed [him] . . . at\n [Alpine] to understand the nature of [his] educational and behavioral\n functioning.\n\n c. The School District convenes an IEP meeting, facilitated by a neutral\n facilitator (not employed by the School District), for [Steven] that\n complies with all procedural requirements of IDEA, particularly all\n of the provisions that the SCO has found the School District to have\n violated, and develops an IEP that includes a description of\n\n 6\n\fto a “fair IEP meeting,” which includes “a clear offer of educational placement” and\n\n“meaningful participation in the IEP process,” App., Vol. VII at 1801; and (3) taken\n\ntogether, those failures amounted to the denial of a FAPE. The district court ordered the\n\nDistrict to reimburse Mother for Steven’s tuition at Alpine for 2016–2017 and awarded\n\nher attorney’s fees as the prevailing party.\n\n III\n\n Mother argues that the appeal is moot, and we must address that issue first because\n\nArticle III limits courts to adjudicating “actual, ongoing controversies.” Honig, 484 U.S.\n\nat 317. To satisfy the case-or-controversy requirement of Article III, “the parties ‘must\n\ncontinue to have a personal stake in the outcome of the lawsuit’ throughout the various\n\nstages of litigation.” Garcia v. Bd. of Educ. of Albuquerque Pub. Sch., 520 F.3d 1116,\n\n1123 (10th Cir. 2008) (quoting Lewis v. Cont’l Bank Corp., 494 U.S. 472, 478 (1990)).\n\n This case concerns Steven’s 2016–2017 IEP, which governed a schoolyear that\n\nhas passed. Although Mother initially sought and was awarded reimbursement for\n\nSteven’s tuition at Alpine, the parties agree that the District paid for Steven’s enrollment\n\nat Alpine pursuant to the IDEA’s stay-put provision,3 and need not reimburse Mother for\n\n\n\n\n placement sufficient to allow [Mother] to understand what is being\n proposed.\n\nApp., Vol. III at 618.\n 3\n The stay-put provision provides that “during the pendency of any\nproceedings conducted pursuant to [the IDEA], unless the State or local educational\nagency and the parents otherwise agree, the child shall remain in [his] then-current\neducational placement . . . .” 20 U.S.C. § 1415(j).\n 7\n\fanything. Therefore, unless a mootness exception applies, there is no “actual, ongoing\n\ncontrovers[y]” before us. Honig, 484 U.S. at 317.\n\n The District argues that this case falls into the exception to the mootness doctrine\n\nfor cases “capable of repetition yet evading review.” Id. at 318 (quoting Murphy v. Hunt,\n\n455 U.S. 478, 482 (1982) (per curiam)). This exception, which applies only in\n\n“exceptional situations,” Spencer v. Kemna, 523 U.S. 1, 17 (1998), can prevent dismissal\n\non mootness grounds when “(1) the challenged action was in its duration too short to be\n\nfully litigated prior to its cessation or expiration, and (2) there [i]s a reasonable\n\nexpectation that the same complaining party would be subjected to the same action\n\nagain,” Murphy, 455 U.S. at 482 (quoting Ill. Elections Bd. v. Socialist Workers Party,\n\n440 U.S. 173, 187 (1979)).\n\n The first prong of the exception is clearly satisfied. A one-year IEP is, by its\n\nnature, “too short [in duration] to be fully litigated prior to its . . . expiration.” Id.; see\n\nalso Sch. Comm. of Town of Burlington v. Dep’t of Educ., 471 U.S. 359, 370 (1985)\n\n(“[T]he [IDEA] review process is ponderous. A final judicial decision on the merits of an\n\nIEP will in most instances come a year or more after the school term covered by that IEP\n\nhas passed.”).\n\n The pivotal issue then becomes whether the District has shown that there is a\n\n“reasonable expectation” that it will be subjected to the same action again. The District’s\n\n“reasonable expectation” must be more than “a mere physical or theoretical possibility”;\n\nit must be something akin to a “demonstrated probability” that the District will again be\n\nin this situation. Murphy, 455 U.S. at 482. The District argues that Mother “almost\n\n 8\n\fcertainly will challenge [Steven’s most recent] IEP when these proceedings have been\n\ncompleted,” Aplt. Reply at 5, and notes that “[a]t the end of [Steven’s December 4, 2018]\n\nIEP meeting, [Mother] expressed her disagreement” with the IEP team’s proposed\n\nplacement at Sierra High School in its The Autism Program, id. at n.2. The District\n\nargues a live controversy remains: whether the District will have to maintain Steven’s\n\nenrollment at Alpine during the pendency of any challenge by Mother to Steven’s\n\nDecember 4, 2018 IEP. [Aplt. Reply at 6.] Even assuming that this amounts to a\n\nreasonable expectation of future IDEA disputes between the District and Mother, it does\n\nnot satisfy the mootness exception in this case because the procedural challenges Mother\n\nraises are fact-specific to Steven’s 2016–2017 IEP proceedings.\n\n Mother relies on two cases in support of her mootness argument: Board of\n\nEducation of Downers Grove Grade School District No. 58 v. Steven L., 89 F.3d 464 (7th\n\nCir. 1996), and District of Columbia v. Jeppsen ex rel. M.J., 468 F. Supp. 2d 107 (D.D.C.\n\n2006). Each case involved a challenge to an IEP for a completed schoolyear and the\n\napplication of the stay-put provision preventing the school from implementing the\n\nchallenged IEP. See Steven L., 89 F.3d at 465; Jeppsen, 468 F. Supp. 2d at 109. In\n\nSteven L., by the time the case reached the Seventh Circuit, the child’s parents had\n\n“already agreed to a new IEP with a different school district.” 89 F.3d at 467. In\n\nJeppsen, the parents and school district had reached a settlement and agreed to the\n\nstudent’s educational placement for the schoolyear at issue. 468 F. Supp. 2d at 110. In\n\neach case, the court concluded that the case was moot. In Steven L., the court concluded\n\nthat the capable-of-repetition exception did not apply because\n\n 9\n\f [the student] has successfully completed grade school and is on his way to\n high school. He will never again attend fifth grade [(the grade to which the\n challenged IEP related)]. The IEP modification at issue . . . has been\n replaced by an IEP for [the student]’s high school years. [The student]’s\n parents struck this agreement with a different entity than the [Defendant\n Board]. There is no continuing controversy. This school district has no\n authority to modify any IEP involving [the student].\n\n89 F.3d at 468. In Jeppsen, the district court also concluded that the exception did not\n\napply, even though “it is likely both that [the district] will attempt to move [student’s]\n\nplacement in the future and that the change will be challenged by [parent],” because “it is\n\nimpossible to predict whether a hearing officer will continue to support the [challenged]\n\nplacement.” 468 F. Supp. 2d at 112 n.5.\n\n These cases support our conclusion that this case is moot. In each case, “[b]ecause\n\nthe status quo remained in effect from the time [the parents] challenged the school\n\ndistrict’s attempt to modify the IEP, they de facto received the relief they originally\n\nsought . . . ; the modified IEP never took effect.” Steven L., 89 F.3d at 468; accord\n\nJeppsen, 468 F. Supp. 2d at 111–12. And, in each case, there was no evidence that the\n\nasserted IDEA violation was likely to occur again. Steven L., 89 F.3d at 468 (“This\n\nschool district has no authority to modify any IEP involving [student].”); Jeppsen, 468 F.\n\nSupp. 2d at 112 n.5 (“[I]t is likely that [student’s] IEP will change in the future, thus, it is\n\nimpossible to predict whether a hearing officer will continue to support the [challenged]\n\nplacement.”).\n\n Each of those facts is present in this case. By operation of the stay-put provision,\n\nSteven remained at Alpine for the 2016–2017 schoolyear and, we assume, he has\n\ncontinued to remain there. And, although the District asserts that Mother “almost\n\n 10\n\fcertainly will challenge” Steven’s December 4, 2018 IEP, Aplt. Reply at 5, nothing\n\nindicates that, even if she does challenge it, her challenges will be of the same procedural\n\nnature as those she brought in this case. A discussion of Honig, on which the District\n\nrelies in support of its capable-of-repetition argument, clarifies this point.\n\n In Honig, two students eligible for special education because of emotional\n\ndisturbance challenged indefinite suspensions by their school district. 484 U.S. at 312–\n\n13. Each student had engaged in “violent and disruptive conduct,” but it was undisputed\n\nthat the students’ conduct was “related to their disabilities.” Id. at 312. The Supreme\n\nCourt concluded that the case was moot for one student, who was twenty-four and no\n\nlonger IDEA-eligible. Id. at 318. The other student, however, was twenty, had not\n\ncompleted high school, and was therefore still entitled to a FAPE. Id. The Court\n\nconcluded that the twenty-year-old student’s claims were not moot because of his\n\n“continued eligibility for educational services under [the IDEA], the nature of his\n\ndisability, and [the school district’s] insistence that all local school districts retain\n\nresidual authority to exclude disabled children for dangerous conduct.” Id. at 318–19\n\n(footnote omitted). This conclusion relied on the “inextricable link between the student’s\n\nviolent behavior and the challenged policy of exclusion.” Brown v. Bartholomew\n\nConsol. Sch. Corp., 442 F.3d 588, 599 (7th Cir. 2006). Given the nature of the student’s\n\ndisability and the school district’s assertion that it could unilaterally refuse to provide\n\neducational services to the student, the Supreme Court had “little difficulty concluding\n\nthat there [wa]s a ‘reasonable expectation,’ that [the student] would once again be\n\nsubjected to” the precise action challenged in that case, and it therefore concluded that his\n\n 11\n\fclaim was not moot. Honig, 484 U.S. at 319–20 (quoting Murphy, 455 U.S. at 478).\n\n The certainty of the continued dispute is not present here as it was in Honig. Even\n\nassuming the District is correct that Mother “almost certainly will challenge” Steven’s\n\nnew IEP, Aplt. Reply at 5, there is no reason to conclude—must less a demonstrated\n\nprobability—that any subsequent IDEA challenge will be premised on the same\n\nprocedural shortcomings by the District that Mother challenges in this case.4 Mother’s\n\nchallenges to Steven’s 2016–2017 IEP were based on specific actions that she alleged the\n\nDistrict did not take in relation to Steven’s 2016–2017 IEP. As relevant on appeal, she\n\nchallenged the District’s failure to (1) have a staff member from the new placements\n\nproposed by the District (Roundup and the SOE) observe Steven at Alpine, [App. Vol. I\n\nat 14,] (2) utilize a neutral facilitator for Steven’s IEP meeting, [id. at 14–15,] and (3)\n\nadequately identify Steven’s proposed educational placement[, id. at 15]. Nothing\n\nsuggests that these alleged procedural failures will be at issue in any subsequent IDEA\n\nchallenge Mother brings.5 If we decided now, more than three years after the challenged\n\n\n 4\n In fact, the District’s assertions about what happened in the December 2018\nIEP meeting indicate that the challenges Mother brings to Steven’s new IEP likely\nwill not be of the same nature as those she brought in this case. The District stated in\nbriefing that during Steven’s 2018 IEP meeting, “[t]he IEP team determined and\nproposed that [Steven] be educated at his neighborhood high school, Sierra High\nSchool in its The Autism Program.” Aplt. Reply at 5. Therefore, Mother’s argument\nin this case that the IDEA required the District to identify Steven’s placement as\neither COLA and LIBERTY (not merely the SOE) seems unlikely to be at issue in\nany challenge Mother may bring to Steven’s most recent IEP.\n 5\n It is true that the parties have been involved in IDEA-related disputes before,\nand that Mother has consistently opposed the District’s attempts to place Steven\nsomewhere other than Alpine. And in some circumstances, ongoing disagreement\n\n 12\n\factions, whether those alleged failures amounted to a violation of the IDEA, we “would\n\nbe issuing, in effect, an advisory opinion. Our decision would merely tell the parties who\n\nwas correct . . . . It would do nothing to define the contours of the parties’ continuing\n\nlegal relationship under the IDEA such that future repetitions of the injury could be\n\navoided.” Brown, 442 F.3d at 599–600.\n\n Despite arguing that the appeal is moot, Mother argues that the district court case\n\n“falls within the exception to the mootness doctrine.” Aplee. Br. at 6. In support, she\n\nasserts that “the District continues to attempt to change Steven’s educational placement in\n\nviolation of the IDEA.” Id. However, as discussed, the capable-of-repetition exception\n\nin the IDEA context looks at the likelihood that the specific IDEA violations alleged will\n\nbe repeated. And the record does not indicate that it is reasonably likely that the District\n\nwill again violate the IDEA in the specific ways that Mother alleges it did in this case.\n\nBecause there is no “reasonable expectation” that the IDEA violations Mother asserts are\n\nlikely to happen again, the capable-of-repetition exception does not prevent us from\n\n\n\n\ncould satisfy the capable-of-repetition exception to mootness. See, e.g., Jenkins v.\nSquillacote, 935 F.2d 303, 308 (D.C. Cir. 1991) (concluding that an IDEA claim was\nnot moot when “both litigants readily agreed that the question of the degree of\nspecificity required of the District in providing notice to parents under the IDEA is . .\n. . reasonably likely to be a recurring legal question with respect to the District’s\neducational plans for the very pupil whose parents are now before this court”). But\nthe only IDEA claims at issue on appeal are the District’s alleged procedural\nviolations in creating Steven’s 2016–2017 IEP. And although it is possible that the\nDistrict might again create an IEP with the same alleged deficiencies, the record does\nnot contain a “demonstrated probability” that it will.\n\n\n 13\n\fconcluding that the district court action is also moot.6\n\n Because the case is moot, we dismiss this appeal, vacate the district court’s ruling,\n\nand remand with instructions to dismiss as moot. See Lewis, 494 U.S. at 482 (1990)\n\n(“Our ordinary practice in disposing of a case that has become moot on appeal is to\n\nvacate the judgment with directions to dismiss.”).7\n\n\n\n\n 6\n As noted, Mother asserted both substantive and procedural IDEA violations\nin district court. As discussed, the record does not support a conclusion that the\nprocedural violations are reasonably likely to occur again. And even if the record\ncould support a conclusion that the substantive violations are reasonably likely to\noccur again, Mother does not argue that distinction, pointing only to the District’s\nalleged procedural violations.\n 7\n Mother’s argument that equity dictates that we affirm the district court’s\njudgment and remand for a determination of attorney’s fees has no support in the law.\nUnder the IDEA, only the “prevailing party” can be awarded attorney’s fees. 20\nU.S.C. § 1415(i)(3)(B). A party can only be determined to prevail if it does so on the\nmerits or with “the necessary judicial imprimatur,” such as through a consent decree.\nBuckhannon Bd. & Care Home v. W. Va. Dep’t of Health & Human Res., 532 U.S.\n598, 605 (2001). Because the case is moot, the court does not have jurisdiction to\nmake a determination on the merits, and Mother cannot be a “prevailing party” under\nthe IDEA.\n Rio Grande Silvery Minnow v. Bureau of Reclamation, 601 F.3d 1096, 1129\n(10th Cir. 2010), which Mother cites in support of her argument for attorney’s fees,\ndoes not dictate otherwise. Silvery Minnow noted that “if the party seeking vacatur\nhas caused mootness, generally we do not order vacatur.” Id. That is not the\ncircumstance here. This case has become moot by the passage of time and the nature\nof the IDEA violations at issue, not by any action by the District.\n 14\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: STEVEN R.F., a Minor BY AND THROUGH His Mother Carrie FERNANDEZ, Plaintiff-Appellee, v. HARRISON SCHOOL DISTRICT NO. 2, and Various of Its Elected and Appointed Representatives in Their Official Capacities, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-28\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nFILED\\n United States Court of Appeals\\n PUBLISH Tenth Circuit\\n\\n UNITED STATES COURT OF APPEALS May 28, 2019\\n\\n Elisabeth A. Shumaker\\n FOR THE TENTH CIRCUIT Clerk of Court\\n _________________________________\\n\\n STEVEN R.F., a minor by and through his\\n mother Carrie Fernandez,\\n\\n Plaintiff - Appellee,\\n\\n v. No. 18-1327\\n\\n HARRISON SCHOOL DISTRICT NO. 2,\\n and various of its elected and appointed\\n representatives in their official capacities,\\n\\n Defendant - Appellant.\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Colorado\\n (D.C. No. 1:17-CV-00629-RBJ)\\n _________________________________\\n\\nJohn R. Stanek, Anderson, Dude, and Lebel, Colorado Springs, Colorado (William K.\\nDude, Anderson, Dude, and Lebel, Colorado Springs, Colorado, and W. Stuart Stuller,\\nCaplan & Ernest, LLP, Boulder, Colorado, with him on the briefs), appearing for\\nAppellant.\\n\\nMichael C. Cook, Cook Varriano, P.C., Colorado Springs, Colorado, appearing for\\nAppellee.\\n _________________________________\\n\\nBefore BRISCOE, LUCERO, and PHILLIPS, Circuit Judges.\\n _________________________________\\n\\nBRISCOE, Circuit Judge.\\n _________________________________\\n\\n In this appeal, Defendant-Appellant Harrison School District No. 2 asks us to\\n\\freverse the district court’s ruling that it violated the Individuals with Disabilities\\n\\nEducation Act (IDEA) by failing to provide Plaintiff-Appellee Steven R.F. with a free\\n\\nappropriate public education. Because we conclude that the case is moot, we dismiss this\\n\\nappeal, vacate the district court’s ruling, and remand with instructions to dismiss as moot.\\n\\n I\\n\\n The IDEA provides federal funds to states for educating children with disabilities,\\n\\nguaranteeing disabled children between the ages of three and twenty-one access to a free\\n\\nappropriate public education (FAPE). 20 U.S.C. §§ 1400(d), 1412(a)(1). A FAPE\\n\\n“emphasizes special education and related services designed to meet [the child’s] unique\\n\\nneeds.” Id. § 1400(d). A child’s individualized education program (IEP) governs how a\\n\\nschool will provide him or her a FAPE. See id. § 1414(d)(1)(A). The IEP is a written\\n\\nstatement developed in a meeting attended by the student’s parents, teacher, and a special\\n\\neducation professional that summarizes the student’s abilities, outlines goals for the\\n\\nstudent’s education, specifies the services the student will receive to achieve those goals,\\n\\nand establishes criteria to evaluate the student’s progress. Id. § 1414(d)(1).\\n\\n The IDEA also requires state and local educational agencies receiving funding\\n\\nunder the Act to “establish and maintain procedures . . . to ensure that children with\\n\\ndisabilities and their parents are guaranteed procedural safeguards with respect to the\\n\\nprovision” of a FAPE. Id. § 1415(a); see also Honig v. Doe, 484 U.S. 305, 311–12\\n\\n(1988). For example, the IDEA requires that a child’s parents be notified by the school\\n\\ndistrict of any proposed change to the child’s educational placement. 20 U.S.C.\\n\\n§ 1415(b)(3). It also requires that the parents be permitted to participate in discussions\\n\\n 2\\n\\frelating to their child’s evaluation and education. Id. § 1414(d)(1)(B)(i). And it requires\\n\\nstates to allow parents the opportunity to bring a complaint about “any matter relating to\\n\\nthe identification, evaluation, or educational placement of [their] child, or the provision\\n\\nof a [FAPE] to such child.” Id. § 1415(b)(6).\\n\\n II\\n\\n Steven R.F. is a fourteen-year-old boy with severe autism. [App., Vol. II at 438.]\\n\\nIn 2013, the District agreed to place Steven at the Alpine Autism Center, a private out-of-\\n\\ndistrict facility in Colorado Springs. [Id.]\\n\\n In 2014, the District proposed to move Steven from Alpine to a public school\\n\\ncalled the School of Excellence (SOE) for the 2014–2015 schoolyear. [Id.] Steven’s\\n\\nmother, Carrie Fernandez (Mother), objected and filed a state complaint asserting various\\n\\nIDEA violations. After an investigation, the State Complaint Officer (SCO) agreed with\\n\\nMother and issued a written decision (2014 SCO Order). As a remedy, the SCO ordered,\\n\\namong other things, that the District could not change Steven’s placement until: (1) staff\\n\\nmembers from any new placement “proposed by” the District “have observed [Steven] . .\\n\\n. at [Alpine] to understand the nature of [his] educational and behavioral functioning” and\\n\\n(2) the District “convenes an IEP meeting, facilitated by a neutral facilitator (not\\n\\nemployed by the School District) . . . and develops an IEP that includes a description of\\n\\nplacement sufficient to allow [Mother] to understand what is being proposed.” App.,\\n\\nVol. II at 618. Steven remained at Alpine for the 2014–2015 and 2015–2016\\n\\nschoolyears. [See id. at 442.]\\n\\n On March 29, 2016, and April 5, 2016, the District held Steven’s IEP meeting for\\n\\n 3\\n\\fthe 2016–2017 schoolyear. [Id. at 444.] The IEP meeting was facilitated by the\\n\\nDistrict’s school psychologist, Michelle McFall. [Id.] Toward the end of the meeting,\\n\\nafter agreeing on required aspects of the IEP, the attendants discussed what facility\\n\\nSteven would attend. [Id. at 446.] Amy Lloyd, the District’s special education\\n\\ncoordinator, proposed three alternatives: Roundup Fellowship, Alpine, and the SOE.\\n\\n[Id.] The team decided on the SOE, over Mother’s objection. [Id.] At the time of the\\n\\nIEP meeting, no staff members from either the SOE or Roundup had observed Steven at\\n\\nAlpine. [See generally id. at 446–48.]\\n\\n After the meeting, McFall prepared a “Prior Written Notice of Special Education\\n\\nAction” summarizing the IEP Team’s discussions and decisions. [Id. at 447; accord\\n\\nApp., Vol. III at 676–79.] The notice identified the SOE as Steven’s placement for\\n\\n2016–2017, but did not identify which program within the SOE Steven would attend.\\n\\n[App., Vol. III at 678.]\\n\\n The SOE is a public school operated by Pikes Peak Board of Cooperative\\n\\nEducational Services. [App., Vol. II at 447.] The SOE has two programs relevant in this\\n\\ncase: the Communication and Language program (COLA) and the Learning\\n\\nIndependence by Educating Responsible Trustworthy Youth program (LIBERTY). [Id.]\\n\\nCOLA is designed for students who have significant behavior issues and who are largely\\n\\nunable to work independently. [Id.] LIBERTY is designed for students with either an\\n\\nautism spectrum diagnosis or a dual diagnosis and who are generally able to express their\\n\\nwants and needs and are able to work in small groups. [Id.] The District believed that\\n\\neither program could have implemented Steven’s IEP. [Id.]\\n\\n 4\\n\\f On May 5, 2016, Mother filed another state complaint alleging that the District\\n\\nviolated the 2014 SCO Order by changing Steven’s educational placement and by not\\n\\nutilizing a neutral facilitator for his 2016 IEP meeting. [App., Vol. I at 60.] She also\\n\\nasserted that the District’s placement decision of the SOE was not based on Steven’s\\n\\nindividual needs, that the District wrongfully predetermined Steven’s placement, and that\\n\\nthe District did not make a written offer of educational placement. [Id.] After an\\n\\ninvestigation, the SCO ruled, as relevant, that the District had violated the 2014 SCO\\n\\nOrder by not utilizing a neutral facilitator for Steven’s 2016 IEP meeting, [id. at 70;] and\\n\\nthat the District’s decision to move Steven to the SOE was predetermined and not based\\n\\non Steven’s individual needs, [id. at 70–72].\\n\\n The District challenged the SCO decision by filing a due process complaint with\\n\\nthe Colorado Office of Administrative Courts pursuant to 20 U.S.C. § 1415(f). The\\n\\nDistrict sought a determination that its proposal to transfer Steven to the SOE for the\\n\\n2016–2017 schoolyear was an appropriate offer of FAPE. [App., Vol. II at 439.] The\\n\\nAdministrative Law Judge deciding the complaint concluded that the “District made an\\n\\noffer of FAPE, and that any procedural violations that may have occurred did not deprive\\n\\n[Steven] of FAPE or educational benefit, and did not deprive [Mother] of her right to\\n\\nmeaningfully participate in the decision-making process.” Id.\\n\\n Mother appealed the ALJ’s determination to federal district court pursuant to 20\\n\\nU.S.C. §§ 1415(i)(2)(A) and (3)(A) and 34 C.F.R. § 300.516(b) and asked the district\\n\\ncourt to find that the 2016–2017 IEP denied Steven the FAPE to which he is entitled.\\n\\nShe asserted that the District violated the IDEA by: (1) not complying with the terms of\\n\\n 5\\n\\fthe 2014 SCO Order; (2) not identifying Steven’s proposed educational placement\\n\\n(COLA or LIBERTY) in his 2016–2017 IEP; (3) predetermining Steven’s placement in\\n\\nthe SOE; and (4) creating an IEP not based on Steven’s individual needs.1 [App., Vol. I\\n\\nat 5–20.] After merits briefing, the district court concluded that the District had violated\\n\\nthe 2014 SCO Order and various procedural protections within the IDEA, and that these\\n\\nviolations amounted to the denial of a FAPE. [See App., Vol. VII at 1786–1801.]\\n\\nSpecifically, the district court ruled, as regards Steven’s 2016 IEP: (1) the District failed\\n\\nto include a specific offer of educational placement; (2) the District failed to comply with\\n\\nthe requirements of the 2014 SCO Order,2 which were designed to protect Mother’s right\\n\\n\\n\\n\\n 1\\n Mother also asserted a claim for a violation of the Rehabilitation Act, 29\\nU.S.C. § 701 et seq. [App., Vol. I at 17–18.] The district court concluded that the\\nDistrict did not violate the Rehabilitation Act, and Mother does not appeal that\\nruling.\\n 2\\n The 2014 SCO Order prohibited the District from changing Steven’s\\neducational placement until:\\n\\n a. The School District conducts [a] comprehensive evaluation[] of\\n [Steven], in accordance with the requirements of IDEA;\\n\\n b. Staff members from any new placement proposed by the School\\n District, which staff would have responsibility for providing special\\n education and related services to [Steven] have observed [him] . . . at\\n [Alpine] to understand the nature of [his] educational and behavioral\\n functioning.\\n\\n c. The School District convenes an IEP meeting, facilitated by a neutral\\n facilitator (not employed by the School District), for [Steven] that\\n complies with all procedural requirements of IDEA, particularly all\\n of the provisions that the SCO has found the School District to have\\n violated, and develops an IEP that includes a description of\\n\\n 6\\n\\fto a “fair IEP meeting,” which includes “a clear offer of educational placement” and\\n\\n“meaningful participation in the IEP process,” App., Vol. VII at 1801; and (3) taken\\n\\ntogether, those failures amounted to the denial of a FAPE. The district court ordered the\\n\\nDistrict to reimburse Mother for Steven’s tuition at Alpine for 2016–2017 and awarded\\n\\nher attorney’s fees as the prevailing party.\\n\\n III\\n\\n Mother argues that the appeal is moot, and we must address that issue first because\\n\\nArticle III limits courts to adjudicating “actual, ongoing controversies.” Honig, 484 U.S.\\n\\nat 317. To satisfy the case-or-controversy requirement of Article III, “the parties ‘must\\n\\ncontinue to have a personal stake in the outcome of the lawsuit’ throughout the various\\n\\nstages of litigation.” Garcia v. Bd. of Educ. of Albuquerque Pub. Sch., 520 F.3d 1116,\\n\\n1123 (10th Cir. 2008) (quoting Lewis v. Cont’l Bank Corp., 494 U.S. 472, 478 (1990)).\\n\\n This case concerns Steven’s 2016–2017 IEP, which governed a schoolyear that\\n\\nhas passed. Although Mother initially sought and was awarded reimbursement for\\n\\nSteven’s tuition at Alpine, the parties agree that the District paid for Steven’s enrollment\\n\\nat Alpine pursuant to the IDEA’s stay-put provision,3 and need not reimburse Mother for\\n\\n\\n\\n\\n placement sufficient to allow [Mother] to understand what is being\\n proposed.\\n\\nApp., Vol. III at 618.\\n 3\\n The stay-put provision provides that “during the pendency of any\\nproceedings conducted pursuant to [the IDEA], unless the State or local educational\\nagency and the parents otherwise agree, the child shall remain in [his] then-current\\neducational placement . . . .” 20 U.S.C. § 1415(j).\\n 7\\n\\fanything. Therefore, unless a mootness exception applies, there is no “actual, ongoing\\n\\ncontrovers[y]” before us. Honig, 484 U.S. at 317.\\n\\n The District argues that this case falls into the exception to the mootness doctrine\\n\\nfor cases “capable of repetition yet evading review.” Id. at 318 (quoting Murphy v. Hunt,\\n\\n455 U.S. 478, 482 (1982) (per curiam)). This exception, which applies only in\\n\\n“exceptional situations,” Spencer v. Kemna, 523 U.S. 1, 17 (1998), can prevent dismissal\\n\\non mootness grounds when “(1) the challenged action was in its duration too short to be\\n\\nfully litigated prior to its cessation or expiration, and (2) there [i]s a reasonable\\n\\nexpectation that the same complaining party would be subjected to the same action\\n\\nagain,” Murphy, 455 U.S. at 482 (quoting Ill. Elections Bd. v. Socialist Workers Party,\\n\\n440 U.S. 173, 187 (1979)).\\n\\n The first prong of the exception is clearly satisfied. A one-year IEP is, by its\\n\\nnature, “too short [in duration] to be fully litigated prior to its . . . expiration.” Id.; see\\n\\nalso Sch. Comm. of Town of Burlington v. Dep’t of Educ., 471 U.S. 359, 370 (1985)\\n\\n(“[T]he [IDEA] review process is ponderous. A final judicial decision on the merits of an\\n\\nIEP will in most instances come a year or more after the school term covered by that IEP\\n\\nhas passed.”).\\n\\n The pivotal issue then becomes whether the District has shown that there is a\\n\\n“reasonable expectation” that it will be subjected to the same action again. The District’s\\n\\n“reasonable expectation” must be more than “a mere physical or theoretical possibility”;\\n\\nit must be something akin to a “demonstrated probability” that the District will again be\\n\\nin this situation. Murphy, 455 U.S. at 482. The District argues that Mother “almost\\n\\n 8\\n\\fcertainly will challenge [Steven’s most recent] IEP when these proceedings have been\\n\\ncompleted,” Aplt. Reply at 5, and notes that “[a]t the end of [Steven’s December 4, 2018]\\n\\nIEP meeting, [Mother] expressed her disagreement” with the IEP team’s proposed\\n\\nplacement at Sierra High School in its The Autism Program, id. at n.2. The District\\n\\nargues a live controversy remains: whether the District will have to maintain Steven’s\\n\\nenrollment at Alpine during the pendency of any challenge by Mother to Steven’s\\n\\nDecember 4, 2018 IEP. [Aplt. Reply at 6.] Even assuming that this amounts to a\\n\\nreasonable expectation of future IDEA disputes between the District and Mother, it does\\n\\nnot satisfy the mootness exception in this case because the procedural challenges Mother\\n\\nraises are fact-specific to Steven’s 2016–2017 IEP proceedings.\\n\\n Mother relies on two cases in support of her mootness argument: Board of\\n\\nEducation of Downers Grove Grade School District No. 58 v. Steven L., 89 F.3d 464 (7th\\n\\nCir. 1996), and District of Columbia v. Jeppsen ex rel. M.J., 468 F. Supp. 2d 107 (D.D.C.\\n\\n2006). Each case involved a challenge to an IEP for a completed schoolyear and the\\n\\napplication of the stay-put provision preventing the school from implementing the\\n\\nchallenged IEP. See Steven L., 89 F.3d at 465; Jeppsen, 468 F. Supp. 2d at 109. In\\n\\nSteven L., by the time the case reached the Seventh Circuit, the child’s parents had\\n\\n“already agreed to a new IEP with a different school district.” 89 F.3d at 467. In\\n\\nJeppsen, the parents and school district had reached a settlement and agreed to the\\n\\nstudent’s educational placement for the schoolyear at issue. 468 F. Supp. 2d at 110. In\\n\\neach case, the court concluded that the case was moot. In Steven L., the court concluded\\n\\nthat the capable-of-repetition exception did not apply because\\n\\n 9\\n\\f [the student] has successfully completed grade school and is on his way to\\n high school. He will never again attend fifth grade [(the grade to which the\\n challenged IEP related)]. The IEP modification at issue . . . has been\\n replaced by an IEP for [the student]’s high school years. [The student]’s\\n parents struck this agreement with a different entity than the [Defendant\\n Board]. There is no continuing controversy. This school district has no\\n authority to modify any IEP involving [the student].\\n\\n89 F.3d at 468. In Jeppsen, the district court also concluded that the exception did not\\n\\napply, even though “it is likely both that [the district] will attempt to move [student’s]\\n\\nplacement in the future and that the change will be challenged by [parent],” because “it is\\n\\nimpossible to predict whether a hearing officer will continue to support the [challenged]\\n\\nplacement.” 468 F. Supp. 2d at 112 n.5.\\n\\n These cases support our conclusion that this case is moot. In each case, “[b]ecause\\n\\nthe status quo remained in effect from the time [the parents] challenged the school\\n\\ndistrict’s attempt to modify the IEP, they de facto received the relief they originally\\n\\nsought . . . ; the modified IEP never took effect.” Steven L., 89 F.3d at 468; accord\\n\\nJeppsen, 468 F. Supp. 2d at 111–12. And, in each case, there was no evidence that the\\n\\nasserted IDEA violation was likely to occur again. Steven L., 89 F.3d at 468 (“This\\n\\nschool district has no authority to modify any IEP involving [student].”); Jeppsen, 468 F.\\n\\nSupp. 2d at 112 n.5 (“[I]t is likely that [student’s] IEP will change in the future, thus, it is\\n\\nimpossible to predict whether a hearing officer will continue to support the [challenged]\\n\\nplacement.”).\\n\\n Each of those facts is present in this case. By operation of the stay-put provision,\\n\\nSteven remained at Alpine for the 2016–2017 schoolyear and, we assume, he has\\n\\ncontinued to remain there. And, although the District asserts that Mother “almost\\n\\n 10\\n\\fcertainly will challenge” Steven’s December 4, 2018 IEP, Aplt. Reply at 5, nothing\\n\\nindicates that, even if she does challenge it, her challenges will be of the same procedural\\n\\nnature as those she brought in this case. A discussion of Honig, on which the District\\n\\nrelies in support of its capable-of-repetition argument, clarifies this point.\\n\\n In Honig, two students eligible for special education because of emotional\\n\\ndisturbance challenged indefinite suspensions by their school district. 484 U.S. at 312–\\n\\n13. Each student had engaged in “violent and disruptive conduct,” but it was undisputed\\n\\nthat the students’ conduct was “related to their disabilities.” Id. at 312. The Supreme\\n\\nCourt concluded that the case was moot for one student, who was twenty-four and no\\n\\nlonger IDEA-eligible. Id. at 318. The other student, however, was twenty, had not\\n\\ncompleted high school, and was therefore still entitled to a FAPE. Id. The Court\\n\\nconcluded that the twenty-year-old student’s claims were not moot because of his\\n\\n“continued eligibility for educational services under [the IDEA], the nature of his\\n\\ndisability, and [the school district’s] insistence that all local school districts retain\\n\\nresidual authority to exclude disabled children for dangerous conduct.” Id. at 318–19\\n\\n(footnote omitted). This conclusion relied on the “inextricable link between the student’s\\n\\nviolent behavior and the challenged policy of exclusion.” Brown v. Bartholomew\\n\\nConsol. Sch. Corp., 442 F.3d 588, 599 (7th Cir. 2006). Given the nature of the student’s\\n\\ndisability and the school district’s assertion that it could unilaterally refuse to provide\\n\\neducational services to the student, the Supreme Court had “little difficulty concluding\\n\\nthat there [wa]s a ‘reasonable expectation,’ that [the student] would once again be\\n\\nsubjected to” the precise action challenged in that case, and it therefore concluded that his\\n\\n 11\\n\\fclaim was not moot. Honig, 484 U.S. at 319–20 (quoting Murphy, 455 U.S. at 478).\\n\\n The certainty of the continued dispute is not present here as it was in Honig. Even\\n\\nassuming the District is correct that Mother “almost certainly will challenge” Steven’s\\n\\nnew IEP, Aplt. Reply at 5, there is no reason to conclude—must less a demonstrated\\n\\nprobability—that any subsequent IDEA challenge will be premised on the same\\n\\nprocedural shortcomings by the District that Mother challenges in this case.4 Mother’s\\n\\nchallenges to Steven’s 2016–2017 IEP were based on specific actions that she alleged the\\n\\nDistrict did not take in relation to Steven’s 2016–2017 IEP. As relevant on appeal, she\\n\\nchallenged the District’s failure to (1) have a staff member from the new placements\\n\\nproposed by the District (Roundup and the SOE) observe Steven at Alpine, [App. Vol. I\\n\\nat 14,] (2) utilize a neutral facilitator for Steven’s IEP meeting, [id. at 14–15,] and (3)\\n\\nadequately identify Steven’s proposed educational placement[, id. at 15]. Nothing\\n\\nsuggests that these alleged procedural failures will be at issue in any subsequent IDEA\\n\\nchallenge Mother brings.5 If we decided now, more than three years after the challenged\\n\\n\\n 4\\n In fact, the District’s assertions about what happened in the December 2018\\nIEP meeting indicate that the challenges Mother brings to Steven’s new IEP likely\\nwill not be of the same nature as those she brought in this case. The District stated in\\nbriefing that during Steven’s 2018 IEP meeting, “[t]he IEP team determined and\\nproposed that [Steven] be educated at his neighborhood high school, Sierra High\\nSchool in its The Autism Program.” Aplt. Reply at 5. Therefore, Mother’s argument\\nin this case that the IDEA required the District to identify Steven’s placement as\\neither COLA and LIBERTY (not merely the SOE) seems unlikely to be at issue in\\nany challenge Mother may bring to Steven’s most recent IEP.\\n 5\\n It is true that the parties have been involved in IDEA-related disputes before,\\nand that Mother has consistently opposed the District’s attempts to place Steven\\nsomewhere other than Alpine. And in some circumstances, ongoing disagreement\\n\\n 12\\n\\factions, whether those alleged failures amounted to a violation of the IDEA, we “would\\n\\nbe issuing, in effect, an advisory opinion. Our decision would merely tell the parties who\\n\\nwas correct . . . . It would do nothing to define the contours of the parties’ continuing\\n\\nlegal relationship under the IDEA such that future repetitions of the injury could be\\n\\navoided.” Brown, 442 F.3d at 599–600.\\n\\n Despite arguing that the appeal is moot, Mother argues that the district court case\\n\\n“falls within the exception to the mootness doctrine.” Aplee. Br. at 6. In support, she\\n\\nasserts that “the District continues to attempt to change Steven’s educational placement in\\n\\nviolation of the IDEA.” Id. However, as discussed, the capable-of-repetition exception\\n\\nin the IDEA context looks at the likelihood that the specific IDEA violations alleged will\\n\\nbe repeated. And the record does not indicate that it is reasonably likely that the District\\n\\nwill again violate the IDEA in the specific ways that Mother alleges it did in this case.\\n\\nBecause there is no “reasonable expectation” that the IDEA violations Mother asserts are\\n\\nlikely to happen again, the capable-of-repetition exception does not prevent us from\\n\\n\\n\\n\\ncould satisfy the capable-of-repetition exception to mootness. See, e.g., Jenkins v.\\nSquillacote, 935 F.2d 303, 308 (D.C. Cir. 1991) (concluding that an IDEA claim was\\nnot moot when “both litigants readily agreed that the question of the degree of\\nspecificity required of the District in providing notice to parents under the IDEA is . .\\n. . reasonably likely to be a recurring legal question with respect to the District’s\\neducational plans for the very pupil whose parents are now before this court”). But\\nthe only IDEA claims at issue on appeal are the District’s alleged procedural\\nviolations in creating Steven’s 2016–2017 IEP. And although it is possible that the\\nDistrict might again create an IEP with the same alleged deficiencies, the record does\\nnot contain a “demonstrated probability” that it will.\\n\\n\\n 13\\n\\fconcluding that the district court action is also moot.6\\n\\n Because the case is moot, we dismiss this appeal, vacate the district court’s ruling,\\n\\nand remand with instructions to dismiss as moot. See Lewis, 494 U.S. at 482 (1990)\\n\\n(“Our ordinary practice in disposing of a case that has become moot on appeal is to\\n\\nvacate the judgment with directions to dismiss.”).7\\n\\n\\n\\n\\n 6\\n As noted, Mother asserted both substantive and procedural IDEA violations\\nin district court. As discussed, the record does not support a conclusion that the\\nprocedural violations are reasonably likely to occur again. And even if the record\\ncould support a conclusion that the substantive violations are reasonably likely to\\noccur again, Mother does not argue that distinction, pointing only to the District’s\\nalleged procedural violations.\\n 7\\n Mother’s argument that equity dictates that we affirm the district court’s\\njudgment and remand for a determination of attorney’s fees has no support in the law.\\nUnder the IDEA, only the “prevailing party” can be awarded attorney’s fees. 20\\nU.S.C. § 1415(i)(3)(B). A party can only be determined to prevail if it does so on the\\nmerits or with “the necessary judicial imprimatur,” such as through a consent decree.\\nBuckhannon Bd. & Care Home v. W. Va. Dep’t of Health & Human Res., 532 U.S.\\n598, 605 (2001). Because the case is moot, the court does not have jurisdiction to\\nmake a determination on the merits, and Mother cannot be a “prevailing party” under\\nthe IDEA.\\n Rio Grande Silvery Minnow v. Bureau of Reclamation, 601 F.3d 1096, 1129\\n(10th Cir. 2010), which Mother cites in support of her argument for attorney’s fees,\\ndoes not dictate otherwise. Silvery Minnow noted that “if the party seeking vacatur\\nhas caused mootness, generally we do not order vacatur.” Id. That is not the\\ncircumstance here. This case has become moot by the passage of time and the nature\\nof the IDEA violations at issue, not by any action by the District.\\n 14\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2270,"cells":{"id":{"kind":"number","value":4623709,"string":"4,623,709"},"name":{"kind":"string","value":"Troy Michael KELL, Petitioner-Appellee, v. Larry BENZON, Warden Utah State Prison, Respondent-Appellant."},"name_abbreviation":{"kind":"string","value":"Kell v. Benzon"},"decision_date":{"kind":"string","value":"2019-05-28"},"docket_number":{"kind":"string","value":"17-4191"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Tenth Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Bacharach, Baldock, Phillips\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9888594/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"040dissent\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9888595/\", \"author_raw\": \"\"}, {\"type\": \"010combined\", \"text\": \"PUBLISH FILED\\n United States Court of Appeals\\n UNITED STATES COURT OF APPEALS Tenth Circuit\\n\\n FOR THE TENTH CIRCUIT May 28, 2019\\n _________________________________\\n Elisabeth A. Shumaker\\n Clerk of Court\\nTROY MICHAEL KELL,\\n\\n Petitioner - Appellee,\\n\\nv. No. 17-4191\\n\\nLARRY BENZON, Warden Utah\\nState Prison,\\n\\n Respondent - Appellant.\\n\\n\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Utah\\n (D.C. No. 2:07-CV-00359-CW)\\n _________________________________\\n\\nAndrew F. Peterson, Assistant Solicitor General (Tyler R. Green, Utah\\nSolicitor General, Thomas Brunker, Deputy Solicitor General, Daniel W.\\nBoyer, Assistant Solicitor General, Sean D. Reyes, Utah Attorney General,\\nSalt Lake City, Utah, with him on the briefs), for Respondent-Appellant.\\n\\nLindsey Layer, Assistant Federal Public Defender, Salt Lake City, Utah\\n(Jon M. Sands, Federal Public Defender for the District of Arizona,\\nAlexandra LeClair, Assistant Federal Public Defender, Salt Lake City,\\nUtah, with him on the briefs), for Petitioner-Appellee.\\n _________________________________\\n\\nBefore BACHARACH, BALDOCK, and PHILLIPS, Circuit Judges.\\n _________________________________\\n\\nBACHARACH, Circuit Judge.\\n _________________________________\\n\\n This is an interlocutory appeal from an order staying a habeas\\n\\nproceeding. We lack jurisdiction and dismiss the appeal.\\n\\n Mr. Troy Kell sought habeas relief, but he had not exhausted two of\\n\\nhis claims in state court. The unexhausted claims created a Catch-22 for\\n\\nMr. Kell, risking a dismissal of all of his claims without an opportunity to\\n\\ntimely refile. To relieve Mr. Kell of this Catch-22, the district court\\n\\nentered a limited stay, halting proceedings on one of the unexhausted\\n\\nclaims while Mr. Kell returned to state court to exhaust the claim. For the\\n\\nremaining habeas claims, however, the district court continued with the\\n\\nproceedings.\\n\\n In the midst of the ongoing habeas proceedings in district court, Utah\\n\\nappealed from the grant of a stay, arguing that the district court should\\n\\nhave declined to grant a stay. Our threshold question involves appellate\\n\\njurisdiction. To establish jurisdiction, Utah relies on the collateral-order\\n\\ndoctrine, which allows appeals from some decisions before the entry of a\\n\\nfinal judgment. But the district court’s issuance of a stay does not satisfy\\n\\nthe collateral-order doctrine’s requirements, so we dismiss the appeal for\\n\\nlack of appellate jurisdiction.\\n\\n1. Mr. Kell timely files a habeas petition.\\n\\n Mr. Kell was convicted of murder and sentenced to death in Utah,\\n\\nand his conviction became final roughly sixteen years ago. Mr. Kell then\\n\\nhad one year to seek federal habeas relief, but the one-year limitations\\n\\n 2\\n\\nperiod was tolled while he pursued state post-conviction remedies. 28\\n\\nU.S.C. § 2244(d). When the state post-conviction proceedings ended in\\n\\n2009, Mr. Kell timely filed a federal habeas petition.\\n\\n2. The district court stays the habeas case to allow Mr. Kell to\\n exhaust a new claim.\\n\\n In 2013, Mr. Kell asserted two new habeas claims: (1) that the trial\\n\\ncourt had improperly commented to the jury that Mr. Kell bore the burden\\n\\nin the penalty phase to show that his life should be spared and (2) that the\\n\\njurors had improperly considered extraneous information. Mr. Kell had not\\n\\nexhausted the two new claims, so the district court needed to grapple with\\n\\nhow to proceed. Continuing with the new habeas claims could prevent\\n\\nconsideration of any of the claims because a federal district court must\\n\\nordinarily dismiss the entire petition when one or more of the habeas\\n\\nclaims are unexhausted. Rose v. Lundy, 455 U.S. 509, 522 (1982). Given\\n\\nthe possibility of dismissal, Mr. Kell faced a dilemma: If the district court\\n\\nwere to dismiss the habeas petition and he later refiled in federal court, the\\n\\nstatute of limitations might have expired on all of his claims.\\n\\n To avoid this dilemma, Mr. Kell requested a stay so that he could\\n\\nexhaust his new habeas claims in state court. For this request, Mr. Kell\\n\\ninvoked a procedure adopted in Rhines v. Weber, 544 U.S. 269 (2005).\\n\\nUnder Rhines, a district court may stay habeas proceedings to permit\\n\\nexhaustion of a claim upon satisfaction of three elements:\\n\\n\\n 3\\n\\n 1. “Good cause” exists for the failure to exhaust the claim.\\n\\n 2. The unexhausted claim is “potentially meritorious.”\\n\\n 3. The petitioner did not engage in “abusive litigation tactics” or\\n intentionally delay the proceedings.\\n\\nRhines, 544 U.S. at 277–78. The district court declined to stay the claim\\n\\ninvolving extraneous influence on the jury, concluding that this claim\\n\\nlacked potential merit. But the district court granted the stay on the claim\\n\\ninvolving the judge’s comment to the jury, concluding that Mr. Kell had\\n\\nsatisfied the three elements for a Rhines stay. For the remaining habeas\\n\\nclaims, however, the district court stated that the proceedings would\\n\\ncontinue without interruption. 1\\n\\n3. Utah appeals the order granting a limited stay.\\n\\n In this appeal, Utah argues that the federal district court erred in\\n\\ngranting the stay because\\n\\n the court used the wrong test for “good cause” and misapplied\\n that test,\\n\\n the new habeas claim lacks potential merit based on timeliness,\\n the existence of a procedural default, and the absence of a\\n constitutional violation, and\\n\\n Mr. Kell was dilatory by waiting over three years to assert the\\n new habeas claim and over eight years to seek a stay based on\\n this claim.\\n\\n\\n\\n1 As the dissent points out, the district court denied certification of an\\ninterlocutory appeal. In denying certification, the district court reasoned\\nthat an interlocutory appeal would slow the litigation.\\n 4\\n\\n4. We lack jurisdiction to consider interlocutory appeals from\\n Rhines stays.\\n\\n We can consider these arguments only if Utah establishes appellate\\n\\njurisdiction. See EEOC v. PJ Utah, L.L.C., 822 F.3d 536, 542 n.7 (10th\\n\\nCir. 2016) (“[T]he appellant . . . bears the burden to establish appellate\\n\\njurisdiction.”). We typically acquire jurisdiction through the district\\n\\ncourt’s entry of a final decision. 28 U.S.C. § 1291. But a stay does not\\n\\nordinarily constitute a final decision. See Crystal Clear Commc’ns, Inc. v.\\n\\nSw. Bell Tel. Co., 415 F.3d 1171, 1176 (10th Cir. 2005) (“If a stay merely\\n\\ndelays litigation and does not effectively terminate proceedings, it is not\\n\\nconsidered a final decision.”).\\n\\n Utah argues that we nonetheless have jurisdiction under the\\n\\ncollateral-order doctrine. This doctrine would apply only if the district\\n\\ncourt’s decision\\n\\n conclusively decided the disputed question,\\n\\n resolved an important issue separate from the merits, and\\n\\n could not be effectively reviewed on direct appeal.\\n\\nVan Cauwenberghe v. Biard, 486 U.S. 517, 522 (1988). The failure to\\n\\nsatisfy any of the three elements would prevent us from applying the\\n\\ncollateral-order doctrine. See Stubblefield v. Windsor Capital Grp., 74 F.3d\\n\\n990, 997 (10th Cir. 1996) (stating that the collateral-order doctrine “does\\n\\nnot apply unless each of the three requirements are met”).\\n\\n 5\\n\\n Each element is considered stringent. E.g., Flanagan v. United\\n\\nStates, 465 U.S. 259, 270 (1984). And “[i]n case after case in year after\\n\\nyear, the Supreme Court has issued increasingly emphatic instructions that\\n\\nthe class of cases capable of satisfying this ‘stringent’ test should be\\n\\nunderstood as ‘small,’ ‘modest,’ and ‘narrow.’” United States v. Wampler,\\n\\n624 F.3d 1330, 1334 (10th Cir. 2010) (Gorsuch, J.). Utah bears the burden\\n\\non each element of this “stringent” test. See Los Lobos Renewable Power,\\n\\nL.L.C. v. Americulture, Inc., 885 F.3d 659, 664 (10th Cir. 2018) (stating\\n\\nthat the “party asserting jurisdiction under the collateral order doctrine”\\n\\nbears the burden on each element).\\n\\n We assume, for the sake of argument, that an order issuing a Rhines\\n\\nstay conclusively determines the disputed question. But the grant of a\\n\\nRhines stay involves issues that are intertwined with the merits and\\n\\nreviewable on direct appeal. We thus lack jurisdiction under the collateral-\\n\\norder doctrine. See Crystal Clear Commc’ns, Inc. v. Sw. Bell Tel. Co., 415\\n\\nF.3d 1171, 1178 (10th Cir. 2005) (noting that the collateral-order doctrine\\n\\ndoes not support appellate jurisdiction if any element is unsatisfied).\\n\\n A. The grant of a Rhines stay is not completely separate from\\n the merits.\\n\\n The collateral-order doctrine applies only when the order involves an\\n\\nimportant issue that is not intertwined with the merits. Coopers & Lybrand\\n\\nv. Livesay, 437 U.S. 463, 469 (1978). For this element, Utah must show\\n\\n\\n 6\\n\\nthat the issues bearing on the appropriateness of a Rhines stay are\\n\\n“completely separate” from the merits. E.g., Cunningham v. Hamilton Cty.,\\n\\nOhio, 527 U.S. 198, 205 (1999). Utah has not made this showing.\\n\\n 1. Avoidance of Piecemeal Litigation\\n\\n The requirement of complete separation is designed to prevent\\n\\npiecemeal appellate review. Van Cauwenberghe v. Biard, 486 U.S. 517,\\n\\n527 (1988). Given this purpose, the collateral-order doctrine would\\n\\nordinarily apply only if an appellate court would probably not need to\\n\\nconsider the merits a second time. 2\\n\\n But interlocutory appeals of Rhines stays would often require federal\\n\\nappellate courts to consider the merits at least twice:\\n\\n once in the interlocutory appeal (when the respondent argues\\n that a Rhines stay is improper because the petitioner’s\\n unexhausted claim lacks potential merit) and\\n\\n again after entry of the judgment (when the parties disagree\\n over the claim’s actual merit).\\n\\n\\n\\n2\\n The Supreme Court has explained:\\n\\n The requirement that the matter be separate from the merits of\\n the action itself means that review now is less likely to force the\\n appellate court to consider approximately the same (or a very\\n similar) matter more than once, and also seems less likely to\\n delay trial court proceeds (for, if the matter is truly collateral,\\n those proceedings might continue while the appeal is pending).\\n\\nJohnson v. Jones, 515 U.S. 304, 311 (1995) (emphasis in original).\\n\\n\\n 7\\n\\nAnd if the district court enters multiple Rhines stays, 3 we could face three\\n\\nor more appeals with overlapping issues.\\n\\n This possibility is apparent here. For example, consider Utah’s\\n\\nargument that the district court’s jury instruction was correct. This\\n\\nargument involves a classic issue on the merits. See Gillette v. Prosper,\\n\\n858 F.3d 833, 839 (3d Cir. 2017) (concluding that the order being appealed\\n\\nwas “closely related” to the merits because “both concern[ed] alleged\\n\\nconstitutional violations” and involved potential release from prison). If\\n\\nwe were to recognize appellate jurisdiction at this stage and Mr. Kell were\\n\\nto obtain habeas relief, we would decide the “potential merit” of Mr. Kell’s\\n\\nnew claim now and the claim’s “actual merit” after the entry of a final\\n\\njudgment. It is hard to imagine a better example of piecemeal litigation—\\n\\nprecisely what the Supreme Court has tried to avoid by limiting the\\n\\ncollateral-order doctrine to classes of orders involving “complete\\n\\nseparation” from the merits.\\n\\n The dissent disagrees:\\n\\n Even where a district court issues multiple Rhines stays, each\\n Rhines stay concerns different claims by a petitioner and\\n therefore different issues. To illustrate, a district court issues a\\n Rhines stay on claim x, allowing the petitioner to exhaust the\\n claim in state court. After the petitioner exhausts claim x in state\\n court and returns to federal court, the district court is not going\\n to issue another Rhines stay for the purpose of allowing the\\n\\n3\\n Here, for example, the district court granted two Rhines stays. Our\\nappeal involves only the second stay.\\n\\n 8\\n\\n petitioner to exhaust claim x. If there is a second Rhines stay, it\\n would be issued for the petitioner to exhaust claim y. If both of\\n these Rhines stays are appealed, and then the final judgment is\\n appealed, the “same issues” would not be before this Court three\\n or more times.\\n\\nDissent at 16–17 n.5 (emphasis in original).\\n\\n We respectfully think that the dissent has misunderstood us. When\\n\\nreviewing a Rhines stay, we consider the “potential merit” of the\\n\\nunexhausted claim. For example, let’s consider Utah’s argument that the\\n\\ndistrict court erred in granting a stay because the unexhausted habeas claim\\n\\nlacks potential merit. If we have appellate jurisdiction under the collateral-\\n\\norder doctrine, we would consider whether the district court acted within\\n\\nits discretion in treating the unexhausted claim as potentially meritorious.\\n\\n Let’s assume, for the sake of argument, that we were to uphold this\\n\\ndetermination. When the habeas case ends in district court, the parties\\n\\ncould appeal the district court’s ultimate determination of the claim’s\\n\\nactual merit. See Alexander v. U.S. Parole Comm’n, 514 F.3d 1083, 1087\\n\\n(10th Cir. 2008) (stating that a conditional writ of habeas corpus is final,\\n\\ncreating appellate jurisdiction); Burton v. Johnson, 975 F.2d 690, 693–94\\n\\n(10th Cir. 1992) (stating that a conditional writ of habeas corpus was an\\n\\nappealable final judgment).\\n\\n The same would be true for any case involving a Rhines stay. So in a\\n\\ncase with multiple Rhines stays and multiple interlocutory appeals, we\\n\\n\\n\\n 9\\n\\ncould face the same issues after a final judgment (even if the interlocutory\\n\\nappeals individually involved different issues).\\n\\n 2. The Significance of the Relationship Between the Rhines\\n Factor of “Potential Merit” and the Actual Merits of Mr.\\n Kell’s New Claim\\n\\n Because “potential merit” is essential for Rhines stays, interlocutory\\n\\nreview would frequently require us to consider the potential merit of the\\n\\nunderlying habeas claims. And “potential merit” is obviously not\\n\\n“completely separate” from the actual merits. The dissent agrees, stating\\n\\nthat the Rhines issue (“potential merit”) “undoubtedly overlaps with the\\n\\nmerits.” Dissent at 16. 4\\n\\n\\n\\n\\n4\\n Utah and the dissent downplay the significance of this relationship\\nbetween the two, calling “potential merit” a “fraction of a fraction” of the\\ntest governing grants of Rhines stays. Appellant’s Reply Br. at 5; Dissent\\nat 16.\\n\\n It is true that potential merit is just one element for a Rhines stay.\\nBut a court can enter a Rhines stay only if the unexhausted claim has\\npotential merit. See pp. 3–4, above. Thus, potential merit may be a\\n“fraction” of the test, but it is a requirement in any Rhines stay.\\n\\n Utah also asserts that the “underlying merit of a habeas claim is only\\na fraction of the ‘potential merit’ factor.” Appellant’s Reply Br. at 5. We\\nare not sure why Utah regards “potential merit” under Rhines as more\\ninclusive than the actual merit of a habeas claim, and Utah supplies no\\nexplanation. Even if Utah were right, however, it has not explained how\\nthe issue of potential merit could satisfy the requirement of complete\\nseparation from the merits.\\n\\n\\n 10\\n\\n 3. Application of the Test of “Complete Separation”\\n\\n To apply the element of complete separation, we must evaluate the\\n\\npertinent issue based on the entire class of orders (Rhines stays) rather\\n\\nthan the particular arguments in this appeal. United States v. Bolden, 353\\n\\nF.3d 870, 876 (10th Cir. 2003). 5 We thus consider whether the issues\\n\\nunderlying a Rhines stay are, “as a whole,” completely separate from the\\n\\nmerits. Id.\\n\\n The Supreme Court has repeatedly cautioned that the collateral-order\\n\\ndoctrine requires “complete separation” from the merits. E.g., Microsoft\\n\\nCorp. v. Baker, 137 S. Ct. 1702, 1708 n.3 (2017); Will v. Hallock, 546 U.S.\\n\\n345, 349 (2006); Sell v. United States, 539 U.S. 166, 176 (2003);\\n\\nCunningham v. Hamilton Cty., Ohio, 527 U.S. 198, 205 (1999);\\n\\nQuackenbush v. Allstate Ins. Co., 517 U.S. 706, 712 (1996); Johnson v.\\n\\nJones, 515 U.S. 304, 310–11 (1995); Digital Equip. Corp. v. Desktop\\n\\nDirect, Inc., 511 U.S. 863, 867 (1994); Richardson-Merrell, Inc. v. Koller,\\n\\n\\n5\\n In Bolden, we considered whether the collateral-order doctrine\\napplied to orders disqualifying an entire U.S. Attorney’s office from\\nrepresenting the government. 353 F.3d at 873. The defendant contended\\nthat the element of separation wasn’t satisfied because the issue of\\ndisqualification was entangled in the merits of his claims. Id. at 876. We\\nrejected this approach, reasoning that the Supreme Court “‘has consistently\\neschewed a case-by-case approach to deciding whether an order is\\nsufficiently collateral.’” Id. (quoting Cunningham v. Hamilton Cty., Ohio,\\n527 U.S. 198, 206 (1999)). We ultimately decided the issue of separation\\n“on the whole of such [disqualification] orders” without determining\\nwhether the particular issues in that case had been separate from the\\nmerits. Id.\\n 11\\n\\n472 U.S. 424, 431 (1985); Coopers & Lybrand v. Livesay, 437 U.S. 463,\\n\\n468–69 (1978).\\n\\n 4. Utah’s Focus on its Own Arguments (Rather than the Class\\n of Orders)\\n\\n Utah also points to its arguments involving good cause, insisting that\\n\\nthey do not relate to the merits. And the dissent relies on Utah’s arguments\\n\\ninvolving timeliness, dilatoriness, and procedural default. The focus of\\n\\nUtah and the dissent on Utah’s particular appeal points is misguided, as it\\n\\ndisregards\\n\\n the overlap between Utah’s appellate arguments and the merits\\n and\\n\\n the need to consider separation categorically based on the class\\n of orders rather than the particular issues invoked by the\\n appellant.\\n\\n a. Utah’s Arguments on Good Cause\\n\\n Utah tries to justify application of the collateral-order doctrine based\\n\\non the district court’s alleged misidentification and misapplication of the\\n\\ntest for good cause. We reject this effort.\\n\\n i. Misidentifying the Test for Good Cause\\n\\n Utah identifies the definition of good cause as an “important” issue.\\n\\nTo determine an issue’s importance under the collateral-order doctrine, we\\n\\nconsider\\n\\n\\n\\n\\n 12\\n\\n whether the issue is “important in a jurisprudential sense” 6 and\\n\\n whether the interests that “‘would potentially go unprotected\\n without immediate appellate review are significant relative to\\n efficiency interests sought to be advanced by adherence to the\\n final judgment rule.’” 7\\n\\n The definition of good cause might be considered jurisprudentially\\n\\nimportant now because we lack a precedent squarely defining the test for\\n\\ngood cause under Rhines. Of course, if we were to undertake interlocutory\\n\\nreview and define the test, that definition would settle the issue, rendering\\n\\nit jurisprudentially unimportant in the future. See 15A Charles Alan\\n\\nWright, Arthur R. Miller & Edward H. Cooper, Federal Practice &\\n\\nProcedure: Jurisdiction & Related Matters § 3911.5, at 438 (2d ed. 1992)\\n\\n(“Implementation of a serious and unsettled question requirement can\\n\\neasily lead to a situation in which a particular question is suitable for\\n\\ncollateral order appeal the first time it is presented, but not thereafter.”).\\n\\n And Utah has not shown an urgency to immediately define the\\n\\nstandard for good cause under Rhines. Indeed, Utah has offered many\\n\\nalternative arguments for reversal, such as expiration of the limitations\\n\\nperiod, procedural default, misapplication of the district court’s own test\\n\\nfor good cause, dilatoriness, and lack of potential merit. Given Utah’s\\n\\n\\n6\\n Marc Dev’t, Inc. v. FDIC, 992 F.2d 1503, 1505 (10th Cir.), vacated\\non other grounds, 12 F.3d 948 (10th Cir. 1993).\\n7\\n Pierce v. Blaine, 467 F.3d 362, 370–71 (3d Cir. 2006) (quoting In re\\nFord Motor Co., 110 F.3d 954, 959 (3d Cir. 1997)).\\n 13\\n\\nalternative arguments, we may not even need to decide the test for good\\n\\ncause if we were to reverse the grant of a Rhines stay.\\n\\n The dissent nonetheless insists that the test for good cause is\\n\\nimportant because a court in “literally every grant of a Rhines stay, not just\\n\\nthis particular grant of a Rhines stay, must decide what the appropriate\\n\\nstandard for determining ‘good cause’ is.” Dissent at 14. We see the issue\\n\\ndifferently. If the collateral-order doctrine applied, only two possibilities\\n\\nexist:\\n\\n 1. We decide now what the test is for good cause.\\n\\n 2. We do not decide the test now, ruling on other grounds.\\n\\n Let’s consider the first possibility (that we decide the test for good\\n\\ncause in this appeal). Once we define the test, future panels and district\\n\\ncourts will be bound by stare decisis to apply that test in all future cases.\\n\\nUnited States v. Meyers, 200 F.3d 715, 720 (10th Cir. 2000). We thus\\n\\ncouldn’t continue to view the definition of good cause as jurisprudentially\\n\\nsignificant once we define the test for good cause.\\n\\n The second possibility is that we avoid defining the test for good\\n\\ncause. This possibility is real because we could reverse a Rhines stay based\\n\\non any of the three prongs. For example, we might reverse the grant of a\\n\\nRhines stay based on dilatoriness or a lack of potential merit rather than\\n\\n\\n\\n\\n 14\\n\\naddress the issue of good cause. 8 But if we don’t decide the test for good\\n\\ncause, how could we apply the collateral-order doctrine based on the\\n\\nimportance of deciding that test? If we were to do so, we could put\\n\\nourselves in the odd position of recognizing appellate jurisdiction to\\n\\ndecide the test for good cause without actually deciding what the test is.\\n\\n Given these two possibilities, application of the collateral-order\\n\\ndoctrine based on the test for good cause would paradoxically allow every\\n\\nrespondent to appeal every grant of a Rhines stay based on an issue that we\\n\\nhave already decided or, if not, might not even need to decide. This\\n\\nparadox highlights the need to consider the importance of the issues\\n\\ncategorically based on the class of orders involved rather than the\\n\\nparticular arguments raised in a particular case. 9\\n\\n\\n8\\n Utah and the dissent criticize Mr. Kell for being dilatory, arguing\\nthat Mr. Kell waited until 2017 to seek a stay on his unexhausted claims.\\nBecause we lack jurisdiction, we have no occasion to address whether Mr.\\nKell was dilatory. We note, however, that Mr. Kell requested a stay in a\\nreply brief filed in 2014. See Kell v. Benzon, No. 2: 07-CV-359, dkt. no.\\n115 at 50 (D. Utah Jan. 24, 2014) (Pet’r’s Reply Br.) (“Mr. Kell asks this\\nCourt to stay these proceedings and hold them in abeyance to allow him to\\nreturn to state court to exhaust those claims.”). But as Utah and the dissent\\npoint out, he didn’t move for a stay on this issue until 2017.\\n9\\n The dissent calls this possibility an “irrelevant rabbit hole,”\\nreasoning that “the question is whether the district court’s order resolves\\nan issue that is completely separate from the merits.” Dissent at 14 n.4. As\\nthe dissent elsewhere acknowledges, however, the question must not only\\nbe completely separate from the merits but also “important.” Dissent at 9–\\n10. Here we are considering the element of importance. Because the\\npresence of an important issue is necessary under the collateral-order\\n\\n 15\\n\\n ii. Misapplying the Test for Good Cause\\n\\n On the merits of the stay, Utah argues that the district court\\n\\nmisapplied the test for good cause. Utah’s argument shows that application\\n\\nof the good cause test not only overlaps with the merits but would often\\n\\nrequire consideration of them. For example, petitioners could sometimes\\n\\nraise the same theory for good cause and the merits of a habeas claim. An\\n\\nexample is a Brady claim. See Brady v. Maryland, 373 U.S. 83 (1963).\\n\\nCourts have considered withholding of information as “good cause.” See\\n\\nDoe v. Jones, 762 F.3d 1174, 1182 (10th Cir. 2014). So when a petitioner\\n\\nasserts a Brady claim, the petitioner might rely on the withholding of\\n\\nevidence for both good cause and the merits of the habeas claim. See, e.g.,\\n\\nWogenstahl v. Mitchell, 668 F.3d 307, 322 (6th Cir. 2012) (concluding that\\n\\na habeas petitioner “had good cause for failing to raise the Brady issue\\n\\nprior to 2003, because the new information about [a prosecution witness’s\\n\\nprior arrest and adjudication of delinquency] was not disclosed until\\n\\nthen”).\\n\\n An overlap also exists between the inquiry on good cause and the\\n\\nmerits of other habeas claims. For example, the inquiry on good cause may\\n\\noverlap with the merits when a petitioner alleges ineffective assistance of\\n\\ntrial counsel. Suppose that a petitioner alleges good cause based on post-\\n\\n\\ndoctrine, our inquiry into the importance of the good-cause test is not an\\n“irrelevant rabbit hole.”\\n 16\\n\\nconviction counsel’s failure to assert ineffective assistance on the part of\\n\\ntrial counsel. This allegation could suffice to avoid a procedural default.\\n\\nMartinez v. Ryan, 566 U.S. 1, 9 (2012). And Utah argues that the tests for\\n\\ngood cause and procedural default are the same. Given this argument, we\\n\\nmight find “good cause” based on post-conviction counsel’s\\n\\nineffectiveness for failure to assert trial counsel’s ineffectiveness. And\\n\\nonce the case ends in district court, we could again face the issue of trial\\n\\ncounsel’s ineffectiveness as part of our review on the merits.\\n\\n The Supreme Court addressed this kind of overlap in Van\\n\\nCauwenberghe v. Biard, 486 U.S. 517 (1988), and Coopers & Lybrand v.\\n\\nLivesay, 437 U.S. 463 (1978). In Van Cauwenberghe, the Court held that\\n\\nthe denial of a motion to dismiss under the doctrine of forum non\\n\\nconveniens was not separate from the merits because the doctrine involves\\n\\nfactors (like the location of the witnesses and evidence) that are enmeshed\\n\\nwith the merits. 486 U.S. at 528–29. And in Coopers & Lybrand, the Court\\n\\nheld that consideration of class certification involved issues intertwined\\n\\nwith the merits because class certification involves merits-related matters\\n\\nlike the typicality of the claims, the adequacy of a representative, and the\\n\\npresence of common questions of law or fact. 437 U.S. at 469 & n.12.\\n\\nThus, the Court held that the collateral-order doctrine does not cover\\n\\ndenials of class certification. Id. at 469. Neither case involved actual\\n\\n\\n\\n 17\\n\\nconsideration of the merits; but in both cases, the issues overlapped with\\n\\nthe merits.\\n\\n Like issues involving forum non conveniens and class certification,\\n\\nthe issue of good cause will often overlap with a court’s preliminary\\n\\nassessment of the merits, preventing application of the collateral-order\\n\\ndoctrine. See Cunningham v. Hamilton Cty., Ohio, 527 U.S. 198, 205\\n\\n(1999) (holding that sanctions orders under Fed. R. Civ. P. 37(a) do not\\n\\nfall under the collateral-order doctrine because they “often will be\\n\\ninextricably intertwined with the merits of the action,” “[m]uch like the\\n\\norders at issue in Van Cauwenberghe and Coopers & Lybrand”).\\n\\n Here, for example, Utah challenges the finding of good cause,\\n\\narguing that Mr. Kell could have asserted the claim at trial and in a direct\\n\\nappeal. To address this argument, we would need to ask whether Mr. Kell’s\\n\\nattorneys should have asserted the claim at trial or in the direct appeal.\\n\\nThis inquiry would presumably overlap with Mr. Kell’s habeas claims of\\n\\nineffective assistance of counsel. Thus, resolution of Utah’s arguments on\\n\\ngood cause could entangle us in the substance of Mr. Kell’s underlying\\n\\nhabeas claims. In these circumstances, consideration of good cause under\\n\\nRhines is not categorically separate from the merits. 10\\n\\n\\n10\\n The dissent questions our application of the requirement of complete\\nseparation, stating that we are avoiding the “obvious” reality that the\\ndefinition of the standard for good cause is “a purely legal issue that has\\n\\n 18\\n\\n b. Timeliness, Dilatoriness, and Procedural Default\\n\\n In this appeal, Utah also argues that (1) Mr. Kell was dilatory and\\n\\n(2) his unexhausted claim is untimely and procedurally defaulted. Utah\\n\\ndoes not suggest that these arguments would support collateral-order\\n\\njurisdiction. But the dissent does, stating that timeliness, dilatoriness, and\\n\\nprocedural default are separate from the merits.\\n\\n For the sake of argument, let’s assume that the dissent is right and\\n\\nignore the fact that Utah (the appellant invoking appellate jurisdiction)\\n\\ndidn’t present these arguments as grounds to invoke the collateral-order\\n\\ndoctrine. See pp. 35–36, below (citing cases for the unavailability of sua\\n\\nsponte arguments to support jurisdiction). As Utah argues, however, the\\n\\nseparate issue must also be considered important in order to trigger this\\n\\n\\nno overlap with the merits of the case.” Dissent at 14 (emphasis in\\noriginal). The dissent bases its disagreement on footnote ten in Mitchell v.\\nForsyth, 472 U.S. 511 (1984). Dissent at 14. But this footnote explains that\\nan issue is not considered “completely separate” from the merits when its\\neffect “may depend . . . on the success of the parties in litigating the other\\nlegal and factual issues that form their underlying dispute.” Mitchell, 472\\nU.S. at 529–30 n.10 (emphasis added).\\n\\n The Supreme Court illustrated this point with a disqualification\\norder. Id. The disqualification order failed this requirement of “complete\\nseparation” because it was “not a legal issue that [could] be decided with\\nreference only to undisputed facts and in isolation from the remaining\\nissues of the case.” Id.\\n\\n Under Mitchell’s footnote ten, misapplication of Rhines’s\\nrequirement of good cause could not satisfy the “complete separation”\\nrequirement unless the issue were categorically separate from the merits of\\nany of the habeas claims.\\n 19\\n\\ndoctrine. See p. 5, above. Neither Utah nor the dissent offers any argument\\n\\nabout the importance of Utah’s arguments on timeliness, dilatoriness, or\\n\\nprocedural default. These arguments involve garden-variety application of\\n\\nlegal principles settled long ago. See U.S. Fidelity & Guaranty Co. v. Arch\\n\\nIns. Co., 578 F.3d 45, 59 (1st Cir. 2009) (concluding that an issue\\n\\ninvolving insufficiency of an affidavit was not “important enough . . . to\\n\\njustify the application of the collateral order doctrine”); United States v.\\n\\nBillmyer, 57 F.3d 31, 35 (1st Cir. 1995) (“Ordinarily, a discovery order\\n\\nwill meet the legal-importance test only if it presents a claim of clear-cut\\n\\nlegal error and not merely a challenge to the district judge’s factual\\n\\ndeterminations or the application of settled legal rule to the particular\\n\\nfacts.”). Thus, Utah’s arguments on timeliness, dilatoriness, and procedural\\n\\ndefault would not constitute important issues, as required to trigger the\\n\\ncollateral-order doctrine.\\n\\n c. The Categorical Approach\\n\\n Perhaps in some appeals of Rhines stays, the specific argument being\\n\\nadvanced might not involve the potential merit of an unexhausted claim.\\n\\nBut the Supreme Court has “consistently eschewed a case-by-case approach\\n\\nto deciding whether an order is sufficiently collateral.” Cunningham v.\\n\\n\\n\\n\\n 20\\n\\nHamilton Cty., Ohio, 527 U.S. 198, 206 (1999); see also p. 11 & n.5\\n\\n(discussing United States v. Bolden, 353 F.3d 870, 876 (10th Cir. 2003)).\\n\\n The wisdom of the Supreme Court’s approach is self-evident. For\\n\\nexample, let’s assume that Utah’s appellate arguments are important and\\n\\ncompletely separate from the merits. If we were to base the collateral-order\\n\\ndoctrine solely on the happenstance of what Utah argues in a given case,\\n\\nwe would be allowing or disallowing interlocutory appeals of all Rhines\\n\\nstays based on what a single party has chosen to argue in a single case.\\n\\nTo avoid this anomaly, the Supreme Court has required us to consider the\\n\\nunderlying class of orders rather than the peculiarities of the arguments\\n\\npresented by this particular appellant. See p. 11, above. So here we\\n\\nconsider the entire category of orders. See id.\\n\\n The dissent apparently agrees, stating that we must “look[] to the\\n\\nissues the class of orders (Rhines stays) generally raise.” Dissent at 12.\\n\\nAnd the dissent acknowledges that we are not to focus on “case-specific\\n\\nissues,” such as the issues presented in this particular order granting a\\n\\nRhines stay. Id.\\n\\n With this acknowledgment, the dissent contends that the appellant\\n\\nmust present “at least one issue” that is “completely separate from the\\n\\nmerits.” Id. at 10 (emphasis in original). But the Supreme Court has\\n\\nconsistently rejected this approach, holding that even if some appeals of\\n\\nRhines stays might involve appellate issues separable from the merits, the\\n\\n 21\\n\\ncollateral-order doctrine cannot apply absent complete separation for the\\n\\nentire class of orders. Richardson-Merrell, Inc. v. Koller, 472 U.S. 424,\\n\\n439 (1985); 11 see also Cunningham v. Hamilton Cty., Ohio, 527 U.S. 198,\\n\\n206 (1999) (“Perhaps not every discovery sanction will be inextricably\\n\\nintertwined with the merits, but we have consistently eschewed a case-by-\\n\\ncase approach to deciding whether an order is collateral.”). So when we\\n\\nassess whether the class of orders entails complete separation from the\\n\\nmerits, we consider the issues in all grants of stays under Rhines. The\\n\\npresence of a single issue separate from the merits in a particular appeal\\n\\nwould not trigger the collateral-order doctrine. See Cunningham, 527 U.S.\\n\\nat 205–06 (holding that sanctions orders under Fed. R. Civ. P. 37(a) are\\n\\ncategorically considered intertwined with the merits even though sanctions\\n\\norders are sometimes separate from the merits); Koller, 472 U.S. at 439–40\\n\\n\\n\\n11\\n The Koller Court explained:\\n\\n This Court . . . has expressly rejected efforts to reduce the\\n finality requirement of [28 U.S.C.] § 1291 to a case-by-case\\n determination of whether a particular ruling should be subject to\\n appeal. Even if some orders disqualifying counsel are separable\\n from the merits of the litigation, many are not. Orders\\n disqualifying attorneys on the ground that they should testify at\\n trial, for example, are inextricable from the merits because they\\n involve an assessment of the likely course of the trial and the\\n effect of the attorney’s testimony on the judgment. Appellate\\n review of orders disqualifying counsel for misconduct may be\\n entwined with the merits of the litigation as well.\\n\\n472 U.S. at 439 (citations omitted).\\n 22\\n\\n(holding that orders disqualifying counsel in civil cases are categorically\\n\\nconsidered intertwined with the merits because many are even though some\\n\\naren’t); see also In re Continental Investment Corp., 637 F.2d 1, 6 (1st Cir.\\n\\n1980) (holding “that denials of disqualification motions as a class raise\\n\\nsignificant legal questions too rarely to bring them within the Cohen\\n\\nexception”).\\n\\n The categorical approach is apparent in the Supreme Court’s\\n\\nhandling of qualified immunity. There the Court has held that legal issues\\n\\ninvolving a clearly established violation are completely separate from the\\n\\nmerits. Mitchell v. Forsyth, 472 U.S. 511, 528 (1985). But the Supreme\\n\\nCourt made that determination by considering the issues arising in the\\n\\nentire class of orders rather than in the particular case being reviewed. See\\n\\nid. at 524–30.\\n\\n The Supreme Court later went further, expressly disavowing a case-\\n\\nby-case approach in Johnson vs. Jones, 515 U.S. 304 (1995). There the\\n\\nCourt refused to extend the collateral-order doctrine to cover denials of\\n\\nqualified immunity based on insufficiency of the evidence. Johnson, 515\\n\\nU.S. at 314–15. The Court explained that under the categorical approach,\\n\\nappellate judges could not consider the particular facts to determine the\\n\\napplicability of the collateral-order doctrine. Id. at 315. Instead, judges\\n\\nwere to consider the kinds of issues likely to arise in appeals involving this\\n\\nclass of orders. Id. at 315–17. For example, the Supreme Court\\n\\n 23\\n\\nacknowledged that the facts in Johnson itself were straightforward, but\\n\\nstressed that many cases involving constitutional torts would entail factual\\n\\ndisputes ill-suited for review under the collateral-order doctrine. Id. at\\n\\n316.\\n\\n Beyond qualified immunity, circuit courts have followed the Supreme\\n\\nCourt’s lead by deciding the element of complete separation based on the\\n\\nclass of orders involved rather than approaching this element based on the\\n\\nparticular issues raised by a particular appellant. See Henry v. Lake\\n\\nCharles Am. Press, L.L.C., 566 F.3d 164, 173 (5th Cir. 2009) (“Consistent\\n\\nwith Supreme Court precedent and the general purposes of the final\\n\\njudgment rule, we determine whether an order is appealable as a general or\\n\\ncategorical matter.”); see also In re Carco Electronics, 536 F.3d 211, 213\\n\\n(3d Cir. 2008) (“[T]he Supreme Court’s statement in Cunningham that we\\n\\nshould not apply the collateral order doctrine on a ‘case-by-case’ basis\\n\\nindicates that we should not attempt to carve out individualized, case-\\n\\nspecific exceptions to the general rule that discovery orders are not\\n\\nimmediately appealable.”); Abelesz v. OTP Bank, 692 F.3d 638, 649 (7th\\n\\nCir. 2012) (“The Supreme Court has applied the collateral order rule\\n\\ncategorically, treating different sorts of defenses or issues as either\\n\\ncovered or not covered.”).\\n\\n * * *\\n\\n\\n\\n 24\\n\\n Viewed as a category, interlocutory appeals of Rhines stays would\\n\\ngenerally enmesh us in the merits. Thus, the collateral-order doctrine’s\\n\\nsecond element is not met when the district court grants a Rhines stay.\\n\\n B. The grant of a Rhines stay can be reviewed in the appeal\\n from a final judgment.\\n\\n Utah fails to satisfy not only the collateral-order doctrine’s second\\n\\nelement but also the third element.\\n\\n Under this element, appellate jurisdiction exists only if the issue is\\n\\nimportant and could not otherwise be effectively reviewed after the entry\\n\\nof final judgment. Mitchell v. Forsyth, 472 U.S. 511, 525 (1985). But we\\n\\ndo not just consider unreviewability; we also consider the importance of\\n\\nthe interest lost by deferring review until after the final judgment. See\\n\\nDigital Equip. Corp. v. Desktop Direct, Inc., 511 U.S. 863, 878–79 (1994).\\n\\nThis inquiry entails “a judgment about the value of the interests that would\\n\\nbe lost through rigorous application of the final judgment requirement.” Id.\\n\\nOn this element, Utah hasn’t satisfied its burden.\\n\\n Utah argues that the grant of a Rhines stay is unreviewable after a\\n\\nfinal judgment because (1) the loss of time can never be remedied and (2)\\n\\nthe grant of a stay becomes moot upon entry of a final judgment. We reject\\n\\nboth arguments.\\n\\n As Utah points out, the delay itself is unreviewable because a court\\n\\ncan’t restore Utah’s lost time. But we do not ordinarily regard the loss of\\n\\n\\n 25\\n\\ntime as sufficiently important to trigger the collateral-order doctrine. See\\n\\nUnited States v. Section 17 Tp. 23 North, Range 22 East of IBM, Delaware\\n\\nCty., Okla., 40 F.3d 320, 322 (10th Cir. 1994) (holding that an interest in\\n\\ndefending a forfeiture action now, as opposed to later, “is not the type of\\n\\n‘important’ right which the Supreme Court contemplated as requiring\\n\\nimmediate review in [Digital Equipment Corp. v. Desktop Direct, Inc., 511\\n\\nU.S. 863 (1994)]”). After all, no pretrial decision can ever restore a party’s\\n\\nlost time, and we routinely disallow interlocutory appeals for most pretrial\\n\\ndecisions. See Mesa Oil, Inc. v. United States, 467 F.3d 1252, 1255 (10th\\n\\nCir. 2006) (“The costs of unnecessary litigation caused by what eventually\\n\\nturns out to be an error by the district court is insufficient to warrant an\\n\\ninterlocutory appeal.”); see also In re Kozeny, 236 F.3d 615, 619–20 (10th\\n\\nCir. 2000) (two-judge motions panel) 12 (“If the stay merely delays the\\n\\nfederal litigation, courts have generally held the stay orders not to be\\n\\nappealable.”); accord Kershaw v. Shalala, 9 F.3d 11, 14 (5th Cir. 1993)\\n\\n(“Absent a Moses Cone situation, stay orders . . . are usually not\\n\\n\\n\\n\\n12\\n Because Kozeny was issued by a two-judge motions panel, we would\\nordinarily discount the opinion’s precedential value. Crystal Clear\\nComm’ns, Inc. v. Sw. Bell Tel. Co., 415 F.3d 1171, 1176 n.3 (10th Cir.\\n2005). Here, however, we are not relying on Kozeny for its precedential\\nvalue. We are instead relying only on the opinion’s observation about our\\ngeneral practice in regarding stay orders as unappealable.\\n\\n\\n 26\\n\\nreviewable as collateral orders.”); 13 see also Hon. Edith H. Jones, Appeals\\n\\nof Arbitration Orders—Coming Out of the Serbonian Bog, 31 S. Tex. L.\\n\\nRev. 361, 372 (1990) (“Absent exceptional circumstances, it is unlikely\\n\\nthat an order granting a motion to stay proceedings should be appealable as\\n\\na collateral order.”).\\n\\n Time is a precious commodity in habeas proceedings, particularly\\n\\nwhen the petitioner faces a death sentence (as Mr. Kell does). And until\\n\\nnow, the case has lingered in state and federal courts for roughly a quarter\\n\\nof a century. But we cannot single out particular cases to decide the extent\\n\\nof the interest lost by deferring review. Instead, we must consider the\\n\\npublic interest based on the class of orders (Rhines stays). See Mohawk\\n\\nIndus., Inc. v. Carpenter, 558 U.S. 100, 107 (2009); 14 In re Motor Fuel\\n\\n\\n13\\n In Kershaw, the Fifth Circuit observed that in Moses Cone, the\\nSupreme Court had regarded a stay as final when its purpose and effect\\nwere to surrender jurisdiction of a federal suit to a state court. Kershaw, 9\\nF.3d at 14 (quoting Moses H. Cone Memorial Hosp. v. Mercury Const.\\nCorp., 460 U.S. 1, 11 n.11 (1983)). This case does not involve surrender of\\njurisdiction over a federal suit. Instead, the district court required Mr. Kell\\nto exhaust state-court remedies so that the federal court could consider the\\nhabeas claim.\\n14\\n In Mohawk Industries, the Supreme Court explained:\\n\\n [T]he decisive consideration is whether delaying review until the\\n entry of final judgment “would imperil a substantial public\\n interest” or “some particular value of higher order.”\\n\\n In making this determination, we do not engage in an\\n “individualized jurisdictional inquiry.” Rather, our focus is on\\n\\n 27\\n\\nTemperature Sales Practices Litig., 641 F.3d 470, 482 (10th Cir. 2011)\\n\\n(“When analyzing the third Cohen requirement, we do not consider whether\\n\\nthe circumstances of the particular case before us warrant our immediate\\n\\nreview; rather, we examine whether the entire category of rulings to which\\n\\nthe claim belongs can be adequately vindicated on review of a final\\n\\njudgment or by other means.”). This approach requires us to decide\\n\\nwhether the value that we place on immediate review would override\\n\\nCongress’s policy against piecemeal review.\\n\\n To answer, we must consider the many important interests that exist,\\n\\noften in tension with one another. For example, the state has important\\n\\ninterests in comity and enforcement of its own criminal judgments, which\\n\\nCongress recognized in the Antiterrorism and Effective Death Penalty Act\\n\\nof 1996. See Williams v. Taylor, 529 U.S. 420, 436 (2000) (stating that the\\n\\nAct was designed to advance “comity, finality, and federalism”). But\\n\\nhabeas review inherently creates tension with comity, as federal courts\\n\\nreview decisions by a state’s highest court. See Duckworth v. Eagan, 492\\n\\n\\n\\n “the entire category to which the claim belongs.” As long as the\\n class of claims, taken as a whole, can be adequately vindicated\\n by other means, “the chance that the litigation at hand might be\\n speeded, or a ‘particular injustic[e]’ averted,” does not provide\\n a basis for jurisdiction under § 1291.\\n\\nMohawk Indus., 558 U.S. at 107 (citations omitted).\\n\\n\\n 28\\n\\nU.S. 195, 211 (1989) (discussing the tension of federal-state relations\\n\\nbecause of habeas review, where “lower federal courts often sit in ‘review’\\n\\nof the judgments of the highest courts of a state judicial system”).\\n\\n To ease this tension, Congress has required habeas petitioners to\\n\\nexhaust state-court remedies. 28 U.S.C. § 2254(b)(1)(A); see also Rose v.\\n\\nLundy, 455 U.S. 509, 518 (1982) (“The exhaustion doctrine is principally\\n\\ndesigned to protect the state courts’ role in the enforcement of federal law\\n\\nand prevent disruption of state judicial proceedings.”). Exhaustion,\\n\\nhowever, can slow the state’s ability to enforce criminal judgments,\\n\\nespecially those involving capital sentences. See Ira P. Robbins, Toward a\\n\\nMore Just & Effective System of Review in State Death Penalty Cases, 40\\n\\nAm. U. L. Rev. 1, 131 (1990) (“[R]equiring exhaustion [in habeas review\\n\\nof death-penalty cases] usually necessitates further delay, even if the\\n\\nunexhausted claim is an obviously frivolous one.”). This risk is\\n\\nparticularly significant in habeas proceedings, where swift action is\\n\\nessential. See Rhodes v. Hannigan, 12 F.3d 989, 992 (10th Cir. 1993)\\n\\n(“Habeas corpus ‘is a speedy remedy, entitled by statute to special,\\n\\npreferential consideration to insure expeditious hearing and\\n\\ndetermination.’” (quoting Van Buskirk v. Wilkinson, 216 F.2d 735, 737–38\\n\\n(9th Cir. 1954))); Johnson v. Rogers, 917 F.2d 1283, 1284 (10th Cir. 1990)\\n\\n(“[W]rits of habeas corpus are intended to afford a ‘swift and imperative\\n\\n\\n\\n 29\\n\\nremedy in all cases of illegal restraint or confinement.’” (quoting Fay v.\\n\\nNoia, 372 U.S. 391, 400 (1963))).\\n\\n The Supreme Court sought to balance these competing interests in\\n\\nRhines by giving discretion to federal district courts to stay habeas\\n\\nproceedings while a petitioner exhausts state-court remedies. Rhines v.\\n\\nWeber, 544 U.S. 269, 276–78 (2005). But discretion can be abused. The\\n\\nquestion presented here is when an appellate court should review the\\n\\ndistrict court’s exercise of discretion. 15 Given the conflicting interests, we\\n\\nmust consider whether interlocutory review of Rhines stays would speed\\n\\nreview or slow it through piecemeal review.\\n\\n For this inquiry, we start with Congress’s policy against piecemeal\\n\\nreview. In general, Congress has tried to avoid piecemeal review by\\n\\nconfining appellate review to final orders. See Abney v. United States, 431\\n\\nU.S. 651, 656 (1977) (“[T]here has been a firm congressional policy\\n\\nagainst interlocutory or ‘piecemeal’ appeals and courts have consistently\\n\\n\\n15\\n Other circuit courts have generally declined to apply the collateral-\\norder doctrine to orders subject to the abuse-of-discretion standard. See\\nGrace v. Vannoy, 826 F.3d 813, 820 (5th Cir. 2016) (“Typically, orders\\nreviewable for abuse of discretion are not appealable under the collateral-\\norder doctrine.”); In re Kemble, 776 F.2d 802, 806 (9th Cir. 1985)\\n(“Ordinarily we should not use the collateral order doctrine to examine the\\nexercise of discretion by trial judges.”). One leading treatise attributed this\\n“wise” practice to a reluctance to undertake interlocutory review when\\nappellate courts have allowed district courts to exercise discretion. 15A\\nCharles Alan Wright, Arthur R. Miller & Edward H. Cooper, Federal\\nPractice & Procedure: Jurisdiction & Related Matters, § 3911.5, at 433–\\n35 (2d ed. 1992).\\n 30\\n\\ngiven effect to that policy.”). And Congress has expressed its judgment\\n\\n“that the district judge has the primary responsibility to police the\\n\\nprejudgment tactics of litigants,” reasoning “that the district judge can\\n\\nbetter exercise that responsibility if the appellate courts do not repeatedly\\n\\nintervene to second-guess prejudgment rulings.” Richardson-Merrell, Inc.\\n\\nv. Koller, 472 U.S. 424, 436 (1985) (emphasis in original).\\n\\n The Supreme Court has respected this congressional policy choice\\n\\nand restricted prejudgment review because it inefficiently fosters\\n\\npiecemeal appeals. See Mohawk Indus., Inc. v. Carpenter, 558 U.S. 100,\\n\\n106 (2009) (“Permitting piecemeal, prejudgment appeals, we have\\n\\nrecognized, undermines ‘efficient judicial administration’ and encroaches\\n\\nupon the prerogatives of district court judges, who play a ‘special role’ in\\n\\nmanaging ongoing litigation.”); Richardson-Merrell, Inc. v. Koller, 472\\n\\nU.S. 424. 430 (1985) (stating that the final judgment rule prevents delays\\n\\nfrom frequent appellate interruptions in the litigation); Abney, 431 U.S. at\\n\\n657 (stating that 28 U.S.C. § 1291, which restricts appellate review to final\\n\\ndecisions, is designed to prevent delays and disruptions through\\n\\nintermediate appeals).\\n\\n Given Congress’s preference against interlocutory review, we must\\n\\nconsider whether Rhines stays involve aberrant circumstances justifying\\n\\nour intrusion into Congress’s effort to avoid piecemeal review. We think\\n\\n\\n\\n 31\\n\\nnot. In Rhines itself, the Supreme Court balanced the compelling interests\\n\\nby devising a procedure to accommodate\\n\\n the state’s interest in comity,\\n\\n the congressional requirement of exhaustion of state-court\\n remedies,\\n\\n the congressional determination that piecemeal review\\n generally slows the litigation,\\n\\n the universal recognition that habeas cases should proceed\\n expeditiously, and\\n\\n the congressional objective in the Antiterrorism and Effective\\n Death Penalty Act to streamline habeas proceedings.\\n\\nRhines v. Weber, 544 U.S. 269, 276–78 (2005); see Howard v. Norris, 616\\n\\nF.3d 799, 802–03 (8th Cir. 2010) (stating that “Rhines effectively balances\\n\\nthe state’s interest in avoiding delay in a habeas proceeding, with the\\n\\npetitioner’s (and the state’s) interest in having habeas claims addressed\\n\\nfirst in state court”); see also Grace v. Vannoy, 826 F3d 813, 819 (5th Cir.\\n\\n2016) (stating that in Rhines, “the Supreme Court implicitly de-emphasized\\n\\nthe importance of the state’s interests in finality and speedy resolution of\\n\\nmixed federal petitions”).\\n\\n If we were to intervene after a district court granted a stay, would\\n\\nour intervention quicken or slow the litigation? Here, the district court\\n\\nstayed the proceedings for only a single claim and stated that the\\n\\nproceedings would continue on all of the other habeas claims. If we were\\n\\n\\n 32\\n\\nto interject ourselves now, we could inadvertently trigger simultaneous\\n\\nlitigation of the same case in three courts:\\n\\n 1. the state district court or the state appellate court,\\n\\n 2. the federal district court, and\\n\\n 3. our court.\\n\\nWe question the efficiency of duplicative litigation in three courts. See\\n\\nSwanson v. DeSantis, 606 F.3d 829, 833 (6th Cir. 2010) (“Claim-by-claim\\n\\nlitigation in the district and appellate courts ‘undermines [Congress’] goal\\n\\nof streamlining federal habeas proceedings . . . .” (emphasis and alteration\\n\\nin original) (quoting Rhines v. Weber, 544 U.S. 269, 277 (2005))).\\n\\n But double or triple litigation tracks could create not only\\n\\ninefficiency but also more delay. For example, if we were to affirm the\\n\\ngrant of a stay, we could be needlessly slowing the habeas litigation for the\\n\\ntime that we take to decide the appeal. And, of course, district courts\\n\\naren’t limited to the number of Rhines stays in a single case. Here, for\\n\\nexample, the district court has issued two Rhines stays. If those stays had\\n\\ntriggered the collateral-order doctrine, we could have slowed the litigation\\n\\ntwice already with the possibility of a third delay when the case ends in\\n\\ndistrict court. In these circumstances, we decline to single out Rhines stays\\n\\n\\n\\n\\n 33\\n\\nas a class of orders that would be resolved more quickly by authorizing\\n\\npiecemeal appeals. 16\", \"author\": \"BACHARACH, Circuit Judge.\"}, {\"type\": \"dissent\", \"author\": \"Our\", \"text\": \"Our dissenting colleague disagrees, stating that this is not the\\n\\nrelevant question. Dissent at 21. But we are simply addressing the\\n\\narguments presented by Utah and our dissenting colleague. Both argue that\\n\\ninterlocutory review is essential to prevent delays in enforcing the State’s\\n\\ncriminal judgment. Indeed, while challenging our characterization of the\\n\\nquestion, the dissent insists that “[t]he delay—which is, in itself, a win for\\n\\nPetitioner—is exactly what harms the State’s interest.” Id. at 21. In short,\\n\\nthe arguments by Utah and our dissenting colleague require us to consider\\n\\nwhether piecemeal review would truly promote the State’s interest in\\n\\nexpeditious enforcement of its criminal judgments or cause more delay.\\n\\n\\n\\n\\n16\\n Utah contends that these stays have “become the norm” for Utah’s\\ndeath row inmates. In fact, as Utah points out, seven Utah inmates on death\\nrow (including Mr. Kell) have requested Rhines stays. The district court\\ndenied two of these requests. Honie v. Benzon, No. 2:07-cv-628 JAR, dkt.\\nno. 120 (D. Utah. Dec. 13, 2017); Lafferty v. Benzon, No. 2:07-cv-322 DB,\\ndkt. no. 379 (D. Utah Oct. 30, 2015). And in a third case, the respondent\\ndid not object to a Rhines stay. Carter v. Benzon, No. 2:02-cv-326 TS, dkt.\\nnos. 567, 576 (D. Utah Mar. 1, 2016). We thus know only that a slight\\nmajority of capital defendants in Utah have obtained Rhines stays over an\\nobjection. Archuleta v. Benzon, No. 2: 07-cv-630 TC, dkt. no. 107 (D. Utah\\nNov. 12, 2014); Kell v. Benzon, No. 2: 07-cv-359, dkt. nos. 51, 258 (D.\\nUtah Oct. 8, 2009, Nov. 16, 2017); Taylor v. Benzon, No. 2: 07-cv-194 TC,\\ndkt no. 45 (D. Utah Feb. 14, 2008); Menzies v. Benzon, No. 2:03-cv-902\\nTC, dkt. nos. 41, 47 (D. Utah Oct. 27, 2004, May 5, 2005).\\n\\n\\n 34\\n\\n Utah and the dissent also argue that waiting for a final judgment\\n\\nmight prevent any appeal of an order granting a Rhines stay. 17 They\\n\\napparently assume that Rhines stays will always become moot even when\\n\\nthey ultimately lead to a grant of habeas relief. But neither Utah nor the\\n\\ndissent says why a Rhines stay would always become moot with a grant of\\n\\nhabeas relief. 18 See Thompson v. Frank, 599 F.3d 1088, 1090 (9th Cir.\\n\\n2010) (declining to apply the collateral-order doctrine to a Rhines stay\\n\\nbecause it would be reviewable after the final judgment). And we don’t\\n\\nordinarily construct arguments in support of appellate jurisdiction. See\\n\\nUnited States ex rel. Ramseyer v. Century Healthcare Corp., 90 F.3d 1514,\\n\\n1518 n.2 (10th Cir. 1996) (“Our duty to consider unargued obstacles to\\n\\nsubject matter jurisdiction does not affect our discretion to decline to\\n\\nconsider waived arguments that might have supported such jurisdiction.”\\n\\n\\n\\n17\\n Rather than await a final judgment, the government could have\\nsought a writ of mandamus. See Gulfstream Aerospace Corp. v. Mayacamas\\nCorp., 485 U.S. 271, 288 n.13 (1988) (“Issuance of a writ of mandamus\\nwill be appropriate in exceptional cases involving stay orders.”); In re\\nKozeny, 236 F.3d 615, 619–20 (10th Cir. 2000) (two-judge motions panel)\\n(concluding that review of a stay order was properly before the Court of\\nAppeals on a petition for mandamus).\\n18\\n Utah devoted a single sentence to this issue, writing (with no\\nexplanation) that “[t]he grant of a Rhines stay will always be moot and\\nunreviewable on plenary appeal.” Appellant’s Opening Br. at 6. In\\nresponse, Mr. Kell argued that if the district court grants relief on the\\nstayed claim, the Court of Appeals could reverse the entry of a Rhines stay\\nand find the claim unexhausted. Appellee’s Response Br. at 6. Utah failed\\nto respond to this argument in its reply brief.\\n 35\\n\\n(emphasis in original)); see also Raley v. Hyundai Motor Co., 642 F.3d\\n\\n1271, 1275 (10th Cir. 2011) (Gorsuch, J.) (“It is the appellant’s burden,\\n\\nnot ours, to conjure up possible theories to invoke our legal authority to\\n\\nhear her appeal.”). Given our reluctance to construct arguments for\\n\\nappellate jurisdiction, we cannot assume—as Utah and the dissent do—that\\n\\nreview of a Rhines stay would become moot if Mr. Kell were to obtain\\n\\nhabeas relief.\\n\\n Even if review of the grant of a Rhines stay would eventually become\\n\\nmoot, however, the final judgment would certainly be appealable. See\\n\\nAlexander v. U.S. Parole Comm’n, 514 F.3d 1083, 1097 (10th Cir. 2008)\\n\\n(stating that a conditional writ of habeas corpus is final, creating appellate\\n\\njurisdiction); Burton v. Johnson, 975 F.2d 690, 693-94 (10th Cir. 1993)\\n\\n(stating that a conditional writ of habeas corpus was an appealable final\\n\\njudgment). Because the district court’s ultimate rulings on the habeas\\n\\nclaims would be reviewable after the final judgment, the collateral-order\\n\\ndoctrine’s third element would remain unsatisfied even if the grant of a\\n\\nRhines stay were to become moot. See Bean v. Dormire, 10 F.3d 538, 539\\n\\n(8th Cir. 1993) (per curiam) (holding that the third element of the\\n\\ncollateral-order doctrine is unsatisfied in a case involving the stay of a\\n\\nprisoner’s § 1983 action because the prisoner’s underlying claims would be\\n\\nreviewable later even if the stay itself were otherwise unreviewable). The\\n\\nonly difference is that waiting for a final judgment would postpone the\\n\\n 36\\n\\nappeal. But as discussed above, the delay results from a congressional\\n\\npolicy choice. See pp. 28–34, above.\\n\\n * * *\\n\\n The issues in Rhines stays are not categorically separate from the\\n\\nmerits and can be effectively reviewed in an appeal from a final judgment.\\n\\nSo two of the three elements of the collateral-order doctrine are absent,\\n\\nprecluding appellate jurisdiction.\\n\\n C. The Supreme Court’s consideration of the merits in Rhines\\n does not support jurisdiction here.\\n\\n Finally, Utah contends that appellate jurisdiction is supported by the\\n\\nSupreme Court’s decision in Rhines to reach the merits. This contention is\\n\\nbased on two steps:\\n\\n 1. Rhines v. Weber was appealed to the Eighth Circuit as a\\n collateral order. See Rhines v. Weber, 346 F.3d 799, 800 (8th\\n Cir. 2003) (per curiam).\\n\\n 2. If the Eighth Circuit had lacked jurisdiction in Rhines, the\\n Supreme Court would not have reached the merits.\\n\\nWe reject this contention.\\n\\n In Rhines, appellate jurisdiction was not mentioned in any of the\\n\\nbriefs or in the Supreme Court’s opinion. And “[w]hen a potential\\n\\njurisdictional defect is neither noted nor discussed in a federal decision,\\n\\nthe decision does not stand for the proposition that no defect existed.”\\n\\nAriz. Christian School Tuition Org. v. Winn, 563 U.S. 125, 144 (2011).\\n\\n\\n\\n 37\\n\\n But it wouldn’t matter here even if the Supreme Court had implicitly\\n\\nblessed application of the collateral-order doctrine in Rhines. Before\\n\\nRhines was appealed to the Eighth Circuit, that court’s opinion in\\n\\nCarmichael v. White had allowed stays of mixed habeas petitions only in\\n\\n“truly exceptional circumstances.” Carmichael v. White, 163 F.3d 1044,\\n\\n1045 (8th Cir. 1998). So when Rhines was appealed to the Eighth Circuit,\\n\\nthe court applied the test that had been used in Carmichael. See Rhines v.\\n\\nWeber, 346 F.3d 799, 800 (8th Cir. 2003) (per curiam) (citing Carmichael,\\n\\n163 F.3d at 1045).\\n\\n When Rhines later went to the Supreme Court, the parties disagreed\\n\\nover the validity of the Eighth Circuit’s test and the extent of a district\\n\\ncourt’s authority to stay, consider, or dismiss mixed habeas petitions. See\\n\\nRhines v. Weber, 544 U.S. 269, 273 (2005). The Supreme Court resolved\\n\\nthis disagreement in Rhines by creating a new test for stays when some of\\n\\nthe habeas claims are unexhausted. See id. at 277–78.\\n\\n Given the Supreme Court’s creation of a new test in Rhines, our\\n\\nconsideration of Utah’s appeal would entail\\n\\n the application of the Rhines factors rather than the previous\\n Eighth Circuit test and\\n\\n the appropriateness of a stay rather than the district court’s\\n authority to stay, consider, or dismiss mixed habeas petitions.\\n\\nThese issues did not exist when Rhines was appealed to the Eighth Circuit.\\n\\nSo even if the Supreme Court had silently concluded that the collateral-\\n 38\\n\\norder doctrine applies to stays granted under the test in Carmichael, that\\n\\nconclusion would not apply to an appeal addressing the appropriateness of\\n\\na stay based on the Rhines factors. See Howard v. Norris, 616 F.3d 799,\\n\\n802–03 (8th Cir. 2010) (noting that the Eighth Circuit’s pre-Rhines\\n\\nrationale for applying the collateral-order doctrine to stays of habeas\\n\\nproceedings was “no longer applicable”). As a result, Rhines’s procedural\\n\\nposture supplies no meaningful guidance on our jurisdictional issue.\\n\\n5. Conclusion\\n\\n We lack appellate jurisdiction. A Rhines stay is not a final decision,\\n\\nand two elements of the collateral-order doctrine are not met. This doctrine\\n\\napplies only when the order conclusively decides an important question,\\n\\nseparate from the merits, that would be effectively unreviewable in a direct\\n\\nappeal from a final judgment. But when Rhines stays are viewed\\n\\ncategorically, the issues are generally inseparable from the merits and\\n\\nreviewable after entry of the final judgment. We thus lack appellate\\n\\njurisdiction and dismiss the appeal.\\n\\n\\n\\n\\n 39\\n\\n17-4191, Kell v. Benzon\"}, {\"author\": \"BALDOCK, Circuit Judge, dissenting\", \"type\": \"dissent\", \"text\": \"BALDOCK, Circuit Judge, dissenting:\\n\\n Today, this Court holds we do not have appellate jurisdiction over grants of Rhines\\n\\nstays in capital cases. In so holding, the Court fails to see the forest for the trees. Despite\\n\\nthe Supreme Court’s repeated admonitions that we should give 28 U.S.C. § 1291 a\\n\\n“practical” rather than a “technical” construction, the Court takes an overly technical view\\n\\nof § 1291 by neglecting to put the grant of a Rhines stay in the proper context of AEDPA\\n\\nand the policy behind enforcing a stringent final judgment rule. The Court further ignores\\n\\nsalient Supreme Court precedent about the collateral order doctrine and severely\\n\\nunderstates a state’s important interest in executing its sentence of death without delay—\\n\\nin this case, against Petitioner Troy Kell, who brutally murdered a fellow inmate almost\\n\\ntwenty-five years ago. For these reasons, I cannot join the Court’s opinion.\\n\\n I.\\n\\n The Court’s opinion brings to mind the 1989 Report of the Ad Hoc Committee on\\n\\nFederal Habeas Corpus in Capital Cases, which was formed by Chief Justice Rehnquist\\n\\nand chaired by Justice Powell. Judicial Conference of the U.S., Ad Hoc Comm. on Fed.\\n\\nHabeas Corpus in Capital Cases, Comm. Report and Proposal (Aug. 23, 1989) [hereinafter\\n\\nPowell Comm. Report]. The Committee determined federal habeas law “has led to\\n\\npiecemeal and repetitious litigation, and years of delay between sentencing and a judicial\\n\\nresolution as to whether the sentence was permissible under the law.” Id. at 1. The\\n\\nCommittee specifically noted: “The lack of coordination between the federal and state legal\\n\\nsystems often results in inefficient and unnecessary steps in the course of litigation.” Id.\\n\\nat 2.\\n\\n Against this backdrop, Congress passed the Antiterrorism and Effective Death\\n\\nPenalty Act of 1996 (AEDPA)—the long title of which is “An Act to deter terrorism,\\n\\nprovide justice for victims, provide for an effective death penalty, and for other purposes.”\\n\\nPub. L. No. 104-132, 110 Stat. 1214 (1996) (emphasis added). In providing for an effective\\n\\ndeath penalty, AEDPA aims to “reduce delays in the execution of state and federal criminal\\n\\nsentences, particularly in capital cases.” Rhines v. Weber, 544 U.S. 269, 276 (2005) (citing\\n\\nWoodford v. Garceau, 538 U.S. 202, 206 (2003)). Toward this end, AEDPA imposes a\\n\\none-year statute of limitations on the filing of a federal habeas petition. 28 U.S.C.\\n\\n§ 2244(d). Another purpose of AEDPA is to promote comity by “encourag[ing] petitioners\\n\\nto seek relief from state courts in the first instance.” Rhines, 544 U.S. at 276. AEDPA\\n\\nachieves this goal by “tolling the 1-year limitations period while a ‘properly filed\\n\\napplication for State post-conviction or other collateral review’ is pending.” Id. (citing 28\\n\\nU.S.C. § 2244(d)(2)).\\n\\n Prior to the passage of AEDPA, a district court was required to dismiss a federal\\n\\nhabeas petition that included both exhausted and unexhausted claims—that is, a “mixed”\\n\\npetition. Rose v. Lundy, 455 U.S. 509, 510 (1982). After dismissal, a petitioner could\\n\\neither resubmit the habeas petition with only exhausted claims or exhaust his claims in state\\n\\ncourt and later file a new petition in federal court. Id. The Powell Committee specifically\\n\\nidentified this “moving back and forth between the federal and state systems in the process\\n\\nof exhausting state remedies” as one of the aforementioned “inefficient and unnecessary\\n\\n 2\\n\\nsteps in the course of litigation.” Powell Comm. Report, supra page 1, at 2. After Congress\\n\\npassed AEDPA, Lundy’s total exhaustion rule created a problem when petitioners filed\\n\\nmixed petitions in federal court. Because of the new one-year statute of limitations,\\n\\ndismissal of mixed petitions pursuant to Lundy likely foreclosed the possibility of federal\\n\\nreview. Rhines, 544 U.S. at 275. To prevent this result, district courts began staying,\\n\\ninstead of dismissing, the federal habeas case to allow the petitioner to exhaust his claims\\n\\nin state court. Id. at 276. The district court would then lift the stay after the petitioner\\n\\nexhausted his claims and resume federal proceedings. Id. at 276–77.\\n\\n In Rhines, the Supreme Court upheld this stay-and-abeyance procedure but\\n\\nacknowledged “[s]tay and abeyance, if employed too frequently, has the potential to\\n\\nundermine” the purposes of AEDPA. Id. at 277. Rather than reducing delays in the\\n\\nexecution of a sentence, stay and abeyance “allow[s] a petitioner to delay the resolution of\\n\\nthe federal proceedings.” Id. And rather than encouraging petitioners to first seek relief in\\n\\nstate court, stay and abeyance “decreas[es] a petitioner’s incentive to exhaust all his claims\\n\\nin state court prior to filing his federal petition.” Id. Stay and abeyance potentially\\n\\nundermines AEDPA’s purposes even more in capital cases, for capital petitioners alone\\n\\nhave every incentive “to prolong their incarceration and avoid execution of the sentence of\\n\\ndeath.” Id. at 277–78; see also Lundy, 455 U.S. at 520 (“The [non-capital] prisoner’s\\n\\nprincipal interest, of course, is in obtaining speedy federal relief on his claims.”). Thus,\\n\\nthe Supreme Court cautioned that stay and abeyance of mixed petitions “should be\\n\\navailable only in limited circumstances.” Id. at 277 (emphasis added). Specifically, stay\\n\\nand abeyance is only available if “[1] the petitioner had good cause for his failure to\\n\\n 3\\n\\nexhaust, [2] his unexhausted claims are potentially meritorious, and [3] there is no\\n\\nindication that the petitioner engaged in intentionally dilatory litigation tactics.” Id. at 278.\\n\\n II.\\n\\n In 1994, Petitioner Troy Kell, a white supremacist incarcerated in state prison,\\n\\nstabbed African-American inmate Lonnie Blackmon sixty-seven times. Petitioner’s attack\\n\\nlasted approximately two and a half minutes, during which Petitioner walked away twice\\n\\nonly to return again to Blackmon’s writhing body to continue to stab him. Blackmon, who\\n\\nwas handcuffed and held down by Petitioner’s accomplice during the attack, bled to death.\\n\\nThe facts of the murder have never been in dispute, as the murder was captured on prison\\n\\nsecurity video. Petitioner proceeded to trial, and in 1996, a jury found Petitioner guilty of\\n\\naggravated murder and sentenced him to death. In 2002, the Supreme Court of Utah upheld\\n\\nhis conviction and sentence on direct appeal. State v. Kell, 61 P.3d 1019 (Utah 2002).\\n\\nPetitioner then pursued state post-conviction relief. The post-conviction court dismissed\\n\\nthe petition, and the Supreme Court of Utah upheld this dismissal in 2008. Kell v. State,\\n\\n194 P.3d 913 (Utah 2008). In January 2009, Petitioner filed a pro se motion for relief under\\n\\nUtah Rule of Civil Procedure 60(b), alleging ineffective assistance of his appointed post-\\n\\nconviction counsel. Later in 2009, Petitioner, through appointed counsel, filed a federal\\n\\nhabeas petition. Shortly thereafter, Petitioner sought and received a Rhines stay in his\\n\\nfederal case while he pursued his claims in state court. In 2012, Petitioner’s state claims\\n\\nwere denied. Kell v. State, 285 P.3d 1133 (Utah 2012).\\n\\n Petitioner’s federal case resumed after the three-year Rhines stay. In 2013,\\n\\nPetitioner filed an amended habeas petition. In this petition filed seventeen years after his\\n\\n 4\\n\\nconviction, Petitioner raised the new claim that the trial court gave an unconstitutional\\n\\nsupplemental jury instruction that shifted the burden of proof onto Petitioner during the\\n\\npenalty phase deliberations. In support, Petitioner attached three juror declarations signed\\n\\neight months before he filed his amended petition. Two jurors recalled the trial judge\\n\\nspeaking to the jury after deliberations began. The other juror recalled, in more specificity,\\n\\nthat when the judge spoke to the jurors during deliberations, he said “that [Petitioner’s]\\n\\nattorney’s [sic] had to show us that [Petitioner’s] life should be spared.” ROA Vol. IV,\\n\\n666. Petitioner noted “[t]here are no indications in the trial transcripts of a question from\\n\\nthe jury after the beginning of deliberations, either during the guilt or penalty phases.” Id.\\n\\nPetitioner concluded: “The error that resulted from [the trial judge’s] ex parte response\\n\\nwhich shifted the burden of proof for the entire penalty proceeding away from the State\\n\\nand onto [Petitioner], was a prejudicial error of constitutional magnitude, requiring\\n\\nreversal.” Id. at 666–67.\\n\\n Over four and a half years after filing his amended habeas petition, Petitioner filed\\n\\na motion for a second Rhines stay so that he could exhaust his supplemental-instruction\\n\\nclaim (and another claim not relevant to this appeal) in state court. 1 In November 2017,\\n\\nthe district court granted the stay, holding Petitioner satisfied the three Rhines elements\\n\\nbecause (1) there was good cause for not previously exhausting the supplemental-\\n\\n\\n\\n 1\\n The Court states that Petitioner requested a stay in 2014. Maj. Op. at 15 n.8. Just\\nto be clear, this “request” consisted of one sentence buried in a 208-page reply brief to his\\npetition, which obviously has not been ruled on. ROA Vol. VI, 1278. The fact remains\\nthat Petitioner did not file a motion to stay regarding the issue underlying this appeal until\\n2017—over four and a half years after filing his amended habeas petition.\\n 5\\n\\ninstruction claim; (2) the claim was potentially meritorious; and (3) there was no indication\\n\\nPetitioner engaged in abusive or dilatory tactics. As to good cause, Petitioner argued he\\n\\ndid not previously exhaust the supplemental-instruction claim because his post-conviction\\n\\ncounsel was ineffective and failed to interview any jurors. In addressing this claim, the\\n\\ndistrict court first explained that neither Supreme Court nor Tenth Circuit precedent has\\n\\ndefined “good cause” in the Rhines context. As a result, some district courts have held\\n\\n“good cause in the Rhines context is akin to good cause to excuse procedural default in\\n\\nfederal court,” while others have given it a “more expansive and equitable reading.” ROA\\n\\nVol. VII, 1725. Relying on a Ninth Circuit opinion and two District of Utah cases, the\\n\\ndistrict court adopted the latter standard that “good cause for a Rhines stay cannot be any\\n\\nmore demanding than a showing of cause for procedural default under Martinez v. Ryan,\\n\\n566 U.S. 1 (2012), and, in fact, may be less demanding.” Id. at 1726 (citing Blake v. Baker,\\n\\n745 F.3d 977 (9th Cir. 2014); Lafferty v. Crowther, No. 2:07-CV-322, ECF No. 379 (D.\\n\\nUtah Oct. 30, 2015); Archuleta v. Crowther, No. 2:07-CV-630, ECF No. 107 (D. Utah\\n\\nNov. 12, 2014)). After establishing the standard, the court concluded that Petitioner’s\\n\\n“post-conviction counsel’s deficient performance constitutes cause under Rhines.” Id. at\\n\\n1727.\\n\\n Regarding the potential merit of the supplemental-instruction claim, the district\\n\\ncourt did not consider the State’s arguments that the claim would be time-barred or\\n\\nprocedurally barred in state court. Invoking notions of “federalism” and “comity,” the\\n\\ncourt held the state courts must “have the opportunity to make those procedural decisions.”\\n\\nId. at 1728–29. The court then explained Petitioner’s claim and apparently held it was\\n\\n 6\\n\\npotentially meritorious. The district court’s analysis—which, again, purports to be about\\n\\nwhether the supplemental-instruction claim was potentially meritorious—reads in full:\\n\\n Counsel in [Petitioner’s] state habeas proceedings admitted that he was\\n unaware of this issue because he failed to speak with any of the jurors, and\\n that there was no strategic reason for his failure to do so. Because counsel\\n was unaware of the issue, he failed to raise this claim to the state court,\\n meaning that [Petitioner] has been denied the opportunity to have this\\n potentially significant claim reviewed by the state court. Counsel’s failure to\\n raise this potentially meritorious claim constitutes good cause under Rhines.\\n\\nId. at 1732 (citation omitted). In other words, the district court concluded Petitioner’s claim\\n\\nwas potentially meritorious without analyzing whether the claim was potentially\\n\\nmeritorious. Instead, the district court looked to Petitioner’s counsel’s failure to investigate\\n\\nand raise the claim in state court—considerations not at all relevant to whether Petitioner’s\\n\\nconstitutional rights were potentially violated by an alleged ex parte supplemental jury\\n\\ninstruction—and confusingly determined this failure constitutes “good cause,” a\\n\\nconclusion the court had already reached in element one.\\n\\n Lastly, the district court held there was “no indication that [Petitioner] has engaged\\n\\nin intentional or abusive dilatory litigation tactics.” Id. at 1733. The court reasoned federal\\n\\nproceedings were stayed until 2012, and Petitioner had followed the case management\\n\\nschedule. Rejecting the State’s argument that nothing prevented Petitioner from bringing\\n\\nthe claim in state court earlier, the court held Petitioner satisfied the third Rhines element.\\n\\n After determining all three elements were satisfied, the district court issued the stay.\\n\\nOnly then did Petitioner file a petition in state court raising the supplemental-instruction\\n\\nclaim. Not surprisingly, the state trial court has since rejected this claim as both time and\\n\\n\\n\\n 7\\n\\nprocedurally barred. The case is now pending before the Supreme Court of Utah. Kell v.\\n\\nBenzon, No. 20180788 (appeal docketed Oct. 1, 2018).\\n\\n In the meantime, the State requested that the district court certify for immediate\\n\\nappeal its grant of a second Rhines stay under 28 U.S.C. § 1292(b). The district court\\n\\ndenied the State’s request because “there is not sufficient basis to find a difference of\\n\\nopinion on which [good cause] standard should apply”—a conclusion that is simply\\n\\nimpossible to reconcile with the court’s previous order noting district courts have applied\\n\\ndifferent “good cause” standards. Doc. 279, at 4. The State also sought to appeal the stay\\n\\npursuant to 28 U.S.C. § 1291, arguing (1) the standard for “good cause” under Rhines\\n\\nshould be the same as “cause” to overcome procedural default and (2) the district court\\n\\nabused its discretion under all three Rhines elements in granting the stay. Before we can\\n\\nreach the merits of these arguments, we must of course have jurisdiction to do so. Because\\n\\nthis is an interlocutory appeal and the district court oddly enough saw fit to deny the State’s\\n\\nrequest for certification of appeal under § 1292(b), the only potential basis for this Court\\n\\nto exercise jurisdiction is § 1291 by way of the collateral order doctrine. 2\\n\\n\\n 2\\n I preface my discussion of the collateral order doctrine by noting Rhines itself was\\nappealed to the Eighth Circuit pursuant to the collateral order doctrine. Rhines v. Weber,\\n346 F.3d 799, 800 (8th Cir. 2003) (per curiam) (“We have jurisdiction under the collateral\\norder doctrine to review an interlocutory order holding a habeas petition in abeyance\\npending exhaustion of state court remedies.”), vacated on other grounds, 544 U.S. 269\\n(2005). The Supreme Court granted certiorari in the case and, without mentioning the\\njurisdictional issue, proceeded to the merits. Rhines, 544 U.S. 269. Even more, the\\nSupreme Court remanded the case to the Eighth Circuit to exercise jurisdiction and\\nadjudicate the case in accordance with the Supreme Court’s opinion. Id. at 279.\\n Federal courts, including the Supreme Court, “have an independent obligation to\\ndetermine whether subject-matter jurisdiction exists, even in the absence of a challenge\\nfrom any party.” Arbaugh v. Y&H Corp., 546 U.S. 500, 514 (2006). The Supreme Court\\n 8\\n\\n III.\\n\\n This Court has “jurisdiction of appeals from all final decisions of the district courts\\n\\nof the United States[.]” 28 U.S.C. § 1291. Encompassed in section 1291’s definition of\\n\\n“final decisions” is “a ‘small class’ of collateral rulings that, although they do not end the\\n\\nlitigation, are appropriately deemed ‘final.’” Mohawk Indus., Inc. v. Carpenter, 558 U.S.\\n\\n100, 106 (2009). This “small class” includes decisions that “finally determine claims of\\n\\nright separable from, and collateral to, rights asserted in the action, too important to be\\n\\ndenied review and too independent of the cause itself to require that appellate consideration\\n\\nbe deferred until the whole case is adjudicated.” Cohen v. Beneficial Indus. Loan Corp.,\\n\\n337 U.S. 541, 546 (1949) (emphasis added). The Supreme Court “has long given [section\\n\\n1291] this practical rather than a technical construction,” id. (emphasis added), and has\\n\\nemphasized the class of collaterally appealable orders is “narrow and selective in its\\n\\nmembership,” Will, 546 U.S. at 350. As the Court’s opinion explains, to fall within this\\n\\nnarrow class of decisions, the order must (1) be “conclusive”; (2) “resolve important\\n\\nquestions separate from the merits”; and (3) be “effectively unreviewable on appeal from\\n\\n\\n\\nhas undertaken this independent obligation and vigilantly guarded the exclusivity of the\\ncollateral order doctrine. See Will v. Hallock, 546 U.S. 345, 350 (2006) (“[W]e have meant\\nwhat we have said; although the Court has been asked many times to expand the ‘small\\nclass’ of collaterally appealable orders, we have instead kept it narrow and selective in\\nmembership.”). In Will, for example, after granting certiorari on the merits of an issue, the\\nSupreme Court vacated and remanded to the Court of Appeals to dismiss for lack of\\njurisdiction because the underlying order was not immediately appealable under the\\ncollateral order doctrine. Id. at 349. At the same time, as this Court points out, the Supreme\\nCourt’s prior exercise of jurisdiction and subsequent remand in Rhines do not necessarily\\nstand for the proposition that the stay was immediately appealable under the collateral order\\ndoctrine. See Hagans v. Lavine, 415 U.S. 528, 535 n.5 (1974).\\n\\n 9\\n\\nthe final judgment in the underlying action.” Swint v. Chambers Cty. Comm’n, 514 U.S.\\n\\n35, 41 (1995). As no question exists whether the first element is satisfied, I turn to the\\n\\nsecond and third elements. 3\\n\\n A.\\n\\n The second collateral order doctrine element requires the order to “resolve important\\n\\nquestions separate from the merits.” Swint, 514 U.S. at 41. This separateness requirement\\n\\n“is a distillation of the principle that there should not be piecemeal review of ‘steps towards\\n\\nfinal judgment in which they will merge.’” Moses H. Cone, 460 U.S. at 12 n.13. The Court\\n\\nand I differ on exactly what must be separate in order to satisfy this element. Whereas this\\n\\nCourt holds the entire collateral order must be completely separate from the merits, I\\n\\ncontend that at least one issue involved in granting a Rhines stay must be completely\\n\\nseparate from the merits. This is clearly what the Supreme Court has required. E.g.,\\n\\nMicrosoft Corp. v. Baker, 137 S. Ct. 1702, 1708 n.3 (2017) (stating the decision must\\n\\n“resolve important issues ‘completely separate from the merits’” (emphasis added)); Will,\\n\\n546 U.S. at 349 (stating the order must “resolve an important issue completely separate\\n\\nfrom the merits of the action” (emphasis added)); Sell v. United States, 539 U.S. 166, 176\\n\\n\\n 3\\n An order is “conclusive” when “nothing in the subsequent course of the\\nproceedings in the district court . . . can alter the court’s conclusion.” See Mitchell v.\\nForsyth, 472 U.S. 511, 527 (1985). This element is plainly met here. Nothing was tentative\\nabout the determination that Petitioner’s federal proceedings would halt while Petitioner\\nexhausted his supplemental-instruction claim in state court. A grant of a Rhines stay is\\nonly subject to revision in the same way every order is subject to revision. See Moses H.\\nCone Mem’l Hosp. v. Mercury Constr. Corp., 460 U.S. 1, 12 & n.14 (1983). This indicates\\n“nothing in the subsequent course of the proceedings in the district court . . . can alter the\\ncourt’s conclusion” that Petitioner was entitled to a Rhines stay. Accordingly, the district\\ncourt’s grant of a Rhines stay is conclusive.\\n 10\\n\\n(2003) (stating a decision is “appealable as a collateral order when it . . . resolves an\\n\\nimportant issue completely separate from the merits of the action” (emphasis added)\\n\\n(brackets and quotations omitted)); Quackenbush v. Allstate Ins. Co., 517 U.S. 706, 712\\n\\n(1996) (stating the order must “conclusively determine a disputed question that is\\n\\ncompletely separate from the merits of the action” (emphasis added) (brackets and\\n\\nquotations omitted)); Johnson v. Jones, 515 U.S. 304, 310–11 (1995) (stating the order\\n\\nmust “resolve an important issue completely separate from the merits of the action”\\n\\n(emphasis added)); Dig. Equip. Corp. v. Desktop Direct, Inc., 511 U.S. 863, 867 (1994)\\n\\n(stating the decision must “resolve important questions completely separate from the\\n\\nmerits” (emphasis added)); Richardson-Merrell, Inc. v. Koller, 472 U.S. 424, 431 (1985)\\n\\n(stating the order must “resolve an important issue completely separate from the merits of\\n\\nthe action” (emphasis added)); Coopers & Lybrand v. Livesay, 437 U.S. 463, 468 (1978)\\n\\n(stating “the order must . . . resolve an important issue completely separate from the merits\\n\\nof the action” (emphasis added)); Abney v. United States, 431 U.S. 651, 658 (1977) (stating\\n\\nthe decision in Cohen “resolved an issue completely collateral to the cause of action\\n\\nasserted” (emphasis added)).\\n\\n Of utmost importance, in each of these cases, “completely separate” modified\\n\\n“issues,” “an issue,” “a question,” and “questions,” not “an order.” Therefore, the only\\n\\nreasonable conclusion to be reached is that there must be “an issue” that is “completely\\n\\nseparate” from the merits of the action. Such a conclusion is consistent with the Supreme\\n\\nCourt’s explicit rejection of the argument that there must be no overlap whatsoever\\n\\nbetween a collateral order and the merits of a claim. Mitchell, 472 U.S. at 529 n.10. In\\n\\n 11\\n\\nMitchell, the Supreme Court explained that if “any factual overlap between a collateral\\n\\nissue and the merits of the plaintiff’s claim is fatal to a claim of immediate appealability,”\\n\\nthen denials of claims of double jeopardy and absolute immunity could not be appealed,\\n\\nfor such claims necessarily require an inquiry into a plaintiff’s factual allegations. Id. But\\n\\nthese claims are appealable pursuant to the collateral order doctrine. Nixon v. Fitzgerald,\\n\\n457 U.S. 731, 742–43 (1982); Abney, 431 U.S. at 662. With this understanding, the\\n\\nSupreme Court held an order denying qualified immunity is immediately appealable.\\n\\nMitchell, 472 U.S. at 530.\\n\\n The Court today understands this to contravene the requirement that we must view\\n\\nthe class of orders as a whole. To be clear, I absolutely agree with the well-settled\\n\\nrequirement that we must focus on the class of orders. We cannot focus on the class of\\n\\norders, however, without looking to the issues the class of orders generally raise. Here, we\\n\\nmust look to Rhines-stay-specific issues. Looking to Rhines-stay-specific issues is wholly\\n\\ndifferent than analyzing the issues on a case-by-case basis. At no point in this dissent do I\\n\\nadvocate for analyzing case-specific issues—something the Court and I agree is\\n\\nunacceptable. In sum, we must look to issues that orders granting Rhines stays generally\\n\\nraise (as opposed to the issues this order granting a Rhines stay raises); if one or more of\\n\\nthese issues is completely separate from the merits, this element is satisfied. From what I\\n\\nunderstand, the Court thinks we must look to issues that any order granting a Rhines stay\\n\\ncould hypothetically raise; if any of these issues overlap with the merits, this element is not\\n\\nsatisfied. This understanding does not comport with Supreme Court precedent, nor our\\n\\nown. Mitchell, 472 U.S. at 529 n.10; United States v. Bolden, 353 F.3d 870, 876 (10th Cir.\\n\\n 12\\n\\n2003) (assuming without deciding an issue implicated in an order could overlap with the\\n\\nunderlying merits but that “on the whole such orders . . . satisfy the separability\\n\\nrequirement”).\\n\\n The requirement that there be “an issue” that is “completely separate” from the\\n\\nmerits is undoubtedly met in this case. In fact, at least three such issues are involved in\\n\\ngranting a Rhines stay. The first, which is a purely legal issue, is whether the appropriate\\n\\nstandard for “good cause” is akin to “cause” to overcome procedural default or is\\n\\nsomething less stringent. “Cause” to overcome procedural default requires a petitioner to\\n\\nshow “something external to the petitioner, something that cannot fairly be attributed to\\n\\nhim” or his counsel prevented the petitioner from raising a claim. Coleman v. Thompson,\\n\\n501 U.S. 722, 753 (1991). Neither we nor the Supreme Court has applied this definition\\n\\nor otherwise defined “good cause” in the Rhines context. In dicta, however, the Supreme\\n\\nCourt has stated that “[a] petitioner’s reasonable confusion about whether a state filing\\n\\nwould be timely will ordinarily constitute ‘good cause’ for him to file in federal court.”\\n\\nPace v. DiGuglielmo, 544 U.S. 408, 416 (2005). This statement could be interpreted as\\n\\nindicating a lesser standard than “cause” to overcome procedural default is appropriate for\\n\\n“good cause” in the Rhines context. Accordingly, district courts are divided on what\\n\\nstandard to use. Compare Hernandez v. Sullivan, 397 F. Supp. 2d 1205, 1207 (C.D. Cal.\\n\\n2005) (“[T]he Court deems it appropriate to look to procedural default case law for\\n\\nguidance in determining whether Petitioner has demonstrated the requisite ‘good cause’\\n\\nfor failing to exhaust his unexhausted claims prior to filing this habeas action.”), with\\n\\nRhines v. Weber, 408 F. Supp. 2d 844, 849 (D.S.D. 2005) (“[T]his court believes that the\\n\\n 13\\n\\nSupreme Court suggested a more expansive definition of ‘good cause’ in Pace and Rhines\\n\\nthan the showing needed for ‘cause’ to excuse a procedural default.”). This issue is\\n\\ncritically important because the resolution of the standard could be the deciding factor in\\n\\nmany cases.\\n\\n Unfortunately, the Court today sidesteps the State’s purely legal argument about the\\n\\n“good cause” standard and unnecessarily criticizes the State’s arguments by noting we\\n\\nmust look to categories of cases rather than the particular arguments raised in an individual\\n\\ncase. Maj. Op. at 12–15. But literally every grant of a Rhines stay, not just this particular\\n\\ngrant of a Rhines stay, must decide what the appropriate standard for determining “good\\n\\ncause” is. 4 Ultimately, by giving this issue short shrift, the Court avoids acknowledging\\n\\nthe obvious: this is a purely legal issue that has no overlap with the merits of the case. In\\n\\nother words, this issue is most assuredly “a legal issue that can be decided with reference\\n\\nonly to undisputed facts and in isolation from the remaining issues of the case.” Mitchell,\\n\\n472 U.S. at 530 n.10.\\n\\n The second issue that does not overlap with the merits is whether the district court\\n\\ncan consider state time and procedural bars in determining whether a claim is “potentially\\n\\n\\n\\n 4\\n Given a district court must hold “good cause” exists (which requires defining the\\n“good cause” standard) in order to issue a Rhines stay, this fact is not up for debate. The\\nCourt “see[s] the issue differently” because if the Court proceeded to the merits, we might\\nnot reach the “good cause” issue and instead rule on other grounds. Maj. Op. at 14–15.\\nBut the question is not whether this Court would necessarily have to rule on the issue. At\\nthe risk of sounding like a broken record, the question is whether the district court’s order\\nresolves an issue that is completely separate from the merits. E.g., Will, 546 U.S. at 349.\\nIn discussing whether this Court would have to decide the “good cause” standard, the Court\\nhas taken the reader down an irrelevant rabbit hole.\\n 14\\n\\nmeritorious.” In this case, the district court answered in the negative: “[I]n considering\\n\\nwhether [Petitioner’s] claims are potentially meritorious, this court will not address\\n\\npossible state court time and procedural bars, but will leave the determination of the\\n\\nprocedural posture of the claims to the state court.” ROA Vol. VII, 1729. The district\\n\\ncourt supported its holding with statements from a district court order, two wholly\\n\\ninapposite out-of-circuit opinions, and one Tenth Circuit opinion that does not address this\\n\\nissue. Id. at 1728–29 (citing Lafferty v. Crowther, 2015 WL 6875393 (D. Utah 2015);\\n\\nSimpson v. Camper, 927 F.2d 392, 393 (8th Cir. 1991); Pike v. Guarino, 492 F.3d 61, 74\\n\\n(1st Cir. 2007); Fairchild v. Workman, 579 F.3d 1134, 1153 (10th Cir. 2009)). The district\\n\\ncourt’s grasp at non-binding (and unpersuasive) authority to support its position is\\n\\nunderstandable because, again, neither the Supreme Court nor the Tenth Circuit has\\n\\nweighed in on whether the refusal to address possible state court time and procedural bars\\n\\nis valid. Like the question of the good cause standard, this purely legal issue is clearly\\n\\ncompletely separate from the merits of a petitioner’s claim.\\n\\n Additionally, the third Rhines element, which requires a court to consider whether\\n\\nthe petitioner engaged in intentionally dilatory litigation tactics, does not overlap with the\\n\\nmerits. While this element does not appear to present a purely legal issue, the facts\\n\\ninvolved are completely separate from the facts involved in a petitioner’s unexhausted\\n\\nclaim. At this point, we have three issues, two of which are purely legal, that have no\\n\\noverlap with the merits of a petitioner’s claim—none whatsoever. The Court today fails to\\n\\nacknowledge this reality.\\n\\n\\n\\n 15\\n\\n The Court instead focuses only on two issues that it asserts overlap with the merits:\\n\\nthe application of the “good cause” standard to the facts of the case and whether the claim\\n\\nhas “potential merit.” This latter issue, which is “a fraction of a fraction” of the total\\n\\ninquiry in issuing a Rhines stay, undoubtedly overlaps with the merits. Rep. Br. at 5. The\\n\\nformer issue’s overlap with the merits, however, is questionable. The Court’s assertion\\n\\nthat the application of the good cause standard will “often overlap with a court’s\\n\\npreliminary assessment of the merits” seems to me to be an exaggeration. Maj. Op. at 18.\\n\\nThe Court points to two situations in which this could happen: if a petitioner raises a Brady\\n\\nclaim and if a petitioner raises a different claim of ineffective assistance of counsel. As\\n\\nexplained above, I do not understand Supreme Court precedent to require us to engage in\\n\\na hypothetical inquiry of all possible permutations of claims that could be brought in order\\n\\nto determine whether an order is appealable pursuant to the collateral order doctrine.\\n\\nAccordingly, I remain focused on the issues grants of Rhines stays generally raise, rather\\n\\nthan every issue a grant of a Rhines stay could hypothetically raise.\\n\\n Even though the district court must consider some factual allegations in a petition\\n\\nbefore granting a Rhines stay (a duty that the district court failed miserably to perform in\\n\\nthis case), a grant of a Rhines stay undoubtedly “resolve[s] important issues ‘completely\\n\\nseparate from the merits.’” Microsoft Corp., 137 S. Ct. at 1708 n.3. Accordingly, the\\n\\nsecond element of the collateral order doctrine is satisfied. 5\\n\\n\\n 5\\n In its discussion of the second element, the Court asserts: “if the district court\\nenters multiple Rhines stays, we could face three or more appeals with overlapping issues.”\\nMaj. Op. at 8. I understand that if Rhines stays are appealable and multiple Rhines stays\\nare entered, this Court could face three or more appeals. But the Court does not clarify\\n 16\\n\\n B.\\n\\n The third collateral order doctrine element requires the order to be “effectively\\n\\nunreviewable on appeal from the final judgment in the underlying action.” Swint, 514 U.S.\\n\\nat 41. This element, too, is undoubtedly met. At no other point will this Court have the\\n\\nopportunity to decide the important issues at stake in granting a Rhines stay. Of course, if\\n\\nthe Petitioner obtains relief from the Utah Supreme Court, the Rhines stay issues will never\\n\\nagain arise in this case because Petitioner will be granted a new state trial. If the Utah\\n\\nSupreme Court denies relief and then the district court denies habeas relief on the\\n\\npreviously unexhausted claim, the issues would be moot on appeal. Petitioner posits the\\n\\nState could appeal the Rhines stay issues after final judgment if he ultimately obtains\\n\\nhabeas relief on the previously unexhausted claim. How can this possibly be? Say, the\\n\\nPetitioner prevails in the district court and the State appeals, arguing among other things\\n\\nthat the district court abused its discretion in granting a Rhines stay years earlier. Would\\n\\nthe district court’s grant of a Rhines stay not be moot at that point? What relief could the\\n\\ncourt possibly grant the State if it prevails on that claim? None! That particular\\n\\ncontroversy is over.\\n\\n\\n\\n\\nwhen these potential “three or more appeals” would concern “overlapping issues.” Even\\nwhere a district court issues multiple Rhines stays, each Rhines stay concerns different\\nclaims by a petitioner and therefore different issues. To illustrate, a district court issues a\\nRhines stay on claim x, allowing the petitioner to exhaust the claim in state court. After\\nthe petitioner exhausts claim x in state court and returns to federal court, the district court\\nis not going to issue another Rhines stay for the purpose of allowing the petitioner to\\nexhaust claim x. If there is a second Rhines stay, it would be issued for the petitioner to\\nexhaust claim y. If both of these Rhines stays are appealed and then the final judgment is\\nappealed, the “same issues” would not be before this Court three or more times.\\n 17\\n\\n The Court points out that “the district court’s ultimate rulings on the habeas claims\\n\\nwould be reviewable after the final judgment.” Maj Op. at 38–39. Of course. But that\\n\\ncertainly does not mean “the collateral-order doctrine’s third element would remain\\n\\nunsatisfied even if the grant of a Rhines stay were to become moot.” Id. at 39. We are not\\n\\nconcerned here with whether other issues involved in this case, such as “the district court’s\\n\\nultimate rulings on the habeas claims,” would be reviewable on appeal of the final\\n\\njudgment; we are concerned with whether the issues involved in granting a Rhines stay are\\n\\nreviewable on appeal of the final judgment. 6\\n\\n Even assuming a court has the opportunity to review a district court’s issuance of a\\n\\nRhines stay after final judgment—a proposition I vehemently disagree with—we must then\\n\\nlook to the importance of the interests at stake. Whether an order is “effectively\\n\\nunreviewable” necessarily requires “a judgment about the value of the interests that would\\n\\nbe lost through rigorous application of a final judgment requirement.” Mohawk Indus.,\\n\\nInc, 558 U.S. at 107 (quoting Dig. Equip. Corp., 511 U.S. at 878–79). “That a ruling ‘may\\n\\nburden litigants in ways that are only imperfectly reparable by appellate reversal of a final\\n\\n\\n\\n\\n 6\\n The Court also states Petitioner could have filed a writ of mandamus rather than\\nawait final judgment. Maj. Op. at 35 n.17. But a writ of mandamus is not the relief the\\nSupreme Court contemplated in Rhines. The standard for issuing a writ of mandamus is\\nhigher than the abuse of discretion standard. In re Cooper Tire & Rubber Co., 568 F.3d\\n1180, 1186–87 (10th Cir. 2009). In fact, we have explicitly stated that “[t]here must be\\nmore than what we would typically consider to be an abuse of discretion in order for the\\nwrit to issue.” Id. at 1186. In Rhines, however, the Supreme Court stated three times that\\nthe standard of review for Rhines stays is “abuse of discretion.” Rhines, 544 U.S. at 277–\\n79. Accordingly, the Supreme Court clearly contemplated Rhines stays to be reviewed on\\ndirect appeal, rather than through a writ of mandamus.\\n\\n 18\\n\\ndistrict court judgment . . . has never sufficed.’” Id. (quoting Dig. Equip. Corp., 511 U.S.\\n\\nat 872). “Instead, the decisive consideration is whether delaying review until the entry of\\n\\nfinal judgment ‘would imperil a substantial public interest’ or ‘some particular value of a\\n\\nhigh order.’” Id. (quoting Will, 546 U.S. at 352–53) (emphasis added). The certain “high\\n\\norder” values the Supreme Court has accepted as being important enough to not delay\\n\\nreview until the entry of final judgment include: “honoring the separation of powers,\\n\\npreserving the efficiency of government and the initiative of its officials, respecting a\\n\\nState’s dignitary interests, and mitigating the government’s advantage over the individual.”\\n\\nWill, 546 U.S. at 352–53.\\n\\n The “decisive” question, then, is just this: does delaying review of the Rhines stay\\n\\nuntil after a petitioner exhausts his claims in state court and returns to federal court “imperil\\n\\na substantial public interest” or “some particular value of a high order”? See Mohawk\\n\\nIndus., Inc., 558 U.S. at 107. The answer is a resounding yes. The “substantial public\\n\\ninterest” or “value of a high order” at issue when a Rhines stay is granted is a state’s right\\n\\nto enforce its criminal judgments, particularly in capital cases. “Our federal system\\n\\nrecognizes the independent power of a State to articulate societal norms through criminal\\n\\nlaw; but the power of a State to pass laws means little if the State cannot enforce them.”\\n\\nMcClesky v. Zant, 499 U.S. 467, 491 (1991). In fact, the Supreme Court has held a state’s\\n\\n“sovereign power to enforce the criminal law” is an interest of “great weight.” In re\\n\\nBlodgett, 502 U.S. 236, 239 (1992) (per curiam). States suffer “severe prejudice” when\\n\\nthey are prevented from exercising this power. Id. (holding Washington “sustained severe\\n\\nprejudice by [a] 2½-year stay of execution”). In particular, “the criminal law is deprived\\n\\n 19\\n\\nof much of its deterrent effect.” Teague v. Lane, 489 U.S. 288, 309 (1989); see also\\n\\nMcClesky, 499 U.S. at 491 (discussing the need for finality in criminal cases). Further, the\\n\\nstate loses legitimacy, as “[t]he resulting lack of finality undermines public confidence in\\n\\nour criminal justice system.” Powell Comm. Report, supra page 1, at 1.\\n\\n Not only has the Supreme Court put “great weight” on a state’s power to enforce its\\n\\ncriminal law, Congress has also prioritized this power with the passage of AEDPA. One\\n\\nof the driving forces in passing AEDPA was to “reduce delays in the execution of state and\\n\\nfederal criminal sentences, particularly in capital cases.” Rhines, 544 U.S. at 276\\n\\n(emphasis added). AEDPA has no teeth if federal habeas law still leads “to piecemeal and\\n\\nrepetitious litigation, and years of delay between sentencing and a judicial resolution as to\\n\\nwhether the sentence was permissible under law,” as it has in this case and potentially many\\n\\nothers. Powell Comm. Report, supra page 1, at 1. Supreme Court precedent and AEDPA\\n\\nindicate a state’s ability to enforce its criminal judgments without delay is a “substantial\\n\\npublic interest” or “value of a high order” that ranks among “honoring the separation of\\n\\npowers, preserving the efficiency of government and the initiative of its officials,\\n\\nrespecting a State’s dignitary interests, and mitigating the government’s advantage over\\n\\nthe individual.” Will, 546 U.S. at 352–53.\\n\\n The Court today does not dispute the importance of the issues at stake. Indeed, this\\n\\nwould be difficult to do in light of the fact that this Court has previously held an appeal\\n\\nconcerning an anti-SLAPP statute, which aims to “nip harassing litigation in the bud,” was\\n\\ntoo important to be denied review until entry after final judgment. Los Lobos Renewable\\n\\nPower, LLC v. Americulture, LLC, 885 F.3d 659, 666–67 (10th Cir. 2018). Instead, the\\n\\n 20\\n\\nCourt focuses on “whether interlocutory review of Rhines stays would speed review or\\n\\nslow it through piecemeal review.” Maj. Op. at 30. This is not the question under the third\\n\\nelement of the collateral order doctrine. 7 Again, the “decisive” question is whether\\n\\ndelaying review of the Rhines stay until after a petitioner exhausts his claims in state court\\n\\nand returns to federal court “imperil a substantial public interest” or “some particular value\\n\\nof a high order.” See Mohawk Indus., Inc., 558 U.S. at 107.\\n\\n Let us not forget: Petitioner stabbed Blackmon to death almost twenty-five years\\n\\nago; he was sentenced to death over twenty-two years ago; his direct appeals ended over\\n\\nsixteen years ago; his state post-conviction proceedings ended over ten years ago; his\\n\\nfederal habeas petition was filed nearly ten years ago; he received his first Rhines stay,\\n\\nwhich lasted three years, over nine years ago; and his amended petition was filed over six\\n\\nyears ago. The State of Utah most certainly has an undeniable interest, deemed important\\n\\nby both the Supreme Court and Congress, to carry out its punishment against Petitioner\\n\\nwithout further delay. This interest is indeed lost if the State cannot appeal the grant of the\\n\\nRhines stay now. The delay—which is, in itself, a win for Petitioner—is exactly what\\n\\nharms the State’s interest. Because delaying review would jeopardize both “a substantial\\n\\n\\n 7\\n Even so, the Court’s analysis of this question is divorced from reality. I suggest if\\nthis court could review Rhines stays, the court might hold, for example, that “good cause”\\nis akin to “cause” under procedural default. Or perhaps the court would hold that district\\ncourts’ refusals to take state time and procedural bars into account in deciding whether a\\nclaim has potential merit does not comport with AEDPA or Rhines’s caution that stays be\\ngranted in only “limited circumstances.” It would seem to me that if either of those very\\npossible things happened, interlocutory review of Rhines stays would undoubtedly speed\\nreview over time, given district courts have issued multiple stays based on a lower standard\\nof “good cause” and an understanding that the district court cannot consider time and\\nprocedural bars.\\n 21\\n\\npublic interest” and “some particular value of a high order,” the grant of a Rhines stay in a\\n\\ncapital case is “effectively unreviewable on appeal from a final judgment.”\\n\\n * * *\\n\\n The Court cites to three other circuits in support of its holding that a grant of a\\n\\nRhines stay is reviewable after final judgment: Grace v. Vannoy, 826 F.3d 813 (5th Cir.\\n\\n2016); Howard v. Norris, 616 F.3d 799 (8th Cir. 2010); and Thompson v. Frank, 599 F.3d\\n\\n1088 (9th Cir. 2010). The most important thing to note about Howard and Thompson is\\n\\nthat neither considers “the decisive consideration” of “whether delaying review until the\\n\\nentry of final judgment ‘would imperil a substantial public interest’ or ‘some particular\\n\\nvalue of a high order.’” Mohawk Indus., Inc., 558 U.S. at 107 (quoting Will, 546 U.S. at\\n\\n352–53) (emphasis added); Howard, 616 F.3d at 802–803; Thompson, 599 F.3d at 1090.\\n\\nThis alone renders their analyses unpersuasive.\\n\\n Even if we push that crucial fact aside, these cases otherwise rest on flimsy\\n\\nreasoning. In Thompson, the Ninth Circuit indeed held “[a] district court order staying\\n\\nproceedings to allow a state habeas petition to exhaust claims in state court is reviewable\\n\\non appeal after final judgment.” 599 F.3d at 1090. In support, the Ninth Circuit cited two\\n\\ncases: Valdovinos v. McGrath, 598 F.3d 568, 573–74 (9th Cir. 2010), vacated sub nom.\\n\\nHorel v. Valdovinos, 562 U.S. 1196 (2011), and Olvera v. Giurbino, 371 F.3d 569, 574\\n\\n(9th Cir. 2004). Olvera involved a district court’s refusal to stay proceedings and,\\n\\ntherefore, lends no support for the proposition for which the Ninth Circuit cited it. 371\\n\\nF.3d at 574. Valdovinos, a vacated Ninth Circuit opinion, does not support Thompson’s\\n\\nholding either. In Valdovinos, the State did not even argue the district court erred in\\n\\n 22\\n\\ngranting a Rhines stay. Br. for Appellee, Valdovinos, 598 F.3d 568 (No. 08-15918), 2009\\n\\nWL 2444195. Rather, the State argued that “the district court erred in allowing petitioner\\n\\nto amend his petition to include new and revised claims he first presented in his traverse\\n\\nafter the AEDPA time limit had passed.” Id. Of course, because the State did not argue\\n\\nthe district court erred in granting a Rhines stay, the Petitioner did not argue such an issue\\n\\nwas moot. Reply Br., Valdovinos, 598 F.3d 568 (No. 08-15918), 2009 WL 2444196.\\n\\nPerhaps confused, the Valdovinos court then—totally unsolicited—noted the district court\\n\\ndid not abuse its discretion in issuing a Rhines stay. 598 F.3d at 573–74. This flippant\\n\\nadvisory statement, which was made in passing as the Valdovinos court addressed the claim\\n\\nthe State actually made in that case, sheds absolutely no light on whether the grant of a\\n\\nRhines stay is effectively unreviewable on appeal from final judgment. Accordingly, by\\n\\nrelying solely on Olvera and Valdovinos, Thompson reached its holding on paper-thin\\n\\nsupport, and this writer cannot take Thompson seriously for such a holding.\\n\\n The Court also cites to Howard, which held the grant of a Rhines stay “fails the third\\n\\ncondition [of the collateral order doctrine] ‘because a district court’s conclusion about\\n\\nwhether a habeas claim has been exhausted is addressable on appeal after final judgment.’”\\n\\n616 F.3d at 802 (quoting Thompson, 599 F.3d at 1090). In Howard, the Eighth Circuit\\n\\nnoted it was “significant” that the petitioner did not “challenge the district court’s\\n\\napplication of the three Rhines factors, and thus [did] not challenge the delay involved in\\n\\nthe stay itself.” Id. at 803. Instead, the petitioner “challenge[d] the propriety of the stay\\n\\nonly as it relate[d] to the merits of whether the district court erred in concluding some of\\n\\n[the petitioner’s] claims were unexhausted.” Id. Thus, Howard might not be applicable to\\n\\n 23\\n\\nour instant case, but even if it is, Howard’s sole reliance on Thompson in its one-sentence\\n\\nanalysis of whether the issues could be addressed on appeal renders its analysis\\n\\nunpersuasive.\\n\\n The latest circuit to join the conversation is the Fifth Circuit in Grace. Grace relied\\n\\non Thompson and Howard—albeit in conjunction with a more thoughtful analysis—to\\n\\nreach the conclusion that Rhines stays are not appealable orders. Grace, 826 F.3d at 820–\\n\\n21. Of utmost importance, however, Grace was not a capital case. Id. at 819 (“Indeed,\\n\\nGrace was sentenced to life in prison; he is not delaying execution of a capital sentence.”).\\n\\nThe interest involved in Grace is completely different than the interest at issue in this case.\\n\\nCapital prisoners have every incentive to delay their proceedings, while other prisoners\\n\\nhave every incentive to expedite their proceedings. Because of this inherent difference\\n\\nbetween capital and non-capital cases, Grace’s reasoning is not relevant to the instant\\n\\ncapital case. Nothing in these three cases moves me in the slightest from my view that\\n\\ngrants of Rhines stays in capital cases are effectively unreviewable on appeal from final\\n\\njudgment.\\n\\n C.\\n\\n As if satisfying the three collateral order doctrine elements was not enough, the\\n\\npolicy behind limiting jurisdiction to “final” orders—which in many cases cuts against the\\n\\nexercise of jurisdiction, see, e.g., Moses H. Cone, 460 U.S. at 31 (Rehnquist, J.,\\n\\ndissenting)—supports our exercise of jurisdiction in this case. One policy behind section\\n\\n1291’s “finality” requirement is to “prevent[] the debilitating effect on judicial\\n\\nadministration caused by piecemeal appeal disposition of what is, in practical consequence,\\n\\n 24\\n\\nbut a single controversy.” Coopers & Lybrand, 437 U.S. at 471 (quoting Eisen v. Carlisle\\n\\n& Jacquelin, 417 U.S. 156, 170 (1974)); see also Moses H. Cone, 460 U.S. at 31\\n\\n(Rehnquist, J., dissenting) (“To be effective, judicial administration must not be leaden-\\n\\nfooted.”). In other words, the finality requirement of section 1291 prevents unnecessary\\n\\nsteps back and forth between the federal district court and the federal appellate court. But\\n\\nironically, piecemeal litigation is precisely what the issuance of a Rhines stay causes!8\\n\\nEven though federal courts do not feel the “debilitating effect,” it is certainly felt by our\\n\\nstate brethren who are currently adjudicating Petitioner’s supplemental-instruction claim\\n\\nthat is in all likelihood time and procedurally barred. The waste of state judicial\\n\\nresources—not to mention the resources of the Utah Office of the Attorney General—is\\n\\nplain. While this is not the particular “debilitating effect on judicial administration” the\\n\\nfinality requirement generally aims to prevent, it is no less of a “debilitating effect on\\n\\njudicial administration” in state court. In sum, because a Rhines stay already causes\\n\\npiecemeal litigation, the policy behind not exercising jurisdiction here—i.e., preventing\\n\\npiecemeal litigation—rings hollow.\\n\\n IV.\\n\\n\\n\\n 8\\n Congress and the Supreme Court have determined this piecemeal litigation, which\\nis specifically caused by the total exhaustion requirement that renders Rhines stays\\nnecessary, is justified by comity. That is, state courts should have the chance to decide all\\nissues before federal courts do. The Powell Committee questioned whether, in reality, we\\npromote comity by allowing the state court to decide an issue before the federal court can.\\nSee Powell Comm. Report, supra page 1, at 22–23 (“Because of the existence of state\\nprocedural default rules, exhaustion is futile in the great majority of cases. It serves the\\nstate interest of comity in theory, but in practice it results in delay and undermines the state\\ninterest in the finality of its criminal convictions.”).\\n 25\\n\\n The Supreme Court has made itself perfectly clear that only a “narrow class” of\\n\\ndecisions fall within the collateral order doctrine, and I have taken this directive to heart.\\n\\nSee Los Lobos Renewable Power, LLC, 885 F.3d at 673–76 (Baldock, J., dissenting from\\n\\nthe Court’s exercise of jurisdiction pursuant to the collateral order doctrine). The grant of\\n\\na Rhines stay in capital cases, however, is one of the few decisions that falls within the\\n\\nnarrow class. The Supreme Court clearly intended there to be meaningful restrictions on\\n\\nwhen a district court may issue a Rhines stay. As the district court’s order demonstrates,\\n\\nthere currently are none.\\n\\n Because we have jurisdiction pursuant to the collateral order doctrine, I respectfully\\n\\ndissent. I would proceed to the merits.\\n\\n\\n\\n\\n 26\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4400962/\", \"author_raw\": \"BALDOCK, Circuit Judge, dissenting\"}]}"},"judge1":{"kind":"string","value":"BACHARACH"},"judge2":{"kind":"string","value":"BALDOCK"},"judge3":{"kind":"string","value":"PHILLIPS"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":5,"string":"5"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":3,"string":"3"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4623709/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":1,"string":"1"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Troy Michael KELL, Petitioner-Appellee, v. Larry BENZON, Warden Utah State Prison, Respondent-Appellant.\nCourt: U.S. Court of Appeals for the Tenth Circuit\nDate decided: 2019-05-28\nOpinion type: majority\nHas dissenting opinion: Yes\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nPUBLISH FILED\n United States Court of Appeals\n UNITED STATES COURT OF APPEALS Tenth Circuit\n\n FOR THE TENTH CIRCUIT May 28, 2019\n _________________________________\n Elisabeth A. Shumaker\n Clerk of Court\nTROY MICHAEL KELL,\n\n Petitioner - Appellee,\n\nv. No. 17-4191\n\nLARRY BENZON, Warden Utah\nState Prison,\n\n Respondent - Appellant.\n\n\n _________________________________\n\n Appeal from the United States District Court\n for the District of Utah\n (D.C. No. 2:07-CV-00359-CW)\n _________________________________\n\nAndrew F. Peterson, Assistant Solicitor General (Tyler R. Green, Utah\nSolicitor General, Thomas Brunker, Deputy Solicitor General, Daniel W.\nBoyer, Assistant Solicitor General, Sean D. Reyes, Utah Attorney General,\nSalt Lake City, Utah, with him on the briefs), for Respondent-Appellant.\n\nLindsey Layer, Assistant Federal Public Defender, Salt Lake City, Utah\n(Jon M. Sands, Federal Public Defender for the District of Arizona,\nAlexandra LeClair, Assistant Federal Public Defender, Salt Lake City,\nUtah, with him on the briefs), for Petitioner-Appellee.\n _________________________________\n\nBefore BACHARACH, BALDOCK, and PHILLIPS, Circuit Judges.\n _________________________________\n\nBACHARACH, Circuit Judge.\n _________________________________\n\n This is an interlocutory appeal from an order staying a habeas\n\nproceeding. We lack jurisdiction and dismiss the appeal.\n\n Mr. Troy Kell sought habeas relief, but he had not exhausted two of\n\nhis claims in state court. The unexhausted claims created a Catch-22 for\n\nMr. Kell, risking a dismissal of all of his claims without an opportunity to\n\ntimely refile. To relieve Mr. Kell of this Catch-22, the district court\n\nentered a limited stay, halting proceedings on one of the unexhausted\n\nclaims while Mr. Kell returned to state court to exhaust the claim. For the\n\nremaining habeas claims, however, the district court continued with the\n\nproceedings.\n\n In the midst of the ongoing habeas proceedings in district court, Utah\n\nappealed from the grant of a stay, arguing that the district court should\n\nhave declined to grant a stay. Our threshold question involves appellate\n\njurisdiction. To establish jurisdiction, Utah relies on the collateral-order\n\ndoctrine, which allows appeals from some decisions before the entry of a\n\nfinal judgment. But the district court’s issuance of a stay does not satisfy\n\nthe collateral-order doctrine’s requirements, so we dismiss the appeal for\n\nlack of appellate jurisdiction.\n\n1. Mr. Kell timely files a habeas petition.\n\n Mr. Kell was convicted of murder and sentenced to death in Utah,\n\nand his conviction became final roughly sixteen years ago. Mr. Kell then\n\nhad one year to seek federal habeas relief, but the one-year limitations\n\n 2\n\nperiod was tolled while he pursued state post-conviction remedies. 28\n\nU.S.C. § 2244(d). When the state post-conviction proceedings ended in\n\n2009, Mr. Kell timely filed a federal habeas petition.\n\n2. The district court stays the habeas case to allow Mr. Kell to\n exhaust a new claim.\n\n In 2013, Mr. Kell asserted two new habeas claims: (1) that the trial\n\ncourt had improperly commented to the jury that Mr. Kell bore the burden\n\nin the penalty phase to show that his life should be spared and (2) that the\n\njurors had improperly considered extraneous information. Mr. Kell had not\n\nexhausted the two new claims, so the district court needed to grapple with\n\nhow to proceed. Continuing with the new habeas claims could prevent\n\nconsideration of any of the claims because a federal district court must\n\nordinarily dismiss the entire petition when one or more of the habeas\n\nclaims are unexhausted. Rose v. Lundy, 455 U.S. 509, 522 (1982). Given\n\nthe possibility of dismissal, Mr. Kell faced a dilemma: If the district court\n\nwere to dismiss the habeas petition and he later refiled in federal court, the\n\nstatute of limitations might have expired on all of his claims.\n\n To avoid this dilemma, Mr. Kell requested a stay so that he could\n\nexhaust his new habeas claims in state court. For this request, Mr. Kell\n\ninvoked a procedure adopted in Rhines v. Weber, 544 U.S. 269 (2005).\n\nUnder Rhines, a district court may stay habeas proceedings to permit\n\nexhaustion of a claim upon satisfaction of three elements:\n\n\n 3\n\n 1. “Good cause” exists for the failure to exhaust the claim.\n\n 2. The unexhausted claim is “potentially meritorious.”\n\n 3. The petitioner did not engage in “abusive litigation tactics” or\n intentionally delay the proceedings.\n\nRhines, 544 U.S. at 277–78. The district court declined to stay the claim\n\ninvolving extraneous influence on the jury, concluding that this claim\n\nlacked potential merit. But the district court granted the stay on the claim\n\ninvolving the judge’s comment to the jury, concluding that Mr. Kell had\n\nsatisfied the three elements for a Rhines stay. For the remaining habeas\n\nclaims, however, the district court stated that the proceedings would\n\ncontinue without interruption. 1\n\n3. Utah appeals the order granting a limited stay.\n\n In this appeal, Utah argues that the federal district court erred in\n\ngranting the stay because\n\n the court used the wrong test for “good cause” and misapplied\n that test,\n\n the new habeas claim lacks potential merit based on timeliness,\n the existence of a procedural default, and the absence of a\n constitutional violation, and\n\n Mr. Kell was dilatory by waiting over three years to assert the\n new habeas claim and over eight years to seek a stay based on\n this claim.\n\n\n\n1 As the dissent points out, the district court denied certification of an\ninterlocutory appeal. In denying certification, the district court reasoned\nthat an interlocutory appeal would slow the litigation.\n 4\n\n4. We lack jurisdiction to consider interlocutory appeals from\n Rhines stays.\n\n We can consider these arguments only if Utah establishes appellate\n\njurisdiction. See EEOC v. PJ Utah, L.L.C., 822 F.3d 536, 542 n.7 (10th\n\nCir. 2016) (“[T]he appellant . . . bears the burden to establish appellate\n\njurisdiction.”). We typically acquire jurisdiction through the district\n\ncourt’s entry of a final decision. 28 U.S.C. § 1291. But a stay does not\n\nordinarily constitute a final decision. See Crystal Clear Commc’ns, Inc. v.\n\nSw. Bell Tel. Co., 415 F.3d 1171, 1176 (10th Cir. 2005) (“If a stay merely\n\ndelays litigation and does not effectively terminate proceedings, it is not\n\nconsidered a final decision.”).\n\n Utah argues that we nonetheless have jurisdiction under the\n\ncollateral-order doctrine. This doctrine would apply only if the district\n\ncourt’s decision\n\n conclusively decided the disputed question,\n\n resolved an important issue separate from the merits, and\n\n could not be effectively reviewed on direct appeal.\n\nVan Cauwenberghe v. Biard, 486 U.S. 517, 522 (1988). The failure to\n\nsatisfy any of the three elements would prevent us from applying the\n\ncollateral-order doctrine. See Stubblefield v. Windsor Capital Grp., 74 F.3d\n\n990, 997 (10th Cir. 1996) (stating that the collateral-order doctrine “does\n\nnot apply unless each of the three requirements are met”).\n\n 5\n\n Each element is considered stringent. E.g., Flanagan v. United\n\nStates, 465 U.S. 259, 270 (1984). And “[i]n case after case in year after\n\nyear, the Supreme Court has issued increasingly emphatic instructions that\n\nthe class of cases capable of satisfying this ‘stringent’ test should be\n\nunderstood as ‘small,’ ‘modest,’ and ‘narrow.’” United States v. Wampler,\n\n624 F.3d 1330, 1334 (10th Cir. 2010) (Gorsuch, J.). Utah bears the burden\n\non each element of this “stringent” test. See Los Lobos Renewable Power,\n\nL.L.C. v. Americulture, Inc., 885 F.3d 659, 664 (10th Cir. 2018) (stating\n\nthat the “party asserting jurisdiction under the collateral order doctrine”\n\nbears the burden on each element).\n\n We assume, for the sake of argument, that an order issuing a Rhines\n\nstay conclusively determines the disputed question. But the grant of a\n\nRhines stay involves issues that are intertwined with the merits and\n\nreviewable on direct appeal. We thus lack jurisdiction under the collateral-\n\norder doctrine. See Crystal Clear Commc’ns, Inc. v. Sw. Bell Tel. Co., 415\n\nF.3d 1171, 1178 (10th Cir. 2005) (noting that the collateral-order doctrine\n\ndoes not support appellate jurisdiction if any element is unsatisfied).\n\n A. The grant of a Rhines stay is not completely separate from\n the merits.\n\n The collateral-order doctrine applies only when the order involves an\n\nimportant issue that is not intertwined with the merits. Coopers & Lybrand\n\nv. Livesay, 437 U.S. 463, 469 (1978). For this element, Utah must show\n\n\n 6\n\nthat the issues bearing on the appropriateness of a Rhines stay are\n\n“completely separate” from the merits. E.g., Cunningham v. Hamilton Cty.,\n\nOhio, 527 U.S. 198, 205 (1999). Utah has not made this showing.\n\n 1. Avoidance of Piecemeal Litigation\n\n The requirement of complete separation is designed to prevent\n\npiecemeal appellate review. Van Cauwenberghe v. Biard, 486 U.S. 517,\n\n527 (1988). Given this purpose, the collateral-order doctrine would\n\nordinarily apply only if an appellate court would probably not need to\n\nconsider the merits a second time. 2\n\n But interlocutory appeals of Rhines stays would often require federal\n\nappellate courts to consider the merits at least twice:\n\n once in the interlocutory appeal (when the respondent argues\n that a Rhines stay is improper because the petitioner’s\n unexhausted claim lacks potential merit) and\n\n again after entry of the judgment (when the parties disagree\n over the claim’s actual merit).\n\n\n\n2\n The Supreme Court has explained:\n\n The requirement that the matter be separate from the merits of\n the action itself means that review now is less likely to force the\n appellate court to consider approximately the same (or a very\n similar) matter more than once, and also seems less likely to\n delay trial court proceeds (for, if the matter is truly collateral,\n those proceedings might continue while the appeal is pending).\n\nJohnson v. Jones, 515 U.S. 304, 311 (1995) (emphasis in original).\n\n\n 7\n\nAnd if the district court enters multiple Rhines stays, 3 we could face three\n\nor more appeals with overlapping issues.\n\n This possibility is apparent here. For example, consider Utah’s\n\nargument that the district court’s jury instruction was correct. This\n\nargument involves a classic issue on the merits. See Gillette v. Prosper,\n\n858 F.3d 833, 839 (3d Cir. 2017) (concluding that the order being appealed\n\nwas “closely related” to the merits because “both concern[ed] alleged\n\nconstitutional violations” and involved potential release from prison). If\n\nwe were to recognize appellate jurisdiction at this stage and Mr. Kell were\n\nto obtain habeas relief, we would decide the “potential merit” of Mr. Kell’s\n\nnew claim now and the claim’s “actual merit” after the entry of a final\n\njudgment. It is hard to imagine a better example of piecemeal litigation—\n\nprecisely what the Supreme Court has tried to avoid by limiting the\n\ncollateral-order doctrine to classes of orders involving “complete\n\nseparation” from the merits.\n\n The dissent disagrees:\n\n Even where a district court issues multiple Rhines stays, each\n Rhines stay concerns different claims by a petitioner and\n therefore different issues. To illustrate, a district court issues a\n Rhines stay on claim x, allowing the petitioner to exhaust the\n claim in state court. After the petitioner exhausts claim x in state\n court and returns to federal court, the district court is not going\n to issue another Rhines stay for the purpose of allowing the\n\n3\n Here, for example, the district court granted two Rhines stays. Our\nappeal involves only the second stay.\n\n 8\n\n petitioner to exhaust claim x. If there is a second Rhines stay, it\n would be issued for the petitioner to exhaust claim y. If both of\n these Rhines stays are appealed, and then the final judgment is\n appealed, the “same issues” would not be before this Court three\n or more times.\n\nDissent at 16–17 n.5 (emphasis in original).\n\n We respectfully think that the dissent has misunderstood us. When\n\nreviewing a Rhines stay, we consider the “potential merit” of the\n\nunexhausted claim. For example, let’s consider Utah’s argument that the\n\ndistrict court erred in granting a stay because the unexhausted habeas claim\n\nlacks potential merit. If we have appellate jurisdiction under the collateral-\n\norder doctrine, we would consider whether the district court acted within\n\nits discretion in treating the unexhausted claim as potentially meritorious.\n\n Let’s assume, for the sake of argument, that we were to uphold this\n\ndetermination. When the habeas case ends in district court, the parties\n\ncould appeal the district court’s ultimate determination of the claim’s\n\nactual merit. See Alexander v. U.S. Parole Comm’n, 514 F.3d 1083, 1087\n\n(10th Cir. 2008) (stating that a conditional writ of habeas corpus is final,\n\ncreating appellate jurisdiction); Burton v. Johnson, 975 F.2d 690, 693–94\n\n(10th Cir. 1992) (stating that a conditional writ of habeas corpus was an\n\nappealable final judgment).\n\n The same would be true for any case involving a Rhines stay. So in a\n\ncase with multiple Rhines stays and multiple interlocutory appeals, we\n\n\n\n 9\n\ncould face the same issues after a final judgment (even if the interlocutory\n\nappeals individually involved different issues).\n\n 2. The Significance of the Relationship Between the Rhines\n Factor of “Potential Merit” and the Actual Merits of Mr.\n Kell’s New Claim\n\n Because “potential merit” is essential for Rhines stays, interlocutory\n\nreview would frequently require us to consider the potential merit of the\n\nunderlying habeas claims. And “potential merit” is obviously not\n\n“completely separate” from the actual merits. The dissent agrees, stating\n\nthat the Rhines issue (“potential merit”) “undoubtedly overlaps with the\n\nmerits.” Dissent at 16. 4\n\n\n\n\n4\n Utah and the dissent downplay the significance of this relationship\nbetween the two, calling “potential merit” a “fraction of a fraction” of the\ntest governing grants of Rhines stays. Appellant’s Reply Br. at 5; Dissent\nat 16.\n\n It is true that potential merit is just one element for a Rhines stay.\nBut a court can enter a Rhines stay only if the unexhausted claim has\npotential merit. See pp. 3–4, above. Thus, potential merit may be a\n“fraction” of the test, but it is a requirement in any Rhines stay.\n\n Utah also asserts that the “underlying merit of a habeas claim is only\na fraction of the ‘potential merit’ factor.” Appellant’s Reply Br. at 5. We\nare not sure why Utah regards “potential merit” under Rhines as more\ninclusive than the actual merit of a habeas claim, and Utah supplies no\nexplanation. Even if Utah were right, however, it has not explained how\nthe issue of potential merit could satisfy the requirement of complete\nseparation from the merits.\n\n\n 10\n\n 3. Application of the Test of “Complete Separation”\n\n To apply the element of complete separation, we must evaluate the\n\npertinent issue based on the entire class of orders (Rhines stays) rather\n\nthan the particular arguments in this appeal. United States v. Bolden, 353\n\nF.3d 870, 876 (10th Cir. 2003). 5 We thus consider whether the issues\n\nunderlying a Rhines stay are, “as a whole,” completely separate from the\n\nmerits. Id.\n\n The Supreme Court has repeatedly cautioned that the collateral-order\n\ndoctrine requires “complete separation” from the merits. E.g., Microsoft\n\nCorp. v. Baker, 137 S. Ct. 1702, 1708 n.3 (2017); Will v. Hallock, 546 U.S.\n\n345, 349 (2006); Sell v. United States, 539 U.S. 166, 176 (2003);\n\nCunningham v. Hamilton Cty., Ohio, 527 U.S. 198, 205 (1999);\n\nQuackenbush v. Allstate Ins. Co., 517 U.S. 706, 712 (1996); Johnson v.\n\nJones, 515 U.S. 304, 310–11 (1995); Digital Equip. Corp. v. Desktop\n\nDirect, Inc., 511 U.S. 863, 867 (1994); Richardson-Merrell, Inc. v. Koller,\n\n\n5\n In Bolden, we considered whether the collateral-order doctrine\napplied to orders disqualifying an entire U.S. Attorney’s office from\nrepresenting the government. 353 F.3d at 873. The defendant contended\nthat the element of separation wasn’t satisfied because the issue of\ndisqualification was entangled in the merits of his claims. Id. at 876. We\nrejected this approach, reasoning that the Supreme Court “‘has consistently\neschewed a case-by-case approach to deciding whether an order is\nsufficiently collateral.’” Id. (quoting Cunningham v. Hamilton Cty., Ohio,\n527 U.S. 198, 206 (1999)). We ultimately decided the issue of separation\n“on the whole of such [disqualification] orders” without determining\nwhether the particular issues in that case had been separate from the\nmerits. Id.\n 11\n\n472 U.S. 424, 431 (1985); Coopers & Lybrand v. Livesay, 437 U.S. 463,\n\n468–69 (1978).\n\n 4. Utah’s Focus on its Own Arguments (Rather than the Class\n of Orders)\n\n Utah also points to its arguments involving good cause, insisting that\n\nthey do not relate to the merits. And the dissent relies on Utah’s arguments\n\ninvolving timeliness, dilatoriness, and procedural default. The focus of\n\nUtah and the dissent on Utah’s particular appeal points is misguided, as it\n\ndisregards\n\n the overlap between Utah’s appellate arguments and the merits\n and\n\n the need to consider separation categorically based on the class\n of orders rather than the particular issues invoked by the\n appellant.\n\n a. Utah’s Arguments on Good Cause\n\n Utah tries to justify application of the collateral-order doctrine based\n\non the district court’s alleged misidentification and misapplication of the\n\ntest for good cause. We reject this effort.\n\n i. Misidentifying the Test for Good Cause\n\n Utah identifies the definition of good cause as an “important” issue.\n\nTo determine an issue’s importance under the collateral-order doctrine, we\n\nconsider\n\n\n\n\n 12\n\n whether the issue is “important in a jurisprudential sense” 6 and\n\n whether the interests that “‘would potentially go unprotected\n without immediate appellate review are significant relative to\n efficiency interests sought to be advanced by adherence to the\n final judgment rule.’” 7\n\n The definition of good cause might be considered jurisprudentially\n\nimportant now because we lack a precedent squarely defining the test for\n\ngood cause under Rhines. Of course, if we were to undertake interlocutory\n\nreview and define the test, that definition would settle the issue, rendering\n\nit jurisprudentially unimportant in the future. See 15A Charles Alan\n\nWright, Arthur R. Miller & Edward H. Cooper, Federal Practice &\n\nProcedure: Jurisdiction & Related Matters § 3911.5, at 438 (2d ed. 1992)\n\n(“Implementation of a serious and unsettled question requirement can\n\neasily lead to a situation in which a particular question is suitable for\n\ncollateral order appeal the first time it is presented, but not thereafter.”).\n\n And Utah has not shown an urgency to immediately define the\n\nstandard for good cause under Rhines. Indeed, Utah has offered many\n\nalternative arguments for reversal, such as expiration of the limitations\n\nperiod, procedural default, misapplication of the district court’s own test\n\nfor good cause, dilatoriness, and lack of potential merit. Given Utah’s\n\n\n6\n Marc Dev’t, Inc. v. FDIC, 992 F.2d 1503, 1505 (10th Cir.), vacated\non other grounds, 12 F.3d 948 (10th Cir. 1993).\n7\n Pierce v. Blaine, 467 F.3d 362, 370–71 (3d Cir. 2006) (quoting In re\nFord Motor Co., 110 F.3d 954, 959 (3d Cir. 1997)).\n 13\n\nalternative arguments, we may not even need to decide the test for good\n\ncause if we were to reverse the grant of a Rhines stay.\n\n The dissent nonetheless insists that the test for good cause is\n\nimportant because a court in “literally every grant of a Rhines stay, not just\n\nthis particular grant of a Rhines stay, must decide what the appropriate\n\nstandard for determining ‘good cause’ is.” Dissent at 14. We see the issue\n\ndifferently. If the collateral-order doctrine applied, only two possibilities\n\nexist:\n\n 1. We decide now what the test is for good cause.\n\n 2. We do not decide the test now, ruling on other grounds.\n\n Let’s consider the first possibility (that we decide the test for good\n\ncause in this appeal). Once we define the test, future panels and district\n\ncourts will be bound by stare decisis to apply that test in all future cases.\n\nUnited States v. Meyers, 200 F.3d 715, 720 (10th Cir. 2000). We thus\n\ncouldn’t continue to view the definition of good cause as jurisprudentially\n\nsignificant once we define the test for good cause.\n\n The second possibility is that we avoid defining the test for good\n\ncause. This possibility is real because we could reverse a Rhines stay based\n\non any of the three prongs. For example, we might reverse the grant of a\n\nRhines stay based on dilatoriness or a lack of potential merit rather than\n\n\n\n\n 14\n\naddress the issue of good cause. 8 But if we don’t decide the test for good\n\ncause, how could we apply the collateral-order doctrine based on the\n\nimportance of deciding that test? If we were to do so, we could put\n\nourselves in the odd position of recognizing appellate jurisdiction to\n\ndecide the test for good cause without actually deciding what the test is.\n\n Given these two possibilities, application of the collateral-order\n\ndoctrine based on the test for good cause would paradoxically allow every\n\nrespondent to appeal every grant of a Rhines stay based on an issue that we\n\nhave already decided or, if not, might not even need to decide. This\n\nparadox highlights the need to consider the importance of the issues\n\ncategorically based on the class of orders involved rather than the\n\nparticular arguments raised in a particular case. 9\n\n\n8\n Utah and the dissent criticize Mr. Kell for being dilatory, arguing\nthat Mr. Kell waited until 2017 to seek a stay on his unexhausted claims.\nBecause we lack jurisdiction, we have no occasion to address whether Mr.\nKell was dilatory. We note, however, that Mr. Kell requested a stay in a\nreply brief filed in 2014. See Kell v. Benzon, No. 2: 07-CV-359, dkt. no.\n115 at 50 (D. Utah Jan. 24, 2014) (Pet’r’s Reply Br.) (“Mr. Kell asks this\nCourt to stay these proceedings and hold them in abeyance to allow him to\nreturn to state court to exhaust those claims.”). But as Utah and the dissent\npoint out, he didn’t move for a stay on this issue until 2017.\n9\n The dissent calls this possibility an “irrelevant rabbit hole,”\nreasoning that “the question is whether the district court’s order resolves\nan issue that is completely separate from the merits.” Dissent at 14 n.4. As\nthe dissent elsewhere acknowledges, however, the question must not only\nbe completely separate from the merits but also “important.” Dissent at 9–\n10. Here we are considering the element of importance. Because the\npresence of an important issue is necessary under the collateral-order\n\n 15\n\n ii. Misapplying the Test for Good Cause\n\n On the merits of the stay, Utah argues that the district court\n\nmisapplied the test for good cause. Utah’s argument shows that application\n\nof the good cause test not only overlaps with the merits but would often\n\nrequire consideration of them. For example, petitioners could sometimes\n\nraise the same theory for good cause and the merits of a habeas claim. An\n\nexample is a Brady claim. See Brady v. Maryland, 373 U.S. 83 (1963).\n\nCourts have considered withholding of information as “good cause.” See\n\nDoe v. Jones, 762 F.3d 1174, 1182 (10th Cir. 2014). So when a petitioner\n\nasserts a Brady claim, the petitioner might rely on the withholding of\n\nevidence for both good cause and the merits of the habeas claim. See, e.g.,\n\nWogenstahl v. Mitchell, 668 F.3d 307, 322 (6th Cir. 2012) (concluding that\n\na habeas petitioner “had good cause for failing to raise the Brady issue\n\nprior to 2003, because the new information about [a prosecution witness’s\n\nprior arrest and adjudication of delinquency] was not disclosed until\n\nthen”).\n\n An overlap also exists between the inquiry on good cause and the\n\nmerits of other habeas claims. For example, the inquiry on good cause may\n\noverlap with the merits when a petitioner alleges ineffective assistance of\n\ntrial counsel. Suppose that a petitioner alleges good cause based on post-\n\n\ndoctrine, our inquiry into the importance of the good-cause test is not an\n“irrelevant rabbit hole.”\n 16\n\nconviction counsel’s failure to assert ineffective assistance on the part of\n\ntrial counsel. This allegation could suffice to avoid a procedural default.\n\nMartinez v. Ryan, 566 U.S. 1, 9 (2012). And Utah argues that the tests for\n\ngood cause and procedural default are the same. Given this argument, we\n\nmight find “good cause” based on post-conviction counsel’s\n\nineffectiveness for failure to assert trial counsel’s ineffectiveness. And\n\nonce the case ends in district court, we could again face the issue of trial\n\ncounsel’s ineffectiveness as part of our review on the merits.\n\n The Supreme Court addressed this kind of overlap in Van\n\nCauwenberghe v. Biard, 486 U.S. 517 (1988), and Coopers & Lybrand v.\n\nLivesay, 437 U.S. 463 (1978). In Van Cauwenberghe, the Court held that\n\nthe denial of a motion to dismiss under the doctrine of forum non\n\nconveniens was not separate from the merits because the doctrine involves\n\nfactors (like the location of the witnesses and evidence) that are enmeshed\n\nwith the merits. 486 U.S. at 528–29. And in Coopers & Lybrand, the Court\n\nheld that consideration of class certification involved issues intertwined\n\nwith the merits because class certification involves merits-related matters\n\nlike the typicality of the claims, the adequacy of a representative, and the\n\npresence of common questions of law or fact. 437 U.S. at 469 & n.12.\n\nThus, the Court held that the collateral-order doctrine does not cover\n\ndenials of class certification. Id. at 469. Neither case involved actual\n\n\n\n 17\n\nconsideration of the merits; but in both cases, the issues overlapped with\n\nthe merits.\n\n Like issues involving forum non conveniens and class certification,\n\nthe issue of good cause will often overlap with a court’s preliminary\n\nassessment of the merits, preventing application of the collateral-order\n\ndoctrine. See Cunningham v. Hamilton Cty., Ohio, 527 U.S. 198, 205\n\n(1999) (holding that sanctions orders under Fed. R. Civ. P. 37(a) do not\n\nfall under the collateral-order doctrine because they “often will be\n\ninextricably intertwined with the merits of the action,” “[m]uch like the\n\norders at issue in Van Cauwenberghe and Coopers & Lybrand”).\n\n Here, for example, Utah challenges the finding of good cause,\n\narguing that Mr. Kell could have asserted the claim at trial and in a direct\n\nappeal. To address this argument, we would need to ask whether Mr. Kell’s\n\nattorneys should have asserted the claim at trial or in the direct appeal.\n\nThis inquiry would presumably overlap with Mr. Kell’s habeas claims of\n\nineffective assistance of counsel. Thus, resolution of Utah’s arguments on\n\ngood cause could entangle us in the substance of Mr. Kell’s underlying\n\nhabeas claims. In these circumstances, consideration of good cause under\n\nRhines is not categorically separate from the merits. 10\n\n\n10\n The dissent questions our application of the requirement of complete\nseparation, stating that we are avoiding the “obvious” reality that the\ndefinition of the standard for good cause is “a purely legal issue that has\n\n 18\n\n b. Timeliness, Dilatoriness, and Procedural Default\n\n In this appeal, Utah also argues that (1) Mr. Kell was dilatory and\n\n(2) his unexhausted claim is untimely and procedurally defaulted. Utah\n\ndoes not suggest that these arguments would support collateral-order\n\njurisdiction. But the dissent does, stating that timeliness, dilatoriness, and\n\nprocedural default are separate from the merits.\n\n For the sake of argument, let’s assume that the dissent is right and\n\nignore the fact that Utah (the appellant invoking appellate jurisdiction)\n\ndidn’t present these arguments as grounds to invoke the collateral-order\n\ndoctrine. See pp. 35–36, below (citing cases for the unavailability of sua\n\nsponte arguments to support jurisdiction). As Utah argues, however, the\n\nseparate issue must also be considered important in order to trigger this\n\n\nno overlap with the merits of the case.” Dissent at 14 (emphasis in\noriginal). The dissent bases its disagreement on footnote ten in Mitchell v.\nForsyth, 472 U.S. 511 (1984). Dissent at 14. But this footnote explains that\nan issue is not considered “completely separate” from the merits when its\neffect “may depend . . . on the success of the parties in litigating the other\nlegal and factual issues that form their underlying dispute.” Mitchell, 472\nU.S. at 529–30 n.10 (emphasis added).\n\n The Supreme Court illustrated this point with a disqualification\norder. Id. The disqualification order failed this requirement of “complete\nseparation” because it was “not a legal issue that [could] be decided with\nreference only to undisputed facts and in isolation from the remaining\nissues of the case.” Id.\n\n Under Mitchell’s footnote ten, misapplication of Rhines’s\nrequirement of good cause could not satisfy the “complete separation”\nrequirement unless the issue were categorically separate from the merits of\nany of the habeas claims.\n 19\n\ndoctrine. See p. 5, above. Neither Utah nor the dissent offers any argument\n\nabout the importance of Utah’s arguments on timeliness, dilatoriness, or\n\nprocedural default. These arguments involve garden-variety application of\n\nlegal principles settled long ago. See U.S. Fidelity & Guaranty Co. v. Arch\n\nIns. Co., 578 F.3d 45, 59 (1st Cir. 2009) (concluding that an issue\n\ninvolving insufficiency of an affidavit was not “important enough . . . to\n\njustify the application of the collateral order doctrine”); United States v.\n\nBillmyer, 57 F.3d 31, 35 (1st Cir. 1995) (“Ordinarily, a discovery order\n\nwill meet the legal-importance test only if it presents a claim of clear-cut\n\nlegal error and not merely a challenge to the district judge’s factual\n\ndeterminations or the application of settled legal rule to the particular\n\nfacts.”). Thus, Utah’s arguments on timeliness, dilatoriness, and procedural\n\ndefault would not constitute important issues, as required to trigger the\n\ncollateral-order doctrine.\n\n c. The Categorical Approach\n\n Perhaps in some appeals of Rhines stays, the specific argument being\n\nadvanced might not involve the potential merit of an unexhausted claim.\n\nBut the Supreme Court has “consistently eschewed a case-by-case approach\n\nto deciding whether an order is sufficiently collateral.” Cunningham v.\n\n\n\n\n 20\n\nHamilton Cty., Ohio, 527 U.S. 198, 206 (1999); see also p. 11 & n.5\n\n(discussing United States v. Bolden, 353 F.3d 870, 876 (10th Cir. 2003)).\n\n The wisdom of the Supreme Court’s approach is self-evident. For\n\nexample, let’s assume that Utah’s appellate arguments are important and\n\ncompletely separate from the merits. If we were to base the collateral-order\n\ndoctrine solely on the happenstance of what Utah argues in a given case,\n\nwe would be allowing or disallowing interlocutory appeals of all Rhines\n\nstays based on what a single party has chosen to argue in a single case.\n\nTo avoid this anomaly, the Supreme Court has required us to consider the\n\nunderlying class of orders rather than the peculiarities of the arguments\n\npresented by this particular appellant. See p. 11, above. So here we\n\nconsider the entire category of orders. See id.\n\n The dissent apparently agrees, stating that we must “look[] to the\n\nissues the class of orders (Rhines stays) generally raise.” Dissent at 12.\n\nAnd the dissent acknowledges that we are not to focus on “case-specific\n\nissues,” such as the issues presented in this particular order granting a\n\nRhines stay. Id.\n\n With this acknowledgment, the dissent contends that the appellant\n\nmust present “at least one issue” that is “completely separate from the\n\nmerits.” Id. at 10 (emphasis in original). But the Supreme Court has\n\nconsistently rejected this approach, holding that even if some appeals of\n\nRhines stays might involve appellate issues separable from the merits, the\n\n 21\n\ncollateral-order doctrine cannot apply absent complete separation for the\n\nentire class of orders. Richardson-Merrell, Inc. v. Koller, 472 U.S. 424,\n\n439 (1985); 11 see also Cunningham v. Hamilton Cty., Ohio, 527 U.S. 198,\n\n206 (1999) (“Perhaps not every discovery sanction will be inextricably\n\nintertwined with the merits, but we have consistently eschewed a case-by-\n\ncase approach to deciding whether an order is collateral.”). So when we\n\nassess whether the class of orders entails complete separation from the\n\nmerits, we consider the issues in all grants of stays under Rhines. The\n\npresence of a single issue separate from the merits in a particular appeal\n\nwould not trigger the collateral-order doctrine. See Cunningham, 527 U.S.\n\nat 205–06 (holding that sanctions orders under Fed. R. Civ. P. 37(a) are\n\ncategorically considered intertwined with the merits even though sanctions\n\norders are sometimes separate from the merits); Koller, 472 U.S. at 439–40\n\n\n\n11\n The Koller Court explained:\n\n This Court . . . has expressly rejected efforts to reduce the\n finality requirement of [28 U.S.C.] § 1291 to a case-by-case\n determination of whether a particular ruling should be subject to\n appeal. Even if some orders disqualifying counsel are separable\n from the merits of the litigation, many are not. Orders\n disqualifying attorneys on the ground that they should testify at\n trial, for example, are inextricable from the merits because they\n involve an assessment of the likely course of the trial and the\n effect of the attorney’s testimony on the judgment. Appellate\n review of orders disqualifying counsel for misconduct may be\n entwined with the merits of the litigation as well.\n\n472 U.S. at 439 (citations omitted).\n 22\n\n(holding that orders disqualifying counsel in civil cases are categorically\n\nconsidered intertwined with the merits because many are even though some\n\naren’t); see also In re Continental Investment Corp., 637 F.2d 1, 6 (1st Cir.\n\n1980) (holding “that denials of disqualification motions as a class raise\n\nsignificant legal questions too rarely to bring them within the Cohen\n\nexception”).\n\n The categorical approach is apparent in the Supreme Court’s\n\nhandling of qualified immunity. There the Court has held that legal issues\n\ninvolving a clearly established violation are completely separate from the\n\nmerits. Mitchell v. Forsyth, 472 U.S. 511, 528 (1985). But the Supreme\n\nCourt made that determination by considering the issues arising in the\n\nentire class of orders rather than in the particular case being reviewed. See\n\nid. at 524–30.\n\n The Supreme Court later went further, expressly disavowing a case-\n\nby-case approach in Johnson vs. Jones, 515 U.S. 304 (1995). There the\n\nCourt refused to extend the collateral-order doctrine to cover denials of\n\nqualified immunity based on insufficiency of the evidence. Johnson, 515\n\nU.S. at 314–15. The Court explained that under the categorical approach,\n\nappellate judges could not consider the particular facts to determine the\n\napplicability of the collateral-order doctrine. Id. at 315. Instead, judges\n\nwere to consider the kinds of issues likely to arise in appeals involving this\n\nclass of orders. Id. at 315–17. For example, the Supreme Court\n\n 23\n\nacknowledged that the facts in Johnson itself were straightforward, but\n\nstressed that many cases involving constitutional torts would entail factual\n\ndisputes ill-suited for review under the collateral-order doctrine. Id. at\n\n316.\n\n Beyond qualified immunity, circuit courts have followed the Supreme\n\nCourt’s lead by deciding the element of complete separation based on the\n\nclass of orders involved rather than approaching this element based on the\n\nparticular issues raised by a particular appellant. See Henry v. Lake\n\nCharles Am. Press, L.L.C., 566 F.3d 164, 173 (5th Cir. 2009) (“Consistent\n\nwith Supreme Court precedent and the general purposes of the final\n\njudgment rule, we determine whether an order is appealable as a general or\n\ncategorical matter.”); see also In re Carco Electronics, 536 F.3d 211, 213\n\n(3d Cir. 2008) (“[T]he Supreme Court’s statement in Cunningham that we\n\nshould not apply the collateral order doctrine on a ‘case-by-case’ basis\n\nindicates that we should not attempt to carve out individualized, case-\n\nspecific exceptions to the general rule that discovery orders are not\n\nimmediately appealable.”); Abelesz v. OTP Bank, 692 F.3d 638, 649 (7th\n\nCir. 2012) (“The Supreme Court has applied the collateral order rule\n\ncategorically, treating different sorts of defenses or issues as either\n\ncovered or not covered.”).\n\n * * *\n\n\n\n 24\n\n Viewed as a category, interlocutory appeals of Rhines stays would\n\ngenerally enmesh us in the merits. Thus, the collateral-order doctrine’s\n\nsecond element is not met when the district court grants a Rhines stay.\n\n B. The grant of a Rhines stay can be reviewed in the appeal\n from a final judgment.\n\n Utah fails to satisfy not only the collateral-order doctrine’s second\n\nelement but also the third element.\n\n Under this element, appellate jurisdiction exists only if the issue is\n\nimportant and could not otherwise be effectively reviewed after the entry\n\nof final judgment. Mitchell v. Forsyth, 472 U.S. 511, 525 (1985). But we\n\ndo not just consider unreviewability; we also consider the importance of\n\nthe interest lost by deferring review until after the final judgment. See\n\nDigital Equip. Corp. v. Desktop Direct, Inc., 511 U.S. 863, 878–79 (1994).\n\nThis inquiry entails “a judgment about the value of the interests that would\n\nbe lost through rigorous application of the final judgment requirement.” Id.\n\nOn this element, Utah hasn’t satisfied its burden.\n\n Utah argues that the grant of a Rhines stay is unreviewable after a\n\nfinal judgment because (1) the loss of time can never be remedied and (2)\n\nthe grant of a stay becomes moot upon entry of a final judgment. We reject\n\nboth arguments.\n\n As Utah points out, the delay itself is unreviewable because a court\n\ncan’t restore Utah’s lost time. But we do not ordinarily regard the loss of\n\n\n 25\n\ntime as sufficiently important to trigger the collateral-order doctrine. See\n\nUnited States v. Section 17 Tp. 23 North, Range 22 East of IBM, Delaware\n\nCty., Okla., 40 F.3d 320, 322 (10th Cir. 1994) (holding that an interest in\n\ndefending a forfeiture action now, as opposed to later, “is not the type of\n\n‘important’ right which the Supreme Court contemplated as requiring\n\nimmediate review in [Digital Equipment Corp. v. Desktop Direct, Inc., 511\n\nU.S. 863 (1994)]”). After all, no pretrial decision can ever restore a party’s\n\nlost time, and we routinely disallow interlocutory appeals for most pretrial\n\ndecisions. See Mesa Oil, Inc. v. United States, 467 F.3d 1252, 1255 (10th\n\nCir. 2006) (“The costs of unnecessary litigation caused by what eventually\n\nturns out to be an error by the district court is insufficient to warrant an\n\ninterlocutory appeal.”); see also In re Kozeny, 236 F.3d 615, 619–20 (10th\n\nCir. 2000) (two-judge motions panel) 12 (“If the stay merely delays the\n\nfederal litigation, courts have generally held the stay orders not to be\n\nappealable.”); accord Kershaw v. Shalala, 9 F.3d 11, 14 (5th Cir. 1993)\n\n(“Absent a Moses Cone situation, stay orders . . . are usually not\n\n\n\n\n12\n Because Kozeny was issued by a two-judge motions panel, we would\nordinarily discount the opinion’s precedential value. Crystal Clear\nComm’ns, Inc. v. Sw. Bell Tel. Co., 415 F.3d 1171, 1176 n.3 (10th Cir.\n2005). Here, however, we are not relying on Kozeny for its precedential\nvalue. We are instead relying only on the opinion’s observation about our\ngeneral practice in regarding stay orders as unappealable.\n\n\n 26\n\nreviewable as collateral orders.”); 13 see also Hon. Edith H. Jones, Appeals\n\nof Arbitration Orders—Coming Out of the Serbonian Bog, 31 S. Tex. L.\n\nRev. 361, 372 (1990) (“Absent exceptional circumstances, it is unlikely\n\nthat an order granting a motion to stay proceedings should be appealable as\n\na collateral order.”).\n\n Time is a precious commodity in habeas proceedings, particularly\n\nwhen the petitioner faces a death sentence (as Mr. Kell does). And until\n\nnow, the case has lingered in state and federal courts for roughly a quarter\n\nof a century. But we cannot single out particular cases to decide the extent\n\nof the interest lost by deferring review. Instead, we must consider the\n\npublic interest based on the class of orders (Rhines stays). See Mohawk\n\nIndus., Inc. v. Carpenter, 558 U.S. 100, 107 (2009); 14 In re Motor Fuel\n\n\n13\n In Kershaw, the Fifth Circuit observed that in Moses Cone, the\nSupreme Court had regarded a stay as final when its purpose and effect\nwere to surrender jurisdiction of a federal suit to a state court. Kershaw, 9\nF.3d at 14 (quoting Moses H. Cone Memorial Hosp. v. Mercury Const.\nCorp., 460 U.S. 1, 11 n.11 (1983)). This case does not involve surrender of\njurisdiction over a federal suit. Instead, the district court required Mr. Kell\nto exhaust state-court remedies so that the federal court could consider the\nhabeas claim.\n14\n In Mohawk Industries, the Supreme Court explained:\n\n [T]he decisive consideration is whether delaying review until the\n entry of final judgment “would imperil a substantial public\n interest” or “some particular value of higher order.”\n\n In making this determination, we do not engage in an\n “individualized jurisdictional inquiry.” Rather, our focus is on\n\n 27\n\nTemperature Sales Practices Litig., 641 F.3d 470, 482 (10th Cir. 2011)\n\n(“When analyzing the third Cohen requirement, we do not consider whether\n\nthe circumstances of the particular case before us warrant our immediate\n\nreview; rather, we examine whether the entire category of rulings to which\n\nthe claim belongs can be adequately vindicated on review of a final\n\njudgment or by other means.”). This approach requires us to decide\n\nwhether the value that we place on immediate review would override\n\nCongress’s policy against piecemeal review.\n\n To answer, we must consider the many important interests that exist,\n\noften in tension with one another. For example, the state has important\n\ninterests in comity and enforcement of its own criminal judgments, which\n\nCongress recognized in the Antiterrorism and Effective Death Penalty Act\n\nof 1996. See Williams v. Taylor, 529 U.S. 420, 436 (2000) (stating that the\n\nAct was designed to advance “comity, finality, and federalism”). But\n\nhabeas review inherently creates tension with comity, as federal courts\n\nreview decisions by a state’s highest court. See Duckworth v. Eagan, 492\n\n\n\n “the entire category to which the claim belongs.” As long as the\n class of claims, taken as a whole, can be adequately vindicated\n by other means, “the chance that the litigation at hand might be\n speeded, or a ‘particular injustic[e]’ averted,” does not provide\n a basis for jurisdiction under § 1291.\n\nMohawk Indus., 558 U.S. at 107 (citations omitted).\n\n\n 28\n\nU.S. 195, 211 (1989) (discussing the tension of federal-state relations\n\nbecause of habeas review, where “lower federal courts often sit in ‘review’\n\nof the judgments of the highest courts of a state judicial system”).\n\n To ease this tension, Congress has required habeas petitioners to\n\nexhaust state-court remedies. 28 U.S.C. § 2254(b)(1)(A); see also Rose v.\n\nLundy, 455 U.S. 509, 518 (1982) (“The exhaustion doctrine is principally\n\ndesigned to protect the state courts’ role in the enforcement of federal law\n\nand prevent disruption of state judicial proceedings.”). Exhaustion,\n\nhowever, can slow the state’s ability to enforce criminal judgments,\n\nespecially those involving capital sentences. See Ira P. Robbins, Toward a\n\nMore Just & Effective System of Review in State Death Penalty Cases, 40\n\nAm. U. L. Rev. 1, 131 (1990) (“[R]equiring exhaustion [in habeas review\n\nof death-penalty cases] usually necessitates further delay, even if the\n\nunexhausted claim is an obviously frivolous one.”). This risk is\n\nparticularly significant in habeas proceedings, where swift action is\n\nessential. See Rhodes v. Hannigan, 12 F.3d 989, 992 (10th Cir. 1993)\n\n(“Habeas corpus ‘is a speedy remedy, entitled by statute to special,\n\npreferential consideration to insure expeditious hearing and\n\ndetermination.’” (quoting Van Buskirk v. Wilkinson, 216 F.2d 735, 737–38\n\n(9th Cir. 1954))); Johnson v. Rogers, 917 F.2d 1283, 1284 (10th Cir. 1990)\n\n(“[W]rits of habeas corpus are intended to afford a ‘swift and imperative\n\n\n\n 29\n\nremedy in all cases of illegal restraint or confinement.’” (quoting Fay v.\n\nNoia, 372 U.S. 391, 400 (1963))).\n\n The Supreme Court sought to balance these competing interests in\n\nRhines by giving discretion to federal district courts to stay habeas\n\nproceedings while a petitioner exhausts state-court remedies. Rhines v.\n\nWeber, 544 U.S. 269, 276–78 (2005). But discretion can be abused. The\n\nquestion presented here is when an appellate court should review the\n\ndistrict court’s exercise of discretion. 15 Given the conflicting interests, we\n\nmust consider whether interlocutory review of Rhines stays would speed\n\nreview or slow it through piecemeal review.\n\n For this inquiry, we start with Congress’s policy against piecemeal\n\nreview. In general, Congress has tried to avoid piecemeal review by\n\nconfining appellate review to final orders. See Abney v. United States, 431\n\nU.S. 651, 656 (1977) (“[T]here has been a firm congressional policy\n\nagainst interlocutory or ‘piecemeal’ appeals and courts have consistently\n\n\n15\n Other circuit courts have generally declined to apply the collateral-\norder doctrine to orders subject to the abuse-of-discretion standard. See\nGrace v. Vannoy, 826 F.3d 813, 820 (5th Cir. 2016) (“Typically, orders\nreviewable for abuse of discretion are not appealable under the collateral-\norder doctrine.”); In re Kemble, 776 F.2d 802, 806 (9th Cir. 1985)\n(“Ordinarily we should not use the collateral order doctrine to examine the\nexercise of discretion by trial judges.”). One leading treatise attributed this\n“wise” practice to a reluctance to undertake interlocutory review when\nappellate courts have allowed district courts to exercise discretion. 15A\nCharles Alan Wright, Arthur R. Miller & Edward H. Cooper, Federal\nPractice & Procedure: Jurisdiction & Related Matters, § 3911.5, at 433–\n35 (2d ed. 1992).\n 30\n\ngiven effect to that policy.”). And Congress has expressed its judgment\n\n“that the district judge has the primary responsibility to police the\n\nprejudgment tactics of litigants,” reasoning “that the district judge can\n\nbetter exercise that responsibility if the appellate courts do not repeatedly\n\nintervene to second-guess prejudgment rulings.” Richardson-Merrell, Inc.\n\nv. Koller, 472 U.S. 424, 436 (1985) (emphasis in original).\n\n The Supreme Court has respected this congressional policy choice\n\nand restricted prejudgment review because it inefficiently fosters\n\npiecemeal appeals. See Mohawk Indus., Inc. v. Carpenter, 558 U.S. 100,\n\n106 (2009) (“Permitting piecemeal, prejudgment appeals, we have\n\nrecognized, undermines ‘efficient judicial administration’ and encroaches\n\nupon the prerogatives of district court judges, who play a ‘special role’ in\n\nmanaging ongoing litigation.”); Richardson-Merrell, Inc. v. Koller, 472\n\nU.S. 424. 430 (1985) (stating that the final judgment rule prevents delays\n\nfrom frequent appellate interruptions in the litigation); Abney, 431 U.S. at\n\n657 (stating that 28 U.S.C. § 1291, which restricts appellate review to final\n\ndecisions, is designed to prevent delays and disruptions through\n\nintermediate appeals).\n\n Given Congress’s preference against interlocutory review, we must\n\nconsider whether Rhines stays involve aberrant circumstances justifying\n\nour intrusion into Congress’s effort to avoid piecemeal review. We think\n\n\n\n 31\n\nnot. In Rhines itself, the Supreme Court balanced the compelling interests\n\nby devising a procedure to accommodate\n\n the state’s interest in comity,\n\n the congressional requirement of exhaustion of state-court\n remedies,\n\n the congressional determination that piecemeal review\n generally slows the litigation,\n\n the universal recognition that habeas cases should proceed\n expeditiously, and\n\n the congressional objective in the Antiterrorism and Effective\n Death Penalty Act to streamline habeas proceedings.\n\nRhines v. Weber, 544 U.S. 269, 276–78 (2005); see Howard v. Norris, 616\n\nF.3d 799, 802–03 (8th Cir. 2010) (stating that “Rhines effectively balances\n\nthe state’s interest in avoiding delay in a habeas proceeding, with the\n\npetitioner’s (and the state’s) interest in having habeas claims addressed\n\nfirst in state court”); see also Grace v. Vannoy, 826 F3d 813, 819 (5th Cir.\n\n2016) (stating that in Rhines, “the Supreme Court implicitly de-emphasized\n\nthe importance of the state’s interests in finality and speedy resolution of\n\nmixed federal petitions”).\n\n If we were to intervene after a district court granted a stay, would\n\nour intervention quicken or slow the litigation? Here, the district court\n\nstayed the proceedings for only a single claim and stated that the\n\nproceedings would continue on all of the other habeas claims. If we were\n\n\n 32\n\nto interject ourselves now, we could inadvertently trigger simultaneous\n\nlitigation of the same case in three courts:\n\n 1. the state district court or the state appellate court,\n\n 2. the federal district court, and\n\n 3. our court.\n\nWe question the efficiency of duplicative litigation in three courts. See\n\nSwanson v. DeSantis, 606 F.3d 829, 833 (6th Cir. 2010) (“Claim-by-claim\n\nlitigation in the district and appellate courts ‘undermines [Congress’] goal\n\nof streamlining federal habeas proceedings . . . .” (emphasis and alteration\n\nin original) (quoting Rhines v. Weber, 544 U.S. 269, 277 (2005))).\n\n But double or triple litigation tracks could create not only\n\ninefficiency but also more delay. For example, if we were to affirm the\n\ngrant of a stay, we could be needlessly slowing the habeas litigation for the\n\ntime that we take to decide the appeal. And, of course, district courts\n\naren’t limited to the number of Rhines stays in a single case. Here, for\n\nexample, the district court has issued two Rhines stays. If those stays had\n\ntriggered the collateral-order doctrine, we could have slowed the litigation\n\ntwice already with the possibility of a third delay when the case ends in\n\ndistrict court. In these circumstances, we decline to single out Rhines stays\n\n\n\n\n 33\n\nas a class of orders that would be resolved more quickly by authorizing\n\npiecemeal appeals. 16\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Troy Michael KELL, Petitioner-Appellee, v. Larry BENZON, Warden Utah State Prison, Respondent-Appellant.\\nCourt: U.S. Court of Appeals for the Tenth Circuit\\nDate decided: 2019-05-28\\nOpinion type: majority\\nHas dissenting opinion: Yes\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nPUBLISH FILED\\n United States Court of Appeals\\n UNITED STATES COURT OF APPEALS Tenth Circuit\\n\\n FOR THE TENTH CIRCUIT May 28, 2019\\n _________________________________\\n Elisabeth A. Shumaker\\n Clerk of Court\\nTROY MICHAEL KELL,\\n\\n Petitioner - Appellee,\\n\\nv. No. 17-4191\\n\\nLARRY BENZON, Warden Utah\\nState Prison,\\n\\n Respondent - Appellant.\\n\\n\\n _________________________________\\n\\n Appeal from the United States District Court\\n for the District of Utah\\n (D.C. No. 2:07-CV-00359-CW)\\n _________________________________\\n\\nAndrew F. Peterson, Assistant Solicitor General (Tyler R. Green, Utah\\nSolicitor General, Thomas Brunker, Deputy Solicitor General, Daniel W.\\nBoyer, Assistant Solicitor General, Sean D. Reyes, Utah Attorney General,\\nSalt Lake City, Utah, with him on the briefs), for Respondent-Appellant.\\n\\nLindsey Layer, Assistant Federal Public Defender, Salt Lake City, Utah\\n(Jon M. Sands, Federal Public Defender for the District of Arizona,\\nAlexandra LeClair, Assistant Federal Public Defender, Salt Lake City,\\nUtah, with him on the briefs), for Petitioner-Appellee.\\n _________________________________\\n\\nBefore BACHARACH, BALDOCK, and PHILLIPS, Circuit Judges.\\n _________________________________\\n\\nBACHARACH, Circuit Judge.\\n _________________________________\\n\\n This is an interlocutory appeal from an order staying a habeas\\n\\nproceeding. We lack jurisdiction and dismiss the appeal.\\n\\n Mr. Troy Kell sought habeas relief, but he had not exhausted two of\\n\\nhis claims in state court. The unexhausted claims created a Catch-22 for\\n\\nMr. Kell, risking a dismissal of all of his claims without an opportunity to\\n\\ntimely refile. To relieve Mr. Kell of this Catch-22, the district court\\n\\nentered a limited stay, halting proceedings on one of the unexhausted\\n\\nclaims while Mr. Kell returned to state court to exhaust the claim. For the\\n\\nremaining habeas claims, however, the district court continued with the\\n\\nproceedings.\\n\\n In the midst of the ongoing habeas proceedings in district court, Utah\\n\\nappealed from the grant of a stay, arguing that the district court should\\n\\nhave declined to grant a stay. Our threshold question involves appellate\\n\\njurisdiction. To establish jurisdiction, Utah relies on the collateral-order\\n\\ndoctrine, which allows appeals from some decisions before the entry of a\\n\\nfinal judgment. But the district court’s issuance of a stay does not satisfy\\n\\nthe collateral-order doctrine’s requirements, so we dismiss the appeal for\\n\\nlack of appellate jurisdiction.\\n\\n1. Mr. Kell timely files a habeas petition.\\n\\n Mr. Kell was convicted of murder and sentenced to death in Utah,\\n\\nand his conviction became final roughly sixteen years ago. Mr. Kell then\\n\\nhad one year to seek federal habeas relief, but the one-year limitations\\n\\n 2\\n\\nperiod was tolled while he pursued state post-conviction remedies. 28\\n\\nU.S.C. § 2244(d). When the state post-conviction proceedings ended in\\n\\n2009, Mr. Kell timely filed a federal habeas petition.\\n\\n2. The district court stays the habeas case to allow Mr. Kell to\\n exhaust a new claim.\\n\\n In 2013, Mr. Kell asserted two new habeas claims: (1) that the trial\\n\\ncourt had improperly commented to the jury that Mr. Kell bore the burden\\n\\nin the penalty phase to show that his life should be spared and (2) that the\\n\\njurors had improperly considered extraneous information. Mr. Kell had not\\n\\nexhausted the two new claims, so the district court needed to grapple with\\n\\nhow to proceed. Continuing with the new habeas claims could prevent\\n\\nconsideration of any of the claims because a federal district court must\\n\\nordinarily dismiss the entire petition when one or more of the habeas\\n\\nclaims are unexhausted. Rose v. Lundy, 455 U.S. 509, 522 (1982). Given\\n\\nthe possibility of dismissal, Mr. Kell faced a dilemma: If the district court\\n\\nwere to dismiss the habeas petition and he later refiled in federal court, the\\n\\nstatute of limitations might have expired on all of his claims.\\n\\n To avoid this dilemma, Mr. Kell requested a stay so that he could\\n\\nexhaust his new habeas claims in state court. For this request, Mr. Kell\\n\\ninvoked a procedure adopted in Rhines v. Weber, 544 U.S. 269 (2005).\\n\\nUnder Rhines, a district court may stay habeas proceedings to permit\\n\\nexhaustion of a claim upon satisfaction of three elements:\\n\\n\\n 3\\n\\n 1. “Good cause” exists for the failure to exhaust the claim.\\n\\n 2. The unexhausted claim is “potentially meritorious.”\\n\\n 3. The petitioner did not engage in “abusive litigation tactics” or\\n intentionally delay the proceedings.\\n\\nRhines, 544 U.S. at 277–78. The district court declined to stay the claim\\n\\ninvolving extraneous influence on the jury, concluding that this claim\\n\\nlacked potential merit. But the district court granted the stay on the claim\\n\\ninvolving the judge’s comment to the jury, concluding that Mr. Kell had\\n\\nsatisfied the three elements for a Rhines stay. For the remaining habeas\\n\\nclaims, however, the district court stated that the proceedings would\\n\\ncontinue without interruption. 1\\n\\n3. Utah appeals the order granting a limited stay.\\n\\n In this appeal, Utah argues that the federal district court erred in\\n\\ngranting the stay because\\n\\n the court used the wrong test for “good cause” and misapplied\\n that test,\\n\\n the new habeas claim lacks potential merit based on timeliness,\\n the existence of a procedural default, and the absence of a\\n constitutional violation, and\\n\\n Mr. Kell was dilatory by waiting over three years to assert the\\n new habeas claim and over eight years to seek a stay based on\\n this claim.\\n\\n\\n\\n1 As the dissent points out, the district court denied certification of an\\ninterlocutory appeal. In denying certification, the district court reasoned\\nthat an interlocutory appeal would slow the litigation.\\n 4\\n\\n4. We lack jurisdiction to consider interlocutory appeals from\\n Rhines stays.\\n\\n We can consider these arguments only if Utah establishes appellate\\n\\njurisdiction. See EEOC v. PJ Utah, L.L.C., 822 F.3d 536, 542 n.7 (10th\\n\\nCir. 2016) (“[T]he appellant . . . bears the burden to establish appellate\\n\\njurisdiction.”). We typically acquire jurisdiction through the district\\n\\ncourt’s entry of a final decision. 28 U.S.C. § 1291. But a stay does not\\n\\nordinarily constitute a final decision. See Crystal Clear Commc’ns, Inc. v.\\n\\nSw. Bell Tel. Co., 415 F.3d 1171, 1176 (10th Cir. 2005) (“If a stay merely\\n\\ndelays litigation and does not effectively terminate proceedings, it is not\\n\\nconsidered a final decision.”).\\n\\n Utah argues that we nonetheless have jurisdiction under the\\n\\ncollateral-order doctrine. This doctrine would apply only if the district\\n\\ncourt’s decision\\n\\n conclusively decided the disputed question,\\n\\n resolved an important issue separate from the merits, and\\n\\n could not be effectively reviewed on direct appeal.\\n\\nVan Cauwenberghe v. Biard, 486 U.S. 517, 522 (1988). The failure to\\n\\nsatisfy any of the three elements would prevent us from applying the\\n\\ncollateral-order doctrine. See Stubblefield v. Windsor Capital Grp., 74 F.3d\\n\\n990, 997 (10th Cir. 1996) (stating that the collateral-order doctrine “does\\n\\nnot apply unless each of the three requirements are met”).\\n\\n 5\\n\\n Each element is considered stringent. E.g., Flanagan v. United\\n\\nStates, 465 U.S. 259, 270 (1984). And “[i]n case after case in year after\\n\\nyear, the Supreme Court has issued increasingly emphatic instructions that\\n\\nthe class of cases capable of satisfying this ‘stringent’ test should be\\n\\nunderstood as ‘small,’ ‘modest,’ and ‘narrow.’” United States v. Wampler,\\n\\n624 F.3d 1330, 1334 (10th Cir. 2010) (Gorsuch, J.). Utah bears the burden\\n\\non each element of this “stringent” test. See Los Lobos Renewable Power,\\n\\nL.L.C. v. Americulture, Inc., 885 F.3d 659, 664 (10th Cir. 2018) (stating\\n\\nthat the “party asserting jurisdiction under the collateral order doctrine”\\n\\nbears the burden on each element).\\n\\n We assume, for the sake of argument, that an order issuing a Rhines\\n\\nstay conclusively determines the disputed question. But the grant of a\\n\\nRhines stay involves issues that are intertwined with the merits and\\n\\nreviewable on direct appeal. We thus lack jurisdiction under the collateral-\\n\\norder doctrine. See Crystal Clear Commc’ns, Inc. v. Sw. Bell Tel. Co., 415\\n\\nF.3d 1171, 1178 (10th Cir. 2005) (noting that the collateral-order doctrine\\n\\ndoes not support appellate jurisdiction if any element is unsatisfied).\\n\\n A. The grant of a Rhines stay is not completely separate from\\n the merits.\\n\\n The collateral-order doctrine applies only when the order involves an\\n\\nimportant issue that is not intertwined with the merits. Coopers & Lybrand\\n\\nv. Livesay, 437 U.S. 463, 469 (1978). For this element, Utah must show\\n\\n\\n 6\\n\\nthat the issues bearing on the appropriateness of a Rhines stay are\\n\\n“completely separate” from the merits. E.g., Cunningham v. Hamilton Cty.,\\n\\nOhio, 527 U.S. 198, 205 (1999). Utah has not made this showing.\\n\\n 1. Avoidance of Piecemeal Litigation\\n\\n The requirement of complete separation is designed to prevent\\n\\npiecemeal appellate review. Van Cauwenberghe v. Biard, 486 U.S. 517,\\n\\n527 (1988). Given this purpose, the collateral-order doctrine would\\n\\nordinarily apply only if an appellate court would probably not need to\\n\\nconsider the merits a second time. 2\\n\\n But interlocutory appeals of Rhines stays would often require federal\\n\\nappellate courts to consider the merits at least twice:\\n\\n once in the interlocutory appeal (when the respondent argues\\n that a Rhines stay is improper because the petitioner’s\\n unexhausted claim lacks potential merit) and\\n\\n again after entry of the judgment (when the parties disagree\\n over the claim’s actual merit).\\n\\n\\n\\n2\\n The Supreme Court has explained:\\n\\n The requirement that the matter be separate from the merits of\\n the action itself means that review now is less likely to force the\\n appellate court to consider approximately the same (or a very\\n similar) matter more than once, and also seems less likely to\\n delay trial court proceeds (for, if the matter is truly collateral,\\n those proceedings might continue while the appeal is pending).\\n\\nJohnson v. Jones, 515 U.S. 304, 311 (1995) (emphasis in original).\\n\\n\\n 7\\n\\nAnd if the district court enters multiple Rhines stays, 3 we could face three\\n\\nor more appeals with overlapping issues.\\n\\n This possibility is apparent here. For example, consider Utah’s\\n\\nargument that the district court’s jury instruction was correct. This\\n\\nargument involves a classic issue on the merits. See Gillette v. Prosper,\\n\\n858 F.3d 833, 839 (3d Cir. 2017) (concluding that the order being appealed\\n\\nwas “closely related” to the merits because “both concern[ed] alleged\\n\\nconstitutional violations” and involved potential release from prison). If\\n\\nwe were to recognize appellate jurisdiction at this stage and Mr. Kell were\\n\\nto obtain habeas relief, we would decide the “potential merit” of Mr. Kell’s\\n\\nnew claim now and the claim’s “actual merit” after the entry of a final\\n\\njudgment. It is hard to imagine a better example of piecemeal litigation—\\n\\nprecisely what the Supreme Court has tried to avoid by limiting the\\n\\ncollateral-order doctrine to classes of orders involving “complete\\n\\nseparation” from the merits.\\n\\n The dissent disagrees:\\n\\n Even where a district court issues multiple Rhines stays, each\\n Rhines stay concerns different claims by a petitioner and\\n therefore different issues. To illustrate, a district court issues a\\n Rhines stay on claim x, allowing the petitioner to exhaust the\\n claim in state court. After the petitioner exhausts claim x in state\\n court and returns to federal court, the district court is not going\\n to issue another Rhines stay for the purpose of allowing the\\n\\n3\\n Here, for example, the district court granted two Rhines stays. Our\\nappeal involves only the second stay.\\n\\n 8\\n\\n petitioner to exhaust claim x. If there is a second Rhines stay, it\\n would be issued for the petitioner to exhaust claim y. If both of\\n these Rhines stays are appealed, and then the final judgment is\\n appealed, the “same issues” would not be before this Court three\\n or more times.\\n\\nDissent at 16–17 n.5 (emphasis in original).\\n\\n We respectfully think that the dissent has misunderstood us. When\\n\\nreviewing a Rhines stay, we consider the “potential merit” of the\\n\\nunexhausted claim. For example, let’s consider Utah’s argument that the\\n\\ndistrict court erred in granting a stay because the unexhausted habeas claim\\n\\nlacks potential merit. If we have appellate jurisdiction under the collateral-\\n\\norder doctrine, we would consider whether the district court acted within\\n\\nits discretion in treating the unexhausted claim as potentially meritorious.\\n\\n Let’s assume, for the sake of argument, that we were to uphold this\\n\\ndetermination. When the habeas case ends in district court, the parties\\n\\ncould appeal the district court’s ultimate determination of the claim’s\\n\\nactual merit. See Alexander v. U.S. Parole Comm’n, 514 F.3d 1083, 1087\\n\\n(10th Cir. 2008) (stating that a conditional writ of habeas corpus is final,\\n\\ncreating appellate jurisdiction); Burton v. Johnson, 975 F.2d 690, 693–94\\n\\n(10th Cir. 1992) (stating that a conditional writ of habeas corpus was an\\n\\nappealable final judgment).\\n\\n The same would be true for any case involving a Rhines stay. So in a\\n\\ncase with multiple Rhines stays and multiple interlocutory appeals, we\\n\\n\\n\\n 9\\n\\ncould face the same issues after a final judgment (even if the interlocutory\\n\\nappeals individually involved different issues).\\n\\n 2. The Significance of the Relationship Between the Rhines\\n Factor of “Potential Merit” and the Actual Merits of Mr.\\n Kell’s New Claim\\n\\n Because “potential merit” is essential for Rhines stays, interlocutory\\n\\nreview would frequently require us to consider the potential merit of the\\n\\nunderlying habeas claims. And “potential merit” is obviously not\\n\\n“completely separate” from the actual merits. The dissent agrees, stating\\n\\nthat the Rhines issue (“potential merit”) “undoubtedly overlaps with the\\n\\nmerits.” Dissent at 16. 4\\n\\n\\n\\n\\n4\\n Utah and the dissent downplay the significance of this relationship\\nbetween the two, calling “potential merit” a “fraction of a fraction” of the\\ntest governing grants of Rhines stays. Appellant’s Reply Br. at 5; Dissent\\nat 16.\\n\\n It is true that potential merit is just one element for a Rhines stay.\\nBut a court can enter a Rhines stay only if the unexhausted claim has\\npotential merit. See pp. 3–4, above. Thus, potential merit may be a\\n“fraction” of the test, but it is a requirement in any Rhines stay.\\n\\n Utah also asserts that the “underlying merit of a habeas claim is only\\na fraction of the ‘potential merit’ factor.” Appellant’s Reply Br. at 5. We\\nare not sure why Utah regards “potential merit” under Rhines as more\\ninclusive than the actual merit of a habeas claim, and Utah supplies no\\nexplanation. Even if Utah were right, however, it has not explained how\\nthe issue of potential merit could satisfy the requirement of complete\\nseparation from the merits.\\n\\n\\n 10\\n\\n 3. Application of the Test of “Complete Separation”\\n\\n To apply the element of complete separation, we must evaluate the\\n\\npertinent issue based on the entire class of orders (Rhines stays) rather\\n\\nthan the particular arguments in this appeal. United States v. Bolden, 353\\n\\nF.3d 870, 876 (10th Cir. 2003). 5 We thus consider whether the issues\\n\\nunderlying a Rhines stay are, “as a whole,” completely separate from the\\n\\nmerits. Id.\\n\\n The Supreme Court has repeatedly cautioned that the collateral-order\\n\\ndoctrine requires “complete separation” from the merits. E.g., Microsoft\\n\\nCorp. v. Baker, 137 S. Ct. 1702, 1708 n.3 (2017); Will v. Hallock, 546 U.S.\\n\\n345, 349 (2006); Sell v. United States, 539 U.S. 166, 176 (2003);\\n\\nCunningham v. Hamilton Cty., Ohio, 527 U.S. 198, 205 (1999);\\n\\nQuackenbush v. Allstate Ins. Co., 517 U.S. 706, 712 (1996); Johnson v.\\n\\nJones, 515 U.S. 304, 310–11 (1995); Digital Equip. Corp. v. Desktop\\n\\nDirect, Inc., 511 U.S. 863, 867 (1994); Richardson-Merrell, Inc. v. Koller,\\n\\n\\n5\\n In Bolden, we considered whether the collateral-order doctrine\\napplied to orders disqualifying an entire U.S. Attorney’s office from\\nrepresenting the government. 353 F.3d at 873. The defendant contended\\nthat the element of separation wasn’t satisfied because the issue of\\ndisqualification was entangled in the merits of his claims. Id. at 876. We\\nrejected this approach, reasoning that the Supreme Court “‘has consistently\\neschewed a case-by-case approach to deciding whether an order is\\nsufficiently collateral.’” Id. (quoting Cunningham v. Hamilton Cty., Ohio,\\n527 U.S. 198, 206 (1999)). We ultimately decided the issue of separation\\n“on the whole of such [disqualification] orders” without determining\\nwhether the particular issues in that case had been separate from the\\nmerits. Id.\\n 11\\n\\n472 U.S. 424, 431 (1985); Coopers & Lybrand v. Livesay, 437 U.S. 463,\\n\\n468–69 (1978).\\n\\n 4. Utah’s Focus on its Own Arguments (Rather than the Class\\n of Orders)\\n\\n Utah also points to its arguments involving good cause, insisting that\\n\\nthey do not relate to the merits. And the dissent relies on Utah’s arguments\\n\\ninvolving timeliness, dilatoriness, and procedural default. The focus of\\n\\nUtah and the dissent on Utah’s particular appeal points is misguided, as it\\n\\ndisregards\\n\\n the overlap between Utah’s appellate arguments and the merits\\n and\\n\\n the need to consider separation categorically based on the class\\n of orders rather than the particular issues invoked by the\\n appellant.\\n\\n a. Utah’s Arguments on Good Cause\\n\\n Utah tries to justify application of the collateral-order doctrine based\\n\\non the district court’s alleged misidentification and misapplication of the\\n\\ntest for good cause. We reject this effort.\\n\\n i. Misidentifying the Test for Good Cause\\n\\n Utah identifies the definition of good cause as an “important” issue.\\n\\nTo determine an issue’s importance under the collateral-order doctrine, we\\n\\nconsider\\n\\n\\n\\n\\n 12\\n\\n whether the issue is “important in a jurisprudential sense” 6 and\\n\\n whether the interests that “‘would potentially go unprotected\\n without immediate appellate review are significant relative to\\n efficiency interests sought to be advanced by adherence to the\\n final judgment rule.’” 7\\n\\n The definition of good cause might be considered jurisprudentially\\n\\nimportant now because we lack a precedent squarely defining the test for\\n\\ngood cause under Rhines. Of course, if we were to undertake interlocutory\\n\\nreview and define the test, that definition would settle the issue, rendering\\n\\nit jurisprudentially unimportant in the future. See 15A Charles Alan\\n\\nWright, Arthur R. Miller & Edward H. Cooper, Federal Practice &\\n\\nProcedure: Jurisdiction & Related Matters § 3911.5, at 438 (2d ed. 1992)\\n\\n(“Implementation of a serious and unsettled question requirement can\\n\\neasily lead to a situation in which a particular question is suitable for\\n\\ncollateral order appeal the first time it is presented, but not thereafter.”).\\n\\n And Utah has not shown an urgency to immediately define the\\n\\nstandard for good cause under Rhines. Indeed, Utah has offered many\\n\\nalternative arguments for reversal, such as expiration of the limitations\\n\\nperiod, procedural default, misapplication of the district court’s own test\\n\\nfor good cause, dilatoriness, and lack of potential merit. Given Utah’s\\n\\n\\n6\\n Marc Dev’t, Inc. v. FDIC, 992 F.2d 1503, 1505 (10th Cir.), vacated\\non other grounds, 12 F.3d 948 (10th Cir. 1993).\\n7\\n Pierce v. Blaine, 467 F.3d 362, 370–71 (3d Cir. 2006) (quoting In re\\nFord Motor Co., 110 F.3d 954, 959 (3d Cir. 1997)).\\n 13\\n\\nalternative arguments, we may not even need to decide the test for good\\n\\ncause if we were to reverse the grant of a Rhines stay.\\n\\n The dissent nonetheless insists that the test for good cause is\\n\\nimportant because a court in “literally every grant of a Rhines stay, not just\\n\\nthis particular grant of a Rhines stay, must decide what the appropriate\\n\\nstandard for determining ‘good cause’ is.” Dissent at 14. We see the issue\\n\\ndifferently. If the collateral-order doctrine applied, only two possibilities\\n\\nexist:\\n\\n 1. We decide now what the test is for good cause.\\n\\n 2. We do not decide the test now, ruling on other grounds.\\n\\n Let’s consider the first possibility (that we decide the test for good\\n\\ncause in this appeal). Once we define the test, future panels and district\\n\\ncourts will be bound by stare decisis to apply that test in all future cases.\\n\\nUnited States v. Meyers, 200 F.3d 715, 720 (10th Cir. 2000). We thus\\n\\ncouldn’t continue to view the definition of good cause as jurisprudentially\\n\\nsignificant once we define the test for good cause.\\n\\n The second possibility is that we avoid defining the test for good\\n\\ncause. This possibility is real because we could reverse a Rhines stay based\\n\\non any of the three prongs. For example, we might reverse the grant of a\\n\\nRhines stay based on dilatoriness or a lack of potential merit rather than\\n\\n\\n\\n\\n 14\\n\\naddress the issue of good cause. 8 But if we don’t decide the test for good\\n\\ncause, how could we apply the collateral-order doctrine based on the\\n\\nimportance of deciding that test? If we were to do so, we could put\\n\\nourselves in the odd position of recognizing appellate jurisdiction to\\n\\ndecide the test for good cause without actually deciding what the test is.\\n\\n Given these two possibilities, application of the collateral-order\\n\\ndoctrine based on the test for good cause would paradoxically allow every\\n\\nrespondent to appeal every grant of a Rhines stay based on an issue that we\\n\\nhave already decided or, if not, might not even need to decide. This\\n\\nparadox highlights the need to consider the importance of the issues\\n\\ncategorically based on the class of orders involved rather than the\\n\\nparticular arguments raised in a particular case. 9\\n\\n\\n8\\n Utah and the dissent criticize Mr. Kell for being dilatory, arguing\\nthat Mr. Kell waited until 2017 to seek a stay on his unexhausted claims.\\nBecause we lack jurisdiction, we have no occasion to address whether Mr.\\nKell was dilatory. We note, however, that Mr. Kell requested a stay in a\\nreply brief filed in 2014. See Kell v. Benzon, No. 2: 07-CV-359, dkt. no.\\n115 at 50 (D. Utah Jan. 24, 2014) (Pet’r’s Reply Br.) (“Mr. Kell asks this\\nCourt to stay these proceedings and hold them in abeyance to allow him to\\nreturn to state court to exhaust those claims.”). But as Utah and the dissent\\npoint out, he didn’t move for a stay on this issue until 2017.\\n9\\n The dissent calls this possibility an “irrelevant rabbit hole,”\\nreasoning that “the question is whether the district court’s order resolves\\nan issue that is completely separate from the merits.” Dissent at 14 n.4. As\\nthe dissent elsewhere acknowledges, however, the question must not only\\nbe completely separate from the merits but also “important.” Dissent at 9–\\n10. Here we are considering the element of importance. Because the\\npresence of an important issue is necessary under the collateral-order\\n\\n 15\\n\\n ii. Misapplying the Test for Good Cause\\n\\n On the merits of the stay, Utah argues that the district court\\n\\nmisapplied the test for good cause. Utah’s argument shows that application\\n\\nof the good cause test not only overlaps with the merits but would often\\n\\nrequire consideration of them. For example, petitioners could sometimes\\n\\nraise the same theory for good cause and the merits of a habeas claim. An\\n\\nexample is a Brady claim. See Brady v. Maryland, 373 U.S. 83 (1963).\\n\\nCourts have considered withholding of information as “good cause.” See\\n\\nDoe v. Jones, 762 F.3d 1174, 1182 (10th Cir. 2014). So when a petitioner\\n\\nasserts a Brady claim, the petitioner might rely on the withholding of\\n\\nevidence for both good cause and the merits of the habeas claim. See, e.g.,\\n\\nWogenstahl v. Mitchell, 668 F.3d 307, 322 (6th Cir. 2012) (concluding that\\n\\na habeas petitioner “had good cause for failing to raise the Brady issue\\n\\nprior to 2003, because the new information about [a prosecution witness’s\\n\\nprior arrest and adjudication of delinquency] was not disclosed until\\n\\nthen”).\\n\\n An overlap also exists between the inquiry on good cause and the\\n\\nmerits of other habeas claims. For example, the inquiry on good cause may\\n\\noverlap with the merits when a petitioner alleges ineffective assistance of\\n\\ntrial counsel. Suppose that a petitioner alleges good cause based on post-\\n\\n\\ndoctrine, our inquiry into the importance of the good-cause test is not an\\n“irrelevant rabbit hole.”\\n 16\\n\\nconviction counsel’s failure to assert ineffective assistance on the part of\\n\\ntrial counsel. This allegation could suffice to avoid a procedural default.\\n\\nMartinez v. Ryan, 566 U.S. 1, 9 (2012). And Utah argues that the tests for\\n\\ngood cause and procedural default are the same. Given this argument, we\\n\\nmight find “good cause” based on post-conviction counsel’s\\n\\nineffectiveness for failure to assert trial counsel’s ineffectiveness. And\\n\\nonce the case ends in district court, we could again face the issue of trial\\n\\ncounsel’s ineffectiveness as part of our review on the merits.\\n\\n The Supreme Court addressed this kind of overlap in Van\\n\\nCauwenberghe v. Biard, 486 U.S. 517 (1988), and Coopers & Lybrand v.\\n\\nLivesay, 437 U.S. 463 (1978). In Van Cauwenberghe, the Court held that\\n\\nthe denial of a motion to dismiss under the doctrine of forum non\\n\\nconveniens was not separate from the merits because the doctrine involves\\n\\nfactors (like the location of the witnesses and evidence) that are enmeshed\\n\\nwith the merits. 486 U.S. at 528–29. And in Coopers & Lybrand, the Court\\n\\nheld that consideration of class certification involved issues intertwined\\n\\nwith the merits because class certification involves merits-related matters\\n\\nlike the typicality of the claims, the adequacy of a representative, and the\\n\\npresence of common questions of law or fact. 437 U.S. at 469 & n.12.\\n\\nThus, the Court held that the collateral-order doctrine does not cover\\n\\ndenials of class certification. Id. at 469. Neither case involved actual\\n\\n\\n\\n 17\\n\\nconsideration of the merits; but in both cases, the issues overlapped with\\n\\nthe merits.\\n\\n Like issues involving forum non conveniens and class certification,\\n\\nthe issue of good cause will often overlap with a court’s preliminary\\n\\nassessment of the merits, preventing application of the collateral-order\\n\\ndoctrine. See Cunningham v. Hamilton Cty., Ohio, 527 U.S. 198, 205\\n\\n(1999) (holding that sanctions orders under Fed. R. Civ. P. 37(a) do not\\n\\nfall under the collateral-order doctrine because they “often will be\\n\\ninextricably intertwined with the merits of the action,” “[m]uch like the\\n\\norders at issue in Van Cauwenberghe and Coopers & Lybrand”).\\n\\n Here, for example, Utah challenges the finding of good cause,\\n\\narguing that Mr. Kell could have asserted the claim at trial and in a direct\\n\\nappeal. To address this argument, we would need to ask whether Mr. Kell’s\\n\\nattorneys should have asserted the claim at trial or in the direct appeal.\\n\\nThis inquiry would presumably overlap with Mr. Kell’s habeas claims of\\n\\nineffective assistance of counsel. Thus, resolution of Utah’s arguments on\\n\\ngood cause could entangle us in the substance of Mr. Kell’s underlying\\n\\nhabeas claims. In these circumstances, consideration of good cause under\\n\\nRhines is not categorically separate from the merits. 10\\n\\n\\n10\\n The dissent questions our application of the requirement of complete\\nseparation, stating that we are avoiding the “obvious” reality that the\\ndefinition of the standard for good cause is “a purely legal issue that has\\n\\n 18\\n\\n b. Timeliness, Dilatoriness, and Procedural Default\\n\\n In this appeal, Utah also argues that (1) Mr. Kell was dilatory and\\n\\n(2) his unexhausted claim is untimely and procedurally defaulted. Utah\\n\\ndoes not suggest that these arguments would support collateral-order\\n\\njurisdiction. But the dissent does, stating that timeliness, dilatoriness, and\\n\\nprocedural default are separate from the merits.\\n\\n For the sake of argument, let’s assume that the dissent is right and\\n\\nignore the fact that Utah (the appellant invoking appellate jurisdiction)\\n\\ndidn’t present these arguments as grounds to invoke the collateral-order\\n\\ndoctrine. See pp. 35–36, below (citing cases for the unavailability of sua\\n\\nsponte arguments to support jurisdiction). As Utah argues, however, the\\n\\nseparate issue must also be considered important in order to trigger this\\n\\n\\nno overlap with the merits of the case.” Dissent at 14 (emphasis in\\noriginal). The dissent bases its disagreement on footnote ten in Mitchell v.\\nForsyth, 472 U.S. 511 (1984). Dissent at 14. But this footnote explains that\\nan issue is not considered “completely separate” from the merits when its\\neffect “may depend . . . on the success of the parties in litigating the other\\nlegal and factual issues that form their underlying dispute.” Mitchell, 472\\nU.S. at 529–30 n.10 (emphasis added).\\n\\n The Supreme Court illustrated this point with a disqualification\\norder. Id. The disqualification order failed this requirement of “complete\\nseparation” because it was “not a legal issue that [could] be decided with\\nreference only to undisputed facts and in isolation from the remaining\\nissues of the case.” Id.\\n\\n Under Mitchell’s footnote ten, misapplication of Rhines’s\\nrequirement of good cause could not satisfy the “complete separation”\\nrequirement unless the issue were categorically separate from the merits of\\nany of the habeas claims.\\n 19\\n\\ndoctrine. See p. 5, above. Neither Utah nor the dissent offers any argument\\n\\nabout the importance of Utah’s arguments on timeliness, dilatoriness, or\\n\\nprocedural default. These arguments involve garden-variety application of\\n\\nlegal principles settled long ago. See U.S. Fidelity & Guaranty Co. v. Arch\\n\\nIns. Co., 578 F.3d 45, 59 (1st Cir. 2009) (concluding that an issue\\n\\ninvolving insufficiency of an affidavit was not “important enough . . . to\\n\\njustify the application of the collateral order doctrine”); United States v.\\n\\nBillmyer, 57 F.3d 31, 35 (1st Cir. 1995) (“Ordinarily, a discovery order\\n\\nwill meet the legal-importance test only if it presents a claim of clear-cut\\n\\nlegal error and not merely a challenge to the district judge’s factual\\n\\ndeterminations or the application of settled legal rule to the particular\\n\\nfacts.”). Thus, Utah’s arguments on timeliness, dilatoriness, and procedural\\n\\ndefault would not constitute important issues, as required to trigger the\\n\\ncollateral-order doctrine.\\n\\n c. The Categorical Approach\\n\\n Perhaps in some appeals of Rhines stays, the specific argument being\\n\\nadvanced might not involve the potential merit of an unexhausted claim.\\n\\nBut the Supreme Court has “consistently eschewed a case-by-case approach\\n\\nto deciding whether an order is sufficiently collateral.” Cunningham v.\\n\\n\\n\\n\\n 20\\n\\nHamilton Cty., Ohio, 527 U.S. 198, 206 (1999); see also p. 11 & n.5\\n\\n(discussing United States v. Bolden, 353 F.3d 870, 876 (10th Cir. 2003)).\\n\\n The wisdom of the Supreme Court’s approach is self-evident. For\\n\\nexample, let’s assume that Utah’s appellate arguments are important and\\n\\ncompletely separate from the merits. If we were to base the collateral-order\\n\\ndoctrine solely on the happenstance of what Utah argues in a given case,\\n\\nwe would be allowing or disallowing interlocutory appeals of all Rhines\\n\\nstays based on what a single party has chosen to argue in a single case.\\n\\nTo avoid this anomaly, the Supreme Court has required us to consider the\\n\\nunderlying class of orders rather than the peculiarities of the arguments\\n\\npresented by this particular appellant. See p. 11, above. So here we\\n\\nconsider the entire category of orders. See id.\\n\\n The dissent apparently agrees, stating that we must “look[] to the\\n\\nissues the class of orders (Rhines stays) generally raise.” Dissent at 12.\\n\\nAnd the dissent acknowledges that we are not to focus on “case-specific\\n\\nissues,” such as the issues presented in this particular order granting a\\n\\nRhines stay. Id.\\n\\n With this acknowledgment, the dissent contends that the appellant\\n\\nmust present “at least one issue” that is “completely separate from the\\n\\nmerits.” Id. at 10 (emphasis in original). But the Supreme Court has\\n\\nconsistently rejected this approach, holding that even if some appeals of\\n\\nRhines stays might involve appellate issues separable from the merits, the\\n\\n 21\\n\\ncollateral-order doctrine cannot apply absent complete separation for the\\n\\nentire class of orders. Richardson-Merrell, Inc. v. Koller, 472 U.S. 424,\\n\\n439 (1985); 11 see also Cunningham v. Hamilton Cty., Ohio, 527 U.S. 198,\\n\\n206 (1999) (“Perhaps not every discovery sanction will be inextricably\\n\\nintertwined with the merits, but we have consistently eschewed a case-by-\\n\\ncase approach to deciding whether an order is collateral.”). So when we\\n\\nassess whether the class of orders entails complete separation from the\\n\\nmerits, we consider the issues in all grants of stays under Rhines. The\\n\\npresence of a single issue separate from the merits in a particular appeal\\n\\nwould not trigger the collateral-order doctrine. See Cunningham, 527 U.S.\\n\\nat 205–06 (holding that sanctions orders under Fed. R. Civ. P. 37(a) are\\n\\ncategorically considered intertwined with the merits even though sanctions\\n\\norders are sometimes separate from the merits); Koller, 472 U.S. at 439–40\\n\\n\\n\\n11\\n The Koller Court explained:\\n\\n This Court . . . has expressly rejected efforts to reduce the\\n finality requirement of [28 U.S.C.] § 1291 to a case-by-case\\n determination of whether a particular ruling should be subject to\\n appeal. Even if some orders disqualifying counsel are separable\\n from the merits of the litigation, many are not. Orders\\n disqualifying attorneys on the ground that they should testify at\\n trial, for example, are inextricable from the merits because they\\n involve an assessment of the likely course of the trial and the\\n effect of the attorney’s testimony on the judgment. Appellate\\n review of orders disqualifying counsel for misconduct may be\\n entwined with the merits of the litigation as well.\\n\\n472 U.S. at 439 (citations omitted).\\n 22\\n\\n(holding that orders disqualifying counsel in civil cases are categorically\\n\\nconsidered intertwined with the merits because many are even though some\\n\\naren’t); see also In re Continental Investment Corp., 637 F.2d 1, 6 (1st Cir.\\n\\n1980) (holding “that denials of disqualification motions as a class raise\\n\\nsignificant legal questions too rarely to bring them within the Cohen\\n\\nexception”).\\n\\n The categorical approach is apparent in the Supreme Court’s\\n\\nhandling of qualified immunity. There the Court has held that legal issues\\n\\ninvolving a clearly established violation are completely separate from the\\n\\nmerits. Mitchell v. Forsyth, 472 U.S. 511, 528 (1985). But the Supreme\\n\\nCourt made that determination by considering the issues arising in the\\n\\nentire class of orders rather than in the particular case being reviewed. See\\n\\nid. at 524–30.\\n\\n The Supreme Court later went further, expressly disavowing a case-\\n\\nby-case approach in Johnson vs. Jones, 515 U.S. 304 (1995). There the\\n\\nCourt refused to extend the collateral-order doctrine to cover denials of\\n\\nqualified immunity based on insufficiency of the evidence. Johnson, 515\\n\\nU.S. at 314–15. The Court explained that under the categorical approach,\\n\\nappellate judges could not consider the particular facts to determine the\\n\\napplicability of the collateral-order doctrine. Id. at 315. Instead, judges\\n\\nwere to consider the kinds of issues likely to arise in appeals involving this\\n\\nclass of orders. Id. at 315–17. For example, the Supreme Court\\n\\n 23\\n\\nacknowledged that the facts in Johnson itself were straightforward, but\\n\\nstressed that many cases involving constitutional torts would entail factual\\n\\ndisputes ill-suited for review under the collateral-order doctrine. Id. at\\n\\n316.\\n\\n Beyond qualified immunity, circuit courts have followed the Supreme\\n\\nCourt’s lead by deciding the element of complete separation based on the\\n\\nclass of orders involved rather than approaching this element based on the\\n\\nparticular issues raised by a particular appellant. See Henry v. Lake\\n\\nCharles Am. Press, L.L.C., 566 F.3d 164, 173 (5th Cir. 2009) (“Consistent\\n\\nwith Supreme Court precedent and the general purposes of the final\\n\\njudgment rule, we determine whether an order is appealable as a general or\\n\\ncategorical matter.”); see also In re Carco Electronics, 536 F.3d 211, 213\\n\\n(3d Cir. 2008) (“[T]he Supreme Court’s statement in Cunningham that we\\n\\nshould not apply the collateral order doctrine on a ‘case-by-case’ basis\\n\\nindicates that we should not attempt to carve out individualized, case-\\n\\nspecific exceptions to the general rule that discovery orders are not\\n\\nimmediately appealable.”); Abelesz v. OTP Bank, 692 F.3d 638, 649 (7th\\n\\nCir. 2012) (“The Supreme Court has applied the collateral order rule\\n\\ncategorically, treating different sorts of defenses or issues as either\\n\\ncovered or not covered.”).\\n\\n * * *\\n\\n\\n\\n 24\\n\\n Viewed as a category, interlocutory appeals of Rhines stays would\\n\\ngenerally enmesh us in the merits. Thus, the collateral-order doctrine’s\\n\\nsecond element is not met when the district court grants a Rhines stay.\\n\\n B. The grant of a Rhines stay can be reviewed in the appeal\\n from a final judgment.\\n\\n Utah fails to satisfy not only the collateral-order doctrine’s second\\n\\nelement but also the third element.\\n\\n Under this element, appellate jurisdiction exists only if the issue is\\n\\nimportant and could not otherwise be effectively reviewed after the entry\\n\\nof final judgment. Mitchell v. Forsyth, 472 U.S. 511, 525 (1985). But we\\n\\ndo not just consider unreviewability; we also consider the importance of\\n\\nthe interest lost by deferring review until after the final judgment. See\\n\\nDigital Equip. Corp. v. Desktop Direct, Inc., 511 U.S. 863, 878–79 (1994).\\n\\nThis inquiry entails “a judgment about the value of the interests that would\\n\\nbe lost through rigorous application of the final judgment requirement.” Id.\\n\\nOn this element, Utah hasn’t satisfied its burden.\\n\\n Utah argues that the grant of a Rhines stay is unreviewable after a\\n\\nfinal judgment because (1) the loss of time can never be remedied and (2)\\n\\nthe grant of a stay becomes moot upon entry of a final judgment. We reject\\n\\nboth arguments.\\n\\n As Utah points out, the delay itself is unreviewable because a court\\n\\ncan’t restore Utah’s lost time. But we do not ordinarily regard the loss of\\n\\n\\n 25\\n\\ntime as sufficiently important to trigger the collateral-order doctrine. See\\n\\nUnited States v. Section 17 Tp. 23 North, Range 22 East of IBM, Delaware\\n\\nCty., Okla., 40 F.3d 320, 322 (10th Cir. 1994) (holding that an interest in\\n\\ndefending a forfeiture action now, as opposed to later, “is not the type of\\n\\n‘important’ right which the Supreme Court contemplated as requiring\\n\\nimmediate review in [Digital Equipment Corp. v. Desktop Direct, Inc., 511\\n\\nU.S. 863 (1994)]”). After all, no pretrial decision can ever restore a party’s\\n\\nlost time, and we routinely disallow interlocutory appeals for most pretrial\\n\\ndecisions. See Mesa Oil, Inc. v. United States, 467 F.3d 1252, 1255 (10th\\n\\nCir. 2006) (“The costs of unnecessary litigation caused by what eventually\\n\\nturns out to be an error by the district court is insufficient to warrant an\\n\\ninterlocutory appeal.”); see also In re Kozeny, 236 F.3d 615, 619–20 (10th\\n\\nCir. 2000) (two-judge motions panel) 12 (“If the stay merely delays the\\n\\nfederal litigation, courts have generally held the stay orders not to be\\n\\nappealable.”); accord Kershaw v. Shalala, 9 F.3d 11, 14 (5th Cir. 1993)\\n\\n(“Absent a Moses Cone situation, stay orders . . . are usually not\\n\\n\\n\\n\\n12\\n Because Kozeny was issued by a two-judge motions panel, we would\\nordinarily discount the opinion’s precedential value. Crystal Clear\\nComm’ns, Inc. v. Sw. Bell Tel. Co., 415 F.3d 1171, 1176 n.3 (10th Cir.\\n2005). Here, however, we are not relying on Kozeny for its precedential\\nvalue. We are instead relying only on the opinion’s observation about our\\ngeneral practice in regarding stay orders as unappealable.\\n\\n\\n 26\\n\\nreviewable as collateral orders.”); 13 see also Hon. Edith H. Jones, Appeals\\n\\nof Arbitration Orders—Coming Out of the Serbonian Bog, 31 S. Tex. L.\\n\\nRev. 361, 372 (1990) (“Absent exceptional circumstances, it is unlikely\\n\\nthat an order granting a motion to stay proceedings should be appealable as\\n\\na collateral order.”).\\n\\n Time is a precious commodity in habeas proceedings, particularly\\n\\nwhen the petitioner faces a death sentence (as Mr. Kell does). And until\\n\\nnow, the case has lingered in state and federal courts for roughly a quarter\\n\\nof a century. But we cannot single out particular cases to decide the extent\\n\\nof the interest lost by deferring review. Instead, we must consider the\\n\\npublic interest based on the class of orders (Rhines stays). See Mohawk\\n\\nIndus., Inc. v. Carpenter, 558 U.S. 100, 107 (2009); 14 In re Motor Fuel\\n\\n\\n13\\n In Kershaw, the Fifth Circuit observed that in Moses Cone, the\\nSupreme Court had regarded a stay as final when its purpose and effect\\nwere to surrender jurisdiction of a federal suit to a state court. Kershaw, 9\\nF.3d at 14 (quoting Moses H. Cone Memorial Hosp. v. Mercury Const.\\nCorp., 460 U.S. 1, 11 n.11 (1983)). This case does not involve surrender of\\njurisdiction over a federal suit. Instead, the district court required Mr. Kell\\nto exhaust state-court remedies so that the federal court could consider the\\nhabeas claim.\\n14\\n In Mohawk Industries, the Supreme Court explained:\\n\\n [T]he decisive consideration is whether delaying review until the\\n entry of final judgment “would imperil a substantial public\\n interest” or “some particular value of higher order.”\\n\\n In making this determination, we do not engage in an\\n “individualized jurisdictional inquiry.” Rather, our focus is on\\n\\n 27\\n\\nTemperature Sales Practices Litig., 641 F.3d 470, 482 (10th Cir. 2011)\\n\\n(“When analyzing the third Cohen requirement, we do not consider whether\\n\\nthe circumstances of the particular case before us warrant our immediate\\n\\nreview; rather, we examine whether the entire category of rulings to which\\n\\nthe claim belongs can be adequately vindicated on review of a final\\n\\njudgment or by other means.”). This approach requires us to decide\\n\\nwhether the value that we place on immediate review would override\\n\\nCongress’s policy against piecemeal review.\\n\\n To answer, we must consider the many important interests that exist,\\n\\noften in tension with one another. For example, the state has important\\n\\ninterests in comity and enforcement of its own criminal judgments, which\\n\\nCongress recognized in the Antiterrorism and Effective Death Penalty Act\\n\\nof 1996. See Williams v. Taylor, 529 U.S. 420, 436 (2000) (stating that the\\n\\nAct was designed to advance “comity, finality, and federalism”). But\\n\\nhabeas review inherently creates tension with comity, as federal courts\\n\\nreview decisions by a state’s highest court. See Duckworth v. Eagan, 492\\n\\n\\n\\n “the entire category to which the claim belongs.” As long as the\\n class of claims, taken as a whole, can be adequately vindicated\\n by other means, “the chance that the litigation at hand might be\\n speeded, or a ‘particular injustic[e]’ averted,” does not provide\\n a basis for jurisdiction under § 1291.\\n\\nMohawk Indus., 558 U.S. at 107 (citations omitted).\\n\\n\\n 28\\n\\nU.S. 195, 211 (1989) (discussing the tension of federal-state relations\\n\\nbecause of habeas review, where “lower federal courts often sit in ‘review’\\n\\nof the judgments of the highest courts of a state judicial system”).\\n\\n To ease this tension, Congress has required habeas petitioners to\\n\\nexhaust state-court remedies. 28 U.S.C. § 2254(b)(1)(A); see also Rose v.\\n\\nLundy, 455 U.S. 509, 518 (1982) (“The exhaustion doctrine is principally\\n\\ndesigned to protect the state courts’ role in the enforcement of federal law\\n\\nand prevent disruption of state judicial proceedings.”). Exhaustion,\\n\\nhowever, can slow the state’s ability to enforce criminal judgments,\\n\\nespecially those involving capital sentences. See Ira P. Robbins, Toward a\\n\\nMore Just & Effective System of Review in State Death Penalty Cases, 40\\n\\nAm. U. L. Rev. 1, 131 (1990) (“[R]equiring exhaustion [in habeas review\\n\\nof death-penalty cases] usually necessitates further delay, even if the\\n\\nunexhausted claim is an obviously frivolous one.”). This risk is\\n\\nparticularly significant in habeas proceedings, where swift action is\\n\\nessential. See Rhodes v. Hannigan, 12 F.3d 989, 992 (10th Cir. 1993)\\n\\n(“Habeas corpus ‘is a speedy remedy, entitled by statute to special,\\n\\npreferential consideration to insure expeditious hearing and\\n\\ndetermination.’” (quoting Van Buskirk v. Wilkinson, 216 F.2d 735, 737–38\\n\\n(9th Cir. 1954))); Johnson v. Rogers, 917 F.2d 1283, 1284 (10th Cir. 1990)\\n\\n(“[W]rits of habeas corpus are intended to afford a ‘swift and imperative\\n\\n\\n\\n 29\\n\\nremedy in all cases of illegal restraint or confinement.’” (quoting Fay v.\\n\\nNoia, 372 U.S. 391, 400 (1963))).\\n\\n The Supreme Court sought to balance these competing interests in\\n\\nRhines by giving discretion to federal district courts to stay habeas\\n\\nproceedings while a petitioner exhausts state-court remedies. Rhines v.\\n\\nWeber, 544 U.S. 269, 276–78 (2005). But discretion can be abused. The\\n\\nquestion presented here is when an appellate court should review the\\n\\ndistrict court’s exercise of discretion. 15 Given the conflicting interests, we\\n\\nmust consider whether interlocutory review of Rhines stays would speed\\n\\nreview or slow it through piecemeal review.\\n\\n For this inquiry, we start with Congress’s policy against piecemeal\\n\\nreview. In general, Congress has tried to avoid piecemeal review by\\n\\nconfining appellate review to final orders. See Abney v. United States, 431\\n\\nU.S. 651, 656 (1977) (“[T]here has been a firm congressional policy\\n\\nagainst interlocutory or ‘piecemeal’ appeals and courts have consistently\\n\\n\\n15\\n Other circuit courts have generally declined to apply the collateral-\\norder doctrine to orders subject to the abuse-of-discretion standard. See\\nGrace v. Vannoy, 826 F.3d 813, 820 (5th Cir. 2016) (“Typically, orders\\nreviewable for abuse of discretion are not appealable under the collateral-\\norder doctrine.”); In re Kemble, 776 F.2d 802, 806 (9th Cir. 1985)\\n(“Ordinarily we should not use the collateral order doctrine to examine the\\nexercise of discretion by trial judges.”). One leading treatise attributed this\\n“wise” practice to a reluctance to undertake interlocutory review when\\nappellate courts have allowed district courts to exercise discretion. 15A\\nCharles Alan Wright, Arthur R. Miller & Edward H. Cooper, Federal\\nPractice & Procedure: Jurisdiction & Related Matters, § 3911.5, at 433–\\n35 (2d ed. 1992).\\n 30\\n\\ngiven effect to that policy.”). And Congress has expressed its judgment\\n\\n“that the district judge has the primary responsibility to police the\\n\\nprejudgment tactics of litigants,” reasoning “that the district judge can\\n\\nbetter exercise that responsibility if the appellate courts do not repeatedly\\n\\nintervene to second-guess prejudgment rulings.” Richardson-Merrell, Inc.\\n\\nv. Koller, 472 U.S. 424, 436 (1985) (emphasis in original).\\n\\n The Supreme Court has respected this congressional policy choice\\n\\nand restricted prejudgment review because it inefficiently fosters\\n\\npiecemeal appeals. See Mohawk Indus., Inc. v. Carpenter, 558 U.S. 100,\\n\\n106 (2009) (“Permitting piecemeal, prejudgment appeals, we have\\n\\nrecognized, undermines ‘efficient judicial administration’ and encroaches\\n\\nupon the prerogatives of district court judges, who play a ‘special role’ in\\n\\nmanaging ongoing litigation.”); Richardson-Merrell, Inc. v. Koller, 472\\n\\nU.S. 424. 430 (1985) (stating that the final judgment rule prevents delays\\n\\nfrom frequent appellate interruptions in the litigation); Abney, 431 U.S. at\\n\\n657 (stating that 28 U.S.C. § 1291, which restricts appellate review to final\\n\\ndecisions, is designed to prevent delays and disruptions through\\n\\nintermediate appeals).\\n\\n Given Congress’s preference against interlocutory review, we must\\n\\nconsider whether Rhines stays involve aberrant circumstances justifying\\n\\nour intrusion into Congress’s effort to avoid piecemeal review. We think\\n\\n\\n\\n 31\\n\\nnot. In Rhines itself, the Supreme Court balanced the compelling interests\\n\\nby devising a procedure to accommodate\\n\\n the state’s interest in comity,\\n\\n the congressional requirement of exhaustion of state-court\\n remedies,\\n\\n the congressional determination that piecemeal review\\n generally slows the litigation,\\n\\n the universal recognition that habeas cases should proceed\\n expeditiously, and\\n\\n the congressional objective in the Antiterrorism and Effective\\n Death Penalty Act to streamline habeas proceedings.\\n\\nRhines v. Weber, 544 U.S. 269, 276–78 (2005); see Howard v. Norris, 616\\n\\nF.3d 799, 802–03 (8th Cir. 2010) (stating that “Rhines effectively balances\\n\\nthe state’s interest in avoiding delay in a habeas proceeding, with the\\n\\npetitioner’s (and the state’s) interest in having habeas claims addressed\\n\\nfirst in state court”); see also Grace v. Vannoy, 826 F3d 813, 819 (5th Cir.\\n\\n2016) (stating that in Rhines, “the Supreme Court implicitly de-emphasized\\n\\nthe importance of the state’s interests in finality and speedy resolution of\\n\\nmixed federal petitions”).\\n\\n If we were to intervene after a district court granted a stay, would\\n\\nour intervention quicken or slow the litigation? Here, the district court\\n\\nstayed the proceedings for only a single claim and stated that the\\n\\nproceedings would continue on all of the other habeas claims. If we were\\n\\n\\n 32\\n\\nto interject ourselves now, we could inadvertently trigger simultaneous\\n\\nlitigation of the same case in three courts:\\n\\n 1. the state district court or the state appellate court,\\n\\n 2. the federal district court, and\\n\\n 3. our court.\\n\\nWe question the efficiency of duplicative litigation in three courts. See\\n\\nSwanson v. DeSantis, 606 F.3d 829, 833 (6th Cir. 2010) (“Claim-by-claim\\n\\nlitigation in the district and appellate courts ‘undermines [Congress’] goal\\n\\nof streamlining federal habeas proceedings . . . .” (emphasis and alteration\\n\\nin original) (quoting Rhines v. Weber, 544 U.S. 269, 277 (2005))).\\n\\n But double or triple litigation tracks could create not only\\n\\ninefficiency but also more delay. For example, if we were to affirm the\\n\\ngrant of a stay, we could be needlessly slowing the habeas litigation for the\\n\\ntime that we take to decide the appeal. And, of course, district courts\\n\\naren’t limited to the number of Rhines stays in a single case. Here, for\\n\\nexample, the district court has issued two Rhines stays. If those stays had\\n\\ntriggered the collateral-order doctrine, we could have slowed the litigation\\n\\ntwice already with the possibility of a third delay when the case ends in\\n\\ndistrict court. In these circumstances, we decline to single out Rhines stays\\n\\n\\n\\n\\n 33\\n\\nas a class of orders that would be resolved more quickly by authorizing\\n\\npiecemeal appeals. 16\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2271,"cells":{"id":{"kind":"number","value":4616237,"string":"4,616,237"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellee, v. Anthony Carl SPENCE, Defendant-Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Anthony Carl Spence"},"decision_date":{"kind":"string","value":"2019-05-02"},"docket_number":{"kind":"string","value":"17-14976"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Carnes, Martin, Anderson\", \"parties\": \"\", \"opinions\": [{\"author\": \"ANDERSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-14976 Date Filed: 05/02/2019 Page: 1 of 13\\n\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-14976\\n ________________________\\n\\n D.C. Docket No. 6:17-cr-00062-CEM-DCI-1\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\n versus\\nANTHONY CARL SPENCE,\\n\\n Defendant-Appellant.\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Florida\\n ________________________\\n\\n (May 2, 2019)\\n\\nBefore ED CARNES, Chief Judge, MARTIN and ANDERSON, Circuit Judges.\\n\\nANDERSON, Circuit Judge:\\n\\n This case presents an issue of first impression in this Circuit involving the\\n\\nconsideration by a sentencing judge of extraterritorial relevant conduct to enhance\\n\\nan offense level under the Sentencing Guidelines. Shortly after Anthony Carl\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 2 of 13\\n\\n\\nSpence arrived at the airport from Jamaica, agents discovered two videos of child\\n\\npornography on his phone. Spence told the agents that he received the cell phone\\n\\nabout a month before in Jamaica. He said that he received the first video from a\\n\\ngirlfriend in New York and that he showed it to school children in Jamaica to\\n\\nencourage them to report if they had been molested. Spence also told the agents\\n\\nthat he sent out the videos to women with children while he was in Jamaica.\\n\\n Spence was charged with knowing transportation of child pornography in\\n\\nviolation of 18 U.S.C. § 2252A(a)(1) and (b)(1) and knowing possession of child\\n\\npornography in violation of 18 U.S.C. § 2252A(a)(5)(B) and (b)(2). He proceeded\\n\\nto trial where he was found guilty of both counts. In calculating Spence’s\\n\\nGuidelines range, the probation officer grouped Counts One and Two, pursuant to\\n\\nU.S.S.G. § 3D1.2(d), and determined that Count One provided the highest offense\\n\\nlevel. Spence’s base offense level was 22 pursuant to § 2G2.2(a)(2). The\\n\\nprobation officer increased Spence’s offense level for a number of factors\\n\\nincluding by two levels, under § 2G2.2(b)(3)(F), because Spence distributed the\\n\\nmaterial. Spence’s total adjusted offense level was 37 and because he had no\\n\\ncriminal history, he had a criminal history category of I. Based upon a total\\n\\noffense level of 37 and a criminal history category of I, Spence’s Guideline\\n\\nimprisonment range was 210 months to 262 months. The probation officer\\n\\nrecommended a sentence of 151 months.\\n\\n\\n 2\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 3 of 13\\n\\n\\n In the addendum to the Presentence Investigation Report (“PSI”), the\\n\\nprobation officer noted, among other objections that do not bear on this appeal, that\\n\\nSpence objected to receiving a two-level enhancement for distribution. Spence\\n\\nstated that any distribution occurred while he was in Jamaica. The probation\\n\\nofficer responded that Spence had admitted to the distribution and noted that there\\n\\nwas no territorial limitation found in § 2G2.2.\\n\\n The court adopted the Guidelines calculation found in the PSI and sentenced\\n\\nSpence to a total sentence of 68 months. The district court stated that it made a\\n\\ndownward variance because of Spence’s lack of sophistication and because there\\n\\nwas no evidence that he was at a high risk of re-offending or of actually molesting\\n\\nchildren. The court stated that “the guidelines are entirely inappropriate based on\\n\\nthis particular set of circumstances.”\\n\\n Spence raises a purely legal question regarding the Sentencing Guidelines,\\n\\nwhich we review de novo. United States v. Vail-Bailon, 868 F.3d 1293, 1296\\n\\n(11th Cir. 2017) (en banc).\\n\\n On appeal, Spence’s sole argument is that his distribution of the videos\\n\\nwhile he was in Jamaica should not have affected his Guidelines calculation. He\\n\\nargues that by including his out-of-country conduct in the calculation of his offense\\n\\nlevel, the district court violated the principle that legislation of Congress should\\n\\napply only within the United States unless a contrary intent appears. In other\\n\\n\\n 3\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 4 of 13\\n\\n\\nwords, Spence is relying upon the canon of statutory construction known as the\\n\\npresumption against the application of congressional statutes to conduct occurring\\n\\nin the territory of a foreign sovereign. See Kiobel v. Royal Dutch Petroleum Co.,\\n\\n569 U.S. 108, 115-16, 133 S. Ct. 1659, 1664 (2013). Spence argues that the\\n\\ndoctrine should be extended so as to apply not only to preclude construction of\\n\\nstatutes as intending to criminalize such extraterritorial conduct but also to apply to\\n\\npreclude sentencing courts from considering such extraterritorial conduct as part of\\n\\nthe “relevant conduct” considered pursuant to U.S.S.G. § 1B1.3 in determining the\\n\\nappropriate sentence for conduct (occurring entirely within the United States) of\\n\\nwhich a defendant was convicted. Thus, Spence argues that his distribution of\\n\\nvideos occurring solely in Jamaica should not have been considered by the district\\n\\ncourt. Spence does not challenge the fact of his distribution or that such\\n\\ndistribution would constitute relevant conduct properly considered by the\\n\\nsentencing court (except for his extraterritorial argument).\\n\\n Thus, the narrow issue in this appeal is whether the presumption against the\\n\\nextraterritorial application of congressional legislation should be extended to apply\\n\\nalso to preclude a sentencing judge from considering extraterritorial conduct which\\n\\nwould otherwise be properly considered as relevant conduct. This is an issue of\\n\\nfirst impression in the Eleventh Circuit.\\n\\n\\n\\n\\n 4\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 5 of 13\\n\\n\\n The Seventh Circuit, the Tenth Circuit, and the Eighth Circuit have\\n\\naddressed this precise issue and have concluded that the presumption against the\\n\\nextraterritorial application of congressional legislation should not be extended to\\n\\npreclude a sentencing judge from considering such extraterritorial conduct.\\n\\n United States v. Dawn, 129 F.3d 878 (7th Cir. 1997), is the leading case.\\n\\nThere, the defendant was charged with receiving and possessing child\\n\\npornography. Dawn had taken the film to be developed in his hometown in\\n\\nWisconsin. The film processor noticed what he suspected to be child pornography\\n\\nand notified the police. The developed film was delivered to Dawn at his home by\\n\\nan undercover officer, and after Dawn received and signed for it, he was arrested.\\n\\nDawn had produced the film while in Honduras. At sentencing, the district court\\n\\napplied the Guidelines provision for production because of the cross-reference\\n\\nfrom the possession and receiving counts.1 The Seventh Circuit noted that the term\\n\\n“offense” is defined broadly to include not only the offense of conviction but also\\n\\nall conduct deemed relevant by U.S.S.G. § 1B1.3 (that is, all relevant conduct). No\\n\\none disputed that the production in Dawn was relevant conduct. Id. at 881. The\\n\\nDawn court relied on the fact that none of the relevant Guidelines provisions turn\\n\\non whether the conduct occurred in the United States. Id. at 882. Instead, the\\n\\n\\n\\n1\\n The court applied several provisions, including U.S.S.G. § 2G2.4. That section has since\\nbeen deleted and consolidated with § 2G2.2, effective November 1, 2004. Thus the analysis in\\nDawn is still pertinent to our discussion.\\n 5\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 6 of 13\\n\\n\\ncourt said, the focus of these provisions is on “the factual and logical relationship\\n\\nbetween the offense of conviction and the defendant’s other acts,” and none of the\\n\\nrelevant Guidelines provisions bars the use of extraterritorial conduct. Id. The\\n\\ndefendant had argued the general principle known as the presumption against the\\n\\nextraterritorial application of congressional legislation—i.e., that statutes apply\\n\\nonly domestically unless Congress explicitly made clear that they applied\\n\\nextraterritorially—barred use of the conduct. The Seventh Circuit rejected this\\n\\nargument because Dawn was not convicted or sentenced for producing the films;\\n\\ninstead, the production activity was relevant conduct, which is properly considered\\n\\nby the sentencing court in determining the appropriate sentence for the offense—\\n\\nreceiving and possessing child pornography—of which Dawn was convicted. The\\n\\ncourt held that Dawn’s production of the films was appropriately considered\\n\\nbecause “it sheds light on the gravity of his conduct as a receiver and possessor of\\n\\nthe films.” Id. at 884-85. “[C]ommon sense . . . [indicates] that a receiver or\\n\\npossessor who has manufactured the pornography in his possession is both more\\n\\nculpable and more dangerous than one who has received or possessed the\\n\\npornography and no more.” Id. at 884.\\n\\n The Eighth and Tenth Circuits have followed Dawn. In United States v.\\n\\nWilkinson, 169 F.3d 1236 (10th Cir. 1999), the Tenth Circuit applied the same\\n\\ncross-reference to the Guidelines provision for production of child pornography\\n\\n\\n 6\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 7 of 13\\n\\n\\nbecause Wilkinson had produced in Thailand the child pornography of which he\\n\\nwas convicted of possessing. Following Dawn’s rationale, the Tenth Circuit noted\\n\\nthat the production was relevant conduct under U.S.S.G. § 1B1.3, that none of the\\n\\nGuidelines provisions at issue carve out an exception for conduct occurring outside\\n\\nthe United States, and that the higher production offense level was imposed—not\\n\\nbecause he was being punished for the production—but rather because of the\\n\\ncommon sense notion that a possessor of child pornography who had manufactured\\n\\nthe pornography was more culpable than one who had merely possessed same. Id.\\n\\nat 1238. Further, the Tenth Circuit pointed to 18 U.S.C. § 3661, which provides:\\n\\n No limitation shall be placed on the information concerning the\\n background, character, and conduct of a person convicted of an\\n offense which a court of the United States may receive and consider\\n for the purpose of imposing an appropriate sentence.\\n\\nId. at 1238-39. Addressing facts similar to those in Dawn and Wilkinson, the\\n\\nEighth Circuit held that extraterritorial relevant conduct could be considered by the\\n\\nsentencing judge. United States v. Zayas, 758 F.3d 986 (8th Cir. 2014).2 The\\n\\nZayas court followed Dawn with little elaboration.\\n\\n We agree with the holding and reasoning of the Seventh Circuit decision in\\n\\nDawn and the Tenth Circuit decision in Wilkinson that the presumption against the\\n\\n\\n\\n2\\n We note that the Third Circuit, in the unpublished opinion, United States v. Castro-\\nValenzuela, 304 F.App’x 986 (3d Cir. 2008), also followed the holding and reasoning of the\\nSeventh Circuit Dawn decision.\\n\\n 7\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 8 of 13\\n\\n\\nextraterritorial application of congressional legislation does not apply in the\\n\\nsentencing context of a court’s consideration of relevant conduct that occurred\\n\\noutside the United States. 3\\n\\n First, the conduct underlying the offense for which Spence was convicted\\n\\nand for which he was sentenced occurred in the United States—i.e., his\\n\\ntransportation and possession of child pornography. He was not convicted on the\\n\\nbasis of conduct that occurred outside the United States, nor was he sentenced for\\n\\nsuch conduct. That relevant conduct which occurred outside the United States was\\n\\nconsidered in assessing the gravity of Spence’s domestic crime does not mean that\\n\\nhe was sentenced for that extraterritorial conduct. The Tenth Circuit in Wilkinson\\n\\nso held, and we agree:\\n\\n Consideration of information about the defendant’s character and\\n conduct at sentencing does not result in “punishment” for any offense\\n other than the one for which the defendant was convicted. Rather, the\\n defendant is punished only for the fact that the present offense was\\n carried out in a manner that warrants increased punishment.\\n\\nWilkinson, 169 F.3d at 1238 (emphasis in original) (alteration and quotation marks\\n\\nomitted) (quoting United States v. Watts, 519 U.S. 148, 155, 117 S. Ct. 633 (1997)\\n\\n(per curiam)).\\n\\n\\n\\n\\n3\\n As noted above, the Eighth Circuit in Zayas has also so held.\\n\\n 8\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 9 of 13\\n\\n\\n Second, there is no language in the relevant Guidelines provisions which\\n\\nlimits consideration of relevant conduct to conduct occurring in the United States. 4\\n\\n Third, confirming the proposition that there is no such geographical limit on\\n\\nrelevant conduct that a sentencing court may properly consider, 18 U.S.C. § 3661\\n\\nexpressly provides:\\n\\n No limitation shall be placed on the information concerning the\\n background, character, and conduct of a person convicted of an\\n offense which a court of the United States may receive and consider\\n for the purpose of imposing an appropriate sentence.\\n\\n18 U.S.C. § 3661. Indeed, even conduct for which a defendant has been acquitted\\n\\nmay be considered for sentencing. United States v. Watts, 519 U.S. at 152, 117 S.\\n\\nCt. at 635.\\n\\n We acknowledge that the Second Circuit decisions in United States v.\\n\\nAzeem, 946 F.2d 13 (2d Cir. 1991), and United States v. Chunza-Plazas, 45 F.3d\\n\\n\\n\\n4\\n Those provisions read, in pertinent part:\\n\\n (a) Base Offense Level:\\n (1) 18, if the defendant is convicted of 18 U.S.C. § 1466A(b), § 2252(a)(4), §\\n 2252A(a)(5), or § 2252A(a)(7).\\n (2) 22, otherwise.\\n (b) Specific Offense Characteristics\\n ...\\n (3) (Apply the greatest):\\n ...\\n (F) If the defendant knowingly engaged in distribution, other than distribution\\n described in subdivisions (A) through (E), increase by 2 levels. . .\\n\\nU.S.S.G. § 2G2.2. Further, the provisions governing the admission of relevant conduct,\\nfound in U.S.S.G. § 1B1.3, contain nothing that would limit the conduct to that which\\noccurred in the United States.\\n 9\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 10 of 13\\n\\n\\n51 (2d Cir. 1995), could be viewed as being in some tension with our holding and\\n\\nthose of the Seventh, Eighth, and Tenth Circuits. In Azeem, the defendant\\n\\nconspired with a DEA informant in Pakistan to import heroin both to New York\\n\\nand also to Cairo. Azeem was charged only with the former. The Second Circuit\\n\\nheld that the drugs in the Cairo transaction should not have been included in the\\n\\ntotal amount of drugs for purposes of determining the base offense level. Although\\n\\nthe court acknowledged that the Cairo transaction was part of the same course of\\n\\nconduct or common scheme—i.e., the court acknowledged that the Cairo\\n\\ntransaction was relevant conduct—and also acknowledged that the relevant\\n\\nconduct provision did not address the issue of foreign crimes and activities, 946\\n\\nF.2d at 17, it held that the district court erred in considering the extraterritorial\\n\\nconduct. The Second Circuit did not mention the doctrine known as the\\n\\npresumption against the extraterritorial application of congressional legislation.\\n\\nRather, it relied on the fact that the Cairo transaction was not a crime against the\\n\\nUnited States, and on the fact that a different Guidelines provision provides that\\n\\nforeign convictions are not counted as part of a defendant’s criminal history. See\\n\\nU.S.S.G. § 4A1.2(h) (“Sentences resulting from foreign convictions are not\\n\\ncounted, but may be considered under § 4A1.3 (Departures Based on Inadequacy\\n\\nof Criminal History Category (Policy Statement)).”). The Second Circuit inferred\\n\\nfrom this that Congress (really the Sentencing Commission) had “chosen to assign\\n\\n\\n 10\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 11 of 13\\n\\n\\nto foreign crimes a rather limited role.” Azeem, 946 F.2d at 17. The court noted\\n\\nwhat seemed to it as good reasons for excluding foreign crimes—e.g., not\\n\\ninvolving courts in “distinguishing between activities that violate both domestic\\n\\nand foreign law and those which violate only domestic law or only foreign law.”\\n\\nId. The Chunza-Plazas decision followed the Azeem rationale with little\\n\\nadditional elaboration, as did the Ninth Circuit in United States v. Chao Fan Xu,\\n\\n706 F.3d 965, 992-93 (9th Cir. 2013).\\n\\n We note that the Second Circuit cases do not address the doctrine of the\\n\\npresumption against the extraterritorial application of congressional legislation,\\n\\nalthough we acknowledge that they do address related concerns. To the extent that\\n\\nthe Second Circuit cases are inconsistent with our holding and that of the Seventh\\n\\nCircuit in Dawn, the Tenth Circuit in Wilkinson, and the Eighth Circuit in Zayas,\\n\\nwe respectfully decline to follow the Second Circuit. We believe that reliance\\n\\nupon U.S.S.G. § 4A1.2(h) in Spence’s case would be misplaced. That Guidelines\\n\\nprovision provides only that foreign convictions and sentences should not be\\n\\ncounted in a defendant’s criminal history. A court required to consider a foreign\\n\\nconviction as part of a defendant’s criminal history might well find itself inquiring\\n\\nabout whether the conduct underlying the foreign crime would violate domestic\\n\\nUnited States law, or whether criminalization of that underlying conduct would\\n\\nviolate the public policy of the United States, or whether counting such foreign\\n\\n\\n 11\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 12 of 13\\n\\n\\nconviction would otherwise be inappropriate. Such are the concerns proffered by\\n\\nthe Azeem panel. However, such concerns are simply not relevant in the\\n\\ncircumstances of Spence’s case. We are not concerned with a foreign conviction;\\n\\nrather, we are concerned only with conduct—i.e., the distribution of particular\\n\\nvideos which have already been determined to be child pornography and have\\n\\nalready been determined to be in violation of United States law. We need not\\n\\nexamine any foreign law to know that it is appropriate to consider such distribution\\n\\nas indicating that Spence’s crime of possessing the videos in the United States is\\n\\nmore culpable than mere possession alone would have been. United States\\n\\nSentencing Guideline § 2G2.2(b)(3)(F) tells us this. For this reason, we do not\\n\\nconsider the rationale of Azeem to be persuasive in the circumstances of the instant\\n\\ncase. Indeed, we note that U.S.S.G. § 4A1.2(h), although it provides that foreign\\n\\nconvictions not be counted as part of a defendant’s criminal history, expressly\\n\\nprovides that foreign convictions and sentences can be considered under the\\n\\nupward departure provision. That, we submit, is inconsistent with Spence’s\\n\\nposition that the presumption against extraterritorial application of congressional\\n\\nlegislation should be extended so as to preclude a sentencing judge from\\n\\nconsidering extraterritorial conduct in the sentencing process.\\n\\n For the foregoing reasons, we reject Spence’s sole argument on appeal. We\\n\\ndecline to extend the doctrine of the presumption against extraterritorial\\n\\n\\n 12\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 13 of 13\\n\\n\\napplication of congressional legislation to also preclude a sentencing judge from\\n\\nconsidering extraterritorial conduct which otherwise is properly considered as\\n\\nrelevant conduct.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 13\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4393490/\", \"author_raw\": \"ANDERSON, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"CARNES"},"judge2":{"kind":"string","value":"MARTIN"},"judge3":{"kind":"string","value":"ANDERSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4616237/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Anthony Carl SPENCE, Defendant-Appellant.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-02\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-14976 Date Filed: 05/02/2019 Page: 1 of 13\n\n\n\n [PUBLISH]\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-14976\n ________________________\n\n D.C. Docket No. 6:17-cr-00062-CEM-DCI-1\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff-Appellee,\n\n versus\nANTHONY CARL SPENCE,\n\n Defendant-Appellant.\n ________________________\n\n Appeal from the United States District Court\n for the Middle District of Florida\n ________________________\n\n (May 2, 2019)\n\nBefore ED CARNES, Chief Judge, MARTIN and ANDERSON, Circuit Judges.\n\nANDERSON, Circuit Judge:\n\n This case presents an issue of first impression in this Circuit involving the\n\nconsideration by a sentencing judge of extraterritorial relevant conduct to enhance\n\nan offense level under the Sentencing Guidelines. Shortly after Anthony Carl\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 2 of 13\n\n\nSpence arrived at the airport from Jamaica, agents discovered two videos of child\n\npornography on his phone. Spence told the agents that he received the cell phone\n\nabout a month before in Jamaica. He said that he received the first video from a\n\ngirlfriend in New York and that he showed it to school children in Jamaica to\n\nencourage them to report if they had been molested. Spence also told the agents\n\nthat he sent out the videos to women with children while he was in Jamaica.\n\n Spence was charged with knowing transportation of child pornography in\n\nviolation of 18 U.S.C. § 2252A(a)(1) and (b)(1) and knowing possession of child\n\npornography in violation of 18 U.S.C. § 2252A(a)(5)(B) and (b)(2). He proceeded\n\nto trial where he was found guilty of both counts. In calculating Spence’s\n\nGuidelines range, the probation officer grouped Counts One and Two, pursuant to\n\nU.S.S.G. § 3D1.2(d), and determined that Count One provided the highest offense\n\nlevel. Spence’s base offense level was 22 pursuant to § 2G2.2(a)(2). The\n\nprobation officer increased Spence’s offense level for a number of factors\n\nincluding by two levels, under § 2G2.2(b)(3)(F), because Spence distributed the\n\nmaterial. Spence’s total adjusted offense level was 37 and because he had no\n\ncriminal history, he had a criminal history category of I. Based upon a total\n\noffense level of 37 and a criminal history category of I, Spence’s Guideline\n\nimprisonment range was 210 months to 262 months. The probation officer\n\nrecommended a sentence of 151 months.\n\n\n 2\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 3 of 13\n\n\n In the addendum to the Presentence Investigation Report (“PSI”), the\n\nprobation officer noted, among other objections that do not bear on this appeal, that\n\nSpence objected to receiving a two-level enhancement for distribution. Spence\n\nstated that any distribution occurred while he was in Jamaica. The probation\n\nofficer responded that Spence had admitted to the distribution and noted that there\n\nwas no territorial limitation found in § 2G2.2.\n\n The court adopted the Guidelines calculation found in the PSI and sentenced\n\nSpence to a total sentence of 68 months. The district court stated that it made a\n\ndownward variance because of Spence’s lack of sophistication and because there\n\nwas no evidence that he was at a high risk of re-offending or of actually molesting\n\nchildren. The court stated that “the guidelines are entirely inappropriate based on\n\nthis particular set of circumstances.”\n\n Spence raises a purely legal question regarding the Sentencing Guidelines,\n\nwhich we review de novo. United States v. Vail-Bailon, 868 F.3d 1293, 1296\n\n(11th Cir. 2017) (en banc).\n\n On appeal, Spence’s sole argument is that his distribution of the videos\n\nwhile he was in Jamaica should not have affected his Guidelines calculation. He\n\nargues that by including his out-of-country conduct in the calculation of his offense\n\nlevel, the district court violated the principle that legislation of Congress should\n\napply only within the United States unless a contrary intent appears. In other\n\n\n 3\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 4 of 13\n\n\nwords, Spence is relying upon the canon of statutory construction known as the\n\npresumption against the application of congressional statutes to conduct occurring\n\nin the territory of a foreign sovereign. See Kiobel v. Royal Dutch Petroleum Co.,\n\n569 U.S. 108, 115-16, 133 S. Ct. 1659, 1664 (2013). Spence argues that the\n\ndoctrine should be extended so as to apply not only to preclude construction of\n\nstatutes as intending to criminalize such extraterritorial conduct but also to apply to\n\npreclude sentencing courts from considering such extraterritorial conduct as part of\n\nthe “relevant conduct” considered pursuant to U.S.S.G. § 1B1.3 in determining the\n\nappropriate sentence for conduct (occurring entirely within the United States) of\n\nwhich a defendant was convicted. Thus, Spence argues that his distribution of\n\nvideos occurring solely in Jamaica should not have been considered by the district\n\ncourt. Spence does not challenge the fact of his distribution or that such\n\ndistribution would constitute relevant conduct properly considered by the\n\nsentencing court (except for his extraterritorial argument).\n\n Thus, the narrow issue in this appeal is whether the presumption against the\n\nextraterritorial application of congressional legislation should be extended to apply\n\nalso to preclude a sentencing judge from considering extraterritorial conduct which\n\nwould otherwise be properly considered as relevant conduct. This is an issue of\n\nfirst impression in the Eleventh Circuit.\n\n\n\n\n 4\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 5 of 13\n\n\n The Seventh Circuit, the Tenth Circuit, and the Eighth Circuit have\n\naddressed this precise issue and have concluded that the presumption against the\n\nextraterritorial application of congressional legislation should not be extended to\n\npreclude a sentencing judge from considering such extraterritorial conduct.\n\n United States v. Dawn, 129 F.3d 878 (7th Cir. 1997), is the leading case.\n\nThere, the defendant was charged with receiving and possessing child\n\npornography. Dawn had taken the film to be developed in his hometown in\n\nWisconsin. The film processor noticed what he suspected to be child pornography\n\nand notified the police. The developed film was delivered to Dawn at his home by\n\nan undercover officer, and after Dawn received and signed for it, he was arrested.\n\nDawn had produced the film while in Honduras. At sentencing, the district court\n\napplied the Guidelines provision for production because of the cross-reference\n\nfrom the possession and receiving counts.1 The Seventh Circuit noted that the term\n\n“offense” is defined broadly to include not only the offense of conviction but also\n\nall conduct deemed relevant by U.S.S.G. § 1B1.3 (that is, all relevant conduct). No\n\none disputed that the production in Dawn was relevant conduct. Id. at 881. The\n\nDawn court relied on the fact that none of the relevant Guidelines provisions turn\n\non whether the conduct occurred in the United States. Id. at 882. Instead, the\n\n\n\n1\n The court applied several provisions, including U.S.S.G. § 2G2.4. That section has since\nbeen deleted and consolidated with § 2G2.2, effective November 1, 2004. Thus the analysis in\nDawn is still pertinent to our discussion.\n 5\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 6 of 13\n\n\ncourt said, the focus of these provisions is on “the factual and logical relationship\n\nbetween the offense of conviction and the defendant’s other acts,” and none of the\n\nrelevant Guidelines provisions bars the use of extraterritorial conduct. Id. The\n\ndefendant had argued the general principle known as the presumption against the\n\nextraterritorial application of congressional legislation—i.e., that statutes apply\n\nonly domestically unless Congress explicitly made clear that they applied\n\nextraterritorially—barred use of the conduct. The Seventh Circuit rejected this\n\nargument because Dawn was not convicted or sentenced for producing the films;\n\ninstead, the production activity was relevant conduct, which is properly considered\n\nby the sentencing court in determining the appropriate sentence for the offense—\n\nreceiving and possessing child pornography—of which Dawn was convicted. The\n\ncourt held that Dawn’s production of the films was appropriately considered\n\nbecause “it sheds light on the gravity of his conduct as a receiver and possessor of\n\nthe films.” Id. at 884-85. “[C]ommon sense . . . [indicates] that a receiver or\n\npossessor who has manufactured the pornography in his possession is both more\n\nculpable and more dangerous than one who has received or possessed the\n\npornography and no more.” Id. at 884.\n\n The Eighth and Tenth Circuits have followed Dawn. In United States v.\n\nWilkinson, 169 F.3d 1236 (10th Cir. 1999), the Tenth Circuit applied the same\n\ncross-reference to the Guidelines provision for production of child pornography\n\n\n 6\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 7 of 13\n\n\nbecause Wilkinson had produced in Thailand the child pornography of which he\n\nwas convicted of possessing. Following Dawn’s rationale, the Tenth Circuit noted\n\nthat the production was relevant conduct under U.S.S.G. § 1B1.3, that none of the\n\nGuidelines provisions at issue carve out an exception for conduct occurring outside\n\nthe United States, and that the higher production offense level was imposed—not\n\nbecause he was being punished for the production—but rather because of the\n\ncommon sense notion that a possessor of child pornography who had manufactured\n\nthe pornography was more culpable than one who had merely possessed same. Id.\n\nat 1238. Further, the Tenth Circuit pointed to 18 U.S.C. § 3661, which provides:\n\n No limitation shall be placed on the information concerning the\n background, character, and conduct of a person convicted of an\n offense which a court of the United States may receive and consider\n for the purpose of imposing an appropriate sentence.\n\nId. at 1238-39. Addressing facts similar to those in Dawn and Wilkinson, the\n\nEighth Circuit held that extraterritorial relevant conduct could be considered by the\n\nsentencing judge. United States v. Zayas, 758 F.3d 986 (8th Cir. 2014).2 The\n\nZayas court followed Dawn with little elaboration.\n\n We agree with the holding and reasoning of the Seventh Circuit decision in\n\nDawn and the Tenth Circuit decision in Wilkinson that the presumption against the\n\n\n\n2\n We note that the Third Circuit, in the unpublished opinion, United States v. Castro-\nValenzuela, 304 F.App’x 986 (3d Cir. 2008), also followed the holding and reasoning of the\nSeventh Circuit Dawn decision.\n\n 7\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 8 of 13\n\n\nextraterritorial application of congressional legislation does not apply in the\n\nsentencing context of a court’s consideration of relevant conduct that occurred\n\noutside the United States. 3\n\n First, the conduct underlying the offense for which Spence was convicted\n\nand for which he was sentenced occurred in the United States—i.e., his\n\ntransportation and possession of child pornography. He was not convicted on the\n\nbasis of conduct that occurred outside the United States, nor was he sentenced for\n\nsuch conduct. That relevant conduct which occurred outside the United States was\n\nconsidered in assessing the gravity of Spence’s domestic crime does not mean that\n\nhe was sentenced for that extraterritorial conduct. The Tenth Circuit in Wilkinson\n\nso held, and we agree:\n\n Consideration of information about the defendant’s character and\n conduct at sentencing does not result in “punishment” for any offense\n other than the one for which the defendant was convicted. Rather, the\n defendant is punished only for the fact that the present offense was\n carried out in a manner that warrants increased punishment.\n\nWilkinson, 169 F.3d at 1238 (emphasis in original) (alteration and quotation marks\n\nomitted) (quoting United States v. Watts, 519 U.S. 148, 155, 117 S. Ct. 633 (1997)\n\n(per curiam)).\n\n\n\n\n3\n As noted above, the Eighth Circuit in Zayas has also so held.\n\n 8\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 9 of 13\n\n\n Second, there is no language in the relevant Guidelines provisions which\n\nlimits consideration of relevant conduct to conduct occurring in the United States. 4\n\n Third, confirming the proposition that there is no such geographical limit on\n\nrelevant conduct that a sentencing court may properly consider, 18 U.S.C. § 3661\n\nexpressly provides:\n\n No limitation shall be placed on the information concerning the\n background, character, and conduct of a person convicted of an\n offense which a court of the United States may receive and consider\n for the purpose of imposing an appropriate sentence.\n\n18 U.S.C. § 3661. Indeed, even conduct for which a defendant has been acquitted\n\nmay be considered for sentencing. United States v. Watts, 519 U.S. at 152, 117 S.\n\nCt. at 635.\n\n We acknowledge that the Second Circuit decisions in United States v.\n\nAzeem, 946 F.2d 13 (2d Cir. 1991), and United States v. Chunza-Plazas, 45 F.3d\n\n\n\n4\n Those provisions read, in pertinent part:\n\n (a) Base Offense Level:\n (1) 18, if the defendant is convicted of 18 U.S.C. § 1466A(b), § 2252(a)(4), §\n 2252A(a)(5), or § 2252A(a)(7).\n (2) 22, otherwise.\n (b) Specific Offense Characteristics\n ...\n (3) (Apply the greatest):\n ...\n (F) If the defendant knowingly engaged in distribution, other than distribution\n described in subdivisions (A) through (E), increase by 2 levels. . .\n\nU.S.S.G. § 2G2.2. Further, the provisions governing the admission of relevant conduct,\nfound in U.S.S.G. § 1B1.3, contain nothing that would limit the conduct to that which\noccurred in the United States.\n 9\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 10 of 13\n\n\n51 (2d Cir. 1995), could be viewed as being in some tension with our holding and\n\nthose of the Seventh, Eighth, and Tenth Circuits. In Azeem, the defendant\n\nconspired with a DEA informant in Pakistan to import heroin both to New York\n\nand also to Cairo. Azeem was charged only with the former. The Second Circuit\n\nheld that the drugs in the Cairo transaction should not have been included in the\n\ntotal amount of drugs for purposes of determining the base offense level. Although\n\nthe court acknowledged that the Cairo transaction was part of the same course of\n\nconduct or common scheme—i.e., the court acknowledged that the Cairo\n\ntransaction was relevant conduct—and also acknowledged that the relevant\n\nconduct provision did not address the issue of foreign crimes and activities, 946\n\nF.2d at 17, it held that the district court erred in considering the extraterritorial\n\nconduct. The Second Circuit did not mention the doctrine known as the\n\npresumption against the extraterritorial application of congressional legislation.\n\nRather, it relied on the fact that the Cairo transaction was not a crime against the\n\nUnited States, and on the fact that a different Guidelines provision provides that\n\nforeign convictions are not counted as part of a defendant’s criminal history. See\n\nU.S.S.G. § 4A1.2(h) (“Sentences resulting from foreign convictions are not\n\ncounted, but may be considered under § 4A1.3 (Departures Based on Inadequacy\n\nof Criminal History Category (Policy Statement)).”). The Second Circuit inferred\n\nfrom this that Congress (really the Sentencing Commission) had “chosen to assign\n\n\n 10\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 11 of 13\n\n\nto foreign crimes a rather limited role.” Azeem, 946 F.2d at 17. The court noted\n\nwhat seemed to it as good reasons for excluding foreign crimes—e.g., not\n\ninvolving courts in “distinguishing between activities that violate both domestic\n\nand foreign law and those which violate only domestic law or only foreign law.”\n\nId. The Chunza-Plazas decision followed the Azeem rationale with little\n\nadditional elaboration, as did the Ninth Circuit in United States v. Chao Fan Xu,\n\n706 F.3d 965, 992-93 (9th Cir. 2013).\n\n We note that the Second Circuit cases do not address the doctrine of the\n\npresumption against the extraterritorial application of congressional legislation,\n\nalthough we acknowledge that they do address related concerns. To the extent that\n\nthe Second Circuit cases are inconsistent with our holding and that of the Seventh\n\nCircuit in Dawn, the Tenth Circuit in Wilkinson, and the Eighth Circuit in Zayas,\n\nwe respectfully decline to follow the Second Circuit. We believe that reliance\n\nupon U.S.S.G. § 4A1.2(h) in Spence’s case would be misplaced. That Guidelines\n\nprovision provides only that foreign convictions and sentences should not be\n\ncounted in a defendant’s criminal history. A court required to consider a foreign\n\nconviction as part of a defendant’s criminal history might well find itself inquiring\n\nabout whether the conduct underlying the foreign crime would violate domestic\n\nUnited States law, or whether criminalization of that underlying conduct would\n\nviolate the public policy of the United States, or whether counting such foreign\n\n\n 11\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 12 of 13\n\n\nconviction would otherwise be inappropriate. Such are the concerns proffered by\n\nthe Azeem panel. However, such concerns are simply not relevant in the\n\ncircumstances of Spence’s case. We are not concerned with a foreign conviction;\n\nrather, we are concerned only with conduct—i.e., the distribution of particular\n\nvideos which have already been determined to be child pornography and have\n\nalready been determined to be in violation of United States law. We need not\n\nexamine any foreign law to know that it is appropriate to consider such distribution\n\nas indicating that Spence’s crime of possessing the videos in the United States is\n\nmore culpable than mere possession alone would have been. United States\n\nSentencing Guideline § 2G2.2(b)(3)(F) tells us this. For this reason, we do not\n\nconsider the rationale of Azeem to be persuasive in the circumstances of the instant\n\ncase. Indeed, we note that U.S.S.G. § 4A1.2(h), although it provides that foreign\n\nconvictions not be counted as part of a defendant’s criminal history, expressly\n\nprovides that foreign convictions and sentences can be considered under the\n\nupward departure provision. That, we submit, is inconsistent with Spence’s\n\nposition that the presumption against extraterritorial application of congressional\n\nlegislation should be extended so as to preclude a sentencing judge from\n\nconsidering extraterritorial conduct in the sentencing process.\n\n For the foregoing reasons, we reject Spence’s sole argument on appeal. We\n\ndecline to extend the doctrine of the presumption against extraterritorial\n\n\n 12\n\f Case: 17-14976 Date Filed: 05/02/2019 Page: 13 of 13\n\n\napplication of congressional legislation to also preclude a sentencing judge from\n\nconsidering extraterritorial conduct which otherwise is properly considered as\n\nrelevant conduct.\n\n AFFIRMED.\n\n\n\n\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Anthony Carl SPENCE, Defendant-Appellant.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-02\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-14976 Date Filed: 05/02/2019 Page: 1 of 13\\n\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-14976\\n ________________________\\n\\n D.C. Docket No. 6:17-cr-00062-CEM-DCI-1\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\n versus\\nANTHONY CARL SPENCE,\\n\\n Defendant-Appellant.\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Florida\\n ________________________\\n\\n (May 2, 2019)\\n\\nBefore ED CARNES, Chief Judge, MARTIN and ANDERSON, Circuit Judges.\\n\\nANDERSON, Circuit Judge:\\n\\n This case presents an issue of first impression in this Circuit involving the\\n\\nconsideration by a sentencing judge of extraterritorial relevant conduct to enhance\\n\\nan offense level under the Sentencing Guidelines. Shortly after Anthony Carl\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 2 of 13\\n\\n\\nSpence arrived at the airport from Jamaica, agents discovered two videos of child\\n\\npornography on his phone. Spence told the agents that he received the cell phone\\n\\nabout a month before in Jamaica. He said that he received the first video from a\\n\\ngirlfriend in New York and that he showed it to school children in Jamaica to\\n\\nencourage them to report if they had been molested. Spence also told the agents\\n\\nthat he sent out the videos to women with children while he was in Jamaica.\\n\\n Spence was charged with knowing transportation of child pornography in\\n\\nviolation of 18 U.S.C. § 2252A(a)(1) and (b)(1) and knowing possession of child\\n\\npornography in violation of 18 U.S.C. § 2252A(a)(5)(B) and (b)(2). He proceeded\\n\\nto trial where he was found guilty of both counts. In calculating Spence’s\\n\\nGuidelines range, the probation officer grouped Counts One and Two, pursuant to\\n\\nU.S.S.G. § 3D1.2(d), and determined that Count One provided the highest offense\\n\\nlevel. Spence’s base offense level was 22 pursuant to § 2G2.2(a)(2). The\\n\\nprobation officer increased Spence’s offense level for a number of factors\\n\\nincluding by two levels, under § 2G2.2(b)(3)(F), because Spence distributed the\\n\\nmaterial. Spence’s total adjusted offense level was 37 and because he had no\\n\\ncriminal history, he had a criminal history category of I. Based upon a total\\n\\noffense level of 37 and a criminal history category of I, Spence’s Guideline\\n\\nimprisonment range was 210 months to 262 months. The probation officer\\n\\nrecommended a sentence of 151 months.\\n\\n\\n 2\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 3 of 13\\n\\n\\n In the addendum to the Presentence Investigation Report (“PSI”), the\\n\\nprobation officer noted, among other objections that do not bear on this appeal, that\\n\\nSpence objected to receiving a two-level enhancement for distribution. Spence\\n\\nstated that any distribution occurred while he was in Jamaica. The probation\\n\\nofficer responded that Spence had admitted to the distribution and noted that there\\n\\nwas no territorial limitation found in § 2G2.2.\\n\\n The court adopted the Guidelines calculation found in the PSI and sentenced\\n\\nSpence to a total sentence of 68 months. The district court stated that it made a\\n\\ndownward variance because of Spence’s lack of sophistication and because there\\n\\nwas no evidence that he was at a high risk of re-offending or of actually molesting\\n\\nchildren. The court stated that “the guidelines are entirely inappropriate based on\\n\\nthis particular set of circumstances.”\\n\\n Spence raises a purely legal question regarding the Sentencing Guidelines,\\n\\nwhich we review de novo. United States v. Vail-Bailon, 868 F.3d 1293, 1296\\n\\n(11th Cir. 2017) (en banc).\\n\\n On appeal, Spence’s sole argument is that his distribution of the videos\\n\\nwhile he was in Jamaica should not have affected his Guidelines calculation. He\\n\\nargues that by including his out-of-country conduct in the calculation of his offense\\n\\nlevel, the district court violated the principle that legislation of Congress should\\n\\napply only within the United States unless a contrary intent appears. In other\\n\\n\\n 3\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 4 of 13\\n\\n\\nwords, Spence is relying upon the canon of statutory construction known as the\\n\\npresumption against the application of congressional statutes to conduct occurring\\n\\nin the territory of a foreign sovereign. See Kiobel v. Royal Dutch Petroleum Co.,\\n\\n569 U.S. 108, 115-16, 133 S. Ct. 1659, 1664 (2013). Spence argues that the\\n\\ndoctrine should be extended so as to apply not only to preclude construction of\\n\\nstatutes as intending to criminalize such extraterritorial conduct but also to apply to\\n\\npreclude sentencing courts from considering such extraterritorial conduct as part of\\n\\nthe “relevant conduct” considered pursuant to U.S.S.G. § 1B1.3 in determining the\\n\\nappropriate sentence for conduct (occurring entirely within the United States) of\\n\\nwhich a defendant was convicted. Thus, Spence argues that his distribution of\\n\\nvideos occurring solely in Jamaica should not have been considered by the district\\n\\ncourt. Spence does not challenge the fact of his distribution or that such\\n\\ndistribution would constitute relevant conduct properly considered by the\\n\\nsentencing court (except for his extraterritorial argument).\\n\\n Thus, the narrow issue in this appeal is whether the presumption against the\\n\\nextraterritorial application of congressional legislation should be extended to apply\\n\\nalso to preclude a sentencing judge from considering extraterritorial conduct which\\n\\nwould otherwise be properly considered as relevant conduct. This is an issue of\\n\\nfirst impression in the Eleventh Circuit.\\n\\n\\n\\n\\n 4\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 5 of 13\\n\\n\\n The Seventh Circuit, the Tenth Circuit, and the Eighth Circuit have\\n\\naddressed this precise issue and have concluded that the presumption against the\\n\\nextraterritorial application of congressional legislation should not be extended to\\n\\npreclude a sentencing judge from considering such extraterritorial conduct.\\n\\n United States v. Dawn, 129 F.3d 878 (7th Cir. 1997), is the leading case.\\n\\nThere, the defendant was charged with receiving and possessing child\\n\\npornography. Dawn had taken the film to be developed in his hometown in\\n\\nWisconsin. The film processor noticed what he suspected to be child pornography\\n\\nand notified the police. The developed film was delivered to Dawn at his home by\\n\\nan undercover officer, and after Dawn received and signed for it, he was arrested.\\n\\nDawn had produced the film while in Honduras. At sentencing, the district court\\n\\napplied the Guidelines provision for production because of the cross-reference\\n\\nfrom the possession and receiving counts.1 The Seventh Circuit noted that the term\\n\\n“offense” is defined broadly to include not only the offense of conviction but also\\n\\nall conduct deemed relevant by U.S.S.G. § 1B1.3 (that is, all relevant conduct). No\\n\\none disputed that the production in Dawn was relevant conduct. Id. at 881. The\\n\\nDawn court relied on the fact that none of the relevant Guidelines provisions turn\\n\\non whether the conduct occurred in the United States. Id. at 882. Instead, the\\n\\n\\n\\n1\\n The court applied several provisions, including U.S.S.G. § 2G2.4. That section has since\\nbeen deleted and consolidated with § 2G2.2, effective November 1, 2004. Thus the analysis in\\nDawn is still pertinent to our discussion.\\n 5\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 6 of 13\\n\\n\\ncourt said, the focus of these provisions is on “the factual and logical relationship\\n\\nbetween the offense of conviction and the defendant’s other acts,” and none of the\\n\\nrelevant Guidelines provisions bars the use of extraterritorial conduct. Id. The\\n\\ndefendant had argued the general principle known as the presumption against the\\n\\nextraterritorial application of congressional legislation—i.e., that statutes apply\\n\\nonly domestically unless Congress explicitly made clear that they applied\\n\\nextraterritorially—barred use of the conduct. The Seventh Circuit rejected this\\n\\nargument because Dawn was not convicted or sentenced for producing the films;\\n\\ninstead, the production activity was relevant conduct, which is properly considered\\n\\nby the sentencing court in determining the appropriate sentence for the offense—\\n\\nreceiving and possessing child pornography—of which Dawn was convicted. The\\n\\ncourt held that Dawn’s production of the films was appropriately considered\\n\\nbecause “it sheds light on the gravity of his conduct as a receiver and possessor of\\n\\nthe films.” Id. at 884-85. “[C]ommon sense . . . [indicates] that a receiver or\\n\\npossessor who has manufactured the pornography in his possession is both more\\n\\nculpable and more dangerous than one who has received or possessed the\\n\\npornography and no more.” Id. at 884.\\n\\n The Eighth and Tenth Circuits have followed Dawn. In United States v.\\n\\nWilkinson, 169 F.3d 1236 (10th Cir. 1999), the Tenth Circuit applied the same\\n\\ncross-reference to the Guidelines provision for production of child pornography\\n\\n\\n 6\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 7 of 13\\n\\n\\nbecause Wilkinson had produced in Thailand the child pornography of which he\\n\\nwas convicted of possessing. Following Dawn’s rationale, the Tenth Circuit noted\\n\\nthat the production was relevant conduct under U.S.S.G. § 1B1.3, that none of the\\n\\nGuidelines provisions at issue carve out an exception for conduct occurring outside\\n\\nthe United States, and that the higher production offense level was imposed—not\\n\\nbecause he was being punished for the production—but rather because of the\\n\\ncommon sense notion that a possessor of child pornography who had manufactured\\n\\nthe pornography was more culpable than one who had merely possessed same. Id.\\n\\nat 1238. Further, the Tenth Circuit pointed to 18 U.S.C. § 3661, which provides:\\n\\n No limitation shall be placed on the information concerning the\\n background, character, and conduct of a person convicted of an\\n offense which a court of the United States may receive and consider\\n for the purpose of imposing an appropriate sentence.\\n\\nId. at 1238-39. Addressing facts similar to those in Dawn and Wilkinson, the\\n\\nEighth Circuit held that extraterritorial relevant conduct could be considered by the\\n\\nsentencing judge. United States v. Zayas, 758 F.3d 986 (8th Cir. 2014).2 The\\n\\nZayas court followed Dawn with little elaboration.\\n\\n We agree with the holding and reasoning of the Seventh Circuit decision in\\n\\nDawn and the Tenth Circuit decision in Wilkinson that the presumption against the\\n\\n\\n\\n2\\n We note that the Third Circuit, in the unpublished opinion, United States v. Castro-\\nValenzuela, 304 F.App’x 986 (3d Cir. 2008), also followed the holding and reasoning of the\\nSeventh Circuit Dawn decision.\\n\\n 7\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 8 of 13\\n\\n\\nextraterritorial application of congressional legislation does not apply in the\\n\\nsentencing context of a court’s consideration of relevant conduct that occurred\\n\\noutside the United States. 3\\n\\n First, the conduct underlying the offense for which Spence was convicted\\n\\nand for which he was sentenced occurred in the United States—i.e., his\\n\\ntransportation and possession of child pornography. He was not convicted on the\\n\\nbasis of conduct that occurred outside the United States, nor was he sentenced for\\n\\nsuch conduct. That relevant conduct which occurred outside the United States was\\n\\nconsidered in assessing the gravity of Spence’s domestic crime does not mean that\\n\\nhe was sentenced for that extraterritorial conduct. The Tenth Circuit in Wilkinson\\n\\nso held, and we agree:\\n\\n Consideration of information about the defendant’s character and\\n conduct at sentencing does not result in “punishment” for any offense\\n other than the one for which the defendant was convicted. Rather, the\\n defendant is punished only for the fact that the present offense was\\n carried out in a manner that warrants increased punishment.\\n\\nWilkinson, 169 F.3d at 1238 (emphasis in original) (alteration and quotation marks\\n\\nomitted) (quoting United States v. Watts, 519 U.S. 148, 155, 117 S. Ct. 633 (1997)\\n\\n(per curiam)).\\n\\n\\n\\n\\n3\\n As noted above, the Eighth Circuit in Zayas has also so held.\\n\\n 8\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 9 of 13\\n\\n\\n Second, there is no language in the relevant Guidelines provisions which\\n\\nlimits consideration of relevant conduct to conduct occurring in the United States. 4\\n\\n Third, confirming the proposition that there is no such geographical limit on\\n\\nrelevant conduct that a sentencing court may properly consider, 18 U.S.C. § 3661\\n\\nexpressly provides:\\n\\n No limitation shall be placed on the information concerning the\\n background, character, and conduct of a person convicted of an\\n offense which a court of the United States may receive and consider\\n for the purpose of imposing an appropriate sentence.\\n\\n18 U.S.C. § 3661. Indeed, even conduct for which a defendant has been acquitted\\n\\nmay be considered for sentencing. United States v. Watts, 519 U.S. at 152, 117 S.\\n\\nCt. at 635.\\n\\n We acknowledge that the Second Circuit decisions in United States v.\\n\\nAzeem, 946 F.2d 13 (2d Cir. 1991), and United States v. Chunza-Plazas, 45 F.3d\\n\\n\\n\\n4\\n Those provisions read, in pertinent part:\\n\\n (a) Base Offense Level:\\n (1) 18, if the defendant is convicted of 18 U.S.C. § 1466A(b), § 2252(a)(4), §\\n 2252A(a)(5), or § 2252A(a)(7).\\n (2) 22, otherwise.\\n (b) Specific Offense Characteristics\\n ...\\n (3) (Apply the greatest):\\n ...\\n (F) If the defendant knowingly engaged in distribution, other than distribution\\n described in subdivisions (A) through (E), increase by 2 levels. . .\\n\\nU.S.S.G. § 2G2.2. Further, the provisions governing the admission of relevant conduct,\\nfound in U.S.S.G. § 1B1.3, contain nothing that would limit the conduct to that which\\noccurred in the United States.\\n 9\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 10 of 13\\n\\n\\n51 (2d Cir. 1995), could be viewed as being in some tension with our holding and\\n\\nthose of the Seventh, Eighth, and Tenth Circuits. In Azeem, the defendant\\n\\nconspired with a DEA informant in Pakistan to import heroin both to New York\\n\\nand also to Cairo. Azeem was charged only with the former. The Second Circuit\\n\\nheld that the drugs in the Cairo transaction should not have been included in the\\n\\ntotal amount of drugs for purposes of determining the base offense level. Although\\n\\nthe court acknowledged that the Cairo transaction was part of the same course of\\n\\nconduct or common scheme—i.e., the court acknowledged that the Cairo\\n\\ntransaction was relevant conduct—and also acknowledged that the relevant\\n\\nconduct provision did not address the issue of foreign crimes and activities, 946\\n\\nF.2d at 17, it held that the district court erred in considering the extraterritorial\\n\\nconduct. The Second Circuit did not mention the doctrine known as the\\n\\npresumption against the extraterritorial application of congressional legislation.\\n\\nRather, it relied on the fact that the Cairo transaction was not a crime against the\\n\\nUnited States, and on the fact that a different Guidelines provision provides that\\n\\nforeign convictions are not counted as part of a defendant’s criminal history. See\\n\\nU.S.S.G. § 4A1.2(h) (“Sentences resulting from foreign convictions are not\\n\\ncounted, but may be considered under § 4A1.3 (Departures Based on Inadequacy\\n\\nof Criminal History Category (Policy Statement)).”). The Second Circuit inferred\\n\\nfrom this that Congress (really the Sentencing Commission) had “chosen to assign\\n\\n\\n 10\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 11 of 13\\n\\n\\nto foreign crimes a rather limited role.” Azeem, 946 F.2d at 17. The court noted\\n\\nwhat seemed to it as good reasons for excluding foreign crimes—e.g., not\\n\\ninvolving courts in “distinguishing between activities that violate both domestic\\n\\nand foreign law and those which violate only domestic law or only foreign law.”\\n\\nId. The Chunza-Plazas decision followed the Azeem rationale with little\\n\\nadditional elaboration, as did the Ninth Circuit in United States v. Chao Fan Xu,\\n\\n706 F.3d 965, 992-93 (9th Cir. 2013).\\n\\n We note that the Second Circuit cases do not address the doctrine of the\\n\\npresumption against the extraterritorial application of congressional legislation,\\n\\nalthough we acknowledge that they do address related concerns. To the extent that\\n\\nthe Second Circuit cases are inconsistent with our holding and that of the Seventh\\n\\nCircuit in Dawn, the Tenth Circuit in Wilkinson, and the Eighth Circuit in Zayas,\\n\\nwe respectfully decline to follow the Second Circuit. We believe that reliance\\n\\nupon U.S.S.G. § 4A1.2(h) in Spence’s case would be misplaced. That Guidelines\\n\\nprovision provides only that foreign convictions and sentences should not be\\n\\ncounted in a defendant’s criminal history. A court required to consider a foreign\\n\\nconviction as part of a defendant’s criminal history might well find itself inquiring\\n\\nabout whether the conduct underlying the foreign crime would violate domestic\\n\\nUnited States law, or whether criminalization of that underlying conduct would\\n\\nviolate the public policy of the United States, or whether counting such foreign\\n\\n\\n 11\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 12 of 13\\n\\n\\nconviction would otherwise be inappropriate. Such are the concerns proffered by\\n\\nthe Azeem panel. However, such concerns are simply not relevant in the\\n\\ncircumstances of Spence’s case. We are not concerned with a foreign conviction;\\n\\nrather, we are concerned only with conduct—i.e., the distribution of particular\\n\\nvideos which have already been determined to be child pornography and have\\n\\nalready been determined to be in violation of United States law. We need not\\n\\nexamine any foreign law to know that it is appropriate to consider such distribution\\n\\nas indicating that Spence’s crime of possessing the videos in the United States is\\n\\nmore culpable than mere possession alone would have been. United States\\n\\nSentencing Guideline § 2G2.2(b)(3)(F) tells us this. For this reason, we do not\\n\\nconsider the rationale of Azeem to be persuasive in the circumstances of the instant\\n\\ncase. Indeed, we note that U.S.S.G. § 4A1.2(h), although it provides that foreign\\n\\nconvictions not be counted as part of a defendant’s criminal history, expressly\\n\\nprovides that foreign convictions and sentences can be considered under the\\n\\nupward departure provision. That, we submit, is inconsistent with Spence’s\\n\\nposition that the presumption against extraterritorial application of congressional\\n\\nlegislation should be extended so as to preclude a sentencing judge from\\n\\nconsidering extraterritorial conduct in the sentencing process.\\n\\n For the foregoing reasons, we reject Spence’s sole argument on appeal. We\\n\\ndecline to extend the doctrine of the presumption against extraterritorial\\n\\n\\n 12\\n\\f Case: 17-14976 Date Filed: 05/02/2019 Page: 13 of 13\\n\\n\\napplication of congressional legislation to also preclude a sentencing judge from\\n\\nconsidering extraterritorial conduct which otherwise is properly considered as\\n\\nrelevant conduct.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2272,"cells":{"id":{"kind":"number","value":4616452,"string":"4,616,452"},"name":{"kind":"string","value":"CITY OF MIAMI, a Florida Municipal Corporation, Plaintiff-Appellant, v. WELLS FARGO & CO., Wells Fargo Bank, N.A., Defendants-Appellees. City of Miami, a Florida Municipal Corporation, Plaintiff-Appellant, v. Bank of America Corporation, Bank of America, N.A., Countrywide Financial Corporation, Countrywide Home Loans, Countrywide Bank, FSB, Defendants-Appellees."},"name_abbreviation":{"kind":"string","value":"City of Miami v. Wells Fargo & Co."},"decision_date":{"kind":"string","value":"2019-05-03"},"docket_number":{"kind":"string","value":"14-14544; 14-14543"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Marcus, Wilson, Schlesinger\", \"parties\": \"\", \"opinions\": [{\"author\": \"MARCUS, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 14-14544 Date Filed: 05/03/2019 Page: 1 of 76\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 14-14544\\n Non-Argument Calendar\\n ________________________\\n\\n D.C. Docket No. 1:13-cv-24508-WPD\\n\\n\\n\\nCITY OF MIAMI,\\na Florida municipal corporation,\\n\\n Plaintiff - Appellant,\\n\\nversus\\n\\nWELLS FARGO & CO.,\\nWELLS FARGO BANK, N.A.,\\n\\n Defendants - Appellees.\\n\\n\\n ________________________\\n\\n No. 14-14543\\n Non-Argument Calendar\\n ________________________\\n\\n D.C. Docket No. 1:13-cv-24506-WPD\\n\\n\\n\\nCITY OF MIAMI,\\na Florida Municipal Corporation,\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 2 of 76\\n\\n\\n Plaintiff - Appellant,\\n\\nversus\\n\\nBANK OF AMERICA CORPORATION,\\nBANK OF AMERICA, N.A.,\\nCOUNTRYWIDE FINANCIAL CORPORATION,\\nCOUNTRYWIDE HOME LOANS,\\nCOUNTRYWIDE BANK, FSB,\\n\\n Defendants - Appellees.\\n\\n ________________________\\n\\n Appeals from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 3, 2019)\\n\\nBefore MARCUS and WILSON, Circuit Judges, and SCHLESINGER, * District\\nJudge.\\n\\nMARCUS, Circuit Judge:\\n\\n This pair of ambitious fair housing lawsuits brought by the City of Miami\\n\\nagainst major financial institutions returns to our Court after having been appealed\\n\\nto the Supreme Court and resolved there in Bank of American Corp. v. City of\\n\\nMiami, 137 S. Ct. 1296 (2017). Miami alleges that, for years, the defendant\\n\\ninstitutions, major nationwide banks, carried on discriminatory lending practices\\n\\nthat intentionally targeted black and Latino Miami residents for predatory loans.\\n\\n\\n*\\n Honorable Harvey E. Schlesinger, United States District Judge for the Middle District of\\nFlorida, sitting by designation.\\n\\n 2\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 3 of 76\\n\\n\\nThe City says this resulted in disproportionate foreclosures on homeowners of\\n\\nthose races, diminished property values in predominantly minority neighborhoods,\\n\\nsubstantially reduced tax revenue for the City, and increased expenditures by the\\n\\nCity for municipal services. When we first heard these cases, we determined that\\n\\nMiami had standing under the Fair Housing Act, and that it had adequately pled\\n\\nproximate cause. See City of Miami v. Bank of Am. Corp., 800 F.3d 1262 (11th\\n\\nCir. 2015); City of Miami v. Wells Fargo & Co., 801 F.3d 1258 (11th Cir. 2015).\\n\\nThe Supreme Court agreed in part. It resolved the hotly contested standing issue in\\n\\nthe City’s favor, but vacated and remanded with regard to proximate cause. See\\n\\nBank of Am., 137 S. Ct. at 1305–06.\\n\\n The Court held that the standard that this panel had applied -- foreseeability -\\n\\n- was not enough on its own to demonstrate proximate cause. Id. at 1306. Instead,\\n\\nthe Court said that proximate cause under the FHA also required “some direct\\n\\nrelation between the injury asserted and the injurious conduct alleged.” Id. at 1306\\n\\n(quotations omitted). But the Court declined to “draw the precise boundaries of\\n\\nproximate cause under the FHA and to determine on which side of the line the\\n\\nCity’s financial injuries fall.” Id. It remanded the case, preferring to leave this\\n\\nissue open for percolation in the lower courts. See id. Today, we take up the\\n\\nquestion of how the principles of proximate cause identified by the Court’s opinion\\n\\n\\n\\n\\n 3\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 4 of 76\\n\\n\\nfunction when applied to the FHA and to the facts as alleged in the City’s\\n\\ncomplaints.\\n\\n At this preliminary stage in the lawsuit, we conclude that the City has\\n\\nadequately pled proximate cause in relation to some of its economic injuries when\\n\\nthe pleadings are measured against the standard required by the Fair Housing Act.\\n\\nProximate cause asks whether there is a direct, logical, and identifiable connection\\n\\nbetween the injury sustained and its alleged cause. If there is no discontinuity to\\n\\ncall into question whether the alleged misconduct led to the injury, proximate\\n\\ncause will have been adequately pled. The question for now is whether, accepting\\n\\nthe allegations as true, as we must, the City has said enough to make out a\\n\\nplausible case -- not whether it will probably prevail. Considering the broad and\\n\\nambitious scope of the FHA, the statute’s expansive text, the exceedingly detailed\\n\\nallegata found in the complaints, and the application of the administrative\\n\\nfeasibility factors laid out by the Supreme Court in Holmes v. Securities Investor\\n\\nProtection Corp., 503 U.S. 258 (1992), we are satisfied that the pleadings set out a\\n\\nplausible claim.\\n\\n The City’s pleadings meet this standard because Miami has alleged a\\n\\nsubstantial injury to its tax base that is not just reasonably foreseeable, but also is\\n\\nnecessarily and directly connected to the Banks’ conduct in redlining and reverse-\\n\\nredlining throughout much of the City. This injury plausibly bears “some direct\\n\\n\\n 4\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 5 of 76\\n\\n\\nrelation” to the claimed misconduct. Bank of Am., 137 S. Ct. at 1306. The injury\\n\\nto the City’s tax base is uniquely felt in the City treasury, and there is no risk that\\n\\nduplicative injuries could be pled by another plaintiff or that the apportionment of\\n\\ndamages amongst different groups of plaintiffs would be a problem. As we see it,\\n\\nthe City is in the best position. Indeed only the City can allege and litigate this\\n\\npeculiar kind of aggregative injury to its tax base. Simply put, a lawsuit\\n\\ncommenced by an individual homeowner cannot challenge the Banks’ policies on\\n\\nthe same citywide scale that the alleged misconduct took place on.\\n\\n However, the City’s pleadings fall short of sufficiently alleging “some direct\\n\\nrelation” between the Banks’ conduct and a claimed increase in expenditures on\\n\\nmunicipal services. The complaints fail to explain how these kinds of injuries --\\n\\nincreases in police, fire, sanitation, and similar municipal expenses -- are anything\\n\\nmore than merely foreseeable consequences of redlining and reverse-redlining.\\n\\nThe Court has told us that foreseeability alone is not enough.\\n\\n We do not mean to suggest that the City’s claims are destined to succeed.\\n\\nMany questions, and many difficult questions, remain and will have to be worked\\n\\nout in the district court. At the motion to dismiss stage, though, we are not asking\\n\\nwhether the complaints meet any probability requirement, only whether they\\n\\nplausibly allege violations of the FHA. Since we have found that they do, we\\n\\nallow this discrete portion of the City’s claims to proceed for now. The plaintiff\\n\\n\\n 5\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 6 of 76\\n\\n\\nhas said enough to get into the courthouse and be heard. We decide nothing more\\n\\ntoday.\\n\\n I. Background\\n\\n A. The City’s Claims\\n\\n On December 13, 2013, the City of Miami brought three complex civil\\n\\nrights actions in the Southern District of Florida against several different financial\\n\\ninstitutions. One suit was filed against Bank of America Corporation, Bank of\\n\\nAmerica N.A., Countrywide Financial Corporation, Countrywide Home Loans,\\n\\nand Countrywide Bank, FSB (collectively “Bank of America”), and another\\n\\nagainst Wells Fargo & Co. and Wells Fargo Bank, N.A. (collectively “Wells\\n\\nFargo”). For simplicity, we refer to all these defendants jointly as “the Banks.”\\n\\nThese were accompanied by another similar case against Citigroup, Inc. and\\n\\nrelated institutions. See City of Miami v. Citigroup, Inc., 801 F.3d 1268 (11th Cir.\\n\\n2015). The first time this panel considered this set of cases, we heard the Citigroup\\n\\ncase as well, but that case was not appealed to the Supreme Court. It has returned\\n\\nto the district court, where it has been stayed pending resolution of the other two.\\n\\nSee Order Staying Case Pending the Supreme Court’s Disposition of Matters Now\\n\\nBefore the Court, City of Miami v. Citigroup Inc., No. 13-cv-24510 (S.D. Fla. July\\n\\n13, 2016). As a result, our opinion today concerns only Bank of America and\\n\\nWells Fargo.\\n\\n\\n 6\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 7 of 76\\n\\n\\n The City alleged in considerable detail that the Banks had violated § 3604(b)\\n\\nand § 3605(a) of the Fair Housing Act. The first of these provisions makes it\\n\\nunlawful “[t]o discriminate against any person in the terms, conditions, or\\n\\nprivileges of sale or rental of a dwelling, or in the provision of services or facilities\\n\\nin connection therewith, because of race, color, religion, sex, familial status, or\\n\\nnational origin.” 42 U.S.C. § 3604(b). The second states that “[i]t shall be\\n\\nunlawful for any person or other entity whose business includes engaging in\\n\\nresidential real estate–related transactions to discriminate against any person in\\n\\nmaking available such a transaction, or in the terms or conditions of such a\\n\\ntransaction, because of race, color, religion, sex, handicap, familial status, or\\n\\nnational origin.” Id. § 3605(a). The City alleged that the Banks had violated these\\n\\nprovisions by intentionally engaging in discriminatory mortgage lending practices\\n\\nthat resulted in a disproportionate and excessive number of defaults by black and\\n\\nLatino homebuyers and caused substantial financial harm to the City. 1\\n\\n\\n1\\n The City also alleged that the Banks unjustly enriched themselves by taking advantage of\\n“benefits conferred by the City” at the same time that they engaged in unlawful lending practices\\nwhich “denied the City revenues it had properly expected through property and other tax\\npayments and . . . cost[] the City additional monies for services it would not have had to\\nprovide . . . absent [the Bank’s] unlawful activities.” Wells Fargo, 801 F.3d at 1261 (quoting\\nComplaint for Violations of the Federal Fair Housing Act at 61, City of Miami v. Wells Fargo &\\nCo., No. 13-24508-CIV (S.D. Fla. July 9, 2014), 2013 WL 6903725); Bank of Am., 800 F. 3d at\\n1267; see also Complaint for Violations of the Federal Fair Housing Act at 52–55, City of Miami\\nv. Bank of Am. Corp., No. 13-24506-CIV (S.D. Fla. July. 9, 2014), 2013 WL 6903721 (raising\\nthe same claims and allegations). The district court held that these claims failed. City of Miami\\nv. Bank of Am., No. 13-24506-CIV, 2014 WL 3362348 at *6–7 (S.D. Fla. July 9, 2014). We\\naffirmed, Bank of Am., 800 F.3d at 1287; Wells Fargo, 801 F.3d at 1267, and the City did not\\nappeal these claims to the Supreme Court. Accordingly, they are no longer in this case.\\n 7\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 8 of 76\\n\\n\\n The City said the Banks made a practice of systematically and intentionally\\n\\nrefusing to extend credit to minority borrowers on the same terms as they would\\n\\nextend credit to non-minority borrowers and, when they did extend credit to\\n\\ncomparably situated minority borrowers, doing so only on predatory terms, worse\\n\\nthan the terms non-minorities received. First Amended Complaint for Violations\\n\\nof the Federal Fair Housing Act at 2–5, City of Miami v. Bank of Am., No. 13-cv-\\n\\n24506 (S.D. Fla. Sept. 9, 2014) (“BoA FAC”); First Amended Complaint for\\n\\nViolations of the Federal Fair Housing Act at 2–5, City of Miami v. Wells Fargo &\\n\\nCo., No. 13-cv-24508 (S.D. Fla. Sept. 9, 2014) (“WF FAC”). 2 This amounted to\\n\\n\\n\\n2\\n The operative complaints for our purposes are the First Amended Complaints in both cases. As\\nwe explain, infra, the City appealed the denial of motions in both cases asking the district court\\nto reconsider the dismissal of its initial Complaints and to grant leave to file the First Amended\\nComplaints. After this panel reversed the decisions in September 2015, litigation proceeded in\\nthe district court for some months before the Supreme Court granted the Banks’ petitions for\\ncertiorari in June 2016. On remand from this Court, the City filed what it styled “Second\\nAmended Complaints,” (even though the First Amended Complaints had not technically been\\nfiled), and both of these were dismissed on multiple grounds, but with leave to amend. Order\\nGranting Motion to Dismiss Second Amended Complaint, Bank of Am., No. 13-cv-24506 (Mar.\\n17, 2016) (No. 98); Order Granting Motion to Dismiss Second Amended Complaint, Wells\\nFargo, No. 13-cv-24508 (Mar. 17, 2016) (No. 77). By the time the Supreme Court granted the\\npetition for certiorari, the City had filed Third Amended Complaints, and both Banks had moved\\nto dismiss these as well. See Defendants’ Motion to Dismiss Third Amended Complaint with\\nPrejudice and Request for Hearing, Bank of Am., No. 13-cv-24506 (May 16, 2016) (No. 103);\\nWells Fargo’s Motion to Dismiss with Prejudice the City’s Third Amended Complaint and\\nRequest for Hearing, Wells Fargo, No. 13-cv-24508 (May 24, 2016) (No 83). Both cases were\\nthen stayed pending resolution in the Supreme Court. Order Staying Case Pending the Supreme\\nCourt’s Disposition of Matters Now Before the Court, Bank of Am., No. 13-cv-24506 (July 13,\\n2016) (No. 128); Order Granting Unopposed Motion to Stay Further Proceedings Pending the\\nSupreme Court’s Disposition of Matters Now Before the Court, Wells Fargo, No. 13-cv-24508\\n(July 13, 2016) (No. 102). Since nothing had been appealed since the Second and Third\\nAmended Complaints were filed, the Supreme Court was explicit that it was looking to the First\\nAmended Complaints, see Bank of Am., 137 S. Ct. at 1301, and we do the same on remand.\\n 8\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 9 of 76\\n\\n\\nboth “redlining” (refusing to extend credit) and “reverse redlining” (extending\\n\\ncredit on worse terms). Black and Latino borrowers were thus unable to refinance\\n\\ntheir loans effectively. BoA FAC at 4; WF FAC at 4; see also Wells Fargo, 801\\n\\nF.3d at 1261; Bank of Am., 800 F. 3d at 1267. The City’s complaints detailed at\\n\\nconsiderable length the nature of these practices and characterized them as\\n\\n“abusive” because they resulted in loans with “unfair terms that [borrowers] could\\n\\nnot afford.” BoA FAC at 13; WF FAC at 11; see, e.g., BoA FAC at 22 (explaining\\n\\nwhat kinds of loans the City would categorize as “predatory”); WF FAC at 34\\n\\n(same).\\n\\n The City claims that these policies were entirely deliberate on the part of the\\n\\nBanks. The Amended Complaints explain that confidential witnesses -- former\\n\\nemployees at both Bank of America and Wells Fargo -- will testify to how\\n\\nminorities and residents of minority neighborhoods were targeted for predatory\\n\\nloan terms. E.g., BoA FAC at 19; WF FAC at 29. Moreover, witnesses allegedly\\n\\nwill testify that Wells Fargo specifically targeted Latino and African American\\n\\ncommunity groups and churches (but never white churches) and that employees\\n\\nwere assigned based on their race to make presentations to these groups. WF FAC\\n\\nat 30. Witnesses from Bank of America likewise will testify that they were\\n\\nencouraged to steer less financially savvy borrowers, often racial minorities,\\n\\ntoward loan products that were decidedly unfavorable to the customer and different\\n\\n\\n 9\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 10 of 76\\n\\n\\nfrom loan products offered to white applicants, but highly favorable to the bank.\\n\\nBoA FAC at 19–20.\\n\\n According to the City, all of this violated the FHA in two stages. To start,\\n\\nthe Banks intentionally discriminated against minority borrowers by targeting them\\n\\nfor burdensome loans. This had a disparate impact on minority borrowers, leading,\\n\\ndown the line, to a disproportionate number of exploitative loans in minority\\n\\nneighborhoods and, eventually, to a disproportionate number of foreclosures on\\n\\nminority-owned properties. BoA FAC at 15–19; WF FAC at 21–29.\\n\\n The City employed detailed regression analyses of the Banks’ self-reported\\n\\ndata to show that a Bank of America loan in a predominantly African-American or\\n\\nLatino Miami neighborhood was 5.857 times more likely to result in foreclosure\\n\\nthan a Bank of America loan in a non-minority Miami neighborhood. BoA FAC at\\n\\n26. For a minority-neighborhood loan from Wells Fargo, foreclosure was 6.975\\n\\ntimes more likely. WF FAC at 39. Further calculations indicated that, controlling\\n\\nfor credit history and other factors, a black Miami borrower was 1.581 times more\\n\\nlikely than a white borrower to receive a predatory loan from Bank of America and\\n\\n4.321 times more likely to receive one from Wells Fargo. BoA FAC at 22; WF\\n\\nFAC at 34. A Latino borrower was 2.087 times more likely to receive such a loan\\n\\nfrom Bank of America and 1.576 times more likely to receive one from Wells\\n\\nFargo. BoA FAC at 22; WF FAC at 34. Notably, even among borrowers with\\n\\n\\n 10\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 11 of 76\\n\\n\\ngood credit (FICO scores over 660), black borrowers were 1.533 and 2.572 times\\n\\nmore likely to receive a predatory loan from Bank of America and Wells Fargo,\\n\\nrespectively. BoA FAC at 22; WF FAC at 34. For Latino borrowers with good\\n\\ncredit, the figures were 2.137 and 1.875 times more likely. BoA FAC at 22; WF\\n\\nFAC at 34. The City identified similar disproportionalities on a larger scale by\\n\\ncomparing predominantly white neighborhoods with predominantly minority ones.\\n\\nSee BoA FAC at 23–25; WF FAC at 35–37.\\n\\n The complaints further alleged that the Banks’ lending practices resulted in\\n\\nminority borrowers suffering especially fast and frequent foreclosures, an\\n\\nimportant indicator of predatory lending practices. See BoA FAC at 29–30; WF\\n\\nFAC at 41. White borrowers’ average time from origination to foreclosure was\\n\\n3.448 years for a Bank of America loan or 3.266 years for a Wells Fargo loan; for\\n\\nblack and Latino borrowers the averages were 3.144 (black) and 3.090 (Latino)\\n\\nyears from Bank of America and 2.996 (both black and Latino) from Wells Fargo.\\n\\nBoA FAC at 28; WF FAC at 41. Confidential witnesses from both Banks will\\n\\nallegedly support the claims that each had deliberately targeted black and Latino\\n\\nborrowers for predatory loans. E.g., BoA FAC at 19–21; WF FAC at 30–31.\\n\\n What’s more, according to the complaints, the Banks’ misconduct was not\\n\\nlimited to loan origination but instead continued almost to the point of foreclosure.\\n\\nAs the Supreme Court noted, Bank of Am., 137 S. Ct. at 1301, the predatory\\n\\n\\n 11\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 12 of 76\\n\\n\\npractices alleged by the City included denying black and Latino customers\\n\\nopportunities to refinance or make loan modifications on fair terms. E.g. BoA\\n\\nFAC at 21; WF FAC at 32. According to the complaints, both Banks would cause\\n\\nforeclosures when “a minority borrower who previously received a predatory loan\\n\\nsought to refinance the loan, only to discover that [the bank] refused to extend\\n\\ncredit at all,” or refused to do so on the same terms they extended when\\n\\n“refinancing similar loans issued to white borrowers.” BoA FAC at 4; WF FAC at\\n\\n4. We note that such refinancing and loan modification decisions can occur before\\n\\nor after a property enters default.\\n\\n The City alleged that it suffered both economic and noneconomic injuries.\\n\\nBoA FAC at 31–35; WF FAC at 44–48. In both complaints the alleged\\n\\nnoneconomic injury was that the Banks’ conduct “adversely impacted the racial\\n\\ncomposition of the City and impaired the City’s goals to assure racial integration\\n\\nand desegregation and the social and professional benefits of living in an integrated\\n\\nsociety.” 3 BoA FAC at 31; WF FAC at 44. The City identified two forms of\\n\\neconomic injuries. It claimed damages from each bank based on reduced property\\n\\ntax revenues, arguing that the Banks’ lending policies caused minority-owned\\n\\n\\n\\n3\\n Because we find that the City adequately pled proximate cause for one of its economic injuries,\\nwe need not evaluate whether it also did so for its noneconomic injuries. The parties in their\\nbriefing have not squarely addressed these injuries, and the Supreme Court had little to say about\\nthem. We leave this matter to the district court to address in the first instance.\\n\\n 12\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 13 of 76\\n\\n\\nproperties to fall into unnecessary or premature foreclosure, causing them to lose\\n\\nsubstantial value and, in turn, decreasing the values of surrounding properties.\\n\\nBoA FAC at 32–34; WF FAC at 45–47. This reduced the City’s tax base and the\\n\\ntax revenue it took in. According to the City, “Hedonic regression” techniques\\n\\ncould be used to quantify with considerable particularity what portion of its losses\\n\\nwas attributable to the Banks’ conduct. BoA FAC at 32–34; WF FAC at 45–47.\\n\\nAdditionally, the City claimed damages based on the cost of the increased\\n\\nmunicipal services it provided to deal with problems attributable to the foreclosed\\n\\nand often vacant properties -- including police, firefighters, building inspectors,\\n\\ndebris collectors, and others. These increased services too, the City claimed,\\n\\nwould not have been necessary if the properties had not been foreclosed upon as a\\n\\nresult of the Banks’ discriminatory lending practices. BoA FAC at 34–35; WF\\n\\nFAC at 47–48.\\n\\n The City also asked for a declaratory judgment stating that the Banks’\\n\\nconduct violated the FHA, an injunction barring the Banks from engaging in\\n\\nsimilar predatory conduct, compensatory and punitive damages, and attorneys’\\n\\nfees. BoA FAC at 40–41; WF FAC at 53–54.\\n\\n\\n\\n\\n 13\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 14 of 76\\n\\n\\n B. District Court and 11th Circuit Decisions\\n\\n On July 9, 2014, the district court granted motions to dismiss by both\\n\\nbanks. 4 City of Miami v. Bank of Am., No. 13-24506-CIV, 2014 WL 3362348\\n\\n(S.D. Fla. July 9, 2014). The court determined first that the City lacked standing\\n\\nbecause, according to this Court’s opinion in Nasser v. City of Homewood, 671\\n\\nF.2d 432 (11th Cir. 1982), its claims fell outside the “zone of interests” protected\\n\\nby the FHA. Bank of Am., 2014 WL 3362348 at *3–4. Miami had alleged\\n\\n“merely economic injuries” that were not “affected by a racial interest.” Id. at *4.\\n\\nThe trial court also determined that the FHA contained a proximate cause\\n\\nrequirement, and that this requirement had not been met because the City failed to\\n\\n“demonstrate that the [Banks’] alleged redlining and reverse redlining caused the\\n\\nforeclosures to occur.” Id. at *5. According to the district court, the City should\\n\\nhave “allege[d] facts that isolate [the Banks’] practices as the cause of any alleged\\n\\nlending disparity.” Id. Additionally, the district court said that the FHA claims fell\\n\\noutside the statute of limitations. Id. at *6–7.\\n\\n The City moved for reconsideration and for leave to file amended\\n\\ncomplaints in both cases, arguing that it had standing and that it could remedy the\\n\\nstatute of limitations issue by amending the complaint. See Bank of Am., 800 F.3d\\n\\n\\n4\\n The court issued a detailed opinion in the Bank of America case. It then adopted and incorporated\\nthat opinion in the Wells Fargo case. City of Miami v. Wells Fargo & Co., No. 13-24508-CIV\\n(S.D. Fla. July 9, 2014).\\n\\n 14\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 15 of 76\\n\\n\\nat 1271; Wells Fargo, 801 F.3d at 1264. The amended complaints added further\\n\\ndetails concerning noneconomic injuries suffered by the City as a result of the\\n\\nBanks’ discriminatory lending practices. See BoA FAC at 31; WF FAC at 44.\\n\\nThe City also argued in its amended complaints that predatory lending had\\n\\n“adversely impacted the racial composition of the City,” “impaired the City’s goals\\n\\nto assure racial integration and desegregation,” and “frustrate[d] the City’s\\n\\nlongstanding and active interest in securing the benefits of an integrated\\n\\ncommunity.” BoA FAC at 31; WF FAC at 44. The district court denied the\\n\\nmotion, and the City appealed to this Court. Bank of Am., 800 F.3d at 1271; Wells\\n\\nFargo, 801 F.3d at 1265.\\n\\n We reversed and remanded in a series of opinions, the most detailed of\\n\\nwhich we issued in City of Miami v. Bank of America Corp., 800 F.3d 1262 (11th\\n\\nCir. 2015). We began by addressing standing and held that the City had alleged an\\n\\ninjury in fact sufficiently concrete and immediate to confer Article III standing. Id.\\n\\nat 1272. Next we addressed “statutory standing” -- a misnomer, since it really\\n\\nconcerns “whether the plaintiff has a cause of action under the statute.” Id. at 1273\\n\\n(quotation omitted). We determined that this plaintiff did because the key statutory\\n\\nlanguage “swe[pt] as broadly as allowed under Article III” and placed the City\\n\\nwithin the statute’s zone of interests. Id. at 1278; see also Trafficante v. Metro\\n\\n\\n\\n\\n 15\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 16 of 76\\n\\n\\nLife Ins. Co., 409 U.S. 205, 209 (1972) (identifying “a congressional intention to\\n\\ndefine [FHA] standing as broadly as is permitted by Article III”).\\n\\n We next held that the FHA did require proximate cause, but that the City’s\\n\\npleadings were adequate. Bank of Am., 800 F.3d at 1279–80, 1283. We rejected\\n\\nthe idea that the City needed to “allege that the [Banks’] actions directly harmed\\n\\nthe City.” Id. As we saw it, the “strict directness requirement” suggested by the\\n\\nBanks could not be the proper standard for the FHA because it “would run afoul of\\n\\nSupreme Court and Eleventh Circuit caselaw allowing entities who have suffered\\n\\nindirect injuries . . . to bring a claim under the FHA.” Bank of Am., 800 F.3d at\\n\\n1281 (citing Gladstone, Realtors v. Village of Bellwood, 441 U.S. 91, 109–11\\n\\n(1979) (allowing a village to sue a firm for discriminatory practices that caused\\n\\nsegregation); Havens Realty Corp. v. Coleman, 455 U.S. 363, 378–79 (1982)\\n\\n(allowing suit by a non-profit for “impairment of its organizational mission” and\\n\\n“drain on its resources”); Baytree of Inverrary Realty Partners v. City of\\n\\nLauderhill, 873 F.2d 1407, 1408–09 (11th Cir. 1989) (allowing a non-minority\\n\\ndeveloper to challenge a zoning decision as discriminatory)). Proximate cause, we\\n\\nsaid, was “not a one-size fits-all analysis.” Id. Rather, it “can differ statute by\\n\\nstatute.” Id.\\n\\n Instead, noting the Supreme Court’s “broad and inclusive” readings of the\\n\\nFHA, e.g., Trafficante, 409 U.S. at 209, we agreed with the City that the proper\\n\\n\\n 16\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 17 of 76\\n\\n\\nstandard for proximate cause was “foreseeability.” Id. at 1281–82. Damages\\n\\nclaims under the FHA were analogous to tort claims, we reasoned, and tort law had\\n\\ntraditionally relied on foreseeability as the standard by which to evaluate causal\\n\\nrelationships and to limit the expansion of liability. See id. at 1282. The City had\\n\\nmet this standard; “it claim[ed] that the [Banks’] discriminatory lending caused\\n\\nproperty owned by minorities to enter premature foreclosure, costing the City tax\\n\\nrevenue and municipal expenditures.” Id. at 1282. We said that “[a]lthough there\\n\\nare several links in that causal chain, none are unforeseeable,” and also noted that\\n\\nthe regression analyses in the complaints made the pleadings more than just\\n\\nspeculative. Id. We made no comment, though, on “whether the City will be able\\n\\nto actually prove its causal claims.” Id. at 1283 (emphasis added). That would be\\n\\nworked out in the district court on a factual basis far beyond the four corners of the\\n\\ncomplaint. Accordingly, we remanded the case. Id. at 1289.\\n\\n Bank of America and Wells Fargo each filed petitions for certiorari, which\\n\\nthe Supreme Court granted. It consolidated the two cases.\\n\\n C. Supreme Court Decision\\n\\n The Supreme Court began by resolving the “statutory standing” question of\\n\\nwhether the City had a cause of action under the FHA. Bank of Am., 137 S. Ct. at\\n\\n1302–05. The Court agreed that its previous cases had interpreted the statute\\n\\nbroadly for standing purposes. See id. Congress had even amended the statute\\n\\n\\n 17\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 18 of 76\\n\\n\\nafter these decisions, without making any change to the relevant language,\\n\\nindicating its assent to the Court’s expansive reading of the original text. Id. at\\n\\n1303–04.\\n\\n On proximate cause, though, the Supreme Court disagreed with this panel\\n\\nbut reached no firm conclusions. It determined that foreseeability, standing alone,\\n\\nwas not a sufficiently rigorous standard. See id. at 1306 (“[T]he Eleventh Circuit\\n\\nerred in holding that foreseeability is sufficient to establish proximate cause under\\n\\nthe FHA.”). The Court explained that “foreseeability alone does not ensure the\\n\\nclose connection that proximate cause requires.” Id. Since lending and housing\\n\\npolicies are deeply interconnected with “economic and social life,” the Court said\\n\\nthat “[a] violation of the FHA may . . . ‘be expected to cause ripples of harm to\\n\\nflow’ far beyond the defendant’s misconduct.” Id. (quoting Assoc. Gen.\\n\\nContractors of Cal., Inc. v. Carpenters, 459 U.S. 519, 534 (1983)). Since\\n\\n“[n]othing in the statute suggests that Congress intended to provide a remedy\\n\\nwherever those ripples travel,” foreseeability alone could not be enough. Id.\\n\\n While the Court was clear that foreseeability was not enough, it was less\\n\\ndefinitive when it came to laying out what more FHA proximate cause required.\\n\\nIts key instructions were these:\\n\\n Rather [than foreseeability], proximate cause under the FHA requires\\n “some direct relation between the injury asserted and the injurious\\n conduct alleged.” Holmes v. Sec. Investor Protect. Corp., 503 U.S. 258,\\n 268 (1992). A damages claim under the statute “is analogous to a\\n 18\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 19 of 76\\n\\n\\n number of tort actions recognized at common law,” Curtis v. Loether,\\n 415 U.S. 189, 195 (1974), and we have repeatedly applied directness\\n principles to statutes with “common-law foundations,” Anza v. Ideal\\n Steel Supply Corp., 547 U.S. 451, 457 (2007). “The general tendency”\\n in these cases is, “in regard to damages at least, is not to go beyond the\\n first step.” Hemi Grp., LLC v. City of New York, 559 U.S. 1, 10\\n (2010). What falls within that “first step” depends in part on the “nature\\n of the statutory cause of action,” Lexmark Int’l, Inc. v. Static Control\\n Components, Inc., 134 S. Ct. 1377, 1390 (2014), and an assessment “of\\n what is administratively possible and convenient,” Holmes, 503 U.S. at\\n 268.\\n\\nBank of Am., 137 S. Ct. at 1306 (citation formats altered).\\n\\n The Court remanded for further proceedings, stating that “[t]he lower courts\\n\\nshould define, in the first instance, the contours of proximate cause under the FHA\\n\\nand decide how that standard applies to the City’s claims for lost property-tax\\n\\nrevenue and increased municipal expenses.” Id. Lacking “the benefit of [the\\n\\nEleventh Circuit’s] judgment” on how to apply the principles it had laid out, and\\n\\nwith no other circuits having weighed in yet, the Court “decline[d]” to speak first.\\n\\nId.\\n\\n In this opinion, we endeavor carefully to apply the Court’s mandate to these\\n\\ncomplaints, to determine if they plausibly state a claim under the Fair Housing Act.\\n\\n II. Standard of Review\\n\\n We review a district court’s decision to dismiss a complaint de novo\\n\\n“accepting the factual allegations in the complaint as true and construing them in\\n\\nthe light most favorable to the plaintiff.” Boyd v. Warden, Holman Corr. Facility,\\n\\n\\n 19\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 20 of 76\\n\\n\\n856 F.3d 853, 863–64 (11th Cir. 2017); see also Ashcroft v. Iqbal, 556 U.S. 662,\\n\\n678 (2009). Here, the district court also denied leave to amend, which we\\n\\ngenerally review for abuse of discretion; however, when, as here, leave to amend\\n\\nwas denied “on the grounds of futility,” we review the denial de novo “because it\\n\\nis a conclusion of law that an amended complaint would necessarily fail.” Id. (“An\\n\\namendment is considered futile when the claim, as amended, would still be subject\\n\\nto dismissal.”). Essentially, then, we must consider de novo whether the City’s\\n\\namended complaints, which the district court declined to entertain, have stated a\\n\\nclaim. This is in line with the review conducted by the Supreme Court, Bank of\\n\\nAm., 137 S. Ct. at 1302, and with our review when we first heard these cases,\\n\\nBank of Am., 800 F.3d at 1271.\\n\\n For this case to proceed past a motion to dismiss, we need not find that the\\n\\nBanks’ actions in fact proximately caused the plaintiff’s injuries; we must find that\\n\\nthe City plausibly alleged that they did so. We evaluate whether each complaint\\n\\n“contain[s] sufficient factual matter . . . to ‘state a claim to relief that is plausible\\n\\non its face.’” Iqbal, 556 U.S. at 678 (quoting Bell Atlantic Corp. v. Twombly, 550\\n\\nU.S. 544, 570 (2007)). The standard is “plausibility”; it is decidedly not a\\n\\n“probability requirement.” Id. Still, plausibility requires that allegations push past\\n\\nthe line of showing “a sheer possibility” and “[w]here a complaint pleads facts that\\n\\nare ‘merely consistent with’ a defendant’s liability, it ‘stops short of the line\\n\\n\\n 20\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 21 of 76\\n\\n\\nbetween possibility and plausibility of entitlement to relief.’” Id. (quoting\\n\\nTwombly, 550 U.S. at 557). Facts are taken as true so long as they are not a\\n\\n“formulaic recitation of the elements” or “conclusory.” Id. at 681 (quoting\\n\\nTwombly, 550 U.S. at 555).\\n\\n III. Analysis\\n\\n Prosser and Keeton observed, of proximate cause, that “[t]here is perhaps\\n\\nnothing in the entire field of law which has called forth more disagreement, or\\n\\nupon which the opinions are in such a welter of confusion.” W. Page Keeton et al.,\\n\\nProsser and Keeton on the Law of Torts § 41, at 263 (5th ed. 1984). The Supreme\\n\\nCourt has not directed the lower courts to propose a sweeping standard for\\n\\nproximate cause that would apply across all cases or to define the word “direct” for\\n\\nall time. Indeed, we are not looking for (and could not find) “a black-letter rule\\n\\nthat will dictate the result in every case.” Holmes, 503 U.S. at 272 n.20. Rather,\\n\\nwe must evaluate where, as a matter of judicial economy and policy, we ought to\\n\\ndraw the line for this particular cause of action and these particular claims. As the\\n\\nCourt has said, proximate cause “label[s] generically the judicial tools used to limit\\n\\na person’s responsibility for the consequences of that person’s own acts. . . .\\n\\n[P]roximate cause reflects ideas of what justice demands, or of what is\\n\\nadministratively possible and convenient.” Id. at 268 (quotation omitted).\\n\\n\\n\\n\\n 21\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 22 of 76\\n\\n\\n We begin our analysis, then, with the Supreme Court’s instructions.\\n\\nProximate cause under the FHA certainly requires foreseeability, which is present\\n\\nhere but is not enough. See Bank of Am. 137 S. Ct. at 1305–06. Proximate cause\\n\\nalso requires “some direct relation between the injury asserted and the injurious\\n\\nconduct alleged.” Id. at 1306 (quoting Holmes, 503 U.S. at 268). Our task today\\n\\nis to determine what plaintiffs must do in order to plausibly allege “some direct\\n\\nrelation” and to evaluate whether the City’s complaints have met that standard.\\n\\n At the outset, we consider the central phrase “some direct relation.” There is\\n\\ngive in the joints between “some direct relation” and “some direct causation.”\\n\\nThese are not identical concepts, and so when, for example, Bank of America\\n\\nsuggests that Miami’s injuries “were not caused ‘directly’ by a loan,” it may not be\\n\\npresenting the question in a way that precisely and accurately reflects the Court’s\\n\\ninstruction. We might agree that the injuries were not “caused directly by a loan”\\n\\nand yet still find “some direct relation” between the injury and the statutory\\n\\nviolations. Causation is “the act or process of causing,” and to “cause” something\\n\\nis “to serve as cause or occasion of” or “to bring [it] into existence.” Webster’s\\n\\nThird New International Dictionary 356 (2002). Relation, on the other hand is “the\\n\\nmode in which one thing or entity stands to another, itself, or others,” or “a logical\\n\\nbond.” Id. at 1916. We are considering “direct relation,” as a critical aspect of\\n\\n“proximate cause,” so some palpable causation is required. We ought not forget,\\n\\n\\n 22\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 23 of 76\\n\\n\\nthough, that foreseeability, while insufficient on its own, remains a requirement\\n\\nand ensures some causal connection. “Some direct relation,” then, works to\\n\\nguarantee that there is a “logical bond” between violation and injury. Put another\\n\\nway, while foreseeability ensures “cause,” “some direct relation” ensures that the\\n\\ncause is sufficiently “proximate.”\\n\\n Further, the law requires “some direct relation” not any quantifiable amount\\n\\nof it. The standard is softened by the modifier “some,” meaning, “of an\\n\\nunspecified but appreciable or not inconsiderable quantity, amount, extent or\\n\\ndegree.” Id. at 2171. The requirement is therefore somewhat easier to meet than if\\n\\nthe Court had said we needed to find “a direct relation.”\\n\\n We are also aware that our analysis must be tied to the Fair Housing Act in a\\n\\nspecific way. The Supreme Court twice emphasized that the policy judgments that\\n\\nshape our proximate cause analysis will necessarily depend on the FHA. For\\n\\nstarters, “what falls within [the] ‘first step,’” to which proximate cause is\\n\\n“general[ly]” constrained, will “depend[] in part on the ‘nature of the statutory\\n\\ncause of action.’” Bank of Am., 137 S. Ct. at 1306. Second, our task is to “define,\\n\\nin the first instance, the contours of proximate cause under the FHA and” to apply\\n\\nthat standard to the City’s claims. Id. (emphasis added).\\n\\n After thoroughly reviewing the City’s complaints, we are satisfied that we\\n\\ncan find “some direct relation,” a meaningful and logical continuity, between the\\n\\n\\n 23\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 24 of 76\\n\\n\\nCity’s tax revenue injury and the Banks’ conduct by following the four guiding\\n\\nprinciples the Court outlined in Bank of America. We begin by considering (a)\\n\\n“what falls within [the] ‘first step’” of the causal chain, as we are aware of “‘[t]he\\n\\ngeneral tendency’ in these cases . . . ‘not to go beyond [that] first step.’” Id.\\n\\n(quoting Hemi Grp., 559 U.S. at 10). What falls within the first step will, we’re\\n\\ntold, depend on (b) “the nature of the statutory cause of action,” and (c) “an\\n\\nassessment of what is administratively possible and convenient.” Id. Finally, since\\n\\nthe common law is the basis for the direct relation requirement, we also look to (d)\\n\\nthe FHA’s common-law antecedents to the extent that we can. Id. We consider\\n\\neach of these principles in turn.\\n\\n A. An intervening step does not vitiate proximate cause\\n\\n The Court has also told us that “[t]he general tendency in these cases, in\\n\\nregard to damages at least, is not to go beyond the first step.” Bank of Am. 137 S.\\n\\nCt. at 1306 (quotations omitted). Both Banks, in their briefing on remand, make\\n\\nmuch of this “first step” analysis. It is clear, though, that proximate cause does not\\n\\nalways cut off at the first step after a violative act. A general tendency is not the\\n\\nsame as a hard and fast rule that dictates the outcome in every case, and Supreme\\n\\nCourt precedent shows that an intervening step will not vitiate proximate cause in\\n\\nall instances. What is more important, precedent reveals, is the certainty with\\n\\nwhich we can say the injury is fairly attributable to the statutory violation. An\\n\\n\\n 24\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 25 of 76\\n\\n\\nextended causal chain often makes attribution more difficult, but may not be the\\n\\nfinal word.\\n\\n 1.\\n\\n Supreme Court precedent makes crystal clear that an intervening step does\\n\\nnot necessarily mean proximate cause has not been plausibly alleged. Lexmark\\n\\nInternational, Inc. v. Static Control Components, Inc., 134 S. Ct. 1377 (2014), is a\\n\\ngood starting point precisely because the chain of causation there was complex and\\n\\ninvolved more than one simple step. The basic facts were these: Lexmark\\n\\nmanufactured and sold both laser printers and toner cartridges for those printers.\\n\\nLexmark, 134 S. Ct. at 1383. Other companies would buy used cartridges, then\\n\\nrefurbish and resell them. Id. The plaintiff company, Static Control, made and\\n\\nsold the components that the refurbishers needed to operate. Id. at 1384. Lexmark\\n\\nwould have preferred that its customers return used cartridges directly to Lexmark,\\n\\nso that it could refurbish and resell them itself. See id. at 1383. Static Control\\n\\nsued under the Lanham Act, alleging that Lexmark falsely and misleadingly led\\n\\nLexmark’s customers to believe that they were legally obligated to return spent\\n\\ncartridges to Lexmark and also led the refurbishers to believe that their businesses\\n\\nwere illegal. Id. at 1384. This, said Static Control, violated the Lanham Act’s\\n\\nprohibition on “false or misleading representation of fact . . . in commercial\\n\\nadvertising or promotion [that] misrepresents the nature, characteristics, [or]\\n\\n\\n 25\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 26 of 76\\n\\n\\nqualities . . . [of] another person’s goods, services, or commercial activities.” Id.\\n\\n(quoting 15 U.S.C. § 1125(a)). The Supreme Court granted certiorari in Lexmark\\n\\nto resolve issues of “statutory standing” under the Lanham Act, including\\n\\nproximate cause. See id. at 1385, 1390. The central question was “whether the\\n\\nharm alleged has a sufficiently close connection to the conduct the statute\\n\\nprohibits.” Id.\\n\\n An “intervening step of consumer deception” between Lexmark’s alleged\\n\\nconduct and the harm sustained by Static Control was not fatal to the claim. Id. at\\n\\n1391. The Court said that a Lanham Act plaintiff could demonstrate proximate\\n\\ncause by “show[ing] . . . injury flowing directly from the deception wrought by the\\n\\ndefendant’s advertising,” including, critically, “deception of consumers caus[ing]\\n\\nthem to withhold trade from the plaintiff.” Id. (emphasis added). Common-law\\n\\nprinciples supported the idea that “a plaintiff [could] be directly injured” even\\n\\nwhen a misrepresentation was made to a third party. Id. Liability was not without\\n\\nlimits, though. A company injured only by a third party’s “inability to meet [its]\\n\\nfinancial obligations” could not sue. Id. at 1392 (quotation omitted).\\n\\n The Court acknowledged, as it would again in Bank of America, the\\n\\n“general tendency” not to go “beyond the first step.” Id. at 1394; see Bank of Am.,\\n\\n137 S. Ct. at 1306. In the circumstances presented by Lexmark, though, the nature\\n\\nof the conduct and the harm sustained persuaded the Court against following this\\n\\n\\n 26\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 27 of 76\\n\\n\\ngeneral tendency. See Lexmark, 134 S. Ct. at 1394. The Court explained its\\n\\nreluctance to invariably limit liability to the first step this way:\\n\\n [T]he reason for that general tendency is that there ordinarily is a\\n “discontinuity” between the injury to the direct victim and the injury to\\n the indirect victim, so that the latter is not surely attributable to the\\n former (and thus also to the defendant’s conduct), but might instead\\n have resulted from “any number of other reasons.”\\n\\nId. (quoting Anza, 547 U.S. at 458–59). This “discontinuity” is evaluated in terms\\n\\nof logical relations and policy judgments. See Anza, 547 U.S. at 459–60. In\\n\\nLexmark, if the refurbishers sold fewer cartridges, “it would follow more or less\\n\\nautomatically” that Static Control suffered a proportional injury, “without the need\\n\\nfor any ‘speculative . . . proceedings’ or ‘intricate, uncertain inquiries.’” Lexmark,\\n\\n134 S. Ct. at 1394 (quoting Anza, 547 U.S. at 459–60).\\n\\n There was no “discontinuity” problem in Lexmark because of the close\\n\\nconnection between Static Control and the remanufacturers it supplied. “Any false\\n\\nadvertising that reduced the remanufacturers’ business necessarily injured Static\\n\\nControl as well.” Id. There was “something very close to a 1:1 relationship”\\n\\nbetween harm to remanufacturers and harm to Static Control because the false\\n\\nadvertising hurt Static Control in direct proportion to how much it hurt the\\n\\nremanufacturers. Id. In other words, harm to Static Control was “so integral an\\n\\naspect of the [violation] alleged” that the Court went beyond the first step in the\\n\\ncausal chain. Id.\\n\\n\\n 27\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 28 of 76\\n\\n\\n Still, Lexmark cabined liability by requiring “economic or reputational\\n\\ninjury flowing directly from the [defendant’s] deception.” Id. at 1391. This\\n\\nrequirement would not be met “when the deception produces injuries to a fellow\\n\\ncommercial actor that in turn affect the plaintiff.” Id. By way of example, the\\n\\nCourt suggested that a competitor whose business failed because of false\\n\\nadvertising could sue the false advertiser, but that competitor’s landlord could not\\n\\nsue the false advertiser for the value of rent payments he could no longer collect.\\n\\nSee id. The landlord’s injury suffered from a “discontinuity” that Static Control’s\\n\\ninjury did not. See id. at 1394.\\n\\n All of this goes to show that intervening steps in a causal chain cannot\\n\\nautomatically and invariably end the analysis. If they could, there would be no\\n\\nmeaningful way to distinguish Static Control from the hypothetical landlord. Each\\n\\nis only injured if the defendant’s direct competitor (the refurbishers on the actual\\n\\nfacts of the case) is injured first. The chain of causation is an important part of the\\n\\nanalysis, but the real deciding factor, at least for this Lanham Act case, was\\n\\nwhether there was a discontinuity between violation and injury, or, put another\\n\\nway, whether the injurious conduct “necessarily injured [the plaintiff] as well” as\\n\\nthe first-step victim, in such a way that the first-step victim was “not [a] more\\n\\nimmediate victim[]” than the plaintiff. Id. Thus we may look to whether the injury\\n\\n\\n\\n\\n 28\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 29 of 76\\n\\n\\nis “surely attributable” to the statutory violation; we do not simply count the steps\\n\\nin the causal chain. Id.\\n\\n Bridge v. Phoenix Bond & Indemnity Co., 553 U.S. 639 (2008), a RICO\\n\\nmail fraud case, makes the same point. In a suit between bidders at County-\\n\\noperated tax lien auctions, the defendants were accused of filing fraudulent\\n\\ndocuments in order to increase their success at the auctions at the expense of the\\n\\nplaintiffs. See Bridge, 553 U.S. at 642–44. To the extent that a chain of causation\\n\\nwas discussed at all, it was explained in terms of reliance. See id. at 657–58. The\\n\\ndefendants argued that the County, not the plaintiffs, had relied on their\\n\\nmisrepresentations. Id. at 648. The Court held that the plaintiffs’ injuries were\\n\\nproximately caused by the defendants’ misrepresentations even though the\\n\\nplaintiffs had not themselves relied on the fraudulent filings -- “first-party reliance”\\n\\nwas not “necessary to ensure that there was a sufficiently direct relationship\\n\\nbetween the defendant’s wrongful conduct and the plaintiff’s injury” to satisfy\\n\\nproximate cause. Id. at 657–58 (emphasis added).\\n\\n The “direct relationship” in Bridge turned on a connection between harm\\n\\nand injury that was non-formalistic and disconnected from step-counting. The\\n\\ndecision instead rested on policy considerations, see id. at 654–55, and on\\n\\ncommon-law principles, see id. at 656–57. The Court never mentioned a “first\\n\\nstep” default rule, but it’s clear that the plaintiffs’ harm would not have fallen in\\n\\n\\n 29\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 30 of 76\\n\\n\\nthe first step, since the County had to rely on the defendants’ misrepresentations\\n\\nand then had to conduct auctions on these fraudulent terms before the plaintiffs\\n\\ncould be injured. Instead, Bridge observed that the Second Restatement of Torts\\n\\n“does not say that only those who rely on the misrepresentation” -- that is, those at\\n\\nthe front of the chain of causation -- “can suffer a legally cognizable injury.”\\n\\nBridge, 553 U.S. at 656 (citing 3 Restatement (Second) of Torts §548A (1976)).\\n\\n While neither Lexmark nor Bridge arose under the FHA, their approach to\\n\\nthe first-step rule is instructive. Both decisions acknowledge that “under common-\\n\\nlaw principles, a plaintiff can be directly injured by a misrepresentation even\\n\\nwhere” someone else relied on it. Lexmark, 134 S. Ct. at 1391 (citing Bridge, 553\\n\\nU.S. at 639). This is a foundational principle of proximate cause; it is not an\\n\\nidiosyncratic wrinkle associated with a particular statute or type of claim. E.g.,\\n\\nBlue Shield of Virginia v. McCready, 457 U.S. 465, 482–84 (1982) (discussing\\n\\n“antitrust injury” as a requirement of proximate cause under certain statutes).\\n\\n 2.\\n\\n Turning to our case, the Banks argue that the City fails to allege proximate\\n\\ncause simply because its injuries fall outside of the “first step.” So wooden a rule\\n\\nwould be inconsistent with precedent as well as with the oft-noted statement that,\\n\\nwhen it comes to proximate cause, it is “virtually impossible to announce a black-\\n\\nletter rule that will dictate the result in every case.” Assoc. Gen., 549 U.S. at 536\\n\\n\\n 30\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 31 of 76\\n\\n\\n(citing Blue Shield, 457 U.S. at 477 n.13; Palsgraf v. Long Island R. Co., 162 N.E.\\n\\n99, 103 (N.Y. 1928) (“[W]hat is a proximate cause, depend[s] in each case upon\\n\\nmany considerations . . . .”) (Andrews, J., dissenting)); see also Lexmark, 134 S.\\n\\nCt. at 1390 (“The proximate-cause inquiry is not easy to define . . .”); Bridge, 553\\n\\nU.S. at 659 (“[P]roximate cause is generally not amenable to bright-line rules.”);\\n\\nHolmes, 503 U.S. at 272 n.20. Proceeding beyond a first step here is consistent\\n\\nwith the instruction that we stop at the first step only as a “general tendency,” and\\n\\nthat we also consider the nature of the cause of action, principles of continuity, and\\n\\nadministrative feasibility. Bank of Am., 137 S. Ct. at 1306.\\n\\n Wells Fargo nevertheless argues that the City’s claims cannot survive\\n\\nproximate cause analysis because they are wholly “contingent,” and points to\\n\\nHolmes v. Securities Investor Protection Corp., 503 U.S. 258 (1992), as an\\n\\nexample of a case where proximate cause failed “because the [plaintiffs’] injuries\\n\\nwere ‘purely contingent on the harm suffered by [third parties].’ [Holmes, 503\\n\\nU.S.] at 271.” But Holmes established no such rule. Rather, it explicitly identified\\n\\nthree distinct considerations by which proximate cause should be evaluated.\\n\\nHolmes, 503 U.S. at 269. We discuss these in considerable detail, infra, but for\\n\\nnow it is enough to observe that contingency on third parties is not among them.\\n\\n\\n\\n\\n 31\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 32 of 76\\n\\n\\nThe Court would have had no recourse to policy considerations if it could have\\n\\ndisposed of Holmes merely based on the involvement of a third party. 5\\n\\n Indeed, if Wells Fargo were right about the application of the first-step rule\\n\\nhere, this case would be over at the pleading stage simply because the chain of\\n\\ncausation involves more than a single step. And there would have been no reason\\n\\nfor the Supreme Court to remand this case back to our Court for further proximate\\n\\ncause analysis. The Supreme Court, too, was obviously aware that individual\\n\\nhomeowners were involved in this case. Again, if that alone were enough to bar\\n\\nproximate cause, the Court would hardly have sought the input of the lower federal\\n\\ncourts. The essential point for us then is that the “general tendency” to stop at the\\n\\nfirst step is just that, a general tendency, not an inexorable rule.\\n\\n If, in fact, there were a hard and fast “only the first step” rule limiting\\n\\nliability, a plaintiff homeowner who was forced into foreclosure on account of a\\n\\npredatory bank loan that violated the Fair Housing Act would never be able to\\n\\nplausibly allege that the foreclosure was proximately caused by the bank’s\\n\\npredation. By the Banks’ lights, there are two critical steps in the chain of\\n\\n\\n5\\n We also reject the application of Anza v. Ideal Steel Supply Corp, 547 U.S. 451, 457 (2006),\\nthat Wells Fargo has offered in its briefing on remand. It cites Anza for its proposed rule that\\nproximate cause cannot exist where the causes of a plaintiff’s injury are distinct from the\\nviolative conduct. But this amounts to simply assuming the answer to our question. Whether the\\ncauses of the City’s injury are too distinct and too remote from the violative conduct is at the\\nheart of the proximate cause inquiry. Furthermore, the Bank’s suggested rule overlooks that\\nAnza applied the factors drawn from Holmes. Anza, 547 U.S. at 459–60.\\n\\n 32\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 33 of 76\\n\\n\\ncausation between the act of redlining and foreclosure: the middle and distinct step\\n\\nbeing a homeowner’s default. So inexorable a rule would even bar the homeowner\\n\\nfrom seeking redress for the foreclosure under the FHA, since the foreclosure only\\n\\noccurs after the homeowner takes the independent step of failing to make payments\\n\\non the predatory loan.\\n\\n If, arguendo, we were to count steps, the Banks’ arguments would still be\\n\\nunconvincing. For starters, the Banks overstate the length of the causal chain by\\n\\nreading the complaints unfavorably to the City, ignoring, among other things,\\n\\nallegations that Bank of America “fail[ed] to offer refinancing or loan\\n\\nmodifications to minority customers on fair terms” and that Wells Fargo “limit[ed]\\n\\nthe ability of minority borrowers to refinance out of the same predatory loans that\\n\\nthey previously received from the Bank.” BoA FAC at 21; WF FAC at 32. These\\n\\nalleged torts and acts of redlining occurred after -- perhaps long after -- the bad\\n\\nloans were originated, and may have occurred far down the causal chain, shortly\\n\\nbefore foreclosure. To take one example of their step-counting, Wells Fargo says\\n\\nthat injury to the City from lost property-tax revenue falls six links down the causal\\n\\nchain and depends on the actions of five independent parties. This count ignores\\n\\nthe complaints’ allegations that distinct FHA violations occurred when\\n\\nhomeowners already having financial difficulties were attempting to refinance or\\n\\notherwise modify their loans, and instead counts only from the point of loan\\n\\n\\n 33\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 34 of 76\\n\\n\\norigination. Because loan modification and refinancing can occur after a borrower\\n\\ndefaults, FHA violations of this type could be far more closely connected to the\\n\\nCity’s lost revenue. At the very least there might only be one step between the\\n\\ndenial of refinancing and a bank’s foreclosing on a property already in default.\\n\\n Additionally, the Bank counts a reduction in a home’s market value and a\\n\\nconcomitant tax assessment of that property as comprising two distinct steps in the\\n\\ncausal chain and speculates that foreclosures are not carried out by the Banks\\n\\nthemselves but by “a fourth party (presumably the mortgage servicers).” The\\n\\ncomplaints make no mention of an independent mortgage servicer, and in fact\\n\\nsuggest that the Banks were involved in refinancing and loan modifications,\\n\\npresumably serving themselves as the loans’ mortgage servicers. By ignoring\\n\\nthese unfavorable facts in the pleadings, and by generally refusing to draw\\n\\ninferences in the City’s favor, this accounting fails to read the complaints in the\\n\\nlight most favorable to the City, as we must at the motion to dismiss stage.\\n\\n Additionally, Wells Fargo’s count is undermined by the very principles\\n\\nanimating the general tendency in tort to stop at the first step. We generally stop\\n\\nthere because, as the time frame is extended and the chain of causation becomes\\n\\nmore attenuated, additional variables (maybe even causes) may intervene, making\\n\\nit more difficult to fairly attribute fault to the tortfeasor. As the Supreme Court put\\n\\nit in this case, “the housing market is interconnected with economic and social\\n\\n\\n 34\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 35 of 76\\n\\n\\nlife,” and “[a] violation of the FHA may . . . be expected to cause ripples of harm\\n\\nto flow far beyond the defendant’s misconduct.” Bank of Am., 137 S. Ct. at 1306\\n\\n(quotations omitted).\\n\\n Thus, a further problem with the Banks’ count is that the variety of factors\\n\\nthat we worry might independently explain a homeowner’s foreclosure (like the\\n\\nloss of a job or spiking health care costs) all occur at the front end of the step-\\n\\ncounting, between the act or acts of redlining and the foreclosure, not later. Once\\n\\nwe have reached increased foreclosures on a neighborhood or citywide basis, it\\n\\nseems to us that the path to the City’s substantially decreased tax base is clear,\\n\\ndirect and immediate; we can discern no obvious intervening roadblocks. Virtually\\n\\nall the independent variables posited by the Banks occur before foreclosure. We\\n\\ncan identify the same kind of continuity here as in Lexmark: if the Banks’\\n\\npredatory lending practices injured homeowners and led to foreclosures on a\\n\\nmassive scale, these injuries inflicted on multiple homeowners in the same city\\n\\nmust almost surely have injured the City as well. There is no discontinuity in this\\n\\nportion of the causal chain. Thus, since the risks of multiple independent variables\\n\\nafter foreclosure are not likely, and are not many, even if we were to count steps in\\n\\nthe way the Banks have suggested, the principles animating the general first-step\\n\\nrule do not support the Banks’ calculation of the post-foreclosure causal chain.\\n\\n\\n\\n\\n 35\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 36 of 76\\n\\n\\n The Banks’ step-counting is self-evidently conducted so as to identify as\\n\\nmany steps as possible. We might just as easily place the same injury at the second\\n\\nor third step: First, a bank extends predatory loans in violation of the FHA.\\n\\nSecond, homeowners default. Third, the bank forecloses and the property values\\n\\nplummet, necessarily reducing the City’s tax base and injuring its fisc. The chain\\n\\nwill be shorter still if struggling homeowners sought to refinance and then faced\\n\\nswift foreclosures when fair terms were not extended. This count, which draws\\n\\ninferences in favor of the City, is decidedly more appropriate for the motion to\\n\\ndismiss stage. At the very least, the ease with which we can count far fewer steps\\n\\nreinforces our view that step-counting is of limited value and cannot alone settle\\n\\nthe challenging questions of proximate cause here.\\n\\n B. The text and history of the FHA suggest a far-reaching statute\\n\\n The Supreme Court also instructs us to consider “the nature of the statutory\\n\\ncause of action.” Id. As we see it, the FHA has a broad remedial purpose, is\\n\\nwritten in decidedly far-reaching terms, and is perfectly capable of accommodating\\n\\nthe type of aggregative causal connection that the City has identified between the\\n\\nBanks’ alleged misconduct and financial harm to Miami. Proximate cause is only\\n\\none means by which Congress sets the scope of liability. Thus, for example\\n\\n“Congress might express limits by defining the parties who may sue, by using\\n\\naffirmative defenses, by providing limited remedies, by narrowly proscribing\\n\\n\\n 36\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 37 of 76\\n\\n\\nprohibited conduct, or by defining statutory terms.” Sandra F. Sperino, Statutory\\n\\nProximate Cause, 88 Notre Dame L. Rev. 1199, 1236 (2013). The result,\\n\\nespecially for complex and repeatedly amended statutes like the FHA, is an\\n\\n“interconnected web of congressional judgments about how and when liability\\n\\nshould be limited.” Id. To develop a proximate cause standard without taking the\\n\\nfull statutory scheme into account would be “to intrude upon” this web and to\\n\\nignore the will of Congress. See id.\\n\\n Most obviously, the “[t]he language of the [FHA] is broad and inclusive.”\\n\\nTrafficante v. Metro. Life Ins. Co., 409 U.S. 205, 209 (1972). It provides for suit\\n\\nby “an aggrieved person,” 42 U.S.C. § 3613(a)(1)(A), (c)(1), expansively defined\\n\\nas “any person who claims to have been injured by a discriminatory housing\\n\\npractice,” § 3602(i) (emphasis added). As we’ve said before, “‘any’ means all.”\\n\\nJones v. Waffle House, Inc., 866 F.3d 1257, 1267 (11th Cir. 2017) (emphases\\n\\nadded). This language facilitates suits by a broad range of potential plaintiffs, and\\n\\nthe Court has told us that it evinces not merely “a congressional intent to confer\\n\\nstanding broadly,” Bank of Am., 137 S. Ct. at 1303, but “a congressional intention\\n\\nto define standing as broadly as it is permitted by Article III,” Trafficante, 409 U.S.\\n\\nat 209. The Court has also noted that later Congresses amended the FHA with full\\n\\nknowledge of the Court’s broad readings and without changing the language the\\n\\nCourt had construed so broadly. Bank of Am., 137 S. Ct. at 1303.\\n\\n\\n 37\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 38 of 76\\n\\n\\n The Fair Housing Act also prohibits a wide range of conduct. Thus, it is a\\n\\nviolation “to refuse to sell or rent . . . or to refuse to negotiate . . . or otherwise\\n\\nmake unavailable or deny, a dwelling to any person because of race, color,\\n\\nreligion, sex, familial status, or national origin” as well as “[t]o discriminate\\n\\nagainst any person in the terms, conditions, or privileges of sale or rental of a\\n\\ndwelling, or in the provision of services or facilities in connection therewith” for\\n\\nany of the same reasons. 42 U.S.C. § 3604(a)–(b). It also expressly forbids racial\\n\\npreferences in housing notices and advertisements, misrepresentation of housing\\n\\navailability based on race, and “representations regarding the entry or prospective\\n\\nentry into the neighborhood” of members of protected classes. Id. § 3604(c)–(e).\\n\\nMost relevant for the City’s claims, it is also “unlawful for any person or other\\n\\nentity whose business includes engaging in residential real estate–related\\n\\ntransactions to discriminate against any person in making available such a\\n\\ntransaction, or in the terms or conditions of such a transaction,” including in loans\\n\\n“for purchasing, constructing, improving, repairing, or maintaining a dwelling.” Id.\\n\\n§ 3605(a). Again, this is far-reaching, and takes aim at discrimination that might\\n\\nbe found throughout the real estate market and throughout the process of buying,\\n\\nmaintaining, or selling a home.\\n\\n The injury to the City is as valid and as cognizable under the FHA as the\\n\\ninjury to the homeowners. See Bank of Am., 137 S. Ct. at 1303 (finding the City\\n\\n\\n 38\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 39 of 76\\n\\n\\nhas standing). And cities have been allowed to sue for similar injuries in the past,\\n\\nas in Gladstone Realtors v. Village of Bellwood, 441 U.S. 91 (1979), where a city\\n\\nalleged it was injured when segregative racial steering practices by two real estate\\n\\nfirms redounded to “the economic and social detriment of the citizens of [the]\\n\\nvillage.” Id. at 95. The village said “racial steering effectively manipulate[d] the\\n\\nhousing market” because marketing homes in certain areas only to buyers of\\n\\ncertain races served to dramatically reduce the number of potential buyers. Id. at\\n\\n109–10. The Court identified “profound” consequences in neighborhoods\\n\\nimpacted by this practice, including financial consequences. Id.; see id. at 111 &\\n\\nn.24. Not only did the village have standing to challenge racial steering, but the\\n\\nCourt even said that “[a] significant reduction in property values directly injures a\\n\\nmunicipality by diminishing its tax base.” Id. at 110–11 (emphasis added). The\\n\\nphrase “directly injures” was not used in a causal sense, but nonetheless suggests\\n\\nthat the Court has not traditionally considered this type of injury to be overly\\n\\nattenuated or nebulous.\\n\\n Moving beyond the text, in evaluating proximate cause for a statutory cause\\n\\nof action, the Court has repeatedly directed us to consider a statute’s remedial aims\\n\\n-- Congress’s priorities in passing it. See, e.g., Blue Shield, 457 U.S. at 478\\n\\n(considering “the relationship of the injury alleged with those forms of injury about\\n\\nwhich Congress was likely to have been concerned”); see also Lexmark, 134 S. Ct.\\n\\n\\n 39\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 40 of 76\\n\\n\\nat 1393 (identifying “diversion of sales to a direct competitor” as possibly “the\\n\\nparadigmatic direct injury from false advertising”); Assoc. Gen. Contractors of\\n\\nCal., Inc. v. California State Council of Carpenters, 459 U.S. 519, 538 (1983)\\n\\n(following Blue Shield in evaluating whether an injury fell “squarely within the\\n\\narea of congressional concern,” (quoting Blue Shield, 457 U.S. at 484)); cf.\\n\\nHolmes, 503 U.S. at 274 (“[W]e fear that RICO’s remedial purposes would more\\n\\nprobably be hobbled than helped . . . .” if the plaintiff’s proximate cause standard\\n\\nwere adopted).\\n\\n The legislative history of the FHA is less detailed than most. Congress\\n\\npassed it through “a truncated legislative process in which no committee reports\\n\\nwere issued.” Rodney A. Smolla, Federal Civil Rights Acts § 3:10, at 546–47 (3d\\n\\ned. 2017). A legislative assistant who worked on the legislation recalled after the\\n\\nAct’s passage that this was “a time when riots threatened to close down every\\n\\nmajor city in the country,” and that the Act was presented as a response; it was\\n\\nhoped that “the law as a teacher might overcome the ignorance and fear of whites\\n\\nwhich previously had blocked attempts to lower a black-white barrier.” Jean\\n\\nEberhart Dubofsky, Fair Housing: A Legislative History and a Perspective, 8\\n\\nWashburn L. J. 149, 154 (1969). The legislative history that we do have and the\\n\\ncontext in which the FHA arose both comport with a proximate cause standard that\\n\\ncan accommodate claims like the City’s. Thus, for example, the Supreme Court\\n\\n\\n 40\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 41 of 76\\n\\n\\nhas recently recounted how, in response to the turmoil of the mid-60s, President\\n\\nJohnson convened the National Advisory Commission on Civil Disorders (the\\n\\n“Kerner Commission”), which “identified residential segregation and unequal\\n\\nhousing and economic conditions in the inner cities as significant, underlying\\n\\ncauses of the social unrest.” Tex. Dept. of Hous. & Cmty. Affairs v. Inclusive\\n\\nCmtys. Project, Inc., 135 S. Ct. 2507, 2516 (2015). “The Commission concluded\\n\\nthat ‘[o]ur Nation is moving toward two societies, one black, one white—separate\\n\\nand unequal.’” Id. (quoting Report of the National Advisory Commission on Civil\\n\\nDisorders 1 (1968)).\\n\\n In passing the Fair Housing Act, Congress explicitly took aim at these broad\\n\\nsocial ills -- maladies that were being felt on a citywide scale. Congress did not\\n\\njust target individual discriminatory landlords, but sought to reshape in meaningful\\n\\nways the landscape of American cities. Senator Walter Mondale, the chief sponsor\\n\\nof the bill that would become the FHA, explained that the Act was intended to end\\n\\nhousing segregation as a means of bringing about racial equality more broadly.\\n\\nThe legislation’s goals were directed at the neighborhood level and indeed were\\n\\naimed beyond the housing market:\\n\\n [O]vert racial discrimination remains in one major sector of American\\n life—that of housing. . . . [F]air housing is one more step toward\\n achieving equality in opportunity and education . . . . The soundest,\\n long-range way to attack segregated schools is to attack the segregated\\n neighborhood.\\n\\n\\n 41\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 42 of 76\\n\\n\\n114 Cong. Rec. 3421 (Feb. 20, 1968); see also id. at 3422 (“[I]n truly integrated\\n\\nneighborhoods people have been able to live in peace and harmony -- and both\\n\\nNegroes and whites are the richer for the experience.”). A co-sponsor asked, “As\\n\\nsegregation continues to grow . . . will not the cities which house the majority of\\n\\nthe nation’s industrial and commercial life find themselves less and less able to\\n\\ncope with their problems, financially and in every other way?” Id. at 2988 (Feb.\\n\\n14, 1968) (statement of Sen. Brooke). The legislation, as its sponsors saw it, was\\n\\ndesigned to extend through chains of causation. Among other things, its sponsors\\n\\nquite specifically referenced harm to a city’s tax base, arising out of discrimination\\n\\nin the housing market. Senator Mondale put it this way:\\n\\n Declining tax base, poor sanitation, loss of jobs, inadequate educational\\n opportunity, and urban squalor will persist as long as discrimination\\n forces millions to live in the rotting cores of central cities.\\n\\nId. at 2274 (Feb. 6, 1968) (emphasis added).\\n\\n It does not go too far to suggest, at least at a high order of abstraction, that in\\n\\nsetting a standard for proximate cause the FHA looks far beyond the single most\\n\\nimmediate consequence of a violation. Limiting the proximate cause calculus in\\n\\nthat way would not be consonant with the powerful remedial purposes animating\\n\\nthe bill. The Act took aim at “the segregated neighborhood” in general, not just at\\n\\nthe prejudiced building owner.\\n\\n\\n\\n\\n 42\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 43 of 76\\n\\n\\n This is all to say that, notwithstanding issues of proof that might arise later\\n\\nin litigation, the FHA was written in broad terms and was aimed at broad\\n\\nproblems. We can discern no reason to think as a general matter that the City’s\\n\\nclaims are out of step with the “nature of the statutory cause of action” and the\\n\\nremedial scheme that Congress created.\\n\\n C. Tracing causation here is not administratively infeasible\\n\\n Perhaps the most important step in the proximate cause analysis in this case\\n\\nis consideration of “what is administratively possible and convenient.” Bank of\\n\\nAm., 137 S. Ct. at 1306 (quoting Holmes, 503 U.S. at 268). This is because\\n\\nadministrative feasibility is most closely connected to the policy judgments upon\\n\\nwhich proximate cause standards necessarily depend. See Holmes, 503 U.S. at 268\\n\\n(“[P]roximate cause reflects ideas of what justice demands, or of what is\\n\\nadministratively possible and convenient.” (internal quotations omitted)). In no\\n\\nsmall part, we conclude that the City has adequately -- that is to say, plausibly --\\n\\npled proximate cause because we find it entirely practicable and not unduly\\n\\ninconvenient for the courts to handle damages like the City’s tax revenue injury.\\n\\nCases like this will never be among the simplest that our courts see, but the federal\\n\\ncourts regularly handle complex and high-stakes cases, so complexity alone is no\\n\\nreason to dismiss a case on the pleadings. As pled, the City’s injury is\\n\\nascertainable with a sufficient degree of precision for some of its economic\\n\\n\\n 43\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 44 of 76\\n\\n\\ninjuries, specifically the harm to its tax base. Since the City’s injuries are unique\\n\\nto its treasury, no other plaintiff will plead the same injuries, or attempt to recover\\n\\nthe same funds. The City is in the best position to allege and litigate this peculiar\\n\\nkind of injury, to deter future violations and, theoretically, to actually remedy its\\n\\ndistinctive injury.\\n\\n In Holmes v. Securities Investor Protection Corp., 503 U.S. 258 (1992), the\\n\\nCourt conducted a proximate cause analysis focused on administrative feasibility.\\n\\nHolmes involved the Securities Investor Protection Corporation (SIPC), a federally\\n\\ncreated non-profit corporation empowered to sue broker-dealers who “ha[ve] failed\\n\\nor [are] in danger of failing to meet [their] obligations to [their] customers.” Id. at\\n\\n261 (quoting 15 U.S.C. § 78eee(a)(3)). In Holmes, SIPC alleged that broker-\\n\\ndealers manipulated securities in “a ‘pattern of racketeering activity’” that violated\\n\\nRICO, 18 U.S.C. §§ 1962, 1961(1), (5). Holmes, 503 U.S. at 263. The case asked\\n\\nwhether SIPC, “neither a purchaser nor a seller of securities” could sue under\\n\\nRICO even though its claims were, in essence, the same claims that could have\\n\\nbeen brought by investors under Rule 10b–5, under which SIPC lacked standing.\\n\\nId. at 265 n.7.\\n\\n RICO allows for a civil action by “[a]ny person injured in his business or\\n\\nproperty by reason of a violation of section 1962.” Id. at 265 (quoting 18 U.S.C.\\n\\n§ 1964(c)). SIPC claimed that it should be allowed to sue under this provision\\n\\n\\n 44\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 45 of 76\\n\\n\\n“because it [was] subrogated to the rights of those customers of the broker-dealers\\n\\nwho did not purchase manipulated securities.” Id. at 270. The chain of causation\\n\\nwas thus the following: The defendants manipulated securities and broker-dealers\\n\\nbought manipulated securities. The broker-dealers sold some of their customers\\n\\nthese manipulated securities, and their value plummeted when the fraud was\\n\\nexposed. As a result, the broker-dealers could not meet their obligations to their\\n\\ncustomers, including to some who had not even bought manipulated securities. It\\n\\nwas these nonpurchasing customers’ rights that SIPC argued it was subrogated to.\\n\\nSee id. at 270–71. Granting, “arguendo” that SIPC was subrogated as it claimed,\\n\\nHolmes, 503 U.S. at 271, the Court found that “the conspirators’ conduct did not\\n\\nproximately cause the nonpurchasing customers’ injury,” id. at 270.\\n\\n The Court pointed to three distinct reasons why “directness of relationship”\\n\\nwas “one of [the] central elements” of “Clayton Act causation.” Holmes, 503 U.S.\\n\\nat 269. First, less direct injuries are harder to attribute to a violation. Id. Second,\\n\\nclaims at different levels of remove complicated the apportionment of harm among\\n\\nplaintiffs at different levels. Id. Third, directly injured plaintiffs usually can be\\n\\ncounted on to sue and deter wrongdoing. Id. at 269–70. All three reasons for\\n\\ndirectness were said to apply “with equal force” to antitrust and RICO suits. Id. at\\n\\n270. The Court then considered the reasons again in the context of the particular\\n\\nclaims and found that each indicated that SIPC’s claims fell outside the proper\\n\\n\\n 45\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 46 of 76\\n\\n\\nlimits of proximate causation. Id. at 272–74. It would appear, from the Court’s\\n\\nanalysis, that these are not only reasons why “directness of relationship” is\\n\\nrequired, but are also important factors against which to measure the directness of\\n\\nthe relationship.\\n\\n When applied to the City’s claims against the Banks, these factors strongly\\n\\nsuggest that the City has plausibly alleged “some direct relation” between the\\n\\nBanks’ alleged conduct and the injury to the City’s tax revenue. We cannot say the\\n\\nsame for the increased-expenditures injury, though. Here, we review how each of\\n\\nthe Holmes factors applies to the City’s economic injuries, distinguishing, when\\n\\nrelevant, between the tax-revenue injury and the increased-expenditures injury.\\n\\nFinally, we explain how the Holmes factors provide a clear means by which to\\n\\ncabin liability and prevent suits by more remotely injured parties.\\n\\n 1.\\n\\n Holmes’s first factor says that directness is required because “the less direct\\n\\nan injury is, the more difficult it becomes to ascertain the amount of a plaintiff’s\\n\\ndamages attributable to the violation, as distinct from other, independent, factors.”\\n\\nHolmes, 503 U.S. at 269. In Holmes, this factor decidedly cut against finding a\\n\\nsufficiently direct relationship because it would have required the district court “to\\n\\ndetermine the extent to which [the nonpurchasing customers’] inability to collect\\n\\nfrom the broker-dealers was the result of the alleged conspiracy to manipulate, as\\n\\n\\n 46\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 47 of 76\\n\\n\\nopposed to” any other reasons why the broker-dealers might not have money on\\n\\nhand (such as “poor business practices,” and the “failure to anticipate\\n\\ndevelopments in the financial markets”). Id. at 273. On this first factor, the City’s\\n\\ntax-revenue injury fares well, and its municipal-expenditures injury fares poorly.\\n\\nThe City has plausibly alleged that it can present an analysis of reduced tax\\n\\nrevenue that is precise enough to avoid difficulties with isolating the role of the\\n\\nBanks’ alleged violations. It has not done so for its municipal expenditures.\\n\\n In its complaints, the City of Miami’s tax-revenue injury seeks damages\\n\\n“based upon reduced property tax revenues resulting from (a) the decreased value\\n\\nof the vacant properties themselves, and (b) the decreased value of properties\\n\\nsurrounding the vacant properties.” BoA FAC at 31; WF FAC at 44. According to\\n\\nthe City, “[r]outinely maintained property tax and other data allow for the precise\\n\\ncalculation of the property tax revenues lost by the City as a direct result of\\n\\nparticular [bank] foreclosures.” BoA FAC at 32; WF FAC at 45. This “Hedonic\\n\\nregression methodology,” the City asserts, “can be used to quantify precisely the\\n\\nproperty tax injury to the City caused by [the Banks’] discriminatory lending\\n\\npractices and resulting foreclosures in minority neighborhoods.” BoA FAC at 34;\\n\\nWF FAC at 47.\\n\\n The City does not go so far as to conduct this analysis and attach the results\\n\\nto its pleadings, but its First Amended Complaints nonetheless suffice to describe\\n\\n\\n 47\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 48 of 76\\n\\n\\nthe analysis in far more than speculative or conclusory fashion. The City has\\n\\nexplained in some detail how this analysis works:\\n\\n Homes in foreclosure tend to experience a substantial decline in\\n value . . . [F]oreclosure properties and the problems associated with\\n them likewise cause especially significant declines in surrounding\\n property values because the neighborhoods become less desirable. . . .\\n Routinely maintained property tax and other data allow for the\\n precise calculation of the property tax revenues lost by the City as a\\n direct result of particular [bank] foreclosures. Using a well-established\\n statistical regression technique that focuses on effects on neighboring\\n properties, the City can isolate the lost property value attributable to\\n [the Banks’] foreclosures and vacancies from losses attributable to\\n other causes, such as neighborhood conditions. This technique, known\\n as Hedonic regression, when applied to housing markets, isolates the\\n factors that contribute to the value of a property by studying thousands\\n of housing transactions. Those factors include the size of a home, the\\n number of bedrooms and bathrooms, whether the neighborhood is safe,\\n whether neighboring properties are well-maintained, and more.\\n Hedonic analysis determines the contribution of each of these house\\n and neighborhood characteristics to the value of a home.\\n\\nBoA FAC at 32–33; WF FAC at 45–46. 6 This gives us a clear idea of the final\\n\\nanalysis -- based on empirical data drawn from thousands of housing transactions,\\n\\nthe City will calculate the impact of the Banks’ foreclosures on property values in\\n\\nredlined (and reverse-redlined) areas of Miami, controlling for other variables and\\n\\nisolating the impact of the redlining. The City points to studies in which this\\n\\n\\n\\n6\\n Wells Fargo says that the City pleads “that it could conduct a study that might be able to show\\nthat foreclosures affect property values.” (emphases in original). The City’s pleading does not\\nhedge its allegations in this way, and discounting the feasibility of its analysis on the front end is\\ninconsistent with our obligation to draw all reasonable inferences in the City’s favor at this\\npreliminary stage.\\n\\n 48\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 49 of 76\\n\\n\\nmethodology has produced the kind of results the City will need to present. BoA\\n\\nFAC at 33–34; WF FAC 46–47. The complaints conclude, then, that\\n\\n“[a]pplication of such Hedonic regression methodology . . . can be used to quantify\\n\\nprecisely the property tax injury to the City caused by [the Banks’] discriminatory\\n\\nlending practices and resulting foreclosures.” BoA FAC at 34; WF FAC at 47.\\n\\n The pleadings strongly suggest, then, that the tax-revenue injury to the City\\n\\nattributable to the Banks’ alleged discriminatory practices is readily calculable.\\n\\nUnder Twombly and Iqbal a mere statement that “[the Banks] caused the loss of\\n\\nproperty tax revenue” would be wholly conclusory and would be disregarded. But\\n\\nby indicating and explaining at considerable length the kind of analysis that would\\n\\nbe conducted to quantify the loss of revenue attributable to discriminatory lending,\\n\\nthe City has plausibly alleged a calculable harm and has made more than a\\n\\nformulaic recitation of how the causation requirement will be met. There could be\\n\\na battle of experts down the line over whether the regression analysis really shows\\n\\nwhat the City says it does, but, as we see it, that would be for a later stage of the\\n\\nlitigation. The complaints’ allegation that regression analysis can pinpoint\\n\\ncausation is sufficient at this stage and helps account for the concerns raised by this\\n\\nfirst factor.\\n\\n The plausibility of hedonic regression analysis has a direct bearing on how\\n\\n“difficult it [is] to ascertain the amount of [the City’s] damage attributable to the\\n\\n\\n 49\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 50 of 76\\n\\n\\nviolation, as distinct from other, independent, factors,” Holmes, 503 U.S. at 269,\\n\\nand thus helps determine “what is administratively possible and convenient,” in\\n\\nterms of damages calculation, Bank of Am., 137 S. Ct. at 1306. Here, the City has\\n\\nplausibly pled that it is practicable and convenient to quantify the property tax\\n\\ninjury’s causal connection to the Banks’ policies. In addition to the studies\\n\\nidentified by the City, we note in passing there has been a substantial amount of\\n\\nwriting (including legal literature) that has discussed or employed hedonic\\n\\nregression analysis as a practicable and effective way of calculating impacts on\\n\\nreal estate values.7 One author at the University of Wisconsin School of Business\\n\\nhas written that “[o]ver the past three decades, hedonic estimation has clearly\\n\\nmatured from a new technology to become the standard way economists deal with\\n\\nhousing heterogeneity.” 8 Likewise, the Organisation for Economic Co-operation\\n\\nand Development’s (OECD) Handbook on Residential Property Prices Indices\\n\\n(RPPI) calls hedonic regression “probably the best method that could be used in\\n\\norder to construct quality RPPIs for various types of property.” 9 While we may\\n\\n\\n7\\n See, e.g., Yun-Chien Chang, Economic Value or Fair Market Value: What Form of Takings\\nCompensation is Efficient?, 20 SUP. CT. ECON. REV. 35, 52–54 (2012); Yun-Chien Chang & Lee\\nAnne Fennell, Partition and Revelation, 81 U. CHI. L. REV. 27, 35 n.35(2014); Randall Akee,\\nCheckerboards and Coase: The Effect of Property Institutions on Efficiency in Housing Markets,\\n52 J.L. & ECON. 395, 402–03 (2009).\\n8\\n Stephen Malpezzi, Hedonic Pricing Models: A Selective and Applied Review, in HOUSING\\nECONOMICS AND PUBLIC POLICY 67, 87 (Tony O’Sullivan & Kenneth Gibb eds., 2003).\\n9\\n OECD, Hedonic Regression Methods, in HANDBOOK ON RESIDENTIAL PROPERTY PRICE INDICES\\n50, 57 (2003).\\n\\n 50\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 51 of 76\\n\\n\\nnot engage in a Daubert analysis at this early stage, that hedonic regression\\n\\nanalysis has been favorably referenced and employed elsewhere and over several\\n\\ndecades cuts against the suggestion at the motion to dismiss stage that it is a wholly\\n\\nimplausible invention of the City’s or that apportioning blame through its\\n\\napplication would be so challenging that the complaints cannot state a claim.\\n\\n At a more basic level, the aggregative nature of the City’s claims also helps\\n\\neliminate any discontinuity between the statutory violation and the injury. See\\n\\nLexmark, 134 S. Ct. at 1394. Here, the claimed violation is a “pattern or practice\\n\\nof reverse redlining” leading to a “disproportionately high rate of foreclosure.”\\n\\nBoA FAC at 30; WF FAC at 43. Even if each individual act of redlining does not\\n\\nbear a one-to-one proportional relationship to Miami’s loss of tax revenue, see\\n\\nLexmark, 134 S. Ct. at 1394, since intervening circumstances affect which\\n\\nindividual properties go into foreclosure, in the aggregate it has been plausibly\\n\\nalleged that the impact of redlining and reverse-redlining can be identified with\\n\\nprecision and deterred. Similarly, in Blue Shield, the Court identified “the physical\\n\\nand economic nexus between the alleged violation and the harm to the plaintiff” as\\n\\na factor to consider when applying proximate cause to the Clayton Act. Blue\\n\\nShield, 457 U.S. at 478. The scale of the misconduct matches the scale of the\\n\\ninjury.\\n\\n\\n\\n\\n 51\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 52 of 76\\n\\n\\n Since the Supreme Court spoke to this issue in Bank of America, two district\\n\\ncourts analyzing similar FHA claims by municipalities against lending institutions\\n\\nhave relied on the availability of regression analysis in finding that proximate\\n\\ncause had been plausibly alleged. Most similarly and most recently, a district court\\n\\nin the Northern District of California entertained a similar case brought by the City\\n\\nof Oakland against Wells Fargo for predatory lending practices. City of Oakland\\n\\nv. Wells Fargo Bank, N.A., No. 15-cv-04321, 2018 WL 3008538 (N.D. Cal. June\\n\\n15, 2018). 10 In denying a motion to dismiss that court recognized, as we have, that\\n\\n“[w]hile the fact of aggregative injury itself does not obviate proximate cause\\n\\nanalysis,” the proffer of “a specific statistical analysis in regard to [the City’s]\\n\\nproperty tax injury” adequately supports the idea that there was “an alleged\\n\\nprovable and quantifiable causal link between the defendant’s conduct and\\n\\nplaintiff’s injury” notwithstanding the suggested length of the causal chain. Id. at\\n\\n*8. But when it came to a municipal-expenditures injury -- similar to Miami’s --\\n\\nthe district court ruled that since “Oakland ha[d] not proffered any statistical\\n\\n\\n\\n10\\n After this decision, the district court in the Oakland case certified two questions for\\ninterlocutory appeal to the Ninth Circuit: “(1) Do Oakland’s claims for damages based on the\\ninjuries asserted in the [First Amended Complaint] satisfy on a motion to dismiss proximate\\ncause required by the FHA?” and “(2) Is the proximate-cause requirement articulated in City of\\nMiami limited to claims for damages under the FHA and not to claims for injunctive or\\ndeclaratory relief?” Order Granting Defendant’s Motion to Amend Order to Include\\nCertification for Interlocutory Appeal, City of Oakland, No. 15-cv-04321, 2018 WL 7575537 at\\n*2. The parties’ briefs before the Ninth Circuit are due in June and July of 2019. City of\\nOakland v. Wells Fargo & Co., No. 19-15169 (9th Cir. Mar. 26, 2019), ECF No. 10.\\n\\n 52\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 53 of 76\\n\\n\\nanalyses comparable to those in the property-tax analysis,” the first Holmes factor\\n\\ncounted against them and problems of multiple causation abounded. Id. at *10.\\n\\nThose claims were dismissed without prejudice. Id. A district court in\\n\\nPhiladelphia found that city had “adequately [pled] proximate cause for . . . non-\\n\\neconomic injuries” stemming from FHA violations in part by relying on “a\\n\\nregression analysis of [bank] loan data” that had demonstrated Latino and African-\\n\\nAmerican borrowers were 2.641 and 4.147 times more likely to go into foreclosure\\n\\nthan similarly situated white borrowers. City of Philadelphia v. Wells Fargo &\\n\\nCo., No. 17-2203, 2018 WL 424451 (E.D. Pa. Jan. 16, 2018).\\n\\n In describing its second claimed economic injury -- increased municipal\\n\\nexpenditures for police, fire, sanitation, and the like resulting from widespread\\n\\nforeclosures -- the City does not do as well when measured against the first\\n\\nHolmes factor. When it comes to this injury, the City’s complaints fail to explain\\n\\nhow we can ascertain with any level of detail or precision which expenditures will\\n\\nbe attributable to the Banks. It is self-evident that this must be accomplished\\n\\nsomehow because the entire increase in municipal expenditures over any time\\n\\nperiod cannot possibly be fairly attributed to the Banks’ conduct. Intervening\\n\\ncauses and independent variables will inevitably run up this measure of damages\\n\\nbecause the City’s expenditures occur at some obvious level of remove from the\\n\\nforeclosures that it says cause them. They are further down the chain, to put it in\\n\\n\\n 53\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 54 of 76\\n\\n\\nstep-counting terms. There is nothing in the pleadings that suggests the plaintiff\\n\\nwill be able to sort out the extent to which these damages are attributable to the\\n\\nBanks’ misconduct.\\n\\n The City’s pleadings on increased expenditures are in stark contrast to their\\n\\npleadings about tax revenue. The increased expenditures pleadings state, in almost\\n\\nconclusory fashion, that “the City is required to provide increased municipal\\n\\nservices” at foreclosed properties and that “these services would not have been\\n\\nnecessary if the properties had not been foreclosed upon.” BoA FAC at 34; WF\\n\\nFAC at 47. The complaints then proceed to list types of expenditures: police, fire,\\n\\nbuilding code enforcement, and the like. If any direct connections exist between\\n\\nthe foreclosure and any of these expenditures, the City has not explained them, and\\n\\nthey are not so obvious as to be self-evident. We also see no explanation of how\\n\\nthe City will identify the amount of increase attributable to the foreclosures or to\\n\\nthe Banks’ conduct. In pleading the tax-revenue injury, however, the City explains\\n\\nin considerable detail how hedonic regression analysis will help pinpoint the\\n\\nattributable loss. This is not to say that hedonic regression analysis, specifically,\\n\\nshould have been referenced again in relation to the expenditure injury in order to\\n\\nsatisfy the first Holmes factor. Rather we suggest only that a pleading in a case\\n\\nlike this must make clear how a plaintiff will demonstrate that an injury is\\n\\n\\n\\n\\n 54\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 55 of 76\\n\\n\\nattributable to a defendant. Hedonic regression serves this role with regard to the\\n\\ntax-revenue injury, but may not be the only way this could ever be accomplished.11\\n\\n The first Holmes factor, addressing the attributability of the injury to the\\n\\ndefendant’s conduct, is where the two economic injuries alleged by the City are\\n\\nmost different in terms of finding a “direct relation.” The tax-revenue injury has\\n\\nbeen pled with detailed explanations of statistical proof, which serve to plausibly\\n\\nallege that the courts will be able to work out just what the Banks can be fairly held\\n\\naccountable for. The municipal-expenditure injury fails to do this. Statistical\\n\\nproofs are not the only method of proof, but, when we readily discern a\\n\\ndiscontinuity between misconduct and injury, for the plaintiff to plausibly plead\\n\\nproximate cause, it must allege something more with which to bridge the gap and\\n\\ndemonstrate that the defendant’s liability will bear “some direct relation” to its\\n\\n\\n\\n11\\n A few other district courts have illustrated the point. In three lawsuits against banks alleging\\nthe same kinds of practices that Miami has alleged, Cook County, Illinois claimed damages\\nbased on “out-of-pocket costs it . . . incurred in processing the discriminatory foreclosures, such\\nas additional funding for the Cook County Sheriff to serve foreclosure notices and for the Circuit\\nCourt of Cook County to process the deluge of foreclosures.” County of Cook v. Bank of Am.\\nCorp., No. 14 C 2280, 2018 WL 1561725 at *7 (N.D. Ill. Mar. 30, 2018); see also County of\\nCook, Ill. v. HSBC N. Am. Holdings, 314 F. Supp. 3d 950, 956 (N.D. Ill. 2018); County of\\nCook, Ill. v. Wells Fargo & Co., 314 F. Supp. 3d 975, 982 (N.D. Ill. 2018). Those out-of-pocket\\ncosts were found to have plausibly been proximately caused by the banks because these\\nexpenditures are automatic results of foreclosures. See HSBC, 314 F. Supp. 3d at 962; Wells\\nFargo, 314 F. Supp. 3d at 984; Bank of Am., 2018 WL 1561725 at *7. These were the only\\nclaimed damages that survived a motion dismiss in the Northern District of Illinois, as all three\\ncourts there found that Cook County had failed to adequately plead proximate cause for the kinds\\nof tax-revenue and municipal-expenditure injuries that Miami pleads here. See HSBC, 913 F.\\nSupp. 3d at 962–64; Wells Fargo, 314 F. Supp. 3d at 988; Bank of Am., 2018 WL 1561725 at\\n*5. Miami pled no out-of-pocket costs closely tied to foreclosures along these lines.\\n 55\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 56 of 76\\n\\n\\nactions. On the increased-expenditure injury, the City has not plausibly pled its\\n\\ncase.\\n\\n 2.\\n\\n Holmes’s second factor posits that “recognizing claims of the indirectly\\n\\ninjured would force courts to adopt complicated rules apportioning damages\\n\\namong plaintiffs removed at different levels of injury from the violative acts, to\\n\\nobviate the risk of multiple recoveries.” Holmes, 503 U.S. at 269. In Holmes, this\\n\\nwas a problem because a trial court would “have to find some way to apportion the\\n\\npossible respective recoveries by the broker-dealers and the customers, who would\\n\\notherwise each be entitled to recover the full treble damages.” Id. at 273. Antitrust\\n\\ncases also emphasize “the risk of duplicative recovery engendered by allowing\\n\\nevery person along a chain of distribution to claim damages” from a single\\n\\nviolation, and have identified this as a powerful reason to allow suit only by more\\n\\ndirectly injured parties. Blue Shield, 457 U.S. at 474–75 (citing Ill. Brick Co. v.\\n\\nIllinois, 431 U.S. 720, 745 (1977); Hawaii v. Standard Oil Co. of Cal., 405 U.S.\\n\\n251 (1972)).\\n\\n Again, no such problem is presented in this case: plainly, the injuries to the\\n\\nCity’s treasury are not shared by any other possible plaintiff. These economic\\n\\ninjuries, whether or not they can ultimately be recovered for, could only be alleged\\n\\nby the City. The City’s theory, therefore, presents no concern about double\\n\\n\\n 56\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 57 of 76\\n\\n\\nrecovery or “piggy-backing,” precisely because its injuries are unique.\\n\\nSubstantially decreased tax revenue and increased municipal costs are injuries that\\n\\naffect the interests of the City alone, so there could not plausibly be any difficulty\\n\\nin apportioning them between multiple plaintiffs. The harm and damages pled by\\n\\nindividual homeowners suing under the FHA would be entirely different. These\\n\\nplaintiffs could sue for actual and punitive damages, injunctive and equitable relief,\\n\\nor attorney’s fees. See 42 U.S.C. § 3613(c). In this Circuit they could also seek\\n\\ndamages based on “anger, embarrassment, and emotional distress.” Banai v.\\n\\nSec’y, U.S. Dep’t of Hous. & Urban Dev. ex rel. Times, 102 F.3d 1203, 1207 (11th\\n\\nCir. 1997). Many courts have permitted FHA plaintiffs to recover pecuniary\\n\\ndamages, including moving costs and forfeited security deposits. E.g., Belcher v.\\n\\nGrand Reserve MGM, LLC, 269 F. Supp. 3d 1219, 1239 (M.D. Ala. 2017). But no\\n\\ncourt could allow a homeowner to recover for harm to a city’s treasury.\\n\\n The City, on the other hand, has claimed it was financially harmed in two\\n\\nways -- injury to its tax base and tax revenue because of reduced property value,\\n\\nand increased expenditures on City services in certain neighborhoods. The\\n\\ndamages that these harms could support do not overlap in any way with or\\n\\nduplicate the damages that individual homeowners may have sustained, because\\n\\nthe harms are entirely separate. The City’s injuries would be “passed on” forms of\\n\\nthe homeowners’ injuries if, for example, it were claiming it lost tax revenue\\n\\n\\n 57\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 58 of 76\\n\\n\\nbecause homeowners who were overpaying on their mortgages were subsequently\\n\\nunable to pay their taxes. But this is not the case. The City alleges instead that the\\n\\nBanks’ misconduct had a direct, necessary, and immediate impact on its fiscal\\n\\nhealth at the neighborhood and citywide level. The homeowners’ losses are\\n\\nobviously related to the losses that Miami allegedly incurred, but they are\\n\\nindependent. Injury to the City’s treasury is a distinct injury, it is not purely\\n\\nderivative of misfortunes visited on homeowners. Even if we were to assume that\\n\\neach victim of discrimination were to successfully bring an individual claim -- a\\n\\nwholly implausible hypothesis -- the City would still have an independent set of\\n\\nclaims based on the independent harm that it suffered. The claims would be linked\\n\\nonly by shared facts surrounding the violation.\\n\\n 3.\\n\\n Holmes’s final factor builds on the first two: “[T]he need to grapple with\\n\\nthese problems,” the Court said, referring to the first two factors, “is simply\\n\\nunjustified by the general interest in deterring injurious conduct, since directly\\n\\ninjured victims can generally be counted on to vindicate the law as private\\n\\nattorneys general, without any of the problems attendant upon suits by plaintiffs\\n\\ninjured more remotely.” Id. at 269–70. Thus, in Holmes, the directly injured\\n\\nbroker-dealers “could be counted on to bring suit for the law’s vindication,” and so\\n\\nit was less necessary for SIPC to sue on behalf of the broker-dealers’ customers.\\n\\n\\n 58\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 59 of 76\\n\\n\\nId. at 273. In Bridge, the same factor cut in the other direction; the plaintiffs were\\n\\ninjured because they had less success at county-run auctions when the defendants\\n\\ncheated, and their harm was “the direct result of [defendant’s] fraud” in part\\n\\nbecause, even though the plaintiffs didn’t themselves rely on any fraudulent\\n\\nassertions, “no more immediate victim is better situated to sue.” Bridge, 553 U.S.\\n\\nat 658.\\n\\n The third Holmes factor has been applied to antitrust statutes as well. The\\n\\navailability of more directly injured plaintiffs influenced the Court’s determination\\n\\nthat “directness” between the plaintiff’s injury and the defendant’s action was\\n\\nlacking in Associated General Contractors of California, Inc. v. Carpenters, 459\\n\\nU.S. 519, 540–41 (1983). There, a union alleged that the defendant employer\\n\\nassociation had “coerced certain third parties . . . to enter into business\\n\\nrelationships with nonunion firms” in a way that violated the Clayton Act. Id. at\\n\\n520–21. This hurt unionized firms and, thus, hurt the plaintiff union. Id. The\\n\\nCourt found that the union had not alleged a sufficiently direct injury, noting that:\\n\\n The existence of an identifiable class of persons whose self-interest\\n would normally motivate them to vindicate the public interest in\\n antitrust enforcement diminishes the justification for allowing a more\\n remote party such as the Union to perform the office of a private\\n attorney general. Denying the Union a remedy on the basis of its\\n allegations in this case is not likely to leave a significant antitrust\\n violation undetected or unremedied.\\n\\nId. at 542.\\n\\n\\n 59\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 60 of 76\\n\\n\\n In these kinds of cases it is preferable for more directly injured plaintiffs to\\n\\ntake the lead in acting as private attorneys general because those plaintiffs will be\\n\\nable to deter future violations more effectively and efficiently. When more directly\\n\\ninjured parties can sue for the full swath of harm caused by statutory violations, the\\n\\nthreat of suit by these parties has the maximum possible deterrent effect on\\n\\npotential violators, and it’s simply not worthwhile to also allow minimally\\n\\ndeterring suits by plaintiffs farther down the causal chain. Cf. Southern Pac. Co. v.\\n\\nDarnell-Taenzer Lumber Co., 245 U.S. 531, 534 (1918) (“The [defendant] ought\\n\\nnot to be allowed to retain his illegal profit, and the only one who can take it from\\n\\nhim is the one that alone was in relation with him, and from whom the [defendant]\\n\\ntook the sum.”) (Holmes, J.).\\n\\n Thus, in antitrust cases the courts have long expressed a “concern for the\\n\\nreduction in the effectiveness of those suits if brought by indirect purchasers with a\\n\\nsmaller stake in the outcome than that of direct purchasers suing for the full\\n\\namount of the overcharge.” Ill. Brick Co., 431 U.S. at 745; see also Lexmark, 134\\n\\nS. Ct. at 1391 (establishing, for the Lanham Act, a rule barring suit by\\n\\n“commercial parties who suffer merely as a result of [a direct] competitor’s\\n\\n‘inability to meet [its] financial obligations’” (quoting Anza, 547 U.S. at 458)).\\n\\nFor this reason, the federal courts have rejected the monopolist’s “passing on”\\n\\ndefense -- the argument that mid-stream purchasers charged monopoly prices are\\n\\n\\n 60\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 61 of 76\\n\\n\\nnot harmed because they can “pass on” any overcharges to consumers. See\\n\\nRichard A. Posner, Economic Analysis of Law 395–96 (9th ed. 2014). Consumers\\n\\ncannot sue over monopoly pricing, but this does not mean there is a meaningful\\n\\nreduction in enforcement. See id. at 396 (“[Consumers’] right [to sue] is less\\n\\nvaluable because, being at once more remote . . . and more numerous, consumers\\n\\nare less efficient antitrust enforcers.”).\\n\\n The same logic surrounding deterrence does not apply here. While the City\\n\\nmay be a step further down the chain of causation, the homeowners are much more\\n\\nnumerous and less well suited to prosecute a global claim. The City’s suit could\\n\\nachieve better deterrence because it aims to recover for a larger injury sustained on\\n\\na citywide basis and to remedy a different, broader violation than a homeowner’s\\n\\nsuit would. The City alleges widespread redlining and reverse-redlining policies\\n\\nconducted by the Banks. The City’s suit challenges the entire policies. A\\n\\ndiscrimination claim by an individual homeowner would challenge only a bank’s\\n\\ndiscriminatory action against that homeowner. Conceivably the banks could face\\n\\nsuits by many homeowners who were discriminated against, or who lost property\\n\\nvalue because their neighbors’ houses were foreclosed on, but these suits wouldn’t\\n\\nserve to condemn the pattern or policy. Individual homeowners would also face\\n\\nmost of the same causation problems -- presumably a variety of factors contributed\\n\\nto any individual foreclosure -- but the regression analysis that can isolate the\\n\\n\\n 61\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 62 of 76\\n\\n\\nimpact of redlining on the neighborhood scale could not solve this problem on the\\n\\nindividual level because of the diversity of individual circumstances.\\n\\n Moreover, even if homeowners were better-situated to vindicate the same\\n\\nwrongdoing -- and that is plainly not the case here -- the additional assumption that\\n\\nothers will pursue the lawsuits and achieve deterrence is nowhere near as likely\\n\\ntrue under the FHA as under the other statutes. Antitrust and, to a lesser extent,\\n\\ncivil RICO suits are typically brought by sophisticated business entities, often with\\n\\ndeep pockets, and those plaintiffs also have the added incentive of realizing treble\\n\\ndamages. In Holmes and Associated General Contractors, the Court left the job of\\n\\ndeterring statutory violations to broker-dealers and businesses using union labor.\\n\\nThese parties were subject to complex regulatory environments and undoubtedly\\n\\nhad counsel in place prepared to sue to vindicate their rights. Here, instead, the\\n\\nalternative plaintiffs are homeowners whose homes were foreclosed upon.\\n\\nCompared with the sophisticated parties involved in the RICO and antitrust cases,\\n\\nit seems far less likely that these injured parties could be counted on to file suit.\\n\\nWhile it’s possible that some might, it seems exceedingly unlikely that more than a\\n\\nhandful at most would do so, and we have seen precious little reason to believe that\\n\\nmany have. The vast majority of individual cases of discriminatory lending cases\\n\\nare left unpursued and unaddressed. In Associated General, the Court observed\\n\\nthat “[d]enying the [plaintiff] a remedy on the basis of its allegations in this case\\n\\n\\n 62\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 63 of 76\\n\\n\\n[was] not likely to leave a significant [statutory] violation undetected or\\n\\nunremedied.” 459 U.S. at 542. That’s less plausible here.\\n\\n As a result, the peculiarities surrounding the claims raised in this case make\\n\\nit distinct from an antitrust case where a mid-stream purchaser can bring\\n\\nessentially the same action against a monopolist as the ultimate consumer would.\\n\\nThe question of efficacy is harder to resolve here because, although the\\n\\nhomeowners are arguably closer in the chain, they are too numerous and diffuse to\\n\\nbe counted on for deterrence. They are better situated only in a narrow, literal\\n\\nsense. The City, on the other hand, has plausibly alleged an injury, calculable in\\n\\nthe aggregate, that bears a direct relation to the Banks’ policies, applied in the\\n\\naggregate, which allegedly violated the statute.\\n\\n 4.\\n\\n The Holmes factors also help cabin proximate cause against other less-\\n\\ndirectly injured plaintiffs. Writing separately in Bank of America, Justice Thomas\\n\\nsuggested that Miami’s theory of causation would require that neighboring\\n\\nhomeowners who were not foreclosed on but whose property values fell could also\\n\\nsue the banks. 137 S. Ct. at 1312 (Thomas, J., concurring in part and dissenting in\\n\\npart). Still other concerns have been raised about the corner grocer who may have\\n\\nlost business on account of foreclosures, the utility company, or maybe even real\\n\\nestate brokers working on commission to resell properties in the area. The Court’s\\n\\n\\n 63\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 64 of 76\\n\\n\\nown guidance from Holmes, attuned as it is to the administrative practicalities, can\\n\\ngo a long way toward allaying these concerns. Application of the Holmes factors\\n\\nreasonably establishes that the City’s injury is logically bound up with the Banks’\\n\\nalleged conduct in meaningful ways missing from injuries to these other putative\\n\\nclaimants.\\n\\n To begin with the first factor, corner grocers or neighboring property\\n\\nowners, unlike the City, would have substantially more difficulty plausibly\\n\\nalleging that they could calculate damages attributable to the Banks’ actions with a\\n\\nreasonable degree of certainty. By contrast, hedonic regression techniques are\\n\\nmost effective when applied on a neighborhood or citywide level, precisely\\n\\nbecause individual variations among homeowners average out when foreclosures\\n\\nare considered in the aggregate. Indeed the amended complaints specifically cite\\n\\nto a study showing that each foreclosure in Chicago was “responsible for an\\n\\naverage decline of approximately 1.1% in the value of each single-family home\\n\\nwithin an eighth of a mile.” BoA FAC at 33; WF FAC at 46. The average decline\\n\\ncan be used to calculate the impact of foreclosures on property value across a\\n\\nneighborhood on account of the large sample size. A neighboring homeowner, on\\n\\nthe other hand, would be affected only by homes closest to his own, and these\\n\\nmight not accurately reflect the citywide average, in terms of causation or value.\\n\\nAnd a corner grocer might be affected by the surrounding few blocks of homes, but\\n\\n\\n 64\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 65 of 76\\n\\n\\nthis may be wholly unrepresentative of citywide trends, making causal attribution\\n\\nto redlining all the more difficult.\\n\\n Put another way, in step-counting terms, the grocer or the utility company is\\n\\ndemonstrably further down the causal chain because many independent variables\\n\\ncan enter the equation after foreclosure occurs. The City will necessarily be\\n\\nharmed as soon as the foreclosures occur. For the grocer, though, a nearby home’s\\n\\nforeclosure does not necessarily mean anything. The causal chain for the grocer is\\n\\nlonger, more attenuated, and more of a problem for proximate cause analysis\\n\\nbecause there is a powerful discontinuity between the foreclosures and the grocer’s\\n\\nloss of profits. It would therefore be exceedingly difficult to trace causation from\\n\\nthe Banks’ predatory practices through the foreclosures to the grocers’ diminished\\n\\nprofits. The corner grocer, or the utility company, is not affected when a home is\\n\\nforeclosed or when property values go down. These parties are not hurt until\\n\\nindividual homeowners decide to spend less money at that grocer, decide not to\\n\\npay the electric bill, or move away. Thus, there are many more third parties, and\\n\\nmany more intervening steps when it comes to the corner grocer or the utility\\n\\ncompany. When a homeowner is given a bad, discriminatory loan, the injury to\\n\\none of these more distant plaintiffs is in no sense “automatic[],” Lexmark, 134 S.\\n\\nCt. at 1394; it therefore becomes harder to attribute back to the Banks.\\n\\n\\n\\n\\n 65\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 66 of 76\\n\\n\\n The application of the second Holmes factor also strongly suggests why any\\n\\ninjury sustained by the corner grocer or by the utility company would not be\\n\\nproximately caused by the Banks’ conduct. These are classic “passed on” injuries.\\n\\nThe Court has consistently said that “where the alleged violations [are] linked to\\n\\nthe asserted harms only through the [directly injured parties’] inability to meet\\n\\ntheir financial obligations” proximate cause will not be found. Anza, 547 U.S. at\\n\\n458; see also Lexmark, 1391 S. Ct. at 1391 (referencing “the electric company,”\\n\\nspecifically, as an entity in this sort of position); Holmes, 503 U.S. at 271.\\n\\nIndividual homeowners have financial obligations to the City in the form of\\n\\nproperty taxes, but the City’s claim is not that it is harmed because property taxes\\n\\nwent unpaid. Rather, the City says that property values decreased and that\\n\\ntherefore it was not entitled to as much property-tax revenue. The City’s loss is\\n\\nnot due to anyone lacking “the wherewithal to pay,” Holmes, 503 U.S. at 271, but\\n\\nto the fact that redlining means the City is not able to collect nearly as much as it\\n\\nwould have, had the alleged FHA violations not occurred in the first place.\\n\\n The third Holmes factor -- the reliability with which a plaintiff could remedy\\n\\nharm or achieve deterrence -- also strongly suggests that we need not fear a deluge\\n\\nof suits by grocers, neighbors, or power companies. These potential plaintiffs,\\n\\neven if injured, would be in a far weaker position and far less likely than the City\\n\\nto achieve deterrence or to remedy the entirety of the harm caused by the Banks’\\n\\n\\n 66\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 67 of 76\\n\\n\\nalleged violations. Their claims would be disjointed, aimed at remedying FHA\\n\\nviolations only on particular blocks, in contrast to the City’s unique ability to\\n\\nattack the Banks’ whole pattern or practice on a municipal level. Any claims by\\n\\nthe corner grocer or the neighboring homeowner would be further out in the chain\\n\\nof causation than the City is, and these claims would lack the broad scope that\\n\\nallows the City to achieve maximal deterrence. Quite simply, they would face far\\n\\ntougher versions of all the challenges the City faces, but with none of the offsetting\\n\\nadvantages.\\n\\n As we see it, the factors articulated by the Supreme Court in Holmes cabin\\n\\nthis decision and keep the floodgates closed. But these factors are not the only\\n\\nreason our ruling does not extend liability beyond what is reasonable.\\n\\nForeseeability remains a real part of the proximate cause calculation and also will\\n\\nfunction to cut off liability in many instances. Dan B. Dobbs, Paul T. Hayden &\\n\\nEllen M. Bublick, The Law of Torts § 199, at 686 (2d ed. 2011) (“The defendant\\n\\nmust have been reasonably able to foresee the kind of harm that was actually\\n\\nsuffered by the plaintiff . . . .”). We are exceedingly dubious that courts would\\n\\nexpect lenders to reasonably foresee unending ripples of harm that overwhelm the\\n\\njudicial branch.\\n\\n\\n\\n\\n 67\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 68 of 76\\n\\n\\n D. Common-law antecedents require direct relation\\n\\n The Court has also told us that the FHA’s common-law antecedents are a\\n\\nprimary reason why “proximate cause under the FHA requires ‘some direct\\n\\nrelation between the injury asserted and the injurious conduct alleged.’” Bank of\\n\\nAm., 137 S. Ct. at 1306. As a result, we know that “[a] damages claim under the\\n\\n[FHA] ‘is analogous to a number of tort actions recognized at common law,’” and\\n\\nthat “directness principles” thus apply. Id. We also observed, in our previous\\n\\nopinions, that FHA damages claims “have long been analogized to tort claims.”\\n\\nSee Bank of Am., 800 F.3d at 1282. These analogues, however, only take us so\\n\\nfar. They do not help flesh out the meaning of “direct relation,” even though they\\n\\nare the basis for imposing the requirement.\\n\\n The Court identified some common-law claims that are analogues for FHA\\n\\nclaims in Curtis v. Loether, 415 U.S. 189 (1973). See Bank of Am., 137 S. Ct. at\\n\\n1306 (citing Curtis for the proposition that an FHA damages claim is analogous to\\n\\ncertain common-law torts). There, the Court was evaluating whether the Seventh\\n\\nAmendment, which guarantees jury trials for “suits at common law,” guaranteed a\\n\\njury in an FHA suit. U.S. CONST. amend VII; see Curtis, 415 U.S. at 190. The\\n\\nCourt said it did, because FHA claims for housing discrimination were comparable\\n\\nto “the common-law duty of innkeepers not to refuse temporary lodging to a\\n\\n\\n\\n\\n 68\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 69 of 76\\n\\n\\ntraveler without justification,” “an action for defamation or intentional infliction of\\n\\nmental distress,” or “law[s] of insult and indignity.” Id. at 195 n.10.\\n\\n The identification of these common-law antecedents does not get us too far.\\n\\nWe lack any clear indication that Congress had these common-law claims in mind\\n\\nwhen drafting the FHA, and so we are reluctant draw too much from them beyond\\n\\nthe “some direct relation” requirement. For one thing, we would not know which\\n\\ncommon-law claim to begin with, since we do not see the obvious correspondence\\n\\nto the common law the Court has identified elsewhere. Thus, for example, this\\n\\ncase is not like Bridge where common-law mail fraud was an obvious precursor to\\n\\nRICO mail fraud. See Bridge, 553 U.S. at 652.\\n\\n Other statutory causes of action have more tangible foundations in particular\\n\\ncommon-law claims. The Court does not define what exactly counts as “common-\\n\\nlaw foundations” but RICO and the antitrust statutes are the paradigmatic\\n\\nexamples. See, e.g., Bridge, 533 U.S. at 651 (“[W]hen Congress established in\\n\\nRICO a civil cause of action for a person ‘injured . . . by reason of’ a\\n\\n‘conspir[acy],’ it meant to adopt . . . well-established common-law civil conspiracy\\n\\nprinciples” (quoting Beck v. Prupis, 529 U.S. 494, 504 (2000))); Holmes, 503 U.S.\\n\\nat 267 (“[C]ourts had read § 7 [of the Sherman Act] to incorporate common-law\\n\\nprinciples of proximate causation.”). In Anza v. Ideal Steel Supply Corp., 547\\n\\nU.S. 451, 457 (2006), a RICO case, the Court also said that “directness principles”\\n\\n\\n 69\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 70 of 76\\n\\n\\napply to statutes with “common-law foundations.” Bank of Am., 137 S. Ct. at\\n\\n1306 (quoting Anza, 547 U.S. at 457). Anza repeated reasoning from Holmes\\n\\ncomparing RICO’s civil suit provision to the Clayton Act’s. Anza, 547 U.S. at 457\\n\\n(citing Holmes, 503 U.S. at 267–68).\\n\\n The connection between the Clayton Act and RICO, laid out in Holmes, was\\n\\nfoundational for proximate cause analysis under RICO. See, e.g., Hemi Group,\\n\\n559 U.S. at 8–10 (citing Holmes, 503 U.S. 258); Bridge, 553 U.S. at 653–55\\n\\n(citing Holmes, 503 U.S. 258); Anza 547 U.S. at 457 (citing Holmes, 503 U.S. at\\n\\n267–68). In fact, RICO’s civil suit provision was modeled on the antitrust statutes\\n\\nof the early 20th century, so standards of proximate cause that applied to early\\n\\nClayton and Sherman Act cases can be readily applied to RICO as well. See\\n\\nHolmes, 503 U.S. at 268; see also Assoc. Gen. Contractors, 459 U.S. at 531–35.\\n\\nEven without a deep dive into legislative history, the connection between the\\n\\nstatutes is obvious because their civil suit provisions are almost identical. The\\n\\nClayton Act reads:\\n\\n [A]ny person who shall be injured in his business or property by reason\\n of anything forbidden in the antitrust laws may sue therefor . . . and\\n shall recover threefold the damages by him sustained, and the cost of\\n suit, including a reasonable attorney’s fee.\\n\\n15 U.S.C. § 15. Likewise, RICO reads:\\n\\n Any person injured in his business or property by reason of a violation\\n of section 1962 of this chapter may sue therefor in any appropriate\\n United States district court and shall recover threefold the damages he\\n\\n 70\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 71 of 76\\n\\n\\n sustains and the cost of the suit, including a reasonable attorney’s\\n fee . . . .\\n\\n18 U.S.C. § 1964(c). Both statutes thus say that “any person” “injured in his\\n\\nbusiness or property” by a violation of the statute has a cause of action and can\\n\\nrecover treble damages plus attorney’s fees.\\n\\n The common-law foundations of the Fair Housing Act are less obvious\\n\\ninsofar as they relate to proximate cause. For starters, the FHA does not employ\\n\\nthe language that the Clayton Act shares with RICO. It authorizes suit by an\\n\\n“aggrieved person,” 42 U.S.C. § 3613(a)(1)(A), expansively defined as “any\\n\\nperson who (1) claims to have been injured by a discriminatory housing practice;\\n\\nor (2) believes that such person will be injured by a discriminatory housing\\n\\npractice that is about to occur.” Id. § 3602(i). Indeed, under the language\\n\\nemployed by Congress in the FHA, the aggrieved person need not be injured\\n\\nspecifically “in his business or property.” Moreover, the remedies are distinct\\n\\nfrom the relief available for a violation of the Clayton Act or RICO -- treble\\n\\ndamages are not available, and the court “may allow” attorney’s fees, but under the\\n\\nFHA it is not required to, as it would be under RICO or the Clayton Act. See 42\\n\\nU.S.C. § 3613(c).\\n\\n These textual differences make it harder to assume that the legislators\\n\\ndrafting the FHA were drawing on the same version of proximate cause that was\\n\\nused in these earlier statutes. We are still able to borrow notions about proximate\\n\\n 71\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 72 of 76\\n\\n\\ncause from the common law for the FHA, but it strikes us as inappropriate simply\\n\\nto assume that the FHA necessarily incorporated the nature and form of proximate\\n\\ncause as it was employed in these other statutes for which we can trace a much\\n\\nmore direct provenance. And, since understandings of proximate cause at common\\n\\nlaw evolved over time, we would need to know which version of common–law\\n\\nproximate cause a statute adopted. See Sperino, supra, at 1225 (“The one thing\\n\\nthat is certain about proximate cause is that its underlying goals are contested and\\n\\nevolving.”). Different statutes may not have incorporated the same common-law\\n\\nstandard; the Palsgraf case and the First Restatement of Torts both postdated\\n\\npassage of the Sherman Act but had become highly foundational texts for\\n\\nunderstanding proximate cause by the time RICO was drafted. Id. The evolving\\n\\nshape of proximate cause at common law further complicates any analysis that\\n\\nwould depend entirely upon incorporating a common-law standard from a statute\\n\\nthat predated the FHA.\\n\\n Congress might have brought common-law standards to bear on the new\\n\\nproblems it addressed in the 1960s, but the fact that we may identify some\\n\\ncommon-law analogue does not necessarily mean that this was the case. The Fair\\n\\nHousing Act does not employ language drawn from the older federal statutes with\\n\\nconnections to the common law, and, as best as we can tell, this cause of action\\n\\ndoes not have an unmistakable common-law antecedent. As a result, while\\n\\n\\n 72\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 73 of 76\\n\\n\\nconsidering the common law may be valuable and informative, and while the\\n\\nstatute’s common-law antecedents do require a plaintiff plausibly to allege “some\\n\\ndirect relation,” we are unable to discern any further lessons from the common law\\n\\nthat bear on our analysis.\\n\\n IV. Conclusion\\n\\n In sum, we hold that there is “some direct relation” between the City’s tax-\\n\\nrevenue injuries and the Bank’s alleged violations of the FHA. The Supreme\\n\\nCourt has never held that the presence of an intervening causal step or the\\n\\ninvolvement of a third party necessarily bars a finding of proximate cause as a\\n\\nmatter of law, and we decline to establish so hard and fast a rule today.\\n\\n The City’s detailed allegations on its tax-revenue injury are sufficient for a\\n\\nvariety of reasons: the FHA is a broad and ambitious statute which employs a\\n\\nstandard of proximate cause that facilitates its operation; Congress meant for the\\n\\nFHA to be a big solution to a big problem -- housing segregation generated by\\n\\nintentional racial discrimination; for half a century courts have read the FHA\\n\\nbroadly and Congress has repeatedly assented to these readings; the impact of the\\n\\nBanks’ redlining can readily be identified at a citywide or neighborhood level, so\\n\\neven if there were not “something very close to a 1:1 relationship,” Lexmark, 134\\n\\nS. Ct. at 1394, the City has plausibly explained how it will calculate damages in a\\n\\nreasonably precise way; the injury is profoundly different from any injuries\\n\\n\\n 73\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 74 of 76\\n\\n\\nsuffered by a homeowner; and there’s no reason to think that homeowners would\\n\\nmake for more efficient plaintiffs. In the absence of any palpable concerns about\\n\\nunadministrable litigation, we ought not to unduly constrain the remedial effect of\\n\\nthe FHA.\\n\\n Put differently, the City has adequately pled proximate cause when it comes\\n\\nto its tax-base injury because the Banks’ redlining and reverse-redlining practices\\n\\nbear some direct relation to the City’s fiscal injuries. There is a logical and direct\\n\\nbond between discriminatory lending as a pattern and practice applied to\\n\\nneighborhoods throughout the City and the reduction in property values. Third\\n\\nparties are involved, but the harm to the City is not contingent on their actions\\n\\nwhen considered in the aggregate. There is no discontinuity between the violation\\n\\nand the harm. Bad loans in the aggregate will mean foreclosures in the aggregate,\\n\\nwhich will mean loss of property value and a reduction in the tax base. An\\n\\nindividual home might go under for a variety of causes, but when discriminatory\\n\\nlending practices pervade a neighborhood or a city, the city’s fisc will necessarily\\n\\nbe affected because we know some number of homes will go under, and some\\n\\nnumber of properties will lose value. When we consider the claimed violations\\n\\nand the injuries sustained in the aggregate -- that is, at the scale that the complaints\\n\\npresent them -- it becomes clearer that injuries to the city’s treasury are necessary,\\n\\ndirect, and immediate results of these kinds of FHA violations.\\n\\n\\n 74\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 75 of 76\\n\\n\\n By many of these same measures, however, the City’s increased municipal\\n\\nexpenditures injury fails, and so the district court was correct to find that proximate\\n\\ncause for this injury had not been adequately pled in the complaints it was\\n\\nreviewing. The City’s increased expenditures have not been plausibly presented as\\n\\ndirectly and automatically resulting from the Banks’ alleged conduct. Even though\\n\\nwe think foreclosures follow directly from the Banks’ conduct, there is too much\\n\\nopportunity in the causal chain between foreclosure and increased expenditures for\\n\\nintervening actors and causes to play a role, and there has been no explanation by\\n\\nthe City of how we might conceivably isolate the injury attributable to the Banks.\\n\\nThus we have identified this alleged injury as being too remote to satisfy proximate\\n\\ncause.\\n\\n We repeat that we have not answered every outstanding question in this\\n\\ncase. Much remains to be determined as the litigation proceeds, but this case is\\n\\nbefore this Court only on a motion to dismiss. It is not our role at this stage to\\n\\ndecide whether hedonic regression analysis can actually identify injuries\\n\\nattributable to violations with sufficient accuracy, or indeed whether the banks\\n\\nactually made decisions based on race as opposed to socioeconomic factors that\\n\\nmay correlate with race or with other considerations. Today we have done only\\n\\ntwo things. Broadly, we have worked out in some detail what proximate cause\\n\\nrequires in an FHA suit. More specifically, we have evaluated whether these\\n\\n\\n 75\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 76 of 76\\n\\n\\ncomplaints against these Banks plausibly allege that Miami’s injuries to its tax\\n\\nbase were directly related to the violations they describe. We simply find that the\\n\\noperative complaints explain in a plausible fashion how the claimed tax-revenue\\n\\ninjuries bear “some direct relation” to the misconduct that the City is challenging.\\n\\nThis harm to Miami, as pled, is not just foreseeable but, when measured in the\\n\\naggregate, is directly related to the pattern of unlawful behavior the City has\\n\\nalleged.\\n\\n The City has plausibly alleged a violation of the FHA and has stated a claim\\n\\nin its First Amended Complaints. Accordingly we conclude that the district court\\n\\nimprovidently dismissed the FHA claims in their entirety and ought to have\\n\\ngranted the City leave to amend its complaints, since amendation would not have\\n\\nbeen futile.12 The cases are remanded to the district court for further proceedings\\n\\nconsistent with this opinion.\\n\\n REVERSED and REMANDED\\n\\n\\n\\n\\n12\\n We leave it to the district court to determine which complaints should be operative for its\\npurposes, or whether to grant the City leave to file new ones. See supra n.2.\\n 76\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4393705/\", \"author_raw\": \"MARCUS, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"MARCUS"},"judge2":{"kind":"string","value":"WILSON"},"judge3":{"kind":"string","value":"SCHLESINGER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4616452/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: CITY OF MIAMI, a Florida Municipal Corporation, Plaintiff-Appellant, v. WELLS FARGO & CO., Wells Fargo Bank, N.A., Defendants-Appellees. City of Miami, a Florida Municipal Corporation, Plaintiff-Appellant, v. Bank of America Corporation, Bank of America, N.A., Countrywide Financial Corporation, Countrywide Home Loans, Countrywide Bank, FSB, Defendants-Appellees.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 14-14544 Date Filed: 05/03/2019 Page: 1 of 76\n\n\n [PUBLISH]\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 14-14544\n Non-Argument Calendar\n ________________________\n\n D.C. Docket No. 1:13-cv-24508-WPD\n\n\n\nCITY OF MIAMI,\na Florida municipal corporation,\n\n Plaintiff - Appellant,\n\nversus\n\nWELLS FARGO & CO.,\nWELLS FARGO BANK, N.A.,\n\n Defendants - Appellees.\n\n\n ________________________\n\n No. 14-14543\n Non-Argument Calendar\n ________________________\n\n D.C. Docket No. 1:13-cv-24506-WPD\n\n\n\nCITY OF MIAMI,\na Florida Municipal Corporation,\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 2 of 76\n\n\n Plaintiff - Appellant,\n\nversus\n\nBANK OF AMERICA CORPORATION,\nBANK OF AMERICA, N.A.,\nCOUNTRYWIDE FINANCIAL CORPORATION,\nCOUNTRYWIDE HOME LOANS,\nCOUNTRYWIDE BANK, FSB,\n\n Defendants - Appellees.\n\n ________________________\n\n Appeals from the United States District Court\n for the Southern District of Florida\n ________________________\n\n (May 3, 2019)\n\nBefore MARCUS and WILSON, Circuit Judges, and SCHLESINGER, * District\nJudge.\n\nMARCUS, Circuit Judge:\n\n This pair of ambitious fair housing lawsuits brought by the City of Miami\n\nagainst major financial institutions returns to our Court after having been appealed\n\nto the Supreme Court and resolved there in Bank of American Corp. v. City of\n\nMiami, 137 S. Ct. 1296 (2017). Miami alleges that, for years, the defendant\n\ninstitutions, major nationwide banks, carried on discriminatory lending practices\n\nthat intentionally targeted black and Latino Miami residents for predatory loans.\n\n\n*\n Honorable Harvey E. Schlesinger, United States District Judge for the Middle District of\nFlorida, sitting by designation.\n\n 2\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 3 of 76\n\n\nThe City says this resulted in disproportionate foreclosures on homeowners of\n\nthose races, diminished property values in predominantly minority neighborhoods,\n\nsubstantially reduced tax revenue for the City, and increased expenditures by the\n\nCity for municipal services. When we first heard these cases, we determined that\n\nMiami had standing under the Fair Housing Act, and that it had adequately pled\n\nproximate cause. See City of Miami v. Bank of Am. Corp., 800 F.3d 1262 (11th\n\nCir. 2015); City of Miami v. Wells Fargo & Co., 801 F.3d 1258 (11th Cir. 2015).\n\nThe Supreme Court agreed in part. It resolved the hotly contested standing issue in\n\nthe City’s favor, but vacated and remanded with regard to proximate cause. See\n\nBank of Am., 137 S. Ct. at 1305–06.\n\n The Court held that the standard that this panel had applied -- foreseeability -\n\n- was not enough on its own to demonstrate proximate cause. Id. at 1306. Instead,\n\nthe Court said that proximate cause under the FHA also required “some direct\n\nrelation between the injury asserted and the injurious conduct alleged.” Id. at 1306\n\n(quotations omitted). But the Court declined to “draw the precise boundaries of\n\nproximate cause under the FHA and to determine on which side of the line the\n\nCity’s financial injuries fall.” Id. It remanded the case, preferring to leave this\n\nissue open for percolation in the lower courts. See id. Today, we take up the\n\nquestion of how the principles of proximate cause identified by the Court’s opinion\n\n\n\n\n 3\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 4 of 76\n\n\nfunction when applied to the FHA and to the facts as alleged in the City’s\n\ncomplaints.\n\n At this preliminary stage in the lawsuit, we conclude that the City has\n\nadequately pled proximate cause in relation to some of its economic injuries when\n\nthe pleadings are measured against the standard required by the Fair Housing Act.\n\nProximate cause asks whether there is a direct, logical, and identifiable connection\n\nbetween the injury sustained and its alleged cause. If there is no discontinuity to\n\ncall into question whether the alleged misconduct led to the injury, proximate\n\ncause will have been adequately pled. The question for now is whether, accepting\n\nthe allegations as true, as we must, the City has said enough to make out a\n\nplausible case -- not whether it will probably prevail. Considering the broad and\n\nambitious scope of the FHA, the statute’s expansive text, the exceedingly detailed\n\nallegata found in the complaints, and the application of the administrative\n\nfeasibility factors laid out by the Supreme Court in Holmes v. Securities Investor\n\nProtection Corp., 503 U.S. 258 (1992), we are satisfied that the pleadings set out a\n\nplausible claim.\n\n The City’s pleadings meet this standard because Miami has alleged a\n\nsubstantial injury to its tax base that is not just reasonably foreseeable, but also is\n\nnecessarily and directly connected to the Banks’ conduct in redlining and reverse-\n\nredlining throughout much of the City. This injury plausibly bears “some direct\n\n\n 4\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 5 of 76\n\n\nrelation” to the claimed misconduct. Bank of Am., 137 S. Ct. at 1306. The injury\n\nto the City’s tax base is uniquely felt in the City treasury, and there is no risk that\n\nduplicative injuries could be pled by another plaintiff or that the apportionment of\n\ndamages amongst different groups of plaintiffs would be a problem. As we see it,\n\nthe City is in the best position. Indeed only the City can allege and litigate this\n\npeculiar kind of aggregative injury to its tax base. Simply put, a lawsuit\n\ncommenced by an individual homeowner cannot challenge the Banks’ policies on\n\nthe same citywide scale that the alleged misconduct took place on.\n\n However, the City’s pleadings fall short of sufficiently alleging “some direct\n\nrelation” between the Banks’ conduct and a claimed increase in expenditures on\n\nmunicipal services. The complaints fail to explain how these kinds of injuries --\n\nincreases in police, fire, sanitation, and similar municipal expenses -- are anything\n\nmore than merely foreseeable consequences of redlining and reverse-redlining.\n\nThe Court has told us that foreseeability alone is not enough.\n\n We do not mean to suggest that the City’s claims are destined to succeed.\n\nMany questions, and many difficult questions, remain and will have to be worked\n\nout in the district court. At the motion to dismiss stage, though, we are not asking\n\nwhether the complaints meet any probability requirement, only whether they\n\nplausibly allege violations of the FHA. Since we have found that they do, we\n\nallow this discrete portion of the City’s claims to proceed for now. The plaintiff\n\n\n 5\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 6 of 76\n\n\nhas said enough to get into the courthouse and be heard. We decide nothing more\n\ntoday.\n\n I. Background\n\n A. The City’s Claims\n\n On December 13, 2013, the City of Miami brought three complex civil\n\nrights actions in the Southern District of Florida against several different financial\n\ninstitutions. One suit was filed against Bank of America Corporation, Bank of\n\nAmerica N.A., Countrywide Financial Corporation, Countrywide Home Loans,\n\nand Countrywide Bank, FSB (collectively “Bank of America”), and another\n\nagainst Wells Fargo & Co. and Wells Fargo Bank, N.A. (collectively “Wells\n\nFargo”). For simplicity, we refer to all these defendants jointly as “the Banks.”\n\nThese were accompanied by another similar case against Citigroup, Inc. and\n\nrelated institutions. See City of Miami v. Citigroup, Inc., 801 F.3d 1268 (11th Cir.\n\n2015). The first time this panel considered this set of cases, we heard the Citigroup\n\ncase as well, but that case was not appealed to the Supreme Court. It has returned\n\nto the district court, where it has been stayed pending resolution of the other two.\n\nSee Order Staying Case Pending the Supreme Court’s Disposition of Matters Now\n\nBefore the Court, City of Miami v. Citigroup Inc., No. 13-cv-24510 (S.D. Fla. July\n\n13, 2016). As a result, our opinion today concerns only Bank of America and\n\nWells Fargo.\n\n\n 6\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 7 of 76\n\n\n The City alleged in considerable detail that the Banks had violated § 3604(b)\n\nand § 3605(a) of the Fair Housing Act. The first of these provisions makes it\n\nunlawful “[t]o discriminate against any person in the terms, conditions, or\n\nprivileges of sale or rental of a dwelling, or in the provision of services or facilities\n\nin connection therewith, because of race, color, religion, sex, familial status, or\n\nnational origin.” 42 U.S.C. § 3604(b). The second states that “[i]t shall be\n\nunlawful for any person or other entity whose business includes engaging in\n\nresidential real estate–related transactions to discriminate against any person in\n\nmaking available such a transaction, or in the terms or conditions of such a\n\ntransaction, because of race, color, religion, sex, handicap, familial status, or\n\nnational origin.” Id. § 3605(a). The City alleged that the Banks had violated these\n\nprovisions by intentionally engaging in discriminatory mortgage lending practices\n\nthat resulted in a disproportionate and excessive number of defaults by black and\n\nLatino homebuyers and caused substantial financial harm to the City. 1\n\n\n1\n The City also alleged that the Banks unjustly enriched themselves by taking advantage of\n“benefits conferred by the City” at the same time that they engaged in unlawful lending practices\nwhich “denied the City revenues it had properly expected through property and other tax\npayments and . . . cost[] the City additional monies for services it would not have had to\nprovide . . . absent [the Bank’s] unlawful activities.” Wells Fargo, 801 F.3d at 1261 (quoting\nComplaint for Violations of the Federal Fair Housing Act at 61, City of Miami v. Wells Fargo &\nCo., No. 13-24508-CIV (S.D. Fla. July 9, 2014), 2013 WL 6903725); Bank of Am., 800 F. 3d at\n1267; see also Complaint for Violations of the Federal Fair Housing Act at 52–55, City of Miami\nv. Bank of Am. Corp., No. 13-24506-CIV (S.D. Fla. July. 9, 2014), 2013 WL 6903721 (raising\nthe same claims and allegations). The district court held that these claims failed. City of Miami\nv. Bank of Am., No. 13-24506-CIV, 2014 WL 3362348 at *6–7 (S.D. Fla. July 9, 2014). We\naffirmed, Bank of Am., 800 F.3d at 1287; Wells Fargo, 801 F.3d at 1267, and the City did not\nappeal these claims to the Supreme Court. Accordingly, they are no longer in this case.\n 7\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 8 of 76\n\n\n The City said the Banks made a practice of systematically and intentionally\n\nrefusing to extend credit to minority borrowers on the same terms as they would\n\nextend credit to non-minority borrowers and, when they did extend credit to\n\ncomparably situated minority borrowers, doing so only on predatory terms, worse\n\nthan the terms non-minorities received. First Amended Complaint for Violations\n\nof the Federal Fair Housing Act at 2–5, City of Miami v. Bank of Am., No. 13-cv-\n\n24506 (S.D. Fla. Sept. 9, 2014) (“BoA FAC”); First Amended Complaint for\n\nViolations of the Federal Fair Housing Act at 2–5, City of Miami v. Wells Fargo &\n\nCo., No. 13-cv-24508 (S.D. Fla. Sept. 9, 2014) (“WF FAC”). 2 This amounted to\n\n\n\n2\n The operative complaints for our purposes are the First Amended Complaints in both cases. As\nwe explain, infra, the City appealed the denial of motions in both cases asking the district court\nto reconsider the dismissal of its initial Complaints and to grant leave to file the First Amended\nComplaints. After this panel reversed the decisions in September 2015, litigation proceeded in\nthe district court for some months before the Supreme Court granted the Banks’ petitions for\ncertiorari in June 2016. On remand from this Court, the City filed what it styled “Second\nAmended Complaints,” (even though the First Amended Complaints had not technically been\nfiled), and both of these were dismissed on multiple grounds, but with leave to amend. Order\nGranting Motion to Dismiss Second Amended Complaint, Bank of Am., No. 13-cv-24506 (Mar.\n17, 2016) (No. 98); Order Granting Motion to Dismiss Second Amended Complaint, Wells\nFargo, No. 13-cv-24508 (Mar. 17, 2016) (No. 77). By the time the Supreme Court granted the\npetition for certiorari, the City had filed Third Amended Complaints, and both Banks had moved\nto dismiss these as well. See Defendants’ Motion to Dismiss Third Amended Complaint with\nPrejudice and Request for Hearing, Bank of Am., No. 13-cv-24506 (May 16, 2016) (No. 103);\nWells Fargo’s Motion to Dismiss with Prejudice the City’s Third Amended Complaint and\nRequest for Hearing, Wells Fargo, No. 13-cv-24508 (May 24, 2016) (No 83). Both cases were\nthen stayed pending resolution in the Supreme Court. Order Staying Case Pending the Supreme\nCourt’s Disposition of Matters Now Before the Court, Bank of Am., No. 13-cv-24506 (July 13,\n2016) (No. 128); Order Granting Unopposed Motion to Stay Further Proceedings Pending the\nSupreme Court’s Disposition of Matters Now Before the Court, Wells Fargo, No. 13-cv-24508\n(July 13, 2016) (No. 102). Since nothing had been appealed since the Second and Third\nAmended Complaints were filed, the Supreme Court was explicit that it was looking to the First\nAmended Complaints, see Bank of Am., 137 S. Ct. at 1301, and we do the same on remand.\n 8\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 9 of 76\n\n\nboth “redlining” (refusing to extend credit) and “reverse redlining” (extending\n\ncredit on worse terms). Black and Latino borrowers were thus unable to refinance\n\ntheir loans effectively. BoA FAC at 4; WF FAC at 4; see also Wells Fargo, 801\n\nF.3d at 1261; Bank of Am., 800 F. 3d at 1267. The City’s complaints detailed at\n\nconsiderable length the nature of these practices and characterized them as\n\n“abusive” because they resulted in loans with “unfair terms that [borrowers] could\n\nnot afford.” BoA FAC at 13; WF FAC at 11; see, e.g., BoA FAC at 22 (explaining\n\nwhat kinds of loans the City would categorize as “predatory”); WF FAC at 34\n\n(same).\n\n The City claims that these policies were entirely deliberate on the part of the\n\nBanks. The Amended Complaints explain that confidential witnesses -- former\n\nemployees at both Bank of America and Wells Fargo -- will testify to how\n\nminorities and residents of minority neighborhoods were targeted for predatory\n\nloan terms. E.g., BoA FAC at 19; WF FAC at 29. Moreover, witnesses allegedly\n\nwill testify that Wells Fargo specifically targeted Latino and African American\n\ncommunity groups and churches (but never white churches) and that employees\n\nwere assigned based on their race to make presentations to these groups. WF FAC\n\nat 30. Witnesses from Bank of America likewise will testify that they were\n\nencouraged to steer less financially savvy borrowers, often racial minorities,\n\ntoward loan products that were decidedly unfavorable to the customer and different\n\n\n 9\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 10 of 76\n\n\nfrom loan products offered to white applicants, but highly favorable to the bank.\n\nBoA FAC at 19–20.\n\n According to the City, all of this violated the FHA in two stages. To start,\n\nthe Banks intentionally discriminated against minority borrowers by targeting them\n\nfor burdensome loans. This had a disparate impact on minority borrowers, leading,\n\ndown the line, to a disproportionate number of exploitative loans in minority\n\nneighborhoods and, eventually, to a disproportionate number of foreclosures on\n\nminority-owned properties. BoA FAC at 15–19; WF FAC at 21–29.\n\n The City employed detailed regression analyses of the Banks’ self-reported\n\ndata to show that a Bank of America loan in a predominantly African-American or\n\nLatino Miami neighborhood was 5.857 times more likely to result in foreclosure\n\nthan a Bank of America loan in a non-minority Miami neighborhood. BoA FAC at\n\n26. For a minority-neighborhood loan from Wells Fargo, foreclosure was 6.975\n\ntimes more likely. WF FAC at 39. Further calculations indicated that, controlling\n\nfor credit history and other factors, a black Miami borrower was 1.581 times more\n\nlikely than a white borrower to receive a predatory loan from Bank of America and\n\n4.321 times more likely to receive one from Wells Fargo. BoA FAC at 22; WF\n\nFAC at 34. A Latino borrower was 2.087 times more likely to receive such a loan\n\nfrom Bank of America and 1.576 times more likely to receive one from Wells\n\nFargo. BoA FAC at 22; WF FAC at 34. Notably, even among borrowers with\n\n\n 10\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 11 of 76\n\n\ngood credit (FICO scores over 660), black borrowers were 1.533 and 2.572 times\n\nmore likely to receive a predatory loan from Bank of America and Wells Fargo,\n\nrespectively. BoA FAC at 22; WF FAC at 34. For Latino borrowers with good\n\ncredit, the figures were 2.137 and 1.875 times more likely. BoA FAC at 22; WF\n\nFAC at 34. The City identified similar disproportionalities on a larger scale by\n\ncomparing predominantly white neighborhoods with predominantly minority ones.\n\nSee BoA FAC at 23–25; WF FAC at 35–37.\n\n The complaints further alleged that the Banks’ lending practices resulted in\n\nminority borrowers suffering especially fast and frequent foreclosures, an\n\nimportant indicator of predatory lending practices. See BoA FAC at 29–30; WF\n\nFAC at 41. White borrowers’ average time from origination to foreclosure was\n\n3.448 years for a Bank of America loan or 3.266 years for a Wells Fargo loan; for\n\nblack and Latino borrowers the averages were 3.144 (black) and 3.090 (Latino)\n\nyears from Bank of America and 2.996 (both black and Latino) from Wells Fargo.\n\nBoA FAC at 28; WF FAC at 41. Confidential witnesses from both Banks will\n\nallegedly support the claims that each had deliberately targeted black and Latino\n\nborrowers for predatory loans. E.g., BoA FAC at 19–21; WF FAC at 30–31.\n\n What’s more, according to the complaints, the Banks’ misconduct was not\n\nlimited to loan origination but instead continued almost to the point of foreclosure.\n\nAs the Supreme Court noted, Bank of Am., 137 S. Ct. at 1301, the predatory\n\n\n 11\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 12 of 76\n\n\npractices alleged by the City included denying black and Latino customers\n\nopportunities to refinance or make loan modifications on fair terms. E.g. BoA\n\nFAC at 21; WF FAC at 32. According to the complaints, both Banks would cause\n\nforeclosures when “a minority borrower who previously received a predatory loan\n\nsought to refinance the loan, only to discover that [the bank] refused to extend\n\ncredit at all,” or refused to do so on the same terms they extended when\n\n“refinancing similar loans issued to white borrowers.” BoA FAC at 4; WF FAC at\n\n4. We note that such refinancing and loan modification decisions can occur before\n\nor after a property enters default.\n\n The City alleged that it suffered both economic and noneconomic injuries.\n\nBoA FAC at 31–35; WF FAC at 44–48. In both complaints the alleged\n\nnoneconomic injury was that the Banks’ conduct “adversely impacted the racial\n\ncomposition of the City and impaired the City’s goals to assure racial integration\n\nand desegregation and the social and professional benefits of living in an integrated\n\nsociety.” 3 BoA FAC at 31; WF FAC at 44. The City identified two forms of\n\neconomic injuries. It claimed damages from each bank based on reduced property\n\ntax revenues, arguing that the Banks’ lending policies caused minority-owned\n\n\n\n3\n Because we find that the City adequately pled proximate cause for one of its economic injuries,\nwe need not evaluate whether it also did so for its noneconomic injuries. The parties in their\nbriefing have not squarely addressed these injuries, and the Supreme Court had little to say about\nthem. We leave this matter to the district court to address in the first instance.\n\n 12\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 13 of 76\n\n\nproperties to fall into unnecessary or premature foreclosure, causing them to lose\n\nsubstantial value and, in turn, decreasing the values of surrounding properties.\n\nBoA FAC at 32–34; WF FAC at 45–47. This reduced the City’s tax base and the\n\ntax revenue it took in. According to the City, “Hedonic regression” techniques\n\ncould be used to quantify with considerable particularity what portion of its losses\n\nwas attributable to the Banks’ conduct. BoA FAC at 32–34; WF FAC at 45–47.\n\nAdditionally, the City claimed damages based on the cost of the increased\n\nmunicipal services it provided to deal with problems attributable to the foreclosed\n\nand often vacant properties -- including police, firefighters, building inspectors,\n\ndebris collectors, and others. These increased services too, the City claimed,\n\nwould not have been necessary if the properties had not been foreclosed upon as a\n\nresult of the Banks’ discriminatory lending practices. BoA FAC at 34–35; WF\n\nFAC at 47–48.\n\n The City also asked for a declaratory judgment stating that the Banks’\n\nconduct violated the FHA, an injunction barring the Banks from engaging in\n\nsimilar predatory conduct, compensatory and punitive damages, and attorneys’\n\nfees. BoA FAC at 40–41; WF FAC at 53–54.\n\n\n\n\n 13\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 14 of 76\n\n\n B. District Court and 11th Circuit Decisions\n\n On July 9, 2014, the district court granted motions to dismiss by both\n\nbanks. 4 City of Miami v. Bank of Am., No. 13-24506-CIV, 2014 WL 3362348\n\n(S.D. Fla. July 9, 2014). The court determined first that the City lacked standing\n\nbecause, according to this Court’s opinion in Nasser v. City of Homewood, 671\n\nF.2d 432 (11th Cir. 1982), its claims fell outside the “zone of interests” protected\n\nby the FHA. Bank of Am., 2014 WL 3362348 at *3–4. Miami had alleged\n\n“merely economic injuries” that were not “affected by a racial interest.” Id. at *4.\n\nThe trial court also determined that the FHA contained a proximate cause\n\nrequirement, and that this requirement had not been met because the City failed to\n\n“demonstrate that the [Banks’] alleged redlining and reverse redlining caused the\n\nforeclosures to occur.” Id. at *5. According to the district court, the City should\n\nhave “allege[d] facts that isolate [the Banks’] practices as the cause of any alleged\n\nlending disparity.” Id. Additionally, the district court said that the FHA claims fell\n\noutside the statute of limitations. Id. at *6–7.\n\n The City moved for reconsideration and for leave to file amended\n\ncomplaints in both cases, arguing that it had standing and that it could remedy the\n\nstatute of limitations issue by amending the complaint. See Bank of Am., 800 F.3d\n\n\n4\n The court issued a detailed opinion in the Bank of America case. It then adopted and incorporated\nthat opinion in the Wells Fargo case. City of Miami v. Wells Fargo & Co., No. 13-24508-CIV\n(S.D. Fla. July 9, 2014).\n\n 14\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 15 of 76\n\n\nat 1271; Wells Fargo, 801 F.3d at 1264. The amended complaints added further\n\ndetails concerning noneconomic injuries suffered by the City as a result of the\n\nBanks’ discriminatory lending practices. See BoA FAC at 31; WF FAC at 44.\n\nThe City also argued in its amended complaints that predatory lending had\n\n“adversely impacted the racial composition of the City,” “impaired the City’s goals\n\nto assure racial integration and desegregation,” and “frustrate[d] the City’s\n\nlongstanding and active interest in securing the benefits of an integrated\n\ncommunity.” BoA FAC at 31; WF FAC at 44. The district court denied the\n\nmotion, and the City appealed to this Court. Bank of Am., 800 F.3d at 1271; Wells\n\nFargo, 801 F.3d at 1265.\n\n We reversed and remanded in a series of opinions, the most detailed of\n\nwhich we issued in City of Miami v. Bank of America Corp., 800 F.3d 1262 (11th\n\nCir. 2015). We began by addressing standing and held that the City had alleged an\n\ninjury in fact sufficiently concrete and immediate to confer Article III standing. Id.\n\nat 1272. Next we addressed “statutory standing” -- a misnomer, since it really\n\nconcerns “whether the plaintiff has a cause of action under the statute.” Id. at 1273\n\n(quotation omitted). We determined that this plaintiff did because the key statutory\n\nlanguage “swe[pt] as broadly as allowed under Article III” and placed the City\n\nwithin the statute’s zone of interests. Id. at 1278; see also Trafficante v. Metro\n\n\n\n\n 15\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 16 of 76\n\n\nLife Ins. Co., 409 U.S. 205, 209 (1972) (identifying “a congressional intention to\n\ndefine [FHA] standing as broadly as is permitted by Article III”).\n\n We next held that the FHA did require proximate cause, but that the City’s\n\npleadings were adequate. Bank of Am., 800 F.3d at 1279–80, 1283. We rejected\n\nthe idea that the City needed to “allege that the [Banks’] actions directly harmed\n\nthe City.” Id. As we saw it, the “strict directness requirement” suggested by the\n\nBanks could not be the proper standard for the FHA because it “would run afoul of\n\nSupreme Court and Eleventh Circuit caselaw allowing entities who have suffered\n\nindirect injuries . . . to bring a claim under the FHA.” Bank of Am., 800 F.3d at\n\n1281 (citing Gladstone, Realtors v. Village of Bellwood, 441 U.S. 91, 109–11\n\n(1979) (allowing a village to sue a firm for discriminatory practices that caused\n\nsegregation); Havens Realty Corp. v. Coleman, 455 U.S. 363, 378–79 (1982)\n\n(allowing suit by a non-profit for “impairment of its organizational mission” and\n\n“drain on its resources”); Baytree of Inverrary Realty Partners v. City of\n\nLauderhill, 873 F.2d 1407, 1408–09 (11th Cir. 1989) (allowing a non-minority\n\ndeveloper to challenge a zoning decision as discriminatory)). Proximate cause, we\n\nsaid, was “not a one-size fits-all analysis.” Id. Rather, it “can differ statute by\n\nstatute.” Id.\n\n Instead, noting the Supreme Court’s “broad and inclusive” readings of the\n\nFHA, e.g., Trafficante, 409 U.S. at 209, we agreed with the City that the proper\n\n\n 16\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 17 of 76\n\n\nstandard for proximate cause was “foreseeability.” Id. at 1281–82. Damages\n\nclaims under the FHA were analogous to tort claims, we reasoned, and tort law had\n\ntraditionally relied on foreseeability as the standard by which to evaluate causal\n\nrelationships and to limit the expansion of liability. See id. at 1282. The City had\n\nmet this standard; “it claim[ed] that the [Banks’] discriminatory lending caused\n\nproperty owned by minorities to enter premature foreclosure, costing the City tax\n\nrevenue and municipal expenditures.” Id. at 1282. We said that “[a]lthough there\n\nare several links in that causal chain, none are unforeseeable,” and also noted that\n\nthe regression analyses in the complaints made the pleadings more than just\n\nspeculative. Id. We made no comment, though, on “whether the City will be able\n\nto actually prove its causal claims.” Id. at 1283 (emphasis added). That would be\n\nworked out in the district court on a factual basis far beyond the four corners of the\n\ncomplaint. Accordingly, we remanded the case. Id. at 1289.\n\n Bank of America and Wells Fargo each filed petitions for certiorari, which\n\nthe Supreme Court granted. It consolidated the two cases.\n\n C. Supreme Court Decision\n\n The Supreme Court began by resolving the “statutory standing” question of\n\nwhether the City had a cause of action under the FHA. Bank of Am., 137 S. Ct. at\n\n1302–05. The Court agreed that its previous cases had interpreted the statute\n\nbroadly for standing purposes. See id. Congress had even amended the statute\n\n\n 17\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 18 of 76\n\n\nafter these decisions, without making any change to the relevant language,\n\nindicating its assent to the Court’s expansive reading of the original text. Id. at\n\n1303–04.\n\n On proximate cause, though, the Supreme Court disagreed with this panel\n\nbut reached no firm conclusions. It determined that foreseeability, standing alone,\n\nwas not a sufficiently rigorous standard. See id. at 1306 (“[T]he Eleventh Circuit\n\nerred in holding that foreseeability is sufficient to establish proximate cause under\n\nthe FHA.”). The Court explained that “foreseeability alone does not ensure the\n\nclose connection that proximate cause requires.” Id. Since lending and housing\n\npolicies are deeply interconnected with “economic and social life,” the Court said\n\nthat “[a] violation of the FHA may . . . ‘be expected to cause ripples of harm to\n\nflow’ far beyond the defendant’s misconduct.” Id. (quoting Assoc. Gen.\n\nContractors of Cal., Inc. v. Carpenters, 459 U.S. 519, 534 (1983)). Since\n\n“[n]othing in the statute suggests that Congress intended to provide a remedy\n\nwherever those ripples travel,” foreseeability alone could not be enough. Id.\n\n While the Court was clear that foreseeability was not enough, it was less\n\ndefinitive when it came to laying out what more FHA proximate cause required.\n\nIts key instructions were these:\n\n Rather [than foreseeability], proximate cause under the FHA requires\n “some direct relation between the injury asserted and the injurious\n conduct alleged.” Holmes v. Sec. Investor Protect. Corp., 503 U.S. 258,\n 268 (1992). A damages claim under the statute “is analogous to a\n 18\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 19 of 76\n\n\n number of tort actions recognized at common law,” Curtis v. Loether,\n 415 U.S. 189, 195 (1974), and we have repeatedly applied directness\n principles to statutes with “common-law foundations,” Anza v. Ideal\n Steel Supply Corp., 547 U.S. 451, 457 (2007). “The general tendency”\n in these cases is, “in regard to damages at least, is not to go beyond the\n first step.” Hemi Grp., LLC v. City of New York, 559 U.S. 1, 10\n (2010). What falls within that “first step” depends in part on the “nature\n of the statutory cause of action,” Lexmark Int’l, Inc. v. Static Control\n Components, Inc., 134 S. Ct. 1377, 1390 (2014), and an assessment “of\n what is administratively possible and convenient,” Holmes, 503 U.S. at\n 268.\n\nBank of Am., 137 S. Ct. at 1306 (citation formats altered).\n\n The Court remanded for further proceedings, stating that “[t]he lower courts\n\nshould define, in the first instance, the contours of proximate cause under the FHA\n\nand decide how that standard applies to the City’s claims for lost property-tax\n\nrevenue and increased municipal expenses.” Id. Lacking “the benefit of [the\n\nEleventh Circuit’s] judgment” on how to apply the principles it had laid out, and\n\nwith no other circuits having weighed in yet, the Court “decline[d]” to speak first.\n\nId.\n\n In this opinion, we endeavor carefully to apply the Court’s mandate to these\n\ncomplaints, to determine if they plausibly state a claim under the Fair Housing Act.\n\n II. Standard of Review\n\n We review a district court’s decision to dismiss a complaint de novo\n\n“accepting the factual allegations in the complaint as true and construing them in\n\nthe light most favorable to the plaintiff.” Boyd v. Warden, Holman Corr. Facility,\n\n\n 19\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 20 of 76\n\n\n856 F.3d 853, 863–64 (11th Cir. 2017); see also Ashcroft v. Iqbal, 556 U.S. 662,\n\n678 (2009). Here, the district court also denied leave to amend, which we\n\ngenerally review for abuse of discretion; however, when, as here, leave to amend\n\nwas denied “on the grounds of futility,” we review the denial de novo “because it\n\nis a conclusion of law that an amended complaint would necessarily fail.” Id. (“An\n\namendment is considered futile when the claim, as amended, would still be subject\n\nto dismissal.”). Essentially, then, we must consider de novo whether the City’s\n\namended complaints, which the district court declined to entertain, have stated a\n\nclaim. This is in line with the review conducted by the Supreme Court, Bank of\n\nAm., 137 S. Ct. at 1302, and with our review when we first heard these cases,\n\nBank of Am., 800 F.3d at 1271.\n\n For this case to proceed past a motion to dismiss, we need not find that the\n\nBanks’ actions in fact proximately caused the plaintiff’s injuries; we must find that\n\nthe City plausibly alleged that they did so. We evaluate whether each complaint\n\n“contain[s] sufficient factual matter . . . to ‘state a claim to relief that is plausible\n\non its face.’” Iqbal, 556 U.S. at 678 (quoting Bell Atlantic Corp. v. Twombly, 550\n\nU.S. 544, 570 (2007)). The standard is “plausibility”; it is decidedly not a\n\n“probability requirement.” Id. Still, plausibility requires that allegations push past\n\nthe line of showing “a sheer possibility” and “[w]here a complaint pleads facts that\n\nare ‘merely consistent with’ a defendant’s liability, it ‘stops short of the line\n\n\n 20\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 21 of 76\n\n\nbetween possibility and plausibility of entitlement to relief.’” Id. (quoting\n\nTwombly, 550 U.S. at 557). Facts are taken as true so long as they are not a\n\n“formulaic recitation of the elements” or “conclusory.” Id. at 681 (quoting\n\nTwombly, 550 U.S. at 555).\n\n III. Analysis\n\n Prosser and Keeton observed, of proximate cause, that “[t]here is perhaps\n\nnothing in the entire field of law which has called forth more disagreement, or\n\nupon which the opinions are in such a welter of confusion.” W. Page Keeton et al.,\n\nProsser and Keeton on the Law of Torts § 41, at 263 (5th ed. 1984). The Supreme\n\nCourt has not directed the lower courts to propose a sweeping standard for\n\nproximate cause that would apply across all cases or to define the word “direct” for\n\nall time. Indeed, we are not looking for (and could not find) “a black-letter rule\n\nthat will dictate the result in every case.” Holmes, 503 U.S. at 272 n.20. Rather,\n\nwe must evaluate where, as a matter of judicial economy and policy, we ought to\n\ndraw the line for this particular cause of action and these particular claims. As the\n\nCourt has said, proximate cause “label[s] generically the judicial tools used to limit\n\na person’s responsibility for the consequences of that person’s own acts. . . .\n\n[P]roximate cause reflects ideas of what justice demands, or of what is\n\nadministratively possible and convenient.” Id. at 268 (quotation omitted).\n\n\n\n\n 21\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 22 of 76\n\n\n We begin our analysis, then, with the Supreme Court’s instructions.\n\nProximate cause under the FHA certainly requires foreseeability, which is present\n\nhere but is not enough. See Bank of Am. 137 S. Ct. at 1305–06. Proximate cause\n\nalso requires “some direct relation between the injury asserted and the injurious\n\nconduct alleged.” Id. at 1306 (quoting Holmes, 503 U.S. at 268). Our task today\n\nis to determine what plaintiffs must do in order to plausibly allege “some direct\n\nrelation” and to evaluate whether the City’s complaints have met that standard.\n\n At the outset, we consider the central phrase “some direct relation.” There is\n\ngive in the joints between “some direct relation” and “some direct causation.”\n\nThese are not identical concepts, and so when, for example, Bank of America\n\nsuggests that Miami’s injuries “were not caused ‘directly’ by a loan,” it may not be\n\npresenting the question in a way that precisely and accurately reflects the Court’s\n\ninstruction. We might agree that the injuries were not “caused directly by a loan”\n\nand yet still find “some direct relation” between the injury and the statutory\n\nviolations. Causation is “the act or process of causing,” and to “cause” something\n\nis “to serve as cause or occasion of” or “to bring [it] into existence.” Webster’s\n\nThird New International Dictionary 356 (2002). Relation, on the other hand is “the\n\nmode in which one thing or entity stands to another, itself, or others,” or “a logical\n\nbond.” Id. at 1916. We are considering “direct relation,” as a critical aspect of\n\n“proximate cause,” so some palpable causation is required. We ought not forget,\n\n\n 22\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 23 of 76\n\n\nthough, that foreseeability, while insufficient on its own, remains a requirement\n\nand ensures some causal connection. “Some direct relation,” then, works to\n\nguarantee that there is a “logical bond” between violation and injury. Put another\n\nway, while foreseeability ensures “cause,” “some direct relation” ensures that the\n\ncause is sufficiently “proximate.”\n\n Further, the law requires “some direct relation” not any quantifiable amount\n\nof it. The standard is softened by the modifier “some,” meaning, “of an\n\nunspecified but appreciable or not inconsiderable quantity, amount, extent or\n\ndegree.” Id. at 2171. The requirement is therefore somewhat easier to meet than if\n\nthe Court had said we needed to find “a direct relation.”\n\n We are also aware that our analysis must be tied to the Fair Housing Act in a\n\nspecific way. The Supreme Court twice emphasized that the policy judgments that\n\nshape our proximate cause analysis will necessarily depend on the FHA. For\n\nstarters, “what falls within [the] ‘first step,’” to which proximate cause is\n\n“general[ly]” constrained, will “depend[] in part on the ‘nature of the statutory\n\ncause of action.’” Bank of Am., 137 S. Ct. at 1306. Second, our task is to “define,\n\nin the first instance, the contours of proximate cause under the FHA and” to apply\n\nthat standard to the City’s claims. Id. (emphasis added).\n\n After thoroughly reviewing the City’s complaints, we are satisfied that we\n\ncan find “some direct relation,” a meaningful and logical continuity, between the\n\n\n 23\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 24 of 76\n\n\nCity’s tax revenue injury and the Banks’ conduct by following the four guiding\n\nprinciples the Court outlined in Bank of America. We begin by considering (a)\n\n“what falls within [the] ‘first step’” of the causal chain, as we are aware of “‘[t]he\n\ngeneral tendency’ in these cases . . . ‘not to go beyond [that] first step.’” Id.\n\n(quoting Hemi Grp., 559 U.S. at 10). What falls within the first step will, we’re\n\ntold, depend on (b) “the nature of the statutory cause of action,” and (c) “an\n\nassessment of what is administratively possible and convenient.” Id. Finally, since\n\nthe common law is the basis for the direct relation requirement, we also look to (d)\n\nthe FHA’s common-law antecedents to the extent that we can. Id. We consider\n\neach of these principles in turn.\n\n A. An intervening step does not vitiate proximate cause\n\n The Court has also told us that “[t]he general tendency in these cases, in\n\nregard to damages at least, is not to go beyond the first step.” Bank of Am. 137 S.\n\nCt. at 1306 (quotations omitted). Both Banks, in their briefing on remand, make\n\nmuch of this “first step” analysis. It is clear, though, that proximate cause does not\n\nalways cut off at the first step after a violative act. A general tendency is not the\n\nsame as a hard and fast rule that dictates the outcome in every case, and Supreme\n\nCourt precedent shows that an intervening step will not vitiate proximate cause in\n\nall instances. What is more important, precedent reveals, is the certainty with\n\nwhich we can say the injury is fairly attributable to the statutory violation. An\n\n\n 24\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 25 of 76\n\n\nextended causal chain often makes attribution more difficult, but may not be the\n\nfinal word.\n\n 1.\n\n Supreme Court precedent makes crystal clear that an intervening step does\n\nnot necessarily mean proximate cause has not been plausibly alleged. Lexmark\n\nInternational, Inc. v. Static Control Components, Inc., 134 S. Ct. 1377 (2014), is a\n\ngood starting point precisely because the chain of causation there was complex and\n\ninvolved more than one simple step. The basic facts were these: Lexmark\n\nmanufactured and sold both laser printers and toner cartridges for those printers.\n\nLexmark, 134 S. Ct. at 1383. Other companies would buy used cartridges, then\n\nrefurbish and resell them. Id. The plaintiff company, Static Control, made and\n\nsold the components that the refurbishers needed to operate. Id. at 1384. Lexmark\n\nwould have preferred that its customers return used cartridges directly to Lexmark,\n\nso that it could refurbish and resell them itself. See id. at 1383. Static Control\n\nsued under the Lanham Act, alleging that Lexmark falsely and misleadingly led\n\nLexmark’s customers to believe that they were legally obligated to return spent\n\ncartridges to Lexmark and also led the refurbishers to believe that their businesses\n\nwere illegal. Id. at 1384. This, said Static Control, violated the Lanham Act’s\n\nprohibition on “false or misleading representation of fact . . . in commercial\n\nadvertising or promotion [that] misrepresents the nature, characteristics, [or]\n\n\n 25\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 26 of 76\n\n\nqualities . . . [of] another person’s goods, services, or commercial activities.” Id.\n\n(quoting 15 U.S.C. § 1125(a)). The Supreme Court granted certiorari in Lexmark\n\nto resolve issues of “statutory standing” under the Lanham Act, including\n\nproximate cause. See id. at 1385, 1390. The central question was “whether the\n\nharm alleged has a sufficiently close connection to the conduct the statute\n\nprohibits.” Id.\n\n An “intervening step of consumer deception” between Lexmark’s alleged\n\nconduct and the harm sustained by Static Control was not fatal to the claim. Id. at\n\n1391. The Court said that a Lanham Act plaintiff could demonstrate proximate\n\ncause by “show[ing] . . . injury flowing directly from the deception wrought by the\n\ndefendant’s advertising,” including, critically, “deception of consumers caus[ing]\n\nthem to withhold trade from the plaintiff.” Id. (emphasis added). Common-law\n\nprinciples supported the idea that “a plaintiff [could] be directly injured” even\n\nwhen a misrepresentation was made to a third party. Id. Liability was not without\n\nlimits, though. A company injured only by a third party’s “inability to meet [its]\n\nfinancial obligations” could not sue. Id. at 1392 (quotation omitted).\n\n The Court acknowledged, as it would again in Bank of America, the\n\n“general tendency” not to go “beyond the first step.” Id. at 1394; see Bank of Am.,\n\n137 S. Ct. at 1306. In the circumstances presented by Lexmark, though, the nature\n\nof the conduct and the harm sustained persuaded the Court against following this\n\n\n 26\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 27 of 76\n\n\ngeneral tendency. See Lexmark, 134 S. Ct. at 1394. The Court explained its\n\nreluctance to invariably limit liability to the first step this way:\n\n [T]he reason for that general tendency is that there ordinarily is a\n “discontinuity” between the injury to the direct victim and the injury to\n the indirect victim, so that the latter is not surely attributable to the\n former (and thus also to the defendant’s conduct), but might instead\n have resulted from “any number of other reasons.”\n\nId. (quoting Anza, 547 U.S. at 458–59). This “discontinuity” is evaluated in terms\n\nof logical relations and policy judgments. See Anza, 547 U.S. at 459–60. In\n\nLexmark, if the refurbishers sold fewer cartridges, “it would follow more or less\n\nautomatically” that Static Control suffered a proportional injury, “without the need\n\nfor any ‘speculative . . . proceedings’ or ‘intricate, uncertain inquiries.’” Lexmark,\n\n134 S. Ct. at 1394 (quoting Anza, 547 U.S. at 459–60).\n\n There was no “discontinuity” problem in Lexmark because of the close\n\nconnection between Static Control and the remanufacturers it supplied. “Any false\n\nadvertising that reduced the remanufacturers’ business necessarily injured Static\n\nControl as well.” Id. There was “something very close to a 1:1 relationship”\n\nbetween harm to remanufacturers and harm to Static Control because the false\n\nadvertising hurt Static Control in direct proportion to how much it hurt the\n\nremanufacturers. Id. In other words, harm to Static Control was “so integral an\n\naspect of the [violation] alleged” that the Court went beyond the first step in the\n\ncausal chain. Id.\n\n\n 27\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 28 of 76\n\n\n Still, Lexmark cabined liability by requiring “economic or reputational\n\ninjury flowing directly from the [defendant’s] deception.” Id. at 1391. This\n\nrequirement would not be met “when the deception produces injuries to a fellow\n\ncommercial actor that in turn affect the plaintiff.” Id. By way of example, the\n\nCourt suggested that a competitor whose business failed because of false\n\nadvertising could sue the false advertiser, but that competitor’s landlord could not\n\nsue the false advertiser for the value of rent payments he could no longer collect.\n\nSee id. The landlord’s injury suffered from a “discontinuity” that Static Control’s\n\ninjury did not. See id. at 1394.\n\n All of this goes to show that intervening steps in a causal chain cannot\n\nautomatically and invariably end the analysis. If they could, there would be no\n\nmeaningful way to distinguish Static Control from the hypothetical landlord. Each\n\nis only injured if the defendant’s direct competitor (the refurbishers on the actual\n\nfacts of the case) is injured first. The chain of causation is an important part of the\n\nanalysis, but the real deciding factor, at least for this Lanham Act case, was\n\nwhether there was a discontinuity between violation and injury, or, put another\n\nway, whether the injurious conduct “necessarily injured [the plaintiff] as well” as\n\nthe first-step victim, in such a way that the first-step victim was “not [a] more\n\nimmediate victim[]” than the plaintiff. Id. Thus we may look to whether the injury\n\n\n\n\n 28\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 29 of 76\n\n\nis “surely attributable” to the statutory violation; we do not simply count the steps\n\nin the causal chain. Id.\n\n Bridge v. Phoenix Bond & Indemnity Co., 553 U.S. 639 (2008), a RICO\n\nmail fraud case, makes the same point. In a suit between bidders at County-\n\noperated tax lien auctions, the defendants were accused of filing fraudulent\n\ndocuments in order to increase their success at the auctions at the expense of the\n\nplaintiffs. See Bridge, 553 U.S. at 642–44. To the extent that a chain of causation\n\nwas discussed at all, it was explained in terms of reliance. See id. at 657–58. The\n\ndefendants argued that the County, not the plaintiffs, had relied on their\n\nmisrepresentations. Id. at 648. The Court held that the plaintiffs’ injuries were\n\nproximately caused by the defendants’ misrepresentations even though the\n\nplaintiffs had not themselves relied on the fraudulent filings -- “first-party reliance”\n\nwas not “necessary to ensure that there was a sufficiently direct relationship\n\nbetween the defendant’s wrongful conduct and the plaintiff’s injury” to satisfy\n\nproximate cause. Id. at 657–58 (emphasis added).\n\n The “direct relationship” in Bridge turned on a connection between harm\n\nand injury that was non-formalistic and disconnected from step-counting. The\n\ndecision instead rested on policy considerations, see id. at 654–55, and on\n\ncommon-law principles, see id. at 656–57. The Court never mentioned a “first\n\nstep” default rule, but it’s clear that the plaintiffs’ harm would not have fallen in\n\n\n 29\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 30 of 76\n\n\nthe first step, since the County had to rely on the defendants’ misrepresentations\n\nand then had to conduct auctions on these fraudulent terms before the plaintiffs\n\ncould be injured. Instead, Bridge observed that the Second Restatement of Torts\n\n“does not say that only those who rely on the misrepresentation” -- that is, those at\n\nthe front of the chain of causation -- “can suffer a legally cognizable injury.”\n\nBridge, 553 U.S. at 656 (citing 3 Restatement (Second) of Torts §548A (1976)).\n\n While neither Lexmark nor Bridge arose under the FHA, their approach to\n\nthe first-step rule is instructive. Both decisions acknowledge that “under common-\n\nlaw principles, a plaintiff can be directly injured by a misrepresentation even\n\nwhere” someone else relied on it. Lexmark, 134 S. Ct. at 1391 (citing Bridge, 553\n\nU.S. at 639). This is a foundational principle of proximate cause; it is not an\n\nidiosyncratic wrinkle associated with a particular statute or type of claim. E.g.,\n\nBlue Shield of Virginia v. McCready, 457 U.S. 465, 482–84 (1982) (discussing\n\n“antitrust injury” as a requirement of proximate cause under certain statutes).\n\n 2.\n\n Turning to our case, the Banks argue that the City fails to allege proximate\n\ncause simply because its injuries fall outside of the “first step.” So wooden a rule\n\nwould be inconsistent with precedent as well as with the oft-noted statement that,\n\nwhen it comes to proximate cause, it is “virtually impossible to announce a black-\n\nletter rule that will dictate the result in every case.” Assoc. Gen., 549 U.S. at 536\n\n\n 30\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 31 of 76\n\n\n(citing Blue Shield, 457 U.S. at 477 n.13; Palsgraf v. Long Island R. Co., 162 N.E.\n\n99, 103 (N.Y. 1928) (“[W]hat is a proximate cause, depend[s] in each case upon\n\nmany considerations . . . .”) (Andrews, J., dissenting)); see also Lexmark, 134 S.\n\nCt. at 1390 (“The proximate-cause inquiry is not easy to define . . .”); Bridge, 553\n\nU.S. at 659 (“[P]roximate cause is generally not amenable to bright-line rules.”);\n\nHolmes, 503 U.S. at 272 n.20. Proceeding beyond a first step here is consistent\n\nwith the instruction that we stop at the first step only as a “general tendency,” and\n\nthat we also consider the nature of the cause of action, principles of continuity, and\n\nadministrative feasibility. Bank of Am., 137 S. Ct. at 1306.\n\n Wells Fargo nevertheless argues that the City’s claims cannot survive\n\nproximate cause analysis because they are wholly “contingent,” and points to\n\nHolmes v. Securities Investor Protection Corp., 503 U.S. 258 (1992), as an\n\nexample of a case where proximate cause failed “because the [plaintiffs’] injuries\n\nwere ‘purely contingent on the harm suffered by [third parties].’ [Holmes, 503\n\nU.S.] at 271.” But Holmes established no such rule. Rather, it explicitly identified\n\nthree distinct considerations by which proximate cause should be evaluated.\n\nHolmes, 503 U.S. at 269. We discuss these in considerable detail, infra, but for\n\nnow it is enough to observe that contingency on third parties is not among them.\n\n\n\n\n 31\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 32 of 76\n\n\nThe Court would have had no recourse to policy considerations if it could have\n\ndisposed of Holmes merely based on the involvement of a third party. 5\n\n Indeed, if Wells Fargo were right about the application of the first-step rule\n\nhere, this case would be over at the pleading stage simply because the chain of\n\ncausation involves more than a single step. And there would have been no reason\n\nfor the Supreme Court to remand this case back to our Court for further proximate\n\ncause analysis. The Supreme Court, too, was obviously aware that individual\n\nhomeowners were involved in this case. Again, if that alone were enough to bar\n\nproximate cause, the Court would hardly have sought the input of the lower federal\n\ncourts. The essential point for us then is that the “general tendency” to stop at the\n\nfirst step is just that, a general tendency, not an inexorable rule.\n\n If, in fact, there were a hard and fast “only the first step” rule limiting\n\nliability, a plaintiff homeowner who was forced into foreclosure on account of a\n\npredatory bank loan that violated the Fair Housing Act would never be able to\n\nplausibly allege that the foreclosure was proximately caused by the bank’s\n\npredation. By the Banks’ lights, there are two critical steps in the chain of\n\n\n5\n We also reject the application of Anza v. Ideal Steel Supply Corp, 547 U.S. 451, 457 (2006),\nthat Wells Fargo has offered in its briefing on remand. It cites Anza for its proposed rule that\nproximate cause cannot exist where the causes of a plaintiff’s injury are distinct from the\nviolative conduct. But this amounts to simply assuming the answer to our question. Whether the\ncauses of the City’s injury are too distinct and too remote from the violative conduct is at the\nheart of the proximate cause inquiry. Furthermore, the Bank’s suggested rule overlooks that\nAnza applied the factors drawn from Holmes. Anza, 547 U.S. at 459–60.\n\n 32\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 33 of 76\n\n\ncausation between the act of redlining and foreclosure: the middle and distinct step\n\nbeing a homeowner’s default. So inexorable a rule would even bar the homeowner\n\nfrom seeking redress for the foreclosure under the FHA, since the foreclosure only\n\noccurs after the homeowner takes the independent step of failing to make payments\n\non the predatory loan.\n\n If, arguendo, we were to count steps, the Banks’ arguments would still be\n\nunconvincing. For starters, the Banks overstate the length of the causal chain by\n\nreading the complaints unfavorably to the City, ignoring, among other things,\n\nallegations that Bank of America “fail[ed] to offer refinancing or loan\n\nmodifications to minority customers on fair terms” and that Wells Fargo “limit[ed]\n\nthe ability of minority borrowers to refinance out of the same predatory loans that\n\nthey previously received from the Bank.” BoA FAC at 21; WF FAC at 32. These\n\nalleged torts and acts of redlining occurred after -- perhaps long after -- the bad\n\nloans were originated, and may have occurred far down the causal chain, shortly\n\nbefore foreclosure. To take one example of their step-counting, Wells Fargo says\n\nthat injury to the City from lost property-tax revenue falls six links down the causal\n\nchain and depends on the actions of five independent parties. This count ignores\n\nthe complaints’ allegations that distinct FHA violations occurred when\n\nhomeowners already having financial difficulties were attempting to refinance or\n\notherwise modify their loans, and instead counts only from the point of loan\n\n\n 33\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 34 of 76\n\n\norigination. Because loan modification and refinancing can occur after a borrower\n\ndefaults, FHA violations of this type could be far more closely connected to the\n\nCity’s lost revenue. At the very least there might only be one step between the\n\ndenial of refinancing and a bank’s foreclosing on a property already in default.\n\n Additionally, the Bank counts a reduction in a home’s market value and a\n\nconcomitant tax assessment of that property as comprising two distinct steps in the\n\ncausal chain and speculates that foreclosures are not carried out by the Banks\n\nthemselves but by “a fourth party (presumably the mortgage servicers).” The\n\ncomplaints make no mention of an independent mortgage servicer, and in fact\n\nsuggest that the Banks were involved in refinancing and loan modifications,\n\npresumably serving themselves as the loans’ mortgage servicers. By ignoring\n\nthese unfavorable facts in the pleadings, and by generally refusing to draw\n\ninferences in the City’s favor, this accounting fails to read the complaints in the\n\nlight most favorable to the City, as we must at the motion to dismiss stage.\n\n Additionally, Wells Fargo’s count is undermined by the very principles\n\nanimating the general tendency in tort to stop at the first step. We generally stop\n\nthere because, as the time frame is extended and the chain of causation becomes\n\nmore attenuated, additional variables (maybe even causes) may intervene, making\n\nit more difficult to fairly attribute fault to the tortfeasor. As the Supreme Court put\n\nit in this case, “the housing market is interconnected with economic and social\n\n\n 34\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 35 of 76\n\n\nlife,” and “[a] violation of the FHA may . . . be expected to cause ripples of harm\n\nto flow far beyond the defendant’s misconduct.” Bank of Am., 137 S. Ct. at 1306\n\n(quotations omitted).\n\n Thus, a further problem with the Banks’ count is that the variety of factors\n\nthat we worry might independently explain a homeowner’s foreclosure (like the\n\nloss of a job or spiking health care costs) all occur at the front end of the step-\n\ncounting, between the act or acts of redlining and the foreclosure, not later. Once\n\nwe have reached increased foreclosures on a neighborhood or citywide basis, it\n\nseems to us that the path to the City’s substantially decreased tax base is clear,\n\ndirect and immediate; we can discern no obvious intervening roadblocks. Virtually\n\nall the independent variables posited by the Banks occur before foreclosure. We\n\ncan identify the same kind of continuity here as in Lexmark: if the Banks’\n\npredatory lending practices injured homeowners and led to foreclosures on a\n\nmassive scale, these injuries inflicted on multiple homeowners in the same city\n\nmust almost surely have injured the City as well. There is no discontinuity in this\n\nportion of the causal chain. Thus, since the risks of multiple independent variables\n\nafter foreclosure are not likely, and are not many, even if we were to count steps in\n\nthe way the Banks have suggested, the principles animating the general first-step\n\nrule do not support the Banks’ calculation of the post-foreclosure causal chain.\n\n\n\n\n 35\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 36 of 76\n\n\n The Banks’ step-counting is self-evidently conducted so as to identify as\n\nmany steps as possible. We might just as easily place the same injury at the second\n\nor third step: First, a bank extends predatory loans in violation of the FHA.\n\nSecond, homeowners default. Third, the bank forecloses and the property values\n\nplummet, necessarily reducing the City’s tax base and injuring its fisc. The chain\n\nwill be shorter still if struggling homeowners sought to refinance and then faced\n\nswift foreclosures when fair terms were not extended. This count, which draws\n\ninferences in favor of the City, is decidedly more appropriate for the motion to\n\ndismiss stage. At the very least, the ease with which we can count far fewer steps\n\nreinforces our view that step-counting is of limited value and cannot alone settle\n\nthe challenging questions of proximate cause here.\n\n B. The text and history of the FHA suggest a far-reaching statute\n\n The Supreme Court also instructs us to consider “the nature of the statutory\n\ncause of action.” Id. As we see it, the FHA has a broad remedial purpose, is\n\nwritten in decidedly far-reaching terms, and is perfectly capable of accommodating\n\nthe type of aggregative causal connection that the City has identified between the\n\nBanks’ alleged misconduct and financial harm to Miami. Proximate cause is only\n\none means by which Congress sets the scope of liability. Thus, for example\n\n“Congress might express limits by defining the parties who may sue, by using\n\naffirmative defenses, by providing limited remedies, by narrowly proscribing\n\n\n 36\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 37 of 76\n\n\nprohibited conduct, or by defining statutory terms.” Sandra F. Sperino, Statutory\n\nProximate Cause, 88 Notre Dame L. Rev. 1199, 1236 (2013). The result,\n\nespecially for complex and repeatedly amended statutes like the FHA, is an\n\n“interconnected web of congressional judgments about how and when liability\n\nshould be limited.” Id. To develop a proximate cause standard without taking the\n\nfull statutory scheme into account would be “to intrude upon” this web and to\n\nignore the will of Congress. See id.\n\n Most obviously, the “[t]he language of the [FHA] is broad and inclusive.”\n\nTrafficante v. Metro. Life Ins. Co., 409 U.S. 205, 209 (1972). It provides for suit\n\nby “an aggrieved person,” 42 U.S.C. § 3613(a)(1)(A), (c)(1), expansively defined\n\nas “any person who claims to have been injured by a discriminatory housing\n\npractice,” § 3602(i) (emphasis added). As we’ve said before, “‘any’ means all.”\n\nJones v. Waffle House, Inc., 866 F.3d 1257, 1267 (11th Cir. 2017) (emphases\n\nadded). This language facilitates suits by a broad range of potential plaintiffs, and\n\nthe Court has told us that it evinces not merely “a congressional intent to confer\n\nstanding broadly,” Bank of Am., 137 S. Ct. at 1303, but “a congressional intention\n\nto define standing as broadly as it is permitted by Article III,” Trafficante, 409 U.S.\n\nat 209. The Court has also noted that later Congresses amended the FHA with full\n\nknowledge of the Court’s broad readings and without changing the language the\n\nCourt had construed so broadly. Bank of Am., 137 S. Ct. at 1303.\n\n\n 37\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 38 of 76\n\n\n The Fair Housing Act also prohibits a wide range of conduct. Thus, it is a\n\nviolation “to refuse to sell or rent . . . or to refuse to negotiate . . . or otherwise\n\nmake unavailable or deny, a dwelling to any person because of race, color,\n\nreligion, sex, familial status, or national origin” as well as “[t]o discriminate\n\nagainst any person in the terms, conditions, or privileges of sale or rental of a\n\ndwelling, or in the provision of services or facilities in connection therewith” for\n\nany of the same reasons. 42 U.S.C. § 3604(a)–(b). It also expressly forbids racial\n\npreferences in housing notices and advertisements, misrepresentation of housing\n\navailability based on race, and “representations regarding the entry or prospective\n\nentry into the neighborhood” of members of protected classes. Id. § 3604(c)–(e).\n\nMost relevant for the City’s claims, it is also “unlawful for any person or other\n\nentity whose business includes engaging in residential real estate–related\n\ntransactions to discriminate against any person in making available such a\n\ntransaction, or in the terms or conditions of such a transaction,” including in loans\n\n“for purchasing, constructing, improving, repairing, or maintaining a dwelling.” Id.\n\n§ 3605(a). Again, this is far-reaching, and takes aim at discrimination that might\n\nbe found throughout the real estate market and throughout the process of buying,\n\nmaintaining, or selling a home.\n\n The injury to the City is as valid and as cognizable under the FHA as the\n\ninjury to the homeowners. See Bank of Am., 137 S. Ct. at 1303 (finding the City\n\n\n 38\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 39 of 76\n\n\nhas standing). And cities have been allowed to sue for similar injuries in the past,\n\nas in Gladstone Realtors v. Village of Bellwood, 441 U.S. 91 (1979), where a city\n\nalleged it was injured when segregative racial steering practices by two real estate\n\nfirms redounded to “the economic and social detriment of the citizens of [the]\n\nvillage.” Id. at 95. The village said “racial steering effectively manipulate[d] the\n\nhousing market” because marketing homes in certain areas only to buyers of\n\ncertain races served to dramatically reduce the number of potential buyers. Id. at\n\n109–10. The Court identified “profound” consequences in neighborhoods\n\nimpacted by this practice, including financial consequences. Id.; see id. at 111 &\n\nn.24. Not only did the village have standing to challenge racial steering, but the\n\nCourt even said that “[a] significant reduction in property values directly injures a\n\nmunicipality by diminishing its tax base.” Id. at 110–11 (emphasis added). The\n\nphrase “directly injures” was not used in a causal sense, but nonetheless suggests\n\nthat the Court has not traditionally considered this type of injury to be overly\n\nattenuated or nebulous.\n\n Moving beyond the text, in evaluating proximate cause for a statutory cause\n\nof action, the Court has repeatedly directed us to consider a statute’s remedial aims\n\n-- Congress’s priorities in passing it. See, e.g., Blue Shield, 457 U.S. at 478\n\n(considering “the relationship of the injury alleged with those forms of injury about\n\nwhich Congress was likely to have been concerned”); see also Lexmark, 134 S. Ct.\n\n\n 39\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 40 of 76\n\n\nat 1393 (identifying “diversion of sales to a direct competitor” as possibly “the\n\nparadigmatic direct injury from false advertising”); Assoc. Gen. Contractors of\n\nCal., Inc. v. California State Council of Carpenters, 459 U.S. 519, 538 (1983)\n\n(following Blue Shield in evaluating whether an injury fell “squarely within the\n\narea of congressional concern,” (quoting Blue Shield, 457 U.S. at 484)); cf.\n\nHolmes, 503 U.S. at 274 (“[W]e fear that RICO’s remedial purposes would more\n\nprobably be hobbled than helped . . . .” if the plaintiff’s proximate cause standard\n\nwere adopted).\n\n The legislative history of the FHA is less detailed than most. Congress\n\npassed it through “a truncated legislative process in which no committee reports\n\nwere issued.” Rodney A. Smolla, Federal Civil Rights Acts § 3:10, at 546–47 (3d\n\ned. 2017). A legislative assistant who worked on the legislation recalled after the\n\nAct’s passage that this was “a time when riots threatened to close down every\n\nmajor city in the country,” and that the Act was presented as a response; it was\n\nhoped that “the law as a teacher might overcome the ignorance and fear of whites\n\nwhich previously had blocked attempts to lower a black-white barrier.” Jean\n\nEberhart Dubofsky, Fair Housing: A Legislative History and a Perspective, 8\n\nWashburn L. J. 149, 154 (1969). The legislative history that we do have and the\n\ncontext in which the FHA arose both comport with a proximate cause standard that\n\ncan accommodate claims like the City’s. Thus, for example, the Supreme Court\n\n\n 40\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 41 of 76\n\n\nhas recently recounted how, in response to the turmoil of the mid-60s, President\n\nJohnson convened the National Advisory Commission on Civil Disorders (the\n\n“Kerner Commission”), which “identified residential segregation and unequal\n\nhousing and economic conditions in the inner cities as significant, underlying\n\ncauses of the social unrest.” Tex. Dept. of Hous. & Cmty. Affairs v. Inclusive\n\nCmtys. Project, Inc., 135 S. Ct. 2507, 2516 (2015). “The Commission concluded\n\nthat ‘[o]ur Nation is moving toward two societies, one black, one white—separate\n\nand unequal.’” Id. (quoting Report of the National Advisory Commission on Civil\n\nDisorders 1 (1968)).\n\n In passing the Fair Housing Act, Congress explicitly took aim at these broad\n\nsocial ills -- maladies that were being felt on a citywide scale. Congress did not\n\njust target individual discriminatory landlords, but sought to reshape in meaningful\n\nways the landscape of American cities. Senator Walter Mondale, the chief sponsor\n\nof the bill that would become the FHA, explained that the Act was intended to end\n\nhousing segregation as a means of bringing about racial equality more broadly.\n\nThe legislation’s goals were directed at the neighborhood level and indeed were\n\naimed beyond the housing market:\n\n [O]vert racial discrimination remains in one major sector of American\n life—that of housing. . . . [F]air housing is one more step toward\n achieving equality in opportunity and education . . . . The soundest,\n long-range way to attack segregated schools is to attack the segregated\n neighborhood.\n\n\n 41\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 42 of 76\n\n\n114 Cong. Rec. 3421 (Feb. 20, 1968); see also id. at 3422 (“[I]n truly integrated\n\nneighborhoods people have been able to live in peace and harmony -- and both\n\nNegroes and whites are the richer for the experience.”). A co-sponsor asked, “As\n\nsegregation continues to grow . . . will not the cities which house the majority of\n\nthe nation’s industrial and commercial life find themselves less and less able to\n\ncope with their problems, financially and in every other way?” Id. at 2988 (Feb.\n\n14, 1968) (statement of Sen. Brooke). The legislation, as its sponsors saw it, was\n\ndesigned to extend through chains of causation. Among other things, its sponsors\n\nquite specifically referenced harm to a city’s tax base, arising out of discrimination\n\nin the housing market. Senator Mondale put it this way:\n\n Declining tax base, poor sanitation, loss of jobs, inadequate educational\n opportunity, and urban squalor will persist as long as discrimination\n forces millions to live in the rotting cores of central cities.\n\nId. at 2274 (Feb. 6, 1968) (emphasis added).\n\n It does not go too far to suggest, at least at a high order of abstraction, that in\n\nsetting a standard for proximate cause the FHA looks far beyond the single most\n\nimmediate consequence of a violation. Limiting the proximate cause calculus in\n\nthat way would not be consonant with the powerful remedial purposes animating\n\nthe bill. The Act took aim at “the segregated neighborhood” in general, not just at\n\nthe prejudiced building owner.\n\n\n\n\n 42\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 43 of 76\n\n\n This is all to say that, notwithstanding issues of proof that might arise later\n\nin litigation, the FHA was written in broad terms and was aimed at broad\n\nproblems. We can discern no reason to think as a general matter that the City’s\n\nclaims are out of step with the “nature of the statutory cause of action” and the\n\nremedial scheme that Congress created.\n\n C. Tracing causation here is not administratively infeasible\n\n Perhaps the most important step in the proximate cause analysis in this case\n\nis consideration of “what is administratively possible and convenient.” Bank of\n\nAm., 137 S. Ct. at 1306 (quoting Holmes, 503 U.S. at 268). This is because\n\nadministrative feasibility is most closely connected to the policy judgments upon\n\nwhich proximate cause standards necessarily depend. See Holmes, 503 U.S. at 268\n\n(“[P]roximate cause reflects ideas of what justice demands, or of what is\n\nadministratively possible and convenient.” (internal quotations omitted)). In no\n\nsmall part, we conclude that the City has adequately -- that is to say, plausibly --\n\npled proximate cause because we find it entirely practicable and not unduly\n\ninconvenient for the courts to handle damages like the City’s tax revenue injury.\n\nCases like this will never be among the simplest that our courts see, but the federal\n\ncourts regularly handle complex and high-stakes cases, so complexity alone is no\n\nreason to dismiss a case on the pleadings. As pled, the City’s injury is\n\nascertainable with a sufficient degree of precision for some of its economic\n\n\n 43\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 44 of 76\n\n\ninjuries, specifically the harm to its tax base. Since the City’s injuries are unique\n\nto its treasury, no other plaintiff will plead the same injuries, or attempt to recover\n\nthe same funds. The City is in the best position to allege and litigate this peculiar\n\nkind of injury, to deter future violations and, theoretically, to actually remedy its\n\ndistinctive injury.\n\n In Holmes v. Securities Investor Protection Corp., 503 U.S. 258 (1992), the\n\nCourt conducted a proximate cause analysis focused on administrative feasibility.\n\nHolmes involved the Securities Investor Protection Corporation (SIPC), a federally\n\ncreated non-profit corporation empowered to sue broker-dealers who “ha[ve] failed\n\nor [are] in danger of failing to meet [their] obligations to [their] customers.” Id. at\n\n261 (quoting 15 U.S.C. § 78eee(a)(3)). In Holmes, SIPC alleged that broker-\n\ndealers manipulated securities in “a ‘pattern of racketeering activity’” that violated\n\nRICO, 18 U.S.C. §§ 1962, 1961(1), (5). Holmes, 503 U.S. at 263. The case asked\n\nwhether SIPC, “neither a purchaser nor a seller of securities” could sue under\n\nRICO even though its claims were, in essence, the same claims that could have\n\nbeen brought by investors under Rule 10b–5, under which SIPC lacked standing.\n\nId. at 265 n.7.\n\n RICO allows for a civil action by “[a]ny person injured in his business or\n\nproperty by reason of a violation of section 1962.” Id. at 265 (quoting 18 U.S.C.\n\n§ 1964(c)). SIPC claimed that it should be allowed to sue under this provision\n\n\n 44\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 45 of 76\n\n\n“because it [was] subrogated to the rights of those customers of the broker-dealers\n\nwho did not purchase manipulated securities.” Id. at 270. The chain of causation\n\nwas thus the following: The defendants manipulated securities and broker-dealers\n\nbought manipulated securities. The broker-dealers sold some of their customers\n\nthese manipulated securities, and their value plummeted when the fraud was\n\nexposed. As a result, the broker-dealers could not meet their obligations to their\n\ncustomers, including to some who had not even bought manipulated securities. It\n\nwas these nonpurchasing customers’ rights that SIPC argued it was subrogated to.\n\nSee id. at 270–71. Granting, “arguendo” that SIPC was subrogated as it claimed,\n\nHolmes, 503 U.S. at 271, the Court found that “the conspirators’ conduct did not\n\nproximately cause the nonpurchasing customers’ injury,” id. at 270.\n\n The Court pointed to three distinct reasons why “directness of relationship”\n\nwas “one of [the] central elements” of “Clayton Act causation.” Holmes, 503 U.S.\n\nat 269. First, less direct injuries are harder to attribute to a violation. Id. Second,\n\nclaims at different levels of remove complicated the apportionment of harm among\n\nplaintiffs at different levels. Id. Third, directly injured plaintiffs usually can be\n\ncounted on to sue and deter wrongdoing. Id. at 269–70. All three reasons for\n\ndirectness were said to apply “with equal force” to antitrust and RICO suits. Id. at\n\n270. The Court then considered the reasons again in the context of the particular\n\nclaims and found that each indicated that SIPC’s claims fell outside the proper\n\n\n 45\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 46 of 76\n\n\nlimits of proximate causation. Id. at 272–74. It would appear, from the Court’s\n\nanalysis, that these are not only reasons why “directness of relationship” is\n\nrequired, but are also important factors against which to measure the directness of\n\nthe relationship.\n\n When applied to the City’s claims against the Banks, these factors strongly\n\nsuggest that the City has plausibly alleged “some direct relation” between the\n\nBanks’ alleged conduct and the injury to the City’s tax revenue. We cannot say the\n\nsame for the increased-expenditures injury, though. Here, we review how each of\n\nthe Holmes factors applies to the City’s economic injuries, distinguishing, when\n\nrelevant, between the tax-revenue injury and the increased-expenditures injury.\n\nFinally, we explain how the Holmes factors provide a clear means by which to\n\ncabin liability and prevent suits by more remotely injured parties.\n\n 1.\n\n Holmes’s first factor says that directness is required because “the less direct\n\nan injury is, the more difficult it becomes to ascertain the amount of a plaintiff’s\n\ndamages attributable to the violation, as distinct from other, independent, factors.”\n\nHolmes, 503 U.S. at 269. In Holmes, this factor decidedly cut against finding a\n\nsufficiently direct relationship because it would have required the district court “to\n\ndetermine the extent to which [the nonpurchasing customers’] inability to collect\n\nfrom the broker-dealers was the result of the alleged conspiracy to manipulate, as\n\n\n 46\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 47 of 76\n\n\nopposed to” any other reasons why the broker-dealers might not have money on\n\nhand (such as “poor business practices,” and the “failure to anticipate\n\ndevelopments in the financial markets”). Id. at 273. On this first factor, the City’s\n\ntax-revenue injury fares well, and its municipal-expenditures injury fares poorly.\n\nThe City has plausibly alleged that it can present an analysis of reduced tax\n\nrevenue that is precise enough to avoid difficulties with isolating the role of the\n\nBanks’ alleged violations. It has not done so for its municipal expenditures.\n\n In its complaints, the City of Miami’s tax-revenue injury seeks damages\n\n“based upon reduced property tax revenues resulting from (a) the decreased value\n\nof the vacant properties themselves, and (b) the decreased value of properties\n\nsurrounding the vacant properties.” BoA FAC at 31; WF FAC at 44. According to\n\nthe City, “[r]outinely maintained property tax and other data allow for the precise\n\ncalculation of the property tax revenues lost by the City as a direct result of\n\nparticular [bank] foreclosures.” BoA FAC at 32; WF FAC at 45. This “Hedonic\n\nregression methodology,” the City asserts, “can be used to quantify precisely the\n\nproperty tax injury to the City caused by [the Banks’] discriminatory lending\n\npractices and resulting foreclosures in minority neighborhoods.” BoA FAC at 34;\n\nWF FAC at 47.\n\n The City does not go so far as to conduct this analysis and attach the results\n\nto its pleadings, but its First Amended Complaints nonetheless suffice to describe\n\n\n 47\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 48 of 76\n\n\nthe analysis in far more than speculative or conclusory fashion. The City has\n\nexplained in some detail how this analysis works:\n\n Homes in foreclosure tend to experience a substantial decline in\n value . . . [F]oreclosure properties and the problems associated with\n them likewise cause especially significant declines in surrounding\n property values because the neighborhoods become less desirable. . . .\n Routinely maintained property tax and other data allow for the\n precise calculation of the property tax revenues lost by the City as a\n direct result of particular [bank] foreclosures. Using a well-established\n statistical regression technique that focuses on effects on neighboring\n properties, the City can isolate the lost property value attributable to\n [the Banks’] foreclosures and vacancies from losses attributable to\n other causes, such as neighborhood conditions. This technique, known\n as Hedonic regression, when applied to housing markets, isolates the\n factors that contribute to the value of a property by studying thousands\n of housing transactions. Those factors include the size of a home, the\n number of bedrooms and bathrooms, whether the neighborhood is safe,\n whether neighboring properties are well-maintained, and more.\n Hedonic analysis determines the contribution of each of these house\n and neighborhood characteristics to the value of a home.\n\nBoA FAC at 32–33; WF FAC at 45–46. 6 This gives us a clear idea of the final\n\nanalysis -- based on empirical data drawn from thousands of housing transactions,\n\nthe City will calculate the impact of the Banks’ foreclosures on property values in\n\nredlined (and reverse-redlined) areas of Miami, controlling for other variables and\n\nisolating the impact of the redlining. The City points to studies in which this\n\n\n\n6\n Wells Fargo says that the City pleads “that it could conduct a study that might be able to show\nthat foreclosures affect property values.” (emphases in original). The City’s pleading does not\nhedge its allegations in this way, and discounting the feasibility of its analysis on the front end is\ninconsistent with our obligation to draw all reasonable inferences in the City’s favor at this\npreliminary stage.\n\n 48\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 49 of 76\n\n\nmethodology has produced the kind of results the City will need to present. BoA\n\nFAC at 33–34; WF FAC 46–47. The complaints conclude, then, that\n\n“[a]pplication of such Hedonic regression methodology . . . can be used to quantify\n\nprecisely the property tax injury to the City caused by [the Banks’] discriminatory\n\nlending practices and resulting foreclosures.” BoA FAC at 34; WF FAC at 47.\n\n The pleadings strongly suggest, then, that the tax-revenue injury to the City\n\nattributable to the Banks’ alleged discriminatory practices is readily calculable.\n\nUnder Twombly and Iqbal a mere statement that “[the Banks] caused the loss of\n\nproperty tax revenue” would be wholly conclusory and would be disregarded. But\n\nby indicating and explaining at considerable length the kind of analysis that would\n\nbe conducted to quantify the loss of revenue attributable to discriminatory lending,\n\nthe City has plausibly alleged a calculable harm and has made more than a\n\nformulaic recitation of how the causation requirement will be met. There could be\n\na battle of experts down the line over whether the regression analysis really shows\n\nwhat the City says it does, but, as we see it, that would be for a later stage of the\n\nlitigation. The complaints’ allegation that regression analysis can pinpoint\n\ncausation is sufficient at this stage and helps account for the concerns raised by this\n\nfirst factor.\n\n The plausibility of hedonic regression analysis has a direct bearing on how\n\n“difficult it [is] to ascertain the amount of [the City’s] damage attributable to the\n\n\n 49\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 50 of 76\n\n\nviolation, as distinct from other, independent, factors,” Holmes, 503 U.S. at 269,\n\nand thus helps determine “what is administratively possible and convenient,” in\n\nterms of damages calculation, Bank of Am., 137 S. Ct. at 1306. Here, the City has\n\nplausibly pled that it is practicable and convenient to quantify the property tax\n\ninjury’s causal connection to the Banks’ policies. In addition to the studies\n\nidentified by the City, we note in passing there has been a substantial amount of\n\nwriting (including legal literature) that has discussed or employed hedonic\n\nregression analysis as a practicable and effective way of calculating impacts on\n\nreal estate values.7 One author at the University of Wisconsin School of Business\n\nhas written that “[o]ver the past three decades, hedonic estimation has clearly\n\nmatured from a new technology to become the standard way economists deal with\n\nhousing heterogeneity.” 8 Likewise, the Organisation for Economic Co-operation\n\nand Development’s (OECD) Handbook on Residential Property Prices Indices\n\n(RPPI) calls hedonic regression “probably the best method that could be used in\n\norder to construct quality RPPIs for various types of property.” 9 While we may\n\n\n7\n See, e.g., Yun-Chien Chang, Economic Value or Fair Market Value: What Form of Takings\nCompensation is Efficient?, 20 SUP. CT. ECON. REV. 35, 52–54 (2012); Yun-Chien Chang & Lee\nAnne Fennell, Partition and Revelation, 81 U. CHI. L. REV. 27, 35 n.35(2014); Randall Akee,\nCheckerboards and Coase: The Effect of Property Institutions on Efficiency in Housing Markets,\n52 J.L. & ECON. 395, 402–03 (2009).\n8\n Stephen Malpezzi, Hedonic Pricing Models: A Selective and Applied Review, in HOUSING\nECONOMICS AND PUBLIC POLICY 67, 87 (Tony O’Sullivan & Kenneth Gibb eds., 2003).\n9\n OECD, Hedonic Regression Methods, in HANDBOOK ON RESIDENTIAL PROPERTY PRICE INDICES\n50, 57 (2003).\n\n 50\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 51 of 76\n\n\nnot engage in a Daubert analysis at this early stage, that hedonic regression\n\nanalysis has been favorably referenced and employed elsewhere and over several\n\ndecades cuts against the suggestion at the motion to dismiss stage that it is a wholly\n\nimplausible invention of the City’s or that apportioning blame through its\n\napplication would be so challenging that the complaints cannot state a claim.\n\n At a more basic level, the aggregative nature of the City’s claims also helps\n\neliminate any discontinuity between the statutory violation and the injury. See\n\nLexmark, 134 S. Ct. at 1394. Here, the claimed violation is a “pattern or practice\n\nof reverse redlining” leading to a “disproportionately high rate of foreclosure.”\n\nBoA FAC at 30; WF FAC at 43. Even if each individual act of redlining does not\n\nbear a one-to-one proportional relationship to Miami’s loss of tax revenue, see\n\nLexmark, 134 S. Ct. at 1394, since intervening circumstances affect which\n\nindividual properties go into foreclosure, in the aggregate it has been plausibly\n\nalleged that the impact of redlining and reverse-redlining can be identified with\n\nprecision and deterred. Similarly, in Blue Shield, the Court identified “the physical\n\nand economic nexus between the alleged violation and the harm to the plaintiff” as\n\na factor to consider when applying proximate cause to the Clayton Act. Blue\n\nShield, 457 U.S. at 478. The scale of the misconduct matches the scale of the\n\ninjury.\n\n\n\n\n 51\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 52 of 76\n\n\n Since the Supreme Court spoke to this issue in Bank of America, two district\n\ncourts analyzing similar FHA claims by municipalities against lending institutions\n\nhave relied on the availability of regression analysis in finding that proximate\n\ncause had been plausibly alleged. Most similarly and most recently, a district court\n\nin the Northern District of California entertained a similar case brought by the City\n\nof Oakland against Wells Fargo for predatory lending practices. City of Oakland\n\nv. Wells Fargo Bank, N.A., No. 15-cv-04321, 2018 WL 3008538 (N.D. Cal. June\n\n15, 2018). 10 In denying a motion to dismiss that court recognized, as we have, that\n\n“[w]hile the fact of aggregative injury itself does not obviate proximate cause\n\nanalysis,” the proffer of “a specific statistical analysis in regard to [the City’s]\n\nproperty tax injury” adequately supports the idea that there was “an alleged\n\nprovable and quantifiable causal link between the defendant’s conduct and\n\nplaintiff’s injury” notwithstanding the suggested length of the causal chain. Id. at\n\n*8. But when it came to a municipal-expenditures injury -- similar to Miami’s --\n\nthe district court ruled that since “Oakland ha[d] not proffered any statistical\n\n\n\n10\n After this decision, the district court in the Oakland case certified two questions for\ninterlocutory appeal to the Ninth Circuit: “(1) Do Oakland’s claims for damages based on the\ninjuries asserted in the [First Amended Complaint] satisfy on a motion to dismiss proximate\ncause required by the FHA?” and “(2) Is the proximate-cause requirement articulated in City of\nMiami limited to claims for damages under the FHA and not to claims for injunctive or\ndeclaratory relief?” Order Granting Defendant’s Motion to Amend Order to Include\nCertification for Interlocutory Appeal, City of Oakland, No. 15-cv-04321, 2018 WL 7575537 at\n*2. The parties’ briefs before the Ninth Circuit are due in June and July of 2019. City of\nOakland v. Wells Fargo & Co., No. 19-15169 (9th Cir. Mar. 26, 2019), ECF No. 10.\n\n 52\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 53 of 76\n\n\nanalyses comparable to those in the property-tax analysis,” the first Holmes factor\n\ncounted against them and problems of multiple causation abounded. Id. at *10.\n\nThose claims were dismissed without prejudice. Id. A district court in\n\nPhiladelphia found that city had “adequately [pled] proximate cause for . . . non-\n\neconomic injuries” stemming from FHA violations in part by relying on “a\n\nregression analysis of [bank] loan data” that had demonstrated Latino and African-\n\nAmerican borrowers were 2.641 and 4.147 times more likely to go into foreclosure\n\nthan similarly situated white borrowers. City of Philadelphia v. Wells Fargo &\n\nCo., No. 17-2203, 2018 WL 424451 (E.D. Pa. Jan. 16, 2018).\n\n In describing its second claimed economic injury -- increased municipal\n\nexpenditures for police, fire, sanitation, and the like resulting from widespread\n\nforeclosures -- the City does not do as well when measured against the first\n\nHolmes factor. When it comes to this injury, the City’s complaints fail to explain\n\nhow we can ascertain with any level of detail or precision which expenditures will\n\nbe attributable to the Banks. It is self-evident that this must be accomplished\n\nsomehow because the entire increase in municipal expenditures over any time\n\nperiod cannot possibly be fairly attributed to the Banks’ conduct. Intervening\n\ncauses and independent variables will inevitably run up this measure of damages\n\nbecause the City’s expenditures occur at some obvious level of remove from the\n\nforeclosures that it says cause them. They are further down the chain, to put it in\n\n\n 53\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 54 of 76\n\n\nstep-counting terms. There is nothing in the pleadings that suggests the plaintiff\n\nwill be able to sort out the extent to which these damages are attributable to the\n\nBanks’ misconduct.\n\n The City’s pleadings on increased expenditures are in stark contrast to their\n\npleadings about tax revenue. The increased expenditures pleadings state, in almost\n\nconclusory fashion, that “the City is required to provide increased municipal\n\nservices” at foreclosed properties and that “these services would not have been\n\nnecessary if the properties had not been foreclosed upon.” BoA FAC at 34; WF\n\nFAC at 47. The complaints then proceed to list types of expenditures: police, fire,\n\nbuilding code enforcement, and the like. If any direct connections exist between\n\nthe foreclosure and any of these expenditures, the City has not explained them, and\n\nthey are not so obvious as to be self-evident. We also see no explanation of how\n\nthe City will identify the amount of increase attributable to the foreclosures or to\n\nthe Banks’ conduct. In pleading the tax-revenue injury, however, the City explains\n\nin considerable detail how hedonic regression analysis will help pinpoint the\n\nattributable loss. This is not to say that hedonic regression analysis, specifically,\n\nshould have been referenced again in relation to the expenditure injury in order to\n\nsatisfy the first Holmes factor. Rather we suggest only that a pleading in a case\n\nlike this must make clear how a plaintiff will demonstrate that an injury is\n\n\n\n\n 54\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 55 of 76\n\n\nattributable to a defendant. Hedonic regression serves this role with regard to the\n\ntax-revenue injury, but may not be the only way this could ever be accomplished.11\n\n The first Holmes factor, addressing the attributability of the injury to the\n\ndefendant’s conduct, is where the two economic injuries alleged by the City are\n\nmost different in terms of finding a “direct relation.” The tax-revenue injury has\n\nbeen pled with detailed explanations of statistical proof, which serve to plausibly\n\nallege that the courts will be able to work out just what the Banks can be fairly held\n\naccountable for. The municipal-expenditure injury fails to do this. Statistical\n\nproofs are not the only method of proof, but, when we readily discern a\n\ndiscontinuity between misconduct and injury, for the plaintiff to plausibly plead\n\nproximate cause, it must allege something more with which to bridge the gap and\n\ndemonstrate that the defendant’s liability will bear “some direct relation” to its\n\n\n\n11\n A few other district courts have illustrated the point. In three lawsuits against banks alleging\nthe same kinds of practices that Miami has alleged, Cook County, Illinois claimed damages\nbased on “out-of-pocket costs it . . . incurred in processing the discriminatory foreclosures, such\nas additional funding for the Cook County Sheriff to serve foreclosure notices and for the Circuit\nCourt of Cook County to process the deluge of foreclosures.” County of Cook v. Bank of Am.\nCorp., No. 14 C 2280, 2018 WL 1561725 at *7 (N.D. Ill. Mar. 30, 2018); see also County of\nCook, Ill. v. HSBC N. Am. Holdings, 314 F. Supp. 3d 950, 956 (N.D. Ill. 2018); County of\nCook, Ill. v. Wells Fargo & Co., 314 F. Supp. 3d 975, 982 (N.D. Ill. 2018). Those out-of-pocket\ncosts were found to have plausibly been proximately caused by the banks because these\nexpenditures are automatic results of foreclosures. See HSBC, 314 F. Supp. 3d at 962; Wells\nFargo, 314 F. Supp. 3d at 984; Bank of Am., 2018 WL 1561725 at *7. These were the only\nclaimed damages that survived a motion dismiss in the Northern District of Illinois, as all three\ncourts there found that Cook County had failed to adequately plead proximate cause for the kinds\nof tax-revenue and municipal-expenditure injuries that Miami pleads here. See HSBC, 913 F.\nSupp. 3d at 962–64; Wells Fargo, 314 F. Supp. 3d at 988; Bank of Am., 2018 WL 1561725 at\n*5. Miami pled no out-of-pocket costs closely tied to foreclosures along these lines.\n 55\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 56 of 76\n\n\nactions. On the increased-expenditure injury, the City has not plausibly pled its\n\ncase.\n\n 2.\n\n Holmes’s second factor posits that “recognizing claims of the indirectly\n\ninjured would force courts to adopt complicated rules apportioning damages\n\namong plaintiffs removed at different levels of injury from the violative acts, to\n\nobviate the risk of multiple recoveries.” Holmes, 503 U.S. at 269. In Holmes, this\n\nwas a problem because a trial court would “have to find some way to apportion the\n\npossible respective recoveries by the broker-dealers and the customers, who would\n\notherwise each be entitled to recover the full treble damages.” Id. at 273. Antitrust\n\ncases also emphasize “the risk of duplicative recovery engendered by allowing\n\nevery person along a chain of distribution to claim damages” from a single\n\nviolation, and have identified this as a powerful reason to allow suit only by more\n\ndirectly injured parties. Blue Shield, 457 U.S. at 474–75 (citing Ill. Brick Co. v.\n\nIllinois, 431 U.S. 720, 745 (1977); Hawaii v. Standard Oil Co. of Cal., 405 U.S.\n\n251 (1972)).\n\n Again, no such problem is presented in this case: plainly, the injuries to the\n\nCity’s treasury are not shared by any other possible plaintiff. These economic\n\ninjuries, whether or not they can ultimately be recovered for, could only be alleged\n\nby the City. The City’s theory, therefore, presents no concern about double\n\n\n 56\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 57 of 76\n\n\nrecovery or “piggy-backing,” precisely because its injuries are unique.\n\nSubstantially decreased tax revenue and increased municipal costs are injuries that\n\naffect the interests of the City alone, so there could not plausibly be any difficulty\n\nin apportioning them between multiple plaintiffs. The harm and damages pled by\n\nindividual homeowners suing under the FHA would be entirely different. These\n\nplaintiffs could sue for actual and punitive damages, injunctive and equitable relief,\n\nor attorney’s fees. See 42 U.S.C. § 3613(c). In this Circuit they could also seek\n\ndamages based on “anger, embarrassment, and emotional distress.” Banai v.\n\nSec’y, U.S. Dep’t of Hous. & Urban Dev. ex rel. Times, 102 F.3d 1203, 1207 (11th\n\nCir. 1997). Many courts have permitted FHA plaintiffs to recover pecuniary\n\ndamages, including moving costs and forfeited security deposits. E.g., Belcher v.\n\nGrand Reserve MGM, LLC, 269 F. Supp. 3d 1219, 1239 (M.D. Ala. 2017). But no\n\ncourt could allow a homeowner to recover for harm to a city’s treasury.\n\n The City, on the other hand, has claimed it was financially harmed in two\n\nways -- injury to its tax base and tax revenue because of reduced property value,\n\nand increased expenditures on City services in certain neighborhoods. The\n\ndamages that these harms could support do not overlap in any way with or\n\nduplicate the damages that individual homeowners may have sustained, because\n\nthe harms are entirely separate. The City’s injuries would be “passed on” forms of\n\nthe homeowners’ injuries if, for example, it were claiming it lost tax revenue\n\n\n 57\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 58 of 76\n\n\nbecause homeowners who were overpaying on their mortgages were subsequently\n\nunable to pay their taxes. But this is not the case. The City alleges instead that the\n\nBanks’ misconduct had a direct, necessary, and immediate impact on its fiscal\n\nhealth at the neighborhood and citywide level. The homeowners’ losses are\n\nobviously related to the losses that Miami allegedly incurred, but they are\n\nindependent. Injury to the City’s treasury is a distinct injury, it is not purely\n\nderivative of misfortunes visited on homeowners. Even if we were to assume that\n\neach victim of discrimination were to successfully bring an individual claim -- a\n\nwholly implausible hypothesis -- the City would still have an independent set of\n\nclaims based on the independent harm that it suffered. The claims would be linked\n\nonly by shared facts surrounding the violation.\n\n 3.\n\n Holmes’s final factor builds on the first two: “[T]he need to grapple with\n\nthese problems,” the Court said, referring to the first two factors, “is simply\n\nunjustified by the general interest in deterring injurious conduct, since directly\n\ninjured victims can generally be counted on to vindicate the law as private\n\nattorneys general, without any of the problems attendant upon suits by plaintiffs\n\ninjured more remotely.” Id. at 269–70. Thus, in Holmes, the directly injured\n\nbroker-dealers “could be counted on to bring suit for the law’s vindication,” and so\n\nit was less necessary for SIPC to sue on behalf of the broker-dealers’ customers.\n\n\n 58\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 59 of 76\n\n\nId. at 273. In Bridge, the same factor cut in the other direction; the plaintiffs were\n\ninjured because they had less success at county-run auctions when the defendants\n\ncheated, and their harm was “the direct result of [defendant’s] fraud” in part\n\nbecause, even though the plaintiffs didn’t themselves rely on any fraudulent\n\nassertions, “no more immediate victim is better situated to sue.” Bridge, 553 U.S.\n\nat 658.\n\n The third Holmes factor has been applied to antitrust statutes as well. The\n\navailability of more directly injured plaintiffs influenced the Court’s determination\n\nthat “directness” between the plaintiff’s injury and the defendant’s action was\n\nlacking in Associated General Contractors of California, Inc. v. Carpenters, 459\n\nU.S. 519, 540–41 (1983). There, a union alleged that the defendant employer\n\nassociation had “coerced certain third parties . . . to enter into business\n\nrelationships with nonunion firms” in a way that violated the Clayton Act. Id. at\n\n520–21. This hurt unionized firms and, thus, hurt the plaintiff union. Id. The\n\nCourt found that the union had not alleged a sufficiently direct injury, noting that:\n\n The existence of an identifiable class of persons whose self-interest\n would normally motivate them to vindicate the public interest in\n antitrust enforcement diminishes the justification for allowing a more\n remote party such as the Union to perform the office of a private\n attorney general. Denying the Union a remedy on the basis of its\n allegations in this case is not likely to leave a significant antitrust\n violation undetected or unremedied.\n\nId. at 542.\n\n\n 59\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 60 of 76\n\n\n In these kinds of cases it is preferable for more directly injured plaintiffs to\n\ntake the lead in acting as private attorneys general because those plaintiffs will be\n\nable to deter future violations more effectively and efficiently. When more directly\n\ninjured parties can sue for the full swath of harm caused by statutory violations, the\n\nthreat of suit by these parties has the maximum possible deterrent effect on\n\npotential violators, and it’s simply not worthwhile to also allow minimally\n\ndeterring suits by plaintiffs farther down the causal chain. Cf. Southern Pac. Co. v.\n\nDarnell-Taenzer Lumber Co., 245 U.S. 531, 534 (1918) (“The [defendant] ought\n\nnot to be allowed to retain his illegal profit, and the only one who can take it from\n\nhim is the one that alone was in relation with him, and from whom the [defendant]\n\ntook the sum.”) (Holmes, J.).\n\n Thus, in antitrust cases the courts have long expressed a “concern for the\n\nreduction in the effectiveness of those suits if brought by indirect purchasers with a\n\nsmaller stake in the outcome than that of direct purchasers suing for the full\n\namount of the overcharge.” Ill. Brick Co., 431 U.S. at 745; see also Lexmark, 134\n\nS. Ct. at 1391 (establishing, for the Lanham Act, a rule barring suit by\n\n“commercial parties who suffer merely as a result of [a direct] competitor’s\n\n‘inability to meet [its] financial obligations’” (quoting Anza, 547 U.S. at 458)).\n\nFor this reason, the federal courts have rejected the monopolist’s “passing on”\n\ndefense -- the argument that mid-stream purchasers charged monopoly prices are\n\n\n 60\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 61 of 76\n\n\nnot harmed because they can “pass on” any overcharges to consumers. See\n\nRichard A. Posner, Economic Analysis of Law 395–96 (9th ed. 2014). Consumers\n\ncannot sue over monopoly pricing, but this does not mean there is a meaningful\n\nreduction in enforcement. See id. at 396 (“[Consumers’] right [to sue] is less\n\nvaluable because, being at once more remote . . . and more numerous, consumers\n\nare less efficient antitrust enforcers.”).\n\n The same logic surrounding deterrence does not apply here. While the City\n\nmay be a step further down the chain of causation, the homeowners are much more\n\nnumerous and less well suited to prosecute a global claim. The City’s suit could\n\nachieve better deterrence because it aims to recover for a larger injury sustained on\n\na citywide basis and to remedy a different, broader violation than a homeowner’s\n\nsuit would. The City alleges widespread redlining and reverse-redlining policies\n\nconducted by the Banks. The City’s suit challenges the entire policies. A\n\ndiscrimination claim by an individual homeowner would challenge only a bank’s\n\ndiscriminatory action against that homeowner. Conceivably the banks could face\n\nsuits by many homeowners who were discriminated against, or who lost property\n\nvalue because their neighbors’ houses were foreclosed on, but these suits wouldn’t\n\nserve to condemn the pattern or policy. Individual homeowners would also face\n\nmost of the same causation problems -- presumably a variety of factors contributed\n\nto any individual foreclosure -- but the regression analysis that can isolate the\n\n\n 61\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 62 of 76\n\n\nimpact of redlining on the neighborhood scale could not solve this problem on the\n\nindividual level because of the diversity of individual circumstances.\n\n Moreover, even if homeowners were better-situated to vindicate the same\n\nwrongdoing -- and that is plainly not the case here -- the additional assumption that\n\nothers will pursue the lawsuits and achieve deterrence is nowhere near as likely\n\ntrue under the FHA as under the other statutes. Antitrust and, to a lesser extent,\n\ncivil RICO suits are typically brought by sophisticated business entities, often with\n\ndeep pockets, and those plaintiffs also have the added incentive of realizing treble\n\ndamages. In Holmes and Associated General Contractors, the Court left the job of\n\ndeterring statutory violations to broker-dealers and businesses using union labor.\n\nThese parties were subject to complex regulatory environments and undoubtedly\n\nhad counsel in place prepared to sue to vindicate their rights. Here, instead, the\n\nalternative plaintiffs are homeowners whose homes were foreclosed upon.\n\nCompared with the sophisticated parties involved in the RICO and antitrust cases,\n\nit seems far less likely that these injured parties could be counted on to file suit.\n\nWhile it’s possible that some might, it seems exceedingly unlikely that more than a\n\nhandful at most would do so, and we have seen precious little reason to believe that\n\nmany have. The vast majority of individual cases of discriminatory lending cases\n\nare left unpursued and unaddressed. In Associated General, the Court observed\n\nthat “[d]enying the [plaintiff] a remedy on the basis of its allegations in this case\n\n\n 62\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 63 of 76\n\n\n[was] not likely to leave a significant [statutory] violation undetected or\n\nunremedied.” 459 U.S. at 542. That’s less plausible here.\n\n As a result, the peculiarities surrounding the claims raised in this case make\n\nit distinct from an antitrust case where a mid-stream purchaser can bring\n\nessentially the same action against a monopolist as the ultimate consumer would.\n\nThe question of efficacy is harder to resolve here because, although the\n\nhomeowners are arguably closer in the chain, they are too numerous and diffuse to\n\nbe counted on for deterrence. They are better situated only in a narrow, literal\n\nsense. The City, on the other hand, has plausibly alleged an injury, calculable in\n\nthe aggregate, that bears a direct relation to the Banks’ policies, applied in the\n\naggregate, which allegedly violated the statute.\n\n 4.\n\n The Holmes factors also help cabin proximate cause against other less-\n\ndirectly injured plaintiffs. Writing separately in Bank of America, Justice Thomas\n\nsuggested that Miami’s theory of causation would require that neighboring\n\nhomeowners who were not foreclosed on but whose property values fell could also\n\nsue the banks. 137 S. Ct. at 1312 (Thomas, J., concurring in part and dissenting in\n\npart). Still other concerns have been raised about the corner grocer who may have\n\nlost business on account of foreclosures, the utility company, or maybe even real\n\nestate brokers working on commission to resell properties in the area. The Court’s\n\n\n 63\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 64 of 76\n\n\nown guidance from Holmes, attuned as it is to the administrative practicalities, can\n\ngo a long way toward allaying these concerns. Application of the Holmes factors\n\nreasonably establishes that the City’s injury is logically bound up with the Banks’\n\nalleged conduct in meaningful ways missing from injuries to these other putative\n\nclaimants.\n\n To begin with the first factor, corner grocers or neighboring property\n\nowners, unlike the City, would have substantially more difficulty plausibly\n\nalleging that they could calculate damages attributable to the Banks’ actions with a\n\nreasonable degree of certainty. By contrast, hedonic regression techniques are\n\nmost effective when applied on a neighborhood or citywide level, precisely\n\nbecause individual variations among homeowners average out when foreclosures\n\nare considered in the aggregate. Indeed the amended complaints specifically cite\n\nto a study showing that each foreclosure in Chicago was “responsible for an\n\naverage decline of approximately 1.1% in the value of each single-family home\n\nwithin an eighth of a mile.” BoA FAC at 33; WF FAC at 46. The average decline\n\ncan be used to calculate the impact of foreclosures on property value across a\n\nneighborhood on account of the large sample size. A neighboring homeowner, on\n\nthe other hand, would be affected only by homes closest to his own, and these\n\nmight not accurately reflect the citywide average, in terms of causation or value.\n\nAnd a corner grocer might be affected by the surrounding few blocks of homes, but\n\n\n 64\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 65 of 76\n\n\nthis may be wholly unrepresentative of citywide trends, making causal attribution\n\nto redlining all the more difficult.\n\n Put another way, in step-counting terms, the grocer or the utility company is\n\ndemonstrably further down the causal chain because many independent variables\n\ncan enter the equation after foreclosure occurs. The City will necessarily be\n\nharmed as soon as the foreclosures occur. For the grocer, though, a nearby home’s\n\nforeclosure does not necessarily mean anything. The causal chain for the grocer is\n\nlonger, more attenuated, and more of a problem for proximate cause analysis\n\nbecause there is a powerful discontinuity between the foreclosures and the grocer’s\n\nloss of profits. It would therefore be exceedingly difficult to trace causation from\n\nthe Banks’ predatory practices through the foreclosures to the grocers’ diminished\n\nprofits. The corner grocer, or the utility company, is not affected when a home is\n\nforeclosed or when property values go down. These parties are not hurt until\n\nindividual homeowners decide to spend less money at that grocer, decide not to\n\npay the electric bill, or move away. Thus, there are many more third parties, and\n\nmany more intervening steps when it comes to the corner grocer or the utility\n\ncompany. When a homeowner is given a bad, discriminatory loan, the injury to\n\none of these more distant plaintiffs is in no sense “automatic[],” Lexmark, 134 S.\n\nCt. at 1394; it therefore becomes harder to attribute back to the Banks.\n\n\n\n\n 65\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 66 of 76\n\n\n The application of the second Holmes factor also strongly suggests why any\n\ninjury sustained by the corner grocer or by the utility company would not be\n\nproximately caused by the Banks’ conduct. These are classic “passed on” injuries.\n\nThe Court has consistently said that “where the alleged violations [are] linked to\n\nthe asserted harms only through the [directly injured parties’] inability to meet\n\ntheir financial obligations” proximate cause will not be found. Anza, 547 U.S. at\n\n458; see also Lexmark, 1391 S. Ct. at 1391 (referencing “the electric company,”\n\nspecifically, as an entity in this sort of position); Holmes, 503 U.S. at 271.\n\nIndividual homeowners have financial obligations to the City in the form of\n\nproperty taxes, but the City’s claim is not that it is harmed because property taxes\n\nwent unpaid. Rather, the City says that property values decreased and that\n\ntherefore it was not entitled to as much property-tax revenue. The City’s loss is\n\nnot due to anyone lacking “the wherewithal to pay,” Holmes, 503 U.S. at 271, but\n\nto the fact that redlining means the City is not able to collect nearly as much as it\n\nwould have, had the alleged FHA violations not occurred in the first place.\n\n The third Holmes factor -- the reliability with which a plaintiff could remedy\n\nharm or achieve deterrence -- also strongly suggests that we need not fear a deluge\n\nof suits by grocers, neighbors, or power companies. These potential plaintiffs,\n\neven if injured, would be in a far weaker position and far less likely than the City\n\nto achieve deterrence or to remedy the entirety of the harm caused by the Banks’\n\n\n 66\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 67 of 76\n\n\nalleged violations. Their claims would be disjointed, aimed at remedying FHA\n\nviolations only on particular blocks, in contrast to the City’s unique ability to\n\nattack the Banks’ whole pattern or practice on a municipal level. Any claims by\n\nthe corner grocer or the neighboring homeowner would be further out in the chain\n\nof causation than the City is, and these claims would lack the broad scope that\n\nallows the City to achieve maximal deterrence. Quite simply, they would face far\n\ntougher versions of all the challenges the City faces, but with none of the offsetting\n\nadvantages.\n\n As we see it, the factors articulated by the Supreme Court in Holmes cabin\n\nthis decision and keep the floodgates closed. But these factors are not the only\n\nreason our ruling does not extend liability beyond what is reasonable.\n\nForeseeability remains a real part of the proximate cause calculation and also will\n\nfunction to cut off liability in many instances. Dan B. Dobbs, Paul T. Hayden &\n\nEllen M. Bublick, The Law of Torts § 199, at 686 (2d ed. 2011) (“The defendant\n\nmust have been reasonably able to foresee the kind of harm that was actually\n\nsuffered by the plaintiff . . . .”). We are exceedingly dubious that courts would\n\nexpect lenders to reasonably foresee unending ripples of harm that overwhelm the\n\njudicial branch.\n\n\n\n\n 67\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 68 of 76\n\n\n D. Common-law antecedents require direct relation\n\n The Court has also told us that the FHA’s common-law antecedents are a\n\nprimary reason why “proximate cause under the FHA requires ‘some direct\n\nrelation between the injury asserted and the injurious conduct alleged.’” Bank of\n\nAm., 137 S. Ct. at 1306. As a result, we know that “[a] damages claim under the\n\n[FHA] ‘is analogous to a number of tort actions recognized at common law,’” and\n\nthat “directness principles” thus apply. Id. We also observed, in our previous\n\nopinions, that FHA damages claims “have long been analogized to tort claims.”\n\nSee Bank of Am., 800 F.3d at 1282. These analogues, however, only take us so\n\nfar. They do not help flesh out the meaning of “direct relation,” even though they\n\nare the basis for imposing the requirement.\n\n The Court identified some common-law claims that are analogues for FHA\n\nclaims in Curtis v. Loether, 415 U.S. 189 (1973). See Bank of Am., 137 S. Ct. at\n\n1306 (citing Curtis for the proposition that an FHA damages claim is analogous to\n\ncertain common-law torts). There, the Court was evaluating whether the Seventh\n\nAmendment, which guarantees jury trials for “suits at common law,” guaranteed a\n\njury in an FHA suit. U.S. CONST. amend VII; see Curtis, 415 U.S. at 190. The\n\nCourt said it did, because FHA claims for housing discrimination were comparable\n\nto “the common-law duty of innkeepers not to refuse temporary lodging to a\n\n\n\n\n 68\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 69 of 76\n\n\ntraveler without justification,” “an action for defamation or intentional infliction of\n\nmental distress,” or “law[s] of insult and indignity.” Id. at 195 n.10.\n\n The identification of these common-law antecedents does not get us too far.\n\nWe lack any clear indication that Congress had these common-law claims in mind\n\nwhen drafting the FHA, and so we are reluctant draw too much from them beyond\n\nthe “some direct relation” requirement. For one thing, we would not know which\n\ncommon-law claim to begin with, since we do not see the obvious correspondence\n\nto the common law the Court has identified elsewhere. Thus, for example, this\n\ncase is not like Bridge where common-law mail fraud was an obvious precursor to\n\nRICO mail fraud. See Bridge, 553 U.S. at 652.\n\n Other statutory causes of action have more tangible foundations in particular\n\ncommon-law claims. The Court does not define what exactly counts as “common-\n\nlaw foundations” but RICO and the antitrust statutes are the paradigmatic\n\nexamples. See, e.g., Bridge, 533 U.S. at 651 (“[W]hen Congress established in\n\nRICO a civil cause of action for a person ‘injured . . . by reason of’ a\n\n‘conspir[acy],’ it meant to adopt . . . well-established common-law civil conspiracy\n\nprinciples” (quoting Beck v. Prupis, 529 U.S. 494, 504 (2000))); Holmes, 503 U.S.\n\nat 267 (“[C]ourts had read § 7 [of the Sherman Act] to incorporate common-law\n\nprinciples of proximate causation.”). In Anza v. Ideal Steel Supply Corp., 547\n\nU.S. 451, 457 (2006), a RICO case, the Court also said that “directness principles”\n\n\n 69\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 70 of 76\n\n\napply to statutes with “common-law foundations.” Bank of Am., 137 S. Ct. at\n\n1306 (quoting Anza, 547 U.S. at 457). Anza repeated reasoning from Holmes\n\ncomparing RICO’s civil suit provision to the Clayton Act’s. Anza, 547 U.S. at 457\n\n(citing Holmes, 503 U.S. at 267–68).\n\n The connection between the Clayton Act and RICO, laid out in Holmes, was\n\nfoundational for proximate cause analysis under RICO. See, e.g., Hemi Group,\n\n559 U.S. at 8–10 (citing Holmes, 503 U.S. 258); Bridge, 553 U.S. at 653–55\n\n(citing Holmes, 503 U.S. 258); Anza 547 U.S. at 457 (citing Holmes, 503 U.S. at\n\n267–68). In fact, RICO’s civil suit provision was modeled on the antitrust statutes\n\nof the early 20th century, so standards of proximate cause that applied to early\n\nClayton and Sherman Act cases can be readily applied to RICO as well. See\n\nHolmes, 503 U.S. at 268; see also Assoc. Gen. Contractors, 459 U.S. at 531–35.\n\nEven without a deep dive into legislative history, the connection between the\n\nstatutes is obvious because their civil suit provisions are almost identical. The\n\nClayton Act reads:\n\n [A]ny person who shall be injured in his business or property by reason\n of anything forbidden in the antitrust laws may sue therefor . . . and\n shall recover threefold the damages by him sustained, and the cost of\n suit, including a reasonable attorney’s fee.\n\n15 U.S.C. § 15. Likewise, RICO reads:\n\n Any person injured in his business or property by reason of a violation\n of section 1962 of this chapter may sue therefor in any appropriate\n United States district court and shall recover threefold the damages he\n\n 70\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 71 of 76\n\n\n sustains and the cost of the suit, including a reasonable attorney’s\n fee . . . .\n\n18 U.S.C. § 1964(c). Both statutes thus say that “any person” “injured in his\n\nbusiness or property” by a violation of the statute has a cause of action and can\n\nrecover treble damages plus attorney’s fees.\n\n The common-law foundations of the Fair Housing Act are less obvious\n\ninsofar as they relate to proximate cause. For starters, the FHA does not employ\n\nthe language that the Clayton Act shares with RICO. It authorizes suit by an\n\n“aggrieved person,” 42 U.S.C. § 3613(a)(1)(A), expansively defined as “any\n\nperson who (1) claims to have been injured by a discriminatory housing practice;\n\nor (2) believes that such person will be injured by a discriminatory housing\n\npractice that is about to occur.” Id. § 3602(i). Indeed, under the language\n\nemployed by Congress in the FHA, the aggrieved person need not be injured\n\nspecifically “in his business or property.” Moreover, the remedies are distinct\n\nfrom the relief available for a violation of the Clayton Act or RICO -- treble\n\ndamages are not available, and the court “may allow” attorney’s fees, but under the\n\nFHA it is not required to, as it would be under RICO or the Clayton Act. See 42\n\nU.S.C. § 3613(c).\n\n These textual differences make it harder to assume that the legislators\n\ndrafting the FHA were drawing on the same version of proximate cause that was\n\nused in these earlier statutes. We are still able to borrow notions about proximate\n\n 71\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 72 of 76\n\n\ncause from the common law for the FHA, but it strikes us as inappropriate simply\n\nto assume that the FHA necessarily incorporated the nature and form of proximate\n\ncause as it was employed in these other statutes for which we can trace a much\n\nmore direct provenance. And, since understandings of proximate cause at common\n\nlaw evolved over time, we would need to know which version of common–law\n\nproximate cause a statute adopted. See Sperino, supra, at 1225 (“The one thing\n\nthat is certain about proximate cause is that its underlying goals are contested and\n\nevolving.”). Different statutes may not have incorporated the same common-law\n\nstandard; the Palsgraf case and the First Restatement of Torts both postdated\n\npassage of the Sherman Act but had become highly foundational texts for\n\nunderstanding proximate cause by the time RICO was drafted. Id. The evolving\n\nshape of proximate cause at common law further complicates any analysis that\n\nwould depend entirely upon incorporating a common-law standard from a statute\n\nthat predated the FHA.\n\n Congress might have brought common-law standards to bear on the new\n\nproblems it addressed in the 1960s, but the fact that we may identify some\n\ncommon-law analogue does not necessarily mean that this was the case. The Fair\n\nHousing Act does not employ language drawn from the older federal statutes with\n\nconnections to the common law, and, as best as we can tell, this cause of action\n\ndoes not have an unmistakable common-law antecedent. As a result, while\n\n\n 72\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 73 of 76\n\n\nconsidering the common law may be valuable and informative, and while the\n\nstatute’s common-law antecedents do require a plaintiff plausibly to allege “some\n\ndirect relation,” we are unable to discern any further lessons from the common law\n\nthat bear on our analysis.\n\n IV. Conclusion\n\n In sum, we hold that there is “some direct relation” between the City’s tax-\n\nrevenue injuries and the Bank’s alleged violations of the FHA. The Supreme\n\nCourt has never held that the presence of an intervening causal step or the\n\ninvolvement of a third party necessarily bars a finding of proximate cause as a\n\nmatter of law, and we decline to establish so hard and fast a rule today.\n\n The City’s detailed allegations on its tax-revenue injury are sufficient for a\n\nvariety of reasons: the FHA is a broad and ambitious statute which employs a\n\nstandard of proximate cause that facilitates its operation; Congress meant for the\n\nFHA to be a big solution to a big problem -- housing segregation generated by\n\nintentional racial discrimination; for half a century courts have read the FHA\n\nbroadly and Congress has repeatedly assented to these readings; the impact of the\n\nBanks’ redlining can readily be identified at a citywide or neighborhood level, so\n\neven if there were not “something very close to a 1:1 relationship,” Lexmark, 134\n\nS. Ct. at 1394, the City has plausibly explained how it will calculate damages in a\n\nreasonably precise way; the injury is profoundly different from any injuries\n\n\n 73\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 74 of 76\n\n\nsuffered by a homeowner; and there’s no reason to think that homeowners would\n\nmake for more efficient plaintiffs. In the absence of any palpable concerns about\n\nunadministrable litigation, we ought not to unduly constrain the remedial effect of\n\nthe FHA.\n\n Put differently, the City has adequately pled proximate cause when it comes\n\nto its tax-base injury because the Banks’ redlining and reverse-redlining practices\n\nbear some direct relation to the City’s fiscal injuries. There is a logical and direct\n\nbond between discriminatory lending as a pattern and practice applied to\n\nneighborhoods throughout the City and the reduction in property values. Third\n\nparties are involved, but the harm to the City is not contingent on their actions\n\nwhen considered in the aggregate. There is no discontinuity between the violation\n\nand the harm. Bad loans in the aggregate will mean foreclosures in the aggregate,\n\nwhich will mean loss of property value and a reduction in the tax base. An\n\nindividual home might go under for a variety of causes, but when discriminatory\n\nlending practices pervade a neighborhood or a city, the city’s fisc will necessarily\n\nbe affected because we know some number of homes will go under, and some\n\nnumber of properties will lose value. When we consider the claimed violations\n\nand the injuries sustained in the aggregate -- that is, at the scale that the complaints\n\npresent them -- it becomes clearer that injuries to the city’s treasury are necessary,\n\ndirect, and immediate results of these kinds of FHA violations.\n\n\n 74\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 75 of 76\n\n\n By many of these same measures, however, the City’s increased municipal\n\nexpenditures injury fails, and so the district court was correct to find that proximate\n\ncause for this injury had not been adequately pled in the complaints it was\n\nreviewing. The City’s increased expenditures have not been plausibly presented as\n\ndirectly and automatically resulting from the Banks’ alleged conduct. Even though\n\nwe think foreclosures follow directly from the Banks’ conduct, there is too much\n\nopportunity in the causal chain between foreclosure and increased expenditures for\n\nintervening actors and causes to play a role, and there has been no explanation by\n\nthe City of how we might conceivably isolate the injury attributable to the Banks.\n\nThus we have identified this alleged injury as being too remote to satisfy proximate\n\ncause.\n\n We repeat that we have not answered every outstanding question in this\n\ncase. Much remains to be determined as the litigation proceeds, but this case is\n\nbefore this Court only on a motion to dismiss. It is not our role at this stage to\n\ndecide whether hedonic regression analysis can actually identify injuries\n\nattributable to violations with sufficient accuracy, or indeed whether the banks\n\nactually made decisions based on race as opposed to socioeconomic factors that\n\nmay correlate with race or with other considerations. Today we have done only\n\ntwo things. Broadly, we have worked out in some detail what proximate cause\n\nrequires in an FHA suit. More specifically, we have evaluated whether these\n\n\n 75\n\f Case: 14-14544 Date Filed: 05/03/2019 Page: 76 of 76\n\n\ncomplaints against these Banks plausibly allege that Miami’s injuries to its tax\n\nbase were directly related to the violations they describe. We simply find that the\n\noperative complaints explain in a plausible fashion how the claimed tax-revenue\n\ninjuries bear “some direct relation” to the misconduct that the City is challenging.\n\nThis harm to Miami, as pled, is not just foreseeable but, when measured in the\n\naggregate, is directly related to the pattern of unlawful behavior the City has\n\nalleged.\n\n The City has plausibly alleged a violation of the FHA and has stated a claim\n\nin its First Amended Complaints. Accordingly we conclude that the district court\n\nimprovidently dismissed the FHA claims in their entirety and ought to have\n\ngranted the City leave to amend its complaints, since amendation would not have\n\nbeen futile.12 The cases are remanded to the district court for further proceedings\n\nconsistent with this opinion.\n\n REVERSED and REMANDED\n\n\n\n\n12\n We leave it to the district court to determine which complaints should be operative for its\npurposes, or whether to grant the City leave to file new ones. See supra n.2.\n 76\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: CITY OF MIAMI, a Florida Municipal Corporation, Plaintiff-Appellant, v. WELLS FARGO & CO., Wells Fargo Bank, N.A., Defendants-Appellees. City of Miami, a Florida Municipal Corporation, Plaintiff-Appellant, v. Bank of America Corporation, Bank of America, N.A., Countrywide Financial Corporation, Countrywide Home Loans, Countrywide Bank, FSB, Defendants-Appellees.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 14-14544 Date Filed: 05/03/2019 Page: 1 of 76\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 14-14544\\n Non-Argument Calendar\\n ________________________\\n\\n D.C. Docket No. 1:13-cv-24508-WPD\\n\\n\\n\\nCITY OF MIAMI,\\na Florida municipal corporation,\\n\\n Plaintiff - Appellant,\\n\\nversus\\n\\nWELLS FARGO & CO.,\\nWELLS FARGO BANK, N.A.,\\n\\n Defendants - Appellees.\\n\\n\\n ________________________\\n\\n No. 14-14543\\n Non-Argument Calendar\\n ________________________\\n\\n D.C. Docket No. 1:13-cv-24506-WPD\\n\\n\\n\\nCITY OF MIAMI,\\na Florida Municipal Corporation,\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 2 of 76\\n\\n\\n Plaintiff - Appellant,\\n\\nversus\\n\\nBANK OF AMERICA CORPORATION,\\nBANK OF AMERICA, N.A.,\\nCOUNTRYWIDE FINANCIAL CORPORATION,\\nCOUNTRYWIDE HOME LOANS,\\nCOUNTRYWIDE BANK, FSB,\\n\\n Defendants - Appellees.\\n\\n ________________________\\n\\n Appeals from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 3, 2019)\\n\\nBefore MARCUS and WILSON, Circuit Judges, and SCHLESINGER, * District\\nJudge.\\n\\nMARCUS, Circuit Judge:\\n\\n This pair of ambitious fair housing lawsuits brought by the City of Miami\\n\\nagainst major financial institutions returns to our Court after having been appealed\\n\\nto the Supreme Court and resolved there in Bank of American Corp. v. City of\\n\\nMiami, 137 S. Ct. 1296 (2017). Miami alleges that, for years, the defendant\\n\\ninstitutions, major nationwide banks, carried on discriminatory lending practices\\n\\nthat intentionally targeted black and Latino Miami residents for predatory loans.\\n\\n\\n*\\n Honorable Harvey E. Schlesinger, United States District Judge for the Middle District of\\nFlorida, sitting by designation.\\n\\n 2\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 3 of 76\\n\\n\\nThe City says this resulted in disproportionate foreclosures on homeowners of\\n\\nthose races, diminished property values in predominantly minority neighborhoods,\\n\\nsubstantially reduced tax revenue for the City, and increased expenditures by the\\n\\nCity for municipal services. When we first heard these cases, we determined that\\n\\nMiami had standing under the Fair Housing Act, and that it had adequately pled\\n\\nproximate cause. See City of Miami v. Bank of Am. Corp., 800 F.3d 1262 (11th\\n\\nCir. 2015); City of Miami v. Wells Fargo & Co., 801 F.3d 1258 (11th Cir. 2015).\\n\\nThe Supreme Court agreed in part. It resolved the hotly contested standing issue in\\n\\nthe City’s favor, but vacated and remanded with regard to proximate cause. See\\n\\nBank of Am., 137 S. Ct. at 1305–06.\\n\\n The Court held that the standard that this panel had applied -- foreseeability -\\n\\n- was not enough on its own to demonstrate proximate cause. Id. at 1306. Instead,\\n\\nthe Court said that proximate cause under the FHA also required “some direct\\n\\nrelation between the injury asserted and the injurious conduct alleged.” Id. at 1306\\n\\n(quotations omitted). But the Court declined to “draw the precise boundaries of\\n\\nproximate cause under the FHA and to determine on which side of the line the\\n\\nCity’s financial injuries fall.” Id. It remanded the case, preferring to leave this\\n\\nissue open for percolation in the lower courts. See id. Today, we take up the\\n\\nquestion of how the principles of proximate cause identified by the Court’s opinion\\n\\n\\n\\n\\n 3\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 4 of 76\\n\\n\\nfunction when applied to the FHA and to the facts as alleged in the City’s\\n\\ncomplaints.\\n\\n At this preliminary stage in the lawsuit, we conclude that the City has\\n\\nadequately pled proximate cause in relation to some of its economic injuries when\\n\\nthe pleadings are measured against the standard required by the Fair Housing Act.\\n\\nProximate cause asks whether there is a direct, logical, and identifiable connection\\n\\nbetween the injury sustained and its alleged cause. If there is no discontinuity to\\n\\ncall into question whether the alleged misconduct led to the injury, proximate\\n\\ncause will have been adequately pled. The question for now is whether, accepting\\n\\nthe allegations as true, as we must, the City has said enough to make out a\\n\\nplausible case -- not whether it will probably prevail. Considering the broad and\\n\\nambitious scope of the FHA, the statute’s expansive text, the exceedingly detailed\\n\\nallegata found in the complaints, and the application of the administrative\\n\\nfeasibility factors laid out by the Supreme Court in Holmes v. Securities Investor\\n\\nProtection Corp., 503 U.S. 258 (1992), we are satisfied that the pleadings set out a\\n\\nplausible claim.\\n\\n The City’s pleadings meet this standard because Miami has alleged a\\n\\nsubstantial injury to its tax base that is not just reasonably foreseeable, but also is\\n\\nnecessarily and directly connected to the Banks’ conduct in redlining and reverse-\\n\\nredlining throughout much of the City. This injury plausibly bears “some direct\\n\\n\\n 4\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 5 of 76\\n\\n\\nrelation” to the claimed misconduct. Bank of Am., 137 S. Ct. at 1306. The injury\\n\\nto the City’s tax base is uniquely felt in the City treasury, and there is no risk that\\n\\nduplicative injuries could be pled by another plaintiff or that the apportionment of\\n\\ndamages amongst different groups of plaintiffs would be a problem. As we see it,\\n\\nthe City is in the best position. Indeed only the City can allege and litigate this\\n\\npeculiar kind of aggregative injury to its tax base. Simply put, a lawsuit\\n\\ncommenced by an individual homeowner cannot challenge the Banks’ policies on\\n\\nthe same citywide scale that the alleged misconduct took place on.\\n\\n However, the City’s pleadings fall short of sufficiently alleging “some direct\\n\\nrelation” between the Banks’ conduct and a claimed increase in expenditures on\\n\\nmunicipal services. The complaints fail to explain how these kinds of injuries --\\n\\nincreases in police, fire, sanitation, and similar municipal expenses -- are anything\\n\\nmore than merely foreseeable consequences of redlining and reverse-redlining.\\n\\nThe Court has told us that foreseeability alone is not enough.\\n\\n We do not mean to suggest that the City’s claims are destined to succeed.\\n\\nMany questions, and many difficult questions, remain and will have to be worked\\n\\nout in the district court. At the motion to dismiss stage, though, we are not asking\\n\\nwhether the complaints meet any probability requirement, only whether they\\n\\nplausibly allege violations of the FHA. Since we have found that they do, we\\n\\nallow this discrete portion of the City’s claims to proceed for now. The plaintiff\\n\\n\\n 5\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 6 of 76\\n\\n\\nhas said enough to get into the courthouse and be heard. We decide nothing more\\n\\ntoday.\\n\\n I. Background\\n\\n A. The City’s Claims\\n\\n On December 13, 2013, the City of Miami brought three complex civil\\n\\nrights actions in the Southern District of Florida against several different financial\\n\\ninstitutions. One suit was filed against Bank of America Corporation, Bank of\\n\\nAmerica N.A., Countrywide Financial Corporation, Countrywide Home Loans,\\n\\nand Countrywide Bank, FSB (collectively “Bank of America”), and another\\n\\nagainst Wells Fargo & Co. and Wells Fargo Bank, N.A. (collectively “Wells\\n\\nFargo”). For simplicity, we refer to all these defendants jointly as “the Banks.”\\n\\nThese were accompanied by another similar case against Citigroup, Inc. and\\n\\nrelated institutions. See City of Miami v. Citigroup, Inc., 801 F.3d 1268 (11th Cir.\\n\\n2015). The first time this panel considered this set of cases, we heard the Citigroup\\n\\ncase as well, but that case was not appealed to the Supreme Court. It has returned\\n\\nto the district court, where it has been stayed pending resolution of the other two.\\n\\nSee Order Staying Case Pending the Supreme Court’s Disposition of Matters Now\\n\\nBefore the Court, City of Miami v. Citigroup Inc., No. 13-cv-24510 (S.D. Fla. July\\n\\n13, 2016). As a result, our opinion today concerns only Bank of America and\\n\\nWells Fargo.\\n\\n\\n 6\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 7 of 76\\n\\n\\n The City alleged in considerable detail that the Banks had violated § 3604(b)\\n\\nand § 3605(a) of the Fair Housing Act. The first of these provisions makes it\\n\\nunlawful “[t]o discriminate against any person in the terms, conditions, or\\n\\nprivileges of sale or rental of a dwelling, or in the provision of services or facilities\\n\\nin connection therewith, because of race, color, religion, sex, familial status, or\\n\\nnational origin.” 42 U.S.C. § 3604(b). The second states that “[i]t shall be\\n\\nunlawful for any person or other entity whose business includes engaging in\\n\\nresidential real estate–related transactions to discriminate against any person in\\n\\nmaking available such a transaction, or in the terms or conditions of such a\\n\\ntransaction, because of race, color, religion, sex, handicap, familial status, or\\n\\nnational origin.” Id. § 3605(a). The City alleged that the Banks had violated these\\n\\nprovisions by intentionally engaging in discriminatory mortgage lending practices\\n\\nthat resulted in a disproportionate and excessive number of defaults by black and\\n\\nLatino homebuyers and caused substantial financial harm to the City. 1\\n\\n\\n1\\n The City also alleged that the Banks unjustly enriched themselves by taking advantage of\\n“benefits conferred by the City” at the same time that they engaged in unlawful lending practices\\nwhich “denied the City revenues it had properly expected through property and other tax\\npayments and . . . cost[] the City additional monies for services it would not have had to\\nprovide . . . absent [the Bank’s] unlawful activities.” Wells Fargo, 801 F.3d at 1261 (quoting\\nComplaint for Violations of the Federal Fair Housing Act at 61, City of Miami v. Wells Fargo &\\nCo., No. 13-24508-CIV (S.D. Fla. July 9, 2014), 2013 WL 6903725); Bank of Am., 800 F. 3d at\\n1267; see also Complaint for Violations of the Federal Fair Housing Act at 52–55, City of Miami\\nv. Bank of Am. Corp., No. 13-24506-CIV (S.D. Fla. July. 9, 2014), 2013 WL 6903721 (raising\\nthe same claims and allegations). The district court held that these claims failed. City of Miami\\nv. Bank of Am., No. 13-24506-CIV, 2014 WL 3362348 at *6–7 (S.D. Fla. July 9, 2014). We\\naffirmed, Bank of Am., 800 F.3d at 1287; Wells Fargo, 801 F.3d at 1267, and the City did not\\nappeal these claims to the Supreme Court. Accordingly, they are no longer in this case.\\n 7\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 8 of 76\\n\\n\\n The City said the Banks made a practice of systematically and intentionally\\n\\nrefusing to extend credit to minority borrowers on the same terms as they would\\n\\nextend credit to non-minority borrowers and, when they did extend credit to\\n\\ncomparably situated minority borrowers, doing so only on predatory terms, worse\\n\\nthan the terms non-minorities received. First Amended Complaint for Violations\\n\\nof the Federal Fair Housing Act at 2–5, City of Miami v. Bank of Am., No. 13-cv-\\n\\n24506 (S.D. Fla. Sept. 9, 2014) (“BoA FAC”); First Amended Complaint for\\n\\nViolations of the Federal Fair Housing Act at 2–5, City of Miami v. Wells Fargo &\\n\\nCo., No. 13-cv-24508 (S.D. Fla. Sept. 9, 2014) (“WF FAC”). 2 This amounted to\\n\\n\\n\\n2\\n The operative complaints for our purposes are the First Amended Complaints in both cases. As\\nwe explain, infra, the City appealed the denial of motions in both cases asking the district court\\nto reconsider the dismissal of its initial Complaints and to grant leave to file the First Amended\\nComplaints. After this panel reversed the decisions in September 2015, litigation proceeded in\\nthe district court for some months before the Supreme Court granted the Banks’ petitions for\\ncertiorari in June 2016. On remand from this Court, the City filed what it styled “Second\\nAmended Complaints,” (even though the First Amended Complaints had not technically been\\nfiled), and both of these were dismissed on multiple grounds, but with leave to amend. Order\\nGranting Motion to Dismiss Second Amended Complaint, Bank of Am., No. 13-cv-24506 (Mar.\\n17, 2016) (No. 98); Order Granting Motion to Dismiss Second Amended Complaint, Wells\\nFargo, No. 13-cv-24508 (Mar. 17, 2016) (No. 77). By the time the Supreme Court granted the\\npetition for certiorari, the City had filed Third Amended Complaints, and both Banks had moved\\nto dismiss these as well. See Defendants’ Motion to Dismiss Third Amended Complaint with\\nPrejudice and Request for Hearing, Bank of Am., No. 13-cv-24506 (May 16, 2016) (No. 103);\\nWells Fargo’s Motion to Dismiss with Prejudice the City’s Third Amended Complaint and\\nRequest for Hearing, Wells Fargo, No. 13-cv-24508 (May 24, 2016) (No 83). Both cases were\\nthen stayed pending resolution in the Supreme Court. Order Staying Case Pending the Supreme\\nCourt’s Disposition of Matters Now Before the Court, Bank of Am., No. 13-cv-24506 (July 13,\\n2016) (No. 128); Order Granting Unopposed Motion to Stay Further Proceedings Pending the\\nSupreme Court’s Disposition of Matters Now Before the Court, Wells Fargo, No. 13-cv-24508\\n(July 13, 2016) (No. 102). Since nothing had been appealed since the Second and Third\\nAmended Complaints were filed, the Supreme Court was explicit that it was looking to the First\\nAmended Complaints, see Bank of Am., 137 S. Ct. at 1301, and we do the same on remand.\\n 8\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 9 of 76\\n\\n\\nboth “redlining” (refusing to extend credit) and “reverse redlining” (extending\\n\\ncredit on worse terms). Black and Latino borrowers were thus unable to refinance\\n\\ntheir loans effectively. BoA FAC at 4; WF FAC at 4; see also Wells Fargo, 801\\n\\nF.3d at 1261; Bank of Am., 800 F. 3d at 1267. The City’s complaints detailed at\\n\\nconsiderable length the nature of these practices and characterized them as\\n\\n“abusive” because they resulted in loans with “unfair terms that [borrowers] could\\n\\nnot afford.” BoA FAC at 13; WF FAC at 11; see, e.g., BoA FAC at 22 (explaining\\n\\nwhat kinds of loans the City would categorize as “predatory”); WF FAC at 34\\n\\n(same).\\n\\n The City claims that these policies were entirely deliberate on the part of the\\n\\nBanks. The Amended Complaints explain that confidential witnesses -- former\\n\\nemployees at both Bank of America and Wells Fargo -- will testify to how\\n\\nminorities and residents of minority neighborhoods were targeted for predatory\\n\\nloan terms. E.g., BoA FAC at 19; WF FAC at 29. Moreover, witnesses allegedly\\n\\nwill testify that Wells Fargo specifically targeted Latino and African American\\n\\ncommunity groups and churches (but never white churches) and that employees\\n\\nwere assigned based on their race to make presentations to these groups. WF FAC\\n\\nat 30. Witnesses from Bank of America likewise will testify that they were\\n\\nencouraged to steer less financially savvy borrowers, often racial minorities,\\n\\ntoward loan products that were decidedly unfavorable to the customer and different\\n\\n\\n 9\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 10 of 76\\n\\n\\nfrom loan products offered to white applicants, but highly favorable to the bank.\\n\\nBoA FAC at 19–20.\\n\\n According to the City, all of this violated the FHA in two stages. To start,\\n\\nthe Banks intentionally discriminated against minority borrowers by targeting them\\n\\nfor burdensome loans. This had a disparate impact on minority borrowers, leading,\\n\\ndown the line, to a disproportionate number of exploitative loans in minority\\n\\nneighborhoods and, eventually, to a disproportionate number of foreclosures on\\n\\nminority-owned properties. BoA FAC at 15–19; WF FAC at 21–29.\\n\\n The City employed detailed regression analyses of the Banks’ self-reported\\n\\ndata to show that a Bank of America loan in a predominantly African-American or\\n\\nLatino Miami neighborhood was 5.857 times more likely to result in foreclosure\\n\\nthan a Bank of America loan in a non-minority Miami neighborhood. BoA FAC at\\n\\n26. For a minority-neighborhood loan from Wells Fargo, foreclosure was 6.975\\n\\ntimes more likely. WF FAC at 39. Further calculations indicated that, controlling\\n\\nfor credit history and other factors, a black Miami borrower was 1.581 times more\\n\\nlikely than a white borrower to receive a predatory loan from Bank of America and\\n\\n4.321 times more likely to receive one from Wells Fargo. BoA FAC at 22; WF\\n\\nFAC at 34. A Latino borrower was 2.087 times more likely to receive such a loan\\n\\nfrom Bank of America and 1.576 times more likely to receive one from Wells\\n\\nFargo. BoA FAC at 22; WF FAC at 34. Notably, even among borrowers with\\n\\n\\n 10\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 11 of 76\\n\\n\\ngood credit (FICO scores over 660), black borrowers were 1.533 and 2.572 times\\n\\nmore likely to receive a predatory loan from Bank of America and Wells Fargo,\\n\\nrespectively. BoA FAC at 22; WF FAC at 34. For Latino borrowers with good\\n\\ncredit, the figures were 2.137 and 1.875 times more likely. BoA FAC at 22; WF\\n\\nFAC at 34. The City identified similar disproportionalities on a larger scale by\\n\\ncomparing predominantly white neighborhoods with predominantly minority ones.\\n\\nSee BoA FAC at 23–25; WF FAC at 35–37.\\n\\n The complaints further alleged that the Banks’ lending practices resulted in\\n\\nminority borrowers suffering especially fast and frequent foreclosures, an\\n\\nimportant indicator of predatory lending practices. See BoA FAC at 29–30; WF\\n\\nFAC at 41. White borrowers’ average time from origination to foreclosure was\\n\\n3.448 years for a Bank of America loan or 3.266 years for a Wells Fargo loan; for\\n\\nblack and Latino borrowers the averages were 3.144 (black) and 3.090 (Latino)\\n\\nyears from Bank of America and 2.996 (both black and Latino) from Wells Fargo.\\n\\nBoA FAC at 28; WF FAC at 41. Confidential witnesses from both Banks will\\n\\nallegedly support the claims that each had deliberately targeted black and Latino\\n\\nborrowers for predatory loans. E.g., BoA FAC at 19–21; WF FAC at 30–31.\\n\\n What’s more, according to the complaints, the Banks’ misconduct was not\\n\\nlimited to loan origination but instead continued almost to the point of foreclosure.\\n\\nAs the Supreme Court noted, Bank of Am., 137 S. Ct. at 1301, the predatory\\n\\n\\n 11\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 12 of 76\\n\\n\\npractices alleged by the City included denying black and Latino customers\\n\\nopportunities to refinance or make loan modifications on fair terms. E.g. BoA\\n\\nFAC at 21; WF FAC at 32. According to the complaints, both Banks would cause\\n\\nforeclosures when “a minority borrower who previously received a predatory loan\\n\\nsought to refinance the loan, only to discover that [the bank] refused to extend\\n\\ncredit at all,” or refused to do so on the same terms they extended when\\n\\n“refinancing similar loans issued to white borrowers.” BoA FAC at 4; WF FAC at\\n\\n4. We note that such refinancing and loan modification decisions can occur before\\n\\nor after a property enters default.\\n\\n The City alleged that it suffered both economic and noneconomic injuries.\\n\\nBoA FAC at 31–35; WF FAC at 44–48. In both complaints the alleged\\n\\nnoneconomic injury was that the Banks’ conduct “adversely impacted the racial\\n\\ncomposition of the City and impaired the City’s goals to assure racial integration\\n\\nand desegregation and the social and professional benefits of living in an integrated\\n\\nsociety.” 3 BoA FAC at 31; WF FAC at 44. The City identified two forms of\\n\\neconomic injuries. It claimed damages from each bank based on reduced property\\n\\ntax revenues, arguing that the Banks’ lending policies caused minority-owned\\n\\n\\n\\n3\\n Because we find that the City adequately pled proximate cause for one of its economic injuries,\\nwe need not evaluate whether it also did so for its noneconomic injuries. The parties in their\\nbriefing have not squarely addressed these injuries, and the Supreme Court had little to say about\\nthem. We leave this matter to the district court to address in the first instance.\\n\\n 12\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 13 of 76\\n\\n\\nproperties to fall into unnecessary or premature foreclosure, causing them to lose\\n\\nsubstantial value and, in turn, decreasing the values of surrounding properties.\\n\\nBoA FAC at 32–34; WF FAC at 45–47. This reduced the City’s tax base and the\\n\\ntax revenue it took in. According to the City, “Hedonic regression” techniques\\n\\ncould be used to quantify with considerable particularity what portion of its losses\\n\\nwas attributable to the Banks’ conduct. BoA FAC at 32–34; WF FAC at 45–47.\\n\\nAdditionally, the City claimed damages based on the cost of the increased\\n\\nmunicipal services it provided to deal with problems attributable to the foreclosed\\n\\nand often vacant properties -- including police, firefighters, building inspectors,\\n\\ndebris collectors, and others. These increased services too, the City claimed,\\n\\nwould not have been necessary if the properties had not been foreclosed upon as a\\n\\nresult of the Banks’ discriminatory lending practices. BoA FAC at 34–35; WF\\n\\nFAC at 47–48.\\n\\n The City also asked for a declaratory judgment stating that the Banks’\\n\\nconduct violated the FHA, an injunction barring the Banks from engaging in\\n\\nsimilar predatory conduct, compensatory and punitive damages, and attorneys’\\n\\nfees. BoA FAC at 40–41; WF FAC at 53–54.\\n\\n\\n\\n\\n 13\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 14 of 76\\n\\n\\n B. District Court and 11th Circuit Decisions\\n\\n On July 9, 2014, the district court granted motions to dismiss by both\\n\\nbanks. 4 City of Miami v. Bank of Am., No. 13-24506-CIV, 2014 WL 3362348\\n\\n(S.D. Fla. July 9, 2014). The court determined first that the City lacked standing\\n\\nbecause, according to this Court’s opinion in Nasser v. City of Homewood, 671\\n\\nF.2d 432 (11th Cir. 1982), its claims fell outside the “zone of interests” protected\\n\\nby the FHA. Bank of Am., 2014 WL 3362348 at *3–4. Miami had alleged\\n\\n“merely economic injuries” that were not “affected by a racial interest.” Id. at *4.\\n\\nThe trial court also determined that the FHA contained a proximate cause\\n\\nrequirement, and that this requirement had not been met because the City failed to\\n\\n“demonstrate that the [Banks’] alleged redlining and reverse redlining caused the\\n\\nforeclosures to occur.” Id. at *5. According to the district court, the City should\\n\\nhave “allege[d] facts that isolate [the Banks’] practices as the cause of any alleged\\n\\nlending disparity.” Id. Additionally, the district court said that the FHA claims fell\\n\\noutside the statute of limitations. Id. at *6–7.\\n\\n The City moved for reconsideration and for leave to file amended\\n\\ncomplaints in both cases, arguing that it had standing and that it could remedy the\\n\\nstatute of limitations issue by amending the complaint. See Bank of Am., 800 F.3d\\n\\n\\n4\\n The court issued a detailed opinion in the Bank of America case. It then adopted and incorporated\\nthat opinion in the Wells Fargo case. City of Miami v. Wells Fargo & Co., No. 13-24508-CIV\\n(S.D. Fla. July 9, 2014).\\n\\n 14\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 15 of 76\\n\\n\\nat 1271; Wells Fargo, 801 F.3d at 1264. The amended complaints added further\\n\\ndetails concerning noneconomic injuries suffered by the City as a result of the\\n\\nBanks’ discriminatory lending practices. See BoA FAC at 31; WF FAC at 44.\\n\\nThe City also argued in its amended complaints that predatory lending had\\n\\n“adversely impacted the racial composition of the City,” “impaired the City’s goals\\n\\nto assure racial integration and desegregation,” and “frustrate[d] the City’s\\n\\nlongstanding and active interest in securing the benefits of an integrated\\n\\ncommunity.” BoA FAC at 31; WF FAC at 44. The district court denied the\\n\\nmotion, and the City appealed to this Court. Bank of Am., 800 F.3d at 1271; Wells\\n\\nFargo, 801 F.3d at 1265.\\n\\n We reversed and remanded in a series of opinions, the most detailed of\\n\\nwhich we issued in City of Miami v. Bank of America Corp., 800 F.3d 1262 (11th\\n\\nCir. 2015). We began by addressing standing and held that the City had alleged an\\n\\ninjury in fact sufficiently concrete and immediate to confer Article III standing. Id.\\n\\nat 1272. Next we addressed “statutory standing” -- a misnomer, since it really\\n\\nconcerns “whether the plaintiff has a cause of action under the statute.” Id. at 1273\\n\\n(quotation omitted). We determined that this plaintiff did because the key statutory\\n\\nlanguage “swe[pt] as broadly as allowed under Article III” and placed the City\\n\\nwithin the statute’s zone of interests. Id. at 1278; see also Trafficante v. Metro\\n\\n\\n\\n\\n 15\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 16 of 76\\n\\n\\nLife Ins. Co., 409 U.S. 205, 209 (1972) (identifying “a congressional intention to\\n\\ndefine [FHA] standing as broadly as is permitted by Article III”).\\n\\n We next held that the FHA did require proximate cause, but that the City’s\\n\\npleadings were adequate. Bank of Am., 800 F.3d at 1279–80, 1283. We rejected\\n\\nthe idea that the City needed to “allege that the [Banks’] actions directly harmed\\n\\nthe City.” Id. As we saw it, the “strict directness requirement” suggested by the\\n\\nBanks could not be the proper standard for the FHA because it “would run afoul of\\n\\nSupreme Court and Eleventh Circuit caselaw allowing entities who have suffered\\n\\nindirect injuries . . . to bring a claim under the FHA.” Bank of Am., 800 F.3d at\\n\\n1281 (citing Gladstone, Realtors v. Village of Bellwood, 441 U.S. 91, 109–11\\n\\n(1979) (allowing a village to sue a firm for discriminatory practices that caused\\n\\nsegregation); Havens Realty Corp. v. Coleman, 455 U.S. 363, 378–79 (1982)\\n\\n(allowing suit by a non-profit for “impairment of its organizational mission” and\\n\\n“drain on its resources”); Baytree of Inverrary Realty Partners v. City of\\n\\nLauderhill, 873 F.2d 1407, 1408–09 (11th Cir. 1989) (allowing a non-minority\\n\\ndeveloper to challenge a zoning decision as discriminatory)). Proximate cause, we\\n\\nsaid, was “not a one-size fits-all analysis.” Id. Rather, it “can differ statute by\\n\\nstatute.” Id.\\n\\n Instead, noting the Supreme Court’s “broad and inclusive” readings of the\\n\\nFHA, e.g., Trafficante, 409 U.S. at 209, we agreed with the City that the proper\\n\\n\\n 16\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 17 of 76\\n\\n\\nstandard for proximate cause was “foreseeability.” Id. at 1281–82. Damages\\n\\nclaims under the FHA were analogous to tort claims, we reasoned, and tort law had\\n\\ntraditionally relied on foreseeability as the standard by which to evaluate causal\\n\\nrelationships and to limit the expansion of liability. See id. at 1282. The City had\\n\\nmet this standard; “it claim[ed] that the [Banks’] discriminatory lending caused\\n\\nproperty owned by minorities to enter premature foreclosure, costing the City tax\\n\\nrevenue and municipal expenditures.” Id. at 1282. We said that “[a]lthough there\\n\\nare several links in that causal chain, none are unforeseeable,” and also noted that\\n\\nthe regression analyses in the complaints made the pleadings more than just\\n\\nspeculative. Id. We made no comment, though, on “whether the City will be able\\n\\nto actually prove its causal claims.” Id. at 1283 (emphasis added). That would be\\n\\nworked out in the district court on a factual basis far beyond the four corners of the\\n\\ncomplaint. Accordingly, we remanded the case. Id. at 1289.\\n\\n Bank of America and Wells Fargo each filed petitions for certiorari, which\\n\\nthe Supreme Court granted. It consolidated the two cases.\\n\\n C. Supreme Court Decision\\n\\n The Supreme Court began by resolving the “statutory standing” question of\\n\\nwhether the City had a cause of action under the FHA. Bank of Am., 137 S. Ct. at\\n\\n1302–05. The Court agreed that its previous cases had interpreted the statute\\n\\nbroadly for standing purposes. See id. Congress had even amended the statute\\n\\n\\n 17\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 18 of 76\\n\\n\\nafter these decisions, without making any change to the relevant language,\\n\\nindicating its assent to the Court’s expansive reading of the original text. Id. at\\n\\n1303–04.\\n\\n On proximate cause, though, the Supreme Court disagreed with this panel\\n\\nbut reached no firm conclusions. It determined that foreseeability, standing alone,\\n\\nwas not a sufficiently rigorous standard. See id. at 1306 (“[T]he Eleventh Circuit\\n\\nerred in holding that foreseeability is sufficient to establish proximate cause under\\n\\nthe FHA.”). The Court explained that “foreseeability alone does not ensure the\\n\\nclose connection that proximate cause requires.” Id. Since lending and housing\\n\\npolicies are deeply interconnected with “economic and social life,” the Court said\\n\\nthat “[a] violation of the FHA may . . . ‘be expected to cause ripples of harm to\\n\\nflow’ far beyond the defendant’s misconduct.” Id. (quoting Assoc. Gen.\\n\\nContractors of Cal., Inc. v. Carpenters, 459 U.S. 519, 534 (1983)). Since\\n\\n“[n]othing in the statute suggests that Congress intended to provide a remedy\\n\\nwherever those ripples travel,” foreseeability alone could not be enough. Id.\\n\\n While the Court was clear that foreseeability was not enough, it was less\\n\\ndefinitive when it came to laying out what more FHA proximate cause required.\\n\\nIts key instructions were these:\\n\\n Rather [than foreseeability], proximate cause under the FHA requires\\n “some direct relation between the injury asserted and the injurious\\n conduct alleged.” Holmes v. Sec. Investor Protect. Corp., 503 U.S. 258,\\n 268 (1992). A damages claim under the statute “is analogous to a\\n 18\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 19 of 76\\n\\n\\n number of tort actions recognized at common law,” Curtis v. Loether,\\n 415 U.S. 189, 195 (1974), and we have repeatedly applied directness\\n principles to statutes with “common-law foundations,” Anza v. Ideal\\n Steel Supply Corp., 547 U.S. 451, 457 (2007). “The general tendency”\\n in these cases is, “in regard to damages at least, is not to go beyond the\\n first step.” Hemi Grp., LLC v. City of New York, 559 U.S. 1, 10\\n (2010). What falls within that “first step” depends in part on the “nature\\n of the statutory cause of action,” Lexmark Int’l, Inc. v. Static Control\\n Components, Inc., 134 S. Ct. 1377, 1390 (2014), and an assessment “of\\n what is administratively possible and convenient,” Holmes, 503 U.S. at\\n 268.\\n\\nBank of Am., 137 S. Ct. at 1306 (citation formats altered).\\n\\n The Court remanded for further proceedings, stating that “[t]he lower courts\\n\\nshould define, in the first instance, the contours of proximate cause under the FHA\\n\\nand decide how that standard applies to the City’s claims for lost property-tax\\n\\nrevenue and increased municipal expenses.” Id. Lacking “the benefit of [the\\n\\nEleventh Circuit’s] judgment” on how to apply the principles it had laid out, and\\n\\nwith no other circuits having weighed in yet, the Court “decline[d]” to speak first.\\n\\nId.\\n\\n In this opinion, we endeavor carefully to apply the Court’s mandate to these\\n\\ncomplaints, to determine if they plausibly state a claim under the Fair Housing Act.\\n\\n II. Standard of Review\\n\\n We review a district court’s decision to dismiss a complaint de novo\\n\\n“accepting the factual allegations in the complaint as true and construing them in\\n\\nthe light most favorable to the plaintiff.” Boyd v. Warden, Holman Corr. Facility,\\n\\n\\n 19\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 20 of 76\\n\\n\\n856 F.3d 853, 863–64 (11th Cir. 2017); see also Ashcroft v. Iqbal, 556 U.S. 662,\\n\\n678 (2009). Here, the district court also denied leave to amend, which we\\n\\ngenerally review for abuse of discretion; however, when, as here, leave to amend\\n\\nwas denied “on the grounds of futility,” we review the denial de novo “because it\\n\\nis a conclusion of law that an amended complaint would necessarily fail.” Id. (“An\\n\\namendment is considered futile when the claim, as amended, would still be subject\\n\\nto dismissal.”). Essentially, then, we must consider de novo whether the City’s\\n\\namended complaints, which the district court declined to entertain, have stated a\\n\\nclaim. This is in line with the review conducted by the Supreme Court, Bank of\\n\\nAm., 137 S. Ct. at 1302, and with our review when we first heard these cases,\\n\\nBank of Am., 800 F.3d at 1271.\\n\\n For this case to proceed past a motion to dismiss, we need not find that the\\n\\nBanks’ actions in fact proximately caused the plaintiff’s injuries; we must find that\\n\\nthe City plausibly alleged that they did so. We evaluate whether each complaint\\n\\n“contain[s] sufficient factual matter . . . to ‘state a claim to relief that is plausible\\n\\non its face.’” Iqbal, 556 U.S. at 678 (quoting Bell Atlantic Corp. v. Twombly, 550\\n\\nU.S. 544, 570 (2007)). The standard is “plausibility”; it is decidedly not a\\n\\n“probability requirement.” Id. Still, plausibility requires that allegations push past\\n\\nthe line of showing “a sheer possibility” and “[w]here a complaint pleads facts that\\n\\nare ‘merely consistent with’ a defendant’s liability, it ‘stops short of the line\\n\\n\\n 20\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 21 of 76\\n\\n\\nbetween possibility and plausibility of entitlement to relief.’” Id. (quoting\\n\\nTwombly, 550 U.S. at 557). Facts are taken as true so long as they are not a\\n\\n“formulaic recitation of the elements” or “conclusory.” Id. at 681 (quoting\\n\\nTwombly, 550 U.S. at 555).\\n\\n III. Analysis\\n\\n Prosser and Keeton observed, of proximate cause, that “[t]here is perhaps\\n\\nnothing in the entire field of law which has called forth more disagreement, or\\n\\nupon which the opinions are in such a welter of confusion.” W. Page Keeton et al.,\\n\\nProsser and Keeton on the Law of Torts § 41, at 263 (5th ed. 1984). The Supreme\\n\\nCourt has not directed the lower courts to propose a sweeping standard for\\n\\nproximate cause that would apply across all cases or to define the word “direct” for\\n\\nall time. Indeed, we are not looking for (and could not find) “a black-letter rule\\n\\nthat will dictate the result in every case.” Holmes, 503 U.S. at 272 n.20. Rather,\\n\\nwe must evaluate where, as a matter of judicial economy and policy, we ought to\\n\\ndraw the line for this particular cause of action and these particular claims. As the\\n\\nCourt has said, proximate cause “label[s] generically the judicial tools used to limit\\n\\na person’s responsibility for the consequences of that person’s own acts. . . .\\n\\n[P]roximate cause reflects ideas of what justice demands, or of what is\\n\\nadministratively possible and convenient.” Id. at 268 (quotation omitted).\\n\\n\\n\\n\\n 21\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 22 of 76\\n\\n\\n We begin our analysis, then, with the Supreme Court’s instructions.\\n\\nProximate cause under the FHA certainly requires foreseeability, which is present\\n\\nhere but is not enough. See Bank of Am. 137 S. Ct. at 1305–06. Proximate cause\\n\\nalso requires “some direct relation between the injury asserted and the injurious\\n\\nconduct alleged.” Id. at 1306 (quoting Holmes, 503 U.S. at 268). Our task today\\n\\nis to determine what plaintiffs must do in order to plausibly allege “some direct\\n\\nrelation” and to evaluate whether the City’s complaints have met that standard.\\n\\n At the outset, we consider the central phrase “some direct relation.” There is\\n\\ngive in the joints between “some direct relation” and “some direct causation.”\\n\\nThese are not identical concepts, and so when, for example, Bank of America\\n\\nsuggests that Miami’s injuries “were not caused ‘directly’ by a loan,” it may not be\\n\\npresenting the question in a way that precisely and accurately reflects the Court’s\\n\\ninstruction. We might agree that the injuries were not “caused directly by a loan”\\n\\nand yet still find “some direct relation” between the injury and the statutory\\n\\nviolations. Causation is “the act or process of causing,” and to “cause” something\\n\\nis “to serve as cause or occasion of” or “to bring [it] into existence.” Webster’s\\n\\nThird New International Dictionary 356 (2002). Relation, on the other hand is “the\\n\\nmode in which one thing or entity stands to another, itself, or others,” or “a logical\\n\\nbond.” Id. at 1916. We are considering “direct relation,” as a critical aspect of\\n\\n“proximate cause,” so some palpable causation is required. We ought not forget,\\n\\n\\n 22\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 23 of 76\\n\\n\\nthough, that foreseeability, while insufficient on its own, remains a requirement\\n\\nand ensures some causal connection. “Some direct relation,” then, works to\\n\\nguarantee that there is a “logical bond” between violation and injury. Put another\\n\\nway, while foreseeability ensures “cause,” “some direct relation” ensures that the\\n\\ncause is sufficiently “proximate.”\\n\\n Further, the law requires “some direct relation” not any quantifiable amount\\n\\nof it. The standard is softened by the modifier “some,” meaning, “of an\\n\\nunspecified but appreciable or not inconsiderable quantity, amount, extent or\\n\\ndegree.” Id. at 2171. The requirement is therefore somewhat easier to meet than if\\n\\nthe Court had said we needed to find “a direct relation.”\\n\\n We are also aware that our analysis must be tied to the Fair Housing Act in a\\n\\nspecific way. The Supreme Court twice emphasized that the policy judgments that\\n\\nshape our proximate cause analysis will necessarily depend on the FHA. For\\n\\nstarters, “what falls within [the] ‘first step,’” to which proximate cause is\\n\\n“general[ly]” constrained, will “depend[] in part on the ‘nature of the statutory\\n\\ncause of action.’” Bank of Am., 137 S. Ct. at 1306. Second, our task is to “define,\\n\\nin the first instance, the contours of proximate cause under the FHA and” to apply\\n\\nthat standard to the City’s claims. Id. (emphasis added).\\n\\n After thoroughly reviewing the City’s complaints, we are satisfied that we\\n\\ncan find “some direct relation,” a meaningful and logical continuity, between the\\n\\n\\n 23\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 24 of 76\\n\\n\\nCity’s tax revenue injury and the Banks’ conduct by following the four guiding\\n\\nprinciples the Court outlined in Bank of America. We begin by considering (a)\\n\\n“what falls within [the] ‘first step’” of the causal chain, as we are aware of “‘[t]he\\n\\ngeneral tendency’ in these cases . . . ‘not to go beyond [that] first step.’” Id.\\n\\n(quoting Hemi Grp., 559 U.S. at 10). What falls within the first step will, we’re\\n\\ntold, depend on (b) “the nature of the statutory cause of action,” and (c) “an\\n\\nassessment of what is administratively possible and convenient.” Id. Finally, since\\n\\nthe common law is the basis for the direct relation requirement, we also look to (d)\\n\\nthe FHA’s common-law antecedents to the extent that we can. Id. We consider\\n\\neach of these principles in turn.\\n\\n A. An intervening step does not vitiate proximate cause\\n\\n The Court has also told us that “[t]he general tendency in these cases, in\\n\\nregard to damages at least, is not to go beyond the first step.” Bank of Am. 137 S.\\n\\nCt. at 1306 (quotations omitted). Both Banks, in their briefing on remand, make\\n\\nmuch of this “first step” analysis. It is clear, though, that proximate cause does not\\n\\nalways cut off at the first step after a violative act. A general tendency is not the\\n\\nsame as a hard and fast rule that dictates the outcome in every case, and Supreme\\n\\nCourt precedent shows that an intervening step will not vitiate proximate cause in\\n\\nall instances. What is more important, precedent reveals, is the certainty with\\n\\nwhich we can say the injury is fairly attributable to the statutory violation. An\\n\\n\\n 24\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 25 of 76\\n\\n\\nextended causal chain often makes attribution more difficult, but may not be the\\n\\nfinal word.\\n\\n 1.\\n\\n Supreme Court precedent makes crystal clear that an intervening step does\\n\\nnot necessarily mean proximate cause has not been plausibly alleged. Lexmark\\n\\nInternational, Inc. v. Static Control Components, Inc., 134 S. Ct. 1377 (2014), is a\\n\\ngood starting point precisely because the chain of causation there was complex and\\n\\ninvolved more than one simple step. The basic facts were these: Lexmark\\n\\nmanufactured and sold both laser printers and toner cartridges for those printers.\\n\\nLexmark, 134 S. Ct. at 1383. Other companies would buy used cartridges, then\\n\\nrefurbish and resell them. Id. The plaintiff company, Static Control, made and\\n\\nsold the components that the refurbishers needed to operate. Id. at 1384. Lexmark\\n\\nwould have preferred that its customers return used cartridges directly to Lexmark,\\n\\nso that it could refurbish and resell them itself. See id. at 1383. Static Control\\n\\nsued under the Lanham Act, alleging that Lexmark falsely and misleadingly led\\n\\nLexmark’s customers to believe that they were legally obligated to return spent\\n\\ncartridges to Lexmark and also led the refurbishers to believe that their businesses\\n\\nwere illegal. Id. at 1384. This, said Static Control, violated the Lanham Act’s\\n\\nprohibition on “false or misleading representation of fact . . . in commercial\\n\\nadvertising or promotion [that] misrepresents the nature, characteristics, [or]\\n\\n\\n 25\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 26 of 76\\n\\n\\nqualities . . . [of] another person’s goods, services, or commercial activities.” Id.\\n\\n(quoting 15 U.S.C. § 1125(a)). The Supreme Court granted certiorari in Lexmark\\n\\nto resolve issues of “statutory standing” under the Lanham Act, including\\n\\nproximate cause. See id. at 1385, 1390. The central question was “whether the\\n\\nharm alleged has a sufficiently close connection to the conduct the statute\\n\\nprohibits.” Id.\\n\\n An “intervening step of consumer deception” between Lexmark’s alleged\\n\\nconduct and the harm sustained by Static Control was not fatal to the claim. Id. at\\n\\n1391. The Court said that a Lanham Act plaintiff could demonstrate proximate\\n\\ncause by “show[ing] . . . injury flowing directly from the deception wrought by the\\n\\ndefendant’s advertising,” including, critically, “deception of consumers caus[ing]\\n\\nthem to withhold trade from the plaintiff.” Id. (emphasis added). Common-law\\n\\nprinciples supported the idea that “a plaintiff [could] be directly injured” even\\n\\nwhen a misrepresentation was made to a third party. Id. Liability was not without\\n\\nlimits, though. A company injured only by a third party’s “inability to meet [its]\\n\\nfinancial obligations” could not sue. Id. at 1392 (quotation omitted).\\n\\n The Court acknowledged, as it would again in Bank of America, the\\n\\n“general tendency” not to go “beyond the first step.” Id. at 1394; see Bank of Am.,\\n\\n137 S. Ct. at 1306. In the circumstances presented by Lexmark, though, the nature\\n\\nof the conduct and the harm sustained persuaded the Court against following this\\n\\n\\n 26\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 27 of 76\\n\\n\\ngeneral tendency. See Lexmark, 134 S. Ct. at 1394. The Court explained its\\n\\nreluctance to invariably limit liability to the first step this way:\\n\\n [T]he reason for that general tendency is that there ordinarily is a\\n “discontinuity” between the injury to the direct victim and the injury to\\n the indirect victim, so that the latter is not surely attributable to the\\n former (and thus also to the defendant’s conduct), but might instead\\n have resulted from “any number of other reasons.”\\n\\nId. (quoting Anza, 547 U.S. at 458–59). This “discontinuity” is evaluated in terms\\n\\nof logical relations and policy judgments. See Anza, 547 U.S. at 459–60. In\\n\\nLexmark, if the refurbishers sold fewer cartridges, “it would follow more or less\\n\\nautomatically” that Static Control suffered a proportional injury, “without the need\\n\\nfor any ‘speculative . . . proceedings’ or ‘intricate, uncertain inquiries.’” Lexmark,\\n\\n134 S. Ct. at 1394 (quoting Anza, 547 U.S. at 459–60).\\n\\n There was no “discontinuity” problem in Lexmark because of the close\\n\\nconnection between Static Control and the remanufacturers it supplied. “Any false\\n\\nadvertising that reduced the remanufacturers’ business necessarily injured Static\\n\\nControl as well.” Id. There was “something very close to a 1:1 relationship”\\n\\nbetween harm to remanufacturers and harm to Static Control because the false\\n\\nadvertising hurt Static Control in direct proportion to how much it hurt the\\n\\nremanufacturers. Id. In other words, harm to Static Control was “so integral an\\n\\naspect of the [violation] alleged” that the Court went beyond the first step in the\\n\\ncausal chain. Id.\\n\\n\\n 27\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 28 of 76\\n\\n\\n Still, Lexmark cabined liability by requiring “economic or reputational\\n\\ninjury flowing directly from the [defendant’s] deception.” Id. at 1391. This\\n\\nrequirement would not be met “when the deception produces injuries to a fellow\\n\\ncommercial actor that in turn affect the plaintiff.” Id. By way of example, the\\n\\nCourt suggested that a competitor whose business failed because of false\\n\\nadvertising could sue the false advertiser, but that competitor’s landlord could not\\n\\nsue the false advertiser for the value of rent payments he could no longer collect.\\n\\nSee id. The landlord’s injury suffered from a “discontinuity” that Static Control’s\\n\\ninjury did not. See id. at 1394.\\n\\n All of this goes to show that intervening steps in a causal chain cannot\\n\\nautomatically and invariably end the analysis. If they could, there would be no\\n\\nmeaningful way to distinguish Static Control from the hypothetical landlord. Each\\n\\nis only injured if the defendant’s direct competitor (the refurbishers on the actual\\n\\nfacts of the case) is injured first. The chain of causation is an important part of the\\n\\nanalysis, but the real deciding factor, at least for this Lanham Act case, was\\n\\nwhether there was a discontinuity between violation and injury, or, put another\\n\\nway, whether the injurious conduct “necessarily injured [the plaintiff] as well” as\\n\\nthe first-step victim, in such a way that the first-step victim was “not [a] more\\n\\nimmediate victim[]” than the plaintiff. Id. Thus we may look to whether the injury\\n\\n\\n\\n\\n 28\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 29 of 76\\n\\n\\nis “surely attributable” to the statutory violation; we do not simply count the steps\\n\\nin the causal chain. Id.\\n\\n Bridge v. Phoenix Bond & Indemnity Co., 553 U.S. 639 (2008), a RICO\\n\\nmail fraud case, makes the same point. In a suit between bidders at County-\\n\\noperated tax lien auctions, the defendants were accused of filing fraudulent\\n\\ndocuments in order to increase their success at the auctions at the expense of the\\n\\nplaintiffs. See Bridge, 553 U.S. at 642–44. To the extent that a chain of causation\\n\\nwas discussed at all, it was explained in terms of reliance. See id. at 657–58. The\\n\\ndefendants argued that the County, not the plaintiffs, had relied on their\\n\\nmisrepresentations. Id. at 648. The Court held that the plaintiffs’ injuries were\\n\\nproximately caused by the defendants’ misrepresentations even though the\\n\\nplaintiffs had not themselves relied on the fraudulent filings -- “first-party reliance”\\n\\nwas not “necessary to ensure that there was a sufficiently direct relationship\\n\\nbetween the defendant’s wrongful conduct and the plaintiff’s injury” to satisfy\\n\\nproximate cause. Id. at 657–58 (emphasis added).\\n\\n The “direct relationship” in Bridge turned on a connection between harm\\n\\nand injury that was non-formalistic and disconnected from step-counting. The\\n\\ndecision instead rested on policy considerations, see id. at 654–55, and on\\n\\ncommon-law principles, see id. at 656–57. The Court never mentioned a “first\\n\\nstep” default rule, but it’s clear that the plaintiffs’ harm would not have fallen in\\n\\n\\n 29\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 30 of 76\\n\\n\\nthe first step, since the County had to rely on the defendants’ misrepresentations\\n\\nand then had to conduct auctions on these fraudulent terms before the plaintiffs\\n\\ncould be injured. Instead, Bridge observed that the Second Restatement of Torts\\n\\n“does not say that only those who rely on the misrepresentation” -- that is, those at\\n\\nthe front of the chain of causation -- “can suffer a legally cognizable injury.”\\n\\nBridge, 553 U.S. at 656 (citing 3 Restatement (Second) of Torts §548A (1976)).\\n\\n While neither Lexmark nor Bridge arose under the FHA, their approach to\\n\\nthe first-step rule is instructive. Both decisions acknowledge that “under common-\\n\\nlaw principles, a plaintiff can be directly injured by a misrepresentation even\\n\\nwhere” someone else relied on it. Lexmark, 134 S. Ct. at 1391 (citing Bridge, 553\\n\\nU.S. at 639). This is a foundational principle of proximate cause; it is not an\\n\\nidiosyncratic wrinkle associated with a particular statute or type of claim. E.g.,\\n\\nBlue Shield of Virginia v. McCready, 457 U.S. 465, 482–84 (1982) (discussing\\n\\n“antitrust injury” as a requirement of proximate cause under certain statutes).\\n\\n 2.\\n\\n Turning to our case, the Banks argue that the City fails to allege proximate\\n\\ncause simply because its injuries fall outside of the “first step.” So wooden a rule\\n\\nwould be inconsistent with precedent as well as with the oft-noted statement that,\\n\\nwhen it comes to proximate cause, it is “virtually impossible to announce a black-\\n\\nletter rule that will dictate the result in every case.” Assoc. Gen., 549 U.S. at 536\\n\\n\\n 30\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 31 of 76\\n\\n\\n(citing Blue Shield, 457 U.S. at 477 n.13; Palsgraf v. Long Island R. Co., 162 N.E.\\n\\n99, 103 (N.Y. 1928) (“[W]hat is a proximate cause, depend[s] in each case upon\\n\\nmany considerations . . . .”) (Andrews, J., dissenting)); see also Lexmark, 134 S.\\n\\nCt. at 1390 (“The proximate-cause inquiry is not easy to define . . .”); Bridge, 553\\n\\nU.S. at 659 (“[P]roximate cause is generally not amenable to bright-line rules.”);\\n\\nHolmes, 503 U.S. at 272 n.20. Proceeding beyond a first step here is consistent\\n\\nwith the instruction that we stop at the first step only as a “general tendency,” and\\n\\nthat we also consider the nature of the cause of action, principles of continuity, and\\n\\nadministrative feasibility. Bank of Am., 137 S. Ct. at 1306.\\n\\n Wells Fargo nevertheless argues that the City’s claims cannot survive\\n\\nproximate cause analysis because they are wholly “contingent,” and points to\\n\\nHolmes v. Securities Investor Protection Corp., 503 U.S. 258 (1992), as an\\n\\nexample of a case where proximate cause failed “because the [plaintiffs’] injuries\\n\\nwere ‘purely contingent on the harm suffered by [third parties].’ [Holmes, 503\\n\\nU.S.] at 271.” But Holmes established no such rule. Rather, it explicitly identified\\n\\nthree distinct considerations by which proximate cause should be evaluated.\\n\\nHolmes, 503 U.S. at 269. We discuss these in considerable detail, infra, but for\\n\\nnow it is enough to observe that contingency on third parties is not among them.\\n\\n\\n\\n\\n 31\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 32 of 76\\n\\n\\nThe Court would have had no recourse to policy considerations if it could have\\n\\ndisposed of Holmes merely based on the involvement of a third party. 5\\n\\n Indeed, if Wells Fargo were right about the application of the first-step rule\\n\\nhere, this case would be over at the pleading stage simply because the chain of\\n\\ncausation involves more than a single step. And there would have been no reason\\n\\nfor the Supreme Court to remand this case back to our Court for further proximate\\n\\ncause analysis. The Supreme Court, too, was obviously aware that individual\\n\\nhomeowners were involved in this case. Again, if that alone were enough to bar\\n\\nproximate cause, the Court would hardly have sought the input of the lower federal\\n\\ncourts. The essential point for us then is that the “general tendency” to stop at the\\n\\nfirst step is just that, a general tendency, not an inexorable rule.\\n\\n If, in fact, there were a hard and fast “only the first step” rule limiting\\n\\nliability, a plaintiff homeowner who was forced into foreclosure on account of a\\n\\npredatory bank loan that violated the Fair Housing Act would never be able to\\n\\nplausibly allege that the foreclosure was proximately caused by the bank’s\\n\\npredation. By the Banks’ lights, there are two critical steps in the chain of\\n\\n\\n5\\n We also reject the application of Anza v. Ideal Steel Supply Corp, 547 U.S. 451, 457 (2006),\\nthat Wells Fargo has offered in its briefing on remand. It cites Anza for its proposed rule that\\nproximate cause cannot exist where the causes of a plaintiff’s injury are distinct from the\\nviolative conduct. But this amounts to simply assuming the answer to our question. Whether the\\ncauses of the City’s injury are too distinct and too remote from the violative conduct is at the\\nheart of the proximate cause inquiry. Furthermore, the Bank’s suggested rule overlooks that\\nAnza applied the factors drawn from Holmes. Anza, 547 U.S. at 459–60.\\n\\n 32\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 33 of 76\\n\\n\\ncausation between the act of redlining and foreclosure: the middle and distinct step\\n\\nbeing a homeowner’s default. So inexorable a rule would even bar the homeowner\\n\\nfrom seeking redress for the foreclosure under the FHA, since the foreclosure only\\n\\noccurs after the homeowner takes the independent step of failing to make payments\\n\\non the predatory loan.\\n\\n If, arguendo, we were to count steps, the Banks’ arguments would still be\\n\\nunconvincing. For starters, the Banks overstate the length of the causal chain by\\n\\nreading the complaints unfavorably to the City, ignoring, among other things,\\n\\nallegations that Bank of America “fail[ed] to offer refinancing or loan\\n\\nmodifications to minority customers on fair terms” and that Wells Fargo “limit[ed]\\n\\nthe ability of minority borrowers to refinance out of the same predatory loans that\\n\\nthey previously received from the Bank.” BoA FAC at 21; WF FAC at 32. These\\n\\nalleged torts and acts of redlining occurred after -- perhaps long after -- the bad\\n\\nloans were originated, and may have occurred far down the causal chain, shortly\\n\\nbefore foreclosure. To take one example of their step-counting, Wells Fargo says\\n\\nthat injury to the City from lost property-tax revenue falls six links down the causal\\n\\nchain and depends on the actions of five independent parties. This count ignores\\n\\nthe complaints’ allegations that distinct FHA violations occurred when\\n\\nhomeowners already having financial difficulties were attempting to refinance or\\n\\notherwise modify their loans, and instead counts only from the point of loan\\n\\n\\n 33\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 34 of 76\\n\\n\\norigination. Because loan modification and refinancing can occur after a borrower\\n\\ndefaults, FHA violations of this type could be far more closely connected to the\\n\\nCity’s lost revenue. At the very least there might only be one step between the\\n\\ndenial of refinancing and a bank’s foreclosing on a property already in default.\\n\\n Additionally, the Bank counts a reduction in a home’s market value and a\\n\\nconcomitant tax assessment of that property as comprising two distinct steps in the\\n\\ncausal chain and speculates that foreclosures are not carried out by the Banks\\n\\nthemselves but by “a fourth party (presumably the mortgage servicers).” The\\n\\ncomplaints make no mention of an independent mortgage servicer, and in fact\\n\\nsuggest that the Banks were involved in refinancing and loan modifications,\\n\\npresumably serving themselves as the loans’ mortgage servicers. By ignoring\\n\\nthese unfavorable facts in the pleadings, and by generally refusing to draw\\n\\ninferences in the City’s favor, this accounting fails to read the complaints in the\\n\\nlight most favorable to the City, as we must at the motion to dismiss stage.\\n\\n Additionally, Wells Fargo’s count is undermined by the very principles\\n\\nanimating the general tendency in tort to stop at the first step. We generally stop\\n\\nthere because, as the time frame is extended and the chain of causation becomes\\n\\nmore attenuated, additional variables (maybe even causes) may intervene, making\\n\\nit more difficult to fairly attribute fault to the tortfeasor. As the Supreme Court put\\n\\nit in this case, “the housing market is interconnected with economic and social\\n\\n\\n 34\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 35 of 76\\n\\n\\nlife,” and “[a] violation of the FHA may . . . be expected to cause ripples of harm\\n\\nto flow far beyond the defendant’s misconduct.” Bank of Am., 137 S. Ct. at 1306\\n\\n(quotations omitted).\\n\\n Thus, a further problem with the Banks’ count is that the variety of factors\\n\\nthat we worry might independently explain a homeowner’s foreclosure (like the\\n\\nloss of a job or spiking health care costs) all occur at the front end of the step-\\n\\ncounting, between the act or acts of redlining and the foreclosure, not later. Once\\n\\nwe have reached increased foreclosures on a neighborhood or citywide basis, it\\n\\nseems to us that the path to the City’s substantially decreased tax base is clear,\\n\\ndirect and immediate; we can discern no obvious intervening roadblocks. Virtually\\n\\nall the independent variables posited by the Banks occur before foreclosure. We\\n\\ncan identify the same kind of continuity here as in Lexmark: if the Banks’\\n\\npredatory lending practices injured homeowners and led to foreclosures on a\\n\\nmassive scale, these injuries inflicted on multiple homeowners in the same city\\n\\nmust almost surely have injured the City as well. There is no discontinuity in this\\n\\nportion of the causal chain. Thus, since the risks of multiple independent variables\\n\\nafter foreclosure are not likely, and are not many, even if we were to count steps in\\n\\nthe way the Banks have suggested, the principles animating the general first-step\\n\\nrule do not support the Banks’ calculation of the post-foreclosure causal chain.\\n\\n\\n\\n\\n 35\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 36 of 76\\n\\n\\n The Banks’ step-counting is self-evidently conducted so as to identify as\\n\\nmany steps as possible. We might just as easily place the same injury at the second\\n\\nor third step: First, a bank extends predatory loans in violation of the FHA.\\n\\nSecond, homeowners default. Third, the bank forecloses and the property values\\n\\nplummet, necessarily reducing the City’s tax base and injuring its fisc. The chain\\n\\nwill be shorter still if struggling homeowners sought to refinance and then faced\\n\\nswift foreclosures when fair terms were not extended. This count, which draws\\n\\ninferences in favor of the City, is decidedly more appropriate for the motion to\\n\\ndismiss stage. At the very least, the ease with which we can count far fewer steps\\n\\nreinforces our view that step-counting is of limited value and cannot alone settle\\n\\nthe challenging questions of proximate cause here.\\n\\n B. The text and history of the FHA suggest a far-reaching statute\\n\\n The Supreme Court also instructs us to consider “the nature of the statutory\\n\\ncause of action.” Id. As we see it, the FHA has a broad remedial purpose, is\\n\\nwritten in decidedly far-reaching terms, and is perfectly capable of accommodating\\n\\nthe type of aggregative causal connection that the City has identified between the\\n\\nBanks’ alleged misconduct and financial harm to Miami. Proximate cause is only\\n\\none means by which Congress sets the scope of liability. Thus, for example\\n\\n“Congress might express limits by defining the parties who may sue, by using\\n\\naffirmative defenses, by providing limited remedies, by narrowly proscribing\\n\\n\\n 36\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 37 of 76\\n\\n\\nprohibited conduct, or by defining statutory terms.” Sandra F. Sperino, Statutory\\n\\nProximate Cause, 88 Notre Dame L. Rev. 1199, 1236 (2013). The result,\\n\\nespecially for complex and repeatedly amended statutes like the FHA, is an\\n\\n“interconnected web of congressional judgments about how and when liability\\n\\nshould be limited.” Id. To develop a proximate cause standard without taking the\\n\\nfull statutory scheme into account would be “to intrude upon” this web and to\\n\\nignore the will of Congress. See id.\\n\\n Most obviously, the “[t]he language of the [FHA] is broad and inclusive.”\\n\\nTrafficante v. Metro. Life Ins. Co., 409 U.S. 205, 209 (1972). It provides for suit\\n\\nby “an aggrieved person,” 42 U.S.C. § 3613(a)(1)(A), (c)(1), expansively defined\\n\\nas “any person who claims to have been injured by a discriminatory housing\\n\\npractice,” § 3602(i) (emphasis added). As we’ve said before, “‘any’ means all.”\\n\\nJones v. Waffle House, Inc., 866 F.3d 1257, 1267 (11th Cir. 2017) (emphases\\n\\nadded). This language facilitates suits by a broad range of potential plaintiffs, and\\n\\nthe Court has told us that it evinces not merely “a congressional intent to confer\\n\\nstanding broadly,” Bank of Am., 137 S. Ct. at 1303, but “a congressional intention\\n\\nto define standing as broadly as it is permitted by Article III,” Trafficante, 409 U.S.\\n\\nat 209. The Court has also noted that later Congresses amended the FHA with full\\n\\nknowledge of the Court’s broad readings and without changing the language the\\n\\nCourt had construed so broadly. Bank of Am., 137 S. Ct. at 1303.\\n\\n\\n 37\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 38 of 76\\n\\n\\n The Fair Housing Act also prohibits a wide range of conduct. Thus, it is a\\n\\nviolation “to refuse to sell or rent . . . or to refuse to negotiate . . . or otherwise\\n\\nmake unavailable or deny, a dwelling to any person because of race, color,\\n\\nreligion, sex, familial status, or national origin” as well as “[t]o discriminate\\n\\nagainst any person in the terms, conditions, or privileges of sale or rental of a\\n\\ndwelling, or in the provision of services or facilities in connection therewith” for\\n\\nany of the same reasons. 42 U.S.C. § 3604(a)–(b). It also expressly forbids racial\\n\\npreferences in housing notices and advertisements, misrepresentation of housing\\n\\navailability based on race, and “representations regarding the entry or prospective\\n\\nentry into the neighborhood” of members of protected classes. Id. § 3604(c)–(e).\\n\\nMost relevant for the City’s claims, it is also “unlawful for any person or other\\n\\nentity whose business includes engaging in residential real estate–related\\n\\ntransactions to discriminate against any person in making available such a\\n\\ntransaction, or in the terms or conditions of such a transaction,” including in loans\\n\\n“for purchasing, constructing, improving, repairing, or maintaining a dwelling.” Id.\\n\\n§ 3605(a). Again, this is far-reaching, and takes aim at discrimination that might\\n\\nbe found throughout the real estate market and throughout the process of buying,\\n\\nmaintaining, or selling a home.\\n\\n The injury to the City is as valid and as cognizable under the FHA as the\\n\\ninjury to the homeowners. See Bank of Am., 137 S. Ct. at 1303 (finding the City\\n\\n\\n 38\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 39 of 76\\n\\n\\nhas standing). And cities have been allowed to sue for similar injuries in the past,\\n\\nas in Gladstone Realtors v. Village of Bellwood, 441 U.S. 91 (1979), where a city\\n\\nalleged it was injured when segregative racial steering practices by two real estate\\n\\nfirms redounded to “the economic and social detriment of the citizens of [the]\\n\\nvillage.” Id. at 95. The village said “racial steering effectively manipulate[d] the\\n\\nhousing market” because marketing homes in certain areas only to buyers of\\n\\ncertain races served to dramatically reduce the number of potential buyers. Id. at\\n\\n109–10. The Court identified “profound” consequences in neighborhoods\\n\\nimpacted by this practice, including financial consequences. Id.; see id. at 111 &\\n\\nn.24. Not only did the village have standing to challenge racial steering, but the\\n\\nCourt even said that “[a] significant reduction in property values directly injures a\\n\\nmunicipality by diminishing its tax base.” Id. at 110–11 (emphasis added). The\\n\\nphrase “directly injures” was not used in a causal sense, but nonetheless suggests\\n\\nthat the Court has not traditionally considered this type of injury to be overly\\n\\nattenuated or nebulous.\\n\\n Moving beyond the text, in evaluating proximate cause for a statutory cause\\n\\nof action, the Court has repeatedly directed us to consider a statute’s remedial aims\\n\\n-- Congress’s priorities in passing it. See, e.g., Blue Shield, 457 U.S. at 478\\n\\n(considering “the relationship of the injury alleged with those forms of injury about\\n\\nwhich Congress was likely to have been concerned”); see also Lexmark, 134 S. Ct.\\n\\n\\n 39\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 40 of 76\\n\\n\\nat 1393 (identifying “diversion of sales to a direct competitor” as possibly “the\\n\\nparadigmatic direct injury from false advertising”); Assoc. Gen. Contractors of\\n\\nCal., Inc. v. California State Council of Carpenters, 459 U.S. 519, 538 (1983)\\n\\n(following Blue Shield in evaluating whether an injury fell “squarely within the\\n\\narea of congressional concern,” (quoting Blue Shield, 457 U.S. at 484)); cf.\\n\\nHolmes, 503 U.S. at 274 (“[W]e fear that RICO’s remedial purposes would more\\n\\nprobably be hobbled than helped . . . .” if the plaintiff’s proximate cause standard\\n\\nwere adopted).\\n\\n The legislative history of the FHA is less detailed than most. Congress\\n\\npassed it through “a truncated legislative process in which no committee reports\\n\\nwere issued.” Rodney A. Smolla, Federal Civil Rights Acts § 3:10, at 546–47 (3d\\n\\ned. 2017). A legislative assistant who worked on the legislation recalled after the\\n\\nAct’s passage that this was “a time when riots threatened to close down every\\n\\nmajor city in the country,” and that the Act was presented as a response; it was\\n\\nhoped that “the law as a teacher might overcome the ignorance and fear of whites\\n\\nwhich previously had blocked attempts to lower a black-white barrier.” Jean\\n\\nEberhart Dubofsky, Fair Housing: A Legislative History and a Perspective, 8\\n\\nWashburn L. J. 149, 154 (1969). The legislative history that we do have and the\\n\\ncontext in which the FHA arose both comport with a proximate cause standard that\\n\\ncan accommodate claims like the City’s. Thus, for example, the Supreme Court\\n\\n\\n 40\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 41 of 76\\n\\n\\nhas recently recounted how, in response to the turmoil of the mid-60s, President\\n\\nJohnson convened the National Advisory Commission on Civil Disorders (the\\n\\n“Kerner Commission”), which “identified residential segregation and unequal\\n\\nhousing and economic conditions in the inner cities as significant, underlying\\n\\ncauses of the social unrest.” Tex. Dept. of Hous. & Cmty. Affairs v. Inclusive\\n\\nCmtys. Project, Inc., 135 S. Ct. 2507, 2516 (2015). “The Commission concluded\\n\\nthat ‘[o]ur Nation is moving toward two societies, one black, one white—separate\\n\\nand unequal.’” Id. (quoting Report of the National Advisory Commission on Civil\\n\\nDisorders 1 (1968)).\\n\\n In passing the Fair Housing Act, Congress explicitly took aim at these broad\\n\\nsocial ills -- maladies that were being felt on a citywide scale. Congress did not\\n\\njust target individual discriminatory landlords, but sought to reshape in meaningful\\n\\nways the landscape of American cities. Senator Walter Mondale, the chief sponsor\\n\\nof the bill that would become the FHA, explained that the Act was intended to end\\n\\nhousing segregation as a means of bringing about racial equality more broadly.\\n\\nThe legislation’s goals were directed at the neighborhood level and indeed were\\n\\naimed beyond the housing market:\\n\\n [O]vert racial discrimination remains in one major sector of American\\n life—that of housing. . . . [F]air housing is one more step toward\\n achieving equality in opportunity and education . . . . The soundest,\\n long-range way to attack segregated schools is to attack the segregated\\n neighborhood.\\n\\n\\n 41\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 42 of 76\\n\\n\\n114 Cong. Rec. 3421 (Feb. 20, 1968); see also id. at 3422 (“[I]n truly integrated\\n\\nneighborhoods people have been able to live in peace and harmony -- and both\\n\\nNegroes and whites are the richer for the experience.”). A co-sponsor asked, “As\\n\\nsegregation continues to grow . . . will not the cities which house the majority of\\n\\nthe nation’s industrial and commercial life find themselves less and less able to\\n\\ncope with their problems, financially and in every other way?” Id. at 2988 (Feb.\\n\\n14, 1968) (statement of Sen. Brooke). The legislation, as its sponsors saw it, was\\n\\ndesigned to extend through chains of causation. Among other things, its sponsors\\n\\nquite specifically referenced harm to a city’s tax base, arising out of discrimination\\n\\nin the housing market. Senator Mondale put it this way:\\n\\n Declining tax base, poor sanitation, loss of jobs, inadequate educational\\n opportunity, and urban squalor will persist as long as discrimination\\n forces millions to live in the rotting cores of central cities.\\n\\nId. at 2274 (Feb. 6, 1968) (emphasis added).\\n\\n It does not go too far to suggest, at least at a high order of abstraction, that in\\n\\nsetting a standard for proximate cause the FHA looks far beyond the single most\\n\\nimmediate consequence of a violation. Limiting the proximate cause calculus in\\n\\nthat way would not be consonant with the powerful remedial purposes animating\\n\\nthe bill. The Act took aim at “the segregated neighborhood” in general, not just at\\n\\nthe prejudiced building owner.\\n\\n\\n\\n\\n 42\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 43 of 76\\n\\n\\n This is all to say that, notwithstanding issues of proof that might arise later\\n\\nin litigation, the FHA was written in broad terms and was aimed at broad\\n\\nproblems. We can discern no reason to think as a general matter that the City’s\\n\\nclaims are out of step with the “nature of the statutory cause of action” and the\\n\\nremedial scheme that Congress created.\\n\\n C. Tracing causation here is not administratively infeasible\\n\\n Perhaps the most important step in the proximate cause analysis in this case\\n\\nis consideration of “what is administratively possible and convenient.” Bank of\\n\\nAm., 137 S. Ct. at 1306 (quoting Holmes, 503 U.S. at 268). This is because\\n\\nadministrative feasibility is most closely connected to the policy judgments upon\\n\\nwhich proximate cause standards necessarily depend. See Holmes, 503 U.S. at 268\\n\\n(“[P]roximate cause reflects ideas of what justice demands, or of what is\\n\\nadministratively possible and convenient.” (internal quotations omitted)). In no\\n\\nsmall part, we conclude that the City has adequately -- that is to say, plausibly --\\n\\npled proximate cause because we find it entirely practicable and not unduly\\n\\ninconvenient for the courts to handle damages like the City’s tax revenue injury.\\n\\nCases like this will never be among the simplest that our courts see, but the federal\\n\\ncourts regularly handle complex and high-stakes cases, so complexity alone is no\\n\\nreason to dismiss a case on the pleadings. As pled, the City’s injury is\\n\\nascertainable with a sufficient degree of precision for some of its economic\\n\\n\\n 43\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 44 of 76\\n\\n\\ninjuries, specifically the harm to its tax base. Since the City’s injuries are unique\\n\\nto its treasury, no other plaintiff will plead the same injuries, or attempt to recover\\n\\nthe same funds. The City is in the best position to allege and litigate this peculiar\\n\\nkind of injury, to deter future violations and, theoretically, to actually remedy its\\n\\ndistinctive injury.\\n\\n In Holmes v. Securities Investor Protection Corp., 503 U.S. 258 (1992), the\\n\\nCourt conducted a proximate cause analysis focused on administrative feasibility.\\n\\nHolmes involved the Securities Investor Protection Corporation (SIPC), a federally\\n\\ncreated non-profit corporation empowered to sue broker-dealers who “ha[ve] failed\\n\\nor [are] in danger of failing to meet [their] obligations to [their] customers.” Id. at\\n\\n261 (quoting 15 U.S.C. § 78eee(a)(3)). In Holmes, SIPC alleged that broker-\\n\\ndealers manipulated securities in “a ‘pattern of racketeering activity’” that violated\\n\\nRICO, 18 U.S.C. §§ 1962, 1961(1), (5). Holmes, 503 U.S. at 263. The case asked\\n\\nwhether SIPC, “neither a purchaser nor a seller of securities” could sue under\\n\\nRICO even though its claims were, in essence, the same claims that could have\\n\\nbeen brought by investors under Rule 10b–5, under which SIPC lacked standing.\\n\\nId. at 265 n.7.\\n\\n RICO allows for a civil action by “[a]ny person injured in his business or\\n\\nproperty by reason of a violation of section 1962.” Id. at 265 (quoting 18 U.S.C.\\n\\n§ 1964(c)). SIPC claimed that it should be allowed to sue under this provision\\n\\n\\n 44\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 45 of 76\\n\\n\\n“because it [was] subrogated to the rights of those customers of the broker-dealers\\n\\nwho did not purchase manipulated securities.” Id. at 270. The chain of causation\\n\\nwas thus the following: The defendants manipulated securities and broker-dealers\\n\\nbought manipulated securities. The broker-dealers sold some of their customers\\n\\nthese manipulated securities, and their value plummeted when the fraud was\\n\\nexposed. As a result, the broker-dealers could not meet their obligations to their\\n\\ncustomers, including to some who had not even bought manipulated securities. It\\n\\nwas these nonpurchasing customers’ rights that SIPC argued it was subrogated to.\\n\\nSee id. at 270–71. Granting, “arguendo” that SIPC was subrogated as it claimed,\\n\\nHolmes, 503 U.S. at 271, the Court found that “the conspirators’ conduct did not\\n\\nproximately cause the nonpurchasing customers’ injury,” id. at 270.\\n\\n The Court pointed to three distinct reasons why “directness of relationship”\\n\\nwas “one of [the] central elements” of “Clayton Act causation.” Holmes, 503 U.S.\\n\\nat 269. First, less direct injuries are harder to attribute to a violation. Id. Second,\\n\\nclaims at different levels of remove complicated the apportionment of harm among\\n\\nplaintiffs at different levels. Id. Third, directly injured plaintiffs usually can be\\n\\ncounted on to sue and deter wrongdoing. Id. at 269–70. All three reasons for\\n\\ndirectness were said to apply “with equal force” to antitrust and RICO suits. Id. at\\n\\n270. The Court then considered the reasons again in the context of the particular\\n\\nclaims and found that each indicated that SIPC’s claims fell outside the proper\\n\\n\\n 45\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 46 of 76\\n\\n\\nlimits of proximate causation. Id. at 272–74. It would appear, from the Court’s\\n\\nanalysis, that these are not only reasons why “directness of relationship” is\\n\\nrequired, but are also important factors against which to measure the directness of\\n\\nthe relationship.\\n\\n When applied to the City’s claims against the Banks, these factors strongly\\n\\nsuggest that the City has plausibly alleged “some direct relation” between the\\n\\nBanks’ alleged conduct and the injury to the City’s tax revenue. We cannot say the\\n\\nsame for the increased-expenditures injury, though. Here, we review how each of\\n\\nthe Holmes factors applies to the City’s economic injuries, distinguishing, when\\n\\nrelevant, between the tax-revenue injury and the increased-expenditures injury.\\n\\nFinally, we explain how the Holmes factors provide a clear means by which to\\n\\ncabin liability and prevent suits by more remotely injured parties.\\n\\n 1.\\n\\n Holmes’s first factor says that directness is required because “the less direct\\n\\nan injury is, the more difficult it becomes to ascertain the amount of a plaintiff’s\\n\\ndamages attributable to the violation, as distinct from other, independent, factors.”\\n\\nHolmes, 503 U.S. at 269. In Holmes, this factor decidedly cut against finding a\\n\\nsufficiently direct relationship because it would have required the district court “to\\n\\ndetermine the extent to which [the nonpurchasing customers’] inability to collect\\n\\nfrom the broker-dealers was the result of the alleged conspiracy to manipulate, as\\n\\n\\n 46\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 47 of 76\\n\\n\\nopposed to” any other reasons why the broker-dealers might not have money on\\n\\nhand (such as “poor business practices,” and the “failure to anticipate\\n\\ndevelopments in the financial markets”). Id. at 273. On this first factor, the City’s\\n\\ntax-revenue injury fares well, and its municipal-expenditures injury fares poorly.\\n\\nThe City has plausibly alleged that it can present an analysis of reduced tax\\n\\nrevenue that is precise enough to avoid difficulties with isolating the role of the\\n\\nBanks’ alleged violations. It has not done so for its municipal expenditures.\\n\\n In its complaints, the City of Miami’s tax-revenue injury seeks damages\\n\\n“based upon reduced property tax revenues resulting from (a) the decreased value\\n\\nof the vacant properties themselves, and (b) the decreased value of properties\\n\\nsurrounding the vacant properties.” BoA FAC at 31; WF FAC at 44. According to\\n\\nthe City, “[r]outinely maintained property tax and other data allow for the precise\\n\\ncalculation of the property tax revenues lost by the City as a direct result of\\n\\nparticular [bank] foreclosures.” BoA FAC at 32; WF FAC at 45. This “Hedonic\\n\\nregression methodology,” the City asserts, “can be used to quantify precisely the\\n\\nproperty tax injury to the City caused by [the Banks’] discriminatory lending\\n\\npractices and resulting foreclosures in minority neighborhoods.” BoA FAC at 34;\\n\\nWF FAC at 47.\\n\\n The City does not go so far as to conduct this analysis and attach the results\\n\\nto its pleadings, but its First Amended Complaints nonetheless suffice to describe\\n\\n\\n 47\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 48 of 76\\n\\n\\nthe analysis in far more than speculative or conclusory fashion. The City has\\n\\nexplained in some detail how this analysis works:\\n\\n Homes in foreclosure tend to experience a substantial decline in\\n value . . . [F]oreclosure properties and the problems associated with\\n them likewise cause especially significant declines in surrounding\\n property values because the neighborhoods become less desirable. . . .\\n Routinely maintained property tax and other data allow for the\\n precise calculation of the property tax revenues lost by the City as a\\n direct result of particular [bank] foreclosures. Using a well-established\\n statistical regression technique that focuses on effects on neighboring\\n properties, the City can isolate the lost property value attributable to\\n [the Banks’] foreclosures and vacancies from losses attributable to\\n other causes, such as neighborhood conditions. This technique, known\\n as Hedonic regression, when applied to housing markets, isolates the\\n factors that contribute to the value of a property by studying thousands\\n of housing transactions. Those factors include the size of a home, the\\n number of bedrooms and bathrooms, whether the neighborhood is safe,\\n whether neighboring properties are well-maintained, and more.\\n Hedonic analysis determines the contribution of each of these house\\n and neighborhood characteristics to the value of a home.\\n\\nBoA FAC at 32–33; WF FAC at 45–46. 6 This gives us a clear idea of the final\\n\\nanalysis -- based on empirical data drawn from thousands of housing transactions,\\n\\nthe City will calculate the impact of the Banks’ foreclosures on property values in\\n\\nredlined (and reverse-redlined) areas of Miami, controlling for other variables and\\n\\nisolating the impact of the redlining. The City points to studies in which this\\n\\n\\n\\n6\\n Wells Fargo says that the City pleads “that it could conduct a study that might be able to show\\nthat foreclosures affect property values.” (emphases in original). The City’s pleading does not\\nhedge its allegations in this way, and discounting the feasibility of its analysis on the front end is\\ninconsistent with our obligation to draw all reasonable inferences in the City’s favor at this\\npreliminary stage.\\n\\n 48\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 49 of 76\\n\\n\\nmethodology has produced the kind of results the City will need to present. BoA\\n\\nFAC at 33–34; WF FAC 46–47. The complaints conclude, then, that\\n\\n“[a]pplication of such Hedonic regression methodology . . . can be used to quantify\\n\\nprecisely the property tax injury to the City caused by [the Banks’] discriminatory\\n\\nlending practices and resulting foreclosures.” BoA FAC at 34; WF FAC at 47.\\n\\n The pleadings strongly suggest, then, that the tax-revenue injury to the City\\n\\nattributable to the Banks’ alleged discriminatory practices is readily calculable.\\n\\nUnder Twombly and Iqbal a mere statement that “[the Banks] caused the loss of\\n\\nproperty tax revenue” would be wholly conclusory and would be disregarded. But\\n\\nby indicating and explaining at considerable length the kind of analysis that would\\n\\nbe conducted to quantify the loss of revenue attributable to discriminatory lending,\\n\\nthe City has plausibly alleged a calculable harm and has made more than a\\n\\nformulaic recitation of how the causation requirement will be met. There could be\\n\\na battle of experts down the line over whether the regression analysis really shows\\n\\nwhat the City says it does, but, as we see it, that would be for a later stage of the\\n\\nlitigation. The complaints’ allegation that regression analysis can pinpoint\\n\\ncausation is sufficient at this stage and helps account for the concerns raised by this\\n\\nfirst factor.\\n\\n The plausibility of hedonic regression analysis has a direct bearing on how\\n\\n“difficult it [is] to ascertain the amount of [the City’s] damage attributable to the\\n\\n\\n 49\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 50 of 76\\n\\n\\nviolation, as distinct from other, independent, factors,” Holmes, 503 U.S. at 269,\\n\\nand thus helps determine “what is administratively possible and convenient,” in\\n\\nterms of damages calculation, Bank of Am., 137 S. Ct. at 1306. Here, the City has\\n\\nplausibly pled that it is practicable and convenient to quantify the property tax\\n\\ninjury’s causal connection to the Banks’ policies. In addition to the studies\\n\\nidentified by the City, we note in passing there has been a substantial amount of\\n\\nwriting (including legal literature) that has discussed or employed hedonic\\n\\nregression analysis as a practicable and effective way of calculating impacts on\\n\\nreal estate values.7 One author at the University of Wisconsin School of Business\\n\\nhas written that “[o]ver the past three decades, hedonic estimation has clearly\\n\\nmatured from a new technology to become the standard way economists deal with\\n\\nhousing heterogeneity.” 8 Likewise, the Organisation for Economic Co-operation\\n\\nand Development’s (OECD) Handbook on Residential Property Prices Indices\\n\\n(RPPI) calls hedonic regression “probably the best method that could be used in\\n\\norder to construct quality RPPIs for various types of property.” 9 While we may\\n\\n\\n7\\n See, e.g., Yun-Chien Chang, Economic Value or Fair Market Value: What Form of Takings\\nCompensation is Efficient?, 20 SUP. CT. ECON. REV. 35, 52–54 (2012); Yun-Chien Chang & Lee\\nAnne Fennell, Partition and Revelation, 81 U. CHI. L. REV. 27, 35 n.35(2014); Randall Akee,\\nCheckerboards and Coase: The Effect of Property Institutions on Efficiency in Housing Markets,\\n52 J.L. & ECON. 395, 402–03 (2009).\\n8\\n Stephen Malpezzi, Hedonic Pricing Models: A Selective and Applied Review, in HOUSING\\nECONOMICS AND PUBLIC POLICY 67, 87 (Tony O’Sullivan & Kenneth Gibb eds., 2003).\\n9\\n OECD, Hedonic Regression Methods, in HANDBOOK ON RESIDENTIAL PROPERTY PRICE INDICES\\n50, 57 (2003).\\n\\n 50\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 51 of 76\\n\\n\\nnot engage in a Daubert analysis at this early stage, that hedonic regression\\n\\nanalysis has been favorably referenced and employed elsewhere and over several\\n\\ndecades cuts against the suggestion at the motion to dismiss stage that it is a wholly\\n\\nimplausible invention of the City’s or that apportioning blame through its\\n\\napplication would be so challenging that the complaints cannot state a claim.\\n\\n At a more basic level, the aggregative nature of the City’s claims also helps\\n\\neliminate any discontinuity between the statutory violation and the injury. See\\n\\nLexmark, 134 S. Ct. at 1394. Here, the claimed violation is a “pattern or practice\\n\\nof reverse redlining” leading to a “disproportionately high rate of foreclosure.”\\n\\nBoA FAC at 30; WF FAC at 43. Even if each individual act of redlining does not\\n\\nbear a one-to-one proportional relationship to Miami’s loss of tax revenue, see\\n\\nLexmark, 134 S. Ct. at 1394, since intervening circumstances affect which\\n\\nindividual properties go into foreclosure, in the aggregate it has been plausibly\\n\\nalleged that the impact of redlining and reverse-redlining can be identified with\\n\\nprecision and deterred. Similarly, in Blue Shield, the Court identified “the physical\\n\\nand economic nexus between the alleged violation and the harm to the plaintiff” as\\n\\na factor to consider when applying proximate cause to the Clayton Act. Blue\\n\\nShield, 457 U.S. at 478. The scale of the misconduct matches the scale of the\\n\\ninjury.\\n\\n\\n\\n\\n 51\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 52 of 76\\n\\n\\n Since the Supreme Court spoke to this issue in Bank of America, two district\\n\\ncourts analyzing similar FHA claims by municipalities against lending institutions\\n\\nhave relied on the availability of regression analysis in finding that proximate\\n\\ncause had been plausibly alleged. Most similarly and most recently, a district court\\n\\nin the Northern District of California entertained a similar case brought by the City\\n\\nof Oakland against Wells Fargo for predatory lending practices. City of Oakland\\n\\nv. Wells Fargo Bank, N.A., No. 15-cv-04321, 2018 WL 3008538 (N.D. Cal. June\\n\\n15, 2018). 10 In denying a motion to dismiss that court recognized, as we have, that\\n\\n“[w]hile the fact of aggregative injury itself does not obviate proximate cause\\n\\nanalysis,” the proffer of “a specific statistical analysis in regard to [the City’s]\\n\\nproperty tax injury” adequately supports the idea that there was “an alleged\\n\\nprovable and quantifiable causal link between the defendant’s conduct and\\n\\nplaintiff’s injury” notwithstanding the suggested length of the causal chain. Id. at\\n\\n*8. But when it came to a municipal-expenditures injury -- similar to Miami’s --\\n\\nthe district court ruled that since “Oakland ha[d] not proffered any statistical\\n\\n\\n\\n10\\n After this decision, the district court in the Oakland case certified two questions for\\ninterlocutory appeal to the Ninth Circuit: “(1) Do Oakland’s claims for damages based on the\\ninjuries asserted in the [First Amended Complaint] satisfy on a motion to dismiss proximate\\ncause required by the FHA?” and “(2) Is the proximate-cause requirement articulated in City of\\nMiami limited to claims for damages under the FHA and not to claims for injunctive or\\ndeclaratory relief?” Order Granting Defendant’s Motion to Amend Order to Include\\nCertification for Interlocutory Appeal, City of Oakland, No. 15-cv-04321, 2018 WL 7575537 at\\n*2. The parties’ briefs before the Ninth Circuit are due in June and July of 2019. City of\\nOakland v. Wells Fargo & Co., No. 19-15169 (9th Cir. Mar. 26, 2019), ECF No. 10.\\n\\n 52\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 53 of 76\\n\\n\\nanalyses comparable to those in the property-tax analysis,” the first Holmes factor\\n\\ncounted against them and problems of multiple causation abounded. Id. at *10.\\n\\nThose claims were dismissed without prejudice. Id. A district court in\\n\\nPhiladelphia found that city had “adequately [pled] proximate cause for . . . non-\\n\\neconomic injuries” stemming from FHA violations in part by relying on “a\\n\\nregression analysis of [bank] loan data” that had demonstrated Latino and African-\\n\\nAmerican borrowers were 2.641 and 4.147 times more likely to go into foreclosure\\n\\nthan similarly situated white borrowers. City of Philadelphia v. Wells Fargo &\\n\\nCo., No. 17-2203, 2018 WL 424451 (E.D. Pa. Jan. 16, 2018).\\n\\n In describing its second claimed economic injury -- increased municipal\\n\\nexpenditures for police, fire, sanitation, and the like resulting from widespread\\n\\nforeclosures -- the City does not do as well when measured against the first\\n\\nHolmes factor. When it comes to this injury, the City’s complaints fail to explain\\n\\nhow we can ascertain with any level of detail or precision which expenditures will\\n\\nbe attributable to the Banks. It is self-evident that this must be accomplished\\n\\nsomehow because the entire increase in municipal expenditures over any time\\n\\nperiod cannot possibly be fairly attributed to the Banks’ conduct. Intervening\\n\\ncauses and independent variables will inevitably run up this measure of damages\\n\\nbecause the City’s expenditures occur at some obvious level of remove from the\\n\\nforeclosures that it says cause them. They are further down the chain, to put it in\\n\\n\\n 53\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 54 of 76\\n\\n\\nstep-counting terms. There is nothing in the pleadings that suggests the plaintiff\\n\\nwill be able to sort out the extent to which these damages are attributable to the\\n\\nBanks’ misconduct.\\n\\n The City’s pleadings on increased expenditures are in stark contrast to their\\n\\npleadings about tax revenue. The increased expenditures pleadings state, in almost\\n\\nconclusory fashion, that “the City is required to provide increased municipal\\n\\nservices” at foreclosed properties and that “these services would not have been\\n\\nnecessary if the properties had not been foreclosed upon.” BoA FAC at 34; WF\\n\\nFAC at 47. The complaints then proceed to list types of expenditures: police, fire,\\n\\nbuilding code enforcement, and the like. If any direct connections exist between\\n\\nthe foreclosure and any of these expenditures, the City has not explained them, and\\n\\nthey are not so obvious as to be self-evident. We also see no explanation of how\\n\\nthe City will identify the amount of increase attributable to the foreclosures or to\\n\\nthe Banks’ conduct. In pleading the tax-revenue injury, however, the City explains\\n\\nin considerable detail how hedonic regression analysis will help pinpoint the\\n\\nattributable loss. This is not to say that hedonic regression analysis, specifically,\\n\\nshould have been referenced again in relation to the expenditure injury in order to\\n\\nsatisfy the first Holmes factor. Rather we suggest only that a pleading in a case\\n\\nlike this must make clear how a plaintiff will demonstrate that an injury is\\n\\n\\n\\n\\n 54\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 55 of 76\\n\\n\\nattributable to a defendant. Hedonic regression serves this role with regard to the\\n\\ntax-revenue injury, but may not be the only way this could ever be accomplished.11\\n\\n The first Holmes factor, addressing the attributability of the injury to the\\n\\ndefendant’s conduct, is where the two economic injuries alleged by the City are\\n\\nmost different in terms of finding a “direct relation.” The tax-revenue injury has\\n\\nbeen pled with detailed explanations of statistical proof, which serve to plausibly\\n\\nallege that the courts will be able to work out just what the Banks can be fairly held\\n\\naccountable for. The municipal-expenditure injury fails to do this. Statistical\\n\\nproofs are not the only method of proof, but, when we readily discern a\\n\\ndiscontinuity between misconduct and injury, for the plaintiff to plausibly plead\\n\\nproximate cause, it must allege something more with which to bridge the gap and\\n\\ndemonstrate that the defendant’s liability will bear “some direct relation” to its\\n\\n\\n\\n11\\n A few other district courts have illustrated the point. In three lawsuits against banks alleging\\nthe same kinds of practices that Miami has alleged, Cook County, Illinois claimed damages\\nbased on “out-of-pocket costs it . . . incurred in processing the discriminatory foreclosures, such\\nas additional funding for the Cook County Sheriff to serve foreclosure notices and for the Circuit\\nCourt of Cook County to process the deluge of foreclosures.” County of Cook v. Bank of Am.\\nCorp., No. 14 C 2280, 2018 WL 1561725 at *7 (N.D. Ill. Mar. 30, 2018); see also County of\\nCook, Ill. v. HSBC N. Am. Holdings, 314 F. Supp. 3d 950, 956 (N.D. Ill. 2018); County of\\nCook, Ill. v. Wells Fargo & Co., 314 F. Supp. 3d 975, 982 (N.D. Ill. 2018). Those out-of-pocket\\ncosts were found to have plausibly been proximately caused by the banks because these\\nexpenditures are automatic results of foreclosures. See HSBC, 314 F. Supp. 3d at 962; Wells\\nFargo, 314 F. Supp. 3d at 984; Bank of Am., 2018 WL 1561725 at *7. These were the only\\nclaimed damages that survived a motion dismiss in the Northern District of Illinois, as all three\\ncourts there found that Cook County had failed to adequately plead proximate cause for the kinds\\nof tax-revenue and municipal-expenditure injuries that Miami pleads here. See HSBC, 913 F.\\nSupp. 3d at 962–64; Wells Fargo, 314 F. Supp. 3d at 988; Bank of Am., 2018 WL 1561725 at\\n*5. Miami pled no out-of-pocket costs closely tied to foreclosures along these lines.\\n 55\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 56 of 76\\n\\n\\nactions. On the increased-expenditure injury, the City has not plausibly pled its\\n\\ncase.\\n\\n 2.\\n\\n Holmes’s second factor posits that “recognizing claims of the indirectly\\n\\ninjured would force courts to adopt complicated rules apportioning damages\\n\\namong plaintiffs removed at different levels of injury from the violative acts, to\\n\\nobviate the risk of multiple recoveries.” Holmes, 503 U.S. at 269. In Holmes, this\\n\\nwas a problem because a trial court would “have to find some way to apportion the\\n\\npossible respective recoveries by the broker-dealers and the customers, who would\\n\\notherwise each be entitled to recover the full treble damages.” Id. at 273. Antitrust\\n\\ncases also emphasize “the risk of duplicative recovery engendered by allowing\\n\\nevery person along a chain of distribution to claim damages” from a single\\n\\nviolation, and have identified this as a powerful reason to allow suit only by more\\n\\ndirectly injured parties. Blue Shield, 457 U.S. at 474–75 (citing Ill. Brick Co. v.\\n\\nIllinois, 431 U.S. 720, 745 (1977); Hawaii v. Standard Oil Co. of Cal., 405 U.S.\\n\\n251 (1972)).\\n\\n Again, no such problem is presented in this case: plainly, the injuries to the\\n\\nCity’s treasury are not shared by any other possible plaintiff. These economic\\n\\ninjuries, whether or not they can ultimately be recovered for, could only be alleged\\n\\nby the City. The City’s theory, therefore, presents no concern about double\\n\\n\\n 56\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 57 of 76\\n\\n\\nrecovery or “piggy-backing,” precisely because its injuries are unique.\\n\\nSubstantially decreased tax revenue and increased municipal costs are injuries that\\n\\naffect the interests of the City alone, so there could not plausibly be any difficulty\\n\\nin apportioning them between multiple plaintiffs. The harm and damages pled by\\n\\nindividual homeowners suing under the FHA would be entirely different. These\\n\\nplaintiffs could sue for actual and punitive damages, injunctive and equitable relief,\\n\\nor attorney’s fees. See 42 U.S.C. § 3613(c). In this Circuit they could also seek\\n\\ndamages based on “anger, embarrassment, and emotional distress.” Banai v.\\n\\nSec’y, U.S. Dep’t of Hous. & Urban Dev. ex rel. Times, 102 F.3d 1203, 1207 (11th\\n\\nCir. 1997). Many courts have permitted FHA plaintiffs to recover pecuniary\\n\\ndamages, including moving costs and forfeited security deposits. E.g., Belcher v.\\n\\nGrand Reserve MGM, LLC, 269 F. Supp. 3d 1219, 1239 (M.D. Ala. 2017). But no\\n\\ncourt could allow a homeowner to recover for harm to a city’s treasury.\\n\\n The City, on the other hand, has claimed it was financially harmed in two\\n\\nways -- injury to its tax base and tax revenue because of reduced property value,\\n\\nand increased expenditures on City services in certain neighborhoods. The\\n\\ndamages that these harms could support do not overlap in any way with or\\n\\nduplicate the damages that individual homeowners may have sustained, because\\n\\nthe harms are entirely separate. The City’s injuries would be “passed on” forms of\\n\\nthe homeowners’ injuries if, for example, it were claiming it lost tax revenue\\n\\n\\n 57\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 58 of 76\\n\\n\\nbecause homeowners who were overpaying on their mortgages were subsequently\\n\\nunable to pay their taxes. But this is not the case. The City alleges instead that the\\n\\nBanks’ misconduct had a direct, necessary, and immediate impact on its fiscal\\n\\nhealth at the neighborhood and citywide level. The homeowners’ losses are\\n\\nobviously related to the losses that Miami allegedly incurred, but they are\\n\\nindependent. Injury to the City’s treasury is a distinct injury, it is not purely\\n\\nderivative of misfortunes visited on homeowners. Even if we were to assume that\\n\\neach victim of discrimination were to successfully bring an individual claim -- a\\n\\nwholly implausible hypothesis -- the City would still have an independent set of\\n\\nclaims based on the independent harm that it suffered. The claims would be linked\\n\\nonly by shared facts surrounding the violation.\\n\\n 3.\\n\\n Holmes’s final factor builds on the first two: “[T]he need to grapple with\\n\\nthese problems,” the Court said, referring to the first two factors, “is simply\\n\\nunjustified by the general interest in deterring injurious conduct, since directly\\n\\ninjured victims can generally be counted on to vindicate the law as private\\n\\nattorneys general, without any of the problems attendant upon suits by plaintiffs\\n\\ninjured more remotely.” Id. at 269–70. Thus, in Holmes, the directly injured\\n\\nbroker-dealers “could be counted on to bring suit for the law’s vindication,” and so\\n\\nit was less necessary for SIPC to sue on behalf of the broker-dealers’ customers.\\n\\n\\n 58\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 59 of 76\\n\\n\\nId. at 273. In Bridge, the same factor cut in the other direction; the plaintiffs were\\n\\ninjured because they had less success at county-run auctions when the defendants\\n\\ncheated, and their harm was “the direct result of [defendant’s] fraud” in part\\n\\nbecause, even though the plaintiffs didn’t themselves rely on any fraudulent\\n\\nassertions, “no more immediate victim is better situated to sue.” Bridge, 553 U.S.\\n\\nat 658.\\n\\n The third Holmes factor has been applied to antitrust statutes as well. The\\n\\navailability of more directly injured plaintiffs influenced the Court’s determination\\n\\nthat “directness” between the plaintiff’s injury and the defendant’s action was\\n\\nlacking in Associated General Contractors of California, Inc. v. Carpenters, 459\\n\\nU.S. 519, 540–41 (1983). There, a union alleged that the defendant employer\\n\\nassociation had “coerced certain third parties . . . to enter into business\\n\\nrelationships with nonunion firms” in a way that violated the Clayton Act. Id. at\\n\\n520–21. This hurt unionized firms and, thus, hurt the plaintiff union. Id. The\\n\\nCourt found that the union had not alleged a sufficiently direct injury, noting that:\\n\\n The existence of an identifiable class of persons whose self-interest\\n would normally motivate them to vindicate the public interest in\\n antitrust enforcement diminishes the justification for allowing a more\\n remote party such as the Union to perform the office of a private\\n attorney general. Denying the Union a remedy on the basis of its\\n allegations in this case is not likely to leave a significant antitrust\\n violation undetected or unremedied.\\n\\nId. at 542.\\n\\n\\n 59\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 60 of 76\\n\\n\\n In these kinds of cases it is preferable for more directly injured plaintiffs to\\n\\ntake the lead in acting as private attorneys general because those plaintiffs will be\\n\\nable to deter future violations more effectively and efficiently. When more directly\\n\\ninjured parties can sue for the full swath of harm caused by statutory violations, the\\n\\nthreat of suit by these parties has the maximum possible deterrent effect on\\n\\npotential violators, and it’s simply not worthwhile to also allow minimally\\n\\ndeterring suits by plaintiffs farther down the causal chain. Cf. Southern Pac. Co. v.\\n\\nDarnell-Taenzer Lumber Co., 245 U.S. 531, 534 (1918) (“The [defendant] ought\\n\\nnot to be allowed to retain his illegal profit, and the only one who can take it from\\n\\nhim is the one that alone was in relation with him, and from whom the [defendant]\\n\\ntook the sum.”) (Holmes, J.).\\n\\n Thus, in antitrust cases the courts have long expressed a “concern for the\\n\\nreduction in the effectiveness of those suits if brought by indirect purchasers with a\\n\\nsmaller stake in the outcome than that of direct purchasers suing for the full\\n\\namount of the overcharge.” Ill. Brick Co., 431 U.S. at 745; see also Lexmark, 134\\n\\nS. Ct. at 1391 (establishing, for the Lanham Act, a rule barring suit by\\n\\n“commercial parties who suffer merely as a result of [a direct] competitor’s\\n\\n‘inability to meet [its] financial obligations’” (quoting Anza, 547 U.S. at 458)).\\n\\nFor this reason, the federal courts have rejected the monopolist’s “passing on”\\n\\ndefense -- the argument that mid-stream purchasers charged monopoly prices are\\n\\n\\n 60\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 61 of 76\\n\\n\\nnot harmed because they can “pass on” any overcharges to consumers. See\\n\\nRichard A. Posner, Economic Analysis of Law 395–96 (9th ed. 2014). Consumers\\n\\ncannot sue over monopoly pricing, but this does not mean there is a meaningful\\n\\nreduction in enforcement. See id. at 396 (“[Consumers’] right [to sue] is less\\n\\nvaluable because, being at once more remote . . . and more numerous, consumers\\n\\nare less efficient antitrust enforcers.”).\\n\\n The same logic surrounding deterrence does not apply here. While the City\\n\\nmay be a step further down the chain of causation, the homeowners are much more\\n\\nnumerous and less well suited to prosecute a global claim. The City’s suit could\\n\\nachieve better deterrence because it aims to recover for a larger injury sustained on\\n\\na citywide basis and to remedy a different, broader violation than a homeowner’s\\n\\nsuit would. The City alleges widespread redlining and reverse-redlining policies\\n\\nconducted by the Banks. The City’s suit challenges the entire policies. A\\n\\ndiscrimination claim by an individual homeowner would challenge only a bank’s\\n\\ndiscriminatory action against that homeowner. Conceivably the banks could face\\n\\nsuits by many homeowners who were discriminated against, or who lost property\\n\\nvalue because their neighbors’ houses were foreclosed on, but these suits wouldn’t\\n\\nserve to condemn the pattern or policy. Individual homeowners would also face\\n\\nmost of the same causation problems -- presumably a variety of factors contributed\\n\\nto any individual foreclosure -- but the regression analysis that can isolate the\\n\\n\\n 61\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 62 of 76\\n\\n\\nimpact of redlining on the neighborhood scale could not solve this problem on the\\n\\nindividual level because of the diversity of individual circumstances.\\n\\n Moreover, even if homeowners were better-situated to vindicate the same\\n\\nwrongdoing -- and that is plainly not the case here -- the additional assumption that\\n\\nothers will pursue the lawsuits and achieve deterrence is nowhere near as likely\\n\\ntrue under the FHA as under the other statutes. Antitrust and, to a lesser extent,\\n\\ncivil RICO suits are typically brought by sophisticated business entities, often with\\n\\ndeep pockets, and those plaintiffs also have the added incentive of realizing treble\\n\\ndamages. In Holmes and Associated General Contractors, the Court left the job of\\n\\ndeterring statutory violations to broker-dealers and businesses using union labor.\\n\\nThese parties were subject to complex regulatory environments and undoubtedly\\n\\nhad counsel in place prepared to sue to vindicate their rights. Here, instead, the\\n\\nalternative plaintiffs are homeowners whose homes were foreclosed upon.\\n\\nCompared with the sophisticated parties involved in the RICO and antitrust cases,\\n\\nit seems far less likely that these injured parties could be counted on to file suit.\\n\\nWhile it’s possible that some might, it seems exceedingly unlikely that more than a\\n\\nhandful at most would do so, and we have seen precious little reason to believe that\\n\\nmany have. The vast majority of individual cases of discriminatory lending cases\\n\\nare left unpursued and unaddressed. In Associated General, the Court observed\\n\\nthat “[d]enying the [plaintiff] a remedy on the basis of its allegations in this case\\n\\n\\n 62\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 63 of 76\\n\\n\\n[was] not likely to leave a significant [statutory] violation undetected or\\n\\nunremedied.” 459 U.S. at 542. That’s less plausible here.\\n\\n As a result, the peculiarities surrounding the claims raised in this case make\\n\\nit distinct from an antitrust case where a mid-stream purchaser can bring\\n\\nessentially the same action against a monopolist as the ultimate consumer would.\\n\\nThe question of efficacy is harder to resolve here because, although the\\n\\nhomeowners are arguably closer in the chain, they are too numerous and diffuse to\\n\\nbe counted on for deterrence. They are better situated only in a narrow, literal\\n\\nsense. The City, on the other hand, has plausibly alleged an injury, calculable in\\n\\nthe aggregate, that bears a direct relation to the Banks’ policies, applied in the\\n\\naggregate, which allegedly violated the statute.\\n\\n 4.\\n\\n The Holmes factors also help cabin proximate cause against other less-\\n\\ndirectly injured plaintiffs. Writing separately in Bank of America, Justice Thomas\\n\\nsuggested that Miami’s theory of causation would require that neighboring\\n\\nhomeowners who were not foreclosed on but whose property values fell could also\\n\\nsue the banks. 137 S. Ct. at 1312 (Thomas, J., concurring in part and dissenting in\\n\\npart). Still other concerns have been raised about the corner grocer who may have\\n\\nlost business on account of foreclosures, the utility company, or maybe even real\\n\\nestate brokers working on commission to resell properties in the area. The Court’s\\n\\n\\n 63\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 64 of 76\\n\\n\\nown guidance from Holmes, attuned as it is to the administrative practicalities, can\\n\\ngo a long way toward allaying these concerns. Application of the Holmes factors\\n\\nreasonably establishes that the City’s injury is logically bound up with the Banks’\\n\\nalleged conduct in meaningful ways missing from injuries to these other putative\\n\\nclaimants.\\n\\n To begin with the first factor, corner grocers or neighboring property\\n\\nowners, unlike the City, would have substantially more difficulty plausibly\\n\\nalleging that they could calculate damages attributable to the Banks’ actions with a\\n\\nreasonable degree of certainty. By contrast, hedonic regression techniques are\\n\\nmost effective when applied on a neighborhood or citywide level, precisely\\n\\nbecause individual variations among homeowners average out when foreclosures\\n\\nare considered in the aggregate. Indeed the amended complaints specifically cite\\n\\nto a study showing that each foreclosure in Chicago was “responsible for an\\n\\naverage decline of approximately 1.1% in the value of each single-family home\\n\\nwithin an eighth of a mile.” BoA FAC at 33; WF FAC at 46. The average decline\\n\\ncan be used to calculate the impact of foreclosures on property value across a\\n\\nneighborhood on account of the large sample size. A neighboring homeowner, on\\n\\nthe other hand, would be affected only by homes closest to his own, and these\\n\\nmight not accurately reflect the citywide average, in terms of causation or value.\\n\\nAnd a corner grocer might be affected by the surrounding few blocks of homes, but\\n\\n\\n 64\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 65 of 76\\n\\n\\nthis may be wholly unrepresentative of citywide trends, making causal attribution\\n\\nto redlining all the more difficult.\\n\\n Put another way, in step-counting terms, the grocer or the utility company is\\n\\ndemonstrably further down the causal chain because many independent variables\\n\\ncan enter the equation after foreclosure occurs. The City will necessarily be\\n\\nharmed as soon as the foreclosures occur. For the grocer, though, a nearby home’s\\n\\nforeclosure does not necessarily mean anything. The causal chain for the grocer is\\n\\nlonger, more attenuated, and more of a problem for proximate cause analysis\\n\\nbecause there is a powerful discontinuity between the foreclosures and the grocer’s\\n\\nloss of profits. It would therefore be exceedingly difficult to trace causation from\\n\\nthe Banks’ predatory practices through the foreclosures to the grocers’ diminished\\n\\nprofits. The corner grocer, or the utility company, is not affected when a home is\\n\\nforeclosed or when property values go down. These parties are not hurt until\\n\\nindividual homeowners decide to spend less money at that grocer, decide not to\\n\\npay the electric bill, or move away. Thus, there are many more third parties, and\\n\\nmany more intervening steps when it comes to the corner grocer or the utility\\n\\ncompany. When a homeowner is given a bad, discriminatory loan, the injury to\\n\\none of these more distant plaintiffs is in no sense “automatic[],” Lexmark, 134 S.\\n\\nCt. at 1394; it therefore becomes harder to attribute back to the Banks.\\n\\n\\n\\n\\n 65\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 66 of 76\\n\\n\\n The application of the second Holmes factor also strongly suggests why any\\n\\ninjury sustained by the corner grocer or by the utility company would not be\\n\\nproximately caused by the Banks’ conduct. These are classic “passed on” injuries.\\n\\nThe Court has consistently said that “where the alleged violations [are] linked to\\n\\nthe asserted harms only through the [directly injured parties’] inability to meet\\n\\ntheir financial obligations” proximate cause will not be found. Anza, 547 U.S. at\\n\\n458; see also Lexmark, 1391 S. Ct. at 1391 (referencing “the electric company,”\\n\\nspecifically, as an entity in this sort of position); Holmes, 503 U.S. at 271.\\n\\nIndividual homeowners have financial obligations to the City in the form of\\n\\nproperty taxes, but the City’s claim is not that it is harmed because property taxes\\n\\nwent unpaid. Rather, the City says that property values decreased and that\\n\\ntherefore it was not entitled to as much property-tax revenue. The City’s loss is\\n\\nnot due to anyone lacking “the wherewithal to pay,” Holmes, 503 U.S. at 271, but\\n\\nto the fact that redlining means the City is not able to collect nearly as much as it\\n\\nwould have, had the alleged FHA violations not occurred in the first place.\\n\\n The third Holmes factor -- the reliability with which a plaintiff could remedy\\n\\nharm or achieve deterrence -- also strongly suggests that we need not fear a deluge\\n\\nof suits by grocers, neighbors, or power companies. These potential plaintiffs,\\n\\neven if injured, would be in a far weaker position and far less likely than the City\\n\\nto achieve deterrence or to remedy the entirety of the harm caused by the Banks’\\n\\n\\n 66\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 67 of 76\\n\\n\\nalleged violations. Their claims would be disjointed, aimed at remedying FHA\\n\\nviolations only on particular blocks, in contrast to the City’s unique ability to\\n\\nattack the Banks’ whole pattern or practice on a municipal level. Any claims by\\n\\nthe corner grocer or the neighboring homeowner would be further out in the chain\\n\\nof causation than the City is, and these claims would lack the broad scope that\\n\\nallows the City to achieve maximal deterrence. Quite simply, they would face far\\n\\ntougher versions of all the challenges the City faces, but with none of the offsetting\\n\\nadvantages.\\n\\n As we see it, the factors articulated by the Supreme Court in Holmes cabin\\n\\nthis decision and keep the floodgates closed. But these factors are not the only\\n\\nreason our ruling does not extend liability beyond what is reasonable.\\n\\nForeseeability remains a real part of the proximate cause calculation and also will\\n\\nfunction to cut off liability in many instances. Dan B. Dobbs, Paul T. Hayden &\\n\\nEllen M. Bublick, The Law of Torts § 199, at 686 (2d ed. 2011) (“The defendant\\n\\nmust have been reasonably able to foresee the kind of harm that was actually\\n\\nsuffered by the plaintiff . . . .”). We are exceedingly dubious that courts would\\n\\nexpect lenders to reasonably foresee unending ripples of harm that overwhelm the\\n\\njudicial branch.\\n\\n\\n\\n\\n 67\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 68 of 76\\n\\n\\n D. Common-law antecedents require direct relation\\n\\n The Court has also told us that the FHA’s common-law antecedents are a\\n\\nprimary reason why “proximate cause under the FHA requires ‘some direct\\n\\nrelation between the injury asserted and the injurious conduct alleged.’” Bank of\\n\\nAm., 137 S. Ct. at 1306. As a result, we know that “[a] damages claim under the\\n\\n[FHA] ‘is analogous to a number of tort actions recognized at common law,’” and\\n\\nthat “directness principles” thus apply. Id. We also observed, in our previous\\n\\nopinions, that FHA damages claims “have long been analogized to tort claims.”\\n\\nSee Bank of Am., 800 F.3d at 1282. These analogues, however, only take us so\\n\\nfar. They do not help flesh out the meaning of “direct relation,” even though they\\n\\nare the basis for imposing the requirement.\\n\\n The Court identified some common-law claims that are analogues for FHA\\n\\nclaims in Curtis v. Loether, 415 U.S. 189 (1973). See Bank of Am., 137 S. Ct. at\\n\\n1306 (citing Curtis for the proposition that an FHA damages claim is analogous to\\n\\ncertain common-law torts). There, the Court was evaluating whether the Seventh\\n\\nAmendment, which guarantees jury trials for “suits at common law,” guaranteed a\\n\\njury in an FHA suit. U.S. CONST. amend VII; see Curtis, 415 U.S. at 190. The\\n\\nCourt said it did, because FHA claims for housing discrimination were comparable\\n\\nto “the common-law duty of innkeepers not to refuse temporary lodging to a\\n\\n\\n\\n\\n 68\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 69 of 76\\n\\n\\ntraveler without justification,” “an action for defamation or intentional infliction of\\n\\nmental distress,” or “law[s] of insult and indignity.” Id. at 195 n.10.\\n\\n The identification of these common-law antecedents does not get us too far.\\n\\nWe lack any clear indication that Congress had these common-law claims in mind\\n\\nwhen drafting the FHA, and so we are reluctant draw too much from them beyond\\n\\nthe “some direct relation” requirement. For one thing, we would not know which\\n\\ncommon-law claim to begin with, since we do not see the obvious correspondence\\n\\nto the common law the Court has identified elsewhere. Thus, for example, this\\n\\ncase is not like Bridge where common-law mail fraud was an obvious precursor to\\n\\nRICO mail fraud. See Bridge, 553 U.S. at 652.\\n\\n Other statutory causes of action have more tangible foundations in particular\\n\\ncommon-law claims. The Court does not define what exactly counts as “common-\\n\\nlaw foundations” but RICO and the antitrust statutes are the paradigmatic\\n\\nexamples. See, e.g., Bridge, 533 U.S. at 651 (“[W]hen Congress established in\\n\\nRICO a civil cause of action for a person ‘injured . . . by reason of’ a\\n\\n‘conspir[acy],’ it meant to adopt . . . well-established common-law civil conspiracy\\n\\nprinciples” (quoting Beck v. Prupis, 529 U.S. 494, 504 (2000))); Holmes, 503 U.S.\\n\\nat 267 (“[C]ourts had read § 7 [of the Sherman Act] to incorporate common-law\\n\\nprinciples of proximate causation.”). In Anza v. Ideal Steel Supply Corp., 547\\n\\nU.S. 451, 457 (2006), a RICO case, the Court also said that “directness principles”\\n\\n\\n 69\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 70 of 76\\n\\n\\napply to statutes with “common-law foundations.” Bank of Am., 137 S. Ct. at\\n\\n1306 (quoting Anza, 547 U.S. at 457). Anza repeated reasoning from Holmes\\n\\ncomparing RICO’s civil suit provision to the Clayton Act’s. Anza, 547 U.S. at 457\\n\\n(citing Holmes, 503 U.S. at 267–68).\\n\\n The connection between the Clayton Act and RICO, laid out in Holmes, was\\n\\nfoundational for proximate cause analysis under RICO. See, e.g., Hemi Group,\\n\\n559 U.S. at 8–10 (citing Holmes, 503 U.S. 258); Bridge, 553 U.S. at 653–55\\n\\n(citing Holmes, 503 U.S. 258); Anza 547 U.S. at 457 (citing Holmes, 503 U.S. at\\n\\n267–68). In fact, RICO’s civil suit provision was modeled on the antitrust statutes\\n\\nof the early 20th century, so standards of proximate cause that applied to early\\n\\nClayton and Sherman Act cases can be readily applied to RICO as well. See\\n\\nHolmes, 503 U.S. at 268; see also Assoc. Gen. Contractors, 459 U.S. at 531–35.\\n\\nEven without a deep dive into legislative history, the connection between the\\n\\nstatutes is obvious because their civil suit provisions are almost identical. The\\n\\nClayton Act reads:\\n\\n [A]ny person who shall be injured in his business or property by reason\\n of anything forbidden in the antitrust laws may sue therefor . . . and\\n shall recover threefold the damages by him sustained, and the cost of\\n suit, including a reasonable attorney’s fee.\\n\\n15 U.S.C. § 15. Likewise, RICO reads:\\n\\n Any person injured in his business or property by reason of a violation\\n of section 1962 of this chapter may sue therefor in any appropriate\\n United States district court and shall recover threefold the damages he\\n\\n 70\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 71 of 76\\n\\n\\n sustains and the cost of the suit, including a reasonable attorney’s\\n fee . . . .\\n\\n18 U.S.C. § 1964(c). Both statutes thus say that “any person” “injured in his\\n\\nbusiness or property” by a violation of the statute has a cause of action and can\\n\\nrecover treble damages plus attorney’s fees.\\n\\n The common-law foundations of the Fair Housing Act are less obvious\\n\\ninsofar as they relate to proximate cause. For starters, the FHA does not employ\\n\\nthe language that the Clayton Act shares with RICO. It authorizes suit by an\\n\\n“aggrieved person,” 42 U.S.C. § 3613(a)(1)(A), expansively defined as “any\\n\\nperson who (1) claims to have been injured by a discriminatory housing practice;\\n\\nor (2) believes that such person will be injured by a discriminatory housing\\n\\npractice that is about to occur.” Id. § 3602(i). Indeed, under the language\\n\\nemployed by Congress in the FHA, the aggrieved person need not be injured\\n\\nspecifically “in his business or property.” Moreover, the remedies are distinct\\n\\nfrom the relief available for a violation of the Clayton Act or RICO -- treble\\n\\ndamages are not available, and the court “may allow” attorney’s fees, but under the\\n\\nFHA it is not required to, as it would be under RICO or the Clayton Act. See 42\\n\\nU.S.C. § 3613(c).\\n\\n These textual differences make it harder to assume that the legislators\\n\\ndrafting the FHA were drawing on the same version of proximate cause that was\\n\\nused in these earlier statutes. We are still able to borrow notions about proximate\\n\\n 71\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 72 of 76\\n\\n\\ncause from the common law for the FHA, but it strikes us as inappropriate simply\\n\\nto assume that the FHA necessarily incorporated the nature and form of proximate\\n\\ncause as it was employed in these other statutes for which we can trace a much\\n\\nmore direct provenance. And, since understandings of proximate cause at common\\n\\nlaw evolved over time, we would need to know which version of common–law\\n\\nproximate cause a statute adopted. See Sperino, supra, at 1225 (“The one thing\\n\\nthat is certain about proximate cause is that its underlying goals are contested and\\n\\nevolving.”). Different statutes may not have incorporated the same common-law\\n\\nstandard; the Palsgraf case and the First Restatement of Torts both postdated\\n\\npassage of the Sherman Act but had become highly foundational texts for\\n\\nunderstanding proximate cause by the time RICO was drafted. Id. The evolving\\n\\nshape of proximate cause at common law further complicates any analysis that\\n\\nwould depend entirely upon incorporating a common-law standard from a statute\\n\\nthat predated the FHA.\\n\\n Congress might have brought common-law standards to bear on the new\\n\\nproblems it addressed in the 1960s, but the fact that we may identify some\\n\\ncommon-law analogue does not necessarily mean that this was the case. The Fair\\n\\nHousing Act does not employ language drawn from the older federal statutes with\\n\\nconnections to the common law, and, as best as we can tell, this cause of action\\n\\ndoes not have an unmistakable common-law antecedent. As a result, while\\n\\n\\n 72\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 73 of 76\\n\\n\\nconsidering the common law may be valuable and informative, and while the\\n\\nstatute’s common-law antecedents do require a plaintiff plausibly to allege “some\\n\\ndirect relation,” we are unable to discern any further lessons from the common law\\n\\nthat bear on our analysis.\\n\\n IV. Conclusion\\n\\n In sum, we hold that there is “some direct relation” between the City’s tax-\\n\\nrevenue injuries and the Bank’s alleged violations of the FHA. The Supreme\\n\\nCourt has never held that the presence of an intervening causal step or the\\n\\ninvolvement of a third party necessarily bars a finding of proximate cause as a\\n\\nmatter of law, and we decline to establish so hard and fast a rule today.\\n\\n The City’s detailed allegations on its tax-revenue injury are sufficient for a\\n\\nvariety of reasons: the FHA is a broad and ambitious statute which employs a\\n\\nstandard of proximate cause that facilitates its operation; Congress meant for the\\n\\nFHA to be a big solution to a big problem -- housing segregation generated by\\n\\nintentional racial discrimination; for half a century courts have read the FHA\\n\\nbroadly and Congress has repeatedly assented to these readings; the impact of the\\n\\nBanks’ redlining can readily be identified at a citywide or neighborhood level, so\\n\\neven if there were not “something very close to a 1:1 relationship,” Lexmark, 134\\n\\nS. Ct. at 1394, the City has plausibly explained how it will calculate damages in a\\n\\nreasonably precise way; the injury is profoundly different from any injuries\\n\\n\\n 73\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 74 of 76\\n\\n\\nsuffered by a homeowner; and there’s no reason to think that homeowners would\\n\\nmake for more efficient plaintiffs. In the absence of any palpable concerns about\\n\\nunadministrable litigation, we ought not to unduly constrain the remedial effect of\\n\\nthe FHA.\\n\\n Put differently, the City has adequately pled proximate cause when it comes\\n\\nto its tax-base injury because the Banks’ redlining and reverse-redlining practices\\n\\nbear some direct relation to the City’s fiscal injuries. There is a logical and direct\\n\\nbond between discriminatory lending as a pattern and practice applied to\\n\\nneighborhoods throughout the City and the reduction in property values. Third\\n\\nparties are involved, but the harm to the City is not contingent on their actions\\n\\nwhen considered in the aggregate. There is no discontinuity between the violation\\n\\nand the harm. Bad loans in the aggregate will mean foreclosures in the aggregate,\\n\\nwhich will mean loss of property value and a reduction in the tax base. An\\n\\nindividual home might go under for a variety of causes, but when discriminatory\\n\\nlending practices pervade a neighborhood or a city, the city’s fisc will necessarily\\n\\nbe affected because we know some number of homes will go under, and some\\n\\nnumber of properties will lose value. When we consider the claimed violations\\n\\nand the injuries sustained in the aggregate -- that is, at the scale that the complaints\\n\\npresent them -- it becomes clearer that injuries to the city’s treasury are necessary,\\n\\ndirect, and immediate results of these kinds of FHA violations.\\n\\n\\n 74\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 75 of 76\\n\\n\\n By many of these same measures, however, the City’s increased municipal\\n\\nexpenditures injury fails, and so the district court was correct to find that proximate\\n\\ncause for this injury had not been adequately pled in the complaints it was\\n\\nreviewing. The City’s increased expenditures have not been plausibly presented as\\n\\ndirectly and automatically resulting from the Banks’ alleged conduct. Even though\\n\\nwe think foreclosures follow directly from the Banks’ conduct, there is too much\\n\\nopportunity in the causal chain between foreclosure and increased expenditures for\\n\\nintervening actors and causes to play a role, and there has been no explanation by\\n\\nthe City of how we might conceivably isolate the injury attributable to the Banks.\\n\\nThus we have identified this alleged injury as being too remote to satisfy proximate\\n\\ncause.\\n\\n We repeat that we have not answered every outstanding question in this\\n\\ncase. Much remains to be determined as the litigation proceeds, but this case is\\n\\nbefore this Court only on a motion to dismiss. It is not our role at this stage to\\n\\ndecide whether hedonic regression analysis can actually identify injuries\\n\\nattributable to violations with sufficient accuracy, or indeed whether the banks\\n\\nactually made decisions based on race as opposed to socioeconomic factors that\\n\\nmay correlate with race or with other considerations. Today we have done only\\n\\ntwo things. Broadly, we have worked out in some detail what proximate cause\\n\\nrequires in an FHA suit. More specifically, we have evaluated whether these\\n\\n\\n 75\\n\\f Case: 14-14544 Date Filed: 05/03/2019 Page: 76 of 76\\n\\n\\ncomplaints against these Banks plausibly allege that Miami’s injuries to its tax\\n\\nbase were directly related to the violations they describe. We simply find that the\\n\\noperative complaints explain in a plausible fashion how the claimed tax-revenue\\n\\ninjuries bear “some direct relation” to the misconduct that the City is challenging.\\n\\nThis harm to Miami, as pled, is not just foreseeable but, when measured in the\\n\\naggregate, is directly related to the pattern of unlawful behavior the City has\\n\\nalleged.\\n\\n The City has plausibly alleged a violation of the FHA and has stated a claim\\n\\nin its First Amended Complaints. Accordingly we conclude that the district court\\n\\nimprovidently dismissed the FHA claims in their entirety and ought to have\\n\\ngranted the City leave to amend its complaints, since amendation would not have\\n\\nbeen futile.12 The cases are remanded to the district court for further proceedings\\n\\nconsistent with this opinion.\\n\\n REVERSED and REMANDED\\n\\n\\n\\n\\n12\\n We leave it to the district court to determine which complaints should be operative for its\\npurposes, or whether to grant the City leave to file new ones. See supra n.2.\\n 76\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2273,"cells":{"id":{"kind":"number","value":4617013,"string":"4,617,013"},"name":{"kind":"string","value":"Steven J. MYERS, Plaintiff-Counter Defendant-Appellant, v. UNITED STATES of America, Defendant-Counter Claimant-Appellee."},"name_abbreviation":{"kind":"string","value":"Steven J. Myers v. United States"},"decision_date":{"kind":"string","value":"2019-05-06"},"docket_number":{"kind":"string","value":"18-11403"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Tjoflat, Jordan, Schlesinger\", \"parties\": \"\", \"opinions\": [{\"author\": \"PER CURIAM\", \"type\": \"010combined\", \"text\": \"Case: 18-11403 Date Filed: 05/06/2019 Page: 1 of 7\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-11403\\n ________________________\\n\\n D.C. Docket No. 1:16-cv-01792-ELR\\n\\n\\nSTEVEN J. MYERS,\\n\\n Plaintiff-Counter Defendant-Appellant,\\n\\nversus\\n\\nUNITED STATES OF AMERICA,\\n\\n Defendant-Counter Claimant-Appellee.\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 6, 2019)\\n\\nBefore TJOFLAT and JORDAN, Circuit Judges, and SCHLESINGER, * District\\nJudge.\\n\\nPER CURIAM:\\n\\n\\n\\n\\n *\\n Honorable Harvey E. Schlesinger, United States District Judge for the Middle District\\nof Florida, sitting by designation.\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 2 of 7\\n\\n\\n Steven Myers was the CFO and co-president of two companies 1 that failed\\n\\nto pay trust fund taxes. Under 26 U.S.C. § 6672(a), the IRS may recover unpaid\\n\\ntaxes against “[a]ny person required to collect, truthfully account for, and pay over\\n\\nany tax” “who willfully fails to collect such tax.” The IRS concluded that Myers\\n\\nwas liable under § 6672(a) and assessed the companies’ trust fund penalties against\\n\\nhim. Myers paid some of the penalties and then sued the Government for a refund.\\n\\nThe Government filed a counterclaim for the balance of the penalties, and both\\n\\nparties moved for summary judgment. The District Court granted summary\\n\\njudgment in favor of the Government. After the benefit of oral argument, we\\n\\naffirm.\\n\\n I.\\n\\n The two companies that Myers worked for were owned by another company\\n\\n(“Parent Company”), and Parent Company was licensed by the U.S. Small\\n\\nBusiness Administration (the “SBA”) as a Small Business Investment Company\\n\\n(the “SBIC”). The SBA guarantees debentures that SBICs issue and has the power\\n\\nto place those SBICs into receivership.\\n\\n Here, Parent Company violated the terms of its license, so the SBA filed suit\\n\\nin the Southern District of New York to place Parent Company into receivership.\\n\\n\\n\\n 1\\n The companies were Window Media, LLC, and Unite Media, LLC. They both\\npublished newspapers.\\n 2\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 3 of 7\\n\\n\\nSee United States v. Avalon Equity Fund, L.P., No. 1:08-cv-7287 (S.D.N.Y., filed\\n\\nAug. 18, 2008). Under an agreed-to Consent Order, the Southern District of New\\n\\nYork placed Parent Company in receivership. Per the Consent Order, the Southern\\n\\nDistrict of New York took “exclusive jurisdiction” of Parent Company and “all of\\n\\nits assets, and the Court appointed the SBA as Parent Company’s receiver.\\n\\n As Parent Company’s receiver, the SBA was given “all powers, authorities,\\n\\nrights and privileges . . . [enjoyed] by the general partners, managers, officers and\\n\\ndirectors” of Parent Company. 2 In turn, Parent Company’s actual general partners,\\n\\nmanagers, officers, and directors were dismissed. Put simply, the SBA was calling\\n\\nthe shots for Parent Company.\\n\\n In 2009, the companies that Myers worked for failed to pay trust fund taxes.\\n\\nDuring this time, Myers was the CFO and co-president, and he had signature\\n\\nauthority on the companies’ bank accounts. Parent Company was in\\n\\nreceivership—meaning the SBA was calling the shots—when the companies that\\n\\nMyers worked for failed to pay their trust fund taxes. Thus, according to Myers,\\n\\nthe SBA’s agent told him to prioritize other vendors over the trust fund taxes.\\n\\n And so he did. Myers knew the trust fund taxes were due, and he didn’t pay\\n\\nthem. But he did approve payments to these more critical vendors. Eventually, the\\n\\n\\n\\n 2\\n The SBA was also given “all powers and authority conferred upon” it under 15 U.S.C. §\\n687c and 28 U.S.C. § 754.\\n 3\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 4 of 7\\n\\n\\nIRS assessed the trust fund tax penalties against Myers, and he paid a portion of\\n\\nthe assessment.\\n\\n II.\\n\\n Myers sued for a refund, and both parties eventually moved for summary\\n\\njudgment. Rejecting Myers’s my-boss-told-me-not-to-pay argument, the District\\n\\nCourt granted summary judgment in favor of the Government.\\n\\n Myers appealed. “On appeal from a grant of summary judgment, this Court\\n\\nreviews legal questions de novo.” Al-Rayes v. Willingham, 914 F.3d 1302, 1306\\n\\n(11th Cir. 2019) (citation omitted).\\n\\n III.\\n\\n Recognizing this Court’s long line of precedent rejecting the my-boss-told-\\n\\nme-not-to-pay argument,3 Myers conceded at oral argument that he would be liable\\n\\nfor the unpaid taxes if Parent Company’s receiver had been a private entity. This\\n\\ncase is different, Myers said, because Parent Company’s receiver was the SBA, a\\n\\ngovernment agency. Myers said he should not be liable because it wasn’t any old\\n\\nboss telling him not to pay—it was a government agent. During argument, Myers\\n\\n\\n\\n 3\\n See Thosteson v. United States, 331 F.3d 1294, 1300 (11th Cir. 2003) (“Acting, or\\nrather failing to act, under orders from his superior does not negate [a defendant’s] culpability\\nunder the statute.”); Thibodeau v. United States, 828 F.2d 1499, 1504 (11th Cir. 1987) (per\\ncuriam) (noting that Eleventh Circuit precedent “hold[s] that an otherwise responsible person\\ncannot be relieved of this obligation [to pay taxes] when directed by another person not to pay\\nthe taxes”); Roth v. United States, 779 F.2d 1567, 1572 (11th Cir. 1986) (rejecting the my-boss-\\ntold-me-not-to-pay defense).\\n 4\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 5 of 7\\n\\n\\nagreed that he would be liable if we apply the same rules to government receivers\\n\\nas we do to private receivers.\\n\\n So, the narrow question before us is whether 26 U.S.C. § 6672(a)—and our\\n\\ncase law interpreting it—applies with equal force when a government agency\\n\\nreceiver tells a taxpayer not to pay trust fund taxes. We hold that it does. We\\n\\ncannot apply different substantive law simply because the receiver in this case was\\n\\nthe SBA. Thus, Myers is liable under § 6672(a).\\n\\n IV.\\n\\n The judgment of the District Court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 5\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 6 of 7\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4394266/\", \"author_raw\": \"PER CURIAM\"}, {\"author\": \"JORDAN, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"JORDAN, Circuit Judge, concurring in the judgment:\\n\\n The majority concludes that Mr. Myers is responsible for trust fund penalties\\n\\nunder 26 U.S.C. § 6672(a) even if he was instructed by an agent of the federal\\n\\ngovernment—here an SBA receiver—to prioritize the payment of other creditors\\n\\nand vendors over the trust fund taxes that were due. According to the majority, there\\n\\nis no basis for adopting a different substantive rule when a federal agency is acting\\n\\nas the receiver. I agree with the result, but would decide the case on a more narrow\\n\\nground.\\n\\n Mr. Myers’ contention is that a person should not be liable under § 6672(a) to\\n\\na federal agency—the IRS—for trust fund penalties if a different federal agency—\\n\\nthe SBA acting as receiver—has told him not to pay trust fund taxes. I am not sure\\n\\nthis legal issue is clear cut, and I can imagine a situation—like the one presented in\\n\\nMcCarty v. United States, 437 F.2d 961, 963–73 (Ct. Cl. 1971)—where the answer\\n\\nwould not be self-evident.\\n\\n My preference is to leave the broad legal question open. As I see things, Mr.\\n\\nMyers is essentially arguing that the IRS should be estopped from recovering trust\\n\\nfund penalties because he acted pursuant to the instructions of the SBA receiver. I\\n\\nwould hold that, on this record, Mr. Myers’ reliance on these instructions was not\\n\\nobjectively reasonable. Cf. United States v. Alvarado, 808 F.3d 474, 484–85 (11th\\n\\n\\n\\n\\n 6\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 7 of 7\\n\\n\\nCir. 2015) (explaining, in the criminal context, that the public authority and\\n\\nentrapment-by-estoppel defenses require reasonable reliance).\\n\\n When the SBA became the receiver of the parent company, it stepped into the\\n\\nprivate status of that entity, see Untied States ex rel. Petras v. Simparel, Inc., 857\\n\\nF.3d 497, 503–04 (3d Cir. 2017), and had to abide by its own liquidation standard\\n\\noperating procedures. Those procedures, in relevant part, required the SBA receiver\\n\\nto make all appropriate filings with federal tax authorities as required by 28 U.S.C.\\n\\n§ 960 if reasonably possible. See id. at 504; Small Business Administration, SBIC\\n\\nLiquidation SOP 10 07 1 at Ch. 7 ¶ 7.b(2) (2007). In turn, § 960 provides that “[a]ny\\n\\nofficers and agents conducting any business under authority of a United States court\\n\\nshall be subject to all Federal . . . taxes applicable to such business to the same extent\\n\\nas if it were conducted by an individual or corporation.” Given this language, Mr.\\n\\nMyers could not have reasonably relied on the do-not-pay instructions of the SBA\\n\\nreceiver. See Cal. State Bd. of Equalization v. Sierra Summit, Inc., 490 U.S. 844,\\n\\n852 (1989) (explaining that Congress’ intent in enacting § 960 was that “a business\\n\\nin receivership . . . should be subject to the same tax liability as the owner had he\\n\\nbeen in possession of, and operating, the enterprise.”).\\n\\n\\n\\n\\n 7\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4394266/\", \"author_raw\": \"JORDAN, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"TJOFLAT"},"judge2":{"kind":"string","value":"JORDAN"},"judge3":{"kind":"string","value":"SCHLESINGER"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":2,"string":"2"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4617013/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Steven J. MYERS, Plaintiff-Counter Defendant-Appellant, v. UNITED STATES of America, Defendant-Counter Claimant-Appellee.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-06\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-11403 Date Filed: 05/06/2019 Page: 1 of 7\n\n\n [PUBLISH]\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 18-11403\n ________________________\n\n D.C. Docket No. 1:16-cv-01792-ELR\n\n\nSTEVEN J. MYERS,\n\n Plaintiff-Counter Defendant-Appellant,\n\nversus\n\nUNITED STATES OF AMERICA,\n\n Defendant-Counter Claimant-Appellee.\n ________________________\n\n Appeal from the United States District Court\n for the Northern District of Georgia\n ________________________\n\n (May 6, 2019)\n\nBefore TJOFLAT and JORDAN, Circuit Judges, and SCHLESINGER, * District\nJudge.\n\nPER CURIAM:\n\n\n\n\n *\n Honorable Harvey E. Schlesinger, United States District Judge for the Middle District\nof Florida, sitting by designation.\n\n Case: 18-11403 Date Filed: 05/06/2019 Page: 2 of 7\n\n\n Steven Myers was the CFO and co-president of two companies 1 that failed\n\nto pay trust fund taxes. Under 26 U.S.C. § 6672(a), the IRS may recover unpaid\n\ntaxes against “[a]ny person required to collect, truthfully account for, and pay over\n\nany tax” “who willfully fails to collect such tax.” The IRS concluded that Myers\n\nwas liable under § 6672(a) and assessed the companies’ trust fund penalties against\n\nhim. Myers paid some of the penalties and then sued the Government for a refund.\n\nThe Government filed a counterclaim for the balance of the penalties, and both\n\nparties moved for summary judgment. The District Court granted summary\n\njudgment in favor of the Government. After the benefit of oral argument, we\n\naffirm.\n\n I.\n\n The two companies that Myers worked for were owned by another company\n\n(“Parent Company”), and Parent Company was licensed by the U.S. Small\n\nBusiness Administration (the “SBA”) as a Small Business Investment Company\n\n(the “SBIC”). The SBA guarantees debentures that SBICs issue and has the power\n\nto place those SBICs into receivership.\n\n Here, Parent Company violated the terms of its license, so the SBA filed suit\n\nin the Southern District of New York to place Parent Company into receivership.\n\n\n\n 1\n The companies were Window Media, LLC, and Unite Media, LLC. They both\npublished newspapers.\n 2\n\n Case: 18-11403 Date Filed: 05/06/2019 Page: 3 of 7\n\n\nSee United States v. Avalon Equity Fund, L.P., No. 1:08-cv-7287 (S.D.N.Y., filed\n\nAug. 18, 2008). Under an agreed-to Consent Order, the Southern District of New\n\nYork placed Parent Company in receivership. Per the Consent Order, the Southern\n\nDistrict of New York took “exclusive jurisdiction” of Parent Company and “all of\n\nits assets, and the Court appointed the SBA as Parent Company’s receiver.\n\n As Parent Company’s receiver, the SBA was given “all powers, authorities,\n\nrights and privileges . . . [enjoyed] by the general partners, managers, officers and\n\ndirectors” of Parent Company. 2 In turn, Parent Company’s actual general partners,\n\nmanagers, officers, and directors were dismissed. Put simply, the SBA was calling\n\nthe shots for Parent Company.\n\n In 2009, the companies that Myers worked for failed to pay trust fund taxes.\n\nDuring this time, Myers was the CFO and co-president, and he had signature\n\nauthority on the companies’ bank accounts. Parent Company was in\n\nreceivership—meaning the SBA was calling the shots—when the companies that\n\nMyers worked for failed to pay their trust fund taxes. Thus, according to Myers,\n\nthe SBA’s agent told him to prioritize other vendors over the trust fund taxes.\n\n And so he did. Myers knew the trust fund taxes were due, and he didn’t pay\n\nthem. But he did approve payments to these more critical vendors. Eventually, the\n\n\n\n 2\n The SBA was also given “all powers and authority conferred upon” it under 15 U.S.C. §\n687c and 28 U.S.C. § 754.\n 3\n\n Case: 18-11403 Date Filed: 05/06/2019 Page: 4 of 7\n\n\nIRS assessed the trust fund tax penalties against Myers, and he paid a portion of\n\nthe assessment.\n\n II.\n\n Myers sued for a refund, and both parties eventually moved for summary\n\njudgment. Rejecting Myers’s my-boss-told-me-not-to-pay argument, the District\n\nCourt granted summary judgment in favor of the Government.\n\n Myers appealed. “On appeal from a grant of summary judgment, this Court\n\nreviews legal questions de novo.” Al-Rayes v. Willingham, 914 F.3d 1302, 1306\n\n(11th Cir. 2019) (citation omitted).\n\n III.\n\n Recognizing this Court’s long line of precedent rejecting the my-boss-told-\n\nme-not-to-pay argument,3 Myers conceded at oral argument that he would be liable\n\nfor the unpaid taxes if Parent Company’s receiver had been a private entity. This\n\ncase is different, Myers said, because Parent Company’s receiver was the SBA, a\n\ngovernment agency. Myers said he should not be liable because it wasn’t any old\n\nboss telling him not to pay—it was a government agent. During argument, Myers\n\n\n\n 3\n See Thosteson v. United States, 331 F.3d 1294, 1300 (11th Cir. 2003) (“Acting, or\nrather failing to act, under orders from his superior does not negate [a defendant’s] culpability\nunder the statute.”); Thibodeau v. United States, 828 F.2d 1499, 1504 (11th Cir. 1987) (per\ncuriam) (noting that Eleventh Circuit precedent “hold[s] that an otherwise responsible person\ncannot be relieved of this obligation [to pay taxes] when directed by another person not to pay\nthe taxes”); Roth v. United States, 779 F.2d 1567, 1572 (11th Cir. 1986) (rejecting the my-boss-\ntold-me-not-to-pay defense).\n 4\n\n Case: 18-11403 Date Filed: 05/06/2019 Page: 5 of 7\n\n\nagreed that he would be liable if we apply the same rules to government receivers\n\nas we do to private receivers.\n\n So, the narrow question before us is whether 26 U.S.C. § 6672(a)—and our\n\ncase law interpreting it—applies with equal force when a government agency\n\nreceiver tells a taxpayer not to pay trust fund taxes. We hold that it does. We\n\ncannot apply different substantive law simply because the receiver in this case was\n\nthe SBA. Thus, Myers is liable under § 6672(a).\n\n IV.\n\n The judgment of the District Court is\n\n AFFIRMED.\n\n\n\n\n 5\n\n Case: 18-11403 Date Filed: 05/06/2019 Page: 6 of 7\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Steven J. MYERS, Plaintiff-Counter Defendant-Appellant, v. UNITED STATES of America, Defendant-Counter Claimant-Appellee.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-06\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-11403 Date Filed: 05/06/2019 Page: 1 of 7\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-11403\\n ________________________\\n\\n D.C. Docket No. 1:16-cv-01792-ELR\\n\\n\\nSTEVEN J. MYERS,\\n\\n Plaintiff-Counter Defendant-Appellant,\\n\\nversus\\n\\nUNITED STATES OF AMERICA,\\n\\n Defendant-Counter Claimant-Appellee.\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 6, 2019)\\n\\nBefore TJOFLAT and JORDAN, Circuit Judges, and SCHLESINGER, * District\\nJudge.\\n\\nPER CURIAM:\\n\\n\\n\\n\\n *\\n Honorable Harvey E. Schlesinger, United States District Judge for the Middle District\\nof Florida, sitting by designation.\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 2 of 7\\n\\n\\n Steven Myers was the CFO and co-president of two companies 1 that failed\\n\\nto pay trust fund taxes. Under 26 U.S.C. § 6672(a), the IRS may recover unpaid\\n\\ntaxes against “[a]ny person required to collect, truthfully account for, and pay over\\n\\nany tax” “who willfully fails to collect such tax.” The IRS concluded that Myers\\n\\nwas liable under § 6672(a) and assessed the companies’ trust fund penalties against\\n\\nhim. Myers paid some of the penalties and then sued the Government for a refund.\\n\\nThe Government filed a counterclaim for the balance of the penalties, and both\\n\\nparties moved for summary judgment. The District Court granted summary\\n\\njudgment in favor of the Government. After the benefit of oral argument, we\\n\\naffirm.\\n\\n I.\\n\\n The two companies that Myers worked for were owned by another company\\n\\n(“Parent Company”), and Parent Company was licensed by the U.S. Small\\n\\nBusiness Administration (the “SBA”) as a Small Business Investment Company\\n\\n(the “SBIC”). The SBA guarantees debentures that SBICs issue and has the power\\n\\nto place those SBICs into receivership.\\n\\n Here, Parent Company violated the terms of its license, so the SBA filed suit\\n\\nin the Southern District of New York to place Parent Company into receivership.\\n\\n\\n\\n 1\\n The companies were Window Media, LLC, and Unite Media, LLC. They both\\npublished newspapers.\\n 2\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 3 of 7\\n\\n\\nSee United States v. Avalon Equity Fund, L.P., No. 1:08-cv-7287 (S.D.N.Y., filed\\n\\nAug. 18, 2008). Under an agreed-to Consent Order, the Southern District of New\\n\\nYork placed Parent Company in receivership. Per the Consent Order, the Southern\\n\\nDistrict of New York took “exclusive jurisdiction” of Parent Company and “all of\\n\\nits assets, and the Court appointed the SBA as Parent Company’s receiver.\\n\\n As Parent Company’s receiver, the SBA was given “all powers, authorities,\\n\\nrights and privileges . . . [enjoyed] by the general partners, managers, officers and\\n\\ndirectors” of Parent Company. 2 In turn, Parent Company’s actual general partners,\\n\\nmanagers, officers, and directors were dismissed. Put simply, the SBA was calling\\n\\nthe shots for Parent Company.\\n\\n In 2009, the companies that Myers worked for failed to pay trust fund taxes.\\n\\nDuring this time, Myers was the CFO and co-president, and he had signature\\n\\nauthority on the companies’ bank accounts. Parent Company was in\\n\\nreceivership—meaning the SBA was calling the shots—when the companies that\\n\\nMyers worked for failed to pay their trust fund taxes. Thus, according to Myers,\\n\\nthe SBA’s agent told him to prioritize other vendors over the trust fund taxes.\\n\\n And so he did. Myers knew the trust fund taxes were due, and he didn’t pay\\n\\nthem. But he did approve payments to these more critical vendors. Eventually, the\\n\\n\\n\\n 2\\n The SBA was also given “all powers and authority conferred upon” it under 15 U.S.C. §\\n687c and 28 U.S.C. § 754.\\n 3\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 4 of 7\\n\\n\\nIRS assessed the trust fund tax penalties against Myers, and he paid a portion of\\n\\nthe assessment.\\n\\n II.\\n\\n Myers sued for a refund, and both parties eventually moved for summary\\n\\njudgment. Rejecting Myers’s my-boss-told-me-not-to-pay argument, the District\\n\\nCourt granted summary judgment in favor of the Government.\\n\\n Myers appealed. “On appeal from a grant of summary judgment, this Court\\n\\nreviews legal questions de novo.” Al-Rayes v. Willingham, 914 F.3d 1302, 1306\\n\\n(11th Cir. 2019) (citation omitted).\\n\\n III.\\n\\n Recognizing this Court’s long line of precedent rejecting the my-boss-told-\\n\\nme-not-to-pay argument,3 Myers conceded at oral argument that he would be liable\\n\\nfor the unpaid taxes if Parent Company’s receiver had been a private entity. This\\n\\ncase is different, Myers said, because Parent Company’s receiver was the SBA, a\\n\\ngovernment agency. Myers said he should not be liable because it wasn’t any old\\n\\nboss telling him not to pay—it was a government agent. During argument, Myers\\n\\n\\n\\n 3\\n See Thosteson v. United States, 331 F.3d 1294, 1300 (11th Cir. 2003) (“Acting, or\\nrather failing to act, under orders from his superior does not negate [a defendant’s] culpability\\nunder the statute.”); Thibodeau v. United States, 828 F.2d 1499, 1504 (11th Cir. 1987) (per\\ncuriam) (noting that Eleventh Circuit precedent “hold[s] that an otherwise responsible person\\ncannot be relieved of this obligation [to pay taxes] when directed by another person not to pay\\nthe taxes”); Roth v. United States, 779 F.2d 1567, 1572 (11th Cir. 1986) (rejecting the my-boss-\\ntold-me-not-to-pay defense).\\n 4\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 5 of 7\\n\\n\\nagreed that he would be liable if we apply the same rules to government receivers\\n\\nas we do to private receivers.\\n\\n So, the narrow question before us is whether 26 U.S.C. § 6672(a)—and our\\n\\ncase law interpreting it—applies with equal force when a government agency\\n\\nreceiver tells a taxpayer not to pay trust fund taxes. We hold that it does. We\\n\\ncannot apply different substantive law simply because the receiver in this case was\\n\\nthe SBA. Thus, Myers is liable under § 6672(a).\\n\\n IV.\\n\\n The judgment of the District Court is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 5\\n\\n Case: 18-11403 Date Filed: 05/06/2019 Page: 6 of 7\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2274,"cells":{"id":{"kind":"number","value":4617071,"string":"4,617,071"},"name":{"kind":"string","value":"Homero F. MERUELO, Petitioner-Appellant, v. COMMISSIONER OF INTERNAL REVENUE, Respondent-Appellee."},"name_abbreviation":{"kind":"string","value":"Homero F. Meruelo v. Commissioner of Internal Revenue"},"decision_date":{"kind":"string","value":"2019-05-06"},"docket_number":{"kind":"string","value":"18-11909"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Pryor, Newsom, Vratil\", \"parties\": \"\", \"opinions\": [{\"author\": \"WILLIAM PRYOR, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-11909 Date Filed: 05/06/2019 Page: 1 of 18\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-11909\\n ________________________\\n\\n Agency No. 001795-13\\n\\n\\n\\nHOMERO F. MERUELO,\\n\\n Petitioner-Appellant,\\n\\nversus\\n\\nCOMMISSIONER OF INTERNAL REVENUE,\\n\\n Respondent-Appellee.\\n\\n ________________________\\n\\n Petition for Review of a Decision of the\\n United States Tax Court\\n ________________________\\n\\n (May 6, 2019)\\n\\nBefore WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District\\nJudge.\\n\\nWILLIAM PRYOR, Circuit Judge:\\n\\n\\n\\n*\\n Honorable Kathryn H. Vratil, United States District Judge for the District of Kansas, sitting by\\ndesignation.\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 2 of 18\\n\\n\\n This appeal from the disallowance of a taxpayer’s claimed deduction for his\\n\\nshare of losses suffered by an S corporation presents the following issue: whether\\n\\nmonetary transfers between various business entities partly owned by the taxpayer\\n\\nand an S corporation that were later reclassified as loans from the taxpayer to the S\\n\\ncorporation established a “bona fide indebtedness” that “runs directly” to the\\n\\ntaxpayer. Treas. Reg. § 1.1366-2(a)(2)(i); see also 26 U.S.C. § 1366. Homero\\n\\nMeruelo was a shareholder of Merco of the Palm Beaches, Inc., which suffered a\\n\\nnearly $27 million loss after banks foreclosed on its condominium complex.\\n\\nMeruelo asserted that he had a sufficient basis in Merco’s indebtedness for him to\\n\\ndeduct $13 million as his share of the loss. Meruelo claimed basis from a $5\\n\\nmillion capital contribution he made to Merco and more than $9 million of\\n\\nindebtedness from net transfers through various other business entities in which he\\n\\nheld an interest. The Internal Revenue Service determined that he could claim only\\n\\nthe $5 million basis and not the $9 million because any debt ran from Merco to the\\n\\nother entities. The Tax Court later ruled that Meruelo had failed to establish a bona\\n\\nfide indebtedness of $9 million running directly to him and that he failed to\\n\\nestablish that he made an “actual economic outlay” toward the debt. Because the\\n\\nTax Court correctly determined that Meruelo did not establish a bona fide\\n\\nindebtedness that ran directly to him, we affirm.\\n\\n\\n\\n\\n 2\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 3 of 18\\n\\n\\n I. BACKGROUND\\n\\n Meruelo, a real estate developer in south Florida, owns interests in several S\\n\\ncorporations, partnerships, and limited liability companies. One of these entities\\n\\nwas Merco of the Palm Beaches, Inc., an S corporation Meruelo incorporated in\\n\\nMarch 2004. Meruelo held 49 percent of Merco’s stock.\\n\\n Subchapter S of the Internal Revenue Code provides “a pass-through system\\n\\nunder which corporate income, losses, deductions, and credits are attributed to\\n\\nindividual shareholders in a manner akin to the tax treatment of partnerships.”\\n\\nBuffered v. Comm’r, 506 U.S. 523, 525 (1993). A shareholder’s ability to deduct\\n\\nhis proportionate share of a corporation’s net operating losses is limited by the sum\\n\\nof his basis in his stock and the corporate indebtedness to him. See 26 U.S.C.\\n\\n§ 1366(d)(1). In other words, the shareholder can increase his basis by contributing\\n\\ncapital to the corporation or by lending money to it.\\n\\n Meruelo incorporated Merco to purchase a condominium complex in a\\n\\nbankruptcy sale. In early 2004, the bankruptcy court approved the sale and\\n\\nrequired Merco to pay a $10 million non-refundable deposit to secure the property.\\n\\nTo raise funds for his share of the deposit, Meruelo obtained a personal loan.\\n\\n Meruelo transferred $4,985,035 of the loan proceeds to Merco Group at\\n\\nAkoya, an S corporation in which he and his mother each held a 50 percent\\n\\ninterest. In March 2004, Akoya transferred into Merco’s escrow account $5\\n\\n\\n\\n 3\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 4 of 18\\n\\n\\nmillion—$4,985,035 of Meruelo’s loan proceeds and $14,965 of Akoya’s own\\n\\nfunds—to cover half the required deposit. Akoya had also previously transferred to\\n\\nMerco enough funds to cover the $5 million balance of the deposit. The\\n\\nCommissioner does not dispute that the $4,985,035 transfer gave Meruelo a\\n\\nshareholder basis in that amount in Merco.\\n\\n From 2004 to 2008, Merco entered into hundreds of transactions with\\n\\nvarious partnerships, S corporations, and limited liability companies in which\\n\\nMeruelo held an interest. These Merco affiliates often paid expenses, such as\\n\\npayroll costs, for each other or for Merco to simplify accounting and enhance\\n\\nliquidity. The payor company recorded these payments to its affiliates as accounts\\n\\nreceivable, and the payee company recorded them as accounts payable. Between\\n\\n2004 and 2008, Merco affiliates made more than $15 million in payments to or on\\n\\nbehalf of Merco, and Merco repaid its affiliates less than $6 million of these\\n\\npayments. On December 31 of each year, Merco’s books and records showed\\n\\nsubstantial net accounts payable to its affiliates.\\n\\n Luis Carreras, a certified public accountant, prepared the tax returns filed by\\n\\nMeruelo, Merco, and the Merco affiliates. When preparing Merco’s tax return for a\\n\\ngiven year, Carreras would net Merco’s accounts payable to its affiliates, as shown\\n\\non Merco’s books as of the preceding December 31, against Merco’s accounts\\n\\nreceivable from its affiliates. If Merco had net accounts payable, Carreras reported\\n\\n\\n\\n 4\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 5 of 18\\n\\n\\nthat amount as a “shareholder loan” on Merco’s tax return. Carreras then allocated\\n\\na percentage of this indebtedness to Meruelo based on Meruelo’s ownership\\n\\ninterests in the various affiliates that had transferred funds to Merco.\\n\\n In March 2004, Carreras drafted a promissory note for Meruelo purportedly\\n\\nto make a $10 million unsecured line of credit available to Merco at a six percent\\n\\ninterest rate. Carreras testified that, when he prepared Meruelo’s and Merco’s tax\\n\\nreturns for tax years 2004 to 2008, he made an annual charge to Merco’s line of\\n\\ncredit for an amount equal to Meruelo’s calculated share of Merco’s net accounts\\n\\npayable to its affiliates for the preceding year.\\n\\n In 2008, Merco incurred a loss of $26,605,840 when banks foreclosed on the\\n\\ncondominium complex it purchased in 2004. Merco reported this loss on its\\n\\nincome tax return, and Merco allocated 49 percent of the loss to Meruelo.\\n\\n Meruelo filed income tax returns for 2005 and 2008. On his 2005 return, he\\n\\nreported taxable income of $13,895,731 and tax due of $4,843,976. On his 2008\\n\\nreturn, he claimed an ordinary loss deduction of $11,795,109. This deduction\\n\\nreflected a $13,036,861 flow-through loss from Merco ($26,605,840 × 49 percent)\\n\\nnetted against gains of $1,241,752 from two other S corporations in which he held\\n\\ninterests. After accounting for other income and deductions, Meruelo reported a net\\n\\noperating loss of $11,793,865 on his 2008 return. In October 2009, he applied for a\\n\\ntentative refund asserting a net operating loss carryback of $11,793,865 from 2008\\n\\n\\n\\n 5\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 6 of 18\\n\\n\\nto 2005. After applying this net operating loss carryback, his original tax lability\\n\\nfor 2005, $4,843,976, was reduced by $3,897,470, to $946,506. In January 2010,\\n\\nthe Internal Revenue Service issued Meruelo a refund of $3,897,470.\\n\\n The Internal Revenue Service selected Meruelo’s 2005 and 2008 returns for\\n\\nexamination. It determined that his basis in Merco was only $4,985,035 based on\\n\\nthe proceeds of the bank loan that Meruelo contributed to Merco through Akoya. It\\n\\ndisallowed, for lack of a sufficient basis, $8,051,826 of the $13,036,861 flow-\\n\\nthrough loss claimed for 2008.\\n\\n After disallowing part of the net operating loss for 2008, the Commissioner\\n\\ndetermined that Meruelo’s carryback to 2005 was limited to $3,706,272 and that\\n\\nhis correct tax due for 2005 was $3,546,781. Because Meruelo had reported a tax\\n\\nliability of only $946,506 for 2005, the Commissioner concluded that Meruelo’s\\n\\ntax deficiency for that year was $2,600,275 and sent Meruelo a notice of\\n\\ndeficiency.\\n\\n Meruelo petitioned the Tax Court for redetermination of his tax deficiency.\\n\\nHe alleged that he had a sufficient basis in Merco for him to fully deduct his share\\n\\nof its 2008 losses. Meruelo alleged that his basis in Merco consisted of $2.7\\n\\nmillion of Akoya’s first deposit of $5 million, all $5 million of Akoya’s second\\n\\ndeposit, and $6,616,857 for his share of intercompany transfers.\\n\\n\\n\\n\\n 6\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 7 of 18\\n\\n\\n Meruelo offered two theories to claim credit for the affiliated companies’\\n\\ntransfers to Merco: the “back-to-back loan” theory and the “incorporated\\n\\npocketbook theory.” Under the back-to-back-loan theory, he argued the affiliated\\n\\ncompanies should have been treated as lending funds to him that he then lent to\\n\\nMerco. And under the incorporated-pocketbook theory, Meruelo argued that he\\n\\nshould have been treated as using his funds, which were held by the affiliated\\n\\ncompanies, to pay Merco’s expenses on his behalf.\\n\\n After a trial, the Tax Court ruled for the Commissioner. The Tax Court\\n\\nacknowledged that Meruelo had an undisputed basis of $4,985,035 in Merco, and it\\n\\nexplained that only $8,051,826 of the $13,036,9861 flow-through loss was in\\n\\ndispute. But the Tax Court determined that Meruelo was not entitled to any of the\\n\\ndisputed basis.\\n\\n The Tax Court explained that section 1366(d)(1)(B) of the Internal Revenue\\n\\nCode allows a shareholder to increase his basis by the amount of the adjusted basis\\n\\nof any indebtedness owed by the S corporation to the shareholder. Because the\\n\\nCode “does not specify how a shareholder may acquire basis in an S corporation’s\\n\\nindebtedness to him,” the Tax Court turned to the legislative history of the\\n\\npredecessor to section 1366 for guidance. The Tax Court explained that earlier\\n\\ndecisions relied on this legislative history and construed language about “a\\n\\nshareholder’s investment in a corporation” to require an “actual economic outlay”\\n\\n\\n\\n 7\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 8 of 18\\n\\n\\nby the shareholder. In other words, the Tax Court ruled that a shareholder must\\n\\nshow that he incurred a cost in making a loan or that he was left poorer in a\\n\\nmaterial sense after the transaction.\\n\\n The Tax Court decided that the test for determining a shareholder’s basis in\\n\\nan S corporation under Treasury Regulation § 1.1366-2(a)(2)—which was\\n\\namended in 2014 and limits debt basis to “bona fide indebtedness of the S\\n\\ncorporation that runs directly to the shareholder”—was effectively the same as that\\n\\nunder the “actual economic outlay” doctrine. The Tax Court explained that it had\\n\\nlong required that a shareholder prove an S corporation’s indebtedness running\\n\\ndirectly to him to deduct his proportionate share of the corporation’s net operating\\n\\nloss. And the Tax Court reasoned that because the 2014 regulation states that\\n\\n“bona fide indebtedness” is to be determined by “general Federal tax principles,”\\n\\nthe 2014 regulation incorporates the actual economic outlay doctrine.\\n\\n The Tax Court rejected Meruelo’s back-to-back-loan theory because there\\n\\nwas no evidence that funds had been lent to Meruelo and then lent back to Merco.\\n\\nThe Tax Court acknowledged that bona fide back-to-back loans, first from an\\n\\naffiliated company to a shareholder and then from the shareholder to the debtor S\\n\\ncorporation, can increase a shareholder’s basis. But it explained that a shareholder\\n\\nis bound by the form of the transaction he initially chose and that transactions\\n\\ndirectly among related companies (and not involving the shareholder) do not\\n\\n\\n\\n 8\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 9 of 18\\n\\n\\nqualify as back-to-back loans. The Tax Court clarified that a taxpayer-shareholder\\n\\ncannot reclassify intercompany loans as shareholder loans for tax purposes when\\n\\npreparing his return. The Tax Court then ruled that, because there was no evidence\\n\\nthat the Merco affiliates had contemporaneously booked transfers between them as\\n\\nshareholder loans—the affiliates instead labeled them as accounts receivable and\\n\\npayable, wage payments, or capital contributions—Meruelo’s back-to-back-loan\\n\\ntheory failed. The Tax Court also ruled that, because Meruelo made no actual\\n\\neconomic outlay toward the monetary transfers from the Merco affiliates to Merco,\\n\\nhe could not claim that these transfers amounted to a shareholder loan.\\n\\n The Tax Court likewise rejected Meruelo’s incorporated-pocketbook theory.\\n\\nThe Tax Court explained that, although some of its rulings allowed basis increases\\n\\nunder an incorporated-pocketbook theory, the facts here were a “far cry” from\\n\\nthose decisions. The Tax Court explained that in other incorporated-pocketbook\\n\\ndecisions, the taxpayer habitually used a single, wholly owned corporation to pay\\n\\nthird parties on his behalf. But many of the Merco affiliates had co-owners besides\\n\\nMeruelo, and Meruelo had not shown that these affiliates had a “habitual practice”\\n\\nof paying his personal expenses. And the Tax Court explained that the\\n\\n“incorporated pocketbook” corporations contemporaneously booked the\\n\\ndisbursements as shareholder loans. The Merco affiliates, by contrast, booked their\\n\\ntransactions as capital contributions, payroll expenses, or intercompany accounts\\n\\n\\n\\n 9\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 10 of 18\\n\\n\\npayable and receivable, and only relabeled the disbursements as shareholder loans\\n\\nat the close of each year. The Tax Court upheld the Commissioner’s determination\\n\\nof a $2,600,275 deficiency.\\n\\n II. STANDARD OF REVIEW\\n\\n We “review the decisions of the Tax Court . . . in the same manner and to\\n\\nthe same extent as decisions of the district courts in civil actions tried without a\\n\\njury.” 26 U.S.C. § 7482(a)(1). “The interpretation of a statutory section of the\\n\\nInternal Revenue Code by the tax court is a question of law reviewed de novo.”\\n\\nMcLaulin v. Comm’r, 276 F.3d 1269, 1272 (11th Cir. 2001).\\n\\n III. DISCUSSION\\n\\n Section 1366 permits a shareholder of an S corporation to deduct his pro\\n\\nrata share of a net operating loss sustained by the corporation:\\n\\n (a) Determination of shareholder’s tax liability.—\\n (1) In general.—In determining the tax under this chapter of a\\n shareholder for the shareholder’s taxable year in which the\\n taxable year of the S corporation ends . . . , there shall be taken\\n into account the shareholder’s pro rata share of the\\n corporation’s—\\n (A) items of income (including tax-exempt income), loss,\\n deduction, or credit the separate treatment of which could\\n affect the liability for tax of any shareholder, and\\n (B) nonseparately computed income or loss.\\n ...\\n (d) Special rules for losses and deductions.—\\n (1) Cannot exceed shareholder’s basis in stock and debt.—\\n The aggregate amount of losses and deductions taken into\\n account by a shareholder under subsection (a) for any taxable\\n year shall not exceed the sum of—\\n\\n\\n 10\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 11 of 18\\n\\n\\n (A) the adjusted basis of the shareholder’s stock in the S\\n corporation . . . , and\\n (B) the shareholder’s adjusted basis of any indebtedness\\n of the S corporation to the shareholder . . . .\\n\\n26 U.S.C. § 1366. Under section 1366(a)(1), an S corporation’s income and\\n\\noperating losses are passed through to its shareholders in a similar way to the tax\\n\\ntreatment of partnerships. Buffered, 506 U.S. at 525; Ellinger v. United States, 470\\n\\nF.3d 1325, 1329 n.2 (11th Cir. 2006). A shareholder may deduct his portion of an\\n\\nS corporation’s net operating losses only to the extent that the loss does not exceed\\n\\nthe sum of “the adjusted basis of the shareholder’s stock in the S corporation,” 26\\n\\nU.S.C. § 1366(d)(1)(A), and “the shareholder’s adjusted basis of any indebtedness\\n\\nof the S corporation to the shareholder,” id. § 1366(d)(1)(B). This appeal concerns\\n\\nonly a shareholder’s adjusted basis of indebtedness under section 1366(d)(1)(B).\\n\\n Meruelo argues, and the Commissioner agrees, that the governing\\n\\nregulation, Treas. Reg. § 1.1366-2, as amended in 2014, provides a standard of\\n\\n“bona fide indebtedness” that must run “directly to the shareholder” for\\n\\ndetermining a shareholder’s debt basis in an S corporation:\\n\\n (2) Basis of indebtedness—(i) In general. The term basis of any\\n indebtedness of the S corporation to the shareholder means the\\n shareholder’s adjusted basis . . . in any bona fide indebtedness of the S\\n corporation that runs directly to the shareholder. Whether indebtedness\\n is bona fide indebtedness to a shareholder is determined under general\\n Federal tax principles and depends upon all of the facts and\\n circumstances.\\n\\n\\n\\n\\n 11\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 12 of 18\\n\\n\\nTreas. Reg. § 1.1366-2(a)(ii)(2) (emphasis added). The Commissioner also agrees\\n\\nthat this regulation applies to Merco’s losses for the 2005 and 2008 tax years\\n\\nbecause those tax years were still open for assessment in July 2014. See id. §\\n\\n1.1366-5(b) (explaining that the regulation applies “with respect to indebtedness\\n\\nbetween an S corporation and its shareholder that resulted from any transaction\\n\\nthat occurred in a year” that was still open for assessment on July 23, 2014).\\n\\n An S corporation’s debt does not run directly to the shareholder if it instead\\n\\nflows through “an entity with passthrough characteristics which advanced the\\n\\nfunds and is closely related to the taxpayer.” Hitchins v. Comm’r, 103 T.C. 711,\\n\\n715 (1994). But the 2014 regulation provides that if a shareholder engages in\\n\\ngenuine “back-to-back” loans—in which an affiliated entity loans the shareholder\\n\\nfunds that he then loans directly to the S corporation—those loans can establish\\n\\nbona fide indebtedness running directly to the shareholder. See Treas. Reg.\\n\\n§ 1.1366-2(a)(2)(iii) (“Example 2. Back-to-back loan transaction. A is the sole\\n\\nshareholder of two S corporations, S1 and S2. S1 loaned $200,000 to A. A then\\n\\nloaned $200,000 to S2 . . . If A’s loan to S2 constitutes bona fide indebtedness\\n\\nfrom S2 to A, A’s back-to-back loan increases A’s basis of indebtedness in\\n\\nS2 . . . .”). So to claim a deduction under section 1366(a), Meruelo had to establish\\n\\nthat a bona fide indebtedness of Merco ran directly to him.\\n\\n\\n\\n\\n 12\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 13 of 18\\n\\n\\n Meruelo presents two alternative arguments that the Tax Court erred in\\n\\ndisallowing his deduction. First, he contends that Merco’s debt ran directly to him\\n\\nunder a back-to-back-loan theory. Second, he contends that the debt ran directly to\\n\\nhim under an incorporated-pocketbook theory. Both arguments fail.\\n\\n A. Meruelo’s Back-to-Back-Loan Theory Fails Because Merco’s Debt Ran to\\n the Merco Affiliates, Not to Meruelo.\\n\\n Meruelo argues that he can claim a debt basis based on his back-to-back-\\n\\nloan theory for two reasons. First, he argues that we should treat the monetary\\n\\ntransfers between the Merco affiliates as back-to-back loans based on the economic\\n\\nsubstance of the transactions rather than the form they took. Second, he\\n\\nalternatively contends that the form of the transactions was sufficient to establish\\n\\nthat they amounted to back-to-back loans.\\n\\n Meruelo’s argument for substance over form is a nonstarter. Taxpayers are\\n\\nordinarily “liable for the tax consequences of the transaction they actually execute\\n\\nand may not reap the benefit of some other transaction that they might have made.”\\n\\nSelfe v. United States, 778 F.2d 769, 773 (11th Cir. 1985). “In other words,\\n\\ntaxpayers ordinarily are bound by the ‘form’ of their transaction and may not argue\\n\\nthat the ‘substance’ of their transaction triggers different tax consequences.” Id.\\n\\nThe Supreme Court has explained that although “a taxpayer is free to organize his\\n\\naffairs as he chooses, nevertheless, once having done so, he must accept the tax\\n\\nconsequences of his choice, whether contemplated or not, and may not enjoy the\\n\\n\\n 13\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 14 of 18\\n\\n\\nbenefit of some other route he might have chosen to follow but did not.” Comm’r\\n\\nv. Nat’l Alfalfa Deyhdrating & Milling Co., 417 U.S. 134, 149 (1974) (citations\\n\\nomitted).\\n\\n The parties cite, and we are aware of, only a single decision in which we\\n\\nhave agreed with a taxpayer that an exceptional circumstance could warrant\\n\\nlooking to the substance of a transaction instead of its form as having a different\\n\\ntax consequence. See Selfe, 778 F.2d at 774. The taxpayer-shareholder in Selfe had\\n\\ninitially obtained a loan in her individual capacity to fund her fledgling retail\\n\\nclothing business and pledged her personal assets as collateral. See id. at 770. At\\n\\nthe bank’s request, she agreed to convert her loan into one from the bank to the S\\n\\ncorporation where she guaranteed the corporation’s indebtedness to the bank and\\n\\ncontinued to pledge her assets as collateral. Id. at 770–71. We concluded that, in\\n\\nthe light of the circumstances suggesting that the bank looked to the shareholder as\\n\\nthe primary obligor on the loan instead of the thinly capitalized S corporation,\\n\\ngenuine issues of material fact existed as to whether the guaranteed loan was\\n\\neffectively a back-to-back loan through the shareholder. Id. at 774–75. We\\n\\nremanded to determine whether the shareholder’s guaranty amounted to either a\\n\\nshareholder loan or an equity investment. Id. at 775.\\n\\n Nothing akin to the exceptional circumstance in Selfe occurred here. Only an\\n\\n“unusual set[] of facts” can warrant judging a transaction based on its substance\\n\\n\\n\\n 14\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 15 of 18\\n\\n\\ninstead of its form. Sleiman v. Comm’r, 187 F.3d 1352, 1359 (11th Cir. 1999)\\n\\n(refusing to extend the approach from Selfe to treat a shareholder-guaranteed loan\\n\\nto an S corporation as if it were a back-to-back loan where the lender looked to the\\n\\nshareholder as only a secondary obligor). Meruelo’s argument about the substance\\n\\nof his transaction—that a portion of the funds the affiliates transferred to Merco\\n\\ncould be considered profits that Meruelo was otherwise entitled to receive and that\\n\\nthe funds were used to pay Merco’s business expenses—hardly presents an\\n\\n“unusual set of facts” about intercompany monetary transfers, and it does not\\n\\njustify setting aside our ordinary rule that the taxpayer is bound by the form his\\n\\ntransactions. See Shebester v. Comm’r, 53 T.C.M. (CCH) 824 (1987) (rejecting\\n\\ntaxpayer’s contention that loans from one controlled S corporation to another\\n\\ncontrolled S corporation were in substance a series of dividends to the shareholder\\n\\nfrom one corporation followed by loans from the shareholder to the other\\n\\ncorporation).\\n\\n Meruelo also argues that his accountant’s end-of-year reclassification of the\\n\\nintercompany transfers, as reflected on his tax returns and on the annual\\n\\nadjustments to the line-of-credit from the 2004 Note, were sufficient to establish\\n\\nthat the transactions amounted to shareholder, but we disagree. “After-the-fact\\n\\nreclassification cannot satisfy the requirement that the debt run directly from the S\\n\\ncorporation to the taxpayer/shareholder, and courts have previously rejected efforts\\n\\n\\n\\n 15\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 16 of 18\\n\\n\\nby taxpayers to establish debt basis in an S corporation using this method.” Broz v.\\n\\nComm’r, 727 F.3d 621, 627 (6th Cir. 2013); Ruckriegel v. Comm’r, 91 T.C.M.\\n\\n(CCH) 1035 (2006) (ruling that yearend reclassification of intercorporate loans as\\n\\nback-to-back loans through the taxpayer was insufficient to provide debt basis);\\n\\nBurnstein v. Comm’r, 47 T.C.M. (CCH) 1100 (1984) (same). Because the\\n\\ntransactions were contemporaneously classified as transactions between the\\n\\naffiliates and Merco, the designation Meruelo’s accountant gave them at the end of\\n\\nthe year does not govern. And we agree with the Tax Court that the accountant’s\\n\\nadjustments to “a notional line of credit, uniformly made after the close of each\\n\\nrelevant tax year, do not suffice to create indebtedness to [Meruelo] where none in\\n\\nfact existed.”\\n\\n B. Meruelo’s Incorporated-Pocketbook Theory Fails Because the Merco\\n Affiliates Were Not His Incorporated Pocketbook.\\n Meruelo alternatively contends that he can claim debt basis based on his\\n\\nincorporated-pocketbook theory. This theory holds that “[a] taxpayer can obtain\\n\\ndebt basis in an S corporation through payments made by a wholly owned\\n\\ncorporate entity if that entity functions as the shareholder’s ‘incorporated\\n\\npocketbook,’ meaning that the taxpayer has a ‘habitual practice of having his\\n\\nwholly owned corporation pay money to third parties on his behalf.’” Broz, 727\\n\\nF.3d at 627–28 (citation omitted). In two decisions, the Tax Court has ruled that\\n\\npayments made to an S corporation by a taxpayer’s “incorporated pocketbook”\\n\\n\\n 16\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 17 of 18\\n\\n\\ncompany were sufficient to establish the shareholder’s debt basis. See Yates v.\\n\\nComm’r, 82 T.C.M. (CCH) 805 (2001); Culnen v. Comm’r, 79 T.C.M. (CCH)\\n\\n1933 (2000), rev’d on other grounds, 28 F. App’x 116 (3d Cir. 2002).\\n\\n Even if we assume that the incorporated-pocketbook theory comports with\\n\\nthe requirement that a debt run “directly to the shareholder,” Meruelo failed to\\n\\nestablish that the Merco affiliates constituted his incorporated pocketbook. Unlike\\n\\nthe shareholders in Yates and Culnen—who used a single, wholly owned entity to\\n\\npay third parties on the shareholder’s behalf—Meruelo seeks to treat eleven\\n\\ndistinct Merco affiliates, many of which he only partially owned, as his\\n\\nincorporated pocketbook. Many of the Merco affiliates acted more like ordinary\\n\\nbusiness entities than as incorporated-pocketbook companies because they both\\n\\ndisbursed and received funds for business expenses from Merco. As the Tax Court\\n\\nexplained, no court has ever ruled that a group of non-wholly owned entities that\\n\\nboth receive and disburse funds in this fashion can constitute an incorporated\\n\\npocketbook. And Meruelo failed to establish that he habitually paid third parties on\\n\\nhis behalf through the putative incorporated-pocketbook companies. Meruelo’s\\n\\nevidence established only that the Merco affiliates regularly paid the expenses of\\n\\nother companies within the affiliate group—not his personal expenses. See Broz,\\n\\n727 F.3d at 628 (affirming Tax Court’s rejection of taxpayers’ “incorporated\\n\\npocketbook” argument where the taxpayers failed to establish that they habitually\\n\\n\\n\\n 17\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 18 of 18\\n\\n\\npaid third parties through the entities); Messina v. Comm’r, 114 T.C. Memo. 2017-\\n\\n213, at *32–33 (2017) (rejecting theory on the same ground); Ruckriegel, 91\\n\\nT.C.M. (CCH) 1035 (same).\\n\\n IV. CONCLUSION\\n\\n We AFFIRM the judgment of the Tax Court in favor of the Commissioner.\\n\\n\\n\\n\\n 18\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4394324/\", \"author_raw\": \"WILLIAM PRYOR, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"PRYOR"},"judge2":{"kind":"string","value":"NEWSOM"},"judge3":{"kind":"string","value":"VRATIL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4617071/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Homero F. MERUELO, Petitioner-Appellant, v. COMMISSIONER OF INTERNAL REVENUE, Respondent-Appellee.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-06\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-11909 Date Filed: 05/06/2019 Page: 1 of 18\n\n\n [PUBLISH]\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 18-11909\n ________________________\n\n Agency No. 001795-13\n\n\n\nHOMERO F. MERUELO,\n\n Petitioner-Appellant,\n\nversus\n\nCOMMISSIONER OF INTERNAL REVENUE,\n\n Respondent-Appellee.\n\n ________________________\n\n Petition for Review of a Decision of the\n United States Tax Court\n ________________________\n\n (May 6, 2019)\n\nBefore WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District\nJudge.\n\nWILLIAM PRYOR, Circuit Judge:\n\n\n\n*\n Honorable Kathryn H. Vratil, United States District Judge for the District of Kansas, sitting by\ndesignation.\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 2 of 18\n\n\n This appeal from the disallowance of a taxpayer’s claimed deduction for his\n\nshare of losses suffered by an S corporation presents the following issue: whether\n\nmonetary transfers between various business entities partly owned by the taxpayer\n\nand an S corporation that were later reclassified as loans from the taxpayer to the S\n\ncorporation established a “bona fide indebtedness” that “runs directly” to the\n\ntaxpayer. Treas. Reg. § 1.1366-2(a)(2)(i); see also 26 U.S.C. § 1366. Homero\n\nMeruelo was a shareholder of Merco of the Palm Beaches, Inc., which suffered a\n\nnearly $27 million loss after banks foreclosed on its condominium complex.\n\nMeruelo asserted that he had a sufficient basis in Merco’s indebtedness for him to\n\ndeduct $13 million as his share of the loss. Meruelo claimed basis from a $5\n\nmillion capital contribution he made to Merco and more than $9 million of\n\nindebtedness from net transfers through various other business entities in which he\n\nheld an interest. The Internal Revenue Service determined that he could claim only\n\nthe $5 million basis and not the $9 million because any debt ran from Merco to the\n\nother entities. The Tax Court later ruled that Meruelo had failed to establish a bona\n\nfide indebtedness of $9 million running directly to him and that he failed to\n\nestablish that he made an “actual economic outlay” toward the debt. Because the\n\nTax Court correctly determined that Meruelo did not establish a bona fide\n\nindebtedness that ran directly to him, we affirm.\n\n\n\n\n 2\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 3 of 18\n\n\n I. BACKGROUND\n\n Meruelo, a real estate developer in south Florida, owns interests in several S\n\ncorporations, partnerships, and limited liability companies. One of these entities\n\nwas Merco of the Palm Beaches, Inc., an S corporation Meruelo incorporated in\n\nMarch 2004. Meruelo held 49 percent of Merco’s stock.\n\n Subchapter S of the Internal Revenue Code provides “a pass-through system\n\nunder which corporate income, losses, deductions, and credits are attributed to\n\nindividual shareholders in a manner akin to the tax treatment of partnerships.”\n\nBuffered v. Comm’r, 506 U.S. 523, 525 (1993). A shareholder’s ability to deduct\n\nhis proportionate share of a corporation’s net operating losses is limited by the sum\n\nof his basis in his stock and the corporate indebtedness to him. See 26 U.S.C.\n\n§ 1366(d)(1). In other words, the shareholder can increase his basis by contributing\n\ncapital to the corporation or by lending money to it.\n\n Meruelo incorporated Merco to purchase a condominium complex in a\n\nbankruptcy sale. In early 2004, the bankruptcy court approved the sale and\n\nrequired Merco to pay a $10 million non-refundable deposit to secure the property.\n\nTo raise funds for his share of the deposit, Meruelo obtained a personal loan.\n\n Meruelo transferred $4,985,035 of the loan proceeds to Merco Group at\n\nAkoya, an S corporation in which he and his mother each held a 50 percent\n\ninterest. In March 2004, Akoya transferred into Merco’s escrow account $5\n\n\n\n 3\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 4 of 18\n\n\nmillion—$4,985,035 of Meruelo’s loan proceeds and $14,965 of Akoya’s own\n\nfunds—to cover half the required deposit. Akoya had also previously transferred to\n\nMerco enough funds to cover the $5 million balance of the deposit. The\n\nCommissioner does not dispute that the $4,985,035 transfer gave Meruelo a\n\nshareholder basis in that amount in Merco.\n\n From 2004 to 2008, Merco entered into hundreds of transactions with\n\nvarious partnerships, S corporations, and limited liability companies in which\n\nMeruelo held an interest. These Merco affiliates often paid expenses, such as\n\npayroll costs, for each other or for Merco to simplify accounting and enhance\n\nliquidity. The payor company recorded these payments to its affiliates as accounts\n\nreceivable, and the payee company recorded them as accounts payable. Between\n\n2004 and 2008, Merco affiliates made more than $15 million in payments to or on\n\nbehalf of Merco, and Merco repaid its affiliates less than $6 million of these\n\npayments. On December 31 of each year, Merco’s books and records showed\n\nsubstantial net accounts payable to its affiliates.\n\n Luis Carreras, a certified public accountant, prepared the tax returns filed by\n\nMeruelo, Merco, and the Merco affiliates. When preparing Merco’s tax return for a\n\ngiven year, Carreras would net Merco’s accounts payable to its affiliates, as shown\n\non Merco’s books as of the preceding December 31, against Merco’s accounts\n\nreceivable from its affiliates. If Merco had net accounts payable, Carreras reported\n\n\n\n 4\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 5 of 18\n\n\nthat amount as a “shareholder loan” on Merco’s tax return. Carreras then allocated\n\na percentage of this indebtedness to Meruelo based on Meruelo’s ownership\n\ninterests in the various affiliates that had transferred funds to Merco.\n\n In March 2004, Carreras drafted a promissory note for Meruelo purportedly\n\nto make a $10 million unsecured line of credit available to Merco at a six percent\n\ninterest rate. Carreras testified that, when he prepared Meruelo’s and Merco’s tax\n\nreturns for tax years 2004 to 2008, he made an annual charge to Merco’s line of\n\ncredit for an amount equal to Meruelo’s calculated share of Merco’s net accounts\n\npayable to its affiliates for the preceding year.\n\n In 2008, Merco incurred a loss of $26,605,840 when banks foreclosed on the\n\ncondominium complex it purchased in 2004. Merco reported this loss on its\n\nincome tax return, and Merco allocated 49 percent of the loss to Meruelo.\n\n Meruelo filed income tax returns for 2005 and 2008. On his 2005 return, he\n\nreported taxable income of $13,895,731 and tax due of $4,843,976. On his 2008\n\nreturn, he claimed an ordinary loss deduction of $11,795,109. This deduction\n\nreflected a $13,036,861 flow-through loss from Merco ($26,605,840 × 49 percent)\n\nnetted against gains of $1,241,752 from two other S corporations in which he held\n\ninterests. After accounting for other income and deductions, Meruelo reported a net\n\noperating loss of $11,793,865 on his 2008 return. In October 2009, he applied for a\n\ntentative refund asserting a net operating loss carryback of $11,793,865 from 2008\n\n\n\n 5\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 6 of 18\n\n\nto 2005. After applying this net operating loss carryback, his original tax lability\n\nfor 2005, $4,843,976, was reduced by $3,897,470, to $946,506. In January 2010,\n\nthe Internal Revenue Service issued Meruelo a refund of $3,897,470.\n\n The Internal Revenue Service selected Meruelo’s 2005 and 2008 returns for\n\nexamination. It determined that his basis in Merco was only $4,985,035 based on\n\nthe proceeds of the bank loan that Meruelo contributed to Merco through Akoya. It\n\ndisallowed, for lack of a sufficient basis, $8,051,826 of the $13,036,861 flow-\n\nthrough loss claimed for 2008.\n\n After disallowing part of the net operating loss for 2008, the Commissioner\n\ndetermined that Meruelo’s carryback to 2005 was limited to $3,706,272 and that\n\nhis correct tax due for 2005 was $3,546,781. Because Meruelo had reported a tax\n\nliability of only $946,506 for 2005, the Commissioner concluded that Meruelo’s\n\ntax deficiency for that year was $2,600,275 and sent Meruelo a notice of\n\ndeficiency.\n\n Meruelo petitioned the Tax Court for redetermination of his tax deficiency.\n\nHe alleged that he had a sufficient basis in Merco for him to fully deduct his share\n\nof its 2008 losses. Meruelo alleged that his basis in Merco consisted of $2.7\n\nmillion of Akoya’s first deposit of $5 million, all $5 million of Akoya’s second\n\ndeposit, and $6,616,857 for his share of intercompany transfers.\n\n\n\n\n 6\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 7 of 18\n\n\n Meruelo offered two theories to claim credit for the affiliated companies’\n\ntransfers to Merco: the “back-to-back loan” theory and the “incorporated\n\npocketbook theory.” Under the back-to-back-loan theory, he argued the affiliated\n\ncompanies should have been treated as lending funds to him that he then lent to\n\nMerco. And under the incorporated-pocketbook theory, Meruelo argued that he\n\nshould have been treated as using his funds, which were held by the affiliated\n\ncompanies, to pay Merco’s expenses on his behalf.\n\n After a trial, the Tax Court ruled for the Commissioner. The Tax Court\n\nacknowledged that Meruelo had an undisputed basis of $4,985,035 in Merco, and it\n\nexplained that only $8,051,826 of the $13,036,9861 flow-through loss was in\n\ndispute. But the Tax Court determined that Meruelo was not entitled to any of the\n\ndisputed basis.\n\n The Tax Court explained that section 1366(d)(1)(B) of the Internal Revenue\n\nCode allows a shareholder to increase his basis by the amount of the adjusted basis\n\nof any indebtedness owed by the S corporation to the shareholder. Because the\n\nCode “does not specify how a shareholder may acquire basis in an S corporation’s\n\nindebtedness to him,” the Tax Court turned to the legislative history of the\n\npredecessor to section 1366 for guidance. The Tax Court explained that earlier\n\ndecisions relied on this legislative history and construed language about “a\n\nshareholder’s investment in a corporation” to require an “actual economic outlay”\n\n\n\n 7\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 8 of 18\n\n\nby the shareholder. In other words, the Tax Court ruled that a shareholder must\n\nshow that he incurred a cost in making a loan or that he was left poorer in a\n\nmaterial sense after the transaction.\n\n The Tax Court decided that the test for determining a shareholder’s basis in\n\nan S corporation under Treasury Regulation § 1.1366-2(a)(2)—which was\n\namended in 2014 and limits debt basis to “bona fide indebtedness of the S\n\ncorporation that runs directly to the shareholder”—was effectively the same as that\n\nunder the “actual economic outlay” doctrine. The Tax Court explained that it had\n\nlong required that a shareholder prove an S corporation’s indebtedness running\n\ndirectly to him to deduct his proportionate share of the corporation’s net operating\n\nloss. And the Tax Court reasoned that because the 2014 regulation states that\n\n“bona fide indebtedness” is to be determined by “general Federal tax principles,”\n\nthe 2014 regulation incorporates the actual economic outlay doctrine.\n\n The Tax Court rejected Meruelo’s back-to-back-loan theory because there\n\nwas no evidence that funds had been lent to Meruelo and then lent back to Merco.\n\nThe Tax Court acknowledged that bona fide back-to-back loans, first from an\n\naffiliated company to a shareholder and then from the shareholder to the debtor S\n\ncorporation, can increase a shareholder’s basis. But it explained that a shareholder\n\nis bound by the form of the transaction he initially chose and that transactions\n\ndirectly among related companies (and not involving the shareholder) do not\n\n\n\n 8\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 9 of 18\n\n\nqualify as back-to-back loans. The Tax Court clarified that a taxpayer-shareholder\n\ncannot reclassify intercompany loans as shareholder loans for tax purposes when\n\npreparing his return. The Tax Court then ruled that, because there was no evidence\n\nthat the Merco affiliates had contemporaneously booked transfers between them as\n\nshareholder loans—the affiliates instead labeled them as accounts receivable and\n\npayable, wage payments, or capital contributions—Meruelo’s back-to-back-loan\n\ntheory failed. The Tax Court also ruled that, because Meruelo made no actual\n\neconomic outlay toward the monetary transfers from the Merco affiliates to Merco,\n\nhe could not claim that these transfers amounted to a shareholder loan.\n\n The Tax Court likewise rejected Meruelo’s incorporated-pocketbook theory.\n\nThe Tax Court explained that, although some of its rulings allowed basis increases\n\nunder an incorporated-pocketbook theory, the facts here were a “far cry” from\n\nthose decisions. The Tax Court explained that in other incorporated-pocketbook\n\ndecisions, the taxpayer habitually used a single, wholly owned corporation to pay\n\nthird parties on his behalf. But many of the Merco affiliates had co-owners besides\n\nMeruelo, and Meruelo had not shown that these affiliates had a “habitual practice”\n\nof paying his personal expenses. And the Tax Court explained that the\n\n“incorporated pocketbook” corporations contemporaneously booked the\n\ndisbursements as shareholder loans. The Merco affiliates, by contrast, booked their\n\ntransactions as capital contributions, payroll expenses, or intercompany accounts\n\n\n\n 9\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 10 of 18\n\n\npayable and receivable, and only relabeled the disbursements as shareholder loans\n\nat the close of each year. The Tax Court upheld the Commissioner’s determination\n\nof a $2,600,275 deficiency.\n\n II. STANDARD OF REVIEW\n\n We “review the decisions of the Tax Court . . . in the same manner and to\n\nthe same extent as decisions of the district courts in civil actions tried without a\n\njury.” 26 U.S.C. § 7482(a)(1). “The interpretation of a statutory section of the\n\nInternal Revenue Code by the tax court is a question of law reviewed de novo.”\n\nMcLaulin v. Comm’r, 276 F.3d 1269, 1272 (11th Cir. 2001).\n\n III. DISCUSSION\n\n Section 1366 permits a shareholder of an S corporation to deduct his pro\n\nrata share of a net operating loss sustained by the corporation:\n\n (a) Determination of shareholder’s tax liability.—\n (1) In general.—In determining the tax under this chapter of a\n shareholder for the shareholder’s taxable year in which the\n taxable year of the S corporation ends . . . , there shall be taken\n into account the shareholder’s pro rata share of the\n corporation’s—\n (A) items of income (including tax-exempt income), loss,\n deduction, or credit the separate treatment of which could\n affect the liability for tax of any shareholder, and\n (B) nonseparately computed income or loss.\n ...\n (d) Special rules for losses and deductions.—\n (1) Cannot exceed shareholder’s basis in stock and debt.—\n The aggregate amount of losses and deductions taken into\n account by a shareholder under subsection (a) for any taxable\n year shall not exceed the sum of—\n\n\n 10\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 11 of 18\n\n\n (A) the adjusted basis of the shareholder’s stock in the S\n corporation . . . , and\n (B) the shareholder’s adjusted basis of any indebtedness\n of the S corporation to the shareholder . . . .\n\n26 U.S.C. § 1366. Under section 1366(a)(1), an S corporation’s income and\n\noperating losses are passed through to its shareholders in a similar way to the tax\n\ntreatment of partnerships. Buffered, 506 U.S. at 525; Ellinger v. United States, 470\n\nF.3d 1325, 1329 n.2 (11th Cir. 2006). A shareholder may deduct his portion of an\n\nS corporation’s net operating losses only to the extent that the loss does not exceed\n\nthe sum of “the adjusted basis of the shareholder’s stock in the S corporation,” 26\n\nU.S.C. § 1366(d)(1)(A), and “the shareholder’s adjusted basis of any indebtedness\n\nof the S corporation to the shareholder,” id. § 1366(d)(1)(B). This appeal concerns\n\nonly a shareholder’s adjusted basis of indebtedness under section 1366(d)(1)(B).\n\n Meruelo argues, and the Commissioner agrees, that the governing\n\nregulation, Treas. Reg. § 1.1366-2, as amended in 2014, provides a standard of\n\n“bona fide indebtedness” that must run “directly to the shareholder” for\n\ndetermining a shareholder’s debt basis in an S corporation:\n\n (2) Basis of indebtedness—(i) In general. The term basis of any\n indebtedness of the S corporation to the shareholder means the\n shareholder’s adjusted basis . . . in any bona fide indebtedness of the S\n corporation that runs directly to the shareholder. Whether indebtedness\n is bona fide indebtedness to a shareholder is determined under general\n Federal tax principles and depends upon all of the facts and\n circumstances.\n\n\n\n\n 11\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 12 of 18\n\n\nTreas. Reg. § 1.1366-2(a)(ii)(2) (emphasis added). The Commissioner also agrees\n\nthat this regulation applies to Merco’s losses for the 2005 and 2008 tax years\n\nbecause those tax years were still open for assessment in July 2014. See id. §\n\n1.1366-5(b) (explaining that the regulation applies “with respect to indebtedness\n\nbetween an S corporation and its shareholder that resulted from any transaction\n\nthat occurred in a year” that was still open for assessment on July 23, 2014).\n\n An S corporation’s debt does not run directly to the shareholder if it instead\n\nflows through “an entity with passthrough characteristics which advanced the\n\nfunds and is closely related to the taxpayer.” Hitchins v. Comm’r, 103 T.C. 711,\n\n715 (1994). But the 2014 regulation provides that if a shareholder engages in\n\ngenuine “back-to-back” loans—in which an affiliated entity loans the shareholder\n\nfunds that he then loans directly to the S corporation—those loans can establish\n\nbona fide indebtedness running directly to the shareholder. See Treas. Reg.\n\n§ 1.1366-2(a)(2)(iii) (“Example 2. Back-to-back loan transaction. A is the sole\n\nshareholder of two S corporations, S1 and S2. S1 loaned $200,000 to A. A then\n\nloaned $200,000 to S2 . . . If A’s loan to S2 constitutes bona fide indebtedness\n\nfrom S2 to A, A’s back-to-back loan increases A’s basis of indebtedness in\n\nS2 . . . .”). So to claim a deduction under section 1366(a), Meruelo had to establish\n\nthat a bona fide indebtedness of Merco ran directly to him.\n\n\n\n\n 12\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 13 of 18\n\n\n Meruelo presents two alternative arguments that the Tax Court erred in\n\ndisallowing his deduction. First, he contends that Merco’s debt ran directly to him\n\nunder a back-to-back-loan theory. Second, he contends that the debt ran directly to\n\nhim under an incorporated-pocketbook theory. Both arguments fail.\n\n A. Meruelo’s Back-to-Back-Loan Theory Fails Because Merco’s Debt Ran to\n the Merco Affiliates, Not to Meruelo.\n\n Meruelo argues that he can claim a debt basis based on his back-to-back-\n\nloan theory for two reasons. First, he argues that we should treat the monetary\n\ntransfers between the Merco affiliates as back-to-back loans based on the economic\n\nsubstance of the transactions rather than the form they took. Second, he\n\nalternatively contends that the form of the transactions was sufficient to establish\n\nthat they amounted to back-to-back loans.\n\n Meruelo’s argument for substance over form is a nonstarter. Taxpayers are\n\nordinarily “liable for the tax consequences of the transaction they actually execute\n\nand may not reap the benefit of some other transaction that they might have made.”\n\nSelfe v. United States, 778 F.2d 769, 773 (11th Cir. 1985). “In other words,\n\ntaxpayers ordinarily are bound by the ‘form’ of their transaction and may not argue\n\nthat the ‘substance’ of their transaction triggers different tax consequences.” Id.\n\nThe Supreme Court has explained that although “a taxpayer is free to organize his\n\naffairs as he chooses, nevertheless, once having done so, he must accept the tax\n\nconsequences of his choice, whether contemplated or not, and may not enjoy the\n\n\n 13\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 14 of 18\n\n\nbenefit of some other route he might have chosen to follow but did not.” Comm’r\n\nv. Nat’l Alfalfa Deyhdrating & Milling Co., 417 U.S. 134, 149 (1974) (citations\n\nomitted).\n\n The parties cite, and we are aware of, only a single decision in which we\n\nhave agreed with a taxpayer that an exceptional circumstance could warrant\n\nlooking to the substance of a transaction instead of its form as having a different\n\ntax consequence. See Selfe, 778 F.2d at 774. The taxpayer-shareholder in Selfe had\n\ninitially obtained a loan in her individual capacity to fund her fledgling retail\n\nclothing business and pledged her personal assets as collateral. See id. at 770. At\n\nthe bank’s request, she agreed to convert her loan into one from the bank to the S\n\ncorporation where she guaranteed the corporation’s indebtedness to the bank and\n\ncontinued to pledge her assets as collateral. Id. at 770–71. We concluded that, in\n\nthe light of the circumstances suggesting that the bank looked to the shareholder as\n\nthe primary obligor on the loan instead of the thinly capitalized S corporation,\n\ngenuine issues of material fact existed as to whether the guaranteed loan was\n\neffectively a back-to-back loan through the shareholder. Id. at 774–75. We\n\nremanded to determine whether the shareholder’s guaranty amounted to either a\n\nshareholder loan or an equity investment. Id. at 775.\n\n Nothing akin to the exceptional circumstance in Selfe occurred here. Only an\n\n“unusual set[] of facts” can warrant judging a transaction based on its substance\n\n\n\n 14\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 15 of 18\n\n\ninstead of its form. Sleiman v. Comm’r, 187 F.3d 1352, 1359 (11th Cir. 1999)\n\n(refusing to extend the approach from Selfe to treat a shareholder-guaranteed loan\n\nto an S corporation as if it were a back-to-back loan where the lender looked to the\n\nshareholder as only a secondary obligor). Meruelo’s argument about the substance\n\nof his transaction—that a portion of the funds the affiliates transferred to Merco\n\ncould be considered profits that Meruelo was otherwise entitled to receive and that\n\nthe funds were used to pay Merco’s business expenses—hardly presents an\n\n“unusual set of facts” about intercompany monetary transfers, and it does not\n\njustify setting aside our ordinary rule that the taxpayer is bound by the form his\n\ntransactions. See Shebester v. Comm’r, 53 T.C.M. (CCH) 824 (1987) (rejecting\n\ntaxpayer’s contention that loans from one controlled S corporation to another\n\ncontrolled S corporation were in substance a series of dividends to the shareholder\n\nfrom one corporation followed by loans from the shareholder to the other\n\ncorporation).\n\n Meruelo also argues that his accountant’s end-of-year reclassification of the\n\nintercompany transfers, as reflected on his tax returns and on the annual\n\nadjustments to the line-of-credit from the 2004 Note, were sufficient to establish\n\nthat the transactions amounted to shareholder, but we disagree. “After-the-fact\n\nreclassification cannot satisfy the requirement that the debt run directly from the S\n\ncorporation to the taxpayer/shareholder, and courts have previously rejected efforts\n\n\n\n 15\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 16 of 18\n\n\nby taxpayers to establish debt basis in an S corporation using this method.” Broz v.\n\nComm’r, 727 F.3d 621, 627 (6th Cir. 2013); Ruckriegel v. Comm’r, 91 T.C.M.\n\n(CCH) 1035 (2006) (ruling that yearend reclassification of intercorporate loans as\n\nback-to-back loans through the taxpayer was insufficient to provide debt basis);\n\nBurnstein v. Comm’r, 47 T.C.M. (CCH) 1100 (1984) (same). Because the\n\ntransactions were contemporaneously classified as transactions between the\n\naffiliates and Merco, the designation Meruelo’s accountant gave them at the end of\n\nthe year does not govern. And we agree with the Tax Court that the accountant’s\n\nadjustments to “a notional line of credit, uniformly made after the close of each\n\nrelevant tax year, do not suffice to create indebtedness to [Meruelo] where none in\n\nfact existed.”\n\n B. Meruelo’s Incorporated-Pocketbook Theory Fails Because the Merco\n Affiliates Were Not His Incorporated Pocketbook.\n Meruelo alternatively contends that he can claim debt basis based on his\n\nincorporated-pocketbook theory. This theory holds that “[a] taxpayer can obtain\n\ndebt basis in an S corporation through payments made by a wholly owned\n\ncorporate entity if that entity functions as the shareholder’s ‘incorporated\n\npocketbook,’ meaning that the taxpayer has a ‘habitual practice of having his\n\nwholly owned corporation pay money to third parties on his behalf.’” Broz, 727\n\nF.3d at 627–28 (citation omitted). In two decisions, the Tax Court has ruled that\n\npayments made to an S corporation by a taxpayer’s “incorporated pocketbook”\n\n\n 16\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 17 of 18\n\n\ncompany were sufficient to establish the shareholder’s debt basis. See Yates v.\n\nComm’r, 82 T.C.M. (CCH) 805 (2001); Culnen v. Comm’r, 79 T.C.M. (CCH)\n\n1933 (2000), rev’d on other grounds, 28 F. App’x 116 (3d Cir. 2002).\n\n Even if we assume that the incorporated-pocketbook theory comports with\n\nthe requirement that a debt run “directly to the shareholder,” Meruelo failed to\n\nestablish that the Merco affiliates constituted his incorporated pocketbook. Unlike\n\nthe shareholders in Yates and Culnen—who used a single, wholly owned entity to\n\npay third parties on the shareholder’s behalf—Meruelo seeks to treat eleven\n\ndistinct Merco affiliates, many of which he only partially owned, as his\n\nincorporated pocketbook. Many of the Merco affiliates acted more like ordinary\n\nbusiness entities than as incorporated-pocketbook companies because they both\n\ndisbursed and received funds for business expenses from Merco. As the Tax Court\n\nexplained, no court has ever ruled that a group of non-wholly owned entities that\n\nboth receive and disburse funds in this fashion can constitute an incorporated\n\npocketbook. And Meruelo failed to establish that he habitually paid third parties on\n\nhis behalf through the putative incorporated-pocketbook companies. Meruelo’s\n\nevidence established only that the Merco affiliates regularly paid the expenses of\n\nother companies within the affiliate group—not his personal expenses. See Broz,\n\n727 F.3d at 628 (affirming Tax Court’s rejection of taxpayers’ “incorporated\n\npocketbook” argument where the taxpayers failed to establish that they habitually\n\n\n\n 17\n\f Case: 18-11909 Date Filed: 05/06/2019 Page: 18 of 18\n\n\npaid third parties through the entities); Messina v. Comm’r, 114 T.C. Memo. 2017-\n\n213, at *32–33 (2017) (rejecting theory on the same ground); Ruckriegel, 91\n\nT.C.M. (CCH) 1035 (same).\n\n IV. CONCLUSION\n\n We AFFIRM the judgment of the Tax Court in favor of the Commissioner.\n\n\n\n\n 18\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Homero F. MERUELO, Petitioner-Appellant, v. COMMISSIONER OF INTERNAL REVENUE, Respondent-Appellee.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-06\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-11909 Date Filed: 05/06/2019 Page: 1 of 18\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-11909\\n ________________________\\n\\n Agency No. 001795-13\\n\\n\\n\\nHOMERO F. MERUELO,\\n\\n Petitioner-Appellant,\\n\\nversus\\n\\nCOMMISSIONER OF INTERNAL REVENUE,\\n\\n Respondent-Appellee.\\n\\n ________________________\\n\\n Petition for Review of a Decision of the\\n United States Tax Court\\n ________________________\\n\\n (May 6, 2019)\\n\\nBefore WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District\\nJudge.\\n\\nWILLIAM PRYOR, Circuit Judge:\\n\\n\\n\\n*\\n Honorable Kathryn H. Vratil, United States District Judge for the District of Kansas, sitting by\\ndesignation.\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 2 of 18\\n\\n\\n This appeal from the disallowance of a taxpayer’s claimed deduction for his\\n\\nshare of losses suffered by an S corporation presents the following issue: whether\\n\\nmonetary transfers between various business entities partly owned by the taxpayer\\n\\nand an S corporation that were later reclassified as loans from the taxpayer to the S\\n\\ncorporation established a “bona fide indebtedness” that “runs directly” to the\\n\\ntaxpayer. Treas. Reg. § 1.1366-2(a)(2)(i); see also 26 U.S.C. § 1366. Homero\\n\\nMeruelo was a shareholder of Merco of the Palm Beaches, Inc., which suffered a\\n\\nnearly $27 million loss after banks foreclosed on its condominium complex.\\n\\nMeruelo asserted that he had a sufficient basis in Merco’s indebtedness for him to\\n\\ndeduct $13 million as his share of the loss. Meruelo claimed basis from a $5\\n\\nmillion capital contribution he made to Merco and more than $9 million of\\n\\nindebtedness from net transfers through various other business entities in which he\\n\\nheld an interest. The Internal Revenue Service determined that he could claim only\\n\\nthe $5 million basis and not the $9 million because any debt ran from Merco to the\\n\\nother entities. The Tax Court later ruled that Meruelo had failed to establish a bona\\n\\nfide indebtedness of $9 million running directly to him and that he failed to\\n\\nestablish that he made an “actual economic outlay” toward the debt. Because the\\n\\nTax Court correctly determined that Meruelo did not establish a bona fide\\n\\nindebtedness that ran directly to him, we affirm.\\n\\n\\n\\n\\n 2\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 3 of 18\\n\\n\\n I. BACKGROUND\\n\\n Meruelo, a real estate developer in south Florida, owns interests in several S\\n\\ncorporations, partnerships, and limited liability companies. One of these entities\\n\\nwas Merco of the Palm Beaches, Inc., an S corporation Meruelo incorporated in\\n\\nMarch 2004. Meruelo held 49 percent of Merco’s stock.\\n\\n Subchapter S of the Internal Revenue Code provides “a pass-through system\\n\\nunder which corporate income, losses, deductions, and credits are attributed to\\n\\nindividual shareholders in a manner akin to the tax treatment of partnerships.”\\n\\nBuffered v. Comm’r, 506 U.S. 523, 525 (1993). A shareholder’s ability to deduct\\n\\nhis proportionate share of a corporation’s net operating losses is limited by the sum\\n\\nof his basis in his stock and the corporate indebtedness to him. See 26 U.S.C.\\n\\n§ 1366(d)(1). In other words, the shareholder can increase his basis by contributing\\n\\ncapital to the corporation or by lending money to it.\\n\\n Meruelo incorporated Merco to purchase a condominium complex in a\\n\\nbankruptcy sale. In early 2004, the bankruptcy court approved the sale and\\n\\nrequired Merco to pay a $10 million non-refundable deposit to secure the property.\\n\\nTo raise funds for his share of the deposit, Meruelo obtained a personal loan.\\n\\n Meruelo transferred $4,985,035 of the loan proceeds to Merco Group at\\n\\nAkoya, an S corporation in which he and his mother each held a 50 percent\\n\\ninterest. In March 2004, Akoya transferred into Merco’s escrow account $5\\n\\n\\n\\n 3\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 4 of 18\\n\\n\\nmillion—$4,985,035 of Meruelo’s loan proceeds and $14,965 of Akoya’s own\\n\\nfunds—to cover half the required deposit. Akoya had also previously transferred to\\n\\nMerco enough funds to cover the $5 million balance of the deposit. The\\n\\nCommissioner does not dispute that the $4,985,035 transfer gave Meruelo a\\n\\nshareholder basis in that amount in Merco.\\n\\n From 2004 to 2008, Merco entered into hundreds of transactions with\\n\\nvarious partnerships, S corporations, and limited liability companies in which\\n\\nMeruelo held an interest. These Merco affiliates often paid expenses, such as\\n\\npayroll costs, for each other or for Merco to simplify accounting and enhance\\n\\nliquidity. The payor company recorded these payments to its affiliates as accounts\\n\\nreceivable, and the payee company recorded them as accounts payable. Between\\n\\n2004 and 2008, Merco affiliates made more than $15 million in payments to or on\\n\\nbehalf of Merco, and Merco repaid its affiliates less than $6 million of these\\n\\npayments. On December 31 of each year, Merco’s books and records showed\\n\\nsubstantial net accounts payable to its affiliates.\\n\\n Luis Carreras, a certified public accountant, prepared the tax returns filed by\\n\\nMeruelo, Merco, and the Merco affiliates. When preparing Merco’s tax return for a\\n\\ngiven year, Carreras would net Merco’s accounts payable to its affiliates, as shown\\n\\non Merco’s books as of the preceding December 31, against Merco’s accounts\\n\\nreceivable from its affiliates. If Merco had net accounts payable, Carreras reported\\n\\n\\n\\n 4\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 5 of 18\\n\\n\\nthat amount as a “shareholder loan” on Merco’s tax return. Carreras then allocated\\n\\na percentage of this indebtedness to Meruelo based on Meruelo’s ownership\\n\\ninterests in the various affiliates that had transferred funds to Merco.\\n\\n In March 2004, Carreras drafted a promissory note for Meruelo purportedly\\n\\nto make a $10 million unsecured line of credit available to Merco at a six percent\\n\\ninterest rate. Carreras testified that, when he prepared Meruelo’s and Merco’s tax\\n\\nreturns for tax years 2004 to 2008, he made an annual charge to Merco’s line of\\n\\ncredit for an amount equal to Meruelo’s calculated share of Merco’s net accounts\\n\\npayable to its affiliates for the preceding year.\\n\\n In 2008, Merco incurred a loss of $26,605,840 when banks foreclosed on the\\n\\ncondominium complex it purchased in 2004. Merco reported this loss on its\\n\\nincome tax return, and Merco allocated 49 percent of the loss to Meruelo.\\n\\n Meruelo filed income tax returns for 2005 and 2008. On his 2005 return, he\\n\\nreported taxable income of $13,895,731 and tax due of $4,843,976. On his 2008\\n\\nreturn, he claimed an ordinary loss deduction of $11,795,109. This deduction\\n\\nreflected a $13,036,861 flow-through loss from Merco ($26,605,840 × 49 percent)\\n\\nnetted against gains of $1,241,752 from two other S corporations in which he held\\n\\ninterests. After accounting for other income and deductions, Meruelo reported a net\\n\\noperating loss of $11,793,865 on his 2008 return. In October 2009, he applied for a\\n\\ntentative refund asserting a net operating loss carryback of $11,793,865 from 2008\\n\\n\\n\\n 5\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 6 of 18\\n\\n\\nto 2005. After applying this net operating loss carryback, his original tax lability\\n\\nfor 2005, $4,843,976, was reduced by $3,897,470, to $946,506. In January 2010,\\n\\nthe Internal Revenue Service issued Meruelo a refund of $3,897,470.\\n\\n The Internal Revenue Service selected Meruelo’s 2005 and 2008 returns for\\n\\nexamination. It determined that his basis in Merco was only $4,985,035 based on\\n\\nthe proceeds of the bank loan that Meruelo contributed to Merco through Akoya. It\\n\\ndisallowed, for lack of a sufficient basis, $8,051,826 of the $13,036,861 flow-\\n\\nthrough loss claimed for 2008.\\n\\n After disallowing part of the net operating loss for 2008, the Commissioner\\n\\ndetermined that Meruelo’s carryback to 2005 was limited to $3,706,272 and that\\n\\nhis correct tax due for 2005 was $3,546,781. Because Meruelo had reported a tax\\n\\nliability of only $946,506 for 2005, the Commissioner concluded that Meruelo’s\\n\\ntax deficiency for that year was $2,600,275 and sent Meruelo a notice of\\n\\ndeficiency.\\n\\n Meruelo petitioned the Tax Court for redetermination of his tax deficiency.\\n\\nHe alleged that he had a sufficient basis in Merco for him to fully deduct his share\\n\\nof its 2008 losses. Meruelo alleged that his basis in Merco consisted of $2.7\\n\\nmillion of Akoya’s first deposit of $5 million, all $5 million of Akoya’s second\\n\\ndeposit, and $6,616,857 for his share of intercompany transfers.\\n\\n\\n\\n\\n 6\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 7 of 18\\n\\n\\n Meruelo offered two theories to claim credit for the affiliated companies’\\n\\ntransfers to Merco: the “back-to-back loan” theory and the “incorporated\\n\\npocketbook theory.” Under the back-to-back-loan theory, he argued the affiliated\\n\\ncompanies should have been treated as lending funds to him that he then lent to\\n\\nMerco. And under the incorporated-pocketbook theory, Meruelo argued that he\\n\\nshould have been treated as using his funds, which were held by the affiliated\\n\\ncompanies, to pay Merco’s expenses on his behalf.\\n\\n After a trial, the Tax Court ruled for the Commissioner. The Tax Court\\n\\nacknowledged that Meruelo had an undisputed basis of $4,985,035 in Merco, and it\\n\\nexplained that only $8,051,826 of the $13,036,9861 flow-through loss was in\\n\\ndispute. But the Tax Court determined that Meruelo was not entitled to any of the\\n\\ndisputed basis.\\n\\n The Tax Court explained that section 1366(d)(1)(B) of the Internal Revenue\\n\\nCode allows a shareholder to increase his basis by the amount of the adjusted basis\\n\\nof any indebtedness owed by the S corporation to the shareholder. Because the\\n\\nCode “does not specify how a shareholder may acquire basis in an S corporation’s\\n\\nindebtedness to him,” the Tax Court turned to the legislative history of the\\n\\npredecessor to section 1366 for guidance. The Tax Court explained that earlier\\n\\ndecisions relied on this legislative history and construed language about “a\\n\\nshareholder’s investment in a corporation” to require an “actual economic outlay”\\n\\n\\n\\n 7\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 8 of 18\\n\\n\\nby the shareholder. In other words, the Tax Court ruled that a shareholder must\\n\\nshow that he incurred a cost in making a loan or that he was left poorer in a\\n\\nmaterial sense after the transaction.\\n\\n The Tax Court decided that the test for determining a shareholder’s basis in\\n\\nan S corporation under Treasury Regulation § 1.1366-2(a)(2)—which was\\n\\namended in 2014 and limits debt basis to “bona fide indebtedness of the S\\n\\ncorporation that runs directly to the shareholder”—was effectively the same as that\\n\\nunder the “actual economic outlay” doctrine. The Tax Court explained that it had\\n\\nlong required that a shareholder prove an S corporation’s indebtedness running\\n\\ndirectly to him to deduct his proportionate share of the corporation’s net operating\\n\\nloss. And the Tax Court reasoned that because the 2014 regulation states that\\n\\n“bona fide indebtedness” is to be determined by “general Federal tax principles,”\\n\\nthe 2014 regulation incorporates the actual economic outlay doctrine.\\n\\n The Tax Court rejected Meruelo’s back-to-back-loan theory because there\\n\\nwas no evidence that funds had been lent to Meruelo and then lent back to Merco.\\n\\nThe Tax Court acknowledged that bona fide back-to-back loans, first from an\\n\\naffiliated company to a shareholder and then from the shareholder to the debtor S\\n\\ncorporation, can increase a shareholder’s basis. But it explained that a shareholder\\n\\nis bound by the form of the transaction he initially chose and that transactions\\n\\ndirectly among related companies (and not involving the shareholder) do not\\n\\n\\n\\n 8\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 9 of 18\\n\\n\\nqualify as back-to-back loans. The Tax Court clarified that a taxpayer-shareholder\\n\\ncannot reclassify intercompany loans as shareholder loans for tax purposes when\\n\\npreparing his return. The Tax Court then ruled that, because there was no evidence\\n\\nthat the Merco affiliates had contemporaneously booked transfers between them as\\n\\nshareholder loans—the affiliates instead labeled them as accounts receivable and\\n\\npayable, wage payments, or capital contributions—Meruelo’s back-to-back-loan\\n\\ntheory failed. The Tax Court also ruled that, because Meruelo made no actual\\n\\neconomic outlay toward the monetary transfers from the Merco affiliates to Merco,\\n\\nhe could not claim that these transfers amounted to a shareholder loan.\\n\\n The Tax Court likewise rejected Meruelo’s incorporated-pocketbook theory.\\n\\nThe Tax Court explained that, although some of its rulings allowed basis increases\\n\\nunder an incorporated-pocketbook theory, the facts here were a “far cry” from\\n\\nthose decisions. The Tax Court explained that in other incorporated-pocketbook\\n\\ndecisions, the taxpayer habitually used a single, wholly owned corporation to pay\\n\\nthird parties on his behalf. But many of the Merco affiliates had co-owners besides\\n\\nMeruelo, and Meruelo had not shown that these affiliates had a “habitual practice”\\n\\nof paying his personal expenses. And the Tax Court explained that the\\n\\n“incorporated pocketbook” corporations contemporaneously booked the\\n\\ndisbursements as shareholder loans. The Merco affiliates, by contrast, booked their\\n\\ntransactions as capital contributions, payroll expenses, or intercompany accounts\\n\\n\\n\\n 9\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 10 of 18\\n\\n\\npayable and receivable, and only relabeled the disbursements as shareholder loans\\n\\nat the close of each year. The Tax Court upheld the Commissioner’s determination\\n\\nof a $2,600,275 deficiency.\\n\\n II. STANDARD OF REVIEW\\n\\n We “review the decisions of the Tax Court . . . in the same manner and to\\n\\nthe same extent as decisions of the district courts in civil actions tried without a\\n\\njury.” 26 U.S.C. § 7482(a)(1). “The interpretation of a statutory section of the\\n\\nInternal Revenue Code by the tax court is a question of law reviewed de novo.”\\n\\nMcLaulin v. Comm’r, 276 F.3d 1269, 1272 (11th Cir. 2001).\\n\\n III. DISCUSSION\\n\\n Section 1366 permits a shareholder of an S corporation to deduct his pro\\n\\nrata share of a net operating loss sustained by the corporation:\\n\\n (a) Determination of shareholder’s tax liability.—\\n (1) In general.—In determining the tax under this chapter of a\\n shareholder for the shareholder’s taxable year in which the\\n taxable year of the S corporation ends . . . , there shall be taken\\n into account the shareholder’s pro rata share of the\\n corporation’s—\\n (A) items of income (including tax-exempt income), loss,\\n deduction, or credit the separate treatment of which could\\n affect the liability for tax of any shareholder, and\\n (B) nonseparately computed income or loss.\\n ...\\n (d) Special rules for losses and deductions.—\\n (1) Cannot exceed shareholder’s basis in stock and debt.—\\n The aggregate amount of losses and deductions taken into\\n account by a shareholder under subsection (a) for any taxable\\n year shall not exceed the sum of—\\n\\n\\n 10\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 11 of 18\\n\\n\\n (A) the adjusted basis of the shareholder’s stock in the S\\n corporation . . . , and\\n (B) the shareholder’s adjusted basis of any indebtedness\\n of the S corporation to the shareholder . . . .\\n\\n26 U.S.C. § 1366. Under section 1366(a)(1), an S corporation’s income and\\n\\noperating losses are passed through to its shareholders in a similar way to the tax\\n\\ntreatment of partnerships. Buffered, 506 U.S. at 525; Ellinger v. United States, 470\\n\\nF.3d 1325, 1329 n.2 (11th Cir. 2006). A shareholder may deduct his portion of an\\n\\nS corporation’s net operating losses only to the extent that the loss does not exceed\\n\\nthe sum of “the adjusted basis of the shareholder’s stock in the S corporation,” 26\\n\\nU.S.C. § 1366(d)(1)(A), and “the shareholder’s adjusted basis of any indebtedness\\n\\nof the S corporation to the shareholder,” id. § 1366(d)(1)(B). This appeal concerns\\n\\nonly a shareholder’s adjusted basis of indebtedness under section 1366(d)(1)(B).\\n\\n Meruelo argues, and the Commissioner agrees, that the governing\\n\\nregulation, Treas. Reg. § 1.1366-2, as amended in 2014, provides a standard of\\n\\n“bona fide indebtedness” that must run “directly to the shareholder” for\\n\\ndetermining a shareholder’s debt basis in an S corporation:\\n\\n (2) Basis of indebtedness—(i) In general. The term basis of any\\n indebtedness of the S corporation to the shareholder means the\\n shareholder’s adjusted basis . . . in any bona fide indebtedness of the S\\n corporation that runs directly to the shareholder. Whether indebtedness\\n is bona fide indebtedness to a shareholder is determined under general\\n Federal tax principles and depends upon all of the facts and\\n circumstances.\\n\\n\\n\\n\\n 11\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 12 of 18\\n\\n\\nTreas. Reg. § 1.1366-2(a)(ii)(2) (emphasis added). The Commissioner also agrees\\n\\nthat this regulation applies to Merco’s losses for the 2005 and 2008 tax years\\n\\nbecause those tax years were still open for assessment in July 2014. See id. §\\n\\n1.1366-5(b) (explaining that the regulation applies “with respect to indebtedness\\n\\nbetween an S corporation and its shareholder that resulted from any transaction\\n\\nthat occurred in a year” that was still open for assessment on July 23, 2014).\\n\\n An S corporation’s debt does not run directly to the shareholder if it instead\\n\\nflows through “an entity with passthrough characteristics which advanced the\\n\\nfunds and is closely related to the taxpayer.” Hitchins v. Comm’r, 103 T.C. 711,\\n\\n715 (1994). But the 2014 regulation provides that if a shareholder engages in\\n\\ngenuine “back-to-back” loans—in which an affiliated entity loans the shareholder\\n\\nfunds that he then loans directly to the S corporation—those loans can establish\\n\\nbona fide indebtedness running directly to the shareholder. See Treas. Reg.\\n\\n§ 1.1366-2(a)(2)(iii) (“Example 2. Back-to-back loan transaction. A is the sole\\n\\nshareholder of two S corporations, S1 and S2. S1 loaned $200,000 to A. A then\\n\\nloaned $200,000 to S2 . . . If A’s loan to S2 constitutes bona fide indebtedness\\n\\nfrom S2 to A, A’s back-to-back loan increases A’s basis of indebtedness in\\n\\nS2 . . . .”). So to claim a deduction under section 1366(a), Meruelo had to establish\\n\\nthat a bona fide indebtedness of Merco ran directly to him.\\n\\n\\n\\n\\n 12\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 13 of 18\\n\\n\\n Meruelo presents two alternative arguments that the Tax Court erred in\\n\\ndisallowing his deduction. First, he contends that Merco’s debt ran directly to him\\n\\nunder a back-to-back-loan theory. Second, he contends that the debt ran directly to\\n\\nhim under an incorporated-pocketbook theory. Both arguments fail.\\n\\n A. Meruelo’s Back-to-Back-Loan Theory Fails Because Merco’s Debt Ran to\\n the Merco Affiliates, Not to Meruelo.\\n\\n Meruelo argues that he can claim a debt basis based on his back-to-back-\\n\\nloan theory for two reasons. First, he argues that we should treat the monetary\\n\\ntransfers between the Merco affiliates as back-to-back loans based on the economic\\n\\nsubstance of the transactions rather than the form they took. Second, he\\n\\nalternatively contends that the form of the transactions was sufficient to establish\\n\\nthat they amounted to back-to-back loans.\\n\\n Meruelo’s argument for substance over form is a nonstarter. Taxpayers are\\n\\nordinarily “liable for the tax consequences of the transaction they actually execute\\n\\nand may not reap the benefit of some other transaction that they might have made.”\\n\\nSelfe v. United States, 778 F.2d 769, 773 (11th Cir. 1985). “In other words,\\n\\ntaxpayers ordinarily are bound by the ‘form’ of their transaction and may not argue\\n\\nthat the ‘substance’ of their transaction triggers different tax consequences.” Id.\\n\\nThe Supreme Court has explained that although “a taxpayer is free to organize his\\n\\naffairs as he chooses, nevertheless, once having done so, he must accept the tax\\n\\nconsequences of his choice, whether contemplated or not, and may not enjoy the\\n\\n\\n 13\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 14 of 18\\n\\n\\nbenefit of some other route he might have chosen to follow but did not.” Comm’r\\n\\nv. Nat’l Alfalfa Deyhdrating & Milling Co., 417 U.S. 134, 149 (1974) (citations\\n\\nomitted).\\n\\n The parties cite, and we are aware of, only a single decision in which we\\n\\nhave agreed with a taxpayer that an exceptional circumstance could warrant\\n\\nlooking to the substance of a transaction instead of its form as having a different\\n\\ntax consequence. See Selfe, 778 F.2d at 774. The taxpayer-shareholder in Selfe had\\n\\ninitially obtained a loan in her individual capacity to fund her fledgling retail\\n\\nclothing business and pledged her personal assets as collateral. See id. at 770. At\\n\\nthe bank’s request, she agreed to convert her loan into one from the bank to the S\\n\\ncorporation where she guaranteed the corporation’s indebtedness to the bank and\\n\\ncontinued to pledge her assets as collateral. Id. at 770–71. We concluded that, in\\n\\nthe light of the circumstances suggesting that the bank looked to the shareholder as\\n\\nthe primary obligor on the loan instead of the thinly capitalized S corporation,\\n\\ngenuine issues of material fact existed as to whether the guaranteed loan was\\n\\neffectively a back-to-back loan through the shareholder. Id. at 774–75. We\\n\\nremanded to determine whether the shareholder’s guaranty amounted to either a\\n\\nshareholder loan or an equity investment. Id. at 775.\\n\\n Nothing akin to the exceptional circumstance in Selfe occurred here. Only an\\n\\n“unusual set[] of facts” can warrant judging a transaction based on its substance\\n\\n\\n\\n 14\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 15 of 18\\n\\n\\ninstead of its form. Sleiman v. Comm’r, 187 F.3d 1352, 1359 (11th Cir. 1999)\\n\\n(refusing to extend the approach from Selfe to treat a shareholder-guaranteed loan\\n\\nto an S corporation as if it were a back-to-back loan where the lender looked to the\\n\\nshareholder as only a secondary obligor). Meruelo’s argument about the substance\\n\\nof his transaction—that a portion of the funds the affiliates transferred to Merco\\n\\ncould be considered profits that Meruelo was otherwise entitled to receive and that\\n\\nthe funds were used to pay Merco’s business expenses—hardly presents an\\n\\n“unusual set of facts” about intercompany monetary transfers, and it does not\\n\\njustify setting aside our ordinary rule that the taxpayer is bound by the form his\\n\\ntransactions. See Shebester v. Comm’r, 53 T.C.M. (CCH) 824 (1987) (rejecting\\n\\ntaxpayer’s contention that loans from one controlled S corporation to another\\n\\ncontrolled S corporation were in substance a series of dividends to the shareholder\\n\\nfrom one corporation followed by loans from the shareholder to the other\\n\\ncorporation).\\n\\n Meruelo also argues that his accountant’s end-of-year reclassification of the\\n\\nintercompany transfers, as reflected on his tax returns and on the annual\\n\\nadjustments to the line-of-credit from the 2004 Note, were sufficient to establish\\n\\nthat the transactions amounted to shareholder, but we disagree. “After-the-fact\\n\\nreclassification cannot satisfy the requirement that the debt run directly from the S\\n\\ncorporation to the taxpayer/shareholder, and courts have previously rejected efforts\\n\\n\\n\\n 15\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 16 of 18\\n\\n\\nby taxpayers to establish debt basis in an S corporation using this method.” Broz v.\\n\\nComm’r, 727 F.3d 621, 627 (6th Cir. 2013); Ruckriegel v. Comm’r, 91 T.C.M.\\n\\n(CCH) 1035 (2006) (ruling that yearend reclassification of intercorporate loans as\\n\\nback-to-back loans through the taxpayer was insufficient to provide debt basis);\\n\\nBurnstein v. Comm’r, 47 T.C.M. (CCH) 1100 (1984) (same). Because the\\n\\ntransactions were contemporaneously classified as transactions between the\\n\\naffiliates and Merco, the designation Meruelo’s accountant gave them at the end of\\n\\nthe year does not govern. And we agree with the Tax Court that the accountant’s\\n\\nadjustments to “a notional line of credit, uniformly made after the close of each\\n\\nrelevant tax year, do not suffice to create indebtedness to [Meruelo] where none in\\n\\nfact existed.”\\n\\n B. Meruelo’s Incorporated-Pocketbook Theory Fails Because the Merco\\n Affiliates Were Not His Incorporated Pocketbook.\\n Meruelo alternatively contends that he can claim debt basis based on his\\n\\nincorporated-pocketbook theory. This theory holds that “[a] taxpayer can obtain\\n\\ndebt basis in an S corporation through payments made by a wholly owned\\n\\ncorporate entity if that entity functions as the shareholder’s ‘incorporated\\n\\npocketbook,’ meaning that the taxpayer has a ‘habitual practice of having his\\n\\nwholly owned corporation pay money to third parties on his behalf.’” Broz, 727\\n\\nF.3d at 627–28 (citation omitted). In two decisions, the Tax Court has ruled that\\n\\npayments made to an S corporation by a taxpayer’s “incorporated pocketbook”\\n\\n\\n 16\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 17 of 18\\n\\n\\ncompany were sufficient to establish the shareholder’s debt basis. See Yates v.\\n\\nComm’r, 82 T.C.M. (CCH) 805 (2001); Culnen v. Comm’r, 79 T.C.M. (CCH)\\n\\n1933 (2000), rev’d on other grounds, 28 F. App’x 116 (3d Cir. 2002).\\n\\n Even if we assume that the incorporated-pocketbook theory comports with\\n\\nthe requirement that a debt run “directly to the shareholder,” Meruelo failed to\\n\\nestablish that the Merco affiliates constituted his incorporated pocketbook. Unlike\\n\\nthe shareholders in Yates and Culnen—who used a single, wholly owned entity to\\n\\npay third parties on the shareholder’s behalf—Meruelo seeks to treat eleven\\n\\ndistinct Merco affiliates, many of which he only partially owned, as his\\n\\nincorporated pocketbook. Many of the Merco affiliates acted more like ordinary\\n\\nbusiness entities than as incorporated-pocketbook companies because they both\\n\\ndisbursed and received funds for business expenses from Merco. As the Tax Court\\n\\nexplained, no court has ever ruled that a group of non-wholly owned entities that\\n\\nboth receive and disburse funds in this fashion can constitute an incorporated\\n\\npocketbook. And Meruelo failed to establish that he habitually paid third parties on\\n\\nhis behalf through the putative incorporated-pocketbook companies. Meruelo’s\\n\\nevidence established only that the Merco affiliates regularly paid the expenses of\\n\\nother companies within the affiliate group—not his personal expenses. See Broz,\\n\\n727 F.3d at 628 (affirming Tax Court’s rejection of taxpayers’ “incorporated\\n\\npocketbook” argument where the taxpayers failed to establish that they habitually\\n\\n\\n\\n 17\\n\\f Case: 18-11909 Date Filed: 05/06/2019 Page: 18 of 18\\n\\n\\npaid third parties through the entities); Messina v. Comm’r, 114 T.C. Memo. 2017-\\n\\n213, at *32–33 (2017) (rejecting theory on the same ground); Ruckriegel, 91\\n\\nT.C.M. (CCH) 1035 (same).\\n\\n IV. CONCLUSION\\n\\n We AFFIRM the judgment of the Tax Court in favor of the Commissioner.\\n\\n\\n\\n\\n 18\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2275,"cells":{"id":{"kind":"number","value":4617606,"string":"4,617,606"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellee, v. David ROTHENBERG, Defendant-Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. David Rothenberg"},"decision_date":{"kind":"string","value":"2019-05-08"},"docket_number":{"kind":"string","value":"17-12349"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Carnes, Rosenbaum, Hull\", \"parties\": \"\", \"opinions\": [{\"author\": \"HULL, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-12349 Date Filed: 05/08/2019 Page: 1 of 67\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-12349\\n ________________________\\n\\n D.C. Docket No. 0:16-cr-60054-WJZ-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\n versus\\n\\nDAVID ROTHENBERG,\\n\\n Defendant-Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 8, 2019)\\n\\nBefore ED CARNES, Chief Judge, and ROSENBAUM and HULL, Circuit Judges.\\n\\nHULL, Circuit Judge:\\n\\n After his guilty plea to possession of child pornography, David Rothenberg\\n\\nappeals from the district court’s restitution order requiring him to pay a total of\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 2 of 67\\n\\n\\n$142,600 in restitution to nine victims depicted in the images of child pornography\\n\\nthat he possessed. Section 2259 mandates that district courts order defendants “to\\n\\npay the victim . . . the full amount of the victim’s losses” as determined by the\\n\\ncourt. 18 U.S.C. § 2259. This case involves the question of how to calculate the\\n\\namount of restitution a possessor of child pornography, like the defendant\\n\\nRothenberg, must pay to a victim whose childhood sexual abuse appears in the\\n\\npornographic images he possessed but did not create or distribute.\\n\\n On appeal, Rothenberg argues that: (1) the district court’s restitution order is\\n\\nflawed as to all of the victims because it failed to calculate and then disaggregate\\n\\nthe victim’s losses caused by the initial abuser, distributors, and other possessors\\n\\nfrom those caused by Rothenberg himself; and (2) as to eight of the victims, the\\n\\nrestitution award is not supported by competent evidence. After review, and with\\n\\nthe benefit of oral argument, we conclude that the district court was not required to\\n\\ncalculate and disaggregate the victim’s losses in the manner Rothenberg suggests\\n\\nand that reliable evidence supports the restitution awards as to eight victims, but\\n\\nnot as to one victim. We thus affirm the restitution amounts as to eight victims and\\n\\nvacate and remand as to one victim.\\n\\n I. INDICTMENT AND GUILTY PLEA\\n\\n Defendant Rothenberg used to be a lawyer, a fact he told an undercover\\n\\nofficer in an internet chatroom called “daddaughtersex.” Rothenberg also sent the\\n\\n\\n 2\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 3 of 67\\n\\n\\nofficer videos of child pornography and bragged that he was sexually exploiting a\\n\\nyoung girl at his house. In 2016, local and federal law enforcement went to\\n\\nRothenberg’s house and rescued the young girl, who confirmed that Rothenberg\\n\\nhad engaged in sexual activity with her. The officers also found and seized\\n\\nRothenberg’s laptop, which contained approximately 1,000 unique video and\\n\\npicture files of child pornography. Some of those images depicted prepubescent\\n\\nchildren under the age of 12, and some portrayed sadistic and masochistic conduct,\\n\\nsuch as the binding and gagging of minor children.\\n\\n In 2016, a grand jury charged Rothenberg with: (1) four counts of\\n\\ndistribution of child pornography, in violation of 18 U.S.C. § 2252(a)(2) & (b)(1)\\n\\n(Counts 1, 3, 4, and 5); (2) one count of receipt of child pornography, in violation\\n\\nof 18 U.S.C. § 2252(a)(2) & (b)(1) (Count 2); and (3) one count of possession of\\n\\nchild pornography depicting a minor under the age of 12, in violation of 18 U.S.C.\\n\\n§ 2252(a)(4)(B) & (b)(2) (Count 6). Pursuant to a written plea agreement,\\n\\nRothenberg pled guilty to the possession offense in Count 6, and the government\\n\\nagreed to dismiss the receipt and distribution charges in Counts 1 through 5. The\\n\\ndistrict court sentenced Rothenberg to 210 months’ imprisonment.\\n\\n On appeal, Rothenberg does not challenge his guilty plea or sentence.\\n\\nRather, Rothenberg challenges only the district court’s restitution order granting a\\n\\ntotal of $142,600 to nine victims, which consists of: (1) $10,000 to Sierra;\\n\\n\\n 3\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 4 of 67\\n\\n\\n(2) $3,000 to Jane; (3) $5,000 to Pia; (4) $5,000 to Mya; (5) $20,000 to Sarah;\\n\\n(6) $9,000 to Vicky; (7) $23,000 to Amy; (8) $42,600 to Jenny; and (9) $25,000 to\\n\\nCasseaopeia. We outline the thorough process the district court followed, the\\n\\nevidence submitted, and then the district court’s findings and conclusions.\\n\\n II. RESTITUTION PROCEEDINGS\\n\\n After sentencing, the district court considered restitution requests pursuant to\\n\\n18 U.S.C. § 2259(a), which provides for mandatory restitution to child\\n\\npornography victims. Generally, the process worked as follows. First, the\\n\\ngovernment identified the individual victims depicted in the images of child\\n\\npornography found on Rothenberg’s computer and notified them or their attorneys\\n\\nof the upcoming restitution hearing. Then a victim’s attorney submitted a\\n\\nrestitution request and supporting documentation to the government. Next, the\\n\\ngovernment determined whether to support that request or ask the district court for\\n\\na different amount. Rothenberg could agree to the request, try to negotiate down\\n\\nwith the government or the victim’s attorney, or challenge the request before the\\n\\ndistrict court.\\n\\n Eventually the government submitted restitution requests on behalf of ten\\n\\nvictims, all of whom were identified in at least one of the images of child\\n\\npornography from Rothenberg’s computer. One of the victims, “Angela,” later\\n\\nwithdrew her request, leaving nine requests at issue for the hearing.\\n\\n\\n 4\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 5 of 67\\n\\n\\nA. Pre-Hearing Memoranda\\n\\n Prior to the restitution hearing, both parties submitted lengthy memoranda\\n\\naddressing (1) how the restitution determination should be made, and (2) what the\\n\\naward should be for each victim. The government and Rothenberg agreed that the\\n\\nSupreme Court’s decision in Paroline v. United States, 572 U.S. 434, 134 S. Ct.\\n\\n1710 (2014), governed how the restitution awards should be made, established a\\n\\nproximate cause requirement, and set forth a variety of factors for district courts to\\n\\nconsider in determining the proper amount of restitution. Under Paroline’s\\n\\nproximate causation requirement, a defendant should pay restitution “in an amount\\n\\nthat comports with the defendant’s relative role in the causal process that underlies\\n\\nthe victim’s general losses.” Paroline, 572 U.S. at 458, 134 S. Ct. at 1727.\\n\\n But the parties disagreed about how exactly to apply the Paroline factors and\\n\\nhow to calculate and determine that amount. The government recognized that,\\n\\nunder Paroline, the district court must impose restitution in an amount that reflects\\n\\nthe particular defendant’s relative role in the continuing traffic in the child\\n\\npornography images of the victim. The government proposed that the district court\\n\\nmake that calculation by using a variation of what is known as the “1/n method,”\\n\\nwhereby the court would divide the total amount of each victim’s losses by the\\n\\nnumber of defendants, across multiple prosecutions, who had been ordered to pay\\n\\nrestitution to the victim. The government submitted that this method would\\n\\n\\n 5\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 6 of 67\\n\\n\\nprovide the district court a starting point from which to exercise its discretion in\\n\\ndetermining the appropriate amount of restitution vis-à-vis Rothenberg, as only a\\n\\npossessor of images of child pornography.\\n\\n Rothenberg argued, by contrast, that the starting point should be\\n\\n“apportionment between the original abuser of the child, versus the distributor, and\\n\\nlater, possessor of the pornography,” which Rothenberg referred to as\\n\\n“disaggregation.” Rothenberg asserted that this disaggregation requires two steps:\\n\\nfirst, the district court must separate the harm caused by the original abuser from\\n\\nthat caused by later distributors and possessors; and second, the district court must\\n\\nseparate the harm caused by the defendant from that caused by other distributors or\\n\\npossessors.\\n\\n Below, we detail for each victim (1) the victim’s restitution request and\\n\\nsupporting evidence, (2) the government’s position, and then (3) Rothenberg’s\\n\\nposition.\\n\\nB. Sierra\\n\\n Sierra submitted a restitution request for $10,000. In support of her request,\\n\\nSierra submitted a medical letter from Dr. Sharon W. Cooper, a forensic\\n\\npediatrician, based on her December 2015 evaluation of Sierra. Dr. Cooper\\n\\nexplained that victims of child pornography can experience physical, emotional,\\n\\nand spiritual issues as a result of their online exploitation, including immunological\\n\\n\\n 6\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 7 of 67\\n\\n\\nproblems, posttraumatic stress disorder (“PTSD”), anxiety, depression, suicidal\\n\\nideation, and feelings of hopelessness. Dr. Cooper noted that “[w]hen images are\\n\\nknown to be in distribution, the pre-existing dysfunction caused by the initial abuse\\n\\nis typically worsened, since children remain at risk for further victimization by the\\n\\nongoing downloading, trading and possession of their images.”\\n\\n With respect to Sierra specifically, Dr. Cooper stated that Sierra’s medical\\n\\nevaluation showed she suffered from worsening insomnia, attention deficit\\n\\nhyperactivity disorder (“ADHD”), depression, suicidal ideation, PTSD, and mood\\n\\nlability. Dr. Cooper noted that, despite being on five different medications,\\n\\nSierra’s condition remained unstable and she recently required emergency\\n\\ntreatment for suicidality. Dr. Cooper opined that “[t]he ongoing presence of\\n\\ntrafficking in images [of Sierra] on the Internet constitutes a significant aspect of\\n\\npsychological maltreatment that will add on to the initial adversities” caused by the\\n\\noriginal abuse. Based on Sierra’s past medical history, the documented adversities\\n\\nfaced by victims of child sexual abuse and child pornography offenses, and\\n\\nSierra’s present medical symptoms, Dr. Cooper estimated a total cost of\\n\\n$661,453.00 for Sierra’s future medical care.\\n\\n Sierra’s counsel also submitted a declaration of attorney’s fees, indicating\\n\\nSierra had incurred nearly $5,000 in attorney’s fees in connection with this case.\\n\\n\\n\\n\\n 7\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 8 of 67\\n\\n\\n The government supported Sierra’s $10,000 restitution request. The\\n\\ngovernment observed that four other defendants had been ordered to pay restitution\\n\\nto victims in the same series of images as Sierra. Those awards were for $4,000,\\n\\n$1,000, $9,000, and $2,000.\\n\\n Rothenberg opposed Sierra’s restitution request. Rothenberg noted that he\\n\\npossessed only one image of Sierra1 and that the requested restitution amount was\\n\\nmore than double the average of Sierra’s prior awards ($4,000). Rothenberg\\n\\nargued that Sierra’s restitution materials made no attempt at disaggregation and\\n\\nthat the government provided no information to demonstrate the relative amount of\\n\\nSierra’s harm caused by his conduct.\\n\\nC. Jane\\n\\n Jane submitted a restitution request for $3,000. In support of her request,\\n\\nJane submitted a victim impact statement, a psychological report, and an economic\\n\\nreport. In her victim impact statement, Jane specifically described how the online\\n\\ntrade in her child pornography images had affected and would continue to affect\\n\\nher. Jane explained: “Knowing people are watching what happened gives me a\\n\\nmix of anxiety, sadness, anger and it disgusts me. . . . If it wasn’t out there, I\\n\\nwouldn’t be as fearful as I am now.” Jane elaborated that the circulation of her\\n\\n\\n 1\\n Throughout we refer to how many images of a victim Rothenberg had. Each of the\\nimages recounted in this case were child pornography, and for brevity sometimes we refer to\\nthem simply as “images.”\\n 8\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 9 of 67\\n\\n\\nimages made her feel afraid and unsafe because she worried that someone who had\\n\\nseen her images online might recognize her and try to harm her. Jane felt that her\\n\\nfuture would not be “very bright” and would be lonely because the existence of her\\n\\nimages online made her socially isolated.\\n\\n Jane’s psychological evaluation was performed by Dr. Jennifer Clark in\\n\\nDecember 2014 “to determine the psychological effects of her continuous re-\\n\\nvictimization in the form of Internet pornographic images and videos of her being\\n\\nexchanged and viewed.” Dr. Clark opined that the online trade in Jane’s images\\n\\nwas currently impacting her, causing her great fear and anxiety and leaving her\\n\\nfeeling unsafe and vulnerable. Dr. Clark observed that the trade in Jane’s images\\n\\nwould continue to impact her in the future by exacerbating her “deep sense of\\n\\nmistrust in others” from the original abuse and hindering her healing and recovery\\n\\nprocess. Dr. Clark explained: “[Jane’s] awareness of the ongoing presence and\\n\\ndistribution of [her] images will remain an ever present trigger to memories of\\n\\nwhat happened and a source of fear for her safety, and thus, ongoing psychological\\n\\ndistress. Therefore, Jane will require therapy throughout her life. . . . Given that\\n\\nmuch of Jane’s distress manifests in somatic symptoms and physiological distress,\\n\\nshe likely will also seek and need significant medical attention in the future.”\\n\\n\\n\\n\\n 9\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 10 of 67\\n\\n\\n Jane’s economic evaluation estimated that she would have future medical\\n\\nand therapy costs of $101,027, and lost wages of between approximately $1.9 and\\n\\n$3.9 million.\\n\\n The government agreed that Jane’s $3,000 restitution request was\\n\\nappropriate. The government noted that seven other defendants had been ordered\\n\\nto pay restitution to Jane. Three of those seven defendants were ordered to pay\\n\\n$1,000, two were ordered to pay $2,500, one was ordered to pay $3,000, and one\\n\\nwas ordered to pay $500.\\n\\n Rothenberg disputed Jane’s requested amount and argued that a restitution\\n\\namount of $800 would be appropriate. Rothenberg noted that he possessed four\\n\\nimages of Jane and that the average award to Jane from the prior cases was $1,642.\\n\\nRothenberg acknowledged that Jane’s restitution materials were “the best of all\\n\\nprovided to attempt disaggregation,” but argued his possession did not warrant a\\n\\n$3,000 award when compared with other defendants. Specifically, Rothenberg\\n\\nnoted that one of the prior cases with a $1,000 restitution order involved\\n\\ndistribution, and three of the other cases involved receipt of Jane’s images.\\n\\nD. Pia\\n\\n Pia submitted a restitution request for $5,000. In support of her request, Pia\\n\\nsubmitted an interim impact statement from Dr. Marsha Hedrick, who conducted a\\n\\nforensic psychological evaluation of Pia, a declaration of attorney’s fees, and a\\n\\n\\n 10\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 11 of 67\\n\\n\\nvictim impact statement from Pia’s mother. Dr. Hedrick noted that Pia\\n\\nexperienced anxiety, nightmares, suspiciousness, and sadness and was emotionally\\n\\nwithdrawn. Dr. Hedrick explained that “[s]eparating the extent to which these\\n\\ndifficulties are related to sexual abuse by her father versus her awareness that her\\n\\nsexual abuse is being viewed by others is not entirely possible,” but it was clear\\n\\ninternet exploitation adds a layer of complexity to the psychological damages\\n\\nvictims of child sexual abuse face. Indeed, Dr. Hedrick noted that Pia’s mother\\n\\nhad explained to Pia there was no way to remove from the internet the images of\\n\\nher sexual abuse, resulting in “a level of suspiciousness and concern about\\n\\nexploitation that is atypical for Pia’s peers” and likely caused Pia to experience\\n\\nfeelings of powerlessness. Dr. Hedrick estimated the cost of Pia’s therapy needs as\\n\\n$81,900, but explained that estimate reflected only the “current, most critical\\n\\nneeds” for Pia and there was no way to know what the full extent of her losses\\n\\nwould be over the course of her lifetime.\\n\\n The government concurred in Pia’s $5,000 restitution request. The\\n\\ngovernment did not have information on any other defendants that were ordered to\\n\\npay restitution to Pia, but Pia’s counsel advised one other defendant was ordered to\\n\\npay restitution.\\n\\n Rothenberg disputed Pia’s requested amount and instead proposed a\\n\\nrestitution award of $1,100. Rothenberg contended there was “no real attempt at\\n\\n\\n 11\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 12 of 67\\n\\n\\ndisaggregation” in Pia’s restitution documents, but agreed some amount of\\n\\nrestitution was appropriate based on the number of images (14) he possessed of\\n\\nPia. Rothenberg reasoned that $1,100 was appropriate because the government\\n\\nhad requested $2,000 in restitution for Jenny (discussed below), and he possessed\\n\\nhalf as many images of Pia as he had of Jenny.\\n\\nE. Mya\\n\\n Mya submitted a restitution request of $5,000. In support of her request,\\n\\nMya’s counsel submitted a restitution cover letter and declarations from both of\\n\\nher attorneys. Mya’s counsel represented that they were still awaiting the results\\n\\nof Mya’s psychological evaluation, but that other similarly situated child\\n\\npornography victims they had represented had psychological treatment costs\\n\\nexceeding $100,000. Mya’s counsel stated that Mya was aware of the existence of\\n\\nher images on the internet and “the knowledge that others have witnessed and even\\n\\nenjoyed [her] abuse is extremely upsetting to [her].” Counsel further represented\\n\\nthat Mya was distrustful of other people and was at risk of being stalked or\\n\\nvictimized by individuals who had seen her images online. Counsel also\\n\\nrepresented that they had expended $2,077.44 thus far in representing Mya and two\\n\\nother victims in the same series (one of whom was victim Pia, discussed above),\\n\\nand anticipated total legal costs of $30,000 for those three victims.\\n\\n\\n\\n\\n 12\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 13 of 67\\n\\n\\n The government did not concur in Mya’s $5,000 restitution request. The\\n\\ngovernment noted that there was no information on whether other defendants were\\n\\nordered to pay restitution to Mya and determined that “[g]iven that [Rothenberg]\\n\\npossessed a single image of Mya and the future medical costs have not yet been\\n\\nestablished,” a restitution award of $500 was appropriate. The government stated\\n\\nthat amount was neither trivial nor too severe.\\n\\n Rothenberg argued there was no sufficient basis for awarding any restitution\\n\\nto Mya given the lack of information regarding her future medical costs.\\n\\nRothenberg also noted that he made an offer to Mya’s counsel to pay the $500\\n\\namount the government sought, but that offer was rejected.\\n\\nF. Sarah\\n\\n Sarah submitted a restitution request of $25,000. In support of her request,\\n\\nSarah submitted, among other things, a cover letter, a victim impact statement, a\\n\\n2014 psychological evaluation by Dr. Randall Green, and an economic report. In\\n\\nthe cover letter, Sarah’s counsel represented that her requested restitution amount\\n\\nof $25,000 would be “less than 1%” of her total losses and that 327 other\\n\\ndefendants were ordered to pay restitution to Sarah.\\n\\n In her victim impact statement, Sarah explained that she worried that people\\n\\nwho had seen her images online would “come after” her and try to victimize her in\\n\\nthe same way her original abuser had. Sarah elaborated: “Every time someone else\\n\\n\\n 13\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 14 of 67\\n\\n\\nsees pictures or videos of me it feels like they are the ones who hurt me to begin\\n\\nwith. . . . It is like I am just here for other people’s pleasure and am not a person\\n\\nmyself with my own wants and needs.” Sarah stated that her fear prevented her\\n\\nfrom leaving the house by herself and from engaging in other normal activities like\\n\\ngoing to school, having a job, or socializing with more than a few people.\\n\\n In his psychological evaluation, Dr. Green assessed “the impact and injuries\\n\\ncaused by the discovery and daily awareness that multiple individuals are viewing\\n\\nimages of sexual crimes being perpetrated against [Sarah] as a child.” As part of\\n\\nhis assessment, Dr. Green interviewed Sarah and also performed various\\n\\npsychological tests. Based on these sources of information, Dr. Green opined that\\n\\n“the discovery of multiple downloaders and distributors of her images effectively\\n\\nexponentially multiplied in [Sarah’s] mind the number of sick and dangerous males\\n\\n‘out there’ who might . . . do her harm.” Dr. Green explained that Sarah’s\\n\\nknowledge of the dissemination of her child pornography images online caused her\\n\\ndaily psychological damage in the form of fear “that has reached a paranoid-like\\n\\nlevel of intensity.” Dr. Green determined that Sarah required “extensive and\\n\\nintensive therapy” for the trauma caused by both the original abuse and the\\n\\ncontinuing traffic in her images. Dr. Green estimated the costs of Sarah’s future\\n\\npsychiatric care were between $265,710 and $303,150.\\n\\n\\n\\n\\n 14\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 15 of 67\\n\\n\\n Sarah’s counsel reported that Sarah had incurred $31,433.77 in attorney’s\\n\\nfees. The economic assessment for Sarah estimated a minimum of approximately\\n\\n$1.9 million in lost wages over her lifetime.\\n\\n The government did not concur in Sarah’s $25,000 restitution request and\\n\\ninstead requested an award of $7,895 based on its 1/n calculation method. The\\n\\ngovernment also provided a list of 155 prior restitution awards to Sarah, which\\n\\nranged from $0 at the low end to $51,500 at the high end.\\n\\n Rothenberg opposed Sarah’s restitution request. Rothenberg cited three\\n\\nother cases involving Sarah in which the government presented the same restitution\\n\\nevidence and the courts found the government failed to establish proximate cause.\\n\\nRothenberg argued that the government provided no evidence to disaggregate the\\n\\nharm proximately caused by his possession of six images of Sarah from that caused\\n\\nby the other defendants in the list it had provided.\\n\\nG. Vicky\\n\\n Vicky submitted a restitution request of $10,000. In support of her request,\\n\\nVicky submitted several victim impact statements, several psychological reports\\n\\nfrom Dr. Green, an economic report, and a statement of attorney’s fees. In her\\n\\nvictim impact statements, Vicky described the effects of the ongoing distribution\\n\\nof the images of her sexual abuse as a child, including feelings of fear and\\n\\nparanoia, nightmares, and panic attacks. In a 2014 psychological status report,\\n\\n\\n 15\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 16 of 67\\n\\n\\nDr. Green opined that Vicky continued to require therapy as a result of the\\n\\ncontinuing traffic in her images, as well as her discovery of attempts by some\\n\\nviewers of her images to invade her privacy. Dr. Green explained that Vicky\\n\\ncontinued to experience anxiety, dissociative responses, social withdrawal, anger,\\n\\nfeelings of powerlessness, and sleep disruption. Dr. Green estimated Vicky’s total\\n\\ntherapy costs to be between $108,975 to $113,600.\\n\\n The economic report estimated Vicky’s net lost wages over the course of her\\n\\nlifetime to be $828,150. Vicky’s counsel represented that Vicky had incurred\\n\\nattorney’s fees and costs of $92,371.96.\\n\\n The government did not concur in Vicky’s $10,000 request and instead\\n\\nrequested an award of $1,283 using its 1/n method. The government provided a\\n\\nlist of 659 other restitution awards to Vicky, which ranged from approximately $24\\n\\nat the low end to $1 million at the high end.\\n\\n Rothenberg opposed Vicky’s restitution request for the same reasons he\\n\\nopposed Sarah’s request, noting that other courts had denied restitution requests\\n\\nbased on the same evidence and that the government failed to disaggregate.\\n\\nRothenberg also noted that he possessed only one image of Vicky and that the\\n\\naverage post-Paroline restitution award to Vicky was $3,632.\\n\\n\\n\\n\\n 16\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 17 of 67\\n\\n\\nH. Amy\\n\\n Amy submitted a restitution request of $25,000. In support of her request,\\n\\nAmy provided a victim impact statement, several psychological evaluations from\\n\\nDr. Joyanna Silberg, and an economic report. In her victim impact statement, Amy\\n\\nstated that she “live[s] in constant fear that someone will see [her] pictures and\\n\\nrecognize [her].” Amy expressed feelings of powerlessness related to the traffic in\\n\\nthe images of her sexual abuse as a child because “the crime has never really\\n\\nstopped and will never really stop.” Amy explained that she experienced fear,\\n\\nshame, and humiliation at the thought of her friends and other people she\\n\\nencounters discovering her images online.\\n\\n In a December 2014 report, Dr. Silberg opined that although Amy had made\\n\\nstrides as a result of an intensive treatment plan initiated in 2012, ongoing issues\\n\\nrelated to PTSD remained. Dr. Silberg explained that Amy continued to\\n\\nexperience flashbacks and nightmares, as well as “fear about the internet and\\n\\nshame associated with the ongoing viewing of her picture.” Dr. Silberg concluded\\n\\nthat Amy “continues to suffer from the ongoing effects of her victimization from\\n\\nchild abuse and from the continued use of her image by child pornography traders,\\n\\nviewers, and abusers,” and recommended continued psychological treatment and\\n\\nmonitoring. Amy’s economic report estimated her net lost wages as $2,855,173,\\n\\nand her future counseling costs as $512,681.\\n\\n\\n 17\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 18 of 67\\n\\n\\n The government did not concur in Amy’s $25,000 request and instead\\n\\nrequested a restitution amount of $15,664 using its 1/n method. The government\\n\\nprovided a list of 215 other restitution awards to Amy, ranging from $50 at the low\\n\\nend to $3.5 million at the high end.\\n\\n Rothenberg opposed Amy’s restitution request. Rothenberg noted that he\\n\\npossessed only one image of Amy and that the average post-Paroline restitution\\n\\naward to her was $3,891. Rothenberg asserted that the government’s list of prior\\n\\nrestitution orders was inaccurate as to some of the awards and argued that the\\n\\ngovernment made no attempt to disaggregate his conduct from that of other\\n\\ndefendants.\\n\\nI. Jenny\\n\\n Jenny submitted a restitution request of $42,600. In support of her request,\\n\\nJenny submitted a victim impact statement and a cover letter from her counsel. In\\n\\nher victim impact statement, Jenny stated that she worried about the images of her\\n\\nsexual abuse that were “out there” and feared being recognized in public. Jenny\\n\\nexpressed a strong desire to forget the abuse she had suffered but explained that\\n\\n“[w]ith the pictures still out there I can’t.”\\n\\n In their cover letter, Jenny’s counsel represented that this was Jenny’s\\n\\nseventh restitution request. Counsel stated that they were still in the process of\\n\\nobtaining expert reports for Jenny, but asserted that “such formal reports” were not\\n\\n\\n 18\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 19 of 67\\n\\n\\nnecessary for the district court to determine restitution. Counsel discussed a\\n\\nproposed bill which would set a $25,000 minimum restitution award for child\\n\\npornography possession offenses, and represented that Jenny had costs of $5,100\\n\\nfor legal and attorney’s fees and $12,500 for the preparation of expert reports.\\n\\nBecause these three items totaled $42,600, Jenny’s counsel contended that $42,600\\n\\namount was the appropriate restitution amount for Jenny.\\n\\n The government did not concur in Jenny’s $42,600 restitution request and\\n\\ninstead requested a restitution award of $2,000. The government emphasized that\\n\\nRothenberg possessed 34 images and one video of Jenny but noted the lack of\\n\\ndocumentation to support Jenny’s restitution request. The government pointed out\\n\\nthat one other defendant was ordered to pay restitution to Jenny in the amount of\\n\\n$7,500.\\n\\n Rothenberg likewise noted the lack of evidence supporting Jenny’s $42,600\\n\\nrestitution request. Nevertheless, based on the number of images of Jenny he\\n\\npossessed, Rothenberg agreed that the government’s requested amount of $2,000\\n\\nwas reasonable.\\n\\nJ. Casseaopeia\\n\\n Casseaopeia submitted a restitution request of $25,000. In support of her\\n\\nrequest, Casseaopeia provided a victim impact statement, a psychological report\\n\\nfrom Dr. Joyce Vesper, and an economic assessment. In her victim impact\\n\\n\\n 19\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 20 of 67\\n\\n\\nstatement, Casseaopeia described her ongoing victimization as a result of the\\n\\nonline trade in her child pornography images. Casseaopeia stated that she worried\\n\\nthe people viewing her images would seek her out and harm her. She explained\\n\\nthat she suffers from anxiety, which makes it hard for her to work or go out in\\n\\npublic, and experiences panic attacks when she thinks someone recognizes her\\n\\nfrom the internet. Casseaopeia further explained that the continuing traffic in her\\n\\nimages made recovery from her PTSD and depression more difficult and\\n\\n“prevent[ed] the wound from healing.”\\n\\n In her September 2015 psychological report, Dr. Vesper described her\\n\\nclinical interview with Casseaopeia and the psychological tests she administered.\\n\\nFrom these assessments, Dr. Vesper concluded that Casseaopeia was “tortured by\\n\\nconstant memories of childhood sexual abuse” and experienced “constant head\\n\\nchatter, graphic flashbacks, [and] panic attacks that are so overwhelming they feel\\n\\nlike heart attacks.” Dr. Vesper described Casseaopeia as living “in constant fear\\n\\nthat the people viewing the pornographic films and pictures of her” online would\\n\\ncapture her and subject her to the same abuse all over again. Dr. Vesper opined\\n\\nthat “[w]ithout the appropriate psychotherapy to address [her] dissociation,\\n\\ndepersonalization, derealization, amnesia, anxiety and depression,” Casseaopeia\\n\\nwould continue to experience flashbacks, nightmares, and depression. Dr. Vesper\\n\\nrecommended intensive psychotherapy for Casseaopeia. In a supplemental report,\\n\\n\\n 20\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 21 of 67\\n\\n\\nDr. Vesper specifically addressed the effects on Casseaopeia of the ongoing traffic\\n\\nin her images. Dr. Vesper explained that Casseaopeia experienced persistent\\n\\nanxiety that people she knows will see on the internet images of her sexual abuse\\n\\nas a child and that this anxiety affects her recovery process.\\n\\n The economic assessment estimated Casseaopeia had economic damages\\n\\ntotaling $1,078,159, including $748,438 in lost earning capacity and $329,721 in\\n\\nfuture medical expenses.\\n\\n The government requested a slightly lower restitution award of $21,563 for\\n\\nCasseaopeia, which was calculated using the 1/n method. The government noted\\n\\nthat 49 other defendants were ordered to pay restitution to Casseaopeia and\\n\\nsubmitted a list of those prior awards. Those prior awards ranged from $0 at the\\n\\nlow end to $50,000 at the high end.\\n\\n Rothenberg opposed Casseaopeia’s restitution request. Rothenberg noted\\n\\nthat he possessed only two images of Casseaopeia and that the average restitution\\n\\naward to her was $3,974. Rothenberg argued that, like many of the other requests,\\n\\nthe government did not differentiate between the harm he caused and that caused\\n\\nby other perpetrators. Rothenberg contended that Dr. Vesper’s report primarily\\n\\ndealt with effects of the original abuse rather than the traffic in Casseaopeia’s\\n\\nimages.\\n\\n\\n\\n\\n 21\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 22 of 67\\n\\n\\nK. Restitution Hearing\\n\\n On November 18, 2016, the district court held a restitution hearing. At the\\n\\nrestitution hearing, the government submitted the evidence on which its restitution\\n\\nrequests were based, all of which was admitted into evidence.2 That evidence\\n\\nconsisted of 891 pages of exhibits submitted by the victims and charts prepared by\\n\\nthe government listing each victim’s prior restitution awards in other federal cases.\\n\\nThe exhibits included the declarations, psychological evaluations, letters, and other\\n\\nevidence referenced in the government’s restitution requests. Rothenberg noted, at\\n\\nthe outset of the hearing, that he agreed with the government’s requested award of\\n\\n$2,000 to Jenny and therefore did not offer any argument as to that award. The\\n\\nremaining requests were disputed, and the parties essentially reiterated the\\n\\narguments raised in their prior memoranda as to those victims.\\n\\n III. COURT’S RESTITUTION ORDER\\n\\n Six months later, on May 9, 2017, the district court issued its restitution\\n\\norder. After outlining in detail Paroline’s framework (and expressing some\\n\\nfrustration with its inexactitude), the district court analyzed each victim’s\\n\\nrestitution request. As a preliminary matter, the district court stated that, with\\n\\n\\n\\n\\n 2\\n Though the district court admitted the restitution exhibits into evidence at the restitution\\nhearing, it did not scan and file those exhibits on the district court docket. On appeal,\\nRothenberg filed an unopposed motion to supplement the record to include those exhibits, which\\nthis Court granted.\\n 22\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 23 of 67\\n\\n\\nrespect to each victim, it had assigned restitution in a manner that comported with\\n\\nRothenberg’s relative role and only for damages he proximately caused. The\\n\\ndistrict court explicitly explained that it had not “attempted to hold [Rothenberg]\\n\\nresponsible for all losses sustained by any victim.” Furthermore, the district court\\n\\nexpressly noted there was no evidence that Rothenberg was connected to the initial\\n\\nabuse of any of the victims or that he had reproduced or distributed their images.\\n\\nInstead, Rothenberg was a possessor only. And the district court specifically stated\\n\\nthat it had “taken these factors into consideration in assigning [Rothenberg] a\\n\\nrelative role as the proximate cause of these victims’ losses.”\\n\\n Turning to the specific awards, the district court determined that Sierra’s\\n\\n$10,000 request was reasonable. The district court found that: (1) Rothenberg\\n\\npossessed one image of Sierra; (2) a small number of criminal defendants had paid\\n\\nrestitution to Sierra; (3) Sierra’s current mental health condition was severe; and\\n\\n(4) Sierra’s projected costs of care exceeded $600,000. The district court found “in\\n\\nconsideration of her large amount of total costs, the small number of contributing\\n\\noffenders, and a request for a proportion of these costs proximately caused and to\\n\\nbe paid by [Rothenberg], who neither created nor distributed her image, that\\n\\n$10,000 is a reasonable request under the Paroline analysis and factors.”\\n\\n Next, the district court determined that Jane’s $3,000 request was\\n\\nreasonable. The district court found that: (1) Rothenberg possessed four images of\\n\\n\\n 23\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 24 of 67\\n\\n\\nJane; (2) a small number of criminal defendants had paid restitution to Jane;\\n\\n(3) Jane’s victim impact statement specifically addressed how the existence of her\\n\\nimages on the internet affected her and isolated the harm caused by possessors and\\n\\ndistributors from that caused by the original abuse; and (4) Jane’s estimated\\n\\nmedical and therapy costs were $101,027. The district court found “in\\n\\nconsideration of her medical costs, the small number of contributing offenders, and\\n\\na request for a proportion of these costs to be paid by [Rothenberg], who neither\\n\\ncreated nor distributed her images, that $3,000 is a reasonable request under the\\n\\nParoline analysis and factors.”\\n\\n The district court then determined that Pia’s $5,000 request was reasonable.\\n\\nThe district court found that: (1) Rothenberg possessed 14 images of Pia; (2) there\\n\\nwas no evidence regarding the number of other criminal defendants ordered to pay\\n\\nrestitution to Pia, though Pia’s counsel indicated that one other defendant was so\\n\\nordered; and (3) Pia’s estimated therapy costs over the next 20 years totaled\\n\\n$81,900. The district court found “in consideration of her total costs, the fact that\\n\\nshe has only received restitution from one other defendant, the large number of\\n\\nimages possessed by [Rothenberg] of [Pia], and a request for a proportion of these\\n\\ncosts to be paid by [Rothenberg], who neither created nor distributed her images,\\n\\nthat $5,000 is a reasonable request under the Paroline analysis and factors.”\\n\\n\\n\\n\\n 24\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 25 of 67\\n\\n\\n The district court also determined that Mya’s $5,000 request was reasonable,\\n\\ndespite the government’s requested amount of only $500. The district court found\\n\\nthat: (1) Rothenberg possessed one image of Mya; (2) there was no indication as to\\n\\nwhether any other criminal defendants were ordered to pay restitution to Mya; and\\n\\n(3) Mya’s counsel indicated a reasonable treatment estimate for Mya would be\\n\\nmore than $100,000. The district court found “in consideration of her total costs,\\n\\nthe fact that she has not received any restitution at this time, and a request for a\\n\\nproportion of these costs to be paid by [Rothenberg], who neither created nor\\n\\ndistributed her images, that $5,000 is a reasonable request under the Paroline\\n\\nanalysis and factors.”\\n\\n As to Sarah, the district court determined that an award of $20,000—$5,000\\n\\nless than Sarah’s requested amount—was reasonable. The district court explained\\n\\nthat: (1) Rothenberg possessed six images of Sarah; (2) over 150 criminal\\n\\ndefendants were ordered to pay restitution to Sarah; (3) Sarah’s victim impact\\n\\nstatement explicitly addressed how the existence of her images on the internet\\n\\naffected her, thereby isolating the harm caused by possession of her images from\\n\\nthat caused by the original abuse; and (4) Sarah’s estimated cost of psychiatric care\\n\\nwas nearly $300,000. The district court found, “in consideration of the amount of\\n\\ncosts, the fact that many other offenders have been required to pay restitution to\\n\\n[Sarah]—which in the case of Sarah, the Court finds contributes to a finding that\\n\\n\\n 25\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 26 of 67\\n\\n\\nthe request is reasonable and acknowledged by many other courts—the large\\n\\nnumber of images possessed of [Sarah], and a request for a proportion of these\\n\\ncosts proximately caused and to be paid by [Rothenberg], who neither created nor\\n\\ndistributed her image[s], that $20,000 is an appropriate amount under the Paroline\\n\\nanalysis and factors.”\\n\\n In a similar vein, the district court determined that for Vicky, $9,000—\\n\\n$1,000 less than Vicky’s requested $10,000 amount—was a reasonable award.\\n\\nThe district court found that: (1) Rothenberg possessed one image of Vicky;\\n\\n(2) more than 600, and possibly more than 800, other criminal defendants were\\n\\nordered to pay restitution to Vicky; (3) Vicky’s victim impact statement\\n\\nspecifically addressed how the online traffic in her images affected her and\\n\\nexplained the distinct harm caused by possessors and distributors of her images;\\n\\nand (4) Vicky’s predicted therapy costs exceeded $100,000. The district court\\n\\nfound “in consideration of the amount of costs, the fact that many other offenders\\n\\nhave been required to pay restitution to [Vicky]—which in the case of Vicky, the\\n\\nCourt finds contributes to a finding that the request is reasonable and\\n\\nacknowledged by many other courts—and a request for a proportion of these costs\\n\\nproximately caused and to be paid by [Rothenberg], who neither created nor\\n\\ndistributed her image, that $9,000 is an appropriate amount under the Paroline\\n\\nanalysis and factors.”\\n\\n\\n 26\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 27 of 67\\n\\n\\n The district court likewise awarded a reduced amount to Amy. The district\\n\\ncourt noted that Amy requested $25,000 and that the government requested\\n\\n$15,664, but the district court ultimately determined that $23,000 was reasonable.\\n\\nThe district court explained that: (1) Rothenberg possessed one image of Amy;\\n\\n(2) more than 200 criminal defendants had paid restitution to Amy; (3) Amy’s\\n\\nvictim impact statement “provide[d] strong support for the different and separate\\n\\nharm that possessors proximately cause to victims such as [herself]”; and\\n\\n(4) Amy’s counseling and therapy costs could exceed $500,000. The district court\\n\\nfound “in consideration of the large amount of costs, the fact that other offenders\\n\\nhave been required to pay restitution to [Amy]—which, again, in the case of Amy,\\n\\nthe Court finds contributes to a finding that the request is reasonable and\\n\\nacknowledged by other courts—and a request for a proportion of these costs\\n\\nproximately caused and to be paid by [Rothenberg], who neither created nor\\n\\ndistributed her image, that $23,000 is an appropriate amount under the Paroline\\n\\nanalysis and factors.”\\n\\n Regarding Jenny, the district court acknowledged that both the government\\n\\nand Rothenberg agreed that $2,000 was an appropriate amount, but that Jenny\\n\\nrequested $42,600. The district court determined that Jenny’s requested amount\\n\\nwas reasonable. The district court emphasized that (1) Rothenberg possessed 34\\n\\nimages and one video of Jenny, and (2) only one other defendant had paid\\n\\n\\n 27\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 28 of 67\\n\\n\\nrestitution to Jenny. The district court conceded there was “less documentation of\\n\\nJenny’s psychological and medical expenses as compared with some other victims\\n\\nin this case,” but found that the $2,000 amount requested by the parties was\\n\\ninsufficient. Considering “the extremely large number of images [Rothenberg]\\n\\npossessed of [Jenny], her costs, the fact that only one other defendant has so far\\n\\ncontributed to these costs, and a request for a proportion of these costs to be paid\\n\\nby [Rothenberg], who neither created nor distributed her images, the Court finds\\n\\nthat $42,600 is a reasonable request under the Paroline analysis and factors.”\\n\\n Lastly, as to Casseaopeia, the district court determined that her requested\\n\\naward of $25,000 was reasonable, even though the government requested only\\n\\n$21,563. The district court found that: (1) Rothenberg possessed two images of\\n\\nCasseaopeia; (2) more than 50 criminal defendants were ordered to pay her\\n\\nrestitution; and (3) her projected costs of care exceeded $300,000. Considering\\n\\n“her costs, the number of contributing offenders, and a request for a proportion of\\n\\nthese costs proximately caused and to be paid by [Rothenberg], who neither\\n\\ncreated nor distributed her image,” the district court found that “$25,000 is a\\n\\nreasonable request under the Paroline analysis and factors.”\\n\\n In total, the district court ordered Rothenberg to pay $142,600 in restitution,\\n\\nto be apportioned to the nine victims in the amounts set out above. On appeal,\\n\\nRothenberg argues that the district court erred as to all nine restitution awards. We\\n\\n\\n 28\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 29 of 67\\n\\n\\nbegin with the restitution statute and then review the Supreme Court’s Paroline\\n\\ndecision, which both parties agree governs this appeal.\\n\\n IV. 18 U.S.C. § 2259\\n\\n Congress has mandated that district courts award restitution to victims of\\n\\ncertain federal crimes, including child pornography possession. See 18 U.S.C.\\n\\n§ 2259(a) (2012).3 The possessor of child pornography must pay restitution to the\\n\\nvictim whose childhood abuse appears in the pornographic materials he possessed.\\n\\nSee id. § 2259(b)(1), (c)(4). The statute requires that “[t]he order of restitution . . .\\n\\nshall direct the defendant to pay the victim . . . the full amount of the victim’s\\n\\nlosses as determined by the court.” Id. § 2259(b)(1). The statute defines the term\\n\\n“full amount of the victim’s losses” to include any costs incurred by the victim for:\\n\\n (A) medical services relating to physical, psychiatric, or psychological\\n care;\\n (B) physical and occupational therapy or rehabilitation;\\n (C) necessary transportation, temporary housing, and child care\\n expenses;\\n (D) lost income;\\n (E) attorneys’ fees, as well as other costs incurred; and\\n (F) any other losses suffered by the victim as a proximate result of the\\n offense.\\n\\n\\n\\n\\n 3\\n Since Rothenberg’s guilty plea and restitution hearing, Congress amended 18 U.S.C.\\n§ 2259, effective December 7, 2018. See Amy, Vicky, and Andy Child Pornography Victim\\nAssistance Act of 2018, Pub. L. No. 115-299, 132 Stat. 4383 (2018). All citations in this opinion\\nare to the previous version of 18 U.S.C. § 2259, which was in effect both when Paroline was\\ndecided and at the time of the district court’s restitution order in this case.\\n 29\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 30 of 67\\n\\n\\nId. § 2259(b)(3) (emphasis added). The statute defines a victim as “the individual\\n\\nharmed as a result of the commission of a crime under this chapter.” Id.\\n\\n§ 2255(c)(4) (emphasis added). A court may not decline to issue restitution\\n\\nbecause of the economic circumstances of the defendant or because the victim has\\n\\nreceived compensation from another source. See id. § 2259(b)(4)(B).\\n\\n “The burden of demonstrating the amount of the loss sustained by a victim\\n\\nas a result of the offense shall be on the attorney for the Government.” Id.\\n\\n§§ 3664(e), 2259(b)(2) (emphasis added). In Paroline, the Supreme Court\\n\\naddressed the meaning of “as a result of” and “proximate result” in § 2259 and\\n\\nprecisely what type of causal connection or proximate cause must exist between\\n\\nthe victim’s losses and the defendant’s offense. We review Paroline next.\\n\\n V. SUPREME COURT’S PAROLINE DECISION\\n\\n Like this case, Paroline involved a possessor of child pornography images in\\n\\nwide circulation on the internet. In Paroline, the defendant was a possessor and not\\n\\na distributor or the initial abuser. See 572 U.S. at 439, 134 S. Ct. at 1716. The\\n\\nSupreme Court grappled with the question of what causal relationship must be\\n\\nestablished between a defendant possessor’s conduct and a victim’s losses for\\n\\npurposes of determining the right to, and the amount of, restitution under § 2259.\\n\\nId. As a preliminary matter, the Supreme Court interpreted § 2259’s statutory\\n\\nlanguage to impose a general proximate-cause limitation. Id. at 448, 134 S. Ct. at\\n\\n\\n 30\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 31 of 67\\n\\n\\n1721. The Supreme Court determined that “[r]estitution is therefore proper under\\n\\n§ 2259 only to the extent the defendant’s offense proximately caused a victim’s\\n\\nlosses.” Id. at 448, 134 S. Ct. at 1722.\\n\\n The difficulty, the Supreme Court explained, comes in applying that\\n\\ncausation requirement in a particular child pornography case. Id. at 449, 134 S. Ct.\\n\\nat 1722. This is so because of the “somewhat atypical causal process underlying\\n\\nthe losses [a child pornography] victim claims.” Id. The Supreme Court reasoned\\n\\nthat it may be “simple enough” for a victim to prove the aggregate losses that stem\\n\\nfrom the ongoing traffic in her images as a whole. Id. Importantly, the Supreme\\n\\nCourt observed that it is more difficult to determine “the ‘full amount’ of those\\n\\ngeneral losses, if any, that are the proximate result of the offense conduct of a\\n\\nparticular defendant who is one of thousands who have possessed and will in the\\n\\nfuture possess the victim’s images but who has no other connection to the victim.”\\n\\nId.\\n\\n Therefore, in child pornography possession offenses, the Paroline Court\\n\\nrecognized that it would be virtually impossible to show that the defendant\\n\\npossessor was a but-for cause of any particular portion of the victim’s losses\\n\\n“where the defendant is an anonymous possessor of images in wide circulation on\\n\\nthe Internet.” Id. at 450-51, 134 S. Ct. at 1722-23. Nevertheless, the Supreme\\n\\nCourt observed that “[w]hile it is not possible to identify a discrete, readily\\n\\n\\n 31\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 32 of 67\\n\\n\\ndefinable incremental loss [a defendant possessor] caused, it is indisputable that\\n\\n[the defendant possessor] was a part of the overall phenomenon that caused [the\\n\\nvictim’s] general losses.” Id. at 456-57, 134 S. Ct. at 1726. And it would\\n\\nundermine the purposes of § 2259 to deny restitution in cases involving possessors\\n\\nof child pornography. Id. at 456-58, 134 S. Ct. at 1726-27.\\n\\n The Supreme Court also recognized that the original abuse crime is\\n\\ncompounded by the distribution and possession of images of the victim’s original\\n\\nabuser’s “horrific acts, which meant the wrongs inflicted on her were in effect\\n\\nrepeated; for she knew her humiliation and hurt were and would be renewed into\\n\\nthe future as an ever-increasing number of wrongdoers witnessed the crimes\\n\\ncommitted against her.” Id. at 441, 134 S. Ct. at 1717. It does not matter that the\\n\\nvictim does not know the name of the possessor because the losses do not flow\\n\\nfrom any specific knowledge of him; rather, the cause of the victim’s losses “is the\\n\\ntrade in her images.” Id. at 456, 134 S. Ct at 1726. The Supreme Court also\\n\\nobserved that “the victim suffers continuing and grievous harm as a result of her\\n\\nknowledge that a large, indeterminate number of individuals have viewed and will\\n\\nin the future view images of the sexual abuse she endured.” Id. at 457, 134 S. Ct.\\n\\nat 1726. “In a sense, every viewing of child pornography is a repetition of the\\n\\nvictim’s abuse.” Id. at 457, 134 S. Ct. at 1727. “The cause of the victim’s general\\n\\nlosses is the trade in her images.” Id. at 456, 134 S. Ct. at 1726.\\n\\n\\n 32\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 33 of 67\\n\\n\\n After rejecting a but-for test for proximate cause, the Paroline Court adopted\\n\\na causation-in-fact standard for cases where: (1) “a defendant possessed a victim’s\\n\\nimages”; (2) “a victim has outstanding losses caused by the continuing traffic in\\n\\nthose images”; and yet (3) “it is impossible to trace a particular amount of those\\n\\nlosses to the individual defendant by recourse to a more traditional causal inquiry.”\\n\\nId. at 458, 134 S. Ct. at 1727. In that situation, the Supreme Court concluded that a\\n\\ndefendant possessor of child pornography should be ordered to pay restitution “in\\n\\nan amount that comports with the defendant’s relative role in the causal process\\n\\nthat underlies the victim’s general losses.” Id. The Supreme Court explained that\\n\\nthe award “would not be severe” in a case where the possessor is only one of many\\n\\nthousands of offenders, but also would not be “a token or nominal amount.” Id. at\\n\\n458-59, 134 S. Ct. at 1727. Rather, the required restitution would be “reasonable\\n\\nand circumscribed” and “suited to the relative size of [the defendant’s] causal\\n\\nrole.” Id. at 459, 134 S. Ct. at 1727.\\n\\n Further, the Supreme Court instructed, there is no “practical way to isolate\\n\\nsome subset of the victim’s general losses that [the possessor] Paroline’s conduct\\n\\nalone would have been sufficient to cause.” Id. at 451, 134 S. Ct. at 1723. In\\n\\nParoline, the defendant possessor was one of thousands who possessed the victim’s\\n\\nimages. Id. at 450, 134 S. Ct. at 1723. The Supreme Court stressed that even though\\n\\nthe victim does not know the possessor, the victim’s “knowledge that her images\\n\\n\\n 33\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 34 of 67\\n\\n\\nwere circulated far and wide renewed the victim’s trauma and made it difficult for\\n\\nher to recover from her abuse.” Id. at 440, 134 S. Ct. at 1717. “While it is not\\n\\npossible to identify a discrete, readily definable incremental loss he [the possessor]\\n\\ncaused, it is indisputable that he was a part of the overall phenomenon that caused\\n\\nher general losses.” Id. at 456-57, 134 S. Ct. at 1726. In other words, the defendant\\n\\npossessor of the images caused in fact part of the general losses, even if “it is\\n\\nimpossible to trace a particular amount of those losses to the individual defendant.”\\n\\nId. at 458, 134 S. Ct. at 1727.\\n\\n The Paroline Court then turned to the question of how district courts are to\\n\\ndetermine the proper amount of restitution in these “possessor” cases. Id. As a\\n\\ngeneral matter, the Supreme Court stated that a district court “must assess as best it\\n\\ncan from available evidence the significance of the individual defendant’s conduct\\n\\nin light of the broader causal process that produced the victim’s losses.” Id. at 459,\\n\\n134 S. Ct. at 1727-28. The Supreme Court emphasized that this “cannot be a precise\\n\\nmathematical inquiry,” but rather involves the exercise of “wide discretion” and\\n\\n“sound judgment” of the sort district courts typically exercise in the context of\\n\\ncriminal sentencing and restitution more broadly. Id. at 459-62, 134 S. Ct. at 1728-\\n\\n29. The Supreme Court then expressly identified “a variety of factors district courts\\n\\nmight consider” in determining a proper restitution amount for possession. Id. at\\n\\n459-60, 134 S. Ct. at 1728 (emphasis added).\\n\\n\\n 34\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 35 of 67\\n\\n\\n As a starting point, the Supreme Court suggested that district courts\\n\\n“determine the amount of the victim’s losses caused by the continuing traffic in the\\n\\nvictim’s images.” Id. at 460, 134 S. Ct. at 1728 (emphasis added). Then, to\\n\\ndetermine the defendant possessor’s relative role in causing those general losses, the\\n\\ndistrict court could consider factors such as: (1) “the number of past criminal\\n\\ndefendants found to have contributed to the victim’s general losses”; (2) “reasonable\\n\\npredictions of the number of future offenders likely to be caught and convicted for\\n\\ncrimes contributing to the victim’s general losses”; (3) “any available and\\n\\nreasonably reliable estimate of the broader number of offenders involved (most of\\n\\nwhom will, of course, never be caught or convicted)”; (4) “whether the defendant\\n\\nreproduced or distributed images of the victim”; (5) “whether the defendant had any\\n\\nconnection to the initial production of the images”; (6) “how many images of the\\n\\nvictim the defendant possessed”; and (7) “other facts relevant to the defendant’s\\n\\nrelative causal role.” Id.\\n\\n The Supreme Court reiterated that these factors should not be used as a “rigid\\n\\nformula,” but should instead serve as “rough guideposts” in determining a restitution\\n\\namount for the possessor criminal defendant. Id. The Supreme Court noted that\\n\\n“[t]his approach is not without its difficulties,” as it “involves discretion and\\n\\nestimation,” but “courts can only do their best to apply the statute as written in a\\n\\nworkable manner.” Id. at 462, 134 S. Ct. at 1729. The Supreme Court emphasized\\n\\n\\n 35\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 36 of 67\\n\\n\\nthat district courts regularly exercise wide discretion, and there was “no reason to\\n\\nbelieve they cannot apply th[is] causal standard . . . in a reasonable manner.” Id.4\\n\\n VI. STANDARD OF REVIEW\\n\\n We review de novo the legality of a restitution order, but review for clear\\n\\nerror the factual findings underlying that order. United States v. McDaniel, 631\\n\\nF.3d 1204, 1207 (11th Cir. 2011); see also United States v. Osman, 853 F.3d 1184,\\n\\n1188 (11th Cir. 2017). We review the amount of the district court’s restitution\\n\\naward only for an abuse of discretion. See United States v. Robertson, 493 F.3d\\n\\n1322, 1330 (11th Cir. 2007); see also Paroline, 572 U.S. at 459, 134 S. Ct at 1727-\\n\\n28 (emphasizing that “determining the proper amount of restitution” involves “the\\n\\nuse of discretion and sound judgment” on the part of the district court).\\n\\n A district court abuses its discretion if it applies an incorrect legal standard,\\n\\nfollows improper procedures, or makes clearly erroneous findings of fact. United\\n\\nStates v. Jordan, 582 F.3d 1239, 1249 (11th Cir. 2009). The abuse of discretion\\n\\nstandard recognizes that the district court has a range of choices, and this Court\\n\\n\\n\\n\\n 4\\n Three of the four dissenting justices were not so sure and complained that “[w]hen it\\ncomes to [the defendant’s] crime—possession of two of [the victim’s] images—it is not possible\\nto do anything more than pick an arbitrary number” as “the amount of the loss sustained by a\\nvictim as a result of” the defendant’s crime. Paroline, 572 U.S. at 463, 134 S. Ct. at 1730\\n(Roberts, C.J., dissenting). The fourth dissenter, Justice Sotomayor, would have embraced the\\nvictim’s joint and several liability theory, holding each possessor liable for restitution in the full\\namount of the victim’s losses. Id. at 473, 134 S. Ct. at 1735 (Sotomayor, J., dissenting).\\n 36\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 37 of 67\\n\\n\\nwill not reverse the district court’s choice as long as its decision does not amount\\n\\nto a clear error of judgment. Id.\\n\\n Osman, our only published post-Paroline restitution decision to date, did not\\n\\naddress how the abuse of discretion standard applies in assessing whether the\\n\\ndistrict court adequately considered the Paroline factors and imposed a reasonable\\n\\nrestitution award. See generally Osman, 853 F.3d at 1189-92. But Paroline itself\\n\\nprovides some important clues. In Paroline, the Supreme Court emphasized that\\n\\ndetermining the proper restitution amount “involves the use of discretion and\\n\\nsound judgment” in a manner akin to that exercised “in the wider context of\\n\\ncriminal sentencing,” and that the ultimate award must be “reasonable and\\n\\ncircumscribed.” Paroline, 572 U.S. at 459, 134 S. Ct. at 1727-28; see also id. at\\n\\n462, 134 S. Ct. at 1729 (explaining that “[d]istrict courts routinely exercise wide\\n\\ndiscretion . . . in sentencing as a general matter” and should likewise apply\\n\\nParoline’s causal standard “in a reasonable manner”). And to guide the district\\n\\ncourt’s exercise of its discretion, the Paroline Court identified a number of factors\\n\\ndistrict courts may consider in fashioning an appropriate restitution award. Id. at\\n\\n459-60, 134 S. Ct. at 1728.\\n\\n Paroline thus established a framework not unlike the one we apply in\\n\\nassessing the reasonableness of a defendant’s sentence, in which we look to see\\n\\nwhether the district court appropriately exercised its sentencing discretion in light\\n\\n\\n 37\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 38 of 67\\n\\n\\nof the 18 U.S.C. § 3553(a) factors. See, e.g., Gall v. United States, 552 U.S. 38,\\n\\n51, 128 S. Ct. 586, 597 (2007); United States v. Irey, 612 F.3d 1160, 1188-91 (11th\\n\\nCir. 2010) (en banc). In that § 3553(a) context, we evaluate whether the district\\n\\ncourt failed to consider relevant factors, improperly weighed the relevant factors,\\n\\nor considered improper factors, and ultimately assess whether, under the totality of\\n\\nthe circumstances, the sentence is reasonable. See Irey, 612 F.3d at 1189. And we\\n\\nwill vacate a sentence imposed by the district court only if we are “left with the\\n\\ndefinite and firm conviction that the district court committed a clear error of\\n\\njudgment in weighing the § 3553(a) factors by arriving at a sentence that lies\\n\\noutside the range of reasonable sentences dictated by the facts of the case.” Id. at\\n\\n1190 (internal quotation marks omitted).\\n\\n Additionally, in sentencing cases, we do not require district courts to make\\n\\ndetailed findings or give a thorough explanation for the sentence it chose. See id.\\n\\nat 1194-95. Specifically, “[t]he district court need not state on the record that it has\\n\\nexplicitly considered each factor and need not discuss each factor,” United States\\n\\nv. Dorman, 488 F.3d 936, 938 (11th Cir. 2007), “so long as the record reflects the\\n\\ncourt’s consideration of many of those factors,” United States v. Carpenter, 803\\n\\nF.3d 1224, 1232 (11th Cir. 2015). “Rather, an acknowledgment by the district\\n\\ncourt that it has considered the defendant’s arguments and the § 3553(a) factors\\n\\nwill suffice.” Dorman, 488 F.3d at 938.\\n\\n\\n 38\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 39 of 67\\n\\n\\n A similar approach makes sense here. As in the sentencing context, in\\n\\nevaluating child pornography restitution awards under Paroline, appellate courts\\n\\nmust determine whether the district court appropriately exercised its broad\\n\\ndiscretion in light of the facts of the particular case and awarded restitution in an\\n\\namount that comports with the particular defendant’s conduct. See Paroline, 572\\n\\nU.S. at 458-59, 462, 134 S. Ct. at 1727-29; Irey, 612 F.3d at 1190. And as in the\\n\\nsentencing context, a number of relevant factors guide the district court’s exercise\\n\\nof its discretion. See Paroline, 572 U.S. at 459-60, 134 S. Ct. at 1728; Gall, 552\\n\\nU.S. at 51, 128 S. Ct. at 597. Furthermore, the Supreme Court in Paroline\\n\\nindicated that the exercise of discretion at issue in child pornography restitution\\n\\ncases is similar to that exercised in criminal sentencing more generally. See\\n\\nParoline, 572 U.S. at 459, 134 S. Ct. at 1727-28.\\n\\n Accordingly, in reviewing child pornography restitution awards under\\n\\nParoline, this Court should consider whether, in light of the Paroline factors, the\\n\\ndistrict court arrived at a restitution amount that lies within the general range of\\n\\nreasonable restitution awards dictated by the facts of the case. See Irey, 612 F.3d\\n\\nat 1190. In doing so, this Court should give due deference to the district court’s\\n\\ndetermination that the Paroline factors, on the whole, justify the restitution amount\\n\\nawarded and should not vacate an award unless left with the definite and firm\\n\\nconviction that the district court committed a clear error of judgment in setting the\\n\\n\\n 39\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 40 of 67\\n\\n\\naward amount. See id.; Gall, 552 U.S. at 51, 128 S. Ct. at 597. Moreover, so long\\n\\nas the district court acknowledges that it has considered the Paroline factors and\\n\\nthe defendant’s arguments regarding restitution, we will not vacate a restitution\\n\\naward solely on the basis that the district court did not address each factor\\n\\nexplicitly. See Carpenter, 803 F.3d at 1232; Dorman, 488 F.3d at 938.\\n\\n With these principles in mind, we turn now to Rothenberg’s disaggregation\\n\\nargument, which is a legal challenge to the district court’s restitution order that we\\n\\nreview de novo. Osman, 853 F.3d at 1188.\\n\\n VII. DISAGGREGATION\\n\\n On appeal, Rothenberg first argues that, as to all nine victims, the district\\n\\ncourt failed to “disaggregate” their losses. Rothenberg contends that Paroline\\n\\nrequires district courts to engage in disaggregation at two levels: first, by\\n\\ndisaggregating the portion of the victim’s losses caused by the original abuse; and\\n\\nsecond, by disaggregating the losses caused by the defendant from those caused by\\n\\nother possessors or distributors.\\n\\n Rothenberg asserts that the district court here failed at the first level by\\n\\nrelying on total loss estimates for each victim that did not separate out and deduct\\n\\nthe losses caused by the original abuser. Because the expert reports did not\\n\\ndisaggregate the losses caused by the original abuser from those caused by the\\n\\ndistributors or possessors, Rothenberg contends that the district court was required\\n\\n\\n 40\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 41 of 67\\n\\n\\nto conduct that separating out itself. Rothenberg maintains that the district court\\n\\nalso failed to disaggregate at the second level by failing to use the amounts of the\\n\\nprior restitution orders against other defendant possessors or distributors for the\\n\\nsame victims as a guidepost for determining his relative level of culpability.\\n\\n The government responds that nothing in Paroline requires district courts to\\n\\nengage in the sort of formal disaggregation Rothenberg envisions. Rather, the\\n\\ngovernment contends that Paroline simply requires that the district court consider\\n\\nthe Paroline factors and exercise its discretion in determining the amount of a\\n\\nvictim’s losses caused by the instant defendant. The government submits that the\\n\\ndistrict court here complied with those requirements, explicitly stating it was not\\n\\nholding Rothenberg accountable for the original abuse or distribution of the\\n\\nvictims’ images and setting restitution amounts that “best approximat[ed]\\n\\nRothenberg’s relative role.”\\n\\n This Court has not yet addressed whether, in awarding restitution post-\\n\\nParoline, district courts first must formally disaggregate a victim’s losses between\\n\\nthe original abuser, distributors, and subsequent possessors. Several of our sister\\n\\ncircuits, however, have grappled with that question, and the results are mixed.\\n\\nA. Eighth and Fifth Circuits’ Decisions\\n\\n We start with the Eighth Circuit’s decision in United States v. Bordman, 895\\n\\nF.3d 1048, 1058-59 (8th Cir. 2018), cert. denied, 2019 WL 1886056 (U.S. Apr. 29,\\n\\n\\n 41\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 42 of 67\\n\\n\\n2019), a restitution case involving a defendant convicted of only possessing child\\n\\npornography. In Bordman, the Eighth Circuit expressly held that a district court is\\n\\nnot required to formally disaggregate categories of loss before ordering restitution,\\n\\nsuch as the loss caused by the initial abuser. Id. at 1058-59.\\n\\n In doing so, the Eighth Circuit affirmed the district court’s $3,000 award of\\n\\nrestitution to a victim where the district court considered multiple factors,\\n\\nincluding: (1) the 1/n method, which took into account the number of defendants\\n\\n(32) who had already paid the victim restitution plus 1 (the defendant Bordman),\\n\\nfor a total of 33; (2) the child pornography being videos with two copies of the\\n\\nsame video in different folders; and (3) the “very aggravating factor” of the nature\\n\\nof the video. Id. at 1052-53, 1059. The victim’s losses included $91,900 in\\n\\ntherapy, related expenses, and for a vocational assessment and counseling, legal\\n\\ncosts of $10,187.13, and attorney’s fees. Id. at 1052. At the sentencing hearing,\\n\\nthe government took the sum of $95,295.71 ($91,900 plus one third of the\\n\\nattorney’s fees) and divided it by 33 defendants, resulting in the sum of $2,887.75.\\n\\nId. at 1052-53. One-third of the attorney’s fees was used because this same\\n\\nattorney had represented three victims. Id. at 1052. The district court imposed a\\n\\n$3,000 restitution amount for the victim. Id. at 1054.\\n\\n On appeal, the defendant-possessor Bordman specifically claimed that “the\\n\\ndistrict court abused its discretion by failing to disaggregate the harm caused by the\\n\\n\\n 42\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 43 of 67\\n\\n\\ninitial abuse from the harm that his later possession caused.” Id. at 1058. In\\n\\nrejecting that claim, the Eighth Circuit reasoned that “one of the Paroline factors\\n\\nalready accounts for disaggregation”—namely, “whether the defendant had any\\n\\nconnection to the initial production of the images.” Id. at 1059 (quoting Paroline,\\n\\n572 U.S. at 460, 134 S. Ct. at 1728). The Eighth Circuit “decline[d] to transform”\\n\\nthis disaggregation factor “from a ‘rough guidepost’ into a ‘rigid formula.’” Id.\\n\\n(quoting Paroline, 572 U.S. at 460, 134 S. Ct. at 1728).\\n\\n The Fifth Circuit also has rejected, under plain error review, a defendant’s\\n\\nchallenge to restitution awards that relied on psychological reports that “did not\\n\\nseparate the losses caused by [the defendant possessor] from the losses caused by\\n\\nother abusers.” United States v. Halverson, 897 F.3d 645, 654-55 n.4 (5th Cir.\\n\\n2018). The Fifth Circuit reasoned that nothing in Paroline clearly required victims\\n\\nto present a new psychological report in each case that “disaggregates a\\n\\ndefendant’s conduct from all other possible sources of the victim’s losses.” Id.\\n\\nThe Fifth Circuit approved the district court’s use of a restitution method which\\n\\nawarded each victim (1) a base $5,000 amount of restitution, plus (2) an additional\\n\\nsum of $1,409 for each image of the victim that the defendant possessed because\\n\\nthe district court discussed factors that bore on the relative significance of the\\n\\ndefendant’s conduct and the district court was not required to make findings as to\\n\\nall of the Paroline factors. Id. at 653-54.\\n\\n\\n 43\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 44 of 67\\n\\n\\nB. Fourth and Seventh Circuits’ Decisions\\n\\n While not directly ruling on the initial-abuser-disaggregation issue, two\\n\\nother decisions of our sister circuits bear mentioning. That is because both\\n\\ndecisions, post-Paroline, (1) emphasized the district court’s wide discretion\\n\\ninherent in determining the amount of restitution, (2) affirmed restitution awards\\n\\nunder various methodologies against possessors of child pornography, and\\n\\n(3) refused to impose more structure beyond the Supreme Court’s multi-factored\\n\\ntest. See United States v. Dillard, 891 F.3d 151, 160-62 (4th Cir. 2018) (noting\\n\\nthat Paroline did not set any “evidentiary minimums” for establishing restitution,\\n\\nthat “[p]ost-Paroline, our sister courts of appeals have approved of various\\n\\nmethods of determining a restitution award,” and that “[d]istrict courts have great\\n\\ndiscretion in selecting an appropriate methodology”); United States v. Sainz, 827\\n\\nF.3d 602, 605-07 (7th Cir. 2016) (discussing the district court’s ability to employ\\n\\nvarying methodologies, including the 1/n method, to calculate a restitution amount\\n\\nunder Paroline and stating that “the bottom line here is that the amount of the\\n\\naward is substantively reasonable”). We discuss Dillard and Sainz in detail, as\\n\\nthey demonstrate not only how to apply the Paroline factors, but also a common-\\n\\nsense, practical approach to restitution for victims whose losses are caused by the\\n\\ncontinuing traffic in their child pornography images.\\n\\n\\n\\n\\n 44\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 45 of 67\\n\\n\\n In the Fourth Circuit’s Dillard decision, while the defendant was the initial\\n\\nabuser of one child victim, he also possessed images of other child victims with\\n\\nwhom he had no contact. Dillard, 891 F.3d at 154. The district court denied all\\n\\nrestitution to the non-contact victims because the record contained no evidence that\\n\\nthe victims were aware Dillard had their images and no evidence connecting the\\n\\nnon-contact victims’ harm to Dillard. Id. at 156. In reversing, the Fourth Circuit\\n\\nexplained Paroline disavowed any such requirements. Id. at 159-60. The Fourth\\n\\nCircuit held the “[g]overnment satisfied its burden of causation by the uncontested\\n\\nevidence that Dillard’s offense conduct included the seven non-contact victims’\\n\\nimages” and “that these victims have outstanding losses caused by the continuing\\n\\ntraffic in those images.” Id. at 160 (internal quotation marks omitted).\\n\\n As to how to calculate those non-contact victims’ losses caused by Dillard,\\n\\nthe Fourth Circuit said the district court “‘might, as a starting point, determine the\\n\\namount of the victim’s losses caused by the continuing traffic in the victim’s\\n\\nimages’” and “‘then set an award of restitution in consideration of factors that bear\\n\\non the relative causal significance of the defendant’s conduct in producing those\\n\\nlosses.’” Id. at 160 (quoting Paroline, 572 U.S. at 460, 134 S. Ct. at 1728). The\\n\\nFourth Circuit remanded for the district court to consider the Paroline factors and\\n\\naward at least some “non-nominal amount of restitution” for the losses of the non-\\n\\ncontact victims whose images Dillard possessed. Id. at 161-62. Where it was\\n\\n\\n 45\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 46 of 67\\n\\n\\n“uncontested that the individuals seeking restitution were Dillard’s victims and had\\n\\noutstanding losses associated with the continued trade in their images, they were\\n\\nentitled by statute to some non-nominal amount of restitution.” Id. at 161 (citing\\n\\nParoline, 572 U.S. at 458-60, 134 S. Ct. at 1727-28).\\n\\n Similarly, the Seventh Circuit’s decision in Sainz stresses the district court’s\\n\\n“considerable discretion in deciding the extent of a defendant’s restitution” who\\n\\npossessed child pornography. Sainz, 827 F.3d at 605. The defendant Sainz\\n\\npossessed six images of the victim that had circulated widely on the internet, but\\n\\nhad no role in creating or distributing them. Id. at 604. The victim had “incurred\\n\\nfinancial losses such as future lost earnings, attorney fees, and medical and\\n\\npsychiatric expenses” that totaled $1.1 million. Id. at 604, 605 n.1. On appeal, the\\n\\ndefendant Sainz did not challenge that he must pay some amount of restitution but\\n\\nargued that the $8,387.43 amount he was ordered to pay was “disproportionate to\\n\\nhis relative role in causing” the victim’s losses. Id. at 604-05. Sainz also claimed\\n\\n“he was not a legal cause of [the victim’s] harm because hundreds or thousands of\\n\\nothers also possessed the images, so she would have been harmed by others even if\\n\\nhe had never possessed the images of her.” Id. at 604.\\n\\n Using the 1/n method advocated for by the government, the district court\\n\\ndivided the total loss of $1.1 million by 136 because defendant Sainz was the 136th\\n\\noffender who was prosecuted and ordered to pay restitution. See id. at 605. By\\n\\n\\n 46\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 47 of 67\\n\\n\\npossessing and viewing the victim’s images, Sainz had re-victimized her and made\\n\\nher feel that the abuse was continuing. Id. at 604.\\n\\n In finding no legal error or abuse of discretion in the $8,387.43 restitution\\n\\naward, the Seventh Circuit affirmed and reasoned: (1) that the Supreme Court in\\n\\nParoline “avoided rigid or mechanical rules” and left the district courts with\\n\\n“considerable discretion”; (2) the amount of restitution for a possessor like Sainz\\n\\n“should be neither ‘severe’ nor a ‘token or nominal amount’”; (3) Paroline does not\\n\\nrequire “district courts to consider in every case every factor mentioned” and the\\n\\ndistrict court does “not err by not addressing every Paroline factor” 5; and (4) the\\n\\nParoline factors are permissive, not mandatory and provide “rough guideposts” that\\n\\n“district courts might consider in determining a proper amount of restitution.” Id.\\n\\nat 605-07 (internal quotation marks omitted). The Seventh Circuit recognized that\\n\\nthe 1/n method is not appropriate for all cases because, when n is “very small or\\n\\nvery large, a more nuanced method may be required.” Id. at 607. The Seventh\\n\\nCircuit concluded, however, that the application of the 1/n method to Sainz’s case\\n\\n“resulted in a reasonable restitution order of $8,400 for an offender who possessed\\n\\nsix images of the victim and indisputably contributed to her harm.” Id.\\n\\n\\n 5\\n The Seventh Circuit explained some of the Paroline factors refer to information that may\\nnot be “reliably known,” such as “the number of offenders likely to be convicted in the future or\\nthe broader numbers of offenders who were involved but are unlikely to be caught.” Sainz, 827\\nF.3d at 607. The Seventh Circuit stated that “the Supreme Court made clear in Paroline that the\\ndifficulty of coming up with reasonable estimates for an indeterminate number of other offenders\\nshould not be a barrier to all compensation for victims of child pornography.” Id.\\n 47\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 48 of 67\\n\\n\\n We acknowledge that the defendant Sainz did not ask the court to\\n\\ndisaggregate the losses from the initial abuser. Nonetheless, the Seventh Circuit’s\\n\\ndecision is instructive because it emphasizes that (1) the district court has\\n\\n“considerable discretion,” (2) the court’s method of restitution calculation can vary\\n\\nfrom case to case depending on the facts, and (3) “the bottom line” is that the\\n\\ndistrict court’s award of $8,387.43 was “substantively reasonable” for the\\n\\ndefendant possessor Sainz, even though there were hundreds of other possessors of\\n\\nthe same victim’s images. See id. at 604-607.\\n\\nC. Ninth and Tenth Circuits’ Decisions\\n\\n In contrast to these decisions, the Ninth and Tenth Circuits have determined\\n\\nthat district courts must engage in some level of disaggregation as to the harms\\n\\ncaused by the original abuse versus the harms caused by later distributors and\\n\\npossessors before awarding restitution against a particular possessor of child\\n\\npornography. See United States v. Galan, 804 F.3d 1287 (9th Cir. 2015); United\\n\\nStates v. Dunn, 777 F.3d 1171 (10th Cir. 2015). But even those post-Paroline\\n\\ndecisions are nuanced and do not adopt a rigid, mathematical rule in that regard.\\n\\nFurthermore, the facts of the Tenth Circuit’s Dunn case are important to\\n\\nunderstand what the Tenth Circuit did or did not conclude in that case.\\n\\n In Dunn, one victim sought restitution of $583,955, which represented her\\n\\ntotal losses minus the amount of restitution already received from other defendants.\\n\\n\\n 48\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 49 of 67\\n\\n\\nSee Dunn, 777 F.3d at 1174, 1179. Because Dunn was a distributor of the images,\\n\\nthe district court determined that “he should be held jointly and severally liable for\\n\\nthe entirety of [the victim’s] injuries.” Id. at 1179. The victim’s total losses were\\n\\n$1,330,015, and the district court held Dunn responsible for $583,955 of those total\\n\\nlosses as the amount not yet paid. See id. at 1181.\\n\\n In reversing, the Tenth Circuit emphasized that the district court held the\\n\\ndefendant Dunn liable for all of the victim’s unpaid losses, including those caused\\n\\nby the initial abuser, and erred by not assessing Dunn’s individual relative role in\\n\\nthe causal process underlying the victim’s losses. See id. at 1181. The Tenth\\n\\nCircuit concluded: “[T]o the extent that the district court relied on an expert report\\n\\nthat did not disaggregate [the harms caused by the original abuser], the district\\n\\ncourt’s adoption of $1.3 million as the total measure of damages cannot stand.” Id.\\n\\nat 1182.6 The disaggregation conclusion in Dunn must be read in the factual\\n\\ncontext of a reversal of a district court’s ruling that a defendant was jointly and\\n\\n\\n\\n\\n 6\\n Though it has not addressed whether district courts must disaggregate, the First Circuit\\nhas held that a district court order comported with Paroline’s framework where it “excluded past\\ncosts and based its award on an estimate of [the victim’s] future therapy costs, occasioned by\\ndefendant’s conduct.” United States v. Rogers, 758 F.3d 37, 39 (1st Cir. 2014). The district\\ncourt also “limited the losses to general losses from ‘continuing’ traffic” in the victim’s images\\nand “distinguished the future therapy losses attributable to defendant from the harm resulting\\nfrom other viewers and from [the victim’s] therapy needs relating to [the original abuser].” Id.\\nThe First Circuit commented that the district court’s $3,150 restitution award “represent[ed] the\\ncost of 18 therapy visits,” but the district court “noted that 50 visits would also have been a\\nreasonable conclusion.” Id. The mere fact that this type of formal disaggregation is permissible\\nunder Paroline, however, does not mean that it is required.\\n 49\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 50 of 67\\n\\n\\nseverally liable with all other defendants, including the abuser, for the entirety of\\n\\nthe victim’s $1,330,015 total losses, minus only what other defendants had already\\n\\npaid. We read Dunn as requiring disaggregation in that case because the defendant\\n\\nwas held jointly and severally liable with the abuser for the entirety of the losses;\\n\\nwe do not read Dunn as requiring disaggregation in each and every restitution case.\\n\\n Unlike Dunn’s recounting of the restitution facts, the Ninth Circuit’s\\n\\ndecision in Galan does not indicate the amounts of the victim’s losses or even the\\n\\nrestitution award at issue. Galan, 804 F.3d at 1288. Rather, Galan recounts only\\n\\nthese two facts: (1) the defendant Galan was not the victim’s original abuser, who\\n\\n“made images of his disgusting crimes against [the victim] over an extended\\n\\nperiod” of time; and (2) that abuse ended about 11 years before Galan possessed\\n\\nthe images. See id.\\n\\n In reversing, the Ninth Circuit went much further than the Tenth. The Ninth\\n\\nCircuit held “that in calculating the amount of restitution to be imposed upon a\\n\\ndefendant who was convicted of distribution or possession of child pornography,\\n\\nthe losses, including ongoing losses, caused by the original abuse of the victim\\n\\nshould be disaggregated from the losses caused by the ongoing distribution and\\n\\npossession of images of that original abuse, to the extent possible.” Id. at 1291.\\n\\nThe Ninth Circuit concluded “that Galan should not be required to pay for losses\\n\\ncaused by the original abuser’s actions.” Id. at 1290. The Ninth Circuit\\n\\n\\n 50\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 51 of 67\\n\\n\\ndetermined, in effect, that some type of calculation should be made between\\n\\noriginal abusers on the one hand and the distributors and possessors on the other.\\n\\nSee id. at 1288, 1290.\\n\\n Importantly, however, the Ninth Circuit cautioned that it “express[ed] no\\n\\nopinion about what portion of the victim’s ongoing loss should be attributable to an\\n\\noriginal abuser.” Id. at 1291. It also did not instruct how the disaggregation\\n\\ncalculation should be done, and it even added that “[i]f the ultimate apportionment\\n\\nis not scientifically precise, we can only say that precision is neither expected nor\\n\\nrequired.” Id.\\n\\nD. Our Analysis\\n\\n After careful review of Paroline, we conclude that a district court is not\\n\\nrequired to determine, calculate, or disaggregate the specific amount of loss caused\\n\\nby the original abuser-creator or distributor of child pornography before it can\\n\\ndecide the amount of the victim’s losses caused by the later defendant who\\n\\npossesses and views the images. Paroline requires no such disaggregation.\\n\\nCertainly, Paroline directed district courts to hold a defendant accountable only for\\n\\nhis own individual conduct and set a restitution “amount that comports with the\\n\\ndefendant’s relative role” in causing the victim’s general losses. See Paroline, 572\\n\\nU.S. at 454-55, 458-59, 134 S. Ct. at 1725, 1727. How a district court arrives at\\n\\nthat figure is largely up to the district court, so long as the number is a “reasonable\\n\\n\\n 51\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 52 of 67\\n\\n\\nand circumscribed award” that is “suited to the relative size” of the defendant’s\\n\\ncausal role in the entire chain of events that caused the victim’s loss. Id. at 459,\\n\\n134 S. Ct. at 1727.\\n\\n In arriving at that figure, Paroline does require some consideration by the\\n\\ndistrict court of whether the defendant possessor was also an abuser-creator or a\\n\\ndistributor. See id. Indeed, that is why Paroline includes among its list of relevant\\n\\nfactors “whether the defendant had any connection to the initial production of the\\n\\nimages,” and “whether the defendant reproduced or distributed images of the\\n\\nvictim.” Id. at 460, 134 S. Ct. at 1728. But those factors do not require that the\\n\\ndistrict court make fact findings about the amount of losses caused by different\\n\\ngroups of offenders.\\n\\n To be clear, the district court should ensure that its restitution order relates\\n\\nonly to the amount of harm and loss caused by the defendant possessor. But\\n\\nParoline also repeatedly stresses the flexibility and broad discretion district courts\\n\\nhave in arriving at such a reasonable restitution amount. See, e.g., id. at 459, 134\\n\\nS. Ct. at 1727-28 (“[A] court must assess as best it can from available evidence the\\n\\nsignificance of the individual defendant’s conduct in light of the broader causal\\n\\nprocess that produced the victim’s losses. This cannot be a precise mathematical\\n\\ninquiry and involves the use of discretion and sound judgment.”); id. at 459-60,\\n\\n134 S. Ct. at 1728 (“[I]t is neither necessary nor appropriate to prescribe a precise\\n\\n\\n 52\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 53 of 67\\n\\n\\nalgorithm for determining the proper restitution amount at this point in the law’s\\n\\ndevelopment. Doing so would unduly constrain the decisionmakers closest to the\\n\\nfacts of any given case.”); id. at 460, 134 S. Ct. at 1728 (“These factors need not be\\n\\nconverted into a rigid formula . . . . They should rather serve as rough guideposts\\n\\nfor determining an amount that fits the offense.”); id. at 462, 134 S. Ct. at 1729\\n\\n(stating, “the approach articulated above involves discretion and estimation,” and\\n\\n“courts can only do their best to apply the statute as written in a workable\\n\\nmanner”).\\n\\n Like the Eighth Circuit, we think it would be inconsistent with Paroline’s\\n\\nflexible, discretionary framework to require district courts to perform an initial,\\n\\nformal step of calculating and then separately assigning a total loss amount to the\\n\\ninitial abuser, then one to the distributors and possessors generally, and only then\\n\\none to the particular defendant possessor. Rather, even if a victim’s total loss\\n\\nestimate includes losses caused both by the original abuser-creator, the distributors,\\n\\nand other possessors, the district court need only indicate in some manner that it\\n\\nhas considered that the instant defendant is a possessor, and not the initial abuser or\\n\\na distributor, and has assigned restitution based solely on the defendant possessor’s\\n\\nparticular conduct and relative role in causing those losses. See id. at 458-62, 134\\n\\nS. Ct. at 1727-29.\\n\\n\\n\\n\\n 53\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 54 of 67\\n\\n\\n Here, the district court did exactly that. In its restitution order, the district\\n\\ncourt explicitly found up front that “there is no evidence with respect to any victim\\n\\nthat [Rothenberg] reproduced or distributed images of the victim or that he had [a]\\n\\nconnection to the initial production of the images.” The district court expressly\\n\\nstated that it had “taken these factors into consideration in assigning [Rothenberg]\\n\\na relative role as the proximate cause of these victims’ losses.” And in setting each\\n\\nindividual award, the district court reiterated that Rothenberg “neither created nor\\n\\ndistributed” the victim’s image. Under Paroline, that is enough. We therefore\\n\\nreject Rothenberg’s disaggregation argument.\\n\\n Before concluding, we recognize that the Supreme Court in Paroline did\\n\\nnote in dicta that “[c]omplications may arise in disaggregating losses sustained as a\\n\\nresult of the initial physical abuse, but those questions may be set aside for present\\n\\npurposes.” Id. at 449, 134 S. Ct. at 1722. We do not read this dicta, which is\\n\\ncontained in a parenthetical, as requiring in any way that the district courts in\\n\\npossessor cases take on the job of determining the harm and loss caused by the\\n\\ninitial abuser or the distributors. 7 Rather, the district court’s job is to determine the\\n\\n\\n\\n 7\\n We acknowledge that the Ninth Circuit concluded that the set-aside statement in this\\nparenthetical meant the Supreme Court “plainly perceived a need for separation” of losses from\\nthe initial abuser and the later possessor defendants. Galan, 804 F.3d at 1290. However, we read\\nthe dicta in this parenthetical sentence not in isolation, but in the context surrounding it, which to\\nus signals that in possessor cases a court is not required to delve into the special losses caused by\\nthe original abuser. Rather, in possessor cases, the court is examining only the general losses\\ncaused by the continuing traffic in the pornographic images and awarding restitution that\\n 54\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 55 of 67\\n\\n\\ndefendant possessor’s causal role in the general losses caused by his participation\\n\\nin the ongoing traffic in the victim’s images.\\n\\n We likewise reject Rothenberg’s argument that the district court erred in\\n\\ncreating restitution disparities between himself and other possessors by\\n\\n“impos[ing] restitution in amounts substantially above the average [for other\\n\\npossessors] without providing any explanation at all.” We recognize that the\\n\\nSupreme Court in Paroline listed as a factor “the number of past criminal\\n\\ndefendants found to have contributed to the victim’s general losses” and noted that\\n\\nthe government “could also inform district courts of restitution sought and ordered\\n\\nin other cases.” See id. at 460, 462, 134 S. Ct. at 1728-29. However, the Supreme\\n\\nCourt did not require district courts to dive into the facts of every past order and\\n\\nposition their restitution findings in relation to those of other courts. See id. The\\n\\ndistrict court is not required to say why it did not follow or disagreed with\\n\\nrestitution orders as to the same victim imposed by other courts. Paroline requires\\n\\nno such fact findings or analysis. Rather, the number of past criminal defendants\\n\\nand their restitution amounts, even as to the same victim, are just one of many\\n\\n\\n\\n\\ncomports with the defendant possessor’s relative role as a possessor. In our view, nothing in\\nParoline requires disaggregation, and everything in Paroline suggests otherwise.\\n 55\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 56 of 67\\n\\n\\nfactors the district court considers generally without having to make mathematical\\n\\ncalculations. 8 See id.\\n\\n VIII. SUFFICIENCY OF THE EVIDENCE\\n\\nA. McGarity\\n\\n Rothenberg’s next argument concerns victims Sierra, Jane, Sarah, Vicky,\\n\\nAmy, and Casseaopeia. 9 As to these six victims, Rothenberg argues that the\\n\\ndistrict court erred in relying on loss estimates that were based on psychological\\n\\nevaluations conducted before his arrest and thus before these victims learned of his\\n\\ncriminal possession offense, citing this Court’s prior precedent in United States v.\\n\\nMcGarity, 669 F.3d 1218 (11th Cir. 2012). The government responds that the\\n\\nportion of McGarity on which Rothenberg relies was overruled by Paroline.\\n\\n In McGarity, which was decided prior to Paroline, this Court concluded that\\n\\na psychological evaluation performed before the defendant’s arrest and prosecution\\n\\ncould not show the harm to the victim. 669 F.3d at 1269. More specifically, for\\n\\nproximate cause to exist in a child pornography case, “there must be a causal\\n\\nconnection between the actions of the end-user and the harm suffered by the\\n\\n 8\\n In this case, the government’s submission and calculations used the 1/n method, but only\\nas a starting point for the district court’s exercise of discretion and then application of the\\nParoline factors. While we affirm the thorough and multifactored process used in this case, we\\ncaution that the application of a strict 1/n approach, in which the only thing the district court does\\nis divide the total loss amount by the total number of defendants who have been ordered to pay\\nrestitution, ordinarily will not meet the individualized assessment requirement of Paroline.\\n 9\\n On appeal, Rothenberg does not challenge the evidentiary basis for victim Pia’s $5,000\\nrestitution award.\\n 56\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 57 of 67\\n\\n\\nvictim.” Id. The McGarity Court determined that, in that case, the government\\n\\nfailed to provide any basis for determining “whether [the defendant’s] possession\\n\\nof child pornography proximately caused any of [the victim’s] harm,” given the\\n\\nvictim’s psychological evaluation occurred before the defendant’s arrest and\\n\\nprosecution. Id.\\n\\n As such, the McGarity Court determined that the psychological evaluation\\n\\ncould not show the harm caused to the victim by the particular defendant’s conduct\\n\\nin that case. Id. at 1269-70 (citing with approval the Second Circuit’s decision in\\n\\nUnited States v. Aumais, 656 F.3d 147, 154 (2d Cir. 2011), that remarked that the\\n\\nvictim’s psychological evaluation preceded the defendant’s arrest, and thus it could\\n\\nnot demonstrate the impact on the victim caused by that defendant). In other\\n\\nwords, the McGarity Court concluded that to establish proximate cause, the\\n\\ngovernment must show that the victim actually learned of the particular\\n\\ndefendant’s possession of her images. See id. at 1269-70.\\n\\n We agree with the government that this aspect of McGarity was abrogated\\n\\nby Paroline. See United States v. Archer, 531 F.3d 1347, 1352 (11th Cir. 2008)\\n\\n(“[A] prior panel’s holding is binding on all subsequent panels unless and until it is\\n\\noverruled or undermined to the point of abrogation by the Supreme Court or by\\n\\nthis court sitting en banc.”). In requiring to show harm that the victim was aware\\n\\nof a particular defendant’s conduct, the McGarity Court essentially required that\\n\\n\\n 57\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 58 of 67\\n\\n\\nthe government establish a direct, but-for causal link between some portion of the\\n\\nvictim’s losses and the specific defendant’s offense. See McGarity, 669 F.3d at\\n\\n1269-70. As discussed above, however, Paroline rejected exactly that sort of direct\\n\\nor but-for causation requirement in setting out its new standard. See Paroline, 572\\n\\nU.S. at 450-59, 134 S. Ct. at 1722-28. In Paroline, the Supreme Court recognized\\n\\nthat “it is not possible to prove that [a victim’s] losses would be less (and by how\\n\\nmuch) but for one possessor’s individual role in the large, loosely connected\\n\\nnetwork through which her images circulate,” nor is there “a practical way to\\n\\nisolate some subset of the victim’s general losses that [the defendant’s] conduct\\n\\nalone would have been sufficient to cause.” Id. at 450-51, 134 S. Ct. at 1723.\\n\\nNevertheless, the Supreme Court explained that “it is indisputable that [the\\n\\ndefendant] was a part of the overall phenomenon that caused [the victim’s] general\\n\\nlosses.” Id. at 457, 134 S. Ct. at 1726.\\n\\n In Paroline, the Supreme Court thus held that, “[i]n this special context”\\n\\nwhere it is clear both that the defendant possessed images of the victim and that the\\n\\nvictim has outstanding losses as a result of the traffic in her images, “but where it\\n\\nis impossible to trace a particular amount of those losses to the individual\\n\\ndefendant,” courts should order restitution “in an amount that comports with the\\n\\ndefendant’s relative role in the causal process that underlies the victim’s general\\n\\nlosses.” Id. at 458, 134 S. Ct. at 1727. The Supreme Court held that the\\n\\n\\n 58\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 59 of 67\\n\\n\\ngovernment need not establish that some specific portion of the victim’s losses\\n\\nwere directly caused by the defendant possessor’s conduct, as McGarity had\\n\\nrequired. See id.; McGarity, 669 F.3d at 1269. Rather, the government need\\n\\nestablish only that the victim suffered losses from the traffic in her images and that\\n\\nthe defendant contributed to those losses by possessing her images, regardless of\\n\\nwhether the victim was specifically aware of the defendant’s conduct. Paroline,\\n\\n572 U.S. at 458, 134 S. Ct. at 1727; see also id. at 442, 450, 134 S. Ct at 1718,\\n\\n1723 (noting that the parties “stipulated that the victim did not know who Paroline\\n\\nwas and that none of her claimed losses flowed from any specific knowledge about\\n\\nhim or his offense conduct,” and the victim therefore could not show her losses\\n\\n“would have been any different but for Paroline’s offense”).\\n\\n We therefore conclude that the portion of McGarity’s holding requiring the\\n\\ngovernment to show that a child pornography victim was aware of, and specifically\\n\\nharmed by, a particular defendant possessor’s conduct was abrogated by Paroline.\\n\\nSee Archer, 531 F.3d at 1352. Consequently, Rothenberg’s challenge to the\\n\\nrestitution awards for six victims—Sierra, Jane, Sarah, Vicky, Amy, and\\n\\nCasseaopeia—based on that portion of McGarity fails. 10\\n\\n\\n\\n 10\\n The government asserts that Rothenberg did not specifically raise this before-my-arrest\\nargument in the district court, and it should be reviewed only for plain error. We need not decide\\nthat issue; regardless of the standard of review, this claim fails because Paroline overruled this\\npart of McGarity and Paroline was decided before Rothenberg’s offense.\\n\\n 59\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 60 of 67\\n\\n\\nB. Mya and Jenny\\n\\n Next, as to victims Mya and Jenny, Rothenberg argues the government\\n\\nfailed to submit reliable or sufficient evidence of their losses because neither of\\n\\nthose victims had psychological or economic reports detailing their losses. In\\n\\nopposition, the government asserts that it need not submit expert reports to\\n\\nestablish a victim’s losses and that the evidence presented in support of Mya’s and\\n\\nJenny’s restitution requests provided a sufficient basis for the district court’s\\n\\nawards. 11\\n\\n The government bears the burden of proving the restitution amount by a\\n\\npreponderance of the evidence. Osman, 853 F.3d at 1189. The government must\\n\\ndo so “with evidence bearing sufficient indicia of reliability to support its probable\\n\\naccuracy.” Id. (internal quotation marks omitted). Nevertheless, because “the\\n\\ndetermination of the restitution amount is by nature an inexact science,” a district\\n\\ncourt “may accept a reasonable estimate of the loss based on the evidence\\n\\npresented.” Id. (internal quotation marks omitted).\\n\\n\\n\\n\\n 11\\n We disagree with the government’s contention that Rothenberg did not preserve his\\nchallenge to Mya’s and Jenny’s restitution awards on the ground that they were not supported by\\ncompetent evidence. Accordingly, we review the factual findings underlying the district court’s\\nrestitution orders as to Mya and Jenny for clear error, Osman, 853 F.3d at 1188, and the amount\\nof their restitution awards for an abuse of discretion, see Robertson, 493 F.3d at 1330; see also\\nParoline, 572 U.S. at 462, 134 S. Ct at 1729 (recognizing that “[d]istrict courts routinely exercise\\nwide discretion . . . in fashioning restitution orders”).\\n 60\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 61 of 67\\n\\n\\n 1. Mya\\n\\n Regarding Mya, the district court did not clearly err in determining that\\n\\nsufficient evidence supported Mya’s restitution request. One of Mya’s counsel,\\n\\nCarol Hepburn, submitted a signed declaration stating Mya needed therapy and/or\\n\\nmedical care. Rothenberg faults the district court for accepting the “self-serving”\\n\\nestimate provided by Mya’s counsel that Mya’s future medical costs would likely\\n\\nexceed $100,000. In her declaration, Hepburn explained that the $100,000\\n\\nestimate was not just pulled out of thin air. Rather, it was based on Hepburn’s\\n\\nexperience representing eight other, similarly situated child pornography victims.\\n\\nIndeed, the restitution exhibits presented to the district court show that Hepburn\\n\\nrepresented or co-represented several of the other victims in this case—Sierra, Pia,\\n\\nSarah, and Vicky. Considering Hepburn’s demonstrated experience in this area, it\\n\\nwas not unreasonable for the district court to consider her estimate as reliable\\n\\nevidence of Mya’s likely future costs. See id.\\n\\n Furthermore, counsel Hepburn explained that Mya was part of the same\\n\\nchild pornography series as Pia. Though a psychological evaluation was\\n\\nunavailable for Mya at the time of the restitution hearing, 12 her co-victim Pia was\\n\\n\\n\\n 12\\n In challenging Mya’s and Jenny’s awards, Rothenberg also argues that a victim must\\nalways supply an expert medical or psychological report to support her restitution request.\\nRothenberg cites no caselaw for this proposition, and nothing in either Paroline or our own\\nprecedent establishes such a rigid requirement. See Osman, 853 F.3d at 1189 (requiring only\\nthat the government present evidence “bearing sufficient indicia of reliability”). Though such\\n 61\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 62 of 67\\n\\n\\nable to submit a preliminary evaluation. That evaluation indicated that, at a bare\\n\\nminimum, Pia had estimated therapy costs of $81,900 and emphasized that this\\n\\nestimate reflected “only the current, most critical needs” for Pia, who like Mya was\\n\\nstill a minor, and did not account for the full extent of her losses or the services she\\n\\nwould require over the course of her lifetime. And notably, Rothenberg does not\\n\\nchallenge the evidentiary basis for Pia’s restitution award in this case. That Mya’s\\n\\nco-victim Pia had preliminary estimated costs of at least $81,900 is a further\\n\\nindicator that counsel Hepburn’s $100,000 total cost estimate for Mya was\\n\\nreasonable and appropriately relied upon by the district court. See id. On this\\n\\nrecord, we are not left with a definite and firm conviction that the district court was\\n\\nmistaken in concluding that sufficient evidence supported Mya’s restitution\\n\\nrequest. See Robertson, 493 F.3d at 1330.\\n\\n Nor did the district court abuse its broad discretion in awarding Mya her\\n\\nrequested restitution amount of $5,000. See id. Here, the district court properly\\n\\nidentified Paroline as the correct legal standard for awarding restitution in child\\n\\npornography cases. In setting the amount of Mya’s restitution award, the district\\n\\ncourt addressed several relevant Paroline factors, noting that: (1) Rothenberg\\n\\npossessed one image of Mya; (2) no other defendant was yet ordered to pay\\n\\n\\n\\n\\nexpert reports are undoubtedly helpful to district court’s in fashioning a restitution award, they\\nare by no means the only way to establish a reasonable estimate of a victim’s losses.\\n 62\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 63 of 67\\n\\n\\nrestitution to Mya; (3) Mya had estimated losses exceeding $100,000; and\\n\\n(4) Rothenberg neither created nor distributed Mya’s images. Paroline, 572 U.S. at\\n\\n460, 134 S. Ct. at 1728. In light of these factors, the district court determined that\\n\\nMya’s $5,000 restitution request was reasonable. Given the wide discretion\\n\\nafforded by Paroline to district courts in this context, we cannot say this\\n\\ndetermination was unreasonable. See id. at 462, 134 S. Ct. at 1729; Jordan, 582\\n\\nF.3d at 1249.\\n\\n 2. Jenny\\n\\n Based on the more limited record as to Jenny, we agree with Rothenberg that\\n\\nthe district court clearly erred in determining there was sufficient evidence to\\n\\nsupport Jenny’s $42,600 request. In support of her restitution request, Jenny’s\\n\\ncounsel submitted a restitution cover letter and a victim impact statement from\\n\\nJenny. In the letter, Jenny’s counsel requested restitution in the following\\n\\namounts: (1) $12,500 to pay for psychological and economic reports; (2) $5,000 in\\n\\nattorney’s fees related to her request in this case; (3) $100 in legal fees related to\\n\\nher request in this case; and (4) $25,000 for “the defendant’s appropriate share of\\n\\nthe general losses caused to Jenny.”\\n\\n Like Mya, at the time of the restitution hearing, Jenny was still in the\\n\\nprocess of obtaining expert reports documenting her total losses. Unlike Mya,\\n\\nhowever, Jenny’s separate counsel did not provide any reasonable estimate of what\\n\\n\\n 63\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 64 of 67\\n\\n\\nthose total losses might be. Indeed, counsel did not provide any estimate of what\\n\\nJenny’s total losses might be. Rather, in asserting that $25,000 was Rothenberg’s\\n\\n“appropriate share” of Jenny’s losses, counsel relied on (1) a proposed statute that\\n\\nwould set a minimum restitution award of $25,000 for possession of child\\n\\npornography, and (2) Masha’s law, 18 U.S.C. § 2255(a), which creates a civil\\n\\ncause of action for victims who suffered personal injury as a result of a child\\n\\npornography offense and sets a liquidated damages amount of $150,000.\\n\\n This evidence is sufficient to show that Jenny has incurred costs of\\n\\n$17,600—to pay for expert reports and legal fees—in connection with her\\n\\nrestitution request in this case, 13 yet it is not sufficient to establish what proportion\\n\\nof Jenny’s as-yet-undetermined total losses Rothenberg proximately caused.\\n\\nJenny’s counsel suggested that the $150,000 liquidated damages amount in\\n\\nMasha’s Law represents a reasonable estimate by Congress of the minimum\\n\\namount of total damages suffered by a child pornography victim. But the damages\\n\\navailable to a plaintiff in a civil lawsuit may be quite different from the concrete\\n\\n“costs incurred” for which § 2259 provides recompense. See 18 U.S.C.\\n\\n§ 2259(c)(2). For example, a plaintiff in a civil damages suit under § 2255(a) may\\n\\nbe able to recover for noneconomic losses, such as pain and suffering or mental\\n\\n\\n 13\\n We note that the $12,500 portion of those costs for psychological and economic reports\\nwould not necessarily be fully attributable to Rothenberg, as Jenny will, unfortunately but\\nundoubtedly, need to use those reports in support of future requests against other defendants.\\n 64\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 65 of 67\\n\\n\\nand emotional distress, that are not available in a restitution proceeding under\\n\\n§ 2259. See Doe v. Hesketh, 828 F.3d 159, 170 (3d Cir. 2016). As such, we do\\n\\nnot see that Masha’s Law provides much guidance in the present context.\\n\\n Similarly, Jenny’s counsel’s reliance on proposed legislation setting a\\n\\nminimum $25,000 restitution award for child pornography possession offenses also\\n\\nprovides little to no guidance here. While Congress certainly would be well within\\n\\nits rights to establish such a mandatory minimum restitution amount in these cases,\\n\\nit had not done so at the time of Rothenberg’s restitution hearing. 14 Thus, the\\n\\ndistrict court was required to instead follow Paroline’s framework, which requires\\n\\nan individualized assessment of each particular defendant’s restitutionary liability\\n\\nbased on his conduct and relative role in the causal process. Paroline, 572 U.S. at\\n\\n445, 458-59, 462, 134 S. Ct. at 1720, 1727-29. Imposing a pre-set minimum\\n\\namount of restitution based solely on the type of offense Rothenberg committed\\n\\ndoes not comply with Paroline’s framework, and the government did not submit\\n\\nevidence from which the district court reasonably could have determined that\\n\\n$25,000 was Rothenberg’s relative share of Jenny’s losses.\\n\\n\\n\\n\\n 14\\n Congress recently passed, and the president signed, a different version of the bill\\nJenny’s counsel referred to, but that version sets the minimum restitution amount much lower, at\\n$3,000. See Amy, Vicky, and Andy Child Pornography Victim Assistance Act of 2018, Pub. L.\\nNo. 115-299, 132 Stat. 4383 (2018).\\n\\n 65\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 66 of 67\\n\\n\\n It is indisputable that Jenny has suffered some, likely large amount of losses\\n\\nfrom the online traffic in her images. See id. at 457, 134 S. Ct. at 1726. It is also\\n\\nindisputable that Rothenberg, who possessed 34 images and 1 video of Jenny, is\\n\\nresponsible for some, possibly significant amount of those losses. Id. But the\\n\\ngovernment bears the burden of proving at least a reasonable estimate of that\\n\\namount based on reliable evidence, and it has not satisfied that burden here.\\n\\nOsman, 853 F.3d at 1189. In the absence of competent evidence to support the\\n\\naward, the district court clearly erred in ordering Rothenberg to pay $42,600 in\\n\\nrestitution to Jenny. See id.\\n\\n We therefore vacate the district court’s restitution award as to Jenny and\\n\\nremand for further proceedings consistent with this opinion. On remand, the\\n\\ndistrict court should allow Jenny to supplement her restitution request with\\n\\nevidence of her losses. See 18 U.S.C. § 3664(d)(5) (allowing a victim to seek an\\n\\namended restitution order if the victim discovers additional losses after\\n\\nsentencing). The district court should then determine, in light of all the available\\n\\nevidence and the Paroline factors, the portion of Jenny’s losses for which\\n\\nRothenberg is responsible. Paroline, 572 U.S. at 458-60, 134 S. Ct. at 1727-28.\\n\\n\\n\\n\\n 66\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 67 of 67\\n\\n\\n IX. CONCLUSION\\n\\n For the foregoing reasons, we affirm the district court’s restitution order as\\n\\nto victims Sierra, Jane, Pia, Mya, Sarah, Vicky, Amy, and Casseaopeia, and vacate\\n\\nand remand the district court’s restitution order as to victim Jenny.\\n\\n AFFIRMED in part; VACATED and REMANDED in part.\\n\\n\\n\\n\\n 67\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4394859/\", \"author_raw\": \"HULL, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"CARNES"},"judge2":{"kind":"string","value":"ROSENBAUM"},"judge3":{"kind":"string","value":"HULL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4617606/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. David ROTHENBERG, Defendant-Appellant.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-08\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-12349 Date Filed: 05/08/2019 Page: 1 of 67\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-12349\n ________________________\n\n D.C. Docket No. 0:16-cr-60054-WJZ-1\n\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff-Appellee,\n\n versus\n\nDAVID ROTHENBERG,\n\n Defendant-Appellant.\n\n ________________________\n\n Appeal from the United States District Court\n for the Southern District of Florida\n ________________________\n\n (May 8, 2019)\n\nBefore ED CARNES, Chief Judge, and ROSENBAUM and HULL, Circuit Judges.\n\nHULL, Circuit Judge:\n\n After his guilty plea to possession of child pornography, David Rothenberg\n\nappeals from the district court’s restitution order requiring him to pay a total of\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 2 of 67\n\n\n$142,600 in restitution to nine victims depicted in the images of child pornography\n\nthat he possessed. Section 2259 mandates that district courts order defendants “to\n\npay the victim . . . the full amount of the victim’s losses” as determined by the\n\ncourt. 18 U.S.C. § 2259. This case involves the question of how to calculate the\n\namount of restitution a possessor of child pornography, like the defendant\n\nRothenberg, must pay to a victim whose childhood sexual abuse appears in the\n\npornographic images he possessed but did not create or distribute.\n\n On appeal, Rothenberg argues that: (1) the district court’s restitution order is\n\nflawed as to all of the victims because it failed to calculate and then disaggregate\n\nthe victim’s losses caused by the initial abuser, distributors, and other possessors\n\nfrom those caused by Rothenberg himself; and (2) as to eight of the victims, the\n\nrestitution award is not supported by competent evidence. After review, and with\n\nthe benefit of oral argument, we conclude that the district court was not required to\n\ncalculate and disaggregate the victim’s losses in the manner Rothenberg suggests\n\nand that reliable evidence supports the restitution awards as to eight victims, but\n\nnot as to one victim. We thus affirm the restitution amounts as to eight victims and\n\nvacate and remand as to one victim.\n\n I. INDICTMENT AND GUILTY PLEA\n\n Defendant Rothenberg used to be a lawyer, a fact he told an undercover\n\nofficer in an internet chatroom called “daddaughtersex.” Rothenberg also sent the\n\n\n 2\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 3 of 67\n\n\nofficer videos of child pornography and bragged that he was sexually exploiting a\n\nyoung girl at his house. In 2016, local and federal law enforcement went to\n\nRothenberg’s house and rescued the young girl, who confirmed that Rothenberg\n\nhad engaged in sexual activity with her. The officers also found and seized\n\nRothenberg’s laptop, which contained approximately 1,000 unique video and\n\npicture files of child pornography. Some of those images depicted prepubescent\n\nchildren under the age of 12, and some portrayed sadistic and masochistic conduct,\n\nsuch as the binding and gagging of minor children.\n\n In 2016, a grand jury charged Rothenberg with: (1) four counts of\n\ndistribution of child pornography, in violation of 18 U.S.C. § 2252(a)(2) & (b)(1)\n\n(Counts 1, 3, 4, and 5); (2) one count of receipt of child pornography, in violation\n\nof 18 U.S.C. § 2252(a)(2) & (b)(1) (Count 2); and (3) one count of possession of\n\nchild pornography depicting a minor under the age of 12, in violation of 18 U.S.C.\n\n§ 2252(a)(4)(B) & (b)(2) (Count 6). Pursuant to a written plea agreement,\n\nRothenberg pled guilty to the possession offense in Count 6, and the government\n\nagreed to dismiss the receipt and distribution charges in Counts 1 through 5. The\n\ndistrict court sentenced Rothenberg to 210 months’ imprisonment.\n\n On appeal, Rothenberg does not challenge his guilty plea or sentence.\n\nRather, Rothenberg challenges only the district court’s restitution order granting a\n\ntotal of $142,600 to nine victims, which consists of: (1) $10,000 to Sierra;\n\n\n 3\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 4 of 67\n\n\n(2) $3,000 to Jane; (3) $5,000 to Pia; (4) $5,000 to Mya; (5) $20,000 to Sarah;\n\n(6) $9,000 to Vicky; (7) $23,000 to Amy; (8) $42,600 to Jenny; and (9) $25,000 to\n\nCasseaopeia. We outline the thorough process the district court followed, the\n\nevidence submitted, and then the district court’s findings and conclusions.\n\n II. RESTITUTION PROCEEDINGS\n\n After sentencing, the district court considered restitution requests pursuant to\n\n18 U.S.C. § 2259(a), which provides for mandatory restitution to child\n\npornography victims. Generally, the process worked as follows. First, the\n\ngovernment identified the individual victims depicted in the images of child\n\npornography found on Rothenberg’s computer and notified them or their attorneys\n\nof the upcoming restitution hearing. Then a victim’s attorney submitted a\n\nrestitution request and supporting documentation to the government. Next, the\n\ngovernment determined whether to support that request or ask the district court for\n\na different amount. Rothenberg could agree to the request, try to negotiate down\n\nwith the government or the victim’s attorney, or challenge the request before the\n\ndistrict court.\n\n Eventually the government submitted restitution requests on behalf of ten\n\nvictims, all of whom were identified in at least one of the images of child\n\npornography from Rothenberg’s computer. One of the victims, “Angela,” later\n\nwithdrew her request, leaving nine requests at issue for the hearing.\n\n\n 4\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 5 of 67\n\n\nA. Pre-Hearing Memoranda\n\n Prior to the restitution hearing, both parties submitted lengthy memoranda\n\naddressing (1) how the restitution determination should be made, and (2) what the\n\naward should be for each victim. The government and Rothenberg agreed that the\n\nSupreme Court’s decision in Paroline v. United States, 572 U.S. 434, 134 S. Ct.\n\n1710 (2014), governed how the restitution awards should be made, established a\n\nproximate cause requirement, and set forth a variety of factors for district courts to\n\nconsider in determining the proper amount of restitution. Under Paroline’s\n\nproximate causation requirement, a defendant should pay restitution “in an amount\n\nthat comports with the defendant’s relative role in the causal process that underlies\n\nthe victim’s general losses.” Paroline, 572 U.S. at 458, 134 S. Ct. at 1727.\n\n But the parties disagreed about how exactly to apply the Paroline factors and\n\nhow to calculate and determine that amount. The government recognized that,\n\nunder Paroline, the district court must impose restitution in an amount that reflects\n\nthe particular defendant’s relative role in the continuing traffic in the child\n\npornography images of the victim. The government proposed that the district court\n\nmake that calculation by using a variation of what is known as the “1/n method,”\n\nwhereby the court would divide the total amount of each victim’s losses by the\n\nnumber of defendants, across multiple prosecutions, who had been ordered to pay\n\nrestitution to the victim. The government submitted that this method would\n\n\n 5\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 6 of 67\n\n\nprovide the district court a starting point from which to exercise its discretion in\n\ndetermining the appropriate amount of restitution vis-à-vis Rothenberg, as only a\n\npossessor of images of child pornography.\n\n Rothenberg argued, by contrast, that the starting point should be\n\n“apportionment between the original abuser of the child, versus the distributor, and\n\nlater, possessor of the pornography,” which Rothenberg referred to as\n\n“disaggregation.” Rothenberg asserted that this disaggregation requires two steps:\n\nfirst, the district court must separate the harm caused by the original abuser from\n\nthat caused by later distributors and possessors; and second, the district court must\n\nseparate the harm caused by the defendant from that caused by other distributors or\n\npossessors.\n\n Below, we detail for each victim (1) the victim’s restitution request and\n\nsupporting evidence, (2) the government’s position, and then (3) Rothenberg’s\n\nposition.\n\nB. Sierra\n\n Sierra submitted a restitution request for $10,000. In support of her request,\n\nSierra submitted a medical letter from Dr. Sharon W. Cooper, a forensic\n\npediatrician, based on her December 2015 evaluation of Sierra. Dr. Cooper\n\nexplained that victims of child pornography can experience physical, emotional,\n\nand spiritual issues as a result of their online exploitation, including immunological\n\n\n 6\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 7 of 67\n\n\nproblems, posttraumatic stress disorder (“PTSD”), anxiety, depression, suicidal\n\nideation, and feelings of hopelessness. Dr. Cooper noted that “[w]hen images are\n\nknown to be in distribution, the pre-existing dysfunction caused by the initial abuse\n\nis typically worsened, since children remain at risk for further victimization by the\n\nongoing downloading, trading and possession of their images.”\n\n With respect to Sierra specifically, Dr. Cooper stated that Sierra’s medical\n\nevaluation showed she suffered from worsening insomnia, attention deficit\n\nhyperactivity disorder (“ADHD”), depression, suicidal ideation, PTSD, and mood\n\nlability. Dr. Cooper noted that, despite being on five different medications,\n\nSierra’s condition remained unstable and she recently required emergency\n\ntreatment for suicidality. Dr. Cooper opined that “[t]he ongoing presence of\n\ntrafficking in images [of Sierra] on the Internet constitutes a significant aspect of\n\npsychological maltreatment that will add on to the initial adversities” caused by the\n\noriginal abuse. Based on Sierra’s past medical history, the documented adversities\n\nfaced by victims of child sexual abuse and child pornography offenses, and\n\nSierra’s present medical symptoms, Dr. Cooper estimated a total cost of\n\n$661,453.00 for Sierra’s future medical care.\n\n Sierra’s counsel also submitted a declaration of attorney’s fees, indicating\n\nSierra had incurred nearly $5,000 in attorney’s fees in connection with this case.\n\n\n\n\n 7\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 8 of 67\n\n\n The government supported Sierra’s $10,000 restitution request. The\n\ngovernment observed that four other defendants had been ordered to pay restitution\n\nto victims in the same series of images as Sierra. Those awards were for $4,000,\n\n$1,000, $9,000, and $2,000.\n\n Rothenberg opposed Sierra’s restitution request. Rothenberg noted that he\n\npossessed only one image of Sierra1 and that the requested restitution amount was\n\nmore than double the average of Sierra’s prior awards ($4,000). Rothenberg\n\nargued that Sierra’s restitution materials made no attempt at disaggregation and\n\nthat the government provided no information to demonstrate the relative amount of\n\nSierra’s harm caused by his conduct.\n\nC. Jane\n\n Jane submitted a restitution request for $3,000. In support of her request,\n\nJane submitted a victim impact statement, a psychological report, and an economic\n\nreport. In her victim impact statement, Jane specifically described how the online\n\ntrade in her child pornography images had affected and would continue to affect\n\nher. Jane explained: “Knowing people are watching what happened gives me a\n\nmix of anxiety, sadness, anger and it disgusts me. . . . If it wasn’t out there, I\n\nwouldn’t be as fearful as I am now.” Jane elaborated that the circulation of her\n\n\n 1\n Throughout we refer to how many images of a victim Rothenberg had. Each of the\nimages recounted in this case were child pornography, and for brevity sometimes we refer to\nthem simply as “images.”\n 8\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 9 of 67\n\n\nimages made her feel afraid and unsafe because she worried that someone who had\n\nseen her images online might recognize her and try to harm her. Jane felt that her\n\nfuture would not be “very bright” and would be lonely because the existence of her\n\nimages online made her socially isolated.\n\n Jane’s psychological evaluation was performed by Dr. Jennifer Clark in\n\nDecember 2014 “to determine the psychological effects of her continuous re-\n\nvictimization in the form of Internet pornographic images and videos of her being\n\nexchanged and viewed.” Dr. Clark opined that the online trade in Jane’s images\n\nwas currently impacting her, causing her great fear and anxiety and leaving her\n\nfeeling unsafe and vulnerable. Dr. Clark observed that the trade in Jane’s images\n\nwould continue to impact her in the future by exacerbating her “deep sense of\n\nmistrust in others” from the original abuse and hindering her healing and recovery\n\nprocess. Dr. Clark explained: “[Jane’s] awareness of the ongoing presence and\n\ndistribution of [her] images will remain an ever present trigger to memories of\n\nwhat happened and a source of fear for her safety, and thus, ongoing psychological\n\ndistress. Therefore, Jane will require therapy throughout her life. . . . Given that\n\nmuch of Jane’s distress manifests in somatic symptoms and physiological distress,\n\nshe likely will also seek and need significant medical attention in the future.”\n\n\n\n\n 9\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 10 of 67\n\n\n Jane’s economic evaluation estimated that she would have future medical\n\nand therapy costs of $101,027, and lost wages of between approximately $1.9 and\n\n$3.9 million.\n\n The government agreed that Jane’s $3,000 restitution request was\n\nappropriate. The government noted that seven other defendants had been ordered\n\nto pay restitution to Jane. Three of those seven defendants were ordered to pay\n\n$1,000, two were ordered to pay $2,500, one was ordered to pay $3,000, and one\n\nwas ordered to pay $500.\n\n Rothenberg disputed Jane’s requested amount and argued that a restitution\n\namount of $800 would be appropriate. Rothenberg noted that he possessed four\n\nimages of Jane and that the average award to Jane from the prior cases was $1,642.\n\nRothenberg acknowledged that Jane’s restitution materials were “the best of all\n\nprovided to attempt disaggregation,” but argued his possession did not warrant a\n\n$3,000 award when compared with other defendants. Specifically, Rothenberg\n\nnoted that one of the prior cases with a $1,000 restitution order involved\n\ndistribution, and three of the other cases involved receipt of Jane’s images.\n\nD. Pia\n\n Pia submitted a restitution request for $5,000. In support of her request, Pia\n\nsubmitted an interim impact statement from Dr. Marsha Hedrick, who conducted a\n\nforensic psychological evaluation of Pia, a declaration of attorney’s fees, and a\n\n\n 10\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 11 of 67\n\n\nvictim impact statement from Pia’s mother. Dr. Hedrick noted that Pia\n\nexperienced anxiety, nightmares, suspiciousness, and sadness and was emotionally\n\nwithdrawn. Dr. Hedrick explained that “[s]eparating the extent to which these\n\ndifficulties are related to sexual abuse by her father versus her awareness that her\n\nsexual abuse is being viewed by others is not entirely possible,” but it was clear\n\ninternet exploitation adds a layer of complexity to the psychological damages\n\nvictims of child sexual abuse face. Indeed, Dr. Hedrick noted that Pia’s mother\n\nhad explained to Pia there was no way to remove from the internet the images of\n\nher sexual abuse, resulting in “a level of suspiciousness and concern about\n\nexploitation that is atypical for Pia’s peers” and likely caused Pia to experience\n\nfeelings of powerlessness. Dr. Hedrick estimated the cost of Pia’s therapy needs as\n\n$81,900, but explained that estimate reflected only the “current, most critical\n\nneeds” for Pia and there was no way to know what the full extent of her losses\n\nwould be over the course of her lifetime.\n\n The government concurred in Pia’s $5,000 restitution request. The\n\ngovernment did not have information on any other defendants that were ordered to\n\npay restitution to Pia, but Pia’s counsel advised one other defendant was ordered to\n\npay restitution.\n\n Rothenberg disputed Pia’s requested amount and instead proposed a\n\nrestitution award of $1,100. Rothenberg contended there was “no real attempt at\n\n\n 11\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 12 of 67\n\n\ndisaggregation” in Pia’s restitution documents, but agreed some amount of\n\nrestitution was appropriate based on the number of images (14) he possessed of\n\nPia. Rothenberg reasoned that $1,100 was appropriate because the government\n\nhad requested $2,000 in restitution for Jenny (discussed below), and he possessed\n\nhalf as many images of Pia as he had of Jenny.\n\nE. Mya\n\n Mya submitted a restitution request of $5,000. In support of her request,\n\nMya’s counsel submitted a restitution cover letter and declarations from both of\n\nher attorneys. Mya’s counsel represented that they were still awaiting the results\n\nof Mya’s psychological evaluation, but that other similarly situated child\n\npornography victims they had represented had psychological treatment costs\n\nexceeding $100,000. Mya’s counsel stated that Mya was aware of the existence of\n\nher images on the internet and “the knowledge that others have witnessed and even\n\nenjoyed [her] abuse is extremely upsetting to [her].” Counsel further represented\n\nthat Mya was distrustful of other people and was at risk of being stalked or\n\nvictimized by individuals who had seen her images online. Counsel also\n\nrepresented that they had expended $2,077.44 thus far in representing Mya and two\n\nother victims in the same series (one of whom was victim Pia, discussed above),\n\nand anticipated total legal costs of $30,000 for those three victims.\n\n\n\n\n 12\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 13 of 67\n\n\n The government did not concur in Mya’s $5,000 restitution request. The\n\ngovernment noted that there was no information on whether other defendants were\n\nordered to pay restitution to Mya and determined that “[g]iven that [Rothenberg]\n\npossessed a single image of Mya and the future medical costs have not yet been\n\nestablished,” a restitution award of $500 was appropriate. The government stated\n\nthat amount was neither trivial nor too severe.\n\n Rothenberg argued there was no sufficient basis for awarding any restitution\n\nto Mya given the lack of information regarding her future medical costs.\n\nRothenberg also noted that he made an offer to Mya’s counsel to pay the $500\n\namount the government sought, but that offer was rejected.\n\nF. Sarah\n\n Sarah submitted a restitution request of $25,000. In support of her request,\n\nSarah submitted, among other things, a cover letter, a victim impact statement, a\n\n2014 psychological evaluation by Dr. Randall Green, and an economic report. In\n\nthe cover letter, Sarah’s counsel represented that her requested restitution amount\n\nof $25,000 would be “less than 1%” of her total losses and that 327 other\n\ndefendants were ordered to pay restitution to Sarah.\n\n In her victim impact statement, Sarah explained that she worried that people\n\nwho had seen her images online would “come after” her and try to victimize her in\n\nthe same way her original abuser had. Sarah elaborated: “Every time someone else\n\n\n 13\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 14 of 67\n\n\nsees pictures or videos of me it feels like they are the ones who hurt me to begin\n\nwith. . . . It is like I am just here for other people’s pleasure and am not a person\n\nmyself with my own wants and needs.” Sarah stated that her fear prevented her\n\nfrom leaving the house by herself and from engaging in other normal activities like\n\ngoing to school, having a job, or socializing with more than a few people.\n\n In his psychological evaluation, Dr. Green assessed “the impact and injuries\n\ncaused by the discovery and daily awareness that multiple individuals are viewing\n\nimages of sexual crimes being perpetrated against [Sarah] as a child.” As part of\n\nhis assessment, Dr. Green interviewed Sarah and also performed various\n\npsychological tests. Based on these sources of information, Dr. Green opined that\n\n“the discovery of multiple downloaders and distributors of her images effectively\n\nexponentially multiplied in [Sarah’s] mind the number of sick and dangerous males\n\n‘out there’ who might . . . do her harm.” Dr. Green explained that Sarah’s\n\nknowledge of the dissemination of her child pornography images online caused her\n\ndaily psychological damage in the form of fear “that has reached a paranoid-like\n\nlevel of intensity.” Dr. Green determined that Sarah required “extensive and\n\nintensive therapy” for the trauma caused by both the original abuse and the\n\ncontinuing traffic in her images. Dr. Green estimated the costs of Sarah’s future\n\npsychiatric care were between $265,710 and $303,150.\n\n\n\n\n 14\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 15 of 67\n\n\n Sarah’s counsel reported that Sarah had incurred $31,433.77 in attorney’s\n\nfees. The economic assessment for Sarah estimated a minimum of approximately\n\n$1.9 million in lost wages over her lifetime.\n\n The government did not concur in Sarah’s $25,000 restitution request and\n\ninstead requested an award of $7,895 based on its 1/n calculation method. The\n\ngovernment also provided a list of 155 prior restitution awards to Sarah, which\n\nranged from $0 at the low end to $51,500 at the high end.\n\n Rothenberg opposed Sarah’s restitution request. Rothenberg cited three\n\nother cases involving Sarah in which the government presented the same restitution\n\nevidence and the courts found the government failed to establish proximate cause.\n\nRothenberg argued that the government provided no evidence to disaggregate the\n\nharm proximately caused by his possession of six images of Sarah from that caused\n\nby the other defendants in the list it had provided.\n\nG. Vicky\n\n Vicky submitted a restitution request of $10,000. In support of her request,\n\nVicky submitted several victim impact statements, several psychological reports\n\nfrom Dr. Green, an economic report, and a statement of attorney’s fees. In her\n\nvictim impact statements, Vicky described the effects of the ongoing distribution\n\nof the images of her sexual abuse as a child, including feelings of fear and\n\nparanoia, nightmares, and panic attacks. In a 2014 psychological status report,\n\n\n 15\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 16 of 67\n\n\nDr. Green opined that Vicky continued to require therapy as a result of the\n\ncontinuing traffic in her images, as well as her discovery of attempts by some\n\nviewers of her images to invade her privacy. Dr. Green explained that Vicky\n\ncontinued to experience anxiety, dissociative responses, social withdrawal, anger,\n\nfeelings of powerlessness, and sleep disruption. Dr. Green estimated Vicky’s total\n\ntherapy costs to be between $108,975 to $113,600.\n\n The economic report estimated Vicky’s net lost wages over the course of her\n\nlifetime to be $828,150. Vicky’s counsel represented that Vicky had incurred\n\nattorney’s fees and costs of $92,371.96.\n\n The government did not concur in Vicky’s $10,000 request and instead\n\nrequested an award of $1,283 using its 1/n method. The government provided a\n\nlist of 659 other restitution awards to Vicky, which ranged from approximately $24\n\nat the low end to $1 million at the high end.\n\n Rothenberg opposed Vicky’s restitution request for the same reasons he\n\nopposed Sarah’s request, noting that other courts had denied restitution requests\n\nbased on the same evidence and that the government failed to disaggregate.\n\nRothenberg also noted that he possessed only one image of Vicky and that the\n\naverage post-Paroline restitution award to Vicky was $3,632.\n\n\n\n\n 16\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 17 of 67\n\n\nH. Amy\n\n Amy submitted a restitution request of $25,000. In support of her request,\n\nAmy provided a victim impact statement, several psychological evaluations from\n\nDr. Joyanna Silberg, and an economic report. In her victim impact statement, Amy\n\nstated that she “live[s] in constant fear that someone will see [her] pictures and\n\nrecognize [her].” Amy expressed feelings of powerlessness related to the traffic in\n\nthe images of her sexual abuse as a child because “the crime has never really\n\nstopped and will never really stop.” Amy explained that she experienced fear,\n\nshame, and humiliation at the thought of her friends and other people she\n\nencounters discovering her images online.\n\n In a December 2014 report, Dr. Silberg opined that although Amy had made\n\nstrides as a result of an intensive treatment plan initiated in 2012, ongoing issues\n\nrelated to PTSD remained. Dr. Silberg explained that Amy continued to\n\nexperience flashbacks and nightmares, as well as “fear about the internet and\n\nshame associated with the ongoing viewing of her picture.” Dr. Silberg concluded\n\nthat Amy “continues to suffer from the ongoing effects of her victimization from\n\nchild abuse and from the continued use of her image by child pornography traders,\n\nviewers, and abusers,” and recommended continued psychological treatment and\n\nmonitoring. Amy’s economic report estimated her net lost wages as $2,855,173,\n\nand her future counseling costs as $512,681.\n\n\n 17\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 18 of 67\n\n\n The government did not concur in Amy’s $25,000 request and instead\n\nrequested a restitution amount of $15,664 using its 1/n method. The government\n\nprovided a list of 215 other restitution awards to Amy, ranging from $50 at the low\n\nend to $3.5 million at the high end.\n\n Rothenberg opposed Amy’s restitution request. Rothenberg noted that he\n\npossessed only one image of Amy and that the average post-Paroline restitution\n\naward to her was $3,891. Rothenberg asserted that the government’s list of prior\n\nrestitution orders was inaccurate as to some of the awards and argued that the\n\ngovernment made no attempt to disaggregate his conduct from that of other\n\ndefendants.\n\nI. Jenny\n\n Jenny submitted a restitution request of $42,600. In support of her request,\n\nJenny submitted a victim impact statement and a cover letter from her counsel. In\n\nher victim impact statement, Jenny stated that she worried about the images of her\n\nsexual abuse that were “out there” and feared being recognized in public. Jenny\n\nexpressed a strong desire to forget the abuse she had suffered but explained that\n\n“[w]ith the pictures still out there I can’t.”\n\n In their cover letter, Jenny’s counsel represented that this was Jenny’s\n\nseventh restitution request. Counsel stated that they were still in the process of\n\nobtaining expert reports for Jenny, but asserted that “such formal reports” were not\n\n\n 18\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 19 of 67\n\n\nnecessary for the district court to determine restitution. Counsel discussed a\n\nproposed bill which would set a $25,000 minimum restitution award for child\n\npornography possession offenses, and represented that Jenny had costs of $5,100\n\nfor legal and attorney’s fees and $12,500 for the preparation of expert reports.\n\nBecause these three items totaled $42,600, Jenny’s counsel contended that $42,600\n\namount was the appropriate restitution amount for Jenny.\n\n The government did not concur in Jenny’s $42,600 restitution request and\n\ninstead requested a restitution award of $2,000. The government emphasized that\n\nRothenberg possessed 34 images and one video of Jenny but noted the lack of\n\ndocumentation to support Jenny’s restitution request. The government pointed out\n\nthat one other defendant was ordered to pay restitution to Jenny in the amount of\n\n$7,500.\n\n Rothenberg likewise noted the lack of evidence supporting Jenny’s $42,600\n\nrestitution request. Nevertheless, based on the number of images of Jenny he\n\npossessed, Rothenberg agreed that the government’s requested amount of $2,000\n\nwas reasonable.\n\nJ. Casseaopeia\n\n Casseaopeia submitted a restitution request of $25,000. In support of her\n\nrequest, Casseaopeia provided a victim impact statement, a psychological report\n\nfrom Dr. Joyce Vesper, and an economic assessment. In her victim impact\n\n\n 19\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 20 of 67\n\n\nstatement, Casseaopeia described her ongoing victimization as a result of the\n\nonline trade in her child pornography images. Casseaopeia stated that she worried\n\nthe people viewing her images would seek her out and harm her. She explained\n\nthat she suffers from anxiety, which makes it hard for her to work or go out in\n\npublic, and experiences panic attacks when she thinks someone recognizes her\n\nfrom the internet. Casseaopeia further explained that the continuing traffic in her\n\nimages made recovery from her PTSD and depression more difficult and\n\n“prevent[ed] the wound from healing.”\n\n In her September 2015 psychological report, Dr. Vesper described her\n\nclinical interview with Casseaopeia and the psychological tests she administered.\n\nFrom these assessments, Dr. Vesper concluded that Casseaopeia was “tortured by\n\nconstant memories of childhood sexual abuse” and experienced “constant head\n\nchatter, graphic flashbacks, [and] panic attacks that are so overwhelming they feel\n\nlike heart attacks.” Dr. Vesper described Casseaopeia as living “in constant fear\n\nthat the people viewing the pornographic films and pictures of her” online would\n\ncapture her and subject her to the same abuse all over again. Dr. Vesper opined\n\nthat “[w]ithout the appropriate psychotherapy to address [her] dissociation,\n\ndepersonalization, derealization, amnesia, anxiety and depression,” Casseaopeia\n\nwould continue to experience flashbacks, nightmares, and depression. Dr. Vesper\n\nrecommended intensive psychotherapy for Casseaopeia. In a supplemental report,\n\n\n 20\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 21 of 67\n\n\nDr. Vesper specifically addressed the effects on Casseaopeia of the ongoing traffic\n\nin her images. Dr. Vesper explained that Casseaopeia experienced persistent\n\nanxiety that people she knows will see on the internet images of her sexual abuse\n\nas a child and that this anxiety affects her recovery process.\n\n The economic assessment estimated Casseaopeia had economic damages\n\ntotaling $1,078,159, including $748,438 in lost earning capacity and $329,721 in\n\nfuture medical expenses.\n\n The government requested a slightly lower restitution award of $21,563 for\n\nCasseaopeia, which was calculated using the 1/n method. The government noted\n\nthat 49 other defendants were ordered to pay restitution to Casseaopeia and\n\nsubmitted a list of those prior awards. Those prior awards ranged from $0 at the\n\nlow end to $50,000 at the high end.\n\n Rothenberg opposed Casseaopeia’s restitution request. Rothenberg noted\n\nthat he possessed only two images of Casseaopeia and that the average restitution\n\naward to her was $3,974. Rothenberg argued that, like many of the other requests,\n\nthe government did not differentiate between the harm he caused and that caused\n\nby other perpetrators. Rothenberg contended that Dr. Vesper’s report primarily\n\ndealt with effects of the original abuse rather than the traffic in Casseaopeia’s\n\nimages.\n\n\n\n\n 21\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 22 of 67\n\n\nK. Restitution Hearing\n\n On November 18, 2016, the district court held a restitution hearing. At the\n\nrestitution hearing, the government submitted the evidence on which its restitution\n\nrequests were based, all of which was admitted into evidence.2 That evidence\n\nconsisted of 891 pages of exhibits submitted by the victims and charts prepared by\n\nthe government listing each victim’s prior restitution awards in other federal cases.\n\nThe exhibits included the declarations, psychological evaluations, letters, and other\n\nevidence referenced in the government’s restitution requests. Rothenberg noted, at\n\nthe outset of the hearing, that he agreed with the government’s requested award of\n\n$2,000 to Jenny and therefore did not offer any argument as to that award. The\n\nremaining requests were disputed, and the parties essentially reiterated the\n\narguments raised in their prior memoranda as to those victims.\n\n III. COURT’S RESTITUTION ORDER\n\n Six months later, on May 9, 2017, the district court issued its restitution\n\norder. After outlining in detail Paroline’s framework (and expressing some\n\nfrustration with its inexactitude), the district court analyzed each victim’s\n\nrestitution request. As a preliminary matter, the district court stated that, with\n\n\n\n\n 2\n Though the district court admitted the restitution exhibits into evidence at the restitution\nhearing, it did not scan and file those exhibits on the district court docket. On appeal,\nRothenberg filed an unopposed motion to supplement the record to include those exhibits, which\nthis Court granted.\n 22\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 23 of 67\n\n\nrespect to each victim, it had assigned restitution in a manner that comported with\n\nRothenberg’s relative role and only for damages he proximately caused. The\n\ndistrict court explicitly explained that it had not “attempted to hold [Rothenberg]\n\nresponsible for all losses sustained by any victim.” Furthermore, the district court\n\nexpressly noted there was no evidence that Rothenberg was connected to the initial\n\nabuse of any of the victims or that he had reproduced or distributed their images.\n\nInstead, Rothenberg was a possessor only. And the district court specifically stated\n\nthat it had “taken these factors into consideration in assigning [Rothenberg] a\n\nrelative role as the proximate cause of these victims’ losses.”\n\n Turning to the specific awards, the district court determined that Sierra’s\n\n$10,000 request was reasonable. The district court found that: (1) Rothenberg\n\npossessed one image of Sierra; (2) a small number of criminal defendants had paid\n\nrestitution to Sierra; (3) Sierra’s current mental health condition was severe; and\n\n(4) Sierra’s projected costs of care exceeded $600,000. The district court found “in\n\nconsideration of her large amount of total costs, the small number of contributing\n\noffenders, and a request for a proportion of these costs proximately caused and to\n\nbe paid by [Rothenberg], who neither created nor distributed her image, that\n\n$10,000 is a reasonable request under the Paroline analysis and factors.”\n\n Next, the district court determined that Jane’s $3,000 request was\n\nreasonable. The district court found that: (1) Rothenberg possessed four images of\n\n\n 23\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 24 of 67\n\n\nJane; (2) a small number of criminal defendants had paid restitution to Jane;\n\n(3) Jane’s victim impact statement specifically addressed how the existence of her\n\nimages on the internet affected her and isolated the harm caused by possessors and\n\ndistributors from that caused by the original abuse; and (4) Jane’s estimated\n\nmedical and therapy costs were $101,027. The district court found “in\n\nconsideration of her medical costs, the small number of contributing offenders, and\n\na request for a proportion of these costs to be paid by [Rothenberg], who neither\n\ncreated nor distributed her images, that $3,000 is a reasonable request under the\n\nParoline analysis and factors.”\n\n The district court then determined that Pia’s $5,000 request was reasonable.\n\nThe district court found that: (1) Rothenberg possessed 14 images of Pia; (2) there\n\nwas no evidence regarding the number of other criminal defendants ordered to pay\n\nrestitution to Pia, though Pia’s counsel indicated that one other defendant was so\n\nordered; and (3) Pia’s estimated therapy costs over the next 20 years totaled\n\n$81,900. The district court found “in consideration of her total costs, the fact that\n\nshe has only received restitution from one other defendant, the large number of\n\nimages possessed by [Rothenberg] of [Pia], and a request for a proportion of these\n\ncosts to be paid by [Rothenberg], who neither created nor distributed her images,\n\nthat $5,000 is a reasonable request under the Paroline analysis and factors.”\n\n\n\n\n 24\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 25 of 67\n\n\n The district court also determined that Mya’s $5,000 request was reasonable,\n\ndespite the government’s requested amount of only $500. The district court found\n\nthat: (1) Rothenberg possessed one image of Mya; (2) there was no indication as to\n\nwhether any other criminal defendants were ordered to pay restitution to Mya; and\n\n(3) Mya’s counsel indicated a reasonable treatment estimate for Mya would be\n\nmore than $100,000. The district court found “in consideration of her total costs,\n\nthe fact that she has not received any restitution at this time, and a request for a\n\nproportion of these costs to be paid by [Rothenberg], who neither created nor\n\ndistributed her images, that $5,000 is a reasonable request under the Paroline\n\nanalysis and factors.”\n\n As to Sarah, the district court determined that an award of $20,000—$5,000\n\nless than Sarah’s requested amount—was reasonable. The district court explained\n\nthat: (1) Rothenberg possessed six images of Sarah; (2) over 150 criminal\n\ndefendants were ordered to pay restitution to Sarah; (3) Sarah’s victim impact\n\nstatement explicitly addressed how the existence of her images on the internet\n\naffected her, thereby isolating the harm caused by possession of her images from\n\nthat caused by the original abuse; and (4) Sarah’s estimated cost of psychiatric care\n\nwas nearly $300,000. The district court found, “in consideration of the amount of\n\ncosts, the fact that many other offenders have been required to pay restitution to\n\n[Sarah]—which in the case of Sarah, the Court finds contributes to a finding that\n\n\n 25\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 26 of 67\n\n\nthe request is reasonable and acknowledged by many other courts—the large\n\nnumber of images possessed of [Sarah], and a request for a proportion of these\n\ncosts proximately caused and to be paid by [Rothenberg], who neither created nor\n\ndistributed her image[s], that $20,000 is an appropriate amount under the Paroline\n\nanalysis and factors.”\n\n In a similar vein, the district court determined that for Vicky, $9,000—\n\n$1,000 less than Vicky’s requested $10,000 amount—was a reasonable award.\n\nThe district court found that: (1) Rothenberg possessed one image of Vicky;\n\n(2) more than 600, and possibly more than 800, other criminal defendants were\n\nordered to pay restitution to Vicky; (3) Vicky’s victim impact statement\n\nspecifically addressed how the online traffic in her images affected her and\n\nexplained the distinct harm caused by possessors and distributors of her images;\n\nand (4) Vicky’s predicted therapy costs exceeded $100,000. The district court\n\nfound “in consideration of the amount of costs, the fact that many other offenders\n\nhave been required to pay restitution to [Vicky]—which in the case of Vicky, the\n\nCourt finds contributes to a finding that the request is reasonable and\n\nacknowledged by many other courts—and a request for a proportion of these costs\n\nproximately caused and to be paid by [Rothenberg], who neither created nor\n\ndistributed her image, that $9,000 is an appropriate amount under the Paroline\n\nanalysis and factors.”\n\n\n 26\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 27 of 67\n\n\n The district court likewise awarded a reduced amount to Amy. The district\n\ncourt noted that Amy requested $25,000 and that the government requested\n\n$15,664, but the district court ultimately determined that $23,000 was reasonable.\n\nThe district court explained that: (1) Rothenberg possessed one image of Amy;\n\n(2) more than 200 criminal defendants had paid restitution to Amy; (3) Amy’s\n\nvictim impact statement “provide[d] strong support for the different and separate\n\nharm that possessors proximately cause to victims such as [herself]”; and\n\n(4) Amy’s counseling and therapy costs could exceed $500,000. The district court\n\nfound “in consideration of the large amount of costs, the fact that other offenders\n\nhave been required to pay restitution to [Amy]—which, again, in the case of Amy,\n\nthe Court finds contributes to a finding that the request is reasonable and\n\nacknowledged by other courts—and a request for a proportion of these costs\n\nproximately caused and to be paid by [Rothenberg], who neither created nor\n\ndistributed her image, that $23,000 is an appropriate amount under the Paroline\n\nanalysis and factors.”\n\n Regarding Jenny, the district court acknowledged that both the government\n\nand Rothenberg agreed that $2,000 was an appropriate amount, but that Jenny\n\nrequested $42,600. The district court determined that Jenny’s requested amount\n\nwas reasonable. The district court emphasized that (1) Rothenberg possessed 34\n\nimages and one video of Jenny, and (2) only one other defendant had paid\n\n\n 27\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 28 of 67\n\n\nrestitution to Jenny. The district court conceded there was “less documentation of\n\nJenny’s psychological and medical expenses as compared with some other victims\n\nin this case,” but found that the $2,000 amount requested by the parties was\n\ninsufficient. Considering “the extremely large number of images [Rothenberg]\n\npossessed of [Jenny], her costs, the fact that only one other defendant has so far\n\ncontributed to these costs, and a request for a proportion of these costs to be paid\n\nby [Rothenberg], who neither created nor distributed her images, the Court finds\n\nthat $42,600 is a reasonable request under the Paroline analysis and factors.”\n\n Lastly, as to Casseaopeia, the district court determined that her requested\n\naward of $25,000 was reasonable, even though the government requested only\n\n$21,563. The district court found that: (1) Rothenberg possessed two images of\n\nCasseaopeia; (2) more than 50 criminal defendants were ordered to pay her\n\nrestitution; and (3) her projected costs of care exceeded $300,000. Considering\n\n“her costs, the number of contributing offenders, and a request for a proportion of\n\nthese costs proximately caused and to be paid by [Rothenberg], who neither\n\ncreated nor distributed her image,” the district court found that “$25,000 is a\n\nreasonable request under the Paroline analysis and factors.”\n\n In total, the district court ordered Rothenberg to pay $142,600 in restitution,\n\nto be apportioned to the nine victims in the amounts set out above. On appeal,\n\nRothenberg argues that the district court erred as to all nine restitution awards. We\n\n\n 28\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 29 of 67\n\n\nbegin with the restitution statute and then review the Supreme Court’s Paroline\n\ndecision, which both parties agree governs this appeal.\n\n IV. 18 U.S.C. § 2259\n\n Congress has mandated that district courts award restitution to victims of\n\ncertain federal crimes, including child pornography possession. See 18 U.S.C.\n\n§ 2259(a) (2012).3 The possessor of child pornography must pay restitution to the\n\nvictim whose childhood abuse appears in the pornographic materials he possessed.\n\nSee id. § 2259(b)(1), (c)(4). The statute requires that “[t]he order of restitution . . .\n\nshall direct the defendant to pay the victim . . . the full amount of the victim’s\n\nlosses as determined by the court.” Id. § 2259(b)(1). The statute defines the term\n\n“full amount of the victim’s losses” to include any costs incurred by the victim for:\n\n (A) medical services relating to physical, psychiatric, or psychological\n care;\n (B) physical and occupational therapy or rehabilitation;\n (C) necessary transportation, temporary housing, and child care\n expenses;\n (D) lost income;\n (E) attorneys’ fees, as well as other costs incurred; and\n (F) any other losses suffered by the victim as a proximate result of the\n offense.\n\n\n\n\n 3\n Since Rothenberg’s guilty plea and restitution hearing, Congress amended 18 U.S.C.\n§ 2259, effective December 7, 2018. See Amy, Vicky, and Andy Child Pornography Victim\nAssistance Act of 2018, Pub. L. No. 115-299, 132 Stat. 4383 (2018). All citations in this opinion\nare to the previous version of 18 U.S.C. § 2259, which was in effect both when Paroline was\ndecided and at the time of the district court’s restitution order in this case.\n 29\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 30 of 67\n\n\nId. § 2259(b)(3) (emphasis added). The statute defines a victim as “the individual\n\nharmed as a result of the commission of a crime under this chapter.” Id.\n\n§ 2255(c)(4) (emphasis added). A court may not decline to issue restitution\n\nbecause of the economic circumstances of the defendant or because the victim has\n\nreceived compensation from another source. See id. § 2259(b)(4)(B).\n\n “The burden of demonstrating the amount of the loss sustained by a victim\n\nas a result of the offense shall be on the attorney for the Government.” Id.\n\n§§ 3664(e), 2259(b)(2) (emphasis added). In Paroline, the Supreme Court\n\naddressed the meaning of “as a result of” and “proximate result” in § 2259 and\n\nprecisely what type of causal connection or proximate cause must exist between\n\nthe victim’s losses and the defendant’s offense. We review Paroline next.\n\n V. SUPREME COURT’S PAROLINE DECISION\n\n Like this case, Paroline involved a possessor of child pornography images in\n\nwide circulation on the internet. In Paroline, the defendant was a possessor and not\n\na distributor or the initial abuser. See 572 U.S. at 439, 134 S. Ct. at 1716. The\n\nSupreme Court grappled with the question of what causal relationship must be\n\nestablished between a defendant possessor’s conduct and a victim’s losses for\n\npurposes of determining the right to, and the amount of, restitution under § 2259.\n\nId. As a preliminary matter, the Supreme Court interpreted § 2259’s statutory\n\nlanguage to impose a general proximate-cause limitation. Id. at 448, 134 S. Ct. at\n\n\n 30\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 31 of 67\n\n\n1721. The Supreme Court determined that “[r]estitution is therefore proper under\n\n§ 2259 only to the extent the defendant’s offense proximately caused a victim’s\n\nlosses.” Id. at 448, 134 S. Ct. at 1722.\n\n The difficulty, the Supreme Court explained, comes in applying that\n\ncausation requirement in a particular child pornography case. Id. at 449, 134 S. Ct.\n\nat 1722. This is so because of the “somewhat atypical causal process underlying\n\nthe losses [a child pornography] victim claims.” Id. The Supreme Court reasoned\n\nthat it may be “simple enough” for a victim to prove the aggregate losses that stem\n\nfrom the ongoing traffic in her images as a whole. Id. Importantly, the Supreme\n\nCourt observed that it is more difficult to determine “the ‘full amount’ of those\n\ngeneral losses, if any, that are the proximate result of the offense conduct of a\n\nparticular defendant who is one of thousands who have possessed and will in the\n\nfuture possess the victim’s images but who has no other connection to the victim.”\n\nId.\n\n Therefore, in child pornography possession offenses, the Paroline Court\n\nrecognized that it would be virtually impossible to show that the defendant\n\npossessor was a but-for cause of any particular portion of the victim’s losses\n\n“where the defendant is an anonymous possessor of images in wide circulation on\n\nthe Internet.” Id. at 450-51, 134 S. Ct. at 1722-23. Nevertheless, the Supreme\n\nCourt observed that “[w]hile it is not possible to identify a discrete, readily\n\n\n 31\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 32 of 67\n\n\ndefinable incremental loss [a defendant possessor] caused, it is indisputable that\n\n[the defendant possessor] was a part of the overall phenomenon that caused [the\n\nvictim’s] general losses.” Id. at 456-57, 134 S. Ct. at 1726. And it would\n\nundermine the purposes of § 2259 to deny restitution in cases involving possessors\n\nof child pornography. Id. at 456-58, 134 S. Ct. at 1726-27.\n\n The Supreme Court also recognized that the original abuse crime is\n\ncompounded by the distribution and possession of images of the victim’s original\n\nabuser’s “horrific acts, which meant the wrongs inflicted on her were in effect\n\nrepeated; for she knew her humiliation and hurt were and would be renewed into\n\nthe future as an ever-increasing number of wrongdoers witnessed the crimes\n\ncommitted against her.” Id. at 441, 134 S. Ct. at 1717. It does not matter that the\n\nvictim does not know the name of the possessor because the losses do not flow\n\nfrom any specific knowledge of him; rather, the cause of the victim’s losses “is the\n\ntrade in her images.” Id. at 456, 134 S. Ct at 1726. The Supreme Court also\n\nobserved that “the victim suffers continuing and grievous harm as a result of her\n\nknowledge that a large, indeterminate number of individuals have viewed and will\n\nin the future view images of the sexual abuse she endured.” Id. at 457, 134 S. Ct.\n\nat 1726. “In a sense, every viewing of child pornography is a repetition of the\n\nvictim’s abuse.” Id. at 457, 134 S. Ct. at 1727. “The cause of the victim’s general\n\nlosses is the trade in her images.” Id. at 456, 134 S. Ct. at 1726.\n\n\n 32\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 33 of 67\n\n\n After rejecting a but-for test for proximate cause, the Paroline Court adopted\n\na causation-in-fact standard for cases where: (1) “a defendant possessed a victim’s\n\nimages”; (2) “a victim has outstanding losses caused by the continuing traffic in\n\nthose images”; and yet (3) “it is impossible to trace a particular amount of those\n\nlosses to the individual defendant by recourse to a more traditional causal inquiry.”\n\nId. at 458, 134 S. Ct. at 1727. In that situation, the Supreme Court concluded that a\n\ndefendant possessor of child pornography should be ordered to pay restitution “in\n\nan amount that comports with the defendant’s relative role in the causal process\n\nthat underlies the victim’s general losses.” Id. The Supreme Court explained that\n\nthe award “would not be severe” in a case where the possessor is only one of many\n\nthousands of offenders, but also would not be “a token or nominal amount.” Id. at\n\n458-59, 134 S. Ct. at 1727. Rather, the required restitution would be “reasonable\n\nand circumscribed” and “suited to the relative size of [the defendant’s] causal\n\nrole.” Id. at 459, 134 S. Ct. at 1727.\n\n Further, the Supreme Court instructed, there is no “practical way to isolate\n\nsome subset of the victim’s general losses that [the possessor] Paroline’s conduct\n\nalone would have been sufficient to cause.” Id. at 451, 134 S. Ct. at 1723. In\n\nParoline, the defendant possessor was one of thousands who possessed the victim’s\n\nimages. Id. at 450, 134 S. Ct. at 1723. The Supreme Court stressed that even though\n\nthe victim does not know the possessor, the victim’s “knowledge that her images\n\n\n 33\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 34 of 67\n\n\nwere circulated far and wide renewed the victim’s trauma and made it difficult for\n\nher to recover from her abuse.” Id. at 440, 134 S. Ct. at 1717. “While it is not\n\npossible to identify a discrete, readily definable incremental loss he [the possessor]\n\ncaused, it is indisputable that he was a part of the overall phenomenon that caused\n\nher general losses.” Id. at 456-57, 134 S. Ct. at 1726. In other words, the defendant\n\npossessor of the images caused in fact part of the general losses, even if “it is\n\nimpossible to trace a particular amount of those losses to the individual defendant.”\n\nId. at 458, 134 S. Ct. at 1727.\n\n The Paroline Court then turned to the question of how district courts are to\n\ndetermine the proper amount of restitution in these “possessor” cases. Id. As a\n\ngeneral matter, the Supreme Court stated that a district court “must assess as best it\n\ncan from available evidence the significance of the individual defendant’s conduct\n\nin light of the broader causal process that produced the victim’s losses.” Id. at 459,\n\n134 S. Ct. at 1727-28. The Supreme Court emphasized that this “cannot be a precise\n\nmathematical inquiry,” but rather involves the exercise of “wide discretion” and\n\n“sound judgment” of the sort district courts typically exercise in the context of\n\ncriminal sentencing and restitution more broadly. Id. at 459-62, 134 S. Ct. at 1728-\n\n29. The Supreme Court then expressly identified “a variety of factors district courts\n\nmight consider” in determining a proper restitution amount for possession. Id. at\n\n459-60, 134 S. Ct. at 1728 (emphasis added).\n\n\n 34\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 35 of 67\n\n\n As a starting point, the Supreme Court suggested that district courts\n\n“determine the amount of the victim’s losses caused by the continuing traffic in the\n\nvictim’s images.” Id. at 460, 134 S. Ct. at 1728 (emphasis added). Then, to\n\ndetermine the defendant possessor’s relative role in causing those general losses, the\n\ndistrict court could consider factors such as: (1) “the number of past criminal\n\ndefendants found to have contributed to the victim’s general losses”; (2) “reasonable\n\npredictions of the number of future offenders likely to be caught and convicted for\n\ncrimes contributing to the victim’s general losses”; (3) “any available and\n\nreasonably reliable estimate of the broader number of offenders involved (most of\n\nwhom will, of course, never be caught or convicted)”; (4) “whether the defendant\n\nreproduced or distributed images of the victim”; (5) “whether the defendant had any\n\nconnection to the initial production of the images”; (6) “how many images of the\n\nvictim the defendant possessed”; and (7) “other facts relevant to the defendant’s\n\nrelative causal role.” Id.\n\n The Supreme Court reiterated that these factors should not be used as a “rigid\n\nformula,” but should instead serve as “rough guideposts” in determining a restitution\n\namount for the possessor criminal defendant. Id. The Supreme Court noted that\n\n“[t]his approach is not without its difficulties,” as it “involves discretion and\n\nestimation,” but “courts can only do their best to apply the statute as written in a\n\nworkable manner.” Id. at 462, 134 S. Ct. at 1729. The Supreme Court emphasized\n\n\n 35\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 36 of 67\n\n\nthat district courts regularly exercise wide discretion, and there was “no reason to\n\nbelieve they cannot apply th[is] causal standard . . . in a reasonable manner.” Id.4\n\n VI. STANDARD OF REVIEW\n\n We review de novo the legality of a restitution order, but review for clear\n\nerror the factual findings underlying that order. United States v. McDaniel, 631\n\nF.3d 1204, 1207 (11th Cir. 2011); see also United States v. Osman, 853 F.3d 1184,\n\n1188 (11th Cir. 2017). We review the amount of the district court’s restitution\n\naward only for an abuse of discretion. See United States v. Robertson, 493 F.3d\n\n1322, 1330 (11th Cir. 2007); see also Paroline, 572 U.S. at 459, 134 S. Ct at 1727-\n\n28 (emphasizing that “determining the proper amount of restitution” involves “the\n\nuse of discretion and sound judgment” on the part of the district court).\n\n A district court abuses its discretion if it applies an incorrect legal standard,\n\nfollows improper procedures, or makes clearly erroneous findings of fact. United\n\nStates v. Jordan, 582 F.3d 1239, 1249 (11th Cir. 2009). The abuse of discretion\n\nstandard recognizes that the district court has a range of choices, and this Court\n\n\n\n\n 4\n Three of the four dissenting justices were not so sure and complained that “[w]hen it\ncomes to [the defendant’s] crime—possession of two of [the victim’s] images—it is not possible\nto do anything more than pick an arbitrary number” as “the amount of the loss sustained by a\nvictim as a result of” the defendant’s crime. Paroline, 572 U.S. at 463, 134 S. Ct. at 1730\n(Roberts, C.J., dissenting). The fourth dissenter, Justice Sotomayor, would have embraced the\nvictim’s joint and several liability theory, holding each possessor liable for restitution in the full\namount of the victim’s losses. Id. at 473, 134 S. Ct. at 1735 (Sotomayor, J., dissenting).\n 36\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 37 of 67\n\n\nwill not reverse the district court’s choice as long as its decision does not amount\n\nto a clear error of judgment. Id.\n\n Osman, our only published post-Paroline restitution decision to date, did not\n\naddress how the abuse of discretion standard applies in assessing whether the\n\ndistrict court adequately considered the Paroline factors and imposed a reasonable\n\nrestitution award. See generally Osman, 853 F.3d at 1189-92. But Paroline itself\n\nprovides some important clues. In Paroline, the Supreme Court emphasized that\n\ndetermining the proper restitution amount “involves the use of discretion and\n\nsound judgment” in a manner akin to that exercised “in the wider context of\n\ncriminal sentencing,” and that the ultimate award must be “reasonable and\n\ncircumscribed.” Paroline, 572 U.S. at 459, 134 S. Ct. at 1727-28; see also id. at\n\n462, 134 S. Ct. at 1729 (explaining that “[d]istrict courts routinely exercise wide\n\ndiscretion . . . in sentencing as a general matter” and should likewise apply\n\nParoline’s causal standard “in a reasonable manner”). And to guide the district\n\ncourt’s exercise of its discretion, the Paroline Court identified a number of factors\n\ndistrict courts may consider in fashioning an appropriate restitution award. Id. at\n\n459-60, 134 S. Ct. at 1728.\n\n Paroline thus established a framework not unlike the one we apply in\n\nassessing the reasonableness of a defendant’s sentence, in which we look to see\n\nwhether the district court appropriately exercised its sentencing discretion in light\n\n\n 37\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 38 of 67\n\n\nof the 18 U.S.C. § 3553(a) factors. See, e.g., Gall v. United States, 552 U.S. 38,\n\n51, 128 S. Ct. 586, 597 (2007); United States v. Irey, 612 F.3d 1160, 1188-91 (11th\n\nCir. 2010) (en banc). In that § 3553(a) context, we evaluate whether the district\n\ncourt failed to consider relevant factors, improperly weighed the relevant factors,\n\nor considered improper factors, and ultimately assess whether, under the totality of\n\nthe circumstances, the sentence is reasonable. See Irey, 612 F.3d at 1189. And we\n\nwill vacate a sentence imposed by the district court only if we are “left with the\n\ndefinite and firm conviction that the district court committed a clear error of\n\njudgment in weighing the § 3553(a) factors by arriving at a sentence that lies\n\noutside the range of reasonable sentences dictated by the facts of the case.” Id. at\n\n1190 (internal quotation marks omitted).\n\n Additionally, in sentencing cases, we do not require district courts to make\n\ndetailed findings or give a thorough explanation for the sentence it chose. See id.\n\nat 1194-95. Specifically, “[t]he district court need not state on the record that it has\n\nexplicitly considered each factor and need not discuss each factor,” United States\n\nv. Dorman, 488 F.3d 936, 938 (11th Cir. 2007), “so long as the record reflects the\n\ncourt’s consideration of many of those factors,” United States v. Carpenter, 803\n\nF.3d 1224, 1232 (11th Cir. 2015). “Rather, an acknowledgment by the district\n\ncourt that it has considered the defendant’s arguments and the § 3553(a) factors\n\nwill suffice.” Dorman, 488 F.3d at 938.\n\n\n 38\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 39 of 67\n\n\n A similar approach makes sense here. As in the sentencing context, in\n\nevaluating child pornography restitution awards under Paroline, appellate courts\n\nmust determine whether the district court appropriately exercised its broad\n\ndiscretion in light of the facts of the particular case and awarded restitution in an\n\namount that comports with the particular defendant’s conduct. See Paroline, 572\n\nU.S. at 458-59, 462, 134 S. Ct. at 1727-29; Irey, 612 F.3d at 1190. And as in the\n\nsentencing context, a number of relevant factors guide the district court’s exercise\n\nof its discretion. See Paroline, 572 U.S. at 459-60, 134 S. Ct. at 1728; Gall, 552\n\nU.S. at 51, 128 S. Ct. at 597. Furthermore, the Supreme Court in Paroline\n\nindicated that the exercise of discretion at issue in child pornography restitution\n\ncases is similar to that exercised in criminal sentencing more generally. See\n\nParoline, 572 U.S. at 459, 134 S. Ct. at 1727-28.\n\n Accordingly, in reviewing child pornography restitution awards under\n\nParoline, this Court should consider whether, in light of the Paroline factors, the\n\ndistrict court arrived at a restitution amount that lies within the general range of\n\nreasonable restitution awards dictated by the facts of the case. See Irey, 612 F.3d\n\nat 1190. In doing so, this Court should give due deference to the district court’s\n\ndetermination that the Paroline factors, on the whole, justify the restitution amount\n\nawarded and should not vacate an award unless left with the definite and firm\n\nconviction that the district court committed a clear error of judgment in setting the\n\n\n 39\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 40 of 67\n\n\naward amount. See id.; Gall, 552 U.S. at 51, 128 S. Ct. at 597. Moreover, so long\n\nas the district court acknowledges that it has considered the Paroline factors and\n\nthe defendant’s arguments regarding restitution, we will not vacate a restitution\n\naward solely on the basis that the district court did not address each factor\n\nexplicitly. See Carpenter, 803 F.3d at 1232; Dorman, 488 F.3d at 938.\n\n With these principles in mind, we turn now to Rothenberg’s disaggregation\n\nargument, which is a legal challenge to the district court’s restitution order that we\n\nreview de novo. Osman, 853 F.3d at 1188.\n\n VII. DISAGGREGATION\n\n On appeal, Rothenberg first argues that, as to all nine victims, the district\n\ncourt failed to “disaggregate” their losses. Rothenberg contends that Paroline\n\nrequires district courts to engage in disaggregation at two levels: first, by\n\ndisaggregating the portion of the victim’s losses caused by the original abuse; and\n\nsecond, by disaggregating the losses caused by the defendant from those caused by\n\nother possessors or distributors.\n\n Rothenberg asserts that the district court here failed at the first level by\n\nrelying on total loss estimates for each victim that did not separate out and deduct\n\nthe losses caused by the original abuser. Because the expert reports did not\n\ndisaggregate the losses caused by the original abuser from those caused by the\n\ndistributors or possessors, Rothenberg contends that the district court was required\n\n\n 40\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 41 of 67\n\n\nto conduct that separating out itself. Rothenberg maintains that the district court\n\nalso failed to disaggregate at the second level by failing to use the amounts of the\n\nprior restitution orders against other defendant possessors or distributors for the\n\nsame victims as a guidepost for determining his relative level of culpability.\n\n The government responds that nothing in Paroline requires district courts to\n\nengage in the sort of formal disaggregation Rothenberg envisions. Rather, the\n\ngovernment contends that Paroline simply requires that the district court consider\n\nthe Paroline factors and exercise its discretion in determining the amount of a\n\nvictim’s losses caused by the instant defendant. The government submits that the\n\ndistrict court here complied with those requirements, explicitly stating it was not\n\nholding Rothenberg accountable for the original abuse or distribution of the\n\nvictims’ images and setting restitution amounts that “best approximat[ed]\n\nRothenberg’s relative role.”\n\n This Court has not yet addressed whether, in awarding restitution post-\n\nParoline, district courts first must formally disaggregate a victim’s losses between\n\nthe original abuser, distributors, and subsequent possessors. Several of our sister\n\ncircuits, however, have grappled with that question, and the results are mixed.\n\nA. Eighth and Fifth Circuits’ Decisions\n\n We start with the Eighth Circuit’s decision in United States v. Bordman, 895\n\nF.3d 1048, 1058-59 (8th Cir. 2018), cert. denied, 2019 WL 1886056 (U.S. Apr. 29,\n\n\n 41\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 42 of 67\n\n\n2019), a restitution case involving a defendant convicted of only possessing child\n\npornography. In Bordman, the Eighth Circuit expressly held that a district court is\n\nnot required to formally disaggregate categories of loss before ordering restitution,\n\nsuch as the loss caused by the initial abuser. Id. at 1058-59.\n\n In doing so, the Eighth Circuit affirmed the district court’s $3,000 award of\n\nrestitution to a victim where the district court considered multiple factors,\n\nincluding: (1) the 1/n method, which took into account the number of defendants\n\n(32) who had already paid the victim restitution plus 1 (the defendant Bordman),\n\nfor a total of 33; (2) the child pornography being videos with two copies of the\n\nsame video in different folders; and (3) the “very aggravating factor” of the nature\n\nof the video. Id. at 1052-53, 1059. The victim’s losses included $91,900 in\n\ntherapy, related expenses, and for a vocational assessment and counseling, legal\n\ncosts of $10,187.13, and attorney’s fees. Id. at 1052. At the sentencing hearing,\n\nthe government took the sum of $95,295.71 ($91,900 plus one third of the\n\nattorney’s fees) and divided it by 33 defendants, resulting in the sum of $2,887.75.\n\nId. at 1052-53. One-third of the attorney’s fees was used because this same\n\nattorney had represented three victims. Id. at 1052. The district court imposed a\n\n$3,000 restitution amount for the victim. Id. at 1054.\n\n On appeal, the defendant-possessor Bordman specifically claimed that “the\n\ndistrict court abused its discretion by failing to disaggregate the harm caused by the\n\n\n 42\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 43 of 67\n\n\ninitial abuse from the harm that his later possession caused.” Id. at 1058. In\n\nrejecting that claim, the Eighth Circuit reasoned that “one of the Paroline factors\n\nalready accounts for disaggregation”—namely, “whether the defendant had any\n\nconnection to the initial production of the images.” Id. at 1059 (quoting Paroline,\n\n572 U.S. at 460, 134 S. Ct. at 1728). The Eighth Circuit “decline[d] to transform”\n\nthis disaggregation factor “from a ‘rough guidepost’ into a ‘rigid formula.’” Id.\n\n(quoting Paroline, 572 U.S. at 460, 134 S. Ct. at 1728).\n\n The Fifth Circuit also has rejected, under plain error review, a defendant’s\n\nchallenge to restitution awards that relied on psychological reports that “did not\n\nseparate the losses caused by [the defendant possessor] from the losses caused by\n\nother abusers.” United States v. Halverson, 897 F.3d 645, 654-55 n.4 (5th Cir.\n\n2018). The Fifth Circuit reasoned that nothing in Paroline clearly required victims\n\nto present a new psychological report in each case that “disaggregates a\n\ndefendant’s conduct from all other possible sources of the victim’s losses.” Id.\n\nThe Fifth Circuit approved the district court’s use of a restitution method which\n\nawarded each victim (1) a base $5,000 amount of restitution, plus (2) an additional\n\nsum of $1,409 for each image of the victim that the defendant possessed because\n\nthe district court discussed factors that bore on the relative significance of the\n\ndefendant’s conduct and the district court was not required to make findings as to\n\nall of the Paroline factors. Id. at 653-54.\n\n\n 43\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 44 of 67\n\n\nB. Fourth and Seventh Circuits’ Decisions\n\n While not directly ruling on the initial-abuser-disaggregation issue, two\n\nother decisions of our sister circuits bear mentioning. That is because both\n\ndecisions, post-Paroline, (1) emphasized the district court’s wide discretion\n\ninherent in determining the amount of restitution, (2) affirmed restitution awards\n\nunder various methodologies against possessors of child pornography, and\n\n(3) refused to impose more structure beyond the Supreme Court’s multi-factored\n\ntest. See United States v. Dillard, 891 F.3d 151, 160-62 (4th Cir. 2018) (noting\n\nthat Paroline did not set any “evidentiary minimums” for establishing restitution,\n\nthat “[p]ost-Paroline, our sister courts of appeals have approved of various\n\nmethods of determining a restitution award,” and that “[d]istrict courts have great\n\ndiscretion in selecting an appropriate methodology”); United States v. Sainz, 827\n\nF.3d 602, 605-07 (7th Cir. 2016) (discussing the district court’s ability to employ\n\nvarying methodologies, including the 1/n method, to calculate a restitution amount\n\nunder Paroline and stating that “the bottom line here is that the amount of the\n\naward is substantively reasonable”). We discuss Dillard and Sainz in detail, as\n\nthey demonstrate not only how to apply the Paroline factors, but also a common-\n\nsense, practical approach to restitution for victims whose losses are caused by the\n\ncontinuing traffic in their child pornography images.\n\n\n\n\n 44\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 45 of 67\n\n\n In the Fourth Circuit’s Dillard decision, while the defendant was the initial\n\nabuser of one child victim, he also possessed images of other child victims with\n\nwhom he had no contact. Dillard, 891 F.3d at 154. The district court denied all\n\nrestitution to the non-contact victims because the record contained no evidence that\n\nthe victims were aware Dillard had their images and no evidence connecting the\n\nnon-contact victims’ harm to Dillard. Id. at 156. In reversing, the Fourth Circuit\n\nexplained Paroline disavowed any such requirements. Id. at 159-60. The Fourth\n\nCircuit held the “[g]overnment satisfied its burden of causation by the uncontested\n\nevidence that Dillard’s offense conduct included the seven non-contact victims’\n\nimages” and “that these victims have outstanding losses caused by the continuing\n\ntraffic in those images.” Id. at 160 (internal quotation marks omitted).\n\n As to how to calculate those non-contact victims’ losses caused by Dillard,\n\nthe Fourth Circuit said the district court “‘might, as a starting point, determine the\n\namount of the victim’s losses caused by the continuing traffic in the victim’s\n\nimages’” and “‘then set an award of restitution in consideration of factors that bear\n\non the relative causal significance of the defendant’s conduct in producing those\n\nlosses.’” Id. at 160 (quoting Paroline, 572 U.S. at 460, 134 S. Ct. at 1728). The\n\nFourth Circuit remanded for the district court to consider the Paroline factors and\n\naward at least some “non-nominal amount of restitution” for the losses of the non-\n\ncontact victims whose images Dillard possessed. Id. at 161-62. Where it was\n\n\n 45\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 46 of 67\n\n\n“uncontested that the individuals seeking restitution were Dillard’s victims and had\n\noutstanding losses associated with the continued trade in their images, they were\n\nentitled by statute to some non-nominal amount of restitution.” Id. at 161 (citing\n\nParoline, 572 U.S. at 458-60, 134 S. Ct. at 1727-28).\n\n Similarly, the Seventh Circuit’s decision in Sainz stresses the district court’s\n\n“considerable discretion in deciding the extent of a defendant’s restitution” who\n\npossessed child pornography. Sainz, 827 F.3d at 605. The defendant Sainz\n\npossessed six images of the victim that had circulated widely on the internet, but\n\nhad no role in creating or distributing them. Id. at 604. The victim had “incurred\n\nfinancial losses such as future lost earnings, attorney fees, and medical and\n\npsychiatric expenses” that totaled $1.1 million. Id. at 604, 605 n.1. On appeal, the\n\ndefendant Sainz did not challenge that he must pay some amount of restitution but\n\nargued that the $8,387.43 amount he was ordered to pay was “disproportionate to\n\nhis relative role in causing” the victim’s losses. Id. at 604-05. Sainz also claimed\n\n“he was not a legal cause of [the victim’s] harm because hundreds or thousands of\n\nothers also possessed the images, so she would have been harmed by others even if\n\nhe had never possessed the images of her.” Id. at 604.\n\n Using the 1/n method advocated for by the government, the district court\n\ndivided the total loss of $1.1 million by 136 because defendant Sainz was the 136th\n\noffender who was prosecuted and ordered to pay restitution. See id. at 605. By\n\n\n 46\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 47 of 67\n\n\npossessing and viewing the victim’s images, Sainz had re-victimized her and made\n\nher feel that the abuse was continuing. Id. at 604.\n\n In finding no legal error or abuse of discretion in the $8,387.43 restitution\n\naward, the Seventh Circuit affirmed and reasoned: (1) that the Supreme Court in\n\nParoline “avoided rigid or mechanical rules” and left the district courts with\n\n“considerable discretion”; (2) the amount of restitution for a possessor like Sainz\n\n“should be neither ‘severe’ nor a ‘token or nominal amount’”; (3) Paroline does not\n\nrequire “district courts to consider in every case every factor mentioned” and the\n\ndistrict court does “not err by not addressing every Paroline factor” 5; and (4) the\n\nParoline factors are permissive, not mandatory and provide “rough guideposts” that\n\n“district courts might consider in determining a proper amount of restitution.” Id.\n\nat 605-07 (internal quotation marks omitted). The Seventh Circuit recognized that\n\nthe 1/n method is not appropriate for all cases because, when n is “very small or\n\nvery large, a more nuanced method may be required.” Id. at 607. The Seventh\n\nCircuit concluded, however, that the application of the 1/n method to Sainz’s case\n\n“resulted in a reasonable restitution order of $8,400 for an offender who possessed\n\nsix images of the victim and indisputably contributed to her harm.” Id.\n\n\n 5\n The Seventh Circuit explained some of the Paroline factors refer to information that may\nnot be “reliably known,” such as “the number of offenders likely to be convicted in the future or\nthe broader numbers of offenders who were involved but are unlikely to be caught.” Sainz, 827\nF.3d at 607. The Seventh Circuit stated that “the Supreme Court made clear in Paroline that the\ndifficulty of coming up with reasonable estimates for an indeterminate number of other offenders\nshould not be a barrier to all compensation for victims of child pornography.” Id.\n 47\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 48 of 67\n\n\n We acknowledge that the defendant Sainz did not ask the court to\n\ndisaggregate the losses from the initial abuser. Nonetheless, the Seventh Circuit’s\n\ndecision is instructive because it emphasizes that (1) the district court has\n\n“considerable discretion,” (2) the court’s method of restitution calculation can vary\n\nfrom case to case depending on the facts, and (3) “the bottom line” is that the\n\ndistrict court’s award of $8,387.43 was “substantively reasonable” for the\n\ndefendant possessor Sainz, even though there were hundreds of other possessors of\n\nthe same victim’s images. See id. at 604-607.\n\nC. Ninth and Tenth Circuits’ Decisions\n\n In contrast to these decisions, the Ninth and Tenth Circuits have determined\n\nthat district courts must engage in some level of disaggregation as to the harms\n\ncaused by the original abuse versus the harms caused by later distributors and\n\npossessors before awarding restitution against a particular possessor of child\n\npornography. See United States v. Galan, 804 F.3d 1287 (9th Cir. 2015); United\n\nStates v. Dunn, 777 F.3d 1171 (10th Cir. 2015). But even those post-Paroline\n\ndecisions are nuanced and do not adopt a rigid, mathematical rule in that regard.\n\nFurthermore, the facts of the Tenth Circuit’s Dunn case are important to\n\nunderstand what the Tenth Circuit did or did not conclude in that case.\n\n In Dunn, one victim sought restitution of $583,955, which represented her\n\ntotal losses minus the amount of restitution already received from other defendants.\n\n\n 48\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 49 of 67\n\n\nSee Dunn, 777 F.3d at 1174, 1179. Because Dunn was a distributor of the images,\n\nthe district court determined that “he should be held jointly and severally liable for\n\nthe entirety of [the victim’s] injuries.” Id. at 1179. The victim’s total losses were\n\n$1,330,015, and the district court held Dunn responsible for $583,955 of those total\n\nlosses as the amount not yet paid. See id. at 1181.\n\n In reversing, the Tenth Circuit emphasized that the district court held the\n\ndefendant Dunn liable for all of the victim’s unpaid losses, including those caused\n\nby the initial abuser, and erred by not assessing Dunn’s individual relative role in\n\nthe causal process underlying the victim’s losses. See id. at 1181. The Tenth\n\nCircuit concluded: “[T]o the extent that the district court relied on an expert report\n\nthat did not disaggregate [the harms caused by the original abuser], the district\n\ncourt’s adoption of $1.3 million as the total measure of damages cannot stand.” Id.\n\nat 1182.6 The disaggregation conclusion in Dunn must be read in the factual\n\ncontext of a reversal of a district court’s ruling that a defendant was jointly and\n\n\n\n\n 6\n Though it has not addressed whether district courts must disaggregate, the First Circuit\nhas held that a district court order comported with Paroline’s framework where it “excluded past\ncosts and based its award on an estimate of [the victim’s] future therapy costs, occasioned by\ndefendant’s conduct.” United States v. Rogers, 758 F.3d 37, 39 (1st Cir. 2014). The district\ncourt also “limited the losses to general losses from ‘continuing’ traffic” in the victim’s images\nand “distinguished the future therapy losses attributable to defendant from the harm resulting\nfrom other viewers and from [the victim’s] therapy needs relating to [the original abuser].” Id.\nThe First Circuit commented that the district court’s $3,150 restitution award “represent[ed] the\ncost of 18 therapy visits,” but the district court “noted that 50 visits would also have been a\nreasonable conclusion.” Id. The mere fact that this type of formal disaggregation is permissible\nunder Paroline, however, does not mean that it is required.\n 49\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 50 of 67\n\n\nseverally liable with all other defendants, including the abuser, for the entirety of\n\nthe victim’s $1,330,015 total losses, minus only what other defendants had already\n\npaid. We read Dunn as requiring disaggregation in that case because the defendant\n\nwas held jointly and severally liable with the abuser for the entirety of the losses;\n\nwe do not read Dunn as requiring disaggregation in each and every restitution case.\n\n Unlike Dunn’s recounting of the restitution facts, the Ninth Circuit’s\n\ndecision in Galan does not indicate the amounts of the victim’s losses or even the\n\nrestitution award at issue. Galan, 804 F.3d at 1288. Rather, Galan recounts only\n\nthese two facts: (1) the defendant Galan was not the victim’s original abuser, who\n\n“made images of his disgusting crimes against [the victim] over an extended\n\nperiod” of time; and (2) that abuse ended about 11 years before Galan possessed\n\nthe images. See id.\n\n In reversing, the Ninth Circuit went much further than the Tenth. The Ninth\n\nCircuit held “that in calculating the amount of restitution to be imposed upon a\n\ndefendant who was convicted of distribution or possession of child pornography,\n\nthe losses, including ongoing losses, caused by the original abuse of the victim\n\nshould be disaggregated from the losses caused by the ongoing distribution and\n\npossession of images of that original abuse, to the extent possible.” Id. at 1291.\n\nThe Ninth Circuit concluded “that Galan should not be required to pay for losses\n\ncaused by the original abuser’s actions.” Id. at 1290. The Ninth Circuit\n\n\n 50\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 51 of 67\n\n\ndetermined, in effect, that some type of calculation should be made between\n\noriginal abusers on the one hand and the distributors and possessors on the other.\n\nSee id. at 1288, 1290.\n\n Importantly, however, the Ninth Circuit cautioned that it “express[ed] no\n\nopinion about what portion of the victim’s ongoing loss should be attributable to an\n\noriginal abuser.” Id. at 1291. It also did not instruct how the disaggregation\n\ncalculation should be done, and it even added that “[i]f the ultimate apportionment\n\nis not scientifically precise, we can only say that precision is neither expected nor\n\nrequired.” Id.\n\nD. Our Analysis\n\n After careful review of Paroline, we conclude that a district court is not\n\nrequired to determine, calculate, or disaggregate the specific amount of loss caused\n\nby the original abuser-creator or distributor of child pornography before it can\n\ndecide the amount of the victim’s losses caused by the later defendant who\n\npossesses and views the images. Paroline requires no such disaggregation.\n\nCertainly, Paroline directed district courts to hold a defendant accountable only for\n\nhis own individual conduct and set a restitution “amount that comports with the\n\ndefendant’s relative role” in causing the victim’s general losses. See Paroline, 572\n\nU.S. at 454-55, 458-59, 134 S. Ct. at 1725, 1727. How a district court arrives at\n\nthat figure is largely up to the district court, so long as the number is a “reasonable\n\n\n 51\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 52 of 67\n\n\nand circumscribed award” that is “suited to the relative size” of the defendant’s\n\ncausal role in the entire chain of events that caused the victim’s loss. Id. at 459,\n\n134 S. Ct. at 1727.\n\n In arriving at that figure, Paroline does require some consideration by the\n\ndistrict court of whether the defendant possessor was also an abuser-creator or a\n\ndistributor. See id. Indeed, that is why Paroline includes among its list of relevant\n\nfactors “whether the defendant had any connection to the initial production of the\n\nimages,” and “whether the defendant reproduced or distributed images of the\n\nvictim.” Id. at 460, 134 S. Ct. at 1728. But those factors do not require that the\n\ndistrict court make fact findings about the amount of losses caused by different\n\ngroups of offenders.\n\n To be clear, the district court should ensure that its restitution order relates\n\nonly to the amount of harm and loss caused by the defendant possessor. But\n\nParoline also repeatedly stresses the flexibility and broad discretion district courts\n\nhave in arriving at such a reasonable restitution amount. See, e.g., id. at 459, 134\n\nS. Ct. at 1727-28 (“[A] court must assess as best it can from available evidence the\n\nsignificance of the individual defendant’s conduct in light of the broader causal\n\nprocess that produced the victim’s losses. This cannot be a precise mathematical\n\ninquiry and involves the use of discretion and sound judgment.”); id. at 459-60,\n\n134 S. Ct. at 1728 (“[I]t is neither necessary nor appropriate to prescribe a precise\n\n\n 52\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 53 of 67\n\n\nalgorithm for determining the proper restitution amount at this point in the law’s\n\ndevelopment. Doing so would unduly constrain the decisionmakers closest to the\n\nfacts of any given case.”); id. at 460, 134 S. Ct. at 1728 (“These factors need not be\n\nconverted into a rigid formula . . . . They should rather serve as rough guideposts\n\nfor determining an amount that fits the offense.”); id. at 462, 134 S. Ct. at 1729\n\n(stating, “the approach articulated above involves discretion and estimation,” and\n\n“courts can only do their best to apply the statute as written in a workable\n\nmanner”).\n\n Like the Eighth Circuit, we think it would be inconsistent with Paroline’s\n\nflexible, discretionary framework to require district courts to perform an initial,\n\nformal step of calculating and then separately assigning a total loss amount to the\n\ninitial abuser, then one to the distributors and possessors generally, and only then\n\none to the particular defendant possessor. Rather, even if a victim’s total loss\n\nestimate includes losses caused both by the original abuser-creator, the distributors,\n\nand other possessors, the district court need only indicate in some manner that it\n\nhas considered that the instant defendant is a possessor, and not the initial abuser or\n\na distributor, and has assigned restitution based solely on the defendant possessor’s\n\nparticular conduct and relative role in causing those losses. See id. at 458-62, 134\n\nS. Ct. at 1727-29.\n\n\n\n\n 53\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 54 of 67\n\n\n Here, the district court did exactly that. In its restitution order, the district\n\ncourt explicitly found up front that “there is no evidence with respect to any victim\n\nthat [Rothenberg] reproduced or distributed images of the victim or that he had [a]\n\nconnection to the initial production of the images.” The district court expressly\n\nstated that it had “taken these factors into consideration in assigning [Rothenberg]\n\na relative role as the proximate cause of these victims’ losses.” And in setting each\n\nindividual award, the district court reiterated that Rothenberg “neither created nor\n\ndistributed” the victim’s image. Under Paroline, that is enough. We therefore\n\nreject Rothenberg’s disaggregation argument.\n\n Before concluding, we recognize that the Supreme Court in Paroline did\n\nnote in dicta that “[c]omplications may arise in disaggregating losses sustained as a\n\nresult of the initial physical abuse, but those questions may be set aside for present\n\npurposes.” Id. at 449, 134 S. Ct. at 1722. We do not read this dicta, which is\n\ncontained in a parenthetical, as requiring in any way that the district courts in\n\npossessor cases take on the job of determining the harm and loss caused by the\n\ninitial abuser or the distributors. 7 Rather, the district court’s job is to determine the\n\n\n\n 7\n We acknowledge that the Ninth Circuit concluded that the set-aside statement in this\nparenthetical meant the Supreme Court “plainly perceived a need for separation” of losses from\nthe initial abuser and the later possessor defendants. Galan, 804 F.3d at 1290. However, we read\nthe dicta in this parenthetical sentence not in isolation, but in the context surrounding it, which to\nus signals that in possessor cases a court is not required to delve into the special losses caused by\nthe original abuser. Rather, in possessor cases, the court is examining only the general losses\ncaused by the continuing traffic in the pornographic images and awarding restitution that\n 54\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 55 of 67\n\n\ndefendant possessor’s causal role in the general losses caused by his participation\n\nin the ongoing traffic in the victim’s images.\n\n We likewise reject Rothenberg’s argument that the district court erred in\n\ncreating restitution disparities between himself and other possessors by\n\n“impos[ing] restitution in amounts substantially above the average [for other\n\npossessors] without providing any explanation at all.” We recognize that the\n\nSupreme Court in Paroline listed as a factor “the number of past criminal\n\ndefendants found to have contributed to the victim’s general losses” and noted that\n\nthe government “could also inform district courts of restitution sought and ordered\n\nin other cases.” See id. at 460, 462, 134 S. Ct. at 1728-29. However, the Supreme\n\nCourt did not require district courts to dive into the facts of every past order and\n\nposition their restitution findings in relation to those of other courts. See id. The\n\ndistrict court is not required to say why it did not follow or disagreed with\n\nrestitution orders as to the same victim imposed by other courts. Paroline requires\n\nno such fact findings or analysis. Rather, the number of past criminal defendants\n\nand their restitution amounts, even as to the same victim, are just one of many\n\n\n\n\ncomports with the defendant possessor’s relative role as a possessor. In our view, nothing in\nParoline requires disaggregation, and everything in Paroline suggests otherwise.\n 55\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 56 of 67\n\n\nfactors the district court considers generally without having to make mathematical\n\ncalculations. 8 See id.\n\n VIII. SUFFICIENCY OF THE EVIDENCE\n\nA. McGarity\n\n Rothenberg’s next argument concerns victims Sierra, Jane, Sarah, Vicky,\n\nAmy, and Casseaopeia. 9 As to these six victims, Rothenberg argues that the\n\ndistrict court erred in relying on loss estimates that were based on psychological\n\nevaluations conducted before his arrest and thus before these victims learned of his\n\ncriminal possession offense, citing this Court’s prior precedent in United States v.\n\nMcGarity, 669 F.3d 1218 (11th Cir. 2012). The government responds that the\n\nportion of McGarity on which Rothenberg relies was overruled by Paroline.\n\n In McGarity, which was decided prior to Paroline, this Court concluded that\n\na psychological evaluation performed before the defendant’s arrest and prosecution\n\ncould not show the harm to the victim. 669 F.3d at 1269. More specifically, for\n\nproximate cause to exist in a child pornography case, “there must be a causal\n\nconnection between the actions of the end-user and the harm suffered by the\n\n 8\n In this case, the government’s submission and calculations used the 1/n method, but only\nas a starting point for the district court’s exercise of discretion and then application of the\nParoline factors. While we affirm the thorough and multifactored process used in this case, we\ncaution that the application of a strict 1/n approach, in which the only thing the district court does\nis divide the total loss amount by the total number of defendants who have been ordered to pay\nrestitution, ordinarily will not meet the individualized assessment requirement of Paroline.\n 9\n On appeal, Rothenberg does not challenge the evidentiary basis for victim Pia’s $5,000\nrestitution award.\n 56\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 57 of 67\n\n\nvictim.” Id. The McGarity Court determined that, in that case, the government\n\nfailed to provide any basis for determining “whether [the defendant’s] possession\n\nof child pornography proximately caused any of [the victim’s] harm,” given the\n\nvictim’s psychological evaluation occurred before the defendant’s arrest and\n\nprosecution. Id.\n\n As such, the McGarity Court determined that the psychological evaluation\n\ncould not show the harm caused to the victim by the particular defendant’s conduct\n\nin that case. Id. at 1269-70 (citing with approval the Second Circuit’s decision in\n\nUnited States v. Aumais, 656 F.3d 147, 154 (2d Cir. 2011), that remarked that the\n\nvictim’s psychological evaluation preceded the defendant’s arrest, and thus it could\n\nnot demonstrate the impact on the victim caused by that defendant). In other\n\nwords, the McGarity Court concluded that to establish proximate cause, the\n\ngovernment must show that the victim actually learned of the particular\n\ndefendant’s possession of her images. See id. at 1269-70.\n\n We agree with the government that this aspect of McGarity was abrogated\n\nby Paroline. See United States v. Archer, 531 F.3d 1347, 1352 (11th Cir. 2008)\n\n(“[A] prior panel’s holding is binding on all subsequent panels unless and until it is\n\noverruled or undermined to the point of abrogation by the Supreme Court or by\n\nthis court sitting en banc.”). In requiring to show harm that the victim was aware\n\nof a particular defendant’s conduct, the McGarity Court essentially required that\n\n\n 57\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 58 of 67\n\n\nthe government establish a direct, but-for causal link between some portion of the\n\nvictim’s losses and the specific defendant’s offense. See McGarity, 669 F.3d at\n\n1269-70. As discussed above, however, Paroline rejected exactly that sort of direct\n\nor but-for causation requirement in setting out its new standard. See Paroline, 572\n\nU.S. at 450-59, 134 S. Ct. at 1722-28. In Paroline, the Supreme Court recognized\n\nthat “it is not possible to prove that [a victim’s] losses would be less (and by how\n\nmuch) but for one possessor’s individual role in the large, loosely connected\n\nnetwork through which her images circulate,” nor is there “a practical way to\n\nisolate some subset of the victim’s general losses that [the defendant’s] conduct\n\nalone would have been sufficient to cause.” Id. at 450-51, 134 S. Ct. at 1723.\n\nNevertheless, the Supreme Court explained that “it is indisputable that [the\n\ndefendant] was a part of the overall phenomenon that caused [the victim’s] general\n\nlosses.” Id. at 457, 134 S. Ct. at 1726.\n\n In Paroline, the Supreme Court thus held that, “[i]n this special context”\n\nwhere it is clear both that the defendant possessed images of the victim and that the\n\nvictim has outstanding losses as a result of the traffic in her images, “but where it\n\nis impossible to trace a particular amount of those losses to the individual\n\ndefendant,” courts should order restitution “in an amount that comports with the\n\ndefendant’s relative role in the causal process that underlies the victim’s general\n\nlosses.” Id. at 458, 134 S. Ct. at 1727. The Supreme Court held that the\n\n\n 58\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 59 of 67\n\n\ngovernment need not establish that some specific portion of the victim’s losses\n\nwere directly caused by the defendant possessor’s conduct, as McGarity had\n\nrequired. See id.; McGarity, 669 F.3d at 1269. Rather, the government need\n\nestablish only that the victim suffered losses from the traffic in her images and that\n\nthe defendant contributed to those losses by possessing her images, regardless of\n\nwhether the victim was specifically aware of the defendant’s conduct. Paroline,\n\n572 U.S. at 458, 134 S. Ct. at 1727; see also id. at 442, 450, 134 S. Ct at 1718,\n\n1723 (noting that the parties “stipulated that the victim did not know who Paroline\n\nwas and that none of her claimed losses flowed from any specific knowledge about\n\nhim or his offense conduct,” and the victim therefore could not show her losses\n\n“would have been any different but for Paroline’s offense”).\n\n We therefore conclude that the portion of McGarity’s holding requiring the\n\ngovernment to show that a child pornography victim was aware of, and specifically\n\nharmed by, a particular defendant possessor’s conduct was abrogated by Paroline.\n\nSee Archer, 531 F.3d at 1352. Consequently, Rothenberg’s challenge to the\n\nrestitution awards for six victims—Sierra, Jane, Sarah, Vicky, Amy, and\n\nCasseaopeia—based on that portion of McGarity fails. 10\n\n\n\n 10\n The government asserts that Rothenberg did not specifically raise this before-my-arrest\nargument in the district court, and it should be reviewed only for plain error. We need not decide\nthat issue; regardless of the standard of review, this claim fails because Paroline overruled this\npart of McGarity and Paroline was decided before Rothenberg’s offense.\n\n 59\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 60 of 67\n\n\nB. Mya and Jenny\n\n Next, as to victims Mya and Jenny, Rothenberg argues the government\n\nfailed to submit reliable or sufficient evidence of their losses because neither of\n\nthose victims had psychological or economic reports detailing their losses. In\n\nopposition, the government asserts that it need not submit expert reports to\n\nestablish a victim’s losses and that the evidence presented in support of Mya’s and\n\nJenny’s restitution requests provided a sufficient basis for the district court’s\n\nawards. 11\n\n The government bears the burden of proving the restitution amount by a\n\npreponderance of the evidence. Osman, 853 F.3d at 1189. The government must\n\ndo so “with evidence bearing sufficient indicia of reliability to support its probable\n\naccuracy.” Id. (internal quotation marks omitted). Nevertheless, because “the\n\ndetermination of the restitution amount is by nature an inexact science,” a district\n\ncourt “may accept a reasonable estimate of the loss based on the evidence\n\npresented.” Id. (internal quotation marks omitted).\n\n\n\n\n 11\n We disagree with the government’s contention that Rothenberg did not preserve his\nchallenge to Mya’s and Jenny’s restitution awards on the ground that they were not supported by\ncompetent evidence. Accordingly, we review the factual findings underlying the district court’s\nrestitution orders as to Mya and Jenny for clear error, Osman, 853 F.3d at 1188, and the amount\nof their restitution awards for an abuse of discretion, see Robertson, 493 F.3d at 1330; see also\nParoline, 572 U.S. at 462, 134 S. Ct at 1729 (recognizing that “[d]istrict courts routinely exercise\nwide discretion . . . in fashioning restitution orders”).\n 60\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 61 of 67\n\n\n 1. Mya\n\n Regarding Mya, the district court did not clearly err in determining that\n\nsufficient evidence supported Mya’s restitution request. One of Mya’s counsel,\n\nCarol Hepburn, submitted a signed declaration stating Mya needed therapy and/or\n\nmedical care. Rothenberg faults the district court for accepting the “self-serving”\n\nestimate provided by Mya’s counsel that Mya’s future medical costs would likely\n\nexceed $100,000. In her declaration, Hepburn explained that the $100,000\n\nestimate was not just pulled out of thin air. Rather, it was based on Hepburn’s\n\nexperience representing eight other, similarly situated child pornography victims.\n\nIndeed, the restitution exhibits presented to the district court show that Hepburn\n\nrepresented or co-represented several of the other victims in this case—Sierra, Pia,\n\nSarah, and Vicky. Considering Hepburn’s demonstrated experience in this area, it\n\nwas not unreasonable for the district court to consider her estimate as reliable\n\nevidence of Mya’s likely future costs. See id.\n\n Furthermore, counsel Hepburn explained that Mya was part of the same\n\nchild pornography series as Pia. Though a psychological evaluation was\n\nunavailable for Mya at the time of the restitution hearing, 12 her co-victim Pia was\n\n\n\n 12\n In challenging Mya’s and Jenny’s awards, Rothenberg also argues that a victim must\nalways supply an expert medical or psychological report to support her restitution request.\nRothenberg cites no caselaw for this proposition, and nothing in either Paroline or our own\nprecedent establishes such a rigid requirement. See Osman, 853 F.3d at 1189 (requiring only\nthat the government present evidence “bearing sufficient indicia of reliability”). Though such\n 61\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 62 of 67\n\n\nable to submit a preliminary evaluation. That evaluation indicated that, at a bare\n\nminimum, Pia had estimated therapy costs of $81,900 and emphasized that this\n\nestimate reflected “only the current, most critical needs” for Pia, who like Mya was\n\nstill a minor, and did not account for the full extent of her losses or the services she\n\nwould require over the course of her lifetime. And notably, Rothenberg does not\n\nchallenge the evidentiary basis for Pia’s restitution award in this case. That Mya’s\n\nco-victim Pia had preliminary estimated costs of at least $81,900 is a further\n\nindicator that counsel Hepburn’s $100,000 total cost estimate for Mya was\n\nreasonable and appropriately relied upon by the district court. See id. On this\n\nrecord, we are not left with a definite and firm conviction that the district court was\n\nmistaken in concluding that sufficient evidence supported Mya’s restitution\n\nrequest. See Robertson, 493 F.3d at 1330.\n\n Nor did the district court abuse its broad discretion in awarding Mya her\n\nrequested restitution amount of $5,000. See id. Here, the district court properly\n\nidentified Paroline as the correct legal standard for awarding restitution in child\n\npornography cases. In setting the amount of Mya’s restitution award, the district\n\ncourt addressed several relevant Paroline factors, noting that: (1) Rothenberg\n\npossessed one image of Mya; (2) no other defendant was yet ordered to pay\n\n\n\n\nexpert reports are undoubtedly helpful to district court’s in fashioning a restitution award, they\nare by no means the only way to establish a reasonable estimate of a victim’s losses.\n 62\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 63 of 67\n\n\nrestitution to Mya; (3) Mya had estimated losses exceeding $100,000; and\n\n(4) Rothenberg neither created nor distributed Mya’s images. Paroline, 572 U.S. at\n\n460, 134 S. Ct. at 1728. In light of these factors, the district court determined that\n\nMya’s $5,000 restitution request was reasonable. Given the wide discretion\n\nafforded by Paroline to district courts in this context, we cannot say this\n\ndetermination was unreasonable. See id. at 462, 134 S. Ct. at 1729; Jordan, 582\n\nF.3d at 1249.\n\n 2. Jenny\n\n Based on the more limited record as to Jenny, we agree with Rothenberg that\n\nthe district court clearly erred in determining there was sufficient evidence to\n\nsupport Jenny’s $42,600 request. In support of her restitution request, Jenny’s\n\ncounsel submitted a restitution cover letter and a victim impact statement from\n\nJenny. In the letter, Jenny’s counsel requested restitution in the following\n\namounts: (1) $12,500 to pay for psychological and economic reports; (2) $5,000 in\n\nattorney’s fees related to her request in this case; (3) $100 in legal fees related to\n\nher request in this case; and (4) $25,000 for “the defendant’s appropriate share of\n\nthe general losses caused to Jenny.”\n\n Like Mya, at the time of the restitution hearing, Jenny was still in the\n\nprocess of obtaining expert reports documenting her total losses. Unlike Mya,\n\nhowever, Jenny’s separate counsel did not provide any reasonable estimate of what\n\n\n 63\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 64 of 67\n\n\nthose total losses might be. Indeed, counsel did not provide any estimate of what\n\nJenny’s total losses might be. Rather, in asserting that $25,000 was Rothenberg’s\n\n“appropriate share” of Jenny’s losses, counsel relied on (1) a proposed statute that\n\nwould set a minimum restitution award of $25,000 for possession of child\n\npornography, and (2) Masha’s law, 18 U.S.C. § 2255(a), which creates a civil\n\ncause of action for victims who suffered personal injury as a result of a child\n\npornography offense and sets a liquidated damages amount of $150,000.\n\n This evidence is sufficient to show that Jenny has incurred costs of\n\n$17,600—to pay for expert reports and legal fees—in connection with her\n\nrestitution request in this case, 13 yet it is not sufficient to establish what proportion\n\nof Jenny’s as-yet-undetermined total losses Rothenberg proximately caused.\n\nJenny’s counsel suggested that the $150,000 liquidated damages amount in\n\nMasha’s Law represents a reasonable estimate by Congress of the minimum\n\namount of total damages suffered by a child pornography victim. But the damages\n\navailable to a plaintiff in a civil lawsuit may be quite different from the concrete\n\n“costs incurred” for which § 2259 provides recompense. See 18 U.S.C.\n\n§ 2259(c)(2). For example, a plaintiff in a civil damages suit under § 2255(a) may\n\nbe able to recover for noneconomic losses, such as pain and suffering or mental\n\n\n 13\n We note that the $12,500 portion of those costs for psychological and economic reports\nwould not necessarily be fully attributable to Rothenberg, as Jenny will, unfortunately but\nundoubtedly, need to use those reports in support of future requests against other defendants.\n 64\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 65 of 67\n\n\nand emotional distress, that are not available in a restitution proceeding under\n\n§ 2259. See Doe v. Hesketh, 828 F.3d 159, 170 (3d Cir. 2016). As such, we do\n\nnot see that Masha’s Law provides much guidance in the present context.\n\n Similarly, Jenny’s counsel’s reliance on proposed legislation setting a\n\nminimum $25,000 restitution award for child pornography possession offenses also\n\nprovides little to no guidance here. While Congress certainly would be well within\n\nits rights to establish such a mandatory minimum restitution amount in these cases,\n\nit had not done so at the time of Rothenberg’s restitution hearing. 14 Thus, the\n\ndistrict court was required to instead follow Paroline’s framework, which requires\n\nan individualized assessment of each particular defendant’s restitutionary liability\n\nbased on his conduct and relative role in the causal process. Paroline, 572 U.S. at\n\n445, 458-59, 462, 134 S. Ct. at 1720, 1727-29. Imposing a pre-set minimum\n\namount of restitution based solely on the type of offense Rothenberg committed\n\ndoes not comply with Paroline’s framework, and the government did not submit\n\nevidence from which the district court reasonably could have determined that\n\n$25,000 was Rothenberg’s relative share of Jenny’s losses.\n\n\n\n\n 14\n Congress recently passed, and the president signed, a different version of the bill\nJenny’s counsel referred to, but that version sets the minimum restitution amount much lower, at\n$3,000. See Amy, Vicky, and Andy Child Pornography Victim Assistance Act of 2018, Pub. L.\nNo. 115-299, 132 Stat. 4383 (2018).\n\n 65\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 66 of 67\n\n\n It is indisputable that Jenny has suffered some, likely large amount of losses\n\nfrom the online traffic in her images. See id. at 457, 134 S. Ct. at 1726. It is also\n\nindisputable that Rothenberg, who possessed 34 images and 1 video of Jenny, is\n\nresponsible for some, possibly significant amount of those losses. Id. But the\n\ngovernment bears the burden of proving at least a reasonable estimate of that\n\namount based on reliable evidence, and it has not satisfied that burden here.\n\nOsman, 853 F.3d at 1189. In the absence of competent evidence to support the\n\naward, the district court clearly erred in ordering Rothenberg to pay $42,600 in\n\nrestitution to Jenny. See id.\n\n We therefore vacate the district court’s restitution award as to Jenny and\n\nremand for further proceedings consistent with this opinion. On remand, the\n\ndistrict court should allow Jenny to supplement her restitution request with\n\nevidence of her losses. See 18 U.S.C. § 3664(d)(5) (allowing a victim to seek an\n\namended restitution order if the victim discovers additional losses after\n\nsentencing). The district court should then determine, in light of all the available\n\nevidence and the Paroline factors, the portion of Jenny’s losses for which\n\nRothenberg is responsible. Paroline, 572 U.S. at 458-60, 134 S. Ct. at 1727-28.\n\n\n\n\n 66\n\f Case: 17-12349 Date Filed: 05/08/2019 Page: 67 of 67\n\n\n IX. CONCLUSION\n\n For the foregoing reasons, we affirm the district court’s restitution order as\n\nto victims Sierra, Jane, Pia, Mya, Sarah, Vicky, Amy, and Casseaopeia, and vacate\n\nand remand the district court’s restitution order as to victim Jenny.\n\n AFFIRMED in part; VACATED and REMANDED in part.\n\n\n\n\n 67\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. David ROTHENBERG, Defendant-Appellant.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-08\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-12349 Date Filed: 05/08/2019 Page: 1 of 67\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-12349\\n ________________________\\n\\n D.C. Docket No. 0:16-cr-60054-WJZ-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\n versus\\n\\nDAVID ROTHENBERG,\\n\\n Defendant-Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 8, 2019)\\n\\nBefore ED CARNES, Chief Judge, and ROSENBAUM and HULL, Circuit Judges.\\n\\nHULL, Circuit Judge:\\n\\n After his guilty plea to possession of child pornography, David Rothenberg\\n\\nappeals from the district court’s restitution order requiring him to pay a total of\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 2 of 67\\n\\n\\n$142,600 in restitution to nine victims depicted in the images of child pornography\\n\\nthat he possessed. Section 2259 mandates that district courts order defendants “to\\n\\npay the victim . . . the full amount of the victim’s losses” as determined by the\\n\\ncourt. 18 U.S.C. § 2259. This case involves the question of how to calculate the\\n\\namount of restitution a possessor of child pornography, like the defendant\\n\\nRothenberg, must pay to a victim whose childhood sexual abuse appears in the\\n\\npornographic images he possessed but did not create or distribute.\\n\\n On appeal, Rothenberg argues that: (1) the district court’s restitution order is\\n\\nflawed as to all of the victims because it failed to calculate and then disaggregate\\n\\nthe victim’s losses caused by the initial abuser, distributors, and other possessors\\n\\nfrom those caused by Rothenberg himself; and (2) as to eight of the victims, the\\n\\nrestitution award is not supported by competent evidence. After review, and with\\n\\nthe benefit of oral argument, we conclude that the district court was not required to\\n\\ncalculate and disaggregate the victim’s losses in the manner Rothenberg suggests\\n\\nand that reliable evidence supports the restitution awards as to eight victims, but\\n\\nnot as to one victim. We thus affirm the restitution amounts as to eight victims and\\n\\nvacate and remand as to one victim.\\n\\n I. INDICTMENT AND GUILTY PLEA\\n\\n Defendant Rothenberg used to be a lawyer, a fact he told an undercover\\n\\nofficer in an internet chatroom called “daddaughtersex.” Rothenberg also sent the\\n\\n\\n 2\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 3 of 67\\n\\n\\nofficer videos of child pornography and bragged that he was sexually exploiting a\\n\\nyoung girl at his house. In 2016, local and federal law enforcement went to\\n\\nRothenberg’s house and rescued the young girl, who confirmed that Rothenberg\\n\\nhad engaged in sexual activity with her. The officers also found and seized\\n\\nRothenberg’s laptop, which contained approximately 1,000 unique video and\\n\\npicture files of child pornography. Some of those images depicted prepubescent\\n\\nchildren under the age of 12, and some portrayed sadistic and masochistic conduct,\\n\\nsuch as the binding and gagging of minor children.\\n\\n In 2016, a grand jury charged Rothenberg with: (1) four counts of\\n\\ndistribution of child pornography, in violation of 18 U.S.C. § 2252(a)(2) & (b)(1)\\n\\n(Counts 1, 3, 4, and 5); (2) one count of receipt of child pornography, in violation\\n\\nof 18 U.S.C. § 2252(a)(2) & (b)(1) (Count 2); and (3) one count of possession of\\n\\nchild pornography depicting a minor under the age of 12, in violation of 18 U.S.C.\\n\\n§ 2252(a)(4)(B) & (b)(2) (Count 6). Pursuant to a written plea agreement,\\n\\nRothenberg pled guilty to the possession offense in Count 6, and the government\\n\\nagreed to dismiss the receipt and distribution charges in Counts 1 through 5. The\\n\\ndistrict court sentenced Rothenberg to 210 months’ imprisonment.\\n\\n On appeal, Rothenberg does not challenge his guilty plea or sentence.\\n\\nRather, Rothenberg challenges only the district court’s restitution order granting a\\n\\ntotal of $142,600 to nine victims, which consists of: (1) $10,000 to Sierra;\\n\\n\\n 3\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 4 of 67\\n\\n\\n(2) $3,000 to Jane; (3) $5,000 to Pia; (4) $5,000 to Mya; (5) $20,000 to Sarah;\\n\\n(6) $9,000 to Vicky; (7) $23,000 to Amy; (8) $42,600 to Jenny; and (9) $25,000 to\\n\\nCasseaopeia. We outline the thorough process the district court followed, the\\n\\nevidence submitted, and then the district court’s findings and conclusions.\\n\\n II. RESTITUTION PROCEEDINGS\\n\\n After sentencing, the district court considered restitution requests pursuant to\\n\\n18 U.S.C. § 2259(a), which provides for mandatory restitution to child\\n\\npornography victims. Generally, the process worked as follows. First, the\\n\\ngovernment identified the individual victims depicted in the images of child\\n\\npornography found on Rothenberg’s computer and notified them or their attorneys\\n\\nof the upcoming restitution hearing. Then a victim’s attorney submitted a\\n\\nrestitution request and supporting documentation to the government. Next, the\\n\\ngovernment determined whether to support that request or ask the district court for\\n\\na different amount. Rothenberg could agree to the request, try to negotiate down\\n\\nwith the government or the victim’s attorney, or challenge the request before the\\n\\ndistrict court.\\n\\n Eventually the government submitted restitution requests on behalf of ten\\n\\nvictims, all of whom were identified in at least one of the images of child\\n\\npornography from Rothenberg’s computer. One of the victims, “Angela,” later\\n\\nwithdrew her request, leaving nine requests at issue for the hearing.\\n\\n\\n 4\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 5 of 67\\n\\n\\nA. Pre-Hearing Memoranda\\n\\n Prior to the restitution hearing, both parties submitted lengthy memoranda\\n\\naddressing (1) how the restitution determination should be made, and (2) what the\\n\\naward should be for each victim. The government and Rothenberg agreed that the\\n\\nSupreme Court’s decision in Paroline v. United States, 572 U.S. 434, 134 S. Ct.\\n\\n1710 (2014), governed how the restitution awards should be made, established a\\n\\nproximate cause requirement, and set forth a variety of factors for district courts to\\n\\nconsider in determining the proper amount of restitution. Under Paroline’s\\n\\nproximate causation requirement, a defendant should pay restitution “in an amount\\n\\nthat comports with the defendant’s relative role in the causal process that underlies\\n\\nthe victim’s general losses.” Paroline, 572 U.S. at 458, 134 S. Ct. at 1727.\\n\\n But the parties disagreed about how exactly to apply the Paroline factors and\\n\\nhow to calculate and determine that amount. The government recognized that,\\n\\nunder Paroline, the district court must impose restitution in an amount that reflects\\n\\nthe particular defendant’s relative role in the continuing traffic in the child\\n\\npornography images of the victim. The government proposed that the district court\\n\\nmake that calculation by using a variation of what is known as the “1/n method,”\\n\\nwhereby the court would divide the total amount of each victim’s losses by the\\n\\nnumber of defendants, across multiple prosecutions, who had been ordered to pay\\n\\nrestitution to the victim. The government submitted that this method would\\n\\n\\n 5\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 6 of 67\\n\\n\\nprovide the district court a starting point from which to exercise its discretion in\\n\\ndetermining the appropriate amount of restitution vis-à-vis Rothenberg, as only a\\n\\npossessor of images of child pornography.\\n\\n Rothenberg argued, by contrast, that the starting point should be\\n\\n“apportionment between the original abuser of the child, versus the distributor, and\\n\\nlater, possessor of the pornography,” which Rothenberg referred to as\\n\\n“disaggregation.” Rothenberg asserted that this disaggregation requires two steps:\\n\\nfirst, the district court must separate the harm caused by the original abuser from\\n\\nthat caused by later distributors and possessors; and second, the district court must\\n\\nseparate the harm caused by the defendant from that caused by other distributors or\\n\\npossessors.\\n\\n Below, we detail for each victim (1) the victim’s restitution request and\\n\\nsupporting evidence, (2) the government’s position, and then (3) Rothenberg’s\\n\\nposition.\\n\\nB. Sierra\\n\\n Sierra submitted a restitution request for $10,000. In support of her request,\\n\\nSierra submitted a medical letter from Dr. Sharon W. Cooper, a forensic\\n\\npediatrician, based on her December 2015 evaluation of Sierra. Dr. Cooper\\n\\nexplained that victims of child pornography can experience physical, emotional,\\n\\nand spiritual issues as a result of their online exploitation, including immunological\\n\\n\\n 6\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 7 of 67\\n\\n\\nproblems, posttraumatic stress disorder (“PTSD”), anxiety, depression, suicidal\\n\\nideation, and feelings of hopelessness. Dr. Cooper noted that “[w]hen images are\\n\\nknown to be in distribution, the pre-existing dysfunction caused by the initial abuse\\n\\nis typically worsened, since children remain at risk for further victimization by the\\n\\nongoing downloading, trading and possession of their images.”\\n\\n With respect to Sierra specifically, Dr. Cooper stated that Sierra’s medical\\n\\nevaluation showed she suffered from worsening insomnia, attention deficit\\n\\nhyperactivity disorder (“ADHD”), depression, suicidal ideation, PTSD, and mood\\n\\nlability. Dr. Cooper noted that, despite being on five different medications,\\n\\nSierra’s condition remained unstable and she recently required emergency\\n\\ntreatment for suicidality. Dr. Cooper opined that “[t]he ongoing presence of\\n\\ntrafficking in images [of Sierra] on the Internet constitutes a significant aspect of\\n\\npsychological maltreatment that will add on to the initial adversities” caused by the\\n\\noriginal abuse. Based on Sierra’s past medical history, the documented adversities\\n\\nfaced by victims of child sexual abuse and child pornography offenses, and\\n\\nSierra’s present medical symptoms, Dr. Cooper estimated a total cost of\\n\\n$661,453.00 for Sierra’s future medical care.\\n\\n Sierra’s counsel also submitted a declaration of attorney’s fees, indicating\\n\\nSierra had incurred nearly $5,000 in attorney’s fees in connection with this case.\\n\\n\\n\\n\\n 7\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 8 of 67\\n\\n\\n The government supported Sierra’s $10,000 restitution request. The\\n\\ngovernment observed that four other defendants had been ordered to pay restitution\\n\\nto victims in the same series of images as Sierra. Those awards were for $4,000,\\n\\n$1,000, $9,000, and $2,000.\\n\\n Rothenberg opposed Sierra’s restitution request. Rothenberg noted that he\\n\\npossessed only one image of Sierra1 and that the requested restitution amount was\\n\\nmore than double the average of Sierra’s prior awards ($4,000). Rothenberg\\n\\nargued that Sierra’s restitution materials made no attempt at disaggregation and\\n\\nthat the government provided no information to demonstrate the relative amount of\\n\\nSierra’s harm caused by his conduct.\\n\\nC. Jane\\n\\n Jane submitted a restitution request for $3,000. In support of her request,\\n\\nJane submitted a victim impact statement, a psychological report, and an economic\\n\\nreport. In her victim impact statement, Jane specifically described how the online\\n\\ntrade in her child pornography images had affected and would continue to affect\\n\\nher. Jane explained: “Knowing people are watching what happened gives me a\\n\\nmix of anxiety, sadness, anger and it disgusts me. . . . If it wasn’t out there, I\\n\\nwouldn’t be as fearful as I am now.” Jane elaborated that the circulation of her\\n\\n\\n 1\\n Throughout we refer to how many images of a victim Rothenberg had. Each of the\\nimages recounted in this case were child pornography, and for brevity sometimes we refer to\\nthem simply as “images.”\\n 8\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 9 of 67\\n\\n\\nimages made her feel afraid and unsafe because she worried that someone who had\\n\\nseen her images online might recognize her and try to harm her. Jane felt that her\\n\\nfuture would not be “very bright” and would be lonely because the existence of her\\n\\nimages online made her socially isolated.\\n\\n Jane’s psychological evaluation was performed by Dr. Jennifer Clark in\\n\\nDecember 2014 “to determine the psychological effects of her continuous re-\\n\\nvictimization in the form of Internet pornographic images and videos of her being\\n\\nexchanged and viewed.” Dr. Clark opined that the online trade in Jane’s images\\n\\nwas currently impacting her, causing her great fear and anxiety and leaving her\\n\\nfeeling unsafe and vulnerable. Dr. Clark observed that the trade in Jane’s images\\n\\nwould continue to impact her in the future by exacerbating her “deep sense of\\n\\nmistrust in others” from the original abuse and hindering her healing and recovery\\n\\nprocess. Dr. Clark explained: “[Jane’s] awareness of the ongoing presence and\\n\\ndistribution of [her] images will remain an ever present trigger to memories of\\n\\nwhat happened and a source of fear for her safety, and thus, ongoing psychological\\n\\ndistress. Therefore, Jane will require therapy throughout her life. . . . Given that\\n\\nmuch of Jane’s distress manifests in somatic symptoms and physiological distress,\\n\\nshe likely will also seek and need significant medical attention in the future.”\\n\\n\\n\\n\\n 9\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 10 of 67\\n\\n\\n Jane’s economic evaluation estimated that she would have future medical\\n\\nand therapy costs of $101,027, and lost wages of between approximately $1.9 and\\n\\n$3.9 million.\\n\\n The government agreed that Jane’s $3,000 restitution request was\\n\\nappropriate. The government noted that seven other defendants had been ordered\\n\\nto pay restitution to Jane. Three of those seven defendants were ordered to pay\\n\\n$1,000, two were ordered to pay $2,500, one was ordered to pay $3,000, and one\\n\\nwas ordered to pay $500.\\n\\n Rothenberg disputed Jane’s requested amount and argued that a restitution\\n\\namount of $800 would be appropriate. Rothenberg noted that he possessed four\\n\\nimages of Jane and that the average award to Jane from the prior cases was $1,642.\\n\\nRothenberg acknowledged that Jane’s restitution materials were “the best of all\\n\\nprovided to attempt disaggregation,” but argued his possession did not warrant a\\n\\n$3,000 award when compared with other defendants. Specifically, Rothenberg\\n\\nnoted that one of the prior cases with a $1,000 restitution order involved\\n\\ndistribution, and three of the other cases involved receipt of Jane’s images.\\n\\nD. Pia\\n\\n Pia submitted a restitution request for $5,000. In support of her request, Pia\\n\\nsubmitted an interim impact statement from Dr. Marsha Hedrick, who conducted a\\n\\nforensic psychological evaluation of Pia, a declaration of attorney’s fees, and a\\n\\n\\n 10\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 11 of 67\\n\\n\\nvictim impact statement from Pia’s mother. Dr. Hedrick noted that Pia\\n\\nexperienced anxiety, nightmares, suspiciousness, and sadness and was emotionally\\n\\nwithdrawn. Dr. Hedrick explained that “[s]eparating the extent to which these\\n\\ndifficulties are related to sexual abuse by her father versus her awareness that her\\n\\nsexual abuse is being viewed by others is not entirely possible,” but it was clear\\n\\ninternet exploitation adds a layer of complexity to the psychological damages\\n\\nvictims of child sexual abuse face. Indeed, Dr. Hedrick noted that Pia’s mother\\n\\nhad explained to Pia there was no way to remove from the internet the images of\\n\\nher sexual abuse, resulting in “a level of suspiciousness and concern about\\n\\nexploitation that is atypical for Pia’s peers” and likely caused Pia to experience\\n\\nfeelings of powerlessness. Dr. Hedrick estimated the cost of Pia’s therapy needs as\\n\\n$81,900, but explained that estimate reflected only the “current, most critical\\n\\nneeds” for Pia and there was no way to know what the full extent of her losses\\n\\nwould be over the course of her lifetime.\\n\\n The government concurred in Pia’s $5,000 restitution request. The\\n\\ngovernment did not have information on any other defendants that were ordered to\\n\\npay restitution to Pia, but Pia’s counsel advised one other defendant was ordered to\\n\\npay restitution.\\n\\n Rothenberg disputed Pia’s requested amount and instead proposed a\\n\\nrestitution award of $1,100. Rothenberg contended there was “no real attempt at\\n\\n\\n 11\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 12 of 67\\n\\n\\ndisaggregation” in Pia’s restitution documents, but agreed some amount of\\n\\nrestitution was appropriate based on the number of images (14) he possessed of\\n\\nPia. Rothenberg reasoned that $1,100 was appropriate because the government\\n\\nhad requested $2,000 in restitution for Jenny (discussed below), and he possessed\\n\\nhalf as many images of Pia as he had of Jenny.\\n\\nE. Mya\\n\\n Mya submitted a restitution request of $5,000. In support of her request,\\n\\nMya’s counsel submitted a restitution cover letter and declarations from both of\\n\\nher attorneys. Mya’s counsel represented that they were still awaiting the results\\n\\nof Mya’s psychological evaluation, but that other similarly situated child\\n\\npornography victims they had represented had psychological treatment costs\\n\\nexceeding $100,000. Mya’s counsel stated that Mya was aware of the existence of\\n\\nher images on the internet and “the knowledge that others have witnessed and even\\n\\nenjoyed [her] abuse is extremely upsetting to [her].” Counsel further represented\\n\\nthat Mya was distrustful of other people and was at risk of being stalked or\\n\\nvictimized by individuals who had seen her images online. Counsel also\\n\\nrepresented that they had expended $2,077.44 thus far in representing Mya and two\\n\\nother victims in the same series (one of whom was victim Pia, discussed above),\\n\\nand anticipated total legal costs of $30,000 for those three victims.\\n\\n\\n\\n\\n 12\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 13 of 67\\n\\n\\n The government did not concur in Mya’s $5,000 restitution request. The\\n\\ngovernment noted that there was no information on whether other defendants were\\n\\nordered to pay restitution to Mya and determined that “[g]iven that [Rothenberg]\\n\\npossessed a single image of Mya and the future medical costs have not yet been\\n\\nestablished,” a restitution award of $500 was appropriate. The government stated\\n\\nthat amount was neither trivial nor too severe.\\n\\n Rothenberg argued there was no sufficient basis for awarding any restitution\\n\\nto Mya given the lack of information regarding her future medical costs.\\n\\nRothenberg also noted that he made an offer to Mya’s counsel to pay the $500\\n\\namount the government sought, but that offer was rejected.\\n\\nF. Sarah\\n\\n Sarah submitted a restitution request of $25,000. In support of her request,\\n\\nSarah submitted, among other things, a cover letter, a victim impact statement, a\\n\\n2014 psychological evaluation by Dr. Randall Green, and an economic report. In\\n\\nthe cover letter, Sarah’s counsel represented that her requested restitution amount\\n\\nof $25,000 would be “less than 1%” of her total losses and that 327 other\\n\\ndefendants were ordered to pay restitution to Sarah.\\n\\n In her victim impact statement, Sarah explained that she worried that people\\n\\nwho had seen her images online would “come after” her and try to victimize her in\\n\\nthe same way her original abuser had. Sarah elaborated: “Every time someone else\\n\\n\\n 13\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 14 of 67\\n\\n\\nsees pictures or videos of me it feels like they are the ones who hurt me to begin\\n\\nwith. . . . It is like I am just here for other people’s pleasure and am not a person\\n\\nmyself with my own wants and needs.” Sarah stated that her fear prevented her\\n\\nfrom leaving the house by herself and from engaging in other normal activities like\\n\\ngoing to school, having a job, or socializing with more than a few people.\\n\\n In his psychological evaluation, Dr. Green assessed “the impact and injuries\\n\\ncaused by the discovery and daily awareness that multiple individuals are viewing\\n\\nimages of sexual crimes being perpetrated against [Sarah] as a child.” As part of\\n\\nhis assessment, Dr. Green interviewed Sarah and also performed various\\n\\npsychological tests. Based on these sources of information, Dr. Green opined that\\n\\n“the discovery of multiple downloaders and distributors of her images effectively\\n\\nexponentially multiplied in [Sarah’s] mind the number of sick and dangerous males\\n\\n‘out there’ who might . . . do her harm.” Dr. Green explained that Sarah’s\\n\\nknowledge of the dissemination of her child pornography images online caused her\\n\\ndaily psychological damage in the form of fear “that has reached a paranoid-like\\n\\nlevel of intensity.” Dr. Green determined that Sarah required “extensive and\\n\\nintensive therapy” for the trauma caused by both the original abuse and the\\n\\ncontinuing traffic in her images. Dr. Green estimated the costs of Sarah’s future\\n\\npsychiatric care were between $265,710 and $303,150.\\n\\n\\n\\n\\n 14\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 15 of 67\\n\\n\\n Sarah’s counsel reported that Sarah had incurred $31,433.77 in attorney’s\\n\\nfees. The economic assessment for Sarah estimated a minimum of approximately\\n\\n$1.9 million in lost wages over her lifetime.\\n\\n The government did not concur in Sarah’s $25,000 restitution request and\\n\\ninstead requested an award of $7,895 based on its 1/n calculation method. The\\n\\ngovernment also provided a list of 155 prior restitution awards to Sarah, which\\n\\nranged from $0 at the low end to $51,500 at the high end.\\n\\n Rothenberg opposed Sarah’s restitution request. Rothenberg cited three\\n\\nother cases involving Sarah in which the government presented the same restitution\\n\\nevidence and the courts found the government failed to establish proximate cause.\\n\\nRothenberg argued that the government provided no evidence to disaggregate the\\n\\nharm proximately caused by his possession of six images of Sarah from that caused\\n\\nby the other defendants in the list it had provided.\\n\\nG. Vicky\\n\\n Vicky submitted a restitution request of $10,000. In support of her request,\\n\\nVicky submitted several victim impact statements, several psychological reports\\n\\nfrom Dr. Green, an economic report, and a statement of attorney’s fees. In her\\n\\nvictim impact statements, Vicky described the effects of the ongoing distribution\\n\\nof the images of her sexual abuse as a child, including feelings of fear and\\n\\nparanoia, nightmares, and panic attacks. In a 2014 psychological status report,\\n\\n\\n 15\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 16 of 67\\n\\n\\nDr. Green opined that Vicky continued to require therapy as a result of the\\n\\ncontinuing traffic in her images, as well as her discovery of attempts by some\\n\\nviewers of her images to invade her privacy. Dr. Green explained that Vicky\\n\\ncontinued to experience anxiety, dissociative responses, social withdrawal, anger,\\n\\nfeelings of powerlessness, and sleep disruption. Dr. Green estimated Vicky’s total\\n\\ntherapy costs to be between $108,975 to $113,600.\\n\\n The economic report estimated Vicky’s net lost wages over the course of her\\n\\nlifetime to be $828,150. Vicky’s counsel represented that Vicky had incurred\\n\\nattorney’s fees and costs of $92,371.96.\\n\\n The government did not concur in Vicky’s $10,000 request and instead\\n\\nrequested an award of $1,283 using its 1/n method. The government provided a\\n\\nlist of 659 other restitution awards to Vicky, which ranged from approximately $24\\n\\nat the low end to $1 million at the high end.\\n\\n Rothenberg opposed Vicky’s restitution request for the same reasons he\\n\\nopposed Sarah’s request, noting that other courts had denied restitution requests\\n\\nbased on the same evidence and that the government failed to disaggregate.\\n\\nRothenberg also noted that he possessed only one image of Vicky and that the\\n\\naverage post-Paroline restitution award to Vicky was $3,632.\\n\\n\\n\\n\\n 16\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 17 of 67\\n\\n\\nH. Amy\\n\\n Amy submitted a restitution request of $25,000. In support of her request,\\n\\nAmy provided a victim impact statement, several psychological evaluations from\\n\\nDr. Joyanna Silberg, and an economic report. In her victim impact statement, Amy\\n\\nstated that she “live[s] in constant fear that someone will see [her] pictures and\\n\\nrecognize [her].” Amy expressed feelings of powerlessness related to the traffic in\\n\\nthe images of her sexual abuse as a child because “the crime has never really\\n\\nstopped and will never really stop.” Amy explained that she experienced fear,\\n\\nshame, and humiliation at the thought of her friends and other people she\\n\\nencounters discovering her images online.\\n\\n In a December 2014 report, Dr. Silberg opined that although Amy had made\\n\\nstrides as a result of an intensive treatment plan initiated in 2012, ongoing issues\\n\\nrelated to PTSD remained. Dr. Silberg explained that Amy continued to\\n\\nexperience flashbacks and nightmares, as well as “fear about the internet and\\n\\nshame associated with the ongoing viewing of her picture.” Dr. Silberg concluded\\n\\nthat Amy “continues to suffer from the ongoing effects of her victimization from\\n\\nchild abuse and from the continued use of her image by child pornography traders,\\n\\nviewers, and abusers,” and recommended continued psychological treatment and\\n\\nmonitoring. Amy’s economic report estimated her net lost wages as $2,855,173,\\n\\nand her future counseling costs as $512,681.\\n\\n\\n 17\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 18 of 67\\n\\n\\n The government did not concur in Amy’s $25,000 request and instead\\n\\nrequested a restitution amount of $15,664 using its 1/n method. The government\\n\\nprovided a list of 215 other restitution awards to Amy, ranging from $50 at the low\\n\\nend to $3.5 million at the high end.\\n\\n Rothenberg opposed Amy’s restitution request. Rothenberg noted that he\\n\\npossessed only one image of Amy and that the average post-Paroline restitution\\n\\naward to her was $3,891. Rothenberg asserted that the government’s list of prior\\n\\nrestitution orders was inaccurate as to some of the awards and argued that the\\n\\ngovernment made no attempt to disaggregate his conduct from that of other\\n\\ndefendants.\\n\\nI. Jenny\\n\\n Jenny submitted a restitution request of $42,600. In support of her request,\\n\\nJenny submitted a victim impact statement and a cover letter from her counsel. In\\n\\nher victim impact statement, Jenny stated that she worried about the images of her\\n\\nsexual abuse that were “out there” and feared being recognized in public. Jenny\\n\\nexpressed a strong desire to forget the abuse she had suffered but explained that\\n\\n“[w]ith the pictures still out there I can’t.”\\n\\n In their cover letter, Jenny’s counsel represented that this was Jenny’s\\n\\nseventh restitution request. Counsel stated that they were still in the process of\\n\\nobtaining expert reports for Jenny, but asserted that “such formal reports” were not\\n\\n\\n 18\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 19 of 67\\n\\n\\nnecessary for the district court to determine restitution. Counsel discussed a\\n\\nproposed bill which would set a $25,000 minimum restitution award for child\\n\\npornography possession offenses, and represented that Jenny had costs of $5,100\\n\\nfor legal and attorney’s fees and $12,500 for the preparation of expert reports.\\n\\nBecause these three items totaled $42,600, Jenny’s counsel contended that $42,600\\n\\namount was the appropriate restitution amount for Jenny.\\n\\n The government did not concur in Jenny’s $42,600 restitution request and\\n\\ninstead requested a restitution award of $2,000. The government emphasized that\\n\\nRothenberg possessed 34 images and one video of Jenny but noted the lack of\\n\\ndocumentation to support Jenny’s restitution request. The government pointed out\\n\\nthat one other defendant was ordered to pay restitution to Jenny in the amount of\\n\\n$7,500.\\n\\n Rothenberg likewise noted the lack of evidence supporting Jenny’s $42,600\\n\\nrestitution request. Nevertheless, based on the number of images of Jenny he\\n\\npossessed, Rothenberg agreed that the government’s requested amount of $2,000\\n\\nwas reasonable.\\n\\nJ. Casseaopeia\\n\\n Casseaopeia submitted a restitution request of $25,000. In support of her\\n\\nrequest, Casseaopeia provided a victim impact statement, a psychological report\\n\\nfrom Dr. Joyce Vesper, and an economic assessment. In her victim impact\\n\\n\\n 19\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 20 of 67\\n\\n\\nstatement, Casseaopeia described her ongoing victimization as a result of the\\n\\nonline trade in her child pornography images. Casseaopeia stated that she worried\\n\\nthe people viewing her images would seek her out and harm her. She explained\\n\\nthat she suffers from anxiety, which makes it hard for her to work or go out in\\n\\npublic, and experiences panic attacks when she thinks someone recognizes her\\n\\nfrom the internet. Casseaopeia further explained that the continuing traffic in her\\n\\nimages made recovery from her PTSD and depression more difficult and\\n\\n“prevent[ed] the wound from healing.”\\n\\n In her September 2015 psychological report, Dr. Vesper described her\\n\\nclinical interview with Casseaopeia and the psychological tests she administered.\\n\\nFrom these assessments, Dr. Vesper concluded that Casseaopeia was “tortured by\\n\\nconstant memories of childhood sexual abuse” and experienced “constant head\\n\\nchatter, graphic flashbacks, [and] panic attacks that are so overwhelming they feel\\n\\nlike heart attacks.” Dr. Vesper described Casseaopeia as living “in constant fear\\n\\nthat the people viewing the pornographic films and pictures of her” online would\\n\\ncapture her and subject her to the same abuse all over again. Dr. Vesper opined\\n\\nthat “[w]ithout the appropriate psychotherapy to address [her] dissociation,\\n\\ndepersonalization, derealization, amnesia, anxiety and depression,” Casseaopeia\\n\\nwould continue to experience flashbacks, nightmares, and depression. Dr. Vesper\\n\\nrecommended intensive psychotherapy for Casseaopeia. In a supplemental report,\\n\\n\\n 20\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 21 of 67\\n\\n\\nDr. Vesper specifically addressed the effects on Casseaopeia of the ongoing traffic\\n\\nin her images. Dr. Vesper explained that Casseaopeia experienced persistent\\n\\nanxiety that people she knows will see on the internet images of her sexual abuse\\n\\nas a child and that this anxiety affects her recovery process.\\n\\n The economic assessment estimated Casseaopeia had economic damages\\n\\ntotaling $1,078,159, including $748,438 in lost earning capacity and $329,721 in\\n\\nfuture medical expenses.\\n\\n The government requested a slightly lower restitution award of $21,563 for\\n\\nCasseaopeia, which was calculated using the 1/n method. The government noted\\n\\nthat 49 other defendants were ordered to pay restitution to Casseaopeia and\\n\\nsubmitted a list of those prior awards. Those prior awards ranged from $0 at the\\n\\nlow end to $50,000 at the high end.\\n\\n Rothenberg opposed Casseaopeia’s restitution request. Rothenberg noted\\n\\nthat he possessed only two images of Casseaopeia and that the average restitution\\n\\naward to her was $3,974. Rothenberg argued that, like many of the other requests,\\n\\nthe government did not differentiate between the harm he caused and that caused\\n\\nby other perpetrators. Rothenberg contended that Dr. Vesper’s report primarily\\n\\ndealt with effects of the original abuse rather than the traffic in Casseaopeia’s\\n\\nimages.\\n\\n\\n\\n\\n 21\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 22 of 67\\n\\n\\nK. Restitution Hearing\\n\\n On November 18, 2016, the district court held a restitution hearing. At the\\n\\nrestitution hearing, the government submitted the evidence on which its restitution\\n\\nrequests were based, all of which was admitted into evidence.2 That evidence\\n\\nconsisted of 891 pages of exhibits submitted by the victims and charts prepared by\\n\\nthe government listing each victim’s prior restitution awards in other federal cases.\\n\\nThe exhibits included the declarations, psychological evaluations, letters, and other\\n\\nevidence referenced in the government’s restitution requests. Rothenberg noted, at\\n\\nthe outset of the hearing, that he agreed with the government’s requested award of\\n\\n$2,000 to Jenny and therefore did not offer any argument as to that award. The\\n\\nremaining requests were disputed, and the parties essentially reiterated the\\n\\narguments raised in their prior memoranda as to those victims.\\n\\n III. COURT’S RESTITUTION ORDER\\n\\n Six months later, on May 9, 2017, the district court issued its restitution\\n\\norder. After outlining in detail Paroline’s framework (and expressing some\\n\\nfrustration with its inexactitude), the district court analyzed each victim’s\\n\\nrestitution request. As a preliminary matter, the district court stated that, with\\n\\n\\n\\n\\n 2\\n Though the district court admitted the restitution exhibits into evidence at the restitution\\nhearing, it did not scan and file those exhibits on the district court docket. On appeal,\\nRothenberg filed an unopposed motion to supplement the record to include those exhibits, which\\nthis Court granted.\\n 22\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 23 of 67\\n\\n\\nrespect to each victim, it had assigned restitution in a manner that comported with\\n\\nRothenberg’s relative role and only for damages he proximately caused. The\\n\\ndistrict court explicitly explained that it had not “attempted to hold [Rothenberg]\\n\\nresponsible for all losses sustained by any victim.” Furthermore, the district court\\n\\nexpressly noted there was no evidence that Rothenberg was connected to the initial\\n\\nabuse of any of the victims or that he had reproduced or distributed their images.\\n\\nInstead, Rothenberg was a possessor only. And the district court specifically stated\\n\\nthat it had “taken these factors into consideration in assigning [Rothenberg] a\\n\\nrelative role as the proximate cause of these victims’ losses.”\\n\\n Turning to the specific awards, the district court determined that Sierra’s\\n\\n$10,000 request was reasonable. The district court found that: (1) Rothenberg\\n\\npossessed one image of Sierra; (2) a small number of criminal defendants had paid\\n\\nrestitution to Sierra; (3) Sierra’s current mental health condition was severe; and\\n\\n(4) Sierra’s projected costs of care exceeded $600,000. The district court found “in\\n\\nconsideration of her large amount of total costs, the small number of contributing\\n\\noffenders, and a request for a proportion of these costs proximately caused and to\\n\\nbe paid by [Rothenberg], who neither created nor distributed her image, that\\n\\n$10,000 is a reasonable request under the Paroline analysis and factors.”\\n\\n Next, the district court determined that Jane’s $3,000 request was\\n\\nreasonable. The district court found that: (1) Rothenberg possessed four images of\\n\\n\\n 23\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 24 of 67\\n\\n\\nJane; (2) a small number of criminal defendants had paid restitution to Jane;\\n\\n(3) Jane’s victim impact statement specifically addressed how the existence of her\\n\\nimages on the internet affected her and isolated the harm caused by possessors and\\n\\ndistributors from that caused by the original abuse; and (4) Jane’s estimated\\n\\nmedical and therapy costs were $101,027. The district court found “in\\n\\nconsideration of her medical costs, the small number of contributing offenders, and\\n\\na request for a proportion of these costs to be paid by [Rothenberg], who neither\\n\\ncreated nor distributed her images, that $3,000 is a reasonable request under the\\n\\nParoline analysis and factors.”\\n\\n The district court then determined that Pia’s $5,000 request was reasonable.\\n\\nThe district court found that: (1) Rothenberg possessed 14 images of Pia; (2) there\\n\\nwas no evidence regarding the number of other criminal defendants ordered to pay\\n\\nrestitution to Pia, though Pia’s counsel indicated that one other defendant was so\\n\\nordered; and (3) Pia’s estimated therapy costs over the next 20 years totaled\\n\\n$81,900. The district court found “in consideration of her total costs, the fact that\\n\\nshe has only received restitution from one other defendant, the large number of\\n\\nimages possessed by [Rothenberg] of [Pia], and a request for a proportion of these\\n\\ncosts to be paid by [Rothenberg], who neither created nor distributed her images,\\n\\nthat $5,000 is a reasonable request under the Paroline analysis and factors.”\\n\\n\\n\\n\\n 24\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 25 of 67\\n\\n\\n The district court also determined that Mya’s $5,000 request was reasonable,\\n\\ndespite the government’s requested amount of only $500. The district court found\\n\\nthat: (1) Rothenberg possessed one image of Mya; (2) there was no indication as to\\n\\nwhether any other criminal defendants were ordered to pay restitution to Mya; and\\n\\n(3) Mya’s counsel indicated a reasonable treatment estimate for Mya would be\\n\\nmore than $100,000. The district court found “in consideration of her total costs,\\n\\nthe fact that she has not received any restitution at this time, and a request for a\\n\\nproportion of these costs to be paid by [Rothenberg], who neither created nor\\n\\ndistributed her images, that $5,000 is a reasonable request under the Paroline\\n\\nanalysis and factors.”\\n\\n As to Sarah, the district court determined that an award of $20,000—$5,000\\n\\nless than Sarah’s requested amount—was reasonable. The district court explained\\n\\nthat: (1) Rothenberg possessed six images of Sarah; (2) over 150 criminal\\n\\ndefendants were ordered to pay restitution to Sarah; (3) Sarah’s victim impact\\n\\nstatement explicitly addressed how the existence of her images on the internet\\n\\naffected her, thereby isolating the harm caused by possession of her images from\\n\\nthat caused by the original abuse; and (4) Sarah’s estimated cost of psychiatric care\\n\\nwas nearly $300,000. The district court found, “in consideration of the amount of\\n\\ncosts, the fact that many other offenders have been required to pay restitution to\\n\\n[Sarah]—which in the case of Sarah, the Court finds contributes to a finding that\\n\\n\\n 25\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 26 of 67\\n\\n\\nthe request is reasonable and acknowledged by many other courts—the large\\n\\nnumber of images possessed of [Sarah], and a request for a proportion of these\\n\\ncosts proximately caused and to be paid by [Rothenberg], who neither created nor\\n\\ndistributed her image[s], that $20,000 is an appropriate amount under the Paroline\\n\\nanalysis and factors.”\\n\\n In a similar vein, the district court determined that for Vicky, $9,000—\\n\\n$1,000 less than Vicky’s requested $10,000 amount—was a reasonable award.\\n\\nThe district court found that: (1) Rothenberg possessed one image of Vicky;\\n\\n(2) more than 600, and possibly more than 800, other criminal defendants were\\n\\nordered to pay restitution to Vicky; (3) Vicky’s victim impact statement\\n\\nspecifically addressed how the online traffic in her images affected her and\\n\\nexplained the distinct harm caused by possessors and distributors of her images;\\n\\nand (4) Vicky’s predicted therapy costs exceeded $100,000. The district court\\n\\nfound “in consideration of the amount of costs, the fact that many other offenders\\n\\nhave been required to pay restitution to [Vicky]—which in the case of Vicky, the\\n\\nCourt finds contributes to a finding that the request is reasonable and\\n\\nacknowledged by many other courts—and a request for a proportion of these costs\\n\\nproximately caused and to be paid by [Rothenberg], who neither created nor\\n\\ndistributed her image, that $9,000 is an appropriate amount under the Paroline\\n\\nanalysis and factors.”\\n\\n\\n 26\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 27 of 67\\n\\n\\n The district court likewise awarded a reduced amount to Amy. The district\\n\\ncourt noted that Amy requested $25,000 and that the government requested\\n\\n$15,664, but the district court ultimately determined that $23,000 was reasonable.\\n\\nThe district court explained that: (1) Rothenberg possessed one image of Amy;\\n\\n(2) more than 200 criminal defendants had paid restitution to Amy; (3) Amy’s\\n\\nvictim impact statement “provide[d] strong support for the different and separate\\n\\nharm that possessors proximately cause to victims such as [herself]”; and\\n\\n(4) Amy’s counseling and therapy costs could exceed $500,000. The district court\\n\\nfound “in consideration of the large amount of costs, the fact that other offenders\\n\\nhave been required to pay restitution to [Amy]—which, again, in the case of Amy,\\n\\nthe Court finds contributes to a finding that the request is reasonable and\\n\\nacknowledged by other courts—and a request for a proportion of these costs\\n\\nproximately caused and to be paid by [Rothenberg], who neither created nor\\n\\ndistributed her image, that $23,000 is an appropriate amount under the Paroline\\n\\nanalysis and factors.”\\n\\n Regarding Jenny, the district court acknowledged that both the government\\n\\nand Rothenberg agreed that $2,000 was an appropriate amount, but that Jenny\\n\\nrequested $42,600. The district court determined that Jenny’s requested amount\\n\\nwas reasonable. The district court emphasized that (1) Rothenberg possessed 34\\n\\nimages and one video of Jenny, and (2) only one other defendant had paid\\n\\n\\n 27\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 28 of 67\\n\\n\\nrestitution to Jenny. The district court conceded there was “less documentation of\\n\\nJenny’s psychological and medical expenses as compared with some other victims\\n\\nin this case,” but found that the $2,000 amount requested by the parties was\\n\\ninsufficient. Considering “the extremely large number of images [Rothenberg]\\n\\npossessed of [Jenny], her costs, the fact that only one other defendant has so far\\n\\ncontributed to these costs, and a request for a proportion of these costs to be paid\\n\\nby [Rothenberg], who neither created nor distributed her images, the Court finds\\n\\nthat $42,600 is a reasonable request under the Paroline analysis and factors.”\\n\\n Lastly, as to Casseaopeia, the district court determined that her requested\\n\\naward of $25,000 was reasonable, even though the government requested only\\n\\n$21,563. The district court found that: (1) Rothenberg possessed two images of\\n\\nCasseaopeia; (2) more than 50 criminal defendants were ordered to pay her\\n\\nrestitution; and (3) her projected costs of care exceeded $300,000. Considering\\n\\n“her costs, the number of contributing offenders, and a request for a proportion of\\n\\nthese costs proximately caused and to be paid by [Rothenberg], who neither\\n\\ncreated nor distributed her image,” the district court found that “$25,000 is a\\n\\nreasonable request under the Paroline analysis and factors.”\\n\\n In total, the district court ordered Rothenberg to pay $142,600 in restitution,\\n\\nto be apportioned to the nine victims in the amounts set out above. On appeal,\\n\\nRothenberg argues that the district court erred as to all nine restitution awards. We\\n\\n\\n 28\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 29 of 67\\n\\n\\nbegin with the restitution statute and then review the Supreme Court’s Paroline\\n\\ndecision, which both parties agree governs this appeal.\\n\\n IV. 18 U.S.C. § 2259\\n\\n Congress has mandated that district courts award restitution to victims of\\n\\ncertain federal crimes, including child pornography possession. See 18 U.S.C.\\n\\n§ 2259(a) (2012).3 The possessor of child pornography must pay restitution to the\\n\\nvictim whose childhood abuse appears in the pornographic materials he possessed.\\n\\nSee id. § 2259(b)(1), (c)(4). The statute requires that “[t]he order of restitution . . .\\n\\nshall direct the defendant to pay the victim . . . the full amount of the victim’s\\n\\nlosses as determined by the court.” Id. § 2259(b)(1). The statute defines the term\\n\\n“full amount of the victim’s losses” to include any costs incurred by the victim for:\\n\\n (A) medical services relating to physical, psychiatric, or psychological\\n care;\\n (B) physical and occupational therapy or rehabilitation;\\n (C) necessary transportation, temporary housing, and child care\\n expenses;\\n (D) lost income;\\n (E) attorneys’ fees, as well as other costs incurred; and\\n (F) any other losses suffered by the victim as a proximate result of the\\n offense.\\n\\n\\n\\n\\n 3\\n Since Rothenberg’s guilty plea and restitution hearing, Congress amended 18 U.S.C.\\n§ 2259, effective December 7, 2018. See Amy, Vicky, and Andy Child Pornography Victim\\nAssistance Act of 2018, Pub. L. No. 115-299, 132 Stat. 4383 (2018). All citations in this opinion\\nare to the previous version of 18 U.S.C. § 2259, which was in effect both when Paroline was\\ndecided and at the time of the district court’s restitution order in this case.\\n 29\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 30 of 67\\n\\n\\nId. § 2259(b)(3) (emphasis added). The statute defines a victim as “the individual\\n\\nharmed as a result of the commission of a crime under this chapter.” Id.\\n\\n§ 2255(c)(4) (emphasis added). A court may not decline to issue restitution\\n\\nbecause of the economic circumstances of the defendant or because the victim has\\n\\nreceived compensation from another source. See id. § 2259(b)(4)(B).\\n\\n “The burden of demonstrating the amount of the loss sustained by a victim\\n\\nas a result of the offense shall be on the attorney for the Government.” Id.\\n\\n§§ 3664(e), 2259(b)(2) (emphasis added). In Paroline, the Supreme Court\\n\\naddressed the meaning of “as a result of” and “proximate result” in § 2259 and\\n\\nprecisely what type of causal connection or proximate cause must exist between\\n\\nthe victim’s losses and the defendant’s offense. We review Paroline next.\\n\\n V. SUPREME COURT’S PAROLINE DECISION\\n\\n Like this case, Paroline involved a possessor of child pornography images in\\n\\nwide circulation on the internet. In Paroline, the defendant was a possessor and not\\n\\na distributor or the initial abuser. See 572 U.S. at 439, 134 S. Ct. at 1716. The\\n\\nSupreme Court grappled with the question of what causal relationship must be\\n\\nestablished between a defendant possessor’s conduct and a victim’s losses for\\n\\npurposes of determining the right to, and the amount of, restitution under § 2259.\\n\\nId. As a preliminary matter, the Supreme Court interpreted § 2259’s statutory\\n\\nlanguage to impose a general proximate-cause limitation. Id. at 448, 134 S. Ct. at\\n\\n\\n 30\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 31 of 67\\n\\n\\n1721. The Supreme Court determined that “[r]estitution is therefore proper under\\n\\n§ 2259 only to the extent the defendant’s offense proximately caused a victim’s\\n\\nlosses.” Id. at 448, 134 S. Ct. at 1722.\\n\\n The difficulty, the Supreme Court explained, comes in applying that\\n\\ncausation requirement in a particular child pornography case. Id. at 449, 134 S. Ct.\\n\\nat 1722. This is so because of the “somewhat atypical causal process underlying\\n\\nthe losses [a child pornography] victim claims.” Id. The Supreme Court reasoned\\n\\nthat it may be “simple enough” for a victim to prove the aggregate losses that stem\\n\\nfrom the ongoing traffic in her images as a whole. Id. Importantly, the Supreme\\n\\nCourt observed that it is more difficult to determine “the ‘full amount’ of those\\n\\ngeneral losses, if any, that are the proximate result of the offense conduct of a\\n\\nparticular defendant who is one of thousands who have possessed and will in the\\n\\nfuture possess the victim’s images but who has no other connection to the victim.”\\n\\nId.\\n\\n Therefore, in child pornography possession offenses, the Paroline Court\\n\\nrecognized that it would be virtually impossible to show that the defendant\\n\\npossessor was a but-for cause of any particular portion of the victim’s losses\\n\\n“where the defendant is an anonymous possessor of images in wide circulation on\\n\\nthe Internet.” Id. at 450-51, 134 S. Ct. at 1722-23. Nevertheless, the Supreme\\n\\nCourt observed that “[w]hile it is not possible to identify a discrete, readily\\n\\n\\n 31\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 32 of 67\\n\\n\\ndefinable incremental loss [a defendant possessor] caused, it is indisputable that\\n\\n[the defendant possessor] was a part of the overall phenomenon that caused [the\\n\\nvictim’s] general losses.” Id. at 456-57, 134 S. Ct. at 1726. And it would\\n\\nundermine the purposes of § 2259 to deny restitution in cases involving possessors\\n\\nof child pornography. Id. at 456-58, 134 S. Ct. at 1726-27.\\n\\n The Supreme Court also recognized that the original abuse crime is\\n\\ncompounded by the distribution and possession of images of the victim’s original\\n\\nabuser’s “horrific acts, which meant the wrongs inflicted on her were in effect\\n\\nrepeated; for she knew her humiliation and hurt were and would be renewed into\\n\\nthe future as an ever-increasing number of wrongdoers witnessed the crimes\\n\\ncommitted against her.” Id. at 441, 134 S. Ct. at 1717. It does not matter that the\\n\\nvictim does not know the name of the possessor because the losses do not flow\\n\\nfrom any specific knowledge of him; rather, the cause of the victim’s losses “is the\\n\\ntrade in her images.” Id. at 456, 134 S. Ct at 1726. The Supreme Court also\\n\\nobserved that “the victim suffers continuing and grievous harm as a result of her\\n\\nknowledge that a large, indeterminate number of individuals have viewed and will\\n\\nin the future view images of the sexual abuse she endured.” Id. at 457, 134 S. Ct.\\n\\nat 1726. “In a sense, every viewing of child pornography is a repetition of the\\n\\nvictim’s abuse.” Id. at 457, 134 S. Ct. at 1727. “The cause of the victim’s general\\n\\nlosses is the trade in her images.” Id. at 456, 134 S. Ct. at 1726.\\n\\n\\n 32\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 33 of 67\\n\\n\\n After rejecting a but-for test for proximate cause, the Paroline Court adopted\\n\\na causation-in-fact standard for cases where: (1) “a defendant possessed a victim’s\\n\\nimages”; (2) “a victim has outstanding losses caused by the continuing traffic in\\n\\nthose images”; and yet (3) “it is impossible to trace a particular amount of those\\n\\nlosses to the individual defendant by recourse to a more traditional causal inquiry.”\\n\\nId. at 458, 134 S. Ct. at 1727. In that situation, the Supreme Court concluded that a\\n\\ndefendant possessor of child pornography should be ordered to pay restitution “in\\n\\nan amount that comports with the defendant’s relative role in the causal process\\n\\nthat underlies the victim’s general losses.” Id. The Supreme Court explained that\\n\\nthe award “would not be severe” in a case where the possessor is only one of many\\n\\nthousands of offenders, but also would not be “a token or nominal amount.” Id. at\\n\\n458-59, 134 S. Ct. at 1727. Rather, the required restitution would be “reasonable\\n\\nand circumscribed” and “suited to the relative size of [the defendant’s] causal\\n\\nrole.” Id. at 459, 134 S. Ct. at 1727.\\n\\n Further, the Supreme Court instructed, there is no “practical way to isolate\\n\\nsome subset of the victim’s general losses that [the possessor] Paroline’s conduct\\n\\nalone would have been sufficient to cause.” Id. at 451, 134 S. Ct. at 1723. In\\n\\nParoline, the defendant possessor was one of thousands who possessed the victim’s\\n\\nimages. Id. at 450, 134 S. Ct. at 1723. The Supreme Court stressed that even though\\n\\nthe victim does not know the possessor, the victim’s “knowledge that her images\\n\\n\\n 33\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 34 of 67\\n\\n\\nwere circulated far and wide renewed the victim’s trauma and made it difficult for\\n\\nher to recover from her abuse.” Id. at 440, 134 S. Ct. at 1717. “While it is not\\n\\npossible to identify a discrete, readily definable incremental loss he [the possessor]\\n\\ncaused, it is indisputable that he was a part of the overall phenomenon that caused\\n\\nher general losses.” Id. at 456-57, 134 S. Ct. at 1726. In other words, the defendant\\n\\npossessor of the images caused in fact part of the general losses, even if “it is\\n\\nimpossible to trace a particular amount of those losses to the individual defendant.”\\n\\nId. at 458, 134 S. Ct. at 1727.\\n\\n The Paroline Court then turned to the question of how district courts are to\\n\\ndetermine the proper amount of restitution in these “possessor” cases. Id. As a\\n\\ngeneral matter, the Supreme Court stated that a district court “must assess as best it\\n\\ncan from available evidence the significance of the individual defendant’s conduct\\n\\nin light of the broader causal process that produced the victim’s losses.” Id. at 459,\\n\\n134 S. Ct. at 1727-28. The Supreme Court emphasized that this “cannot be a precise\\n\\nmathematical inquiry,” but rather involves the exercise of “wide discretion” and\\n\\n“sound judgment” of the sort district courts typically exercise in the context of\\n\\ncriminal sentencing and restitution more broadly. Id. at 459-62, 134 S. Ct. at 1728-\\n\\n29. The Supreme Court then expressly identified “a variety of factors district courts\\n\\nmight consider” in determining a proper restitution amount for possession. Id. at\\n\\n459-60, 134 S. Ct. at 1728 (emphasis added).\\n\\n\\n 34\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 35 of 67\\n\\n\\n As a starting point, the Supreme Court suggested that district courts\\n\\n“determine the amount of the victim’s losses caused by the continuing traffic in the\\n\\nvictim’s images.” Id. at 460, 134 S. Ct. at 1728 (emphasis added). Then, to\\n\\ndetermine the defendant possessor’s relative role in causing those general losses, the\\n\\ndistrict court could consider factors such as: (1) “the number of past criminal\\n\\ndefendants found to have contributed to the victim’s general losses”; (2) “reasonable\\n\\npredictions of the number of future offenders likely to be caught and convicted for\\n\\ncrimes contributing to the victim’s general losses”; (3) “any available and\\n\\nreasonably reliable estimate of the broader number of offenders involved (most of\\n\\nwhom will, of course, never be caught or convicted)”; (4) “whether the defendant\\n\\nreproduced or distributed images of the victim”; (5) “whether the defendant had any\\n\\nconnection to the initial production of the images”; (6) “how many images of the\\n\\nvictim the defendant possessed”; and (7) “other facts relevant to the defendant’s\\n\\nrelative causal role.” Id.\\n\\n The Supreme Court reiterated that these factors should not be used as a “rigid\\n\\nformula,” but should instead serve as “rough guideposts” in determining a restitution\\n\\namount for the possessor criminal defendant. Id. The Supreme Court noted that\\n\\n“[t]his approach is not without its difficulties,” as it “involves discretion and\\n\\nestimation,” but “courts can only do their best to apply the statute as written in a\\n\\nworkable manner.” Id. at 462, 134 S. Ct. at 1729. The Supreme Court emphasized\\n\\n\\n 35\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 36 of 67\\n\\n\\nthat district courts regularly exercise wide discretion, and there was “no reason to\\n\\nbelieve they cannot apply th[is] causal standard . . . in a reasonable manner.” Id.4\\n\\n VI. STANDARD OF REVIEW\\n\\n We review de novo the legality of a restitution order, but review for clear\\n\\nerror the factual findings underlying that order. United States v. McDaniel, 631\\n\\nF.3d 1204, 1207 (11th Cir. 2011); see also United States v. Osman, 853 F.3d 1184,\\n\\n1188 (11th Cir. 2017). We review the amount of the district court’s restitution\\n\\naward only for an abuse of discretion. See United States v. Robertson, 493 F.3d\\n\\n1322, 1330 (11th Cir. 2007); see also Paroline, 572 U.S. at 459, 134 S. Ct at 1727-\\n\\n28 (emphasizing that “determining the proper amount of restitution” involves “the\\n\\nuse of discretion and sound judgment” on the part of the district court).\\n\\n A district court abuses its discretion if it applies an incorrect legal standard,\\n\\nfollows improper procedures, or makes clearly erroneous findings of fact. United\\n\\nStates v. Jordan, 582 F.3d 1239, 1249 (11th Cir. 2009). The abuse of discretion\\n\\nstandard recognizes that the district court has a range of choices, and this Court\\n\\n\\n\\n\\n 4\\n Three of the four dissenting justices were not so sure and complained that “[w]hen it\\ncomes to [the defendant’s] crime—possession of two of [the victim’s] images—it is not possible\\nto do anything more than pick an arbitrary number” as “the amount of the loss sustained by a\\nvictim as a result of” the defendant’s crime. Paroline, 572 U.S. at 463, 134 S. Ct. at 1730\\n(Roberts, C.J., dissenting). The fourth dissenter, Justice Sotomayor, would have embraced the\\nvictim’s joint and several liability theory, holding each possessor liable for restitution in the full\\namount of the victim’s losses. Id. at 473, 134 S. Ct. at 1735 (Sotomayor, J., dissenting).\\n 36\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 37 of 67\\n\\n\\nwill not reverse the district court’s choice as long as its decision does not amount\\n\\nto a clear error of judgment. Id.\\n\\n Osman, our only published post-Paroline restitution decision to date, did not\\n\\naddress how the abuse of discretion standard applies in assessing whether the\\n\\ndistrict court adequately considered the Paroline factors and imposed a reasonable\\n\\nrestitution award. See generally Osman, 853 F.3d at 1189-92. But Paroline itself\\n\\nprovides some important clues. In Paroline, the Supreme Court emphasized that\\n\\ndetermining the proper restitution amount “involves the use of discretion and\\n\\nsound judgment” in a manner akin to that exercised “in the wider context of\\n\\ncriminal sentencing,” and that the ultimate award must be “reasonable and\\n\\ncircumscribed.” Paroline, 572 U.S. at 459, 134 S. Ct. at 1727-28; see also id. at\\n\\n462, 134 S. Ct. at 1729 (explaining that “[d]istrict courts routinely exercise wide\\n\\ndiscretion . . . in sentencing as a general matter” and should likewise apply\\n\\nParoline’s causal standard “in a reasonable manner”). And to guide the district\\n\\ncourt’s exercise of its discretion, the Paroline Court identified a number of factors\\n\\ndistrict courts may consider in fashioning an appropriate restitution award. Id. at\\n\\n459-60, 134 S. Ct. at 1728.\\n\\n Paroline thus established a framework not unlike the one we apply in\\n\\nassessing the reasonableness of a defendant’s sentence, in which we look to see\\n\\nwhether the district court appropriately exercised its sentencing discretion in light\\n\\n\\n 37\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 38 of 67\\n\\n\\nof the 18 U.S.C. § 3553(a) factors. See, e.g., Gall v. United States, 552 U.S. 38,\\n\\n51, 128 S. Ct. 586, 597 (2007); United States v. Irey, 612 F.3d 1160, 1188-91 (11th\\n\\nCir. 2010) (en banc). In that § 3553(a) context, we evaluate whether the district\\n\\ncourt failed to consider relevant factors, improperly weighed the relevant factors,\\n\\nor considered improper factors, and ultimately assess whether, under the totality of\\n\\nthe circumstances, the sentence is reasonable. See Irey, 612 F.3d at 1189. And we\\n\\nwill vacate a sentence imposed by the district court only if we are “left with the\\n\\ndefinite and firm conviction that the district court committed a clear error of\\n\\njudgment in weighing the § 3553(a) factors by arriving at a sentence that lies\\n\\noutside the range of reasonable sentences dictated by the facts of the case.” Id. at\\n\\n1190 (internal quotation marks omitted).\\n\\n Additionally, in sentencing cases, we do not require district courts to make\\n\\ndetailed findings or give a thorough explanation for the sentence it chose. See id.\\n\\nat 1194-95. Specifically, “[t]he district court need not state on the record that it has\\n\\nexplicitly considered each factor and need not discuss each factor,” United States\\n\\nv. Dorman, 488 F.3d 936, 938 (11th Cir. 2007), “so long as the record reflects the\\n\\ncourt’s consideration of many of those factors,” United States v. Carpenter, 803\\n\\nF.3d 1224, 1232 (11th Cir. 2015). “Rather, an acknowledgment by the district\\n\\ncourt that it has considered the defendant’s arguments and the § 3553(a) factors\\n\\nwill suffice.” Dorman, 488 F.3d at 938.\\n\\n\\n 38\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 39 of 67\\n\\n\\n A similar approach makes sense here. As in the sentencing context, in\\n\\nevaluating child pornography restitution awards under Paroline, appellate courts\\n\\nmust determine whether the district court appropriately exercised its broad\\n\\ndiscretion in light of the facts of the particular case and awarded restitution in an\\n\\namount that comports with the particular defendant’s conduct. See Paroline, 572\\n\\nU.S. at 458-59, 462, 134 S. Ct. at 1727-29; Irey, 612 F.3d at 1190. And as in the\\n\\nsentencing context, a number of relevant factors guide the district court’s exercise\\n\\nof its discretion. See Paroline, 572 U.S. at 459-60, 134 S. Ct. at 1728; Gall, 552\\n\\nU.S. at 51, 128 S. Ct. at 597. Furthermore, the Supreme Court in Paroline\\n\\nindicated that the exercise of discretion at issue in child pornography restitution\\n\\ncases is similar to that exercised in criminal sentencing more generally. See\\n\\nParoline, 572 U.S. at 459, 134 S. Ct. at 1727-28.\\n\\n Accordingly, in reviewing child pornography restitution awards under\\n\\nParoline, this Court should consider whether, in light of the Paroline factors, the\\n\\ndistrict court arrived at a restitution amount that lies within the general range of\\n\\nreasonable restitution awards dictated by the facts of the case. See Irey, 612 F.3d\\n\\nat 1190. In doing so, this Court should give due deference to the district court’s\\n\\ndetermination that the Paroline factors, on the whole, justify the restitution amount\\n\\nawarded and should not vacate an award unless left with the definite and firm\\n\\nconviction that the district court committed a clear error of judgment in setting the\\n\\n\\n 39\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 40 of 67\\n\\n\\naward amount. See id.; Gall, 552 U.S. at 51, 128 S. Ct. at 597. Moreover, so long\\n\\nas the district court acknowledges that it has considered the Paroline factors and\\n\\nthe defendant’s arguments regarding restitution, we will not vacate a restitution\\n\\naward solely on the basis that the district court did not address each factor\\n\\nexplicitly. See Carpenter, 803 F.3d at 1232; Dorman, 488 F.3d at 938.\\n\\n With these principles in mind, we turn now to Rothenberg’s disaggregation\\n\\nargument, which is a legal challenge to the district court’s restitution order that we\\n\\nreview de novo. Osman, 853 F.3d at 1188.\\n\\n VII. DISAGGREGATION\\n\\n On appeal, Rothenberg first argues that, as to all nine victims, the district\\n\\ncourt failed to “disaggregate” their losses. Rothenberg contends that Paroline\\n\\nrequires district courts to engage in disaggregation at two levels: first, by\\n\\ndisaggregating the portion of the victim’s losses caused by the original abuse; and\\n\\nsecond, by disaggregating the losses caused by the defendant from those caused by\\n\\nother possessors or distributors.\\n\\n Rothenberg asserts that the district court here failed at the first level by\\n\\nrelying on total loss estimates for each victim that did not separate out and deduct\\n\\nthe losses caused by the original abuser. Because the expert reports did not\\n\\ndisaggregate the losses caused by the original abuser from those caused by the\\n\\ndistributors or possessors, Rothenberg contends that the district court was required\\n\\n\\n 40\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 41 of 67\\n\\n\\nto conduct that separating out itself. Rothenberg maintains that the district court\\n\\nalso failed to disaggregate at the second level by failing to use the amounts of the\\n\\nprior restitution orders against other defendant possessors or distributors for the\\n\\nsame victims as a guidepost for determining his relative level of culpability.\\n\\n The government responds that nothing in Paroline requires district courts to\\n\\nengage in the sort of formal disaggregation Rothenberg envisions. Rather, the\\n\\ngovernment contends that Paroline simply requires that the district court consider\\n\\nthe Paroline factors and exercise its discretion in determining the amount of a\\n\\nvictim’s losses caused by the instant defendant. The government submits that the\\n\\ndistrict court here complied with those requirements, explicitly stating it was not\\n\\nholding Rothenberg accountable for the original abuse or distribution of the\\n\\nvictims’ images and setting restitution amounts that “best approximat[ed]\\n\\nRothenberg’s relative role.”\\n\\n This Court has not yet addressed whether, in awarding restitution post-\\n\\nParoline, district courts first must formally disaggregate a victim’s losses between\\n\\nthe original abuser, distributors, and subsequent possessors. Several of our sister\\n\\ncircuits, however, have grappled with that question, and the results are mixed.\\n\\nA. Eighth and Fifth Circuits’ Decisions\\n\\n We start with the Eighth Circuit’s decision in United States v. Bordman, 895\\n\\nF.3d 1048, 1058-59 (8th Cir. 2018), cert. denied, 2019 WL 1886056 (U.S. Apr. 29,\\n\\n\\n 41\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 42 of 67\\n\\n\\n2019), a restitution case involving a defendant convicted of only possessing child\\n\\npornography. In Bordman, the Eighth Circuit expressly held that a district court is\\n\\nnot required to formally disaggregate categories of loss before ordering restitution,\\n\\nsuch as the loss caused by the initial abuser. Id. at 1058-59.\\n\\n In doing so, the Eighth Circuit affirmed the district court’s $3,000 award of\\n\\nrestitution to a victim where the district court considered multiple factors,\\n\\nincluding: (1) the 1/n method, which took into account the number of defendants\\n\\n(32) who had already paid the victim restitution plus 1 (the defendant Bordman),\\n\\nfor a total of 33; (2) the child pornography being videos with two copies of the\\n\\nsame video in different folders; and (3) the “very aggravating factor” of the nature\\n\\nof the video. Id. at 1052-53, 1059. The victim’s losses included $91,900 in\\n\\ntherapy, related expenses, and for a vocational assessment and counseling, legal\\n\\ncosts of $10,187.13, and attorney’s fees. Id. at 1052. At the sentencing hearing,\\n\\nthe government took the sum of $95,295.71 ($91,900 plus one third of the\\n\\nattorney’s fees) and divided it by 33 defendants, resulting in the sum of $2,887.75.\\n\\nId. at 1052-53. One-third of the attorney’s fees was used because this same\\n\\nattorney had represented three victims. Id. at 1052. The district court imposed a\\n\\n$3,000 restitution amount for the victim. Id. at 1054.\\n\\n On appeal, the defendant-possessor Bordman specifically claimed that “the\\n\\ndistrict court abused its discretion by failing to disaggregate the harm caused by the\\n\\n\\n 42\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 43 of 67\\n\\n\\ninitial abuse from the harm that his later possession caused.” Id. at 1058. In\\n\\nrejecting that claim, the Eighth Circuit reasoned that “one of the Paroline factors\\n\\nalready accounts for disaggregation”—namely, “whether the defendant had any\\n\\nconnection to the initial production of the images.” Id. at 1059 (quoting Paroline,\\n\\n572 U.S. at 460, 134 S. Ct. at 1728). The Eighth Circuit “decline[d] to transform”\\n\\nthis disaggregation factor “from a ‘rough guidepost’ into a ‘rigid formula.’” Id.\\n\\n(quoting Paroline, 572 U.S. at 460, 134 S. Ct. at 1728).\\n\\n The Fifth Circuit also has rejected, under plain error review, a defendant’s\\n\\nchallenge to restitution awards that relied on psychological reports that “did not\\n\\nseparate the losses caused by [the defendant possessor] from the losses caused by\\n\\nother abusers.” United States v. Halverson, 897 F.3d 645, 654-55 n.4 (5th Cir.\\n\\n2018). The Fifth Circuit reasoned that nothing in Paroline clearly required victims\\n\\nto present a new psychological report in each case that “disaggregates a\\n\\ndefendant’s conduct from all other possible sources of the victim’s losses.” Id.\\n\\nThe Fifth Circuit approved the district court’s use of a restitution method which\\n\\nawarded each victim (1) a base $5,000 amount of restitution, plus (2) an additional\\n\\nsum of $1,409 for each image of the victim that the defendant possessed because\\n\\nthe district court discussed factors that bore on the relative significance of the\\n\\ndefendant’s conduct and the district court was not required to make findings as to\\n\\nall of the Paroline factors. Id. at 653-54.\\n\\n\\n 43\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 44 of 67\\n\\n\\nB. Fourth and Seventh Circuits’ Decisions\\n\\n While not directly ruling on the initial-abuser-disaggregation issue, two\\n\\nother decisions of our sister circuits bear mentioning. That is because both\\n\\ndecisions, post-Paroline, (1) emphasized the district court’s wide discretion\\n\\ninherent in determining the amount of restitution, (2) affirmed restitution awards\\n\\nunder various methodologies against possessors of child pornography, and\\n\\n(3) refused to impose more structure beyond the Supreme Court’s multi-factored\\n\\ntest. See United States v. Dillard, 891 F.3d 151, 160-62 (4th Cir. 2018) (noting\\n\\nthat Paroline did not set any “evidentiary minimums” for establishing restitution,\\n\\nthat “[p]ost-Paroline, our sister courts of appeals have approved of various\\n\\nmethods of determining a restitution award,” and that “[d]istrict courts have great\\n\\ndiscretion in selecting an appropriate methodology”); United States v. Sainz, 827\\n\\nF.3d 602, 605-07 (7th Cir. 2016) (discussing the district court’s ability to employ\\n\\nvarying methodologies, including the 1/n method, to calculate a restitution amount\\n\\nunder Paroline and stating that “the bottom line here is that the amount of the\\n\\naward is substantively reasonable”). We discuss Dillard and Sainz in detail, as\\n\\nthey demonstrate not only how to apply the Paroline factors, but also a common-\\n\\nsense, practical approach to restitution for victims whose losses are caused by the\\n\\ncontinuing traffic in their child pornography images.\\n\\n\\n\\n\\n 44\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 45 of 67\\n\\n\\n In the Fourth Circuit’s Dillard decision, while the defendant was the initial\\n\\nabuser of one child victim, he also possessed images of other child victims with\\n\\nwhom he had no contact. Dillard, 891 F.3d at 154. The district court denied all\\n\\nrestitution to the non-contact victims because the record contained no evidence that\\n\\nthe victims were aware Dillard had their images and no evidence connecting the\\n\\nnon-contact victims’ harm to Dillard. Id. at 156. In reversing, the Fourth Circuit\\n\\nexplained Paroline disavowed any such requirements. Id. at 159-60. The Fourth\\n\\nCircuit held the “[g]overnment satisfied its burden of causation by the uncontested\\n\\nevidence that Dillard’s offense conduct included the seven non-contact victims’\\n\\nimages” and “that these victims have outstanding losses caused by the continuing\\n\\ntraffic in those images.” Id. at 160 (internal quotation marks omitted).\\n\\n As to how to calculate those non-contact victims’ losses caused by Dillard,\\n\\nthe Fourth Circuit said the district court “‘might, as a starting point, determine the\\n\\namount of the victim’s losses caused by the continuing traffic in the victim’s\\n\\nimages’” and “‘then set an award of restitution in consideration of factors that bear\\n\\non the relative causal significance of the defendant’s conduct in producing those\\n\\nlosses.’” Id. at 160 (quoting Paroline, 572 U.S. at 460, 134 S. Ct. at 1728). The\\n\\nFourth Circuit remanded for the district court to consider the Paroline factors and\\n\\naward at least some “non-nominal amount of restitution” for the losses of the non-\\n\\ncontact victims whose images Dillard possessed. Id. at 161-62. Where it was\\n\\n\\n 45\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 46 of 67\\n\\n\\n“uncontested that the individuals seeking restitution were Dillard’s victims and had\\n\\noutstanding losses associated with the continued trade in their images, they were\\n\\nentitled by statute to some non-nominal amount of restitution.” Id. at 161 (citing\\n\\nParoline, 572 U.S. at 458-60, 134 S. Ct. at 1727-28).\\n\\n Similarly, the Seventh Circuit’s decision in Sainz stresses the district court’s\\n\\n“considerable discretion in deciding the extent of a defendant’s restitution” who\\n\\npossessed child pornography. Sainz, 827 F.3d at 605. The defendant Sainz\\n\\npossessed six images of the victim that had circulated widely on the internet, but\\n\\nhad no role in creating or distributing them. Id. at 604. The victim had “incurred\\n\\nfinancial losses such as future lost earnings, attorney fees, and medical and\\n\\npsychiatric expenses” that totaled $1.1 million. Id. at 604, 605 n.1. On appeal, the\\n\\ndefendant Sainz did not challenge that he must pay some amount of restitution but\\n\\nargued that the $8,387.43 amount he was ordered to pay was “disproportionate to\\n\\nhis relative role in causing” the victim’s losses. Id. at 604-05. Sainz also claimed\\n\\n“he was not a legal cause of [the victim’s] harm because hundreds or thousands of\\n\\nothers also possessed the images, so she would have been harmed by others even if\\n\\nhe had never possessed the images of her.” Id. at 604.\\n\\n Using the 1/n method advocated for by the government, the district court\\n\\ndivided the total loss of $1.1 million by 136 because defendant Sainz was the 136th\\n\\noffender who was prosecuted and ordered to pay restitution. See id. at 605. By\\n\\n\\n 46\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 47 of 67\\n\\n\\npossessing and viewing the victim’s images, Sainz had re-victimized her and made\\n\\nher feel that the abuse was continuing. Id. at 604.\\n\\n In finding no legal error or abuse of discretion in the $8,387.43 restitution\\n\\naward, the Seventh Circuit affirmed and reasoned: (1) that the Supreme Court in\\n\\nParoline “avoided rigid or mechanical rules” and left the district courts with\\n\\n“considerable discretion”; (2) the amount of restitution for a possessor like Sainz\\n\\n“should be neither ‘severe’ nor a ‘token or nominal amount’”; (3) Paroline does not\\n\\nrequire “district courts to consider in every case every factor mentioned” and the\\n\\ndistrict court does “not err by not addressing every Paroline factor” 5; and (4) the\\n\\nParoline factors are permissive, not mandatory and provide “rough guideposts” that\\n\\n“district courts might consider in determining a proper amount of restitution.” Id.\\n\\nat 605-07 (internal quotation marks omitted). The Seventh Circuit recognized that\\n\\nthe 1/n method is not appropriate for all cases because, when n is “very small or\\n\\nvery large, a more nuanced method may be required.” Id. at 607. The Seventh\\n\\nCircuit concluded, however, that the application of the 1/n method to Sainz’s case\\n\\n“resulted in a reasonable restitution order of $8,400 for an offender who possessed\\n\\nsix images of the victim and indisputably contributed to her harm.” Id.\\n\\n\\n 5\\n The Seventh Circuit explained some of the Paroline factors refer to information that may\\nnot be “reliably known,” such as “the number of offenders likely to be convicted in the future or\\nthe broader numbers of offenders who were involved but are unlikely to be caught.” Sainz, 827\\nF.3d at 607. The Seventh Circuit stated that “the Supreme Court made clear in Paroline that the\\ndifficulty of coming up with reasonable estimates for an indeterminate number of other offenders\\nshould not be a barrier to all compensation for victims of child pornography.” Id.\\n 47\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 48 of 67\\n\\n\\n We acknowledge that the defendant Sainz did not ask the court to\\n\\ndisaggregate the losses from the initial abuser. Nonetheless, the Seventh Circuit’s\\n\\ndecision is instructive because it emphasizes that (1) the district court has\\n\\n“considerable discretion,” (2) the court’s method of restitution calculation can vary\\n\\nfrom case to case depending on the facts, and (3) “the bottom line” is that the\\n\\ndistrict court’s award of $8,387.43 was “substantively reasonable” for the\\n\\ndefendant possessor Sainz, even though there were hundreds of other possessors of\\n\\nthe same victim’s images. See id. at 604-607.\\n\\nC. Ninth and Tenth Circuits’ Decisions\\n\\n In contrast to these decisions, the Ninth and Tenth Circuits have determined\\n\\nthat district courts must engage in some level of disaggregation as to the harms\\n\\ncaused by the original abuse versus the harms caused by later distributors and\\n\\npossessors before awarding restitution against a particular possessor of child\\n\\npornography. See United States v. Galan, 804 F.3d 1287 (9th Cir. 2015); United\\n\\nStates v. Dunn, 777 F.3d 1171 (10th Cir. 2015). But even those post-Paroline\\n\\ndecisions are nuanced and do not adopt a rigid, mathematical rule in that regard.\\n\\nFurthermore, the facts of the Tenth Circuit’s Dunn case are important to\\n\\nunderstand what the Tenth Circuit did or did not conclude in that case.\\n\\n In Dunn, one victim sought restitution of $583,955, which represented her\\n\\ntotal losses minus the amount of restitution already received from other defendants.\\n\\n\\n 48\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 49 of 67\\n\\n\\nSee Dunn, 777 F.3d at 1174, 1179. Because Dunn was a distributor of the images,\\n\\nthe district court determined that “he should be held jointly and severally liable for\\n\\nthe entirety of [the victim’s] injuries.” Id. at 1179. The victim’s total losses were\\n\\n$1,330,015, and the district court held Dunn responsible for $583,955 of those total\\n\\nlosses as the amount not yet paid. See id. at 1181.\\n\\n In reversing, the Tenth Circuit emphasized that the district court held the\\n\\ndefendant Dunn liable for all of the victim’s unpaid losses, including those caused\\n\\nby the initial abuser, and erred by not assessing Dunn’s individual relative role in\\n\\nthe causal process underlying the victim’s losses. See id. at 1181. The Tenth\\n\\nCircuit concluded: “[T]o the extent that the district court relied on an expert report\\n\\nthat did not disaggregate [the harms caused by the original abuser], the district\\n\\ncourt’s adoption of $1.3 million as the total measure of damages cannot stand.” Id.\\n\\nat 1182.6 The disaggregation conclusion in Dunn must be read in the factual\\n\\ncontext of a reversal of a district court’s ruling that a defendant was jointly and\\n\\n\\n\\n\\n 6\\n Though it has not addressed whether district courts must disaggregate, the First Circuit\\nhas held that a district court order comported with Paroline’s framework where it “excluded past\\ncosts and based its award on an estimate of [the victim’s] future therapy costs, occasioned by\\ndefendant’s conduct.” United States v. Rogers, 758 F.3d 37, 39 (1st Cir. 2014). The district\\ncourt also “limited the losses to general losses from ‘continuing’ traffic” in the victim’s images\\nand “distinguished the future therapy losses attributable to defendant from the harm resulting\\nfrom other viewers and from [the victim’s] therapy needs relating to [the original abuser].” Id.\\nThe First Circuit commented that the district court’s $3,150 restitution award “represent[ed] the\\ncost of 18 therapy visits,” but the district court “noted that 50 visits would also have been a\\nreasonable conclusion.” Id. The mere fact that this type of formal disaggregation is permissible\\nunder Paroline, however, does not mean that it is required.\\n 49\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 50 of 67\\n\\n\\nseverally liable with all other defendants, including the abuser, for the entirety of\\n\\nthe victim’s $1,330,015 total losses, minus only what other defendants had already\\n\\npaid. We read Dunn as requiring disaggregation in that case because the defendant\\n\\nwas held jointly and severally liable with the abuser for the entirety of the losses;\\n\\nwe do not read Dunn as requiring disaggregation in each and every restitution case.\\n\\n Unlike Dunn’s recounting of the restitution facts, the Ninth Circuit’s\\n\\ndecision in Galan does not indicate the amounts of the victim’s losses or even the\\n\\nrestitution award at issue. Galan, 804 F.3d at 1288. Rather, Galan recounts only\\n\\nthese two facts: (1) the defendant Galan was not the victim’s original abuser, who\\n\\n“made images of his disgusting crimes against [the victim] over an extended\\n\\nperiod” of time; and (2) that abuse ended about 11 years before Galan possessed\\n\\nthe images. See id.\\n\\n In reversing, the Ninth Circuit went much further than the Tenth. The Ninth\\n\\nCircuit held “that in calculating the amount of restitution to be imposed upon a\\n\\ndefendant who was convicted of distribution or possession of child pornography,\\n\\nthe losses, including ongoing losses, caused by the original abuse of the victim\\n\\nshould be disaggregated from the losses caused by the ongoing distribution and\\n\\npossession of images of that original abuse, to the extent possible.” Id. at 1291.\\n\\nThe Ninth Circuit concluded “that Galan should not be required to pay for losses\\n\\ncaused by the original abuser’s actions.” Id. at 1290. The Ninth Circuit\\n\\n\\n 50\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 51 of 67\\n\\n\\ndetermined, in effect, that some type of calculation should be made between\\n\\noriginal abusers on the one hand and the distributors and possessors on the other.\\n\\nSee id. at 1288, 1290.\\n\\n Importantly, however, the Ninth Circuit cautioned that it “express[ed] no\\n\\nopinion about what portion of the victim’s ongoing loss should be attributable to an\\n\\noriginal abuser.” Id. at 1291. It also did not instruct how the disaggregation\\n\\ncalculation should be done, and it even added that “[i]f the ultimate apportionment\\n\\nis not scientifically precise, we can only say that precision is neither expected nor\\n\\nrequired.” Id.\\n\\nD. Our Analysis\\n\\n After careful review of Paroline, we conclude that a district court is not\\n\\nrequired to determine, calculate, or disaggregate the specific amount of loss caused\\n\\nby the original abuser-creator or distributor of child pornography before it can\\n\\ndecide the amount of the victim’s losses caused by the later defendant who\\n\\npossesses and views the images. Paroline requires no such disaggregation.\\n\\nCertainly, Paroline directed district courts to hold a defendant accountable only for\\n\\nhis own individual conduct and set a restitution “amount that comports with the\\n\\ndefendant’s relative role” in causing the victim’s general losses. See Paroline, 572\\n\\nU.S. at 454-55, 458-59, 134 S. Ct. at 1725, 1727. How a district court arrives at\\n\\nthat figure is largely up to the district court, so long as the number is a “reasonable\\n\\n\\n 51\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 52 of 67\\n\\n\\nand circumscribed award” that is “suited to the relative size” of the defendant’s\\n\\ncausal role in the entire chain of events that caused the victim’s loss. Id. at 459,\\n\\n134 S. Ct. at 1727.\\n\\n In arriving at that figure, Paroline does require some consideration by the\\n\\ndistrict court of whether the defendant possessor was also an abuser-creator or a\\n\\ndistributor. See id. Indeed, that is why Paroline includes among its list of relevant\\n\\nfactors “whether the defendant had any connection to the initial production of the\\n\\nimages,” and “whether the defendant reproduced or distributed images of the\\n\\nvictim.” Id. at 460, 134 S. Ct. at 1728. But those factors do not require that the\\n\\ndistrict court make fact findings about the amount of losses caused by different\\n\\ngroups of offenders.\\n\\n To be clear, the district court should ensure that its restitution order relates\\n\\nonly to the amount of harm and loss caused by the defendant possessor. But\\n\\nParoline also repeatedly stresses the flexibility and broad discretion district courts\\n\\nhave in arriving at such a reasonable restitution amount. See, e.g., id. at 459, 134\\n\\nS. Ct. at 1727-28 (“[A] court must assess as best it can from available evidence the\\n\\nsignificance of the individual defendant’s conduct in light of the broader causal\\n\\nprocess that produced the victim’s losses. This cannot be a precise mathematical\\n\\ninquiry and involves the use of discretion and sound judgment.”); id. at 459-60,\\n\\n134 S. Ct. at 1728 (“[I]t is neither necessary nor appropriate to prescribe a precise\\n\\n\\n 52\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 53 of 67\\n\\n\\nalgorithm for determining the proper restitution amount at this point in the law’s\\n\\ndevelopment. Doing so would unduly constrain the decisionmakers closest to the\\n\\nfacts of any given case.”); id. at 460, 134 S. Ct. at 1728 (“These factors need not be\\n\\nconverted into a rigid formula . . . . They should rather serve as rough guideposts\\n\\nfor determining an amount that fits the offense.”); id. at 462, 134 S. Ct. at 1729\\n\\n(stating, “the approach articulated above involves discretion and estimation,” and\\n\\n“courts can only do their best to apply the statute as written in a workable\\n\\nmanner”).\\n\\n Like the Eighth Circuit, we think it would be inconsistent with Paroline’s\\n\\nflexible, discretionary framework to require district courts to perform an initial,\\n\\nformal step of calculating and then separately assigning a total loss amount to the\\n\\ninitial abuser, then one to the distributors and possessors generally, and only then\\n\\none to the particular defendant possessor. Rather, even if a victim’s total loss\\n\\nestimate includes losses caused both by the original abuser-creator, the distributors,\\n\\nand other possessors, the district court need only indicate in some manner that it\\n\\nhas considered that the instant defendant is a possessor, and not the initial abuser or\\n\\na distributor, and has assigned restitution based solely on the defendant possessor’s\\n\\nparticular conduct and relative role in causing those losses. See id. at 458-62, 134\\n\\nS. Ct. at 1727-29.\\n\\n\\n\\n\\n 53\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 54 of 67\\n\\n\\n Here, the district court did exactly that. In its restitution order, the district\\n\\ncourt explicitly found up front that “there is no evidence with respect to any victim\\n\\nthat [Rothenberg] reproduced or distributed images of the victim or that he had [a]\\n\\nconnection to the initial production of the images.” The district court expressly\\n\\nstated that it had “taken these factors into consideration in assigning [Rothenberg]\\n\\na relative role as the proximate cause of these victims’ losses.” And in setting each\\n\\nindividual award, the district court reiterated that Rothenberg “neither created nor\\n\\ndistributed” the victim’s image. Under Paroline, that is enough. We therefore\\n\\nreject Rothenberg’s disaggregation argument.\\n\\n Before concluding, we recognize that the Supreme Court in Paroline did\\n\\nnote in dicta that “[c]omplications may arise in disaggregating losses sustained as a\\n\\nresult of the initial physical abuse, but those questions may be set aside for present\\n\\npurposes.” Id. at 449, 134 S. Ct. at 1722. We do not read this dicta, which is\\n\\ncontained in a parenthetical, as requiring in any way that the district courts in\\n\\npossessor cases take on the job of determining the harm and loss caused by the\\n\\ninitial abuser or the distributors. 7 Rather, the district court’s job is to determine the\\n\\n\\n\\n 7\\n We acknowledge that the Ninth Circuit concluded that the set-aside statement in this\\nparenthetical meant the Supreme Court “plainly perceived a need for separation” of losses from\\nthe initial abuser and the later possessor defendants. Galan, 804 F.3d at 1290. However, we read\\nthe dicta in this parenthetical sentence not in isolation, but in the context surrounding it, which to\\nus signals that in possessor cases a court is not required to delve into the special losses caused by\\nthe original abuser. Rather, in possessor cases, the court is examining only the general losses\\ncaused by the continuing traffic in the pornographic images and awarding restitution that\\n 54\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 55 of 67\\n\\n\\ndefendant possessor’s causal role in the general losses caused by his participation\\n\\nin the ongoing traffic in the victim’s images.\\n\\n We likewise reject Rothenberg’s argument that the district court erred in\\n\\ncreating restitution disparities between himself and other possessors by\\n\\n“impos[ing] restitution in amounts substantially above the average [for other\\n\\npossessors] without providing any explanation at all.” We recognize that the\\n\\nSupreme Court in Paroline listed as a factor “the number of past criminal\\n\\ndefendants found to have contributed to the victim’s general losses” and noted that\\n\\nthe government “could also inform district courts of restitution sought and ordered\\n\\nin other cases.” See id. at 460, 462, 134 S. Ct. at 1728-29. However, the Supreme\\n\\nCourt did not require district courts to dive into the facts of every past order and\\n\\nposition their restitution findings in relation to those of other courts. See id. The\\n\\ndistrict court is not required to say why it did not follow or disagreed with\\n\\nrestitution orders as to the same victim imposed by other courts. Paroline requires\\n\\nno such fact findings or analysis. Rather, the number of past criminal defendants\\n\\nand their restitution amounts, even as to the same victim, are just one of many\\n\\n\\n\\n\\ncomports with the defendant possessor’s relative role as a possessor. In our view, nothing in\\nParoline requires disaggregation, and everything in Paroline suggests otherwise.\\n 55\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 56 of 67\\n\\n\\nfactors the district court considers generally without having to make mathematical\\n\\ncalculations. 8 See id.\\n\\n VIII. SUFFICIENCY OF THE EVIDENCE\\n\\nA. McGarity\\n\\n Rothenberg’s next argument concerns victims Sierra, Jane, Sarah, Vicky,\\n\\nAmy, and Casseaopeia. 9 As to these six victims, Rothenberg argues that the\\n\\ndistrict court erred in relying on loss estimates that were based on psychological\\n\\nevaluations conducted before his arrest and thus before these victims learned of his\\n\\ncriminal possession offense, citing this Court’s prior precedent in United States v.\\n\\nMcGarity, 669 F.3d 1218 (11th Cir. 2012). The government responds that the\\n\\nportion of McGarity on which Rothenberg relies was overruled by Paroline.\\n\\n In McGarity, which was decided prior to Paroline, this Court concluded that\\n\\na psychological evaluation performed before the defendant’s arrest and prosecution\\n\\ncould not show the harm to the victim. 669 F.3d at 1269. More specifically, for\\n\\nproximate cause to exist in a child pornography case, “there must be a causal\\n\\nconnection between the actions of the end-user and the harm suffered by the\\n\\n 8\\n In this case, the government’s submission and calculations used the 1/n method, but only\\nas a starting point for the district court’s exercise of discretion and then application of the\\nParoline factors. While we affirm the thorough and multifactored process used in this case, we\\ncaution that the application of a strict 1/n approach, in which the only thing the district court does\\nis divide the total loss amount by the total number of defendants who have been ordered to pay\\nrestitution, ordinarily will not meet the individualized assessment requirement of Paroline.\\n 9\\n On appeal, Rothenberg does not challenge the evidentiary basis for victim Pia’s $5,000\\nrestitution award.\\n 56\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 57 of 67\\n\\n\\nvictim.” Id. The McGarity Court determined that, in that case, the government\\n\\nfailed to provide any basis for determining “whether [the defendant’s] possession\\n\\nof child pornography proximately caused any of [the victim’s] harm,” given the\\n\\nvictim’s psychological evaluation occurred before the defendant’s arrest and\\n\\nprosecution. Id.\\n\\n As such, the McGarity Court determined that the psychological evaluation\\n\\ncould not show the harm caused to the victim by the particular defendant’s conduct\\n\\nin that case. Id. at 1269-70 (citing with approval the Second Circuit’s decision in\\n\\nUnited States v. Aumais, 656 F.3d 147, 154 (2d Cir. 2011), that remarked that the\\n\\nvictim’s psychological evaluation preceded the defendant’s arrest, and thus it could\\n\\nnot demonstrate the impact on the victim caused by that defendant). In other\\n\\nwords, the McGarity Court concluded that to establish proximate cause, the\\n\\ngovernment must show that the victim actually learned of the particular\\n\\ndefendant’s possession of her images. See id. at 1269-70.\\n\\n We agree with the government that this aspect of McGarity was abrogated\\n\\nby Paroline. See United States v. Archer, 531 F.3d 1347, 1352 (11th Cir. 2008)\\n\\n(“[A] prior panel’s holding is binding on all subsequent panels unless and until it is\\n\\noverruled or undermined to the point of abrogation by the Supreme Court or by\\n\\nthis court sitting en banc.”). In requiring to show harm that the victim was aware\\n\\nof a particular defendant’s conduct, the McGarity Court essentially required that\\n\\n\\n 57\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 58 of 67\\n\\n\\nthe government establish a direct, but-for causal link between some portion of the\\n\\nvictim’s losses and the specific defendant’s offense. See McGarity, 669 F.3d at\\n\\n1269-70. As discussed above, however, Paroline rejected exactly that sort of direct\\n\\nor but-for causation requirement in setting out its new standard. See Paroline, 572\\n\\nU.S. at 450-59, 134 S. Ct. at 1722-28. In Paroline, the Supreme Court recognized\\n\\nthat “it is not possible to prove that [a victim’s] losses would be less (and by how\\n\\nmuch) but for one possessor’s individual role in the large, loosely connected\\n\\nnetwork through which her images circulate,” nor is there “a practical way to\\n\\nisolate some subset of the victim’s general losses that [the defendant’s] conduct\\n\\nalone would have been sufficient to cause.” Id. at 450-51, 134 S. Ct. at 1723.\\n\\nNevertheless, the Supreme Court explained that “it is indisputable that [the\\n\\ndefendant] was a part of the overall phenomenon that caused [the victim’s] general\\n\\nlosses.” Id. at 457, 134 S. Ct. at 1726.\\n\\n In Paroline, the Supreme Court thus held that, “[i]n this special context”\\n\\nwhere it is clear both that the defendant possessed images of the victim and that the\\n\\nvictim has outstanding losses as a result of the traffic in her images, “but where it\\n\\nis impossible to trace a particular amount of those losses to the individual\\n\\ndefendant,” courts should order restitution “in an amount that comports with the\\n\\ndefendant’s relative role in the causal process that underlies the victim’s general\\n\\nlosses.” Id. at 458, 134 S. Ct. at 1727. The Supreme Court held that the\\n\\n\\n 58\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 59 of 67\\n\\n\\ngovernment need not establish that some specific portion of the victim’s losses\\n\\nwere directly caused by the defendant possessor’s conduct, as McGarity had\\n\\nrequired. See id.; McGarity, 669 F.3d at 1269. Rather, the government need\\n\\nestablish only that the victim suffered losses from the traffic in her images and that\\n\\nthe defendant contributed to those losses by possessing her images, regardless of\\n\\nwhether the victim was specifically aware of the defendant’s conduct. Paroline,\\n\\n572 U.S. at 458, 134 S. Ct. at 1727; see also id. at 442, 450, 134 S. Ct at 1718,\\n\\n1723 (noting that the parties “stipulated that the victim did not know who Paroline\\n\\nwas and that none of her claimed losses flowed from any specific knowledge about\\n\\nhim or his offense conduct,” and the victim therefore could not show her losses\\n\\n“would have been any different but for Paroline’s offense”).\\n\\n We therefore conclude that the portion of McGarity’s holding requiring the\\n\\ngovernment to show that a child pornography victim was aware of, and specifically\\n\\nharmed by, a particular defendant possessor’s conduct was abrogated by Paroline.\\n\\nSee Archer, 531 F.3d at 1352. Consequently, Rothenberg’s challenge to the\\n\\nrestitution awards for six victims—Sierra, Jane, Sarah, Vicky, Amy, and\\n\\nCasseaopeia—based on that portion of McGarity fails. 10\\n\\n\\n\\n 10\\n The government asserts that Rothenberg did not specifically raise this before-my-arrest\\nargument in the district court, and it should be reviewed only for plain error. We need not decide\\nthat issue; regardless of the standard of review, this claim fails because Paroline overruled this\\npart of McGarity and Paroline was decided before Rothenberg’s offense.\\n\\n 59\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 60 of 67\\n\\n\\nB. Mya and Jenny\\n\\n Next, as to victims Mya and Jenny, Rothenberg argues the government\\n\\nfailed to submit reliable or sufficient evidence of their losses because neither of\\n\\nthose victims had psychological or economic reports detailing their losses. In\\n\\nopposition, the government asserts that it need not submit expert reports to\\n\\nestablish a victim’s losses and that the evidence presented in support of Mya’s and\\n\\nJenny’s restitution requests provided a sufficient basis for the district court’s\\n\\nawards. 11\\n\\n The government bears the burden of proving the restitution amount by a\\n\\npreponderance of the evidence. Osman, 853 F.3d at 1189. The government must\\n\\ndo so “with evidence bearing sufficient indicia of reliability to support its probable\\n\\naccuracy.” Id. (internal quotation marks omitted). Nevertheless, because “the\\n\\ndetermination of the restitution amount is by nature an inexact science,” a district\\n\\ncourt “may accept a reasonable estimate of the loss based on the evidence\\n\\npresented.” Id. (internal quotation marks omitted).\\n\\n\\n\\n\\n 11\\n We disagree with the government’s contention that Rothenberg did not preserve his\\nchallenge to Mya’s and Jenny’s restitution awards on the ground that they were not supported by\\ncompetent evidence. Accordingly, we review the factual findings underlying the district court’s\\nrestitution orders as to Mya and Jenny for clear error, Osman, 853 F.3d at 1188, and the amount\\nof their restitution awards for an abuse of discretion, see Robertson, 493 F.3d at 1330; see also\\nParoline, 572 U.S. at 462, 134 S. Ct at 1729 (recognizing that “[d]istrict courts routinely exercise\\nwide discretion . . . in fashioning restitution orders”).\\n 60\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 61 of 67\\n\\n\\n 1. Mya\\n\\n Regarding Mya, the district court did not clearly err in determining that\\n\\nsufficient evidence supported Mya’s restitution request. One of Mya’s counsel,\\n\\nCarol Hepburn, submitted a signed declaration stating Mya needed therapy and/or\\n\\nmedical care. Rothenberg faults the district court for accepting the “self-serving”\\n\\nestimate provided by Mya’s counsel that Mya’s future medical costs would likely\\n\\nexceed $100,000. In her declaration, Hepburn explained that the $100,000\\n\\nestimate was not just pulled out of thin air. Rather, it was based on Hepburn’s\\n\\nexperience representing eight other, similarly situated child pornography victims.\\n\\nIndeed, the restitution exhibits presented to the district court show that Hepburn\\n\\nrepresented or co-represented several of the other victims in this case—Sierra, Pia,\\n\\nSarah, and Vicky. Considering Hepburn’s demonstrated experience in this area, it\\n\\nwas not unreasonable for the district court to consider her estimate as reliable\\n\\nevidence of Mya’s likely future costs. See id.\\n\\n Furthermore, counsel Hepburn explained that Mya was part of the same\\n\\nchild pornography series as Pia. Though a psychological evaluation was\\n\\nunavailable for Mya at the time of the restitution hearing, 12 her co-victim Pia was\\n\\n\\n\\n 12\\n In challenging Mya’s and Jenny’s awards, Rothenberg also argues that a victim must\\nalways supply an expert medical or psychological report to support her restitution request.\\nRothenberg cites no caselaw for this proposition, and nothing in either Paroline or our own\\nprecedent establishes such a rigid requirement. See Osman, 853 F.3d at 1189 (requiring only\\nthat the government present evidence “bearing sufficient indicia of reliability”). Though such\\n 61\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 62 of 67\\n\\n\\nable to submit a preliminary evaluation. That evaluation indicated that, at a bare\\n\\nminimum, Pia had estimated therapy costs of $81,900 and emphasized that this\\n\\nestimate reflected “only the current, most critical needs” for Pia, who like Mya was\\n\\nstill a minor, and did not account for the full extent of her losses or the services she\\n\\nwould require over the course of her lifetime. And notably, Rothenberg does not\\n\\nchallenge the evidentiary basis for Pia’s restitution award in this case. That Mya’s\\n\\nco-victim Pia had preliminary estimated costs of at least $81,900 is a further\\n\\nindicator that counsel Hepburn’s $100,000 total cost estimate for Mya was\\n\\nreasonable and appropriately relied upon by the district court. See id. On this\\n\\nrecord, we are not left with a definite and firm conviction that the district court was\\n\\nmistaken in concluding that sufficient evidence supported Mya’s restitution\\n\\nrequest. See Robertson, 493 F.3d at 1330.\\n\\n Nor did the district court abuse its broad discretion in awarding Mya her\\n\\nrequested restitution amount of $5,000. See id. Here, the district court properly\\n\\nidentified Paroline as the correct legal standard for awarding restitution in child\\n\\npornography cases. In setting the amount of Mya’s restitution award, the district\\n\\ncourt addressed several relevant Paroline factors, noting that: (1) Rothenberg\\n\\npossessed one image of Mya; (2) no other defendant was yet ordered to pay\\n\\n\\n\\n\\nexpert reports are undoubtedly helpful to district court’s in fashioning a restitution award, they\\nare by no means the only way to establish a reasonable estimate of a victim’s losses.\\n 62\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 63 of 67\\n\\n\\nrestitution to Mya; (3) Mya had estimated losses exceeding $100,000; and\\n\\n(4) Rothenberg neither created nor distributed Mya’s images. Paroline, 572 U.S. at\\n\\n460, 134 S. Ct. at 1728. In light of these factors, the district court determined that\\n\\nMya’s $5,000 restitution request was reasonable. Given the wide discretion\\n\\nafforded by Paroline to district courts in this context, we cannot say this\\n\\ndetermination was unreasonable. See id. at 462, 134 S. Ct. at 1729; Jordan, 582\\n\\nF.3d at 1249.\\n\\n 2. Jenny\\n\\n Based on the more limited record as to Jenny, we agree with Rothenberg that\\n\\nthe district court clearly erred in determining there was sufficient evidence to\\n\\nsupport Jenny’s $42,600 request. In support of her restitution request, Jenny’s\\n\\ncounsel submitted a restitution cover letter and a victim impact statement from\\n\\nJenny. In the letter, Jenny’s counsel requested restitution in the following\\n\\namounts: (1) $12,500 to pay for psychological and economic reports; (2) $5,000 in\\n\\nattorney’s fees related to her request in this case; (3) $100 in legal fees related to\\n\\nher request in this case; and (4) $25,000 for “the defendant’s appropriate share of\\n\\nthe general losses caused to Jenny.”\\n\\n Like Mya, at the time of the restitution hearing, Jenny was still in the\\n\\nprocess of obtaining expert reports documenting her total losses. Unlike Mya,\\n\\nhowever, Jenny’s separate counsel did not provide any reasonable estimate of what\\n\\n\\n 63\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 64 of 67\\n\\n\\nthose total losses might be. Indeed, counsel did not provide any estimate of what\\n\\nJenny’s total losses might be. Rather, in asserting that $25,000 was Rothenberg’s\\n\\n“appropriate share” of Jenny’s losses, counsel relied on (1) a proposed statute that\\n\\nwould set a minimum restitution award of $25,000 for possession of child\\n\\npornography, and (2) Masha’s law, 18 U.S.C. § 2255(a), which creates a civil\\n\\ncause of action for victims who suffered personal injury as a result of a child\\n\\npornography offense and sets a liquidated damages amount of $150,000.\\n\\n This evidence is sufficient to show that Jenny has incurred costs of\\n\\n$17,600—to pay for expert reports and legal fees—in connection with her\\n\\nrestitution request in this case, 13 yet it is not sufficient to establish what proportion\\n\\nof Jenny’s as-yet-undetermined total losses Rothenberg proximately caused.\\n\\nJenny’s counsel suggested that the $150,000 liquidated damages amount in\\n\\nMasha’s Law represents a reasonable estimate by Congress of the minimum\\n\\namount of total damages suffered by a child pornography victim. But the damages\\n\\navailable to a plaintiff in a civil lawsuit may be quite different from the concrete\\n\\n“costs incurred” for which § 2259 provides recompense. See 18 U.S.C.\\n\\n§ 2259(c)(2). For example, a plaintiff in a civil damages suit under § 2255(a) may\\n\\nbe able to recover for noneconomic losses, such as pain and suffering or mental\\n\\n\\n 13\\n We note that the $12,500 portion of those costs for psychological and economic reports\\nwould not necessarily be fully attributable to Rothenberg, as Jenny will, unfortunately but\\nundoubtedly, need to use those reports in support of future requests against other defendants.\\n 64\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 65 of 67\\n\\n\\nand emotional distress, that are not available in a restitution proceeding under\\n\\n§ 2259. See Doe v. Hesketh, 828 F.3d 159, 170 (3d Cir. 2016). As such, we do\\n\\nnot see that Masha’s Law provides much guidance in the present context.\\n\\n Similarly, Jenny’s counsel’s reliance on proposed legislation setting a\\n\\nminimum $25,000 restitution award for child pornography possession offenses also\\n\\nprovides little to no guidance here. While Congress certainly would be well within\\n\\nits rights to establish such a mandatory minimum restitution amount in these cases,\\n\\nit had not done so at the time of Rothenberg’s restitution hearing. 14 Thus, the\\n\\ndistrict court was required to instead follow Paroline’s framework, which requires\\n\\nan individualized assessment of each particular defendant’s restitutionary liability\\n\\nbased on his conduct and relative role in the causal process. Paroline, 572 U.S. at\\n\\n445, 458-59, 462, 134 S. Ct. at 1720, 1727-29. Imposing a pre-set minimum\\n\\namount of restitution based solely on the type of offense Rothenberg committed\\n\\ndoes not comply with Paroline’s framework, and the government did not submit\\n\\nevidence from which the district court reasonably could have determined that\\n\\n$25,000 was Rothenberg’s relative share of Jenny’s losses.\\n\\n\\n\\n\\n 14\\n Congress recently passed, and the president signed, a different version of the bill\\nJenny’s counsel referred to, but that version sets the minimum restitution amount much lower, at\\n$3,000. See Amy, Vicky, and Andy Child Pornography Victim Assistance Act of 2018, Pub. L.\\nNo. 115-299, 132 Stat. 4383 (2018).\\n\\n 65\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 66 of 67\\n\\n\\n It is indisputable that Jenny has suffered some, likely large amount of losses\\n\\nfrom the online traffic in her images. See id. at 457, 134 S. Ct. at 1726. It is also\\n\\nindisputable that Rothenberg, who possessed 34 images and 1 video of Jenny, is\\n\\nresponsible for some, possibly significant amount of those losses. Id. But the\\n\\ngovernment bears the burden of proving at least a reasonable estimate of that\\n\\namount based on reliable evidence, and it has not satisfied that burden here.\\n\\nOsman, 853 F.3d at 1189. In the absence of competent evidence to support the\\n\\naward, the district court clearly erred in ordering Rothenberg to pay $42,600 in\\n\\nrestitution to Jenny. See id.\\n\\n We therefore vacate the district court’s restitution award as to Jenny and\\n\\nremand for further proceedings consistent with this opinion. On remand, the\\n\\ndistrict court should allow Jenny to supplement her restitution request with\\n\\nevidence of her losses. See 18 U.S.C. § 3664(d)(5) (allowing a victim to seek an\\n\\namended restitution order if the victim discovers additional losses after\\n\\nsentencing). The district court should then determine, in light of all the available\\n\\nevidence and the Paroline factors, the portion of Jenny’s losses for which\\n\\nRothenberg is responsible. Paroline, 572 U.S. at 458-60, 134 S. Ct. at 1727-28.\\n\\n\\n\\n\\n 66\\n\\f Case: 17-12349 Date Filed: 05/08/2019 Page: 67 of 67\\n\\n\\n IX. CONCLUSION\\n\\n For the foregoing reasons, we affirm the district court’s restitution order as\\n\\nto victims Sierra, Jane, Pia, Mya, Sarah, Vicky, Amy, and Casseaopeia, and vacate\\n\\nand remand the district court’s restitution order as to victim Jenny.\\n\\n AFFIRMED in part; VACATED and REMANDED in part.\\n\\n\\n\\n\\n 67\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2276,"cells":{"id":{"kind":"number","value":4618173,"string":"4,618,173"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Nyreekis Jarnell Hunter v. Mike Hale"},"decision_date":{"kind":"string","value":"2019-05-09"},"docket_number":{"kind":"string","value":"18-10487"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before TJOFLAT, NEWSOM, and GILMAN, * Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"NEWSOM, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-10487 Date Filed: 05/09/2019 Page: 1 of 23\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-10487\\n ________________________\\n\\n D.C. Docket No. 2:16-cv-01521-MHH\\n\\nANTHONY PIAZZA,\\nas personal representative of the Estate of\\nRicky DeAngelo Hinkle, deceased,\\n\\n Plaintiff,\\n\\nNYREEKIS JARNELL HUNTER,\\nas personal representative of the Estate of\\nRicky DeAngelo Hinkle, deceased,\\n\\n Plaintiff - Appellee,\\n\\n\\n versus\\n\\nJEFFERSON COUNTY, ALABAMA,\\nan Alabama county, individually, et al,\\n\\n Defendants,\\n\\nMIKE HALE,\\nRON EDDINGS,\\nHABIMANA DUKUZUMUREMYI,\\neach individually,\\n\\n Defendants - Appellants.\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 2 of 23\\n\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Alabama\\n ________________________\\n\\n (May 9, 2019)\\n\\nBefore TJOFLAT, NEWSOM, and GILMAN, * Circuit Judges.\\n\\nNEWSOM, Circuit Judge:\\n\\n Ricky Hinkle died in the Birmingham City Jail after being shocked with a\\n\\ntaser, twice. Hinkle’s son, Nyreekis Hunter, brought suit under 42 U.S.C. § 1983\\n\\nalleging several claims on his behalf, including, as relevant here, (1) an excessive-\\n\\nforce claim against Deputy Habimana Dukuzumuremyi and (2) supervisory-\\n\\nliability claims for excessive force and deliberate indifference to Hinkle’s serious\\n\\nmedical needs against Sheriff Mike Hale and Captain Ron Eddings. The officers\\n\\nmoved to dismiss Hunter’s suit based on qualified immunity, the district court\\n\\ndenied their motion, and the officers now appeal.\\n\\n After careful review, we agree in part and disagree in part with the district\\n\\ncourt’s decision. We agree that the facts as Hunter has pleaded them show that\\n\\nDeputy Dukuzumuremyi violated Hinkle’s clearly established constitutional right\\n\\nto be free from excessive force. In particular, we hold that Dukuzumuremyi\\n\\ncrossed the constitutional line, and clearly so, when, having already tased Hinkle\\n\\n\\n*\\n Honorable Ronald Lee Gilman, United States Circuit Judge for the Sixth Circuit, sitting by\\ndesignation.\\n 2\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 3 of 23\\n\\n\\nonce—dropping him to the floor, rendering him motionless, and causing him to\\n\\nurinate on himself—Dukuzumuremyi shocked him again a full eight seconds later.\\n\\nWe disagree, however, that Hunter’s allegations show—as they must to support a\\n\\nsupervisory-liability claim—a causal connection between either the use of force\\n\\nagainst Hinkle or any deliberate indifference to Hinkle’s serious medical needs, on\\n\\nthe one hand, and any policy or custom implemented by Sheriff Hale or Captain\\n\\nEddings, on the other. Accordingly, we affirm the district court’s decision to deny\\n\\nqualified immunity to Deputy Dukuzumuremyi but reverse its decision to deny\\n\\nqualified immunity to Sheriff Hale and Captain Eddings.\\n\\n I\\n\\n Ricky Hinkle, who suffered from alcoholism, heart disease, and depression,\\n\\nwas arrested while “visibly intoxicated” and was taken to the Jefferson County Jail\\n\\nin Bessemer, Alabama. 1 The next day, he was transferred to the Birmingham City\\n\\nJail. Soon thereafter, he began suffering from alcohol-withdrawal symptoms and\\n\\nexhibiting delusional behavior. Jail officers moved Hinkle three different times\\n\\nbefore eventually (and presumably due to his deteriorating condition) placing him\\n\\nin a cell on Level 3, where Deputies Habimana Dukuzumuremyi and Christopher\\n\\nCotten were working.\\n\\n\\n1\\n The factual allegations in this case are largely undisputed, but because this appeal arises in a\\nmotion-to-dismiss posture, where the parties’ memories diverge we adopt Hunter’s re-telling.\\nSee Cottone v. Jenne, 326 F.3d 1352, 1357 (11th Cir. 2003).\\n 3\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 4 of 23\\n\\n\\n Shortly after Hinkle arrived on Level 3, Dukuzumuremyi realized that he\\n\\ncouldn’t see him on the video monitor, so he called to him over the loudspeaker.\\n\\nWhen Hinkle didn’t respond, Cotten went to investigate and found Hinkle in the\\n\\ncorner of his cell, wearing only underpants and shoes. When Cotten asked Hinkle\\n\\nwhy he was in the corner, Hinkle responded that he “wanted to die.” At this,\\n\\nCotten decided to move Hinkle to a padded cell. He walked Hinkle toward the cell\\n\\nand asked him to remove his shoes. Hinkle initially obeyed but then ran down the\\n\\nhallway to the bathroom and grabbed a shower curtain. Cotten took the shower\\n\\ncurtain away from Hinkle shortly before Dukuzumuremyi arrived on the scene.\\n\\n After the officers attempted three times to pull Hinkle into his new cell,\\n\\nDukuzumuremyi fired his taser, hitting Hinkle on the left side of his chest just\\n\\nabove his heart. As a result of that taser shock—which lasted 5 seconds—Hinkle\\n\\nfell to the floor on his right side and urinated on himself. Dukuzumuremyi then\\n\\nordered Hinkle to roll over to be handcuffed, but Hinkle remained unresponsive.\\n\\nEight seconds after the end of the first shock, and while Hinkle still lay motionless\\n\\n(and wet) on the ground, Dukuzumuremyi tased him again, this time on the front\\n\\nleft side of his neck. Shortly after the second shock, Hinkle went into cardiac\\n\\narrest. He was taken to the emergency room, where he was pronounced dead.\\n\\n\\n\\n\\n 4\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 5 of 23\\n\\n\\n Hinkle’s son Nyreekis Hunter, acting as personal representative of Hinkle’s\\n\\nestate, brought suit under 42 U.S.C. § 1983 on Hinkle’s behalf.2 As relevant here,\\n\\nHunter sued Deputy Dukuzumuremyi for excessive force and Deputy Cotten for\\n\\nfailure to intervene, and both deputies for deliberate indifference to Hinkle’s\\n\\nserious medical needs. He also sued Sheriff Hale and Captain Eddings on a\\n\\nsupervisory-liability theory based on the excessive-force and deliberate-\\n\\nindifference claims. The officers moved to dismiss on qualified-immunity\\n\\ngrounds.3\\n\\n The district court granted in part and denied in part the officers’ motion to\\n\\ndismiss. The court dismissed the deliberate-indifference claim against\\n\\nDukuzumuremyi and Cotten, finding that the complaint “contain[ed] no allegations\\n\\nto indicate that either deputy had subjective knowledge of the decedent’s medical\\n\\ncondition.” The court also dismissed the failure-to-intervene claim against\\n\\nCotten. 4 But the court denied the motion to dismiss as to (1) the excessive-force\\n\\n\\n\\n\\n2\\n The initial complaint was filed by Anthony Piazza, who is not related to Hinkle. After some\\ndispute over whether Piazza could properly represent Hinkle’s estate, Hunter replaced Piazza as\\nHinkle’s personal representative.\\n3\\n Hunter also brought state-law claims against each officer for negligence and wrongful death;\\nthe district court dismissed each claim on state-law grounds.\\n4\\n Deputy Cotten is not a party to this appeal because the district court dismissed all claims against\\nhim. Two other defendants, Dr. David Hicks and Advanced Correctional Healthcare, were also\\nnamed in Hunter’s complaint—for exhibiting deliberate indifference to Hinkle’s serious medical\\nneeds—but neither is a party to this appeal.\\n\\n 5\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 6 of 23\\n\\n\\nclaim against Dukuzumuremyi and (2) the supervisory-liability claims against Hale\\n\\nand Eddings. Dukuzumuremyi, Hale, and Eddings timely appealed.5\\n\\n II\\n\\n We review de novo a district court’s denial of qualified immunity. Cottone\\n\\nv. Jenne, 326 F.3d 1352, 1357 (11th Cir. 2003). Qualified immunity shields a\\n\\ngovernment official from liability unless he violates “clearly established statutory\\n\\nor constitutional rights of which a reasonable person would have known.” Foy v.\\n\\nHolston, 94 F.3d 1528, 1532 (11th Cir. 1996). An officer asserting a qualified-\\n\\nimmunity defense bears the initial burden of showing that he was “acting within\\n\\nhis discretionary authority.” Skop v. City of Atlanta, 485 F.3d 1130, 1136 (11th\\n\\nCir. 2007). After the officer makes this showing—and here, it is undisputed—the\\n\\nburden shifts to the plaintiff to show that (1) the officer violated a constitutional\\n\\nright and (2) the right was clearly established at the time of the alleged\\n\\nviolation. Holloman ex rel. Holloman v. Harland, 370 F.3d 1252, 1264 (11th Cir.\\n\\n2004). We may consider these two prongs in either order; an official is entitled to\\n\\n\\n\\n\\n5\\n We have jurisdiction over the officers’ interlocutory appeal under 28 U.S.C. § 1291 because the\\ndistrict court denied qualified immunity based on questions of law—namely, whether the officers\\nviolated Hinkle’s constitutional rights and whether those rights were clearly established. See\\nMitchell v. Forsyth, 472 U.S. 511, 530 (1985) (“[A] district court’s denial of a claim of qualified\\nimmunity, to the extent that it turns on an issue of law, is an appealable ‘final decision’ within\\nthe meaning of 28 U.S.C. § 1291 notwithstanding the absence of a final judgment.”).\\n\\n\\n 6\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 7 of 23\\n\\n\\nqualified immunity if the plaintiff fails to establish either. Jacoby v. Baldwin\\n\\nCounty, 835 F.3d 1338, 1344 (11th Cir. 2016).\\n\\n We start with the excessive-force claim against Deputy Dukuzumuremyi,\\n\\nand then move to the supervisory-liability claims against Sheriff Hale and Captain\\n\\nEddings.\\n\\n A\\n\\n 1\\n\\n First things first. What constitutional provision governs the use of force in\\n\\nthis case, and what doctrinal standard guides our analysis? While the Fourth\\n\\nAmendment prevents the use of excessive force during arrests, see Graham v.\\n\\nConnor, 490 U.S. 386, 388 (1989), and the Eighth Amendment serves as the\\n\\nprimary source of protection against excessive force after conviction, see Whitley\\n\\nv. Albers, 475 U.S. 312, 327 (1986), it is the Fourteenth Amendment that protects\\n\\nthose who exist in the in-between—pretrial detainees. Garrett v. Athens–Clarke\\n\\nCounty, 378 F.3d 1274, 1279 n.11 (11th Cir. 2004).6\\n\\n That pretrial detainees fall within the Fourteenth Amendment’s ambit dates\\n\\nto the Supreme Court’s decision in Bell v. Wolfish, 441 U.S. 520 (1979). The\\n\\n\\n6\\n Although some courts have extended Fourth Amendment protections into the pretrial detention\\nphase, see, e.g., Aldini v. Johnson, 609 F.3d 858, 866 (6th Cir. 2010), “[n]either [this Court] nor\\nthe Supreme Court has decided whether the Fourth Amendment continues to provide individuals\\nwith protection from excessive force beyond the point at which an arrest ends and pretrial\\ndetention begins,” J W by & through Tammy Williams v. Birmingham Board of Education, 904\\nF.3d 1248, 1259 (11th Cir. 2018).\\n 7\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 8 of 23\\n\\n\\nCourt explained there that the “proper inquiry” when “evaluating the\\n\\nconstitutionality of conditions or restrictions of pretrial detention” is “whether\\n\\nthose conditions amount to punishment of the detainee.” Id. at 535. “For under\\n\\nthe Due Process Clause,” the Court continued, “a detainee may not be punished\\n\\nprior to an adjudication of guilt in accordance with due process of law.” Id.\\n\\n Although pretrial detainees’ excessive-force claims have been analyzed\\n\\nunder the Fourteenth Amendment since Bell, the constitutional inquiry—at least in\\n\\nthis Circuit—has long resembled the one that governs prisoners’ excessive-force\\n\\nclaims under the Eighth Amendment. Historically, both prisoners and pretrial\\n\\ndetainees needed to show not only that a jail official deliberately used excessive\\n\\nforce, but also that the official did so “maliciously or sadistically for the very\\n\\npurpose of causing harm.” Bozeman v. Orum, 422 F.3d 1265, 1271 (11th Cir.\\n\\n2005), overruled by Kingsley v. Hendrickson, 135 S. Ct. 2466, 2473 (2015). All\\n\\nthat changed a few years back, though, when the Supreme Court clarified that,\\n\\nunlike a prisoner bringing an Eighth Amendment excessive-force claim, a pretrial\\n\\ndetainee raising a Fourteenth Amendment claim needn’t prove an officer’s\\n\\nsubjective intent to harm but instead need show only that “the force purposely or\\n\\nknowingly used against him was objectively unreasonable.” Kingsley, 135 S. Ct.\\n\\nat 2473.\\n\\n\\n\\n\\n 8\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 9 of 23\\n\\n\\n Harking back to Bell, the Kingsley Court explained that, unlike in Eighth\\n\\nAmendment cases, there is no need in the pretrial-detainee context to determine\\n\\n“when punishment is unconstitutional” because a pretrial detainee has not yet been\\n\\nadjudicated guilty and thus may not be punished at all. Id. at 2475 (emphasis\\n\\nadded). Although, under Bell, impermissible “punishment” could mean force\\n\\ndeployed with a subjective, “expressed intent to punish,” it also could mean force\\n\\nthat, as an objective matter, is “not rationally related to a legitimate governmental”\\n\\npurpose or is “excessive in relation to that purpose.” Id. at 2473–74. After\\n\\nKingsley, then, if force used against a pretrial detainee is more severe than is\\n\\nnecessary to subdue him or otherwise achieve a permissible governmental\\n\\nobjective, it constitutes “punishment” and is therefore unconstitutional. Notably,\\n\\ninasmuch as it entails an inquiry into the objective reasonableness of the officers’\\n\\nactions, the Fourteenth Amendment standard has come to resemble the test that\\n\\ngoverns excessive-force claims brought by arrestees under the Fourth Amendment.\\n\\nCompare Kingsley, 135 S. Ct. at 2472–73 (holding that a pretrial detainee in the\\n\\nFourteenth Amendment context “must show only that the force purposely or\\n\\nknowingly used against him was objectively unreasonable”), with Graham, 490\\n\\nU.S. at 397 (explaining that the Fourth Amendment excessive-force inquiry asks\\n\\n“whether the officers’ actions are ‘objectively reasonable’ in light of the facts and\\n\\n\\n\\n\\n 9\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 10 of 23\\n\\n\\ncircumstances confronting them, without regard to their underlying intent or\\n\\nmotivation”).\\n\\n Obviously, “legitimate interests”—including the need to “preserve internal\\n\\norder and discipline” and “maintain institutional security”—may at times require\\n\\njail officers to use force. Kingsley, 135 S. Ct. at 2473 (citation omitted). And of\\n\\ncourse, officers facing disturbances are often forced to make “split-second\\n\\njudgments” about the need for such force “in circumstances that are tense,\\n\\nuncertain, and rapidly evolving.” Id. at 2474 (quoting Graham, 490 U.S. at 397).\\n\\nBecause of this, we can’t (and won’t) evaluate a pretrial detainee’s excessive-force\\n\\nchallenge in a glib, post-hoc fashion or “with the 20/20 vision of hindsight.” Id. at\\n\\n2473. Instead, we must do our best to consider the situation through the lens of “a\\n\\nreasonable officer on the scene.” Id.\\n\\n How do we know, then, when force is reasonable and when it is “excessive\\n\\nin relation to its purpose”? Well, as relevant to this case, our decisions make one\\n\\nthing clear: “Once a prisoner has stopped resisting there is no longer a need for\\n\\nforce, so the use of force thereafter is disproportionate to the need.” Danley v.\\n\\nAllen, 540 F.3d 1298, 1309 (11th Cir. 2008) (emphasis added), abrogated on other\\n\\ngrounds by Kingsley, 135 S. Ct. 2466. Accordingly, “[w]hen jailers continue to\\n\\nuse substantial force against a prisoner who has clearly stopped resisting—whether\\n\\nbecause he has decided to become compliant, he has been subdued, or he is\\n\\n\\n 10\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 11 of 23\\n\\n\\notherwise incapacitated—that use of force is excessive.” Id. (emphasis added); see\\n\\nalso Ort v. White, 813 F.2d 318, 327 (11th Cir. 1987) (“A [F]ourteenth\\n\\n[A]mendment violation occurs . . . where prison officers continue to employ force\\n\\nor other coercive measures after the necessity for such coercive action has\\n\\nceased.”); Bozeman, 422 F.3d at 1271–72 (finding excessive force when officers\\n\\ncontinued to suffocate a detainee by pushing his face into a mattress after he had\\n\\nstopped struggling and said he’d had enough), overruled on other grounds by\\n\\nKingsley, 135 S. Ct. 2466.7 In other words, because force in the pretrial detainee\\n\\ncontext may be defensive or preventative—but never punitive—the continuing use\\n\\nof force is impermissible when a detainee is complying, has been forced to comply,\\n\\nor is clearly unable to comply.\\n\\n 2\\n\\n In the case before us, then, we must determine whether the force used\\n\\nagainst Hinkle was objectively unreasonable—i.e., whether it was “excessive in\\n\\nrelation to [its] purpose.” Kingsley, 135 S. Ct. at 2473–74. To briefly recap, the\\n\\ncritical events began when Hinkle broke away from Cotten, ran down the hallway,\\n\\n\\n7\\n To be clear, Bozeman and Danley remain relevant to our inquiry even though both employed\\nthe more stringent pre-Kingsley standard of proof: whether force was applied “maliciously or\\nsadistically for the very purpose of causing harm.” Bozeman, 422 F.3d at 1272. Because\\nproving both that the force applied in a given situation was objectively excessive and that it was\\napplied “maliciously or sadistically for the very purpose of causing harm” will almost invariably\\nbe more difficult than proving only that the force used was objectively excessive, these cases\\ncontinue to provide pertinent examples of excessive force in the pretrial-detainee context.\\n\\n 11\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 12 of 23\\n\\n\\nand grabbed a shower curtain. (Not the curtain rod, mind you—the curtain.) After\\n\\nthree unsuccessful attempts to lead Hinkle into his cell, Dukuzumuremyi fired his\\n\\ntaser, hitting Hinkle just above the heart with a five-second shock. Eight seconds\\n\\nafter the first shock ended—and with Hinkle still prostrate on the ground, and\\n\\nhaving wet himself—Dukuzumuremyi tased Hinkle again.\\n\\n The parties don’t dispute that the first shock was a permissible use of force\\n\\ngiven Hinkle’s resistance and the officers’ need to “preserve internal order and\\n\\ndiscipline” and “maintain institutional security.” See Kingsley, 135 S. Ct. at 2473.\\n\\nThe issue is the second shock. Dukuzumuremyi asserts that the second shock\\n\\ndoesn’t constitute excessive force in light of (1) Hinkle’s failure to roll over to be\\n\\nhandcuffed “after being ordered—and being given an opportunity—to do so,” and\\n\\n(2) the “split-second decisions” that jail officers must make. The facts alleged,\\n\\nhowever, undermine both assertions.\\n\\n Again, according to Hunter’s complaint, following the first taser shock\\n\\nHinkle fell to the floor, lay motionless, and urinated on himself. Even so,\\n\\nDukuzumuremyi contends that because Hinkle failed to obey the subsequent order\\n\\nto roll over and be handcuffed, he was not yet fully compliant. Because Hinkle\\n\\nwas not following commands, the argument goes, the second shock couldn’t have\\n\\ncrossed the constitutional line. Oral Arg. Tr. 7:07. Wrong. It seems to us totally\\n\\nunreasonable to expect that a man who is lying on the floor immobilized—and\\n\\n\\n 12\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 13 of 23\\n\\n\\nincontinent—following a taser shock should pep up, roll over, and submit to\\n\\nhandcuffing within eight seconds. But, Dukuzumuremyi counters, Hunter’s\\n\\ncomplaint doesn’t specifically allege that Hinkle “could not” roll over, only that he\\n\\n“did not.” Oral Arg. Tr. 7:45. Come on. The only reasonable inference is that\\n\\nHinkle, who was lying motionless on the floor after a five-second taser shock—\\n\\nunable to hold his own urine—“did not” immediately roll over because he “could\\n\\nnot.” (Really, is there any surer indication of a grown man’s inability to control his\\n\\nbodily functions than his wetting himself?)\\n\\n The same facts undermine Dukuzumuremyi’s contention that the second\\n\\nshock should be swept into the zone of reasonableness by the deference owed an\\n\\nofficer’s split-second decisions. Although we don’t for a minute discount the\\n\\ndifficult decisions that jail officers must make in the heat of a tussle, simply\\n\\ncounting to eight aloud reveals the problem with Dukuzumuremyi’s argument. In\\n\\neight seconds, you can tie a shoe, sing the chorus of “Row, Row, Row Your Boat,”\\n\\nor complete a qualified rodeo bull ride. And in eight seconds, we believe, any\\n\\nreasonable officer would have concluded that a detainee who lay inert on the floor,\\n\\nhaving soiled himself, was no longer putting up a fight. See Kingsley, 135 S. Ct. at\\n\\n2473 (listing “whether the plaintiff was actively resisting” and “any effort made by\\n\\nthe officer to temper or to limit the amount of force used” as factors potentially\\n\\nrelevant to the excessive-force determination).\\n\\n\\n 13\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 14 of 23\\n\\n\\n Our conclusion is fortified by additional considerations that the Supreme\\n\\nCourt mentioned in Kingsley that “bear on the reasonableness or unreasonableness\\n\\nof the force used,” including the severity of the security issue posed by the detainee\\n\\nand the threat reasonably perceived by the officer. See Kingsley, 135 S. Ct. at\\n\\n2473. Although officers may (of course) use force to “preserve internal order and\\n\\ndiscipline” and “maintain institutional security,” the severity of the problem and\\n\\nthe corresponding risk to the officers in this case were—from the very outset—\\n\\nexceedingly minimal. See id. Instead of facing, say, a man armed with a knife\\n\\nrunning toward them, the officers here faced a man armed with a shower curtain\\n\\nrunning away from them. See, e.g., Shaw v. City of Selma, 884 F.3d 1093, 1099\\n\\n(11th Cir. 2018) (officer entitled to qualified immunity on an excessive-force claim\\n\\nafter shooting a mentally-ill man walking toward him with a hatchet); Smith v.\\n\\nLePage, 834 F.3d 1285, 1294–95 (11th Cir. 2016) (officer entitled to qualified\\n\\nimmunity on an excessive-force claim when a suspect holding a knife refused to\\n\\ncomply with orders to disarm himself); Singletary v. Vargas, 804 F.3d 1174, 1185\\n\\n(11th Cir. 2015) (officer entitled to qualified immunity on an excessive-force claim\\n\\nbased on his reasonable belief that a car rolling toward him presented a deadly\\n\\nthreat). Although non-compliant, Hinkle had neither threatened nor attempted to\\n\\nharm the officers. While we don’t question Dukuzumuremyi’s split-second\\n\\ndecision to deploy his taser once following several unsuccessful attempts to lead\\n\\n\\n 14\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 15 of 23\\n\\n\\nHinkle into his cell, we see no legitimate basis for the second shock, particularly\\n\\nconsidering (1) that the first shock had immobilized Hinkle and (2) the minimal\\n\\nthreat to order, safety, and security that Hinkle posed even from the outset.\\n\\n At the end of the day the question before us is this: Is it excessive to tase for\\n\\na second time a man who, as a result of an initial shock, is lying motionless on the\\n\\nfloor and has wet himself, and who presented only a minimal threat to begin with?\\n\\nUndoubtedly, yes. We hold that, based on the allegations in Hunter’s complaint,\\n\\nthe force used against Hinkle was excessive, and thus unconstitutional.\\n\\n 3\\n\\n Of course, to overcome Dukuzumuremyi’s qualified-immunity defense,\\n\\nHunter must further show that the law that governs his case was “clearly\\n\\nestablished” at the time of the alleged violation. To qualify, a legal principle must\\n\\nbe “settled” and “clear enough that every reasonable official would interpret it to\\n\\nestablish the particular rule the plaintiff seeks to apply.” District of Columbia v.\\n\\nWesby, 138 S. Ct. 577, 589–90 (2018). The critical question is whether the law\\n\\ngave the officer “fair warning” that his conduct was unconstitutional. Glasscox v.\\n\\nCity of Argo, 903 F.3d 1207, 1217–18 (11th Cir. 2018) (citing Hope v. Pelzer, 536\\n\\nU.S. 730, 741 (2002)).\\n\\n Here, it certainly did. It was more than ten years ago now that this Court\\n\\nheld, in no uncertain terms, that “[w]hen jailers continue to use substantial force\\n\\n\\n 15\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 16 of 23\\n\\n\\nagainst a prisoner who has clearly stopped resisting—whether because he has\\n\\ndecided to become compliant, he has been subdued, or he is otherwise\\n\\nincapacitated—that use of force is excessive.” Danley, 540 F.3d at 1309; see also\\n\\nid. (“Once a prisoner has stopped resisting there is no longer a need for force, so\\n\\nthe use of force thereafter is disproportionate to the need.”).8 And Danley was no\\n\\ninnovation; for decades our decisions have embraced and reiterated the principle\\n\\nthat an officer may not continue to use force after a detainee has clearly stopped\\n\\nresisting. See Skrtich v. Thornton, 280 F.3d 1295, 1303 (11th Cir. 2002)\\n\\n(“[G]overnment officials may not use gratuitous force against a prisoner who has\\n\\nbeen already subdued or, as in this case, incapacitated.”); Williams v. Burton, 943\\n\\nF.2d 1572, 1576 (11th Cir. 1991) (“The basic legal principle is that once the\\n\\nnecessity for the application of force ceases, any continued use of harmful force\\n\\ncan be a violation of the Eighth and Fourteenth Amendments.”); Ort, 813 F.2d at\\n\\n327 (“A [F]ourteenth [A]mendment violation occurs . . . where prison officers\\n\\ncontinue to employ force or other coercive measures after the necessity for such\\n\\ncoercive action has ceased.”).9\\n\\n8\\n Again, although Kingsley changed the nature of the inquiry—by dropping the requirement that\\na plaintiff prove the officers’ subjective malicious intent—it did not change the law with respect\\nto the objective reasonableness of using force against unresisting subjects.\\n9\\n The same basic rule guides our Fourth Amendment cases concerning the use of force against\\nunresisting or subdued arrestees. See, e.g., Hadley v. Gutierrez, 526 F.3d 1324, 1330 (11th Cir.\\n2008) (punching a suspect in the stomach constituted excessive force when he was already\\nsubdued and not struggling); Lee v. Ferraro, 284 F.3d 1188, 1200 (11th Cir. 2002) (slamming a\\nsuspect’s head onto the hood of her car constituted excessive force when she no longer posed a\\n 16\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 17 of 23\\n\\n\\n To be clear, it is no answer to say that Danley involved pepper spray, Skrtich\\n\\nkicks and punches, Williams four-point restraints, etc.—and that none of those\\n\\ncases concerned the use of a taser specifically. It’s true, of course, that to defeat\\n\\nqualified immunity a rule must be specific enough that an act’s unlawfulness\\n\\n“follow[s] immediately from the conclusion that the rule was firmly established,”\\n\\nWesby, 138 S. Ct. at 590 (citation omitted). But we have never suggested that the\\n\\nlongstanding prohibition on a jail officer’s use of force on an incapacitated\\n\\ndetainee turns on as fine a point as the particular weapon deployed. And indeed, in\\n\\nthe analogous Fourth Amendment context, we have flatly rejected that very\\n\\ndistinction—in a case involving a taser, no less. In Fils v. City of Aventura, we\\n\\nconsidered allegations that police officers had impermissibly tased a non-violent,\\n\\nunresisting suspect. 647 F.3d 1272, 1288–90 (11th Cir. 2011). In finding the law\\n\\nprohibiting the tasing clearly established, we relied on one case holding that an\\n\\nofficer had used excessive force when he pepper-sprayed a secured suspect in the\\n\\nface as she sat shackled in the backseat of his cruiser, see id. at 1289 (citing\\n\\nVinyard v. Wilson, 311 F.3d 1340 (11th Cir. 2002)), another holding that an officer\\n\\nhad used excessive force when he punched a handcuffed and unresisting plaintiff\\n\\nin the stomach, see id. (citing Hadley v. Gutierrez, 526 F.3d 1324 (11th Cir.\\n\\n\\n\\nthreat to the officer nor a flight risk); Slicker v. Jackson, 215 F.3d 1225, 1233 (11th Cir.\\n2000) (kicking a suspect in the ribs constituted excessive force when he was subdued and no\\nlonger resisting).\\n 17\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 18 of 23\\n\\n\\n2008)), and yet another holding that an officer had used excessive force when he\\n\\nsicced his police dog on a suspect who was lying still on the ground, see id. (citing\\n\\nPriester v. City of Riviera Beach, 208 F.3d 919 (11th Cir. 2000)). We emphasized\\n\\nthat “[a]lthough none of these cases involved tasers,” there was “no meaningful\\n\\ndistinction under these circumstances” between the use of a taser on an unresisting\\n\\nsuspect and the use of pepper spray, fists, or police dogs. Id.; see also Wate v.\\n\\nKubler, 839 F.3d 1012, 1022 (11th Cir. 2016) (looking not only to a taser-specific\\n\\ncase but also to cases involving a gut-punch and a head-slam to determine that the\\n\\nuse of force on an unresisting arrestee violated clearly established law).\\n\\n So too here. There is “no meaningful distinction” between pepper spray to\\n\\nan unresisting detainee’s face, a kick to his gut, or a taser to his chest and neck.\\n\\nThe crucial question is whether the law gave Dukuzumuremyi “fair warning” that\\n\\nhis conduct—tasing an already-tased, incapacitated, incontinent, and unresisting\\n\\ndetainee—violated the Fourteenth Amendment. In the light of our use-of-force\\n\\nprecedent, we have no trouble concluding that it did. 10\\n\\n\\n10\\n A panel of this Court also found it clearly established that the repeated deployment of a taser\\non an unresisting arrestee constituted excessive force in violation of the Fourth Amendment.\\nGlasscox v. City of Argo, 903 F.3d 1207 (11th Cir. 2018). We don’t rely on Glasscox because\\nlaw can be clearly established for overcoming qualified immunity only if it is established prior to\\nthe relevant events, and Hinkle’s death occurred in 2014, four years before Glasscox issued.\\nThat being said, the Glasscox Court based its decision on two earlier cases—Oliver v. Fiorino,\\n586 F.3d 898 (11th Cir. 2009), and Smith v. Mattox, 127 F.3d 1416 (11th Cir. 1997)—that\\ntogether establish that the repeated use of a taser on an unresisting arrestee constitutes excessive\\nforce. Given the ample Fourteenth Amendment precedent prohibiting jail officers from using\\nforce on an unresisting detainee, we needn’t rely on Oliver and Smith; we simply note that, given\\n 18\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 19 of 23\\n\\n\\n * * *\\n\\n Accordingly, we hold that Deputy Dukuzumuremyi’s second taser shock\\n\\nviolated Hunter’s clearly established Fourteenth Amendment right to be free from\\n\\nexcessive force and that the district court therefore correctly rejected\\n\\nDukuzumuremyi’s qualified-immunity defense.\\n\\n B\\n\\n We turn, then, to consider the supervisory-liability claims against Sheriff\\n\\nHale and Captain Eddings. The standard by which a supervisor can be held liable\\n\\nfor the actions of a subordinate is “extremely rigorous.” Cottone, 326 F.3d at\\n\\n1360. Supervisory officials cannot be held liable under § 1983 for unconstitutional\\n\\nacts by their subordinates based on respondeat-superior or vicarious-liability\\n\\nprinciples. Hartley v. Parnell, 193 F.3d 1263, 1269 (11th Cir. 1999). Instead,\\n\\nabsent allegations of personal participation—of which there are none here\\n\\nconcerning Hale or Eddings—supervisory liability is permissible only if there is a\\n\\n“causal connection” between a supervisor’s actions and the alleged constitutional\\n\\nviolation. Cottone, 326 F.3d at 1360.\\n\\n One way that a plaintiff can show the requisite causal connection is by\\n\\ndemonstrating that a supervisor’s policy or custom resulted in “deliberate\\n\\n\\n\\nthe similarities between the Fourth and Fourteenth Amendment inquiries, see supra at 9, they\\nwould likely lead to the same result.\\n\\n 19\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 20 of 23\\n\\n\\nindifference to constitutional rights.” 11 Id. at 1360–61. A plaintiff can also show\\n\\nthat the absence of a policy led to a violation of constitutional rights. Rivas v.\\n\\nFreeman, 940 F.2d 1491, 1495 (11th Cir. 1991). Either way, though, to prove that\\n\\na policy or its absence caused a constitutional harm, a plaintiff must point to\\n\\nmultiple incidents, see Rivas, 940 F.2d at 1495–96, or multiple reports of prior\\n\\nmisconduct by a particular employee, see Danley, 540 F.3d at 1315. “A single\\n\\nincident of a constitutional violation is insufficient to prove a policy or custom\\n\\neven when the incident involves several [subordinates].” Craig v. Floyd County,\\n\\n643 F.3d 1306, 1312 (11th Cir. 2011); see also Goebert v. Lee County, 510 F.3d\\n\\n1312, 1332 (11th Cir. 2007) (holding that plaintiff failed to meet the rigorous\\n\\nstandard for supervisory liability when she failed to show that any other inmates\\n\\nhad suffered the same alleged violation). Hunter has not made the requisite\\n\\nshowing with respect to either of the two theories that underlie his supervisory-\\n\\nliability claims against Hale and Eddings.\\n\\n 1\\n\\n With respect to excessive force, Hunter asserts that Hale and Eddings\\n\\n“fail[ed] to adopt and implement adequate policies” concerning the appropriate use\\n\\nof force and that this failure resulted in a violation of Hinkle’s constitutional rights.\\n\\n\\n11\\n Hale was the Sheriff of Jefferson County at the time of the relevant events, and Eddings was\\nthe Commander of the Birmingham City Jail. The parties do not dispute that both acted as\\npolicymakers for the jail.\\n 20\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 21 of 23\\n\\n\\nHunter does not, however, allege any other incidents or reports of excessive force\\n\\nby jail employees. Because Hunter’s excessive-force claim focuses solely on\\n\\nHinkle’s episode—“a single incident of unconstitutional activity”—it does not, as a\\n\\nmatter of law, state a claim against Hale and Eddings for supervisory liability. See\\n\\nCraig, 643 F.3d at 1312; see also Weiland v. Palm Beach Cty. Sheriff’s Office, 792\\n\\nF.3d 1313, 1329 (11th Cir. 2015) (holding that the “conclusory allegation that the\\n\\nSheriff’s Office was ‘on notice’ of the need to ‘promulgate, implement, and/or\\n\\noversee’ policies pertaining to the ‘use of force’” was insufficient when the claim\\n\\narose from a single incident involving two deputies).12\\n\\n 2\\n\\n The same goes for the supervisory-liability claims predicated on an alleged\\n\\ndeliberate indifference to Hinkle’s serious medical needs. Hunter asserts that\\n\\nHinkle was an alcoholic who was neither treated for his alcoholism nor provided\\n\\nhis prescription medication upon admission to the jail. Hunter does not, though,\\n\\npoint to other instances of inadequate medical screening or delayed medical care at\\n\\n\\n\\n12\\n Compare Valdes v. Crosby, 450 F.3d 1231 (11th Cir. 2006) (finding supervisory liability when\\nmultiple inmate complaints, warnings from other prison guards, and letters from family members\\nput a prison warden on notice of a history of widespread abuse by certain prison guards and\\nevidenced a causal connection between an inmate’s death by beating and the warden’s policy or\\ncustom), with Hartley v. Parnell, 193 F.3d 1263 (11th Cir. 1999) (finding no supervisory liability\\nfor a school superintendent based on a teacher’s sexual abuse of a student in the absence of any\\nprior acts by a teacher that would have put the superintendent on notice that the teacher might\\ncommit abuse or any evidence of a policy that could have led a teacher to believe that his\\nbehavior was permissible).\\n\\n 21\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 22 of 23\\n\\n\\nthe Birmingham City Jail, nor does he allege any facts indicating that Hale or\\n\\nEddings were on notice of the officers’ alleged deliberate indifference. Cf.\\n\\nAnderson v. City of Atlanta, 778 F.2d 678, 686 (11th Cir. 1985) (finding\\n\\nsupervisory liability for deliberate indifference to a pretrial detainee’s serious\\n\\nmedical needs when a supervisor failed to act after repeated complaints of\\n\\ninadequate staffing). Because Hunter’s complaint contains only conclusory\\n\\nassertions that jail officers were indifferent to Hinkle’s needs pursuant to certain\\n\\npolicies or customs—without alleging any facts concerning those policies or\\n\\ncustoms—he has not stated a claim for supervisory liability for deliberate\\n\\nindifference to serious medical needs. See Ashcroft v. Iqbal, 556 U.S. 662, 678\\n\\n(2009) (“[A] complaint [does not] suffice if it tenders ‘naked assertion[s]’ devoid\\n\\nof ‘further factual enhancement.’”) (quoting Bell Atl. Corp. v. Twombly, 550 U.S.\\n\\n544, 557 (2007)).\\n\\n * * *\\n\\n Accordingly, we hold that Hunter has failed to plead facts sufficient to\\n\\nsustain supervisory-liability claims against Sheriff Hale or Captain Eddings and\\n\\nthat the district court therefore erred in rejecting the officers’ qualified-immunity\\n\\ndefenses to those claims.\\n\\n\\n\\n\\n 22\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 23 of 23\\n\\n\\n III\\n\\n For the foregoing reasons, we affirm the district court’s denial of qualified\\n\\nimmunity to Deputy Dukuzumuremyi and reverse its denial of qualified immunity\\n\\nto Sheriff Hale and Captain Eddings.\\n\\n AFFIRMED IN PART AND REVERSED IN PART.\\n\\n\\n\\n\\n 23\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4395426/\", \"author_raw\": \"NEWSOM, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"TJOFLAT"},"judge2":{"kind":"string","value":"NEWSOM"},"judge3":{"kind":"string","value":"GILMAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"TJOFLAT\": \", Circuit\", \"NEWSOM\": \", Circuit\", \"GILMAN\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4618173/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Nyreekis Jarnell Hunter v. Mike Hale\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-09\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-10487 Date Filed: 05/09/2019 Page: 1 of 23\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 18-10487\n ________________________\n\n D.C. Docket No. 2:16-cv-01521-MHH\n\nANTHONY PIAZZA,\nas personal representative of the Estate of\nRicky DeAngelo Hinkle, deceased,\n\n Plaintiff,\n\nNYREEKIS JARNELL HUNTER,\nas personal representative of the Estate of\nRicky DeAngelo Hinkle, deceased,\n\n Plaintiff - Appellee,\n\n\n versus\n\nJEFFERSON COUNTY, ALABAMA,\nan Alabama county, individually, et al,\n\n Defendants,\n\nMIKE HALE,\nRON EDDINGS,\nHABIMANA DUKUZUMUREMYI,\neach individually,\n\n Defendants - Appellants.\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 2 of 23\n\n\n ________________________\n\n Appeal from the United States District Court\n for the Northern District of Alabama\n ________________________\n\n (May 9, 2019)\n\nBefore TJOFLAT, NEWSOM, and GILMAN, * Circuit Judges.\n\nNEWSOM, Circuit Judge:\n\n Ricky Hinkle died in the Birmingham City Jail after being shocked with a\n\ntaser, twice. Hinkle’s son, Nyreekis Hunter, brought suit under 42 U.S.C. § 1983\n\nalleging several claims on his behalf, including, as relevant here, (1) an excessive-\n\nforce claim against Deputy Habimana Dukuzumuremyi and (2) supervisory-\n\nliability claims for excessive force and deliberate indifference to Hinkle’s serious\n\nmedical needs against Sheriff Mike Hale and Captain Ron Eddings. The officers\n\nmoved to dismiss Hunter’s suit based on qualified immunity, the district court\n\ndenied their motion, and the officers now appeal.\n\n After careful review, we agree in part and disagree in part with the district\n\ncourt’s decision. We agree that the facts as Hunter has pleaded them show that\n\nDeputy Dukuzumuremyi violated Hinkle’s clearly established constitutional right\n\nto be free from excessive force. In particular, we hold that Dukuzumuremyi\n\ncrossed the constitutional line, and clearly so, when, having already tased Hinkle\n\n\n*\n Honorable Ronald Lee Gilman, United States Circuit Judge for the Sixth Circuit, sitting by\ndesignation.\n 2\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 3 of 23\n\n\nonce—dropping him to the floor, rendering him motionless, and causing him to\n\nurinate on himself—Dukuzumuremyi shocked him again a full eight seconds later.\n\nWe disagree, however, that Hunter’s allegations show—as they must to support a\n\nsupervisory-liability claim—a causal connection between either the use of force\n\nagainst Hinkle or any deliberate indifference to Hinkle’s serious medical needs, on\n\nthe one hand, and any policy or custom implemented by Sheriff Hale or Captain\n\nEddings, on the other. Accordingly, we affirm the district court’s decision to deny\n\nqualified immunity to Deputy Dukuzumuremyi but reverse its decision to deny\n\nqualified immunity to Sheriff Hale and Captain Eddings.\n\n I\n\n Ricky Hinkle, who suffered from alcoholism, heart disease, and depression,\n\nwas arrested while “visibly intoxicated” and was taken to the Jefferson County Jail\n\nin Bessemer, Alabama. 1 The next day, he was transferred to the Birmingham City\n\nJail. Soon thereafter, he began suffering from alcohol-withdrawal symptoms and\n\nexhibiting delusional behavior. Jail officers moved Hinkle three different times\n\nbefore eventually (and presumably due to his deteriorating condition) placing him\n\nin a cell on Level 3, where Deputies Habimana Dukuzumuremyi and Christopher\n\nCotten were working.\n\n\n1\n The factual allegations in this case are largely undisputed, but because this appeal arises in a\nmotion-to-dismiss posture, where the parties’ memories diverge we adopt Hunter’s re-telling.\nSee Cottone v. Jenne, 326 F.3d 1352, 1357 (11th Cir. 2003).\n 3\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 4 of 23\n\n\n Shortly after Hinkle arrived on Level 3, Dukuzumuremyi realized that he\n\ncouldn’t see him on the video monitor, so he called to him over the loudspeaker.\n\nWhen Hinkle didn’t respond, Cotten went to investigate and found Hinkle in the\n\ncorner of his cell, wearing only underpants and shoes. When Cotten asked Hinkle\n\nwhy he was in the corner, Hinkle responded that he “wanted to die.” At this,\n\nCotten decided to move Hinkle to a padded cell. He walked Hinkle toward the cell\n\nand asked him to remove his shoes. Hinkle initially obeyed but then ran down the\n\nhallway to the bathroom and grabbed a shower curtain. Cotten took the shower\n\ncurtain away from Hinkle shortly before Dukuzumuremyi arrived on the scene.\n\n After the officers attempted three times to pull Hinkle into his new cell,\n\nDukuzumuremyi fired his taser, hitting Hinkle on the left side of his chest just\n\nabove his heart. As a result of that taser shock—which lasted 5 seconds—Hinkle\n\nfell to the floor on his right side and urinated on himself. Dukuzumuremyi then\n\nordered Hinkle to roll over to be handcuffed, but Hinkle remained unresponsive.\n\nEight seconds after the end of the first shock, and while Hinkle still lay motionless\n\n(and wet) on the ground, Dukuzumuremyi tased him again, this time on the front\n\nleft side of his neck. Shortly after the second shock, Hinkle went into cardiac\n\narrest. He was taken to the emergency room, where he was pronounced dead.\n\n\n\n\n 4\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 5 of 23\n\n\n Hinkle’s son Nyreekis Hunter, acting as personal representative of Hinkle’s\n\nestate, brought suit under 42 U.S.C. § 1983 on Hinkle’s behalf.2 As relevant here,\n\nHunter sued Deputy Dukuzumuremyi for excessive force and Deputy Cotten for\n\nfailure to intervene, and both deputies for deliberate indifference to Hinkle’s\n\nserious medical needs. He also sued Sheriff Hale and Captain Eddings on a\n\nsupervisory-liability theory based on the excessive-force and deliberate-\n\nindifference claims. The officers moved to dismiss on qualified-immunity\n\ngrounds.3\n\n The district court granted in part and denied in part the officers’ motion to\n\ndismiss. The court dismissed the deliberate-indifference claim against\n\nDukuzumuremyi and Cotten, finding that the complaint “contain[ed] no allegations\n\nto indicate that either deputy had subjective knowledge of the decedent’s medical\n\ncondition.” The court also dismissed the failure-to-intervene claim against\n\nCotten. 4 But the court denied the motion to dismiss as to (1) the excessive-force\n\n\n\n\n2\n The initial complaint was filed by Anthony Piazza, who is not related to Hinkle. After some\ndispute over whether Piazza could properly represent Hinkle’s estate, Hunter replaced Piazza as\nHinkle’s personal representative.\n3\n Hunter also brought state-law claims against each officer for negligence and wrongful death;\nthe district court dismissed each claim on state-law grounds.\n4\n Deputy Cotten is not a party to this appeal because the district court dismissed all claims against\nhim. Two other defendants, Dr. David Hicks and Advanced Correctional Healthcare, were also\nnamed in Hunter’s complaint—for exhibiting deliberate indifference to Hinkle’s serious medical\nneeds—but neither is a party to this appeal.\n\n 5\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 6 of 23\n\n\nclaim against Dukuzumuremyi and (2) the supervisory-liability claims against Hale\n\nand Eddings. Dukuzumuremyi, Hale, and Eddings timely appealed.5\n\n II\n\n We review de novo a district court’s denial of qualified immunity. Cottone\n\nv. Jenne, 326 F.3d 1352, 1357 (11th Cir. 2003). Qualified immunity shields a\n\ngovernment official from liability unless he violates “clearly established statutory\n\nor constitutional rights of which a reasonable person would have known.” Foy v.\n\nHolston, 94 F.3d 1528, 1532 (11th Cir. 1996). An officer asserting a qualified-\n\nimmunity defense bears the initial burden of showing that he was “acting within\n\nhis discretionary authority.” Skop v. City of Atlanta, 485 F.3d 1130, 1136 (11th\n\nCir. 2007). After the officer makes this showing—and here, it is undisputed—the\n\nburden shifts to the plaintiff to show that (1) the officer violated a constitutional\n\nright and (2) the right was clearly established at the time of the alleged\n\nviolation. Holloman ex rel. Holloman v. Harland, 370 F.3d 1252, 1264 (11th Cir.\n\n2004). We may consider these two prongs in either order; an official is entitled to\n\n\n\n\n5\n We have jurisdiction over the officers’ interlocutory appeal under 28 U.S.C. § 1291 because the\ndistrict court denied qualified immunity based on questions of law—namely, whether the officers\nviolated Hinkle’s constitutional rights and whether those rights were clearly established. See\nMitchell v. Forsyth, 472 U.S. 511, 530 (1985) (“[A] district court’s denial of a claim of qualified\nimmunity, to the extent that it turns on an issue of law, is an appealable ‘final decision’ within\nthe meaning of 28 U.S.C. § 1291 notwithstanding the absence of a final judgment.”).\n\n\n 6\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 7 of 23\n\n\nqualified immunity if the plaintiff fails to establish either. Jacoby v. Baldwin\n\nCounty, 835 F.3d 1338, 1344 (11th Cir. 2016).\n\n We start with the excessive-force claim against Deputy Dukuzumuremyi,\n\nand then move to the supervisory-liability claims against Sheriff Hale and Captain\n\nEddings.\n\n A\n\n 1\n\n First things first. What constitutional provision governs the use of force in\n\nthis case, and what doctrinal standard guides our analysis? While the Fourth\n\nAmendment prevents the use of excessive force during arrests, see Graham v.\n\nConnor, 490 U.S. 386, 388 (1989), and the Eighth Amendment serves as the\n\nprimary source of protection against excessive force after conviction, see Whitley\n\nv. Albers, 475 U.S. 312, 327 (1986), it is the Fourteenth Amendment that protects\n\nthose who exist in the in-between—pretrial detainees. Garrett v. Athens–Clarke\n\nCounty, 378 F.3d 1274, 1279 n.11 (11th Cir. 2004).6\n\n That pretrial detainees fall within the Fourteenth Amendment’s ambit dates\n\nto the Supreme Court’s decision in Bell v. Wolfish, 441 U.S. 520 (1979). The\n\n\n6\n Although some courts have extended Fourth Amendment protections into the pretrial detention\nphase, see, e.g., Aldini v. Johnson, 609 F.3d 858, 866 (6th Cir. 2010), “[n]either [this Court] nor\nthe Supreme Court has decided whether the Fourth Amendment continues to provide individuals\nwith protection from excessive force beyond the point at which an arrest ends and pretrial\ndetention begins,” J W by & through Tammy Williams v. Birmingham Board of Education, 904\nF.3d 1248, 1259 (11th Cir. 2018).\n 7\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 8 of 23\n\n\nCourt explained there that the “proper inquiry” when “evaluating the\n\nconstitutionality of conditions or restrictions of pretrial detention” is “whether\n\nthose conditions amount to punishment of the detainee.” Id. at 535. “For under\n\nthe Due Process Clause,” the Court continued, “a detainee may not be punished\n\nprior to an adjudication of guilt in accordance with due process of law.” Id.\n\n Although pretrial detainees’ excessive-force claims have been analyzed\n\nunder the Fourteenth Amendment since Bell, the constitutional inquiry—at least in\n\nthis Circuit—has long resembled the one that governs prisoners’ excessive-force\n\nclaims under the Eighth Amendment. Historically, both prisoners and pretrial\n\ndetainees needed to show not only that a jail official deliberately used excessive\n\nforce, but also that the official did so “maliciously or sadistically for the very\n\npurpose of causing harm.” Bozeman v. Orum, 422 F.3d 1265, 1271 (11th Cir.\n\n2005), overruled by Kingsley v. Hendrickson, 135 S. Ct. 2466, 2473 (2015). All\n\nthat changed a few years back, though, when the Supreme Court clarified that,\n\nunlike a prisoner bringing an Eighth Amendment excessive-force claim, a pretrial\n\ndetainee raising a Fourteenth Amendment claim needn’t prove an officer’s\n\nsubjective intent to harm but instead need show only that “the force purposely or\n\nknowingly used against him was objectively unreasonable.” Kingsley, 135 S. Ct.\n\nat 2473.\n\n\n\n\n 8\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 9 of 23\n\n\n Harking back to Bell, the Kingsley Court explained that, unlike in Eighth\n\nAmendment cases, there is no need in the pretrial-detainee context to determine\n\n“when punishment is unconstitutional” because a pretrial detainee has not yet been\n\nadjudicated guilty and thus may not be punished at all. Id. at 2475 (emphasis\n\nadded). Although, under Bell, impermissible “punishment” could mean force\n\ndeployed with a subjective, “expressed intent to punish,” it also could mean force\n\nthat, as an objective matter, is “not rationally related to a legitimate governmental”\n\npurpose or is “excessive in relation to that purpose.” Id. at 2473–74. After\n\nKingsley, then, if force used against a pretrial detainee is more severe than is\n\nnecessary to subdue him or otherwise achieve a permissible governmental\n\nobjective, it constitutes “punishment” and is therefore unconstitutional. Notably,\n\ninasmuch as it entails an inquiry into the objective reasonableness of the officers’\n\nactions, the Fourteenth Amendment standard has come to resemble the test that\n\ngoverns excessive-force claims brought by arrestees under the Fourth Amendment.\n\nCompare Kingsley, 135 S. Ct. at 2472–73 (holding that a pretrial detainee in the\n\nFourteenth Amendment context “must show only that the force purposely or\n\nknowingly used against him was objectively unreasonable”), with Graham, 490\n\nU.S. at 397 (explaining that the Fourth Amendment excessive-force inquiry asks\n\n“whether the officers’ actions are ‘objectively reasonable’ in light of the facts and\n\n\n\n\n 9\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 10 of 23\n\n\ncircumstances confronting them, without regard to their underlying intent or\n\nmotivation”).\n\n Obviously, “legitimate interests”—including the need to “preserve internal\n\norder and discipline” and “maintain institutional security”—may at times require\n\njail officers to use force. Kingsley, 135 S. Ct. at 2473 (citation omitted). And of\n\ncourse, officers facing disturbances are often forced to make “split-second\n\njudgments” about the need for such force “in circumstances that are tense,\n\nuncertain, and rapidly evolving.” Id. at 2474 (quoting Graham, 490 U.S. at 397).\n\nBecause of this, we can’t (and won’t) evaluate a pretrial detainee’s excessive-force\n\nchallenge in a glib, post-hoc fashion or “with the 20/20 vision of hindsight.” Id. at\n\n2473. Instead, we must do our best to consider the situation through the lens of “a\n\nreasonable officer on the scene.” Id.\n\n How do we know, then, when force is reasonable and when it is “excessive\n\nin relation to its purpose”? Well, as relevant to this case, our decisions make one\n\nthing clear: “Once a prisoner has stopped resisting there is no longer a need for\n\nforce, so the use of force thereafter is disproportionate to the need.” Danley v.\n\nAllen, 540 F.3d 1298, 1309 (11th Cir. 2008) (emphasis added), abrogated on other\n\ngrounds by Kingsley, 135 S. Ct. 2466. Accordingly, “[w]hen jailers continue to\n\nuse substantial force against a prisoner who has clearly stopped resisting—whether\n\nbecause he has decided to become compliant, he has been subdued, or he is\n\n\n 10\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 11 of 23\n\n\notherwise incapacitated—that use of force is excessive.” Id. (emphasis added); see\n\nalso Ort v. White, 813 F.2d 318, 327 (11th Cir. 1987) (“A [F]ourteenth\n\n[A]mendment violation occurs . . . where prison officers continue to employ force\n\nor other coercive measures after the necessity for such coercive action has\n\nceased.”); Bozeman, 422 F.3d at 1271–72 (finding excessive force when officers\n\ncontinued to suffocate a detainee by pushing his face into a mattress after he had\n\nstopped struggling and said he’d had enough), overruled on other grounds by\n\nKingsley, 135 S. Ct. 2466.7 In other words, because force in the pretrial detainee\n\ncontext may be defensive or preventative—but never punitive—the continuing use\n\nof force is impermissible when a detainee is complying, has been forced to comply,\n\nor is clearly unable to comply.\n\n 2\n\n In the case before us, then, we must determine whether the force used\n\nagainst Hinkle was objectively unreasonable—i.e., whether it was “excessive in\n\nrelation to [its] purpose.” Kingsley, 135 S. Ct. at 2473–74. To briefly recap, the\n\ncritical events began when Hinkle broke away from Cotten, ran down the hallway,\n\n\n7\n To be clear, Bozeman and Danley remain relevant to our inquiry even though both employed\nthe more stringent pre-Kingsley standard of proof: whether force was applied “maliciously or\nsadistically for the very purpose of causing harm.” Bozeman, 422 F.3d at 1272. Because\nproving both that the force applied in a given situation was objectively excessive and that it was\napplied “maliciously or sadistically for the very purpose of causing harm” will almost invariably\nbe more difficult than proving only that the force used was objectively excessive, these cases\ncontinue to provide pertinent examples of excessive force in the pretrial-detainee context.\n\n 11\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 12 of 23\n\n\nand grabbed a shower curtain. (Not the curtain rod, mind you—the curtain.) After\n\nthree unsuccessful attempts to lead Hinkle into his cell, Dukuzumuremyi fired his\n\ntaser, hitting Hinkle just above the heart with a five-second shock. Eight seconds\n\nafter the first shock ended—and with Hinkle still prostrate on the ground, and\n\nhaving wet himself—Dukuzumuremyi tased Hinkle again.\n\n The parties don’t dispute that the first shock was a permissible use of force\n\ngiven Hinkle’s resistance and the officers’ need to “preserve internal order and\n\ndiscipline” and “maintain institutional security.” See Kingsley, 135 S. Ct. at 2473.\n\nThe issue is the second shock. Dukuzumuremyi asserts that the second shock\n\ndoesn’t constitute excessive force in light of (1) Hinkle’s failure to roll over to be\n\nhandcuffed “after being ordered—and being given an opportunity—to do so,” and\n\n(2) the “split-second decisions” that jail officers must make. The facts alleged,\n\nhowever, undermine both assertions.\n\n Again, according to Hunter’s complaint, following the first taser shock\n\nHinkle fell to the floor, lay motionless, and urinated on himself. Even so,\n\nDukuzumuremyi contends that because Hinkle failed to obey the subsequent order\n\nto roll over and be handcuffed, he was not yet fully compliant. Because Hinkle\n\nwas not following commands, the argument goes, the second shock couldn’t have\n\ncrossed the constitutional line. Oral Arg. Tr. 7:07. Wrong. It seems to us totally\n\nunreasonable to expect that a man who is lying on the floor immobilized—and\n\n\n 12\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 13 of 23\n\n\nincontinent—following a taser shock should pep up, roll over, and submit to\n\nhandcuffing within eight seconds. But, Dukuzumuremyi counters, Hunter’s\n\ncomplaint doesn’t specifically allege that Hinkle “could not” roll over, only that he\n\n“did not.” Oral Arg. Tr. 7:45. Come on. The only reasonable inference is that\n\nHinkle, who was lying motionless on the floor after a five-second taser shock—\n\nunable to hold his own urine—“did not” immediately roll over because he “could\n\nnot.” (Really, is there any surer indication of a grown man’s inability to control his\n\nbodily functions than his wetting himself?)\n\n The same facts undermine Dukuzumuremyi’s contention that the second\n\nshock should be swept into the zone of reasonableness by the deference owed an\n\nofficer’s split-second decisions. Although we don’t for a minute discount the\n\ndifficult decisions that jail officers must make in the heat of a tussle, simply\n\ncounting to eight aloud reveals the problem with Dukuzumuremyi’s argument. In\n\neight seconds, you can tie a shoe, sing the chorus of “Row, Row, Row Your Boat,”\n\nor complete a qualified rodeo bull ride. And in eight seconds, we believe, any\n\nreasonable officer would have concluded that a detainee who lay inert on the floor,\n\nhaving soiled himself, was no longer putting up a fight. See Kingsley, 135 S. Ct. at\n\n2473 (listing “whether the plaintiff was actively resisting” and “any effort made by\n\nthe officer to temper or to limit the amount of force used” as factors potentially\n\nrelevant to the excessive-force determination).\n\n\n 13\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 14 of 23\n\n\n Our conclusion is fortified by additional considerations that the Supreme\n\nCourt mentioned in Kingsley that “bear on the reasonableness or unreasonableness\n\nof the force used,” including the severity of the security issue posed by the detainee\n\nand the threat reasonably perceived by the officer. See Kingsley, 135 S. Ct. at\n\n2473. Although officers may (of course) use force to “preserve internal order and\n\ndiscipline” and “maintain institutional security,” the severity of the problem and\n\nthe corresponding risk to the officers in this case were—from the very outset—\n\nexceedingly minimal. See id. Instead of facing, say, a man armed with a knife\n\nrunning toward them, the officers here faced a man armed with a shower curtain\n\nrunning away from them. See, e.g., Shaw v. City of Selma, 884 F.3d 1093, 1099\n\n(11th Cir. 2018) (officer entitled to qualified immunity on an excessive-force claim\n\nafter shooting a mentally-ill man walking toward him with a hatchet); Smith v.\n\nLePage, 834 F.3d 1285, 1294–95 (11th Cir. 2016) (officer entitled to qualified\n\nimmunity on an excessive-force claim when a suspect holding a knife refused to\n\ncomply with orders to disarm himself); Singletary v. Vargas, 804 F.3d 1174, 1185\n\n(11th Cir. 2015) (officer entitled to qualified immunity on an excessive-force claim\n\nbased on his reasonable belief that a car rolling toward him presented a deadly\n\nthreat). Although non-compliant, Hinkle had neither threatened nor attempted to\n\nharm the officers. While we don’t question Dukuzumuremyi’s split-second\n\ndecision to deploy his taser once following several unsuccessful attempts to lead\n\n\n 14\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 15 of 23\n\n\nHinkle into his cell, we see no legitimate basis for the second shock, particularly\n\nconsidering (1) that the first shock had immobilized Hinkle and (2) the minimal\n\nthreat to order, safety, and security that Hinkle posed even from the outset.\n\n At the end of the day the question before us is this: Is it excessive to tase for\n\na second time a man who, as a result of an initial shock, is lying motionless on the\n\nfloor and has wet himself, and who presented only a minimal threat to begin with?\n\nUndoubtedly, yes. We hold that, based on the allegations in Hunter’s complaint,\n\nthe force used against Hinkle was excessive, and thus unconstitutional.\n\n 3\n\n Of course, to overcome Dukuzumuremyi’s qualified-immunity defense,\n\nHunter must further show that the law that governs his case was “clearly\n\nestablished” at the time of the alleged violation. To qualify, a legal principle must\n\nbe “settled” and “clear enough that every reasonable official would interpret it to\n\nestablish the particular rule the plaintiff seeks to apply.” District of Columbia v.\n\nWesby, 138 S. Ct. 577, 589–90 (2018). The critical question is whether the law\n\ngave the officer “fair warning” that his conduct was unconstitutional. Glasscox v.\n\nCity of Argo, 903 F.3d 1207, 1217–18 (11th Cir. 2018) (citing Hope v. Pelzer, 536\n\nU.S. 730, 741 (2002)).\n\n Here, it certainly did. It was more than ten years ago now that this Court\n\nheld, in no uncertain terms, that “[w]hen jailers continue to use substantial force\n\n\n 15\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 16 of 23\n\n\nagainst a prisoner who has clearly stopped resisting—whether because he has\n\ndecided to become compliant, he has been subdued, or he is otherwise\n\nincapacitated—that use of force is excessive.” Danley, 540 F.3d at 1309; see also\n\nid. (“Once a prisoner has stopped resisting there is no longer a need for force, so\n\nthe use of force thereafter is disproportionate to the need.”).8 And Danley was no\n\ninnovation; for decades our decisions have embraced and reiterated the principle\n\nthat an officer may not continue to use force after a detainee has clearly stopped\n\nresisting. See Skrtich v. Thornton, 280 F.3d 1295, 1303 (11th Cir. 2002)\n\n(“[G]overnment officials may not use gratuitous force against a prisoner who has\n\nbeen already subdued or, as in this case, incapacitated.”); Williams v. Burton, 943\n\nF.2d 1572, 1576 (11th Cir. 1991) (“The basic legal principle is that once the\n\nnecessity for the application of force ceases, any continued use of harmful force\n\ncan be a violation of the Eighth and Fourteenth Amendments.”); Ort, 813 F.2d at\n\n327 (“A [F]ourteenth [A]mendment violation occurs . . . where prison officers\n\ncontinue to employ force or other coercive measures after the necessity for such\n\ncoercive action has ceased.”).9\n\n8\n Again, although Kingsley changed the nature of the inquiry—by dropping the requirement that\na plaintiff prove the officers’ subjective malicious intent—it did not change the law with respect\nto the objective reasonableness of using force against unresisting subjects.\n9\n The same basic rule guides our Fourth Amendment cases concerning the use of force against\nunresisting or subdued arrestees. See, e.g., Hadley v. Gutierrez, 526 F.3d 1324, 1330 (11th Cir.\n2008) (punching a suspect in the stomach constituted excessive force when he was already\nsubdued and not struggling); Lee v. Ferraro, 284 F.3d 1188, 1200 (11th Cir. 2002) (slamming a\nsuspect’s head onto the hood of her car constituted excessive force when she no longer posed a\n 16\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 17 of 23\n\n\n To be clear, it is no answer to say that Danley involved pepper spray, Skrtich\n\nkicks and punches, Williams four-point restraints, etc.—and that none of those\n\ncases concerned the use of a taser specifically. It’s true, of course, that to defeat\n\nqualified immunity a rule must be specific enough that an act’s unlawfulness\n\n“follow[s] immediately from the conclusion that the rule was firmly established,”\n\nWesby, 138 S. Ct. at 590 (citation omitted). But we have never suggested that the\n\nlongstanding prohibition on a jail officer’s use of force on an incapacitated\n\ndetainee turns on as fine a point as the particular weapon deployed. And indeed, in\n\nthe analogous Fourth Amendment context, we have flatly rejected that very\n\ndistinction—in a case involving a taser, no less. In Fils v. City of Aventura, we\n\nconsidered allegations that police officers had impermissibly tased a non-violent,\n\nunresisting suspect. 647 F.3d 1272, 1288–90 (11th Cir. 2011). In finding the law\n\nprohibiting the tasing clearly established, we relied on one case holding that an\n\nofficer had used excessive force when he pepper-sprayed a secured suspect in the\n\nface as she sat shackled in the backseat of his cruiser, see id. at 1289 (citing\n\nVinyard v. Wilson, 311 F.3d 1340 (11th Cir. 2002)), another holding that an officer\n\nhad used excessive force when he punched a handcuffed and unresisting plaintiff\n\nin the stomach, see id. (citing Hadley v. Gutierrez, 526 F.3d 1324 (11th Cir.\n\n\n\nthreat to the officer nor a flight risk); Slicker v. Jackson, 215 F.3d 1225, 1233 (11th Cir.\n2000) (kicking a suspect in the ribs constituted excessive force when he was subdued and no\nlonger resisting).\n 17\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 18 of 23\n\n\n2008)), and yet another holding that an officer had used excessive force when he\n\nsicced his police dog on a suspect who was lying still on the ground, see id. (citing\n\nPriester v. City of Riviera Beach, 208 F.3d 919 (11th Cir. 2000)). We emphasized\n\nthat “[a]lthough none of these cases involved tasers,” there was “no meaningful\n\ndistinction under these circumstances” between the use of a taser on an unresisting\n\nsuspect and the use of pepper spray, fists, or police dogs. Id.; see also Wate v.\n\nKubler, 839 F.3d 1012, 1022 (11th Cir. 2016) (looking not only to a taser-specific\n\ncase but also to cases involving a gut-punch and a head-slam to determine that the\n\nuse of force on an unresisting arrestee violated clearly established law).\n\n So too here. There is “no meaningful distinction” between pepper spray to\n\nan unresisting detainee’s face, a kick to his gut, or a taser to his chest and neck.\n\nThe crucial question is whether the law gave Dukuzumuremyi “fair warning” that\n\nhis conduct—tasing an already-tased, incapacitated, incontinent, and unresisting\n\ndetainee—violated the Fourteenth Amendment. In the light of our use-of-force\n\nprecedent, we have no trouble concluding that it did. 10\n\n\n10\n A panel of this Court also found it clearly established that the repeated deployment of a taser\non an unresisting arrestee constituted excessive force in violation of the Fourth Amendment.\nGlasscox v. City of Argo, 903 F.3d 1207 (11th Cir. 2018). We don’t rely on Glasscox because\nlaw can be clearly established for overcoming qualified immunity only if it is established prior to\nthe relevant events, and Hinkle’s death occurred in 2014, four years before Glasscox issued.\nThat being said, the Glasscox Court based its decision on two earlier cases—Oliver v. Fiorino,\n586 F.3d 898 (11th Cir. 2009), and Smith v. Mattox, 127 F.3d 1416 (11th Cir. 1997)—that\ntogether establish that the repeated use of a taser on an unresisting arrestee constitutes excessive\nforce. Given the ample Fourteenth Amendment precedent prohibiting jail officers from using\nforce on an unresisting detainee, we needn’t rely on Oliver and Smith; we simply note that, given\n 18\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 19 of 23\n\n\n * * *\n\n Accordingly, we hold that Deputy Dukuzumuremyi’s second taser shock\n\nviolated Hunter’s clearly established Fourteenth Amendment right to be free from\n\nexcessive force and that the district court therefore correctly rejected\n\nDukuzumuremyi’s qualified-immunity defense.\n\n B\n\n We turn, then, to consider the supervisory-liability claims against Sheriff\n\nHale and Captain Eddings. The standard by which a supervisor can be held liable\n\nfor the actions of a subordinate is “extremely rigorous.” Cottone, 326 F.3d at\n\n1360. Supervisory officials cannot be held liable under § 1983 for unconstitutional\n\nacts by their subordinates based on respondeat-superior or vicarious-liability\n\nprinciples. Hartley v. Parnell, 193 F.3d 1263, 1269 (11th Cir. 1999). Instead,\n\nabsent allegations of personal participation—of which there are none here\n\nconcerning Hale or Eddings—supervisory liability is permissible only if there is a\n\n“causal connection” between a supervisor’s actions and the alleged constitutional\n\nviolation. Cottone, 326 F.3d at 1360.\n\n One way that a plaintiff can show the requisite causal connection is by\n\ndemonstrating that a supervisor’s policy or custom resulted in “deliberate\n\n\n\nthe similarities between the Fourth and Fourteenth Amendment inquiries, see supra at 9, they\nwould likely lead to the same result.\n\n 19\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 20 of 23\n\n\nindifference to constitutional rights.” 11 Id. at 1360–61. A plaintiff can also show\n\nthat the absence of a policy led to a violation of constitutional rights. Rivas v.\n\nFreeman, 940 F.2d 1491, 1495 (11th Cir. 1991). Either way, though, to prove that\n\na policy or its absence caused a constitutional harm, a plaintiff must point to\n\nmultiple incidents, see Rivas, 940 F.2d at 1495–96, or multiple reports of prior\n\nmisconduct by a particular employee, see Danley, 540 F.3d at 1315. “A single\n\nincident of a constitutional violation is insufficient to prove a policy or custom\n\neven when the incident involves several [subordinates].” Craig v. Floyd County,\n\n643 F.3d 1306, 1312 (11th Cir. 2011); see also Goebert v. Lee County, 510 F.3d\n\n1312, 1332 (11th Cir. 2007) (holding that plaintiff failed to meet the rigorous\n\nstandard for supervisory liability when she failed to show that any other inmates\n\nhad suffered the same alleged violation). Hunter has not made the requisite\n\nshowing with respect to either of the two theories that underlie his supervisory-\n\nliability claims against Hale and Eddings.\n\n 1\n\n With respect to excessive force, Hunter asserts that Hale and Eddings\n\n“fail[ed] to adopt and implement adequate policies” concerning the appropriate use\n\nof force and that this failure resulted in a violation of Hinkle’s constitutional rights.\n\n\n11\n Hale was the Sheriff of Jefferson County at the time of the relevant events, and Eddings was\nthe Commander of the Birmingham City Jail. The parties do not dispute that both acted as\npolicymakers for the jail.\n 20\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 21 of 23\n\n\nHunter does not, however, allege any other incidents or reports of excessive force\n\nby jail employees. Because Hunter’s excessive-force claim focuses solely on\n\nHinkle’s episode—“a single incident of unconstitutional activity”—it does not, as a\n\nmatter of law, state a claim against Hale and Eddings for supervisory liability. See\n\nCraig, 643 F.3d at 1312; see also Weiland v. Palm Beach Cty. Sheriff’s Office, 792\n\nF.3d 1313, 1329 (11th Cir. 2015) (holding that the “conclusory allegation that the\n\nSheriff’s Office was ‘on notice’ of the need to ‘promulgate, implement, and/or\n\noversee’ policies pertaining to the ‘use of force’” was insufficient when the claim\n\narose from a single incident involving two deputies).12\n\n 2\n\n The same goes for the supervisory-liability claims predicated on an alleged\n\ndeliberate indifference to Hinkle’s serious medical needs. Hunter asserts that\n\nHinkle was an alcoholic who was neither treated for his alcoholism nor provided\n\nhis prescription medication upon admission to the jail. Hunter does not, though,\n\npoint to other instances of inadequate medical screening or delayed medical care at\n\n\n\n12\n Compare Valdes v. Crosby, 450 F.3d 1231 (11th Cir. 2006) (finding supervisory liability when\nmultiple inmate complaints, warnings from other prison guards, and letters from family members\nput a prison warden on notice of a history of widespread abuse by certain prison guards and\nevidenced a causal connection between an inmate’s death by beating and the warden’s policy or\ncustom), with Hartley v. Parnell, 193 F.3d 1263 (11th Cir. 1999) (finding no supervisory liability\nfor a school superintendent based on a teacher’s sexual abuse of a student in the absence of any\nprior acts by a teacher that would have put the superintendent on notice that the teacher might\ncommit abuse or any evidence of a policy that could have led a teacher to believe that his\nbehavior was permissible).\n\n 21\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 22 of 23\n\n\nthe Birmingham City Jail, nor does he allege any facts indicating that Hale or\n\nEddings were on notice of the officers’ alleged deliberate indifference. Cf.\n\nAnderson v. City of Atlanta, 778 F.2d 678, 686 (11th Cir. 1985) (finding\n\nsupervisory liability for deliberate indifference to a pretrial detainee’s serious\n\nmedical needs when a supervisor failed to act after repeated complaints of\n\ninadequate staffing). Because Hunter’s complaint contains only conclusory\n\nassertions that jail officers were indifferent to Hinkle’s needs pursuant to certain\n\npolicies or customs—without alleging any facts concerning those policies or\n\ncustoms—he has not stated a claim for supervisory liability for deliberate\n\nindifference to serious medical needs. See Ashcroft v. Iqbal, 556 U.S. 662, 678\n\n(2009) (“[A] complaint [does not] suffice if it tenders ‘naked assertion[s]’ devoid\n\nof ‘further factual enhancement.’”) (quoting Bell Atl. Corp. v. Twombly, 550 U.S.\n\n544, 557 (2007)).\n\n * * *\n\n Accordingly, we hold that Hunter has failed to plead facts sufficient to\n\nsustain supervisory-liability claims against Sheriff Hale or Captain Eddings and\n\nthat the district court therefore erred in rejecting the officers’ qualified-immunity\n\ndefenses to those claims.\n\n\n\n\n 22\n\f Case: 18-10487 Date Filed: 05/09/2019 Page: 23 of 23\n\n\n III\n\n For the foregoing reasons, we affirm the district court’s denial of qualified\n\nimmunity to Deputy Dukuzumuremyi and reverse its denial of qualified immunity\n\nto Sheriff Hale and Captain Eddings.\n\n AFFIRMED IN PART AND REVERSED IN PART.\n\n\n\n\n 23\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Nyreekis Jarnell Hunter v. Mike Hale\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-09\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-10487 Date Filed: 05/09/2019 Page: 1 of 23\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-10487\\n ________________________\\n\\n D.C. Docket No. 2:16-cv-01521-MHH\\n\\nANTHONY PIAZZA,\\nas personal representative of the Estate of\\nRicky DeAngelo Hinkle, deceased,\\n\\n Plaintiff,\\n\\nNYREEKIS JARNELL HUNTER,\\nas personal representative of the Estate of\\nRicky DeAngelo Hinkle, deceased,\\n\\n Plaintiff - Appellee,\\n\\n\\n versus\\n\\nJEFFERSON COUNTY, ALABAMA,\\nan Alabama county, individually, et al,\\n\\n Defendants,\\n\\nMIKE HALE,\\nRON EDDINGS,\\nHABIMANA DUKUZUMUREMYI,\\neach individually,\\n\\n Defendants - Appellants.\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 2 of 23\\n\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Alabama\\n ________________________\\n\\n (May 9, 2019)\\n\\nBefore TJOFLAT, NEWSOM, and GILMAN, * Circuit Judges.\\n\\nNEWSOM, Circuit Judge:\\n\\n Ricky Hinkle died in the Birmingham City Jail after being shocked with a\\n\\ntaser, twice. Hinkle’s son, Nyreekis Hunter, brought suit under 42 U.S.C. § 1983\\n\\nalleging several claims on his behalf, including, as relevant here, (1) an excessive-\\n\\nforce claim against Deputy Habimana Dukuzumuremyi and (2) supervisory-\\n\\nliability claims for excessive force and deliberate indifference to Hinkle’s serious\\n\\nmedical needs against Sheriff Mike Hale and Captain Ron Eddings. The officers\\n\\nmoved to dismiss Hunter’s suit based on qualified immunity, the district court\\n\\ndenied their motion, and the officers now appeal.\\n\\n After careful review, we agree in part and disagree in part with the district\\n\\ncourt’s decision. We agree that the facts as Hunter has pleaded them show that\\n\\nDeputy Dukuzumuremyi violated Hinkle’s clearly established constitutional right\\n\\nto be free from excessive force. In particular, we hold that Dukuzumuremyi\\n\\ncrossed the constitutional line, and clearly so, when, having already tased Hinkle\\n\\n\\n*\\n Honorable Ronald Lee Gilman, United States Circuit Judge for the Sixth Circuit, sitting by\\ndesignation.\\n 2\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 3 of 23\\n\\n\\nonce—dropping him to the floor, rendering him motionless, and causing him to\\n\\nurinate on himself—Dukuzumuremyi shocked him again a full eight seconds later.\\n\\nWe disagree, however, that Hunter’s allegations show—as they must to support a\\n\\nsupervisory-liability claim—a causal connection between either the use of force\\n\\nagainst Hinkle or any deliberate indifference to Hinkle’s serious medical needs, on\\n\\nthe one hand, and any policy or custom implemented by Sheriff Hale or Captain\\n\\nEddings, on the other. Accordingly, we affirm the district court’s decision to deny\\n\\nqualified immunity to Deputy Dukuzumuremyi but reverse its decision to deny\\n\\nqualified immunity to Sheriff Hale and Captain Eddings.\\n\\n I\\n\\n Ricky Hinkle, who suffered from alcoholism, heart disease, and depression,\\n\\nwas arrested while “visibly intoxicated” and was taken to the Jefferson County Jail\\n\\nin Bessemer, Alabama. 1 The next day, he was transferred to the Birmingham City\\n\\nJail. Soon thereafter, he began suffering from alcohol-withdrawal symptoms and\\n\\nexhibiting delusional behavior. Jail officers moved Hinkle three different times\\n\\nbefore eventually (and presumably due to his deteriorating condition) placing him\\n\\nin a cell on Level 3, where Deputies Habimana Dukuzumuremyi and Christopher\\n\\nCotten were working.\\n\\n\\n1\\n The factual allegations in this case are largely undisputed, but because this appeal arises in a\\nmotion-to-dismiss posture, where the parties’ memories diverge we adopt Hunter’s re-telling.\\nSee Cottone v. Jenne, 326 F.3d 1352, 1357 (11th Cir. 2003).\\n 3\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 4 of 23\\n\\n\\n Shortly after Hinkle arrived on Level 3, Dukuzumuremyi realized that he\\n\\ncouldn’t see him on the video monitor, so he called to him over the loudspeaker.\\n\\nWhen Hinkle didn’t respond, Cotten went to investigate and found Hinkle in the\\n\\ncorner of his cell, wearing only underpants and shoes. When Cotten asked Hinkle\\n\\nwhy he was in the corner, Hinkle responded that he “wanted to die.” At this,\\n\\nCotten decided to move Hinkle to a padded cell. He walked Hinkle toward the cell\\n\\nand asked him to remove his shoes. Hinkle initially obeyed but then ran down the\\n\\nhallway to the bathroom and grabbed a shower curtain. Cotten took the shower\\n\\ncurtain away from Hinkle shortly before Dukuzumuremyi arrived on the scene.\\n\\n After the officers attempted three times to pull Hinkle into his new cell,\\n\\nDukuzumuremyi fired his taser, hitting Hinkle on the left side of his chest just\\n\\nabove his heart. As a result of that taser shock—which lasted 5 seconds—Hinkle\\n\\nfell to the floor on his right side and urinated on himself. Dukuzumuremyi then\\n\\nordered Hinkle to roll over to be handcuffed, but Hinkle remained unresponsive.\\n\\nEight seconds after the end of the first shock, and while Hinkle still lay motionless\\n\\n(and wet) on the ground, Dukuzumuremyi tased him again, this time on the front\\n\\nleft side of his neck. Shortly after the second shock, Hinkle went into cardiac\\n\\narrest. He was taken to the emergency room, where he was pronounced dead.\\n\\n\\n\\n\\n 4\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 5 of 23\\n\\n\\n Hinkle’s son Nyreekis Hunter, acting as personal representative of Hinkle’s\\n\\nestate, brought suit under 42 U.S.C. § 1983 on Hinkle’s behalf.2 As relevant here,\\n\\nHunter sued Deputy Dukuzumuremyi for excessive force and Deputy Cotten for\\n\\nfailure to intervene, and both deputies for deliberate indifference to Hinkle’s\\n\\nserious medical needs. He also sued Sheriff Hale and Captain Eddings on a\\n\\nsupervisory-liability theory based on the excessive-force and deliberate-\\n\\nindifference claims. The officers moved to dismiss on qualified-immunity\\n\\ngrounds.3\\n\\n The district court granted in part and denied in part the officers’ motion to\\n\\ndismiss. The court dismissed the deliberate-indifference claim against\\n\\nDukuzumuremyi and Cotten, finding that the complaint “contain[ed] no allegations\\n\\nto indicate that either deputy had subjective knowledge of the decedent’s medical\\n\\ncondition.” The court also dismissed the failure-to-intervene claim against\\n\\nCotten. 4 But the court denied the motion to dismiss as to (1) the excessive-force\\n\\n\\n\\n\\n2\\n The initial complaint was filed by Anthony Piazza, who is not related to Hinkle. After some\\ndispute over whether Piazza could properly represent Hinkle’s estate, Hunter replaced Piazza as\\nHinkle’s personal representative.\\n3\\n Hunter also brought state-law claims against each officer for negligence and wrongful death;\\nthe district court dismissed each claim on state-law grounds.\\n4\\n Deputy Cotten is not a party to this appeal because the district court dismissed all claims against\\nhim. Two other defendants, Dr. David Hicks and Advanced Correctional Healthcare, were also\\nnamed in Hunter’s complaint—for exhibiting deliberate indifference to Hinkle’s serious medical\\nneeds—but neither is a party to this appeal.\\n\\n 5\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 6 of 23\\n\\n\\nclaim against Dukuzumuremyi and (2) the supervisory-liability claims against Hale\\n\\nand Eddings. Dukuzumuremyi, Hale, and Eddings timely appealed.5\\n\\n II\\n\\n We review de novo a district court’s denial of qualified immunity. Cottone\\n\\nv. Jenne, 326 F.3d 1352, 1357 (11th Cir. 2003). Qualified immunity shields a\\n\\ngovernment official from liability unless he violates “clearly established statutory\\n\\nor constitutional rights of which a reasonable person would have known.” Foy v.\\n\\nHolston, 94 F.3d 1528, 1532 (11th Cir. 1996). An officer asserting a qualified-\\n\\nimmunity defense bears the initial burden of showing that he was “acting within\\n\\nhis discretionary authority.” Skop v. City of Atlanta, 485 F.3d 1130, 1136 (11th\\n\\nCir. 2007). After the officer makes this showing—and here, it is undisputed—the\\n\\nburden shifts to the plaintiff to show that (1) the officer violated a constitutional\\n\\nright and (2) the right was clearly established at the time of the alleged\\n\\nviolation. Holloman ex rel. Holloman v. Harland, 370 F.3d 1252, 1264 (11th Cir.\\n\\n2004). We may consider these two prongs in either order; an official is entitled to\\n\\n\\n\\n\\n5\\n We have jurisdiction over the officers’ interlocutory appeal under 28 U.S.C. § 1291 because the\\ndistrict court denied qualified immunity based on questions of law—namely, whether the officers\\nviolated Hinkle’s constitutional rights and whether those rights were clearly established. See\\nMitchell v. Forsyth, 472 U.S. 511, 530 (1985) (“[A] district court’s denial of a claim of qualified\\nimmunity, to the extent that it turns on an issue of law, is an appealable ‘final decision’ within\\nthe meaning of 28 U.S.C. § 1291 notwithstanding the absence of a final judgment.”).\\n\\n\\n 6\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 7 of 23\\n\\n\\nqualified immunity if the plaintiff fails to establish either. Jacoby v. Baldwin\\n\\nCounty, 835 F.3d 1338, 1344 (11th Cir. 2016).\\n\\n We start with the excessive-force claim against Deputy Dukuzumuremyi,\\n\\nand then move to the supervisory-liability claims against Sheriff Hale and Captain\\n\\nEddings.\\n\\n A\\n\\n 1\\n\\n First things first. What constitutional provision governs the use of force in\\n\\nthis case, and what doctrinal standard guides our analysis? While the Fourth\\n\\nAmendment prevents the use of excessive force during arrests, see Graham v.\\n\\nConnor, 490 U.S. 386, 388 (1989), and the Eighth Amendment serves as the\\n\\nprimary source of protection against excessive force after conviction, see Whitley\\n\\nv. Albers, 475 U.S. 312, 327 (1986), it is the Fourteenth Amendment that protects\\n\\nthose who exist in the in-between—pretrial detainees. Garrett v. Athens–Clarke\\n\\nCounty, 378 F.3d 1274, 1279 n.11 (11th Cir. 2004).6\\n\\n That pretrial detainees fall within the Fourteenth Amendment’s ambit dates\\n\\nto the Supreme Court’s decision in Bell v. Wolfish, 441 U.S. 520 (1979). The\\n\\n\\n6\\n Although some courts have extended Fourth Amendment protections into the pretrial detention\\nphase, see, e.g., Aldini v. Johnson, 609 F.3d 858, 866 (6th Cir. 2010), “[n]either [this Court] nor\\nthe Supreme Court has decided whether the Fourth Amendment continues to provide individuals\\nwith protection from excessive force beyond the point at which an arrest ends and pretrial\\ndetention begins,” J W by & through Tammy Williams v. Birmingham Board of Education, 904\\nF.3d 1248, 1259 (11th Cir. 2018).\\n 7\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 8 of 23\\n\\n\\nCourt explained there that the “proper inquiry” when “evaluating the\\n\\nconstitutionality of conditions or restrictions of pretrial detention” is “whether\\n\\nthose conditions amount to punishment of the detainee.” Id. at 535. “For under\\n\\nthe Due Process Clause,” the Court continued, “a detainee may not be punished\\n\\nprior to an adjudication of guilt in accordance with due process of law.” Id.\\n\\n Although pretrial detainees’ excessive-force claims have been analyzed\\n\\nunder the Fourteenth Amendment since Bell, the constitutional inquiry—at least in\\n\\nthis Circuit—has long resembled the one that governs prisoners’ excessive-force\\n\\nclaims under the Eighth Amendment. Historically, both prisoners and pretrial\\n\\ndetainees needed to show not only that a jail official deliberately used excessive\\n\\nforce, but also that the official did so “maliciously or sadistically for the very\\n\\npurpose of causing harm.” Bozeman v. Orum, 422 F.3d 1265, 1271 (11th Cir.\\n\\n2005), overruled by Kingsley v. Hendrickson, 135 S. Ct. 2466, 2473 (2015). All\\n\\nthat changed a few years back, though, when the Supreme Court clarified that,\\n\\nunlike a prisoner bringing an Eighth Amendment excessive-force claim, a pretrial\\n\\ndetainee raising a Fourteenth Amendment claim needn’t prove an officer’s\\n\\nsubjective intent to harm but instead need show only that “the force purposely or\\n\\nknowingly used against him was objectively unreasonable.” Kingsley, 135 S. Ct.\\n\\nat 2473.\\n\\n\\n\\n\\n 8\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 9 of 23\\n\\n\\n Harking back to Bell, the Kingsley Court explained that, unlike in Eighth\\n\\nAmendment cases, there is no need in the pretrial-detainee context to determine\\n\\n“when punishment is unconstitutional” because a pretrial detainee has not yet been\\n\\nadjudicated guilty and thus may not be punished at all. Id. at 2475 (emphasis\\n\\nadded). Although, under Bell, impermissible “punishment” could mean force\\n\\ndeployed with a subjective, “expressed intent to punish,” it also could mean force\\n\\nthat, as an objective matter, is “not rationally related to a legitimate governmental”\\n\\npurpose or is “excessive in relation to that purpose.” Id. at 2473–74. After\\n\\nKingsley, then, if force used against a pretrial detainee is more severe than is\\n\\nnecessary to subdue him or otherwise achieve a permissible governmental\\n\\nobjective, it constitutes “punishment” and is therefore unconstitutional. Notably,\\n\\ninasmuch as it entails an inquiry into the objective reasonableness of the officers’\\n\\nactions, the Fourteenth Amendment standard has come to resemble the test that\\n\\ngoverns excessive-force claims brought by arrestees under the Fourth Amendment.\\n\\nCompare Kingsley, 135 S. Ct. at 2472–73 (holding that a pretrial detainee in the\\n\\nFourteenth Amendment context “must show only that the force purposely or\\n\\nknowingly used against him was objectively unreasonable”), with Graham, 490\\n\\nU.S. at 397 (explaining that the Fourth Amendment excessive-force inquiry asks\\n\\n“whether the officers’ actions are ‘objectively reasonable’ in light of the facts and\\n\\n\\n\\n\\n 9\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 10 of 23\\n\\n\\ncircumstances confronting them, without regard to their underlying intent or\\n\\nmotivation”).\\n\\n Obviously, “legitimate interests”—including the need to “preserve internal\\n\\norder and discipline” and “maintain institutional security”—may at times require\\n\\njail officers to use force. Kingsley, 135 S. Ct. at 2473 (citation omitted). And of\\n\\ncourse, officers facing disturbances are often forced to make “split-second\\n\\njudgments” about the need for such force “in circumstances that are tense,\\n\\nuncertain, and rapidly evolving.” Id. at 2474 (quoting Graham, 490 U.S. at 397).\\n\\nBecause of this, we can’t (and won’t) evaluate a pretrial detainee’s excessive-force\\n\\nchallenge in a glib, post-hoc fashion or “with the 20/20 vision of hindsight.” Id. at\\n\\n2473. Instead, we must do our best to consider the situation through the lens of “a\\n\\nreasonable officer on the scene.” Id.\\n\\n How do we know, then, when force is reasonable and when it is “excessive\\n\\nin relation to its purpose”? Well, as relevant to this case, our decisions make one\\n\\nthing clear: “Once a prisoner has stopped resisting there is no longer a need for\\n\\nforce, so the use of force thereafter is disproportionate to the need.” Danley v.\\n\\nAllen, 540 F.3d 1298, 1309 (11th Cir. 2008) (emphasis added), abrogated on other\\n\\ngrounds by Kingsley, 135 S. Ct. 2466. Accordingly, “[w]hen jailers continue to\\n\\nuse substantial force against a prisoner who has clearly stopped resisting—whether\\n\\nbecause he has decided to become compliant, he has been subdued, or he is\\n\\n\\n 10\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 11 of 23\\n\\n\\notherwise incapacitated—that use of force is excessive.” Id. (emphasis added); see\\n\\nalso Ort v. White, 813 F.2d 318, 327 (11th Cir. 1987) (“A [F]ourteenth\\n\\n[A]mendment violation occurs . . . where prison officers continue to employ force\\n\\nor other coercive measures after the necessity for such coercive action has\\n\\nceased.”); Bozeman, 422 F.3d at 1271–72 (finding excessive force when officers\\n\\ncontinued to suffocate a detainee by pushing his face into a mattress after he had\\n\\nstopped struggling and said he’d had enough), overruled on other grounds by\\n\\nKingsley, 135 S. Ct. 2466.7 In other words, because force in the pretrial detainee\\n\\ncontext may be defensive or preventative—but never punitive—the continuing use\\n\\nof force is impermissible when a detainee is complying, has been forced to comply,\\n\\nor is clearly unable to comply.\\n\\n 2\\n\\n In the case before us, then, we must determine whether the force used\\n\\nagainst Hinkle was objectively unreasonable—i.e., whether it was “excessive in\\n\\nrelation to [its] purpose.” Kingsley, 135 S. Ct. at 2473–74. To briefly recap, the\\n\\ncritical events began when Hinkle broke away from Cotten, ran down the hallway,\\n\\n\\n7\\n To be clear, Bozeman and Danley remain relevant to our inquiry even though both employed\\nthe more stringent pre-Kingsley standard of proof: whether force was applied “maliciously or\\nsadistically for the very purpose of causing harm.” Bozeman, 422 F.3d at 1272. Because\\nproving both that the force applied in a given situation was objectively excessive and that it was\\napplied “maliciously or sadistically for the very purpose of causing harm” will almost invariably\\nbe more difficult than proving only that the force used was objectively excessive, these cases\\ncontinue to provide pertinent examples of excessive force in the pretrial-detainee context.\\n\\n 11\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 12 of 23\\n\\n\\nand grabbed a shower curtain. (Not the curtain rod, mind you—the curtain.) After\\n\\nthree unsuccessful attempts to lead Hinkle into his cell, Dukuzumuremyi fired his\\n\\ntaser, hitting Hinkle just above the heart with a five-second shock. Eight seconds\\n\\nafter the first shock ended—and with Hinkle still prostrate on the ground, and\\n\\nhaving wet himself—Dukuzumuremyi tased Hinkle again.\\n\\n The parties don’t dispute that the first shock was a permissible use of force\\n\\ngiven Hinkle’s resistance and the officers’ need to “preserve internal order and\\n\\ndiscipline” and “maintain institutional security.” See Kingsley, 135 S. Ct. at 2473.\\n\\nThe issue is the second shock. Dukuzumuremyi asserts that the second shock\\n\\ndoesn’t constitute excessive force in light of (1) Hinkle’s failure to roll over to be\\n\\nhandcuffed “after being ordered—and being given an opportunity—to do so,” and\\n\\n(2) the “split-second decisions” that jail officers must make. The facts alleged,\\n\\nhowever, undermine both assertions.\\n\\n Again, according to Hunter’s complaint, following the first taser shock\\n\\nHinkle fell to the floor, lay motionless, and urinated on himself. Even so,\\n\\nDukuzumuremyi contends that because Hinkle failed to obey the subsequent order\\n\\nto roll over and be handcuffed, he was not yet fully compliant. Because Hinkle\\n\\nwas not following commands, the argument goes, the second shock couldn’t have\\n\\ncrossed the constitutional line. Oral Arg. Tr. 7:07. Wrong. It seems to us totally\\n\\nunreasonable to expect that a man who is lying on the floor immobilized—and\\n\\n\\n 12\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 13 of 23\\n\\n\\nincontinent—following a taser shock should pep up, roll over, and submit to\\n\\nhandcuffing within eight seconds. But, Dukuzumuremyi counters, Hunter’s\\n\\ncomplaint doesn’t specifically allege that Hinkle “could not” roll over, only that he\\n\\n“did not.” Oral Arg. Tr. 7:45. Come on. The only reasonable inference is that\\n\\nHinkle, who was lying motionless on the floor after a five-second taser shock—\\n\\nunable to hold his own urine—“did not” immediately roll over because he “could\\n\\nnot.” (Really, is there any surer indication of a grown man’s inability to control his\\n\\nbodily functions than his wetting himself?)\\n\\n The same facts undermine Dukuzumuremyi’s contention that the second\\n\\nshock should be swept into the zone of reasonableness by the deference owed an\\n\\nofficer’s split-second decisions. Although we don’t for a minute discount the\\n\\ndifficult decisions that jail officers must make in the heat of a tussle, simply\\n\\ncounting to eight aloud reveals the problem with Dukuzumuremyi’s argument. In\\n\\neight seconds, you can tie a shoe, sing the chorus of “Row, Row, Row Your Boat,”\\n\\nor complete a qualified rodeo bull ride. And in eight seconds, we believe, any\\n\\nreasonable officer would have concluded that a detainee who lay inert on the floor,\\n\\nhaving soiled himself, was no longer putting up a fight. See Kingsley, 135 S. Ct. at\\n\\n2473 (listing “whether the plaintiff was actively resisting” and “any effort made by\\n\\nthe officer to temper or to limit the amount of force used” as factors potentially\\n\\nrelevant to the excessive-force determination).\\n\\n\\n 13\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 14 of 23\\n\\n\\n Our conclusion is fortified by additional considerations that the Supreme\\n\\nCourt mentioned in Kingsley that “bear on the reasonableness or unreasonableness\\n\\nof the force used,” including the severity of the security issue posed by the detainee\\n\\nand the threat reasonably perceived by the officer. See Kingsley, 135 S. Ct. at\\n\\n2473. Although officers may (of course) use force to “preserve internal order and\\n\\ndiscipline” and “maintain institutional security,” the severity of the problem and\\n\\nthe corresponding risk to the officers in this case were—from the very outset—\\n\\nexceedingly minimal. See id. Instead of facing, say, a man armed with a knife\\n\\nrunning toward them, the officers here faced a man armed with a shower curtain\\n\\nrunning away from them. See, e.g., Shaw v. City of Selma, 884 F.3d 1093, 1099\\n\\n(11th Cir. 2018) (officer entitled to qualified immunity on an excessive-force claim\\n\\nafter shooting a mentally-ill man walking toward him with a hatchet); Smith v.\\n\\nLePage, 834 F.3d 1285, 1294–95 (11th Cir. 2016) (officer entitled to qualified\\n\\nimmunity on an excessive-force claim when a suspect holding a knife refused to\\n\\ncomply with orders to disarm himself); Singletary v. Vargas, 804 F.3d 1174, 1185\\n\\n(11th Cir. 2015) (officer entitled to qualified immunity on an excessive-force claim\\n\\nbased on his reasonable belief that a car rolling toward him presented a deadly\\n\\nthreat). Although non-compliant, Hinkle had neither threatened nor attempted to\\n\\nharm the officers. While we don’t question Dukuzumuremyi’s split-second\\n\\ndecision to deploy his taser once following several unsuccessful attempts to lead\\n\\n\\n 14\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 15 of 23\\n\\n\\nHinkle into his cell, we see no legitimate basis for the second shock, particularly\\n\\nconsidering (1) that the first shock had immobilized Hinkle and (2) the minimal\\n\\nthreat to order, safety, and security that Hinkle posed even from the outset.\\n\\n At the end of the day the question before us is this: Is it excessive to tase for\\n\\na second time a man who, as a result of an initial shock, is lying motionless on the\\n\\nfloor and has wet himself, and who presented only a minimal threat to begin with?\\n\\nUndoubtedly, yes. We hold that, based on the allegations in Hunter’s complaint,\\n\\nthe force used against Hinkle was excessive, and thus unconstitutional.\\n\\n 3\\n\\n Of course, to overcome Dukuzumuremyi’s qualified-immunity defense,\\n\\nHunter must further show that the law that governs his case was “clearly\\n\\nestablished” at the time of the alleged violation. To qualify, a legal principle must\\n\\nbe “settled” and “clear enough that every reasonable official would interpret it to\\n\\nestablish the particular rule the plaintiff seeks to apply.” District of Columbia v.\\n\\nWesby, 138 S. Ct. 577, 589–90 (2018). The critical question is whether the law\\n\\ngave the officer “fair warning” that his conduct was unconstitutional. Glasscox v.\\n\\nCity of Argo, 903 F.3d 1207, 1217–18 (11th Cir. 2018) (citing Hope v. Pelzer, 536\\n\\nU.S. 730, 741 (2002)).\\n\\n Here, it certainly did. It was more than ten years ago now that this Court\\n\\nheld, in no uncertain terms, that “[w]hen jailers continue to use substantial force\\n\\n\\n 15\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 16 of 23\\n\\n\\nagainst a prisoner who has clearly stopped resisting—whether because he has\\n\\ndecided to become compliant, he has been subdued, or he is otherwise\\n\\nincapacitated—that use of force is excessive.” Danley, 540 F.3d at 1309; see also\\n\\nid. (“Once a prisoner has stopped resisting there is no longer a need for force, so\\n\\nthe use of force thereafter is disproportionate to the need.”).8 And Danley was no\\n\\ninnovation; for decades our decisions have embraced and reiterated the principle\\n\\nthat an officer may not continue to use force after a detainee has clearly stopped\\n\\nresisting. See Skrtich v. Thornton, 280 F.3d 1295, 1303 (11th Cir. 2002)\\n\\n(“[G]overnment officials may not use gratuitous force against a prisoner who has\\n\\nbeen already subdued or, as in this case, incapacitated.”); Williams v. Burton, 943\\n\\nF.2d 1572, 1576 (11th Cir. 1991) (“The basic legal principle is that once the\\n\\nnecessity for the application of force ceases, any continued use of harmful force\\n\\ncan be a violation of the Eighth and Fourteenth Amendments.”); Ort, 813 F.2d at\\n\\n327 (“A [F]ourteenth [A]mendment violation occurs . . . where prison officers\\n\\ncontinue to employ force or other coercive measures after the necessity for such\\n\\ncoercive action has ceased.”).9\\n\\n8\\n Again, although Kingsley changed the nature of the inquiry—by dropping the requirement that\\na plaintiff prove the officers’ subjective malicious intent—it did not change the law with respect\\nto the objective reasonableness of using force against unresisting subjects.\\n9\\n The same basic rule guides our Fourth Amendment cases concerning the use of force against\\nunresisting or subdued arrestees. See, e.g., Hadley v. Gutierrez, 526 F.3d 1324, 1330 (11th Cir.\\n2008) (punching a suspect in the stomach constituted excessive force when he was already\\nsubdued and not struggling); Lee v. Ferraro, 284 F.3d 1188, 1200 (11th Cir. 2002) (slamming a\\nsuspect’s head onto the hood of her car constituted excessive force when she no longer posed a\\n 16\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 17 of 23\\n\\n\\n To be clear, it is no answer to say that Danley involved pepper spray, Skrtich\\n\\nkicks and punches, Williams four-point restraints, etc.—and that none of those\\n\\ncases concerned the use of a taser specifically. It’s true, of course, that to defeat\\n\\nqualified immunity a rule must be specific enough that an act’s unlawfulness\\n\\n“follow[s] immediately from the conclusion that the rule was firmly established,”\\n\\nWesby, 138 S. Ct. at 590 (citation omitted). But we have never suggested that the\\n\\nlongstanding prohibition on a jail officer’s use of force on an incapacitated\\n\\ndetainee turns on as fine a point as the particular weapon deployed. And indeed, in\\n\\nthe analogous Fourth Amendment context, we have flatly rejected that very\\n\\ndistinction—in a case involving a taser, no less. In Fils v. City of Aventura, we\\n\\nconsidered allegations that police officers had impermissibly tased a non-violent,\\n\\nunresisting suspect. 647 F.3d 1272, 1288–90 (11th Cir. 2011). In finding the law\\n\\nprohibiting the tasing clearly established, we relied on one case holding that an\\n\\nofficer had used excessive force when he pepper-sprayed a secured suspect in the\\n\\nface as she sat shackled in the backseat of his cruiser, see id. at 1289 (citing\\n\\nVinyard v. Wilson, 311 F.3d 1340 (11th Cir. 2002)), another holding that an officer\\n\\nhad used excessive force when he punched a handcuffed and unresisting plaintiff\\n\\nin the stomach, see id. (citing Hadley v. Gutierrez, 526 F.3d 1324 (11th Cir.\\n\\n\\n\\nthreat to the officer nor a flight risk); Slicker v. Jackson, 215 F.3d 1225, 1233 (11th Cir.\\n2000) (kicking a suspect in the ribs constituted excessive force when he was subdued and no\\nlonger resisting).\\n 17\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 18 of 23\\n\\n\\n2008)), and yet another holding that an officer had used excessive force when he\\n\\nsicced his police dog on a suspect who was lying still on the ground, see id. (citing\\n\\nPriester v. City of Riviera Beach, 208 F.3d 919 (11th Cir. 2000)). We emphasized\\n\\nthat “[a]lthough none of these cases involved tasers,” there was “no meaningful\\n\\ndistinction under these circumstances” between the use of a taser on an unresisting\\n\\nsuspect and the use of pepper spray, fists, or police dogs. Id.; see also Wate v.\\n\\nKubler, 839 F.3d 1012, 1022 (11th Cir. 2016) (looking not only to a taser-specific\\n\\ncase but also to cases involving a gut-punch and a head-slam to determine that the\\n\\nuse of force on an unresisting arrestee violated clearly established law).\\n\\n So too here. There is “no meaningful distinction” between pepper spray to\\n\\nan unresisting detainee’s face, a kick to his gut, or a taser to his chest and neck.\\n\\nThe crucial question is whether the law gave Dukuzumuremyi “fair warning” that\\n\\nhis conduct—tasing an already-tased, incapacitated, incontinent, and unresisting\\n\\ndetainee—violated the Fourteenth Amendment. In the light of our use-of-force\\n\\nprecedent, we have no trouble concluding that it did. 10\\n\\n\\n10\\n A panel of this Court also found it clearly established that the repeated deployment of a taser\\non an unresisting arrestee constituted excessive force in violation of the Fourth Amendment.\\nGlasscox v. City of Argo, 903 F.3d 1207 (11th Cir. 2018). We don’t rely on Glasscox because\\nlaw can be clearly established for overcoming qualified immunity only if it is established prior to\\nthe relevant events, and Hinkle’s death occurred in 2014, four years before Glasscox issued.\\nThat being said, the Glasscox Court based its decision on two earlier cases—Oliver v. Fiorino,\\n586 F.3d 898 (11th Cir. 2009), and Smith v. Mattox, 127 F.3d 1416 (11th Cir. 1997)—that\\ntogether establish that the repeated use of a taser on an unresisting arrestee constitutes excessive\\nforce. Given the ample Fourteenth Amendment precedent prohibiting jail officers from using\\nforce on an unresisting detainee, we needn’t rely on Oliver and Smith; we simply note that, given\\n 18\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 19 of 23\\n\\n\\n * * *\\n\\n Accordingly, we hold that Deputy Dukuzumuremyi’s second taser shock\\n\\nviolated Hunter’s clearly established Fourteenth Amendment right to be free from\\n\\nexcessive force and that the district court therefore correctly rejected\\n\\nDukuzumuremyi’s qualified-immunity defense.\\n\\n B\\n\\n We turn, then, to consider the supervisory-liability claims against Sheriff\\n\\nHale and Captain Eddings. The standard by which a supervisor can be held liable\\n\\nfor the actions of a subordinate is “extremely rigorous.” Cottone, 326 F.3d at\\n\\n1360. Supervisory officials cannot be held liable under § 1983 for unconstitutional\\n\\nacts by their subordinates based on respondeat-superior or vicarious-liability\\n\\nprinciples. Hartley v. Parnell, 193 F.3d 1263, 1269 (11th Cir. 1999). Instead,\\n\\nabsent allegations of personal participation—of which there are none here\\n\\nconcerning Hale or Eddings—supervisory liability is permissible only if there is a\\n\\n“causal connection” between a supervisor’s actions and the alleged constitutional\\n\\nviolation. Cottone, 326 F.3d at 1360.\\n\\n One way that a plaintiff can show the requisite causal connection is by\\n\\ndemonstrating that a supervisor’s policy or custom resulted in “deliberate\\n\\n\\n\\nthe similarities between the Fourth and Fourteenth Amendment inquiries, see supra at 9, they\\nwould likely lead to the same result.\\n\\n 19\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 20 of 23\\n\\n\\nindifference to constitutional rights.” 11 Id. at 1360–61. A plaintiff can also show\\n\\nthat the absence of a policy led to a violation of constitutional rights. Rivas v.\\n\\nFreeman, 940 F.2d 1491, 1495 (11th Cir. 1991). Either way, though, to prove that\\n\\na policy or its absence caused a constitutional harm, a plaintiff must point to\\n\\nmultiple incidents, see Rivas, 940 F.2d at 1495–96, or multiple reports of prior\\n\\nmisconduct by a particular employee, see Danley, 540 F.3d at 1315. “A single\\n\\nincident of a constitutional violation is insufficient to prove a policy or custom\\n\\neven when the incident involves several [subordinates].” Craig v. Floyd County,\\n\\n643 F.3d 1306, 1312 (11th Cir. 2011); see also Goebert v. Lee County, 510 F.3d\\n\\n1312, 1332 (11th Cir. 2007) (holding that plaintiff failed to meet the rigorous\\n\\nstandard for supervisory liability when she failed to show that any other inmates\\n\\nhad suffered the same alleged violation). Hunter has not made the requisite\\n\\nshowing with respect to either of the two theories that underlie his supervisory-\\n\\nliability claims against Hale and Eddings.\\n\\n 1\\n\\n With respect to excessive force, Hunter asserts that Hale and Eddings\\n\\n“fail[ed] to adopt and implement adequate policies” concerning the appropriate use\\n\\nof force and that this failure resulted in a violation of Hinkle’s constitutional rights.\\n\\n\\n11\\n Hale was the Sheriff of Jefferson County at the time of the relevant events, and Eddings was\\nthe Commander of the Birmingham City Jail. The parties do not dispute that both acted as\\npolicymakers for the jail.\\n 20\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 21 of 23\\n\\n\\nHunter does not, however, allege any other incidents or reports of excessive force\\n\\nby jail employees. Because Hunter’s excessive-force claim focuses solely on\\n\\nHinkle’s episode—“a single incident of unconstitutional activity”—it does not, as a\\n\\nmatter of law, state a claim against Hale and Eddings for supervisory liability. See\\n\\nCraig, 643 F.3d at 1312; see also Weiland v. Palm Beach Cty. Sheriff’s Office, 792\\n\\nF.3d 1313, 1329 (11th Cir. 2015) (holding that the “conclusory allegation that the\\n\\nSheriff’s Office was ‘on notice’ of the need to ‘promulgate, implement, and/or\\n\\noversee’ policies pertaining to the ‘use of force’” was insufficient when the claim\\n\\narose from a single incident involving two deputies).12\\n\\n 2\\n\\n The same goes for the supervisory-liability claims predicated on an alleged\\n\\ndeliberate indifference to Hinkle’s serious medical needs. Hunter asserts that\\n\\nHinkle was an alcoholic who was neither treated for his alcoholism nor provided\\n\\nhis prescription medication upon admission to the jail. Hunter does not, though,\\n\\npoint to other instances of inadequate medical screening or delayed medical care at\\n\\n\\n\\n12\\n Compare Valdes v. Crosby, 450 F.3d 1231 (11th Cir. 2006) (finding supervisory liability when\\nmultiple inmate complaints, warnings from other prison guards, and letters from family members\\nput a prison warden on notice of a history of widespread abuse by certain prison guards and\\nevidenced a causal connection between an inmate’s death by beating and the warden’s policy or\\ncustom), with Hartley v. Parnell, 193 F.3d 1263 (11th Cir. 1999) (finding no supervisory liability\\nfor a school superintendent based on a teacher’s sexual abuse of a student in the absence of any\\nprior acts by a teacher that would have put the superintendent on notice that the teacher might\\ncommit abuse or any evidence of a policy that could have led a teacher to believe that his\\nbehavior was permissible).\\n\\n 21\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 22 of 23\\n\\n\\nthe Birmingham City Jail, nor does he allege any facts indicating that Hale or\\n\\nEddings were on notice of the officers’ alleged deliberate indifference. Cf.\\n\\nAnderson v. City of Atlanta, 778 F.2d 678, 686 (11th Cir. 1985) (finding\\n\\nsupervisory liability for deliberate indifference to a pretrial detainee’s serious\\n\\nmedical needs when a supervisor failed to act after repeated complaints of\\n\\ninadequate staffing). Because Hunter’s complaint contains only conclusory\\n\\nassertions that jail officers were indifferent to Hinkle’s needs pursuant to certain\\n\\npolicies or customs—without alleging any facts concerning those policies or\\n\\ncustoms—he has not stated a claim for supervisory liability for deliberate\\n\\nindifference to serious medical needs. See Ashcroft v. Iqbal, 556 U.S. 662, 678\\n\\n(2009) (“[A] complaint [does not] suffice if it tenders ‘naked assertion[s]’ devoid\\n\\nof ‘further factual enhancement.’”) (quoting Bell Atl. Corp. v. Twombly, 550 U.S.\\n\\n544, 557 (2007)).\\n\\n * * *\\n\\n Accordingly, we hold that Hunter has failed to plead facts sufficient to\\n\\nsustain supervisory-liability claims against Sheriff Hale or Captain Eddings and\\n\\nthat the district court therefore erred in rejecting the officers’ qualified-immunity\\n\\ndefenses to those claims.\\n\\n\\n\\n\\n 22\\n\\f Case: 18-10487 Date Filed: 05/09/2019 Page: 23 of 23\\n\\n\\n III\\n\\n For the foregoing reasons, we affirm the district court’s denial of qualified\\n\\nimmunity to Deputy Dukuzumuremyi and reverse its denial of qualified immunity\\n\\nto Sheriff Hale and Captain Eddings.\\n\\n AFFIRMED IN PART AND REVERSED IN PART.\\n\\n\\n\\n\\n 23\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2277,"cells":{"id":{"kind":"number","value":4618174,"string":"4,618,174"},"name":{"kind":"string","value":"FLAT CREEK TRANSPORTATION, LLC, an Alabama Limited Liability Company, Plaintiff - Appellant, v. FEDERAL MOTOR CARRIER SAFETY ADMINISTRATION, Kenny Price, in His Capacity as Alabama Division Administrator (Federal Motor Carrier Safety Administration), Elaine L. Chao, in Her Capacity as Secretary of the United States Department of Transportation, Defendants - Appellees, Anthony R. Foxx, in His Capacity as Secretary of the United States Department of Transportation, Defendant."},"name_abbreviation":{"kind":"string","value":"Flat Creek Transportation, LLC v. Federal Motor Carrier Safety Administration"},"decision_date":{"kind":"string","value":"2019-05-09"},"docket_number":{"kind":"string","value":"17-14670"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Tjoflat, Newsom, Gilman\", \"parties\": \"\", \"opinions\": [{\"author\": \"NEWSOM, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-14670 Date Filed: 05/09/2019 Page: 1 of 13\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-14670\\n ________________________\\n\\n D.C. Docket No. 1:16-cv-00876-WKW-TFM\\n\\nFLAT CREEK TRANSPORTATION, LLC,\\nan Alabama limited liability company,\\n\\n Plaintiff - Appellant,\\n\\n versus\\n\\nFEDERAL MOTOR CARRIER SAFETY ADMINISTRATION,\\nKENNY PRICE,\\nin his capacity as Alabama Division Administrator\\n(Federal Motor Carrier Safety Administration),\\nELAINE L. CHAO,\\nin her capacity as Secretary of the United States Department of Transportation,\\n\\n Defendants - Appellees,\\n\\nANTHONY R. FOXX,\\nin his capacity as Secretary of the United States Department of Transportation,\\n\\n Defendant.\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 2 of 13\\n\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Alabama\\n ________________________\\n (May 9, 2019)\\n\\nBefore TJOFLAT, NEWSOM, and GILMAN, * Circuit Judges.\\n\\nNEWSOM, Circuit Judge:\\n\\n Flat Creek Transportation sued for declaratory and injunctive relief on the\\n\\nground that the Federal Motor Carrier Safety Administration had unfairly targeted\\n\\nit for compliance reviews and used an unsound methodology in doing so. The\\n\\ndistrict court determined that it lacked subject matter jurisdiction to consider Flat\\n\\nCreek’s claims. We reach the same destination, albeit by a different route. We\\n\\nhold that Flat Creek has failed to establish that it suffered an injury in fact\\n\\nsufficient to confer standing to sue.\\n\\n I\\n\\n Flat Creek is a commercial trucking company that transports non-hazardous\\n\\nmaterials—mainly refrigerated food products. Because it operates in interstate\\n\\ncommerce, Flat Creek is subject to Department of Transportation regulations. And\\n\\nbecause its claim in this case arises against the backdrop of that regulatory\\n\\n\\n\\n\\n*\\n Honorable Ronald L. Gilman, United States Circuit Judge for the Sixth Circuit, sitting by\\ndesignation.\\n\\n 2\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 3 of 13\\n\\n\\nframework, we begin with an overview. (Warning: Unavoidable Acronyms\\n\\nAhead.)\\n\\n A\\n\\n Within the Department of Transportation, the Federal Motor Carrier Safety\\n\\nAdministration (“FMCSA”) investigates carriers and operators to ensure that they\\n\\nare safe to operate on the nation’s roadways. FMCSA uses a safety-fitness rating\\n\\nmethodology—the Safety Measurement System (“SMS”)—to quantify carriers’\\n\\nperformance. For example, the SMS pulls data from the Motor Carrier\\n\\nManagement Information System (“MCMIS”) related to the following metrics: (1)\\n\\nunsafe driving, (2) fatigued driving, (3) driver fitness, (4) controlled-substance and\\n\\nalcohol usage, (5) vehicle maintenance, (6) hazardous-material compliance, and (7)\\n\\ncrash history. See 75 Fed. Reg. 18256, 18258 (April 9, 2010). A carrier is given a\\n\\nweighted score in each category, and then ranked against other carriers. A non-\\n\\npassenger carrier like Flat Creek will receive a “High Risk” designation only if it\\n\\nboth (1) has “not received an onsite investigation in the previous 18 months” and\\n\\n(2) scores at or above the 90th percentile for two consecutive months in two or\\n\\nmore of the MCMIS categories “most closely correlated with crash risk”: unsafe\\n\\ndriving, fatigued driving, vehicle maintenance, and crash history. See 81 Fed. Reg.\\n\\n11875–11876 Table 2 (March 7, 2016).\\n\\n\\n\\n\\n 3\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 4 of 13\\n\\n\\n This “High Risk” designation matters to carriers because FMCSA\\n\\nconcentrates its compliance-review resources on high-risk carriers. A compliance\\n\\nreview is an in-depth “on-site investigation of the carrier’s operations” that\\n\\nexamines the carrier’s compliance with FMCSA regulations. 49 C.F.R. § 385.3;\\n\\nsee generally 49 C.F.R. § 350 et seq. During a compliance review, an investigator\\n\\nwill commonly check driver-qualification files, records of duty status (basically, a\\n\\nmeasure of the number of hours a driver works per 24-hour day), and vehicle-\\n\\nmaintenance data. Within 30 days of the review, FMCSA is required to give the\\n\\ncarrier written notice that it has received one of three safety ratings: Satisfactory,\\n\\nConditional, or Unsatisfactory. 49 C.F.R. §§ 385.3, 385.11(a).\\n\\n Safety ratings become “final” in slightly different ways. A Satisfactory\\n\\nrating, the highest possible, is final and effective on the date of notice. 49 C.F.R.\\n\\n§ 385.11(b). A Conditional or Unsatisfactory rating becomes final after 60 days if\\n\\nit is not upgraded or overturned. Id. § 385.11(c). If a carrier seeks administrative\\n\\nreview of an Unsatisfactory or Conditional rating, FMCSA’s Chief Safety Officer\\n\\nmust issue a written decision, which will constitute final agency action. Id.\\n\\n§ 385.15. Alternatively, a carrier can take corrective action to remedy a reported\\n\\ndefect and then request an upgrade from FMCSA. Id. § 385.11(f). If a carrier\\n\\nreceives a final Unsatisfactory safety rating, it is prohibited from operating. Id.\\n\\n§ 385.13(a).\\n\\n\\n 4\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 5 of 13\\n\\n\\n Naturally, commercial carriers don’t particularly want a “High Risk”\\n\\ndesignation—because it increases their odds of a compliance review, which in turn\\n\\nincreases the odds of suffering an Unsatisfactory safety rating. To address carriers’\\n\\nconcerns about the accuracy of the data that factor into the MCMIS system and\\n\\nthat can prompt a high-risk designation, FMCSA operates DataQs, an online\\n\\nsystem that permits carriers to contest those data. See FMCSA Notice to Amend a\\n\\nSystem of Records, 77 Fed. Reg. 42548-02, 42551 (July 19, 2012).\\n\\n B\\n\\n Flat Creek’s managing member is Charles Patterson Sr.; Charles’ son,\\n\\nCharles Patterson Jr., formed and operates a separate trucking company, Liberty\\n\\nExpress. In July 2016, FMCSA’s Alabama Division conducted a compliance\\n\\nreview of Liberty. Flat Creek alleges that during Liberty’s review, FMCSA agents\\n\\nasked a bunch of questions about Flat Creek. Not long after, Flat Creek says, its\\n\\nregulatory consultant “received surreptitious reports from confidential informant(s)\\n\\nthat agents … planned an unannounced on-site compliance investigation at Flat\\n\\nCreek with the intent to falsely charge Flat Creek with multiple regulatory\\n\\nviolations sufficient to … forc[e] a cessation of Flat Creek’s operations and likely\\n\\nleading to business closure.” Br. of Appellant at 8–9.\\n\\n Flat Creek further asserts that it received “flawed” scores and misleading\\n\\ncrash indicators from the MCMIS data, which FMCSA failed to keep “complete,\\n\\n\\n 5\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 6 of 13\\n\\n\\ntimely, and accurate” as required by 49 U.S.C. § 31106(a)(3)(F). Flat Creek insists\\n\\nthat, contrary to the MCMIS data, the company’s industry performance was above\\n\\naverage. Because of the allegedly false data, Flat Creek contends that it “has been\\n\\nconsistently but illegally targeted and harassed with multiple unwanted\\n\\ninterventions by FMCSA agents.” Compl. at ¶ 47. It points to three specific\\n\\nevents: an allegedly false Notice of Violation on October 6, 2011; another of the\\n\\nsame, on August 10, 2012; and an unfavorable compliance-review report on June\\n\\n15, 2015. And even before those three instances, Flat Creek alleges that it was\\n\\nsubject to “an unusually high number of [compliance review] interventions.” Id. at\\n\\n¶ 48. Most provocatively, Flat Creek further asserts that FMCSA’s adverse\\n\\nregulatory actions were taken in part due to “on[going] prejudice and bias” against\\n\\nPatterson Sr. Compl. at ¶ 58.\\n\\n Flat Creek admits that none of the additional compliance reviews “resulted\\n\\nin a safety rating less than ‘Satisfactory.’”\\n\\n C\\n\\n Flat Creek filed a complaint seeking declaratory and injunctive relief under\\n\\nthe Administrative Procedure Act, 5 U.S.C. § 500 et seq. (2000). FMCSA\\n\\nresponded with a motion to dismiss for lack of subject matter jurisdiction pursuant\\n\\nto Federal Rule of Civil Procedure 12(b)(1). While the motion to dismiss was\\n\\npending, Flat Creek received a letter from FMCSA’s Alabama Division notifying it\\n\\n\\n 6\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 7 of 13\\n\\n\\nof an impending on-site compliance review. Seeking to head off that review, Flat\\n\\nCreek filed an emergency motion for a preliminary injunction. Flat Creek’s\\n\\nmotion was denied, and the review went ahead as scheduled.\\n\\n Following the compliance review, FMCSA initially advised Flat Creek that\\n\\nits safety rating would be downgraded from Satisfactory to Conditional. FMCSA\\n\\nargued to the district court that the case was unripe because the new Conditional\\n\\nrating was not yet final. A month later, however, FMCSA notified the district\\n\\ncourt that the agency had reviewed Flat Creek’s downgraded safety rating sua\\n\\nsponte, removed a violation incorrectly included in the calculation, and restored the\\n\\nrating to Satisfactory. 1\\n\\n The district court granted FMCSA’s Rule 12(b)(1) motion on the ground that\\n\\nthe Hobbs Act, 28 U.S.C. § 2342(3)(A), vested the courts of appeals with exclusive\\n\\n\\n\\n\\n1\\n Because Flat Creek’s safety rating was upgraded during the course of this litigation, its most\\nrecent “Satisfactory” mark is not reflected in its complaint. Flat Creek contends that the district\\ncourt erred when it said that it was engaging in a “facial attack” analysis of subject matter\\njurisdiction—which limits a court to a plaintiff’s allegations—and then proceeded to look\\nbeyond the complaint for proof that Flat Creek ultimately received a “Satisfactory” rating.\\nRanging beyond the complaint, Flat Creek asserts, is permissible only in the case of a “factual\\nattack” on subject matter jurisdiction. See Garcia v. Copenhaver, Bell & Assoc., 104 F.3d 1256,\\n1260–61 (11th Cir. 1997) (citing Lawrence v. Dunbar, 919 F.2d 1525, 1528–29 (11th Cir.\\n1990)). But, where the extra-complaint fact does not implicate the merits of the plaintiff’s case,\\n“the trial court is free to weigh the evidence and satisfy itself as to the existence of its power to\\nhear the case.” Garcia, 104 F.3d at 1261 (quoting Lawrence, 919 F.2d at 1529). Moreover, and\\nin any event—and dispositively here—the fact that Flat Creek’s safety rating is now\\n“Satisfactory” is undisputed. See Br. of Appellant at 21 (“Flat Creek’s … “Satisfactory” safety\\nrating [is] ultimately the result of the March 28, 2017 compliance review.”).\\n\\n 7\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 8 of 13\\n\\n\\njurisdiction to provide Flat Creek the injunctive relief that it had requested. 2 We\\n\\nfind it unnecessary to decide the Hobbs Act question, because we conclude that\\n\\nFlat Creek has failed to establish standing to sue.\\n\\n II\\n\\n We review de novo whether a party has standing. See Perry v. Cable News\\n\\nNetwork, Inc., 854 F.3d 1336, 1339 (11th Cir. 2017). Flat Creek contends that it\\n\\nhas standing to sue because it was injured in two ways: first, its most recent safety\\n\\nrating—which originally came back “Conditional” but was thereafter upgraded to\\n\\n“Satisfactory”—and second, by the ongoing potential for agency bias in the\\n\\nconduct of compliance reviews. We hold that the injuries that Flat Creek alleges\\n\\ndo not establish the requisite standing.\\n\\n The doctrine of standing is “an essential and unchanging part” of the case-\\n\\nor-controversy requirement embodied in Article III of the Constitution. Lujan v.\\n\\nDefenders of Wildlife, 504 U.S. 555, 560 (1992). The “‘irreducible constitutional\\n\\n\\n\\n2\\n Not that Hobbs Act. See 18 U.S.C. § 1951. This one vests exclusive jurisdiction in the courts\\nof appeals\\n\\n to enjoin, set aside, suspend (in whole or in part), or to determine the validity of\\n … all rules, regulations, or final orders of the Secretary of Transportation issued\\n … pursuant to part B or C of subtitle IV, subchapter III of chapter 311, chapter\\n 313, or chapter 315 of title 49.\\n\\n28 U.S.C. § 2342(3)(A) (emphasis added). The question that we excuse ourselves from deciding\\ntoday is whether Flat Creek’s challenges are sufficiently broad that they, in effect, contest the\\nvalidity of an agency rule, regulation, or final order.\\n\\n 8\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 9 of 13\\n\\n\\nminimum’ of standing” requires a plaintiff to show that he “(1) suffered an injury\\n\\nin fact, (2) that is fairly traceable to the challenged conduct of the defendant, and\\n\\n(3) that is likely to be redressed by a favorable judicial decision.” Spokeo, Inc. v.\\n\\nRobins, 136 S. Ct. 1540, 1547 (2016) (quoting Lujan, 504 U.S. at 560–61). “The\\n\\nplaintiff, as the party invoking federal jurisdiction, bears the burden of establishing\\n\\nthese elements.” Id. And because standing doctrine is intended to “confine[] the\\n\\nfederal courts to a properly judicial role,” id., we take seriously the requirement\\n\\nthat a plaintiff clearly demonstrate each requirement. Finally, and importantly\\n\\nhere, the Supreme Court has made clear that “Article III demands that an ‘actual\\n\\ncontroversy’ persist throughout all stages of litigation” and, therefore, that standing\\n\\nrequirements “must be met by persons seeking appellate review, just as [they] must\\n\\nbe met by persons appearing in courts of first instance.” Hollingsworth v. Perry,\\n\\n570 U.S. 693, 705 (2013) (quoting Already, LLC v. Nike, Inc., 568 U.S. 85, 90–91\\n\\n(2013), and Arizonans for Official English v. Arizona, 520 U.S. 43, 64 (1997)).\\n\\n “First and foremost” among the standing doctrine’s requirements is “injury\\n\\nin fact.” Spokeo, 136 S. Ct. at 1547 (quoting Steel Co. v. Citizens for a Better\\n\\nEnv’t, 523 U.S. 83, 103 (1998)). In order to satisfy the injury-in-fact requirement,\\n\\n“a plaintiff must show that he or she suffered ‘an invasion of a legally protected\\n\\ninterest’” that is both (1) “‘concrete and particularized’” and (2) “‘actual or\\n\\nimminent.’” Id. at 1548 (quoting Lujan, 504 U.S. at 560). For an injury to be\\n\\n\\n 9\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 10 of 13\\n\\n\\n“concrete,” “it must actually exist”—that is, it must be “‘real,’ and not ‘abstract.’”\\n\\nId. (quoting Webster’s Third New International Dictionary 472 (1971)). And for\\n\\nan injury to be “particularized,” “it ‘must affect the plaintiff in a personal and\\n\\nindividual way.’” Id. (quoting Lujan, 504 U.S. at 560).\\n\\n Flat Creek’s allegations don’t meet the constitutional standard. To begin\\n\\nwith the most obvious point, Flat Creek has no standing to pursue its once-upon-a-\\n\\ntime pre-enforcement effort to prevent FMCSA from conducting a compliance\\n\\nreview. While Flat Creek’s case was pending in the district court, the compliance\\n\\nreview went forward, and all now agree that Flat Creek received a Satisfactory\\n\\nsafety rating, the highest possible mark. Flat Creek certainly suffered no\\n\\ncognizable injury as a result of a passing rating. See Ezzell Trucking, Inc. v. Fed.\\n\\nMotor Carrier Safety Admin., 309 F.3d 24, 25–26 (D.C. Cir. 2002) (dismissing\\n\\ncarrier’s challenge for lack of standing under similar circumstances).3\\n\\n Separately, and notwithstanding its Satisfactory rating, Flat Creek alleges\\n\\nthat it continues to suffer present injury because it remains subject to an enhanced\\n\\nthreat of future compliance reviews at the hands of (in its view) a biased agency.\\n\\nIn particular, Flat Creek asserts that FMCSA has an “improper on[going] prejudice\\n\\n\\n\\n3\\n Alternatively, one might view this aspect of Flat Creek’s lawsuit as moot, in that it “no longer\\npresent[s] a case or controversy under Article III, § 2 of the Constitution”—as it must “through\\nall stages of federal judicial proceedings, trial and appellate.” Spencer v. Kemna, 523 U.S. 1, 7\\n(1998).\\n\\n 10\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 11 of 13\\n\\n\\nand bias against [Charles] Patterson, Sr. and Flat Creek” and that FMCSA will use\\n\\nfuture compliance reviews “as a pretext for [its] real but illegal purpose of\\n\\nfabricating regulatory violations” and ultimately “terminating Flat Creek’s\\n\\noperations.” Compl. at ¶¶ 58–59. These allegations fail to satisfy the\\n\\nconstitutional test. The injury that Flat Creek asserts—designation as a “High\\n\\nRisk” carrier, subject to an increased likelihood of compliance reviews—is neither\\n\\n“concrete” nor “imminent,” but rather “conjectural” and “hypothetical.” Spokeo,\\n\\n136 S. Ct. at 1548. That is so for two related reasons. First, as a matter of sheer\\n\\ntiming, Flat Creek can’t be designated “High Risk” for a full 18 months after an\\n\\nonsite investigation. See FMCSA Notification of Changes to the Definition of High\\n\\nRisk Motor Carrier, 81 Fed. Reg. 11875, 11875 (March 6, 2016) (“Non-passenger\\n\\ncarriers are considered ‘High Risk’ if they have two or more” safety categories “at\\n\\nor above the 90th percentile for two consecutive months and they have not\\n\\nreceived an onsite investigation in the previous 18 months.” (emphasis added)).\\n\\nAs already noted, during the course of this litigation, in April 2017, the\\n\\nAdministration conducted an onsite investigation of Flat Creek—meaning that Flat\\n\\nCreek wasn’t even eligible for a “High Risk” classification until October 2018.\\n\\nFlat Creek has given us no indication during the pendency of this appeal that any\\n\\nsuch contingency has materialized. Cf. Whitmore v. Arkansas, 495 U.S. 149, 158\\n\\n\\n\\n\\n 11\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 12 of 13\\n\\n\\n(1990) (holding that “[a]llegations of possible future injury” do not confer Article\\n\\nIII standing).\\n\\n Second, even after the 18-month period runs, a carrier can be deemed “High\\n\\nRisk” only if additional conditions obtain. In particular, before a carrier can be\\n\\ndesignated “High Risk,” it must be determined that the carrier scores at or above\\n\\nthe 90th percentile on two of the following metrics: (1) unsafe driving, (2) fatigued\\n\\ndriving, (3) vehicle maintenance, and (4) crash history. See 81 Fed. Reg. 11875,\\n\\n11876 Table 2. Again, so far as we can tell from the record and Flat Creek’s\\n\\narguments to us, there is no indication that any of those conditions has been\\n\\nsatisfied.4\\n\\n Because Flat Creek has shown neither concreteness nor imminence, it has\\n\\nfailed to establish that it has suffered a cognizable injury in fact. Accordingly, it\\n\\nlacks standing to sue.\\n\\n * * *\\n\\n\\n\\n\\n4\\n Note that, just as Flat Creek’s challenge to the April 2017 compliance review could be deemed\\nmoot—in addition to insufficiently injurious for standing purposes—its allegation that it faces\\nfuture compliance reviews at some unspecified time down the road might be thought to be\\nunripe—in addition to impermissibly hypothetical and conjectural for standing purposes. See,\\ne.g., Texas v. United States, 523 U.S. 296, 300 (1998) (holding that a claim that “rests upon\\ncontingent future events that may not occur as anticipated, or indeed may not occur at all” is not\\nripe for adjudication).\\n\\n 12\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 13 of 13\\n\\n\\n Flat Creek has failed to establish the requisite standing to sue under Article\\n\\nIII of the Constitution. We lack jurisdiction to address its claim, and therefore\\n\\nAFFIRM the district court’s dismissal of Flat Creek’s complaint.\\n\\n\\n\\n\\n 13\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4395427/\", \"author_raw\": \"NEWSOM, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"TJOFLAT"},"judge2":{"kind":"string","value":"NEWSOM"},"judge3":{"kind":"string","value":"GILMAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4618174/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: FLAT CREEK TRANSPORTATION, LLC, an Alabama Limited Liability Company, Plaintiff - Appellant, v. FEDERAL MOTOR CARRIER SAFETY ADMINISTRATION, Kenny Price, in His Capacity as Alabama Division Administrator (Federal Motor Carrier Safety Administration), Elaine L. Chao, in Her Capacity as Secretary of the United States Department of Transportation, Defendants - Appellees, Anthony R. Foxx, in His Capacity as Secretary of the United States Department of Transportation, Defendant.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-09\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-14670 Date Filed: 05/09/2019 Page: 1 of 13\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-14670\n ________________________\n\n D.C. Docket No. 1:16-cv-00876-WKW-TFM\n\nFLAT CREEK TRANSPORTATION, LLC,\nan Alabama limited liability company,\n\n Plaintiff - Appellant,\n\n versus\n\nFEDERAL MOTOR CARRIER SAFETY ADMINISTRATION,\nKENNY PRICE,\nin his capacity as Alabama Division Administrator\n(Federal Motor Carrier Safety Administration),\nELAINE L. CHAO,\nin her capacity as Secretary of the United States Department of Transportation,\n\n Defendants - Appellees,\n\nANTHONY R. FOXX,\nin his capacity as Secretary of the United States Department of Transportation,\n\n Defendant.\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 2 of 13\n\n\n ________________________\n\n Appeal from the United States District Court\n for the Middle District of Alabama\n ________________________\n (May 9, 2019)\n\nBefore TJOFLAT, NEWSOM, and GILMAN, * Circuit Judges.\n\nNEWSOM, Circuit Judge:\n\n Flat Creek Transportation sued for declaratory and injunctive relief on the\n\nground that the Federal Motor Carrier Safety Administration had unfairly targeted\n\nit for compliance reviews and used an unsound methodology in doing so. The\n\ndistrict court determined that it lacked subject matter jurisdiction to consider Flat\n\nCreek’s claims. We reach the same destination, albeit by a different route. We\n\nhold that Flat Creek has failed to establish that it suffered an injury in fact\n\nsufficient to confer standing to sue.\n\n I\n\n Flat Creek is a commercial trucking company that transports non-hazardous\n\nmaterials—mainly refrigerated food products. Because it operates in interstate\n\ncommerce, Flat Creek is subject to Department of Transportation regulations. And\n\nbecause its claim in this case arises against the backdrop of that regulatory\n\n\n\n\n*\n Honorable Ronald L. Gilman, United States Circuit Judge for the Sixth Circuit, sitting by\ndesignation.\n\n 2\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 3 of 13\n\n\nframework, we begin with an overview. (Warning: Unavoidable Acronyms\n\nAhead.)\n\n A\n\n Within the Department of Transportation, the Federal Motor Carrier Safety\n\nAdministration (“FMCSA”) investigates carriers and operators to ensure that they\n\nare safe to operate on the nation’s roadways. FMCSA uses a safety-fitness rating\n\nmethodology—the Safety Measurement System (“SMS”)—to quantify carriers’\n\nperformance. For example, the SMS pulls data from the Motor Carrier\n\nManagement Information System (“MCMIS”) related to the following metrics: (1)\n\nunsafe driving, (2) fatigued driving, (3) driver fitness, (4) controlled-substance and\n\nalcohol usage, (5) vehicle maintenance, (6) hazardous-material compliance, and (7)\n\ncrash history. See 75 Fed. Reg. 18256, 18258 (April 9, 2010). A carrier is given a\n\nweighted score in each category, and then ranked against other carriers. A non-\n\npassenger carrier like Flat Creek will receive a “High Risk” designation only if it\n\nboth (1) has “not received an onsite investigation in the previous 18 months” and\n\n(2) scores at or above the 90th percentile for two consecutive months in two or\n\nmore of the MCMIS categories “most closely correlated with crash risk”: unsafe\n\ndriving, fatigued driving, vehicle maintenance, and crash history. See 81 Fed. Reg.\n\n11875–11876 Table 2 (March 7, 2016).\n\n\n\n\n 3\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 4 of 13\n\n\n This “High Risk” designation matters to carriers because FMCSA\n\nconcentrates its compliance-review resources on high-risk carriers. A compliance\n\nreview is an in-depth “on-site investigation of the carrier’s operations” that\n\nexamines the carrier’s compliance with FMCSA regulations. 49 C.F.R. § 385.3;\n\nsee generally 49 C.F.R. § 350 et seq. During a compliance review, an investigator\n\nwill commonly check driver-qualification files, records of duty status (basically, a\n\nmeasure of the number of hours a driver works per 24-hour day), and vehicle-\n\nmaintenance data. Within 30 days of the review, FMCSA is required to give the\n\ncarrier written notice that it has received one of three safety ratings: Satisfactory,\n\nConditional, or Unsatisfactory. 49 C.F.R. §§ 385.3, 385.11(a).\n\n Safety ratings become “final” in slightly different ways. A Satisfactory\n\nrating, the highest possible, is final and effective on the date of notice. 49 C.F.R.\n\n§ 385.11(b). A Conditional or Unsatisfactory rating becomes final after 60 days if\n\nit is not upgraded or overturned. Id. § 385.11(c). If a carrier seeks administrative\n\nreview of an Unsatisfactory or Conditional rating, FMCSA’s Chief Safety Officer\n\nmust issue a written decision, which will constitute final agency action. Id.\n\n§ 385.15. Alternatively, a carrier can take corrective action to remedy a reported\n\ndefect and then request an upgrade from FMCSA. Id. § 385.11(f). If a carrier\n\nreceives a final Unsatisfactory safety rating, it is prohibited from operating. Id.\n\n§ 385.13(a).\n\n\n 4\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 5 of 13\n\n\n Naturally, commercial carriers don’t particularly want a “High Risk”\n\ndesignation—because it increases their odds of a compliance review, which in turn\n\nincreases the odds of suffering an Unsatisfactory safety rating. To address carriers’\n\nconcerns about the accuracy of the data that factor into the MCMIS system and\n\nthat can prompt a high-risk designation, FMCSA operates DataQs, an online\n\nsystem that permits carriers to contest those data. See FMCSA Notice to Amend a\n\nSystem of Records, 77 Fed. Reg. 42548-02, 42551 (July 19, 2012).\n\n B\n\n Flat Creek’s managing member is Charles Patterson Sr.; Charles’ son,\n\nCharles Patterson Jr., formed and operates a separate trucking company, Liberty\n\nExpress. In July 2016, FMCSA’s Alabama Division conducted a compliance\n\nreview of Liberty. Flat Creek alleges that during Liberty’s review, FMCSA agents\n\nasked a bunch of questions about Flat Creek. Not long after, Flat Creek says, its\n\nregulatory consultant “received surreptitious reports from confidential informant(s)\n\nthat agents … planned an unannounced on-site compliance investigation at Flat\n\nCreek with the intent to falsely charge Flat Creek with multiple regulatory\n\nviolations sufficient to … forc[e] a cessation of Flat Creek’s operations and likely\n\nleading to business closure.” Br. of Appellant at 8–9.\n\n Flat Creek further asserts that it received “flawed” scores and misleading\n\ncrash indicators from the MCMIS data, which FMCSA failed to keep “complete,\n\n\n 5\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 6 of 13\n\n\ntimely, and accurate” as required by 49 U.S.C. § 31106(a)(3)(F). Flat Creek insists\n\nthat, contrary to the MCMIS data, the company’s industry performance was above\n\naverage. Because of the allegedly false data, Flat Creek contends that it “has been\n\nconsistently but illegally targeted and harassed with multiple unwanted\n\ninterventions by FMCSA agents.” Compl. at ¶ 47. It points to three specific\n\nevents: an allegedly false Notice of Violation on October 6, 2011; another of the\n\nsame, on August 10, 2012; and an unfavorable compliance-review report on June\n\n15, 2015. And even before those three instances, Flat Creek alleges that it was\n\nsubject to “an unusually high number of [compliance review] interventions.” Id. at\n\n¶ 48. Most provocatively, Flat Creek further asserts that FMCSA’s adverse\n\nregulatory actions were taken in part due to “on[going] prejudice and bias” against\n\nPatterson Sr. Compl. at ¶ 58.\n\n Flat Creek admits that none of the additional compliance reviews “resulted\n\nin a safety rating less than ‘Satisfactory.’”\n\n C\n\n Flat Creek filed a complaint seeking declaratory and injunctive relief under\n\nthe Administrative Procedure Act, 5 U.S.C. § 500 et seq. (2000). FMCSA\n\nresponded with a motion to dismiss for lack of subject matter jurisdiction pursuant\n\nto Federal Rule of Civil Procedure 12(b)(1). While the motion to dismiss was\n\npending, Flat Creek received a letter from FMCSA’s Alabama Division notifying it\n\n\n 6\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 7 of 13\n\n\nof an impending on-site compliance review. Seeking to head off that review, Flat\n\nCreek filed an emergency motion for a preliminary injunction. Flat Creek’s\n\nmotion was denied, and the review went ahead as scheduled.\n\n Following the compliance review, FMCSA initially advised Flat Creek that\n\nits safety rating would be downgraded from Satisfactory to Conditional. FMCSA\n\nargued to the district court that the case was unripe because the new Conditional\n\nrating was not yet final. A month later, however, FMCSA notified the district\n\ncourt that the agency had reviewed Flat Creek’s downgraded safety rating sua\n\nsponte, removed a violation incorrectly included in the calculation, and restored the\n\nrating to Satisfactory. 1\n\n The district court granted FMCSA’s Rule 12(b)(1) motion on the ground that\n\nthe Hobbs Act, 28 U.S.C. § 2342(3)(A), vested the courts of appeals with exclusive\n\n\n\n\n1\n Because Flat Creek’s safety rating was upgraded during the course of this litigation, its most\nrecent “Satisfactory” mark is not reflected in its complaint. Flat Creek contends that the district\ncourt erred when it said that it was engaging in a “facial attack” analysis of subject matter\njurisdiction—which limits a court to a plaintiff’s allegations—and then proceeded to look\nbeyond the complaint for proof that Flat Creek ultimately received a “Satisfactory” rating.\nRanging beyond the complaint, Flat Creek asserts, is permissible only in the case of a “factual\nattack” on subject matter jurisdiction. See Garcia v. Copenhaver, Bell & Assoc., 104 F.3d 1256,\n1260–61 (11th Cir. 1997) (citing Lawrence v. Dunbar, 919 F.2d 1525, 1528–29 (11th Cir.\n1990)). But, where the extra-complaint fact does not implicate the merits of the plaintiff’s case,\n“the trial court is free to weigh the evidence and satisfy itself as to the existence of its power to\nhear the case.” Garcia, 104 F.3d at 1261 (quoting Lawrence, 919 F.2d at 1529). Moreover, and\nin any event—and dispositively here—the fact that Flat Creek’s safety rating is now\n“Satisfactory” is undisputed. See Br. of Appellant at 21 (“Flat Creek’s … “Satisfactory” safety\nrating [is] ultimately the result of the March 28, 2017 compliance review.”).\n\n 7\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 8 of 13\n\n\njurisdiction to provide Flat Creek the injunctive relief that it had requested. 2 We\n\nfind it unnecessary to decide the Hobbs Act question, because we conclude that\n\nFlat Creek has failed to establish standing to sue.\n\n II\n\n We review de novo whether a party has standing. See Perry v. Cable News\n\nNetwork, Inc., 854 F.3d 1336, 1339 (11th Cir. 2017). Flat Creek contends that it\n\nhas standing to sue because it was injured in two ways: first, its most recent safety\n\nrating—which originally came back “Conditional” but was thereafter upgraded to\n\n“Satisfactory”—and second, by the ongoing potential for agency bias in the\n\nconduct of compliance reviews. We hold that the injuries that Flat Creek alleges\n\ndo not establish the requisite standing.\n\n The doctrine of standing is “an essential and unchanging part” of the case-\n\nor-controversy requirement embodied in Article III of the Constitution. Lujan v.\n\nDefenders of Wildlife, 504 U.S. 555, 560 (1992). The “‘irreducible constitutional\n\n\n\n2\n Not that Hobbs Act. See 18 U.S.C. § 1951. This one vests exclusive jurisdiction in the courts\nof appeals\n\n to enjoin, set aside, suspend (in whole or in part), or to determine the validity of\n … all rules, regulations, or final orders of the Secretary of Transportation issued\n … pursuant to part B or C of subtitle IV, subchapter III of chapter 311, chapter\n 313, or chapter 315 of title 49.\n\n28 U.S.C. § 2342(3)(A) (emphasis added). The question that we excuse ourselves from deciding\ntoday is whether Flat Creek’s challenges are sufficiently broad that they, in effect, contest the\nvalidity of an agency rule, regulation, or final order.\n\n 8\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 9 of 13\n\n\nminimum’ of standing” requires a plaintiff to show that he “(1) suffered an injury\n\nin fact, (2) that is fairly traceable to the challenged conduct of the defendant, and\n\n(3) that is likely to be redressed by a favorable judicial decision.” Spokeo, Inc. v.\n\nRobins, 136 S. Ct. 1540, 1547 (2016) (quoting Lujan, 504 U.S. at 560–61). “The\n\nplaintiff, as the party invoking federal jurisdiction, bears the burden of establishing\n\nthese elements.” Id. And because standing doctrine is intended to “confine[] the\n\nfederal courts to a properly judicial role,” id., we take seriously the requirement\n\nthat a plaintiff clearly demonstrate each requirement. Finally, and importantly\n\nhere, the Supreme Court has made clear that “Article III demands that an ‘actual\n\ncontroversy’ persist throughout all stages of litigation” and, therefore, that standing\n\nrequirements “must be met by persons seeking appellate review, just as [they] must\n\nbe met by persons appearing in courts of first instance.” Hollingsworth v. Perry,\n\n570 U.S. 693, 705 (2013) (quoting Already, LLC v. Nike, Inc., 568 U.S. 85, 90–91\n\n(2013), and Arizonans for Official English v. Arizona, 520 U.S. 43, 64 (1997)).\n\n “First and foremost” among the standing doctrine’s requirements is “injury\n\nin fact.” Spokeo, 136 S. Ct. at 1547 (quoting Steel Co. v. Citizens for a Better\n\nEnv’t, 523 U.S. 83, 103 (1998)). In order to satisfy the injury-in-fact requirement,\n\n“a plaintiff must show that he or she suffered ‘an invasion of a legally protected\n\ninterest’” that is both (1) “‘concrete and particularized’” and (2) “‘actual or\n\nimminent.’” Id. at 1548 (quoting Lujan, 504 U.S. at 560). For an injury to be\n\n\n 9\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 10 of 13\n\n\n“concrete,” “it must actually exist”—that is, it must be “‘real,’ and not ‘abstract.’”\n\nId. (quoting Webster’s Third New International Dictionary 472 (1971)). And for\n\nan injury to be “particularized,” “it ‘must affect the plaintiff in a personal and\n\nindividual way.’” Id. (quoting Lujan, 504 U.S. at 560).\n\n Flat Creek’s allegations don’t meet the constitutional standard. To begin\n\nwith the most obvious point, Flat Creek has no standing to pursue its once-upon-a-\n\ntime pre-enforcement effort to prevent FMCSA from conducting a compliance\n\nreview. While Flat Creek’s case was pending in the district court, the compliance\n\nreview went forward, and all now agree that Flat Creek received a Satisfactory\n\nsafety rating, the highest possible mark. Flat Creek certainly suffered no\n\ncognizable injury as a result of a passing rating. See Ezzell Trucking, Inc. v. Fed.\n\nMotor Carrier Safety Admin., 309 F.3d 24, 25–26 (D.C. Cir. 2002) (dismissing\n\ncarrier’s challenge for lack of standing under similar circumstances).3\n\n Separately, and notwithstanding its Satisfactory rating, Flat Creek alleges\n\nthat it continues to suffer present injury because it remains subject to an enhanced\n\nthreat of future compliance reviews at the hands of (in its view) a biased agency.\n\nIn particular, Flat Creek asserts that FMCSA has an “improper on[going] prejudice\n\n\n\n3\n Alternatively, one might view this aspect of Flat Creek’s lawsuit as moot, in that it “no longer\npresent[s] a case or controversy under Article III, § 2 of the Constitution”—as it must “through\nall stages of federal judicial proceedings, trial and appellate.” Spencer v. Kemna, 523 U.S. 1, 7\n(1998).\n\n 10\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 11 of 13\n\n\nand bias against [Charles] Patterson, Sr. and Flat Creek” and that FMCSA will use\n\nfuture compliance reviews “as a pretext for [its] real but illegal purpose of\n\nfabricating regulatory violations” and ultimately “terminating Flat Creek’s\n\noperations.” Compl. at ¶¶ 58–59. These allegations fail to satisfy the\n\nconstitutional test. The injury that Flat Creek asserts—designation as a “High\n\nRisk” carrier, subject to an increased likelihood of compliance reviews—is neither\n\n“concrete” nor “imminent,” but rather “conjectural” and “hypothetical.” Spokeo,\n\n136 S. Ct. at 1548. That is so for two related reasons. First, as a matter of sheer\n\ntiming, Flat Creek can’t be designated “High Risk” for a full 18 months after an\n\nonsite investigation. See FMCSA Notification of Changes to the Definition of High\n\nRisk Motor Carrier, 81 Fed. Reg. 11875, 11875 (March 6, 2016) (“Non-passenger\n\ncarriers are considered ‘High Risk’ if they have two or more” safety categories “at\n\nor above the 90th percentile for two consecutive months and they have not\n\nreceived an onsite investigation in the previous 18 months.” (emphasis added)).\n\nAs already noted, during the course of this litigation, in April 2017, the\n\nAdministration conducted an onsite investigation of Flat Creek—meaning that Flat\n\nCreek wasn’t even eligible for a “High Risk” classification until October 2018.\n\nFlat Creek has given us no indication during the pendency of this appeal that any\n\nsuch contingency has materialized. Cf. Whitmore v. Arkansas, 495 U.S. 149, 158\n\n\n\n\n 11\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 12 of 13\n\n\n(1990) (holding that “[a]llegations of possible future injury” do not confer Article\n\nIII standing).\n\n Second, even after the 18-month period runs, a carrier can be deemed “High\n\nRisk” only if additional conditions obtain. In particular, before a carrier can be\n\ndesignated “High Risk,” it must be determined that the carrier scores at or above\n\nthe 90th percentile on two of the following metrics: (1) unsafe driving, (2) fatigued\n\ndriving, (3) vehicle maintenance, and (4) crash history. See 81 Fed. Reg. 11875,\n\n11876 Table 2. Again, so far as we can tell from the record and Flat Creek’s\n\narguments to us, there is no indication that any of those conditions has been\n\nsatisfied.4\n\n Because Flat Creek has shown neither concreteness nor imminence, it has\n\nfailed to establish that it has suffered a cognizable injury in fact. Accordingly, it\n\nlacks standing to sue.\n\n * * *\n\n\n\n\n4\n Note that, just as Flat Creek’s challenge to the April 2017 compliance review could be deemed\nmoot—in addition to insufficiently injurious for standing purposes—its allegation that it faces\nfuture compliance reviews at some unspecified time down the road might be thought to be\nunripe—in addition to impermissibly hypothetical and conjectural for standing purposes. See,\ne.g., Texas v. United States, 523 U.S. 296, 300 (1998) (holding that a claim that “rests upon\ncontingent future events that may not occur as anticipated, or indeed may not occur at all” is not\nripe for adjudication).\n\n 12\n\f Case: 17-14670 Date Filed: 05/09/2019 Page: 13 of 13\n\n\n Flat Creek has failed to establish the requisite standing to sue under Article\n\nIII of the Constitution. We lack jurisdiction to address its claim, and therefore\n\nAFFIRM the district court’s dismissal of Flat Creek’s complaint.\n\n\n\n\n 13\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: FLAT CREEK TRANSPORTATION, LLC, an Alabama Limited Liability Company, Plaintiff - Appellant, v. FEDERAL MOTOR CARRIER SAFETY ADMINISTRATION, Kenny Price, in His Capacity as Alabama Division Administrator (Federal Motor Carrier Safety Administration), Elaine L. Chao, in Her Capacity as Secretary of the United States Department of Transportation, Defendants - Appellees, Anthony R. Foxx, in His Capacity as Secretary of the United States Department of Transportation, Defendant.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-09\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-14670 Date Filed: 05/09/2019 Page: 1 of 13\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-14670\\n ________________________\\n\\n D.C. Docket No. 1:16-cv-00876-WKW-TFM\\n\\nFLAT CREEK TRANSPORTATION, LLC,\\nan Alabama limited liability company,\\n\\n Plaintiff - Appellant,\\n\\n versus\\n\\nFEDERAL MOTOR CARRIER SAFETY ADMINISTRATION,\\nKENNY PRICE,\\nin his capacity as Alabama Division Administrator\\n(Federal Motor Carrier Safety Administration),\\nELAINE L. CHAO,\\nin her capacity as Secretary of the United States Department of Transportation,\\n\\n Defendants - Appellees,\\n\\nANTHONY R. FOXX,\\nin his capacity as Secretary of the United States Department of Transportation,\\n\\n Defendant.\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 2 of 13\\n\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Alabama\\n ________________________\\n (May 9, 2019)\\n\\nBefore TJOFLAT, NEWSOM, and GILMAN, * Circuit Judges.\\n\\nNEWSOM, Circuit Judge:\\n\\n Flat Creek Transportation sued for declaratory and injunctive relief on the\\n\\nground that the Federal Motor Carrier Safety Administration had unfairly targeted\\n\\nit for compliance reviews and used an unsound methodology in doing so. The\\n\\ndistrict court determined that it lacked subject matter jurisdiction to consider Flat\\n\\nCreek’s claims. We reach the same destination, albeit by a different route. We\\n\\nhold that Flat Creek has failed to establish that it suffered an injury in fact\\n\\nsufficient to confer standing to sue.\\n\\n I\\n\\n Flat Creek is a commercial trucking company that transports non-hazardous\\n\\nmaterials—mainly refrigerated food products. Because it operates in interstate\\n\\ncommerce, Flat Creek is subject to Department of Transportation regulations. And\\n\\nbecause its claim in this case arises against the backdrop of that regulatory\\n\\n\\n\\n\\n*\\n Honorable Ronald L. Gilman, United States Circuit Judge for the Sixth Circuit, sitting by\\ndesignation.\\n\\n 2\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 3 of 13\\n\\n\\nframework, we begin with an overview. (Warning: Unavoidable Acronyms\\n\\nAhead.)\\n\\n A\\n\\n Within the Department of Transportation, the Federal Motor Carrier Safety\\n\\nAdministration (“FMCSA”) investigates carriers and operators to ensure that they\\n\\nare safe to operate on the nation’s roadways. FMCSA uses a safety-fitness rating\\n\\nmethodology—the Safety Measurement System (“SMS”)—to quantify carriers’\\n\\nperformance. For example, the SMS pulls data from the Motor Carrier\\n\\nManagement Information System (“MCMIS”) related to the following metrics: (1)\\n\\nunsafe driving, (2) fatigued driving, (3) driver fitness, (4) controlled-substance and\\n\\nalcohol usage, (5) vehicle maintenance, (6) hazardous-material compliance, and (7)\\n\\ncrash history. See 75 Fed. Reg. 18256, 18258 (April 9, 2010). A carrier is given a\\n\\nweighted score in each category, and then ranked against other carriers. A non-\\n\\npassenger carrier like Flat Creek will receive a “High Risk” designation only if it\\n\\nboth (1) has “not received an onsite investigation in the previous 18 months” and\\n\\n(2) scores at or above the 90th percentile for two consecutive months in two or\\n\\nmore of the MCMIS categories “most closely correlated with crash risk”: unsafe\\n\\ndriving, fatigued driving, vehicle maintenance, and crash history. See 81 Fed. Reg.\\n\\n11875–11876 Table 2 (March 7, 2016).\\n\\n\\n\\n\\n 3\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 4 of 13\\n\\n\\n This “High Risk” designation matters to carriers because FMCSA\\n\\nconcentrates its compliance-review resources on high-risk carriers. A compliance\\n\\nreview is an in-depth “on-site investigation of the carrier’s operations” that\\n\\nexamines the carrier’s compliance with FMCSA regulations. 49 C.F.R. § 385.3;\\n\\nsee generally 49 C.F.R. § 350 et seq. During a compliance review, an investigator\\n\\nwill commonly check driver-qualification files, records of duty status (basically, a\\n\\nmeasure of the number of hours a driver works per 24-hour day), and vehicle-\\n\\nmaintenance data. Within 30 days of the review, FMCSA is required to give the\\n\\ncarrier written notice that it has received one of three safety ratings: Satisfactory,\\n\\nConditional, or Unsatisfactory. 49 C.F.R. §§ 385.3, 385.11(a).\\n\\n Safety ratings become “final” in slightly different ways. A Satisfactory\\n\\nrating, the highest possible, is final and effective on the date of notice. 49 C.F.R.\\n\\n§ 385.11(b). A Conditional or Unsatisfactory rating becomes final after 60 days if\\n\\nit is not upgraded or overturned. Id. § 385.11(c). If a carrier seeks administrative\\n\\nreview of an Unsatisfactory or Conditional rating, FMCSA’s Chief Safety Officer\\n\\nmust issue a written decision, which will constitute final agency action. Id.\\n\\n§ 385.15. Alternatively, a carrier can take corrective action to remedy a reported\\n\\ndefect and then request an upgrade from FMCSA. Id. § 385.11(f). If a carrier\\n\\nreceives a final Unsatisfactory safety rating, it is prohibited from operating. Id.\\n\\n§ 385.13(a).\\n\\n\\n 4\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 5 of 13\\n\\n\\n Naturally, commercial carriers don’t particularly want a “High Risk”\\n\\ndesignation—because it increases their odds of a compliance review, which in turn\\n\\nincreases the odds of suffering an Unsatisfactory safety rating. To address carriers’\\n\\nconcerns about the accuracy of the data that factor into the MCMIS system and\\n\\nthat can prompt a high-risk designation, FMCSA operates DataQs, an online\\n\\nsystem that permits carriers to contest those data. See FMCSA Notice to Amend a\\n\\nSystem of Records, 77 Fed. Reg. 42548-02, 42551 (July 19, 2012).\\n\\n B\\n\\n Flat Creek’s managing member is Charles Patterson Sr.; Charles’ son,\\n\\nCharles Patterson Jr., formed and operates a separate trucking company, Liberty\\n\\nExpress. In July 2016, FMCSA’s Alabama Division conducted a compliance\\n\\nreview of Liberty. Flat Creek alleges that during Liberty’s review, FMCSA agents\\n\\nasked a bunch of questions about Flat Creek. Not long after, Flat Creek says, its\\n\\nregulatory consultant “received surreptitious reports from confidential informant(s)\\n\\nthat agents … planned an unannounced on-site compliance investigation at Flat\\n\\nCreek with the intent to falsely charge Flat Creek with multiple regulatory\\n\\nviolations sufficient to … forc[e] a cessation of Flat Creek’s operations and likely\\n\\nleading to business closure.” Br. of Appellant at 8–9.\\n\\n Flat Creek further asserts that it received “flawed” scores and misleading\\n\\ncrash indicators from the MCMIS data, which FMCSA failed to keep “complete,\\n\\n\\n 5\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 6 of 13\\n\\n\\ntimely, and accurate” as required by 49 U.S.C. § 31106(a)(3)(F). Flat Creek insists\\n\\nthat, contrary to the MCMIS data, the company’s industry performance was above\\n\\naverage. Because of the allegedly false data, Flat Creek contends that it “has been\\n\\nconsistently but illegally targeted and harassed with multiple unwanted\\n\\ninterventions by FMCSA agents.” Compl. at ¶ 47. It points to three specific\\n\\nevents: an allegedly false Notice of Violation on October 6, 2011; another of the\\n\\nsame, on August 10, 2012; and an unfavorable compliance-review report on June\\n\\n15, 2015. And even before those three instances, Flat Creek alleges that it was\\n\\nsubject to “an unusually high number of [compliance review] interventions.” Id. at\\n\\n¶ 48. Most provocatively, Flat Creek further asserts that FMCSA’s adverse\\n\\nregulatory actions were taken in part due to “on[going] prejudice and bias” against\\n\\nPatterson Sr. Compl. at ¶ 58.\\n\\n Flat Creek admits that none of the additional compliance reviews “resulted\\n\\nin a safety rating less than ‘Satisfactory.’”\\n\\n C\\n\\n Flat Creek filed a complaint seeking declaratory and injunctive relief under\\n\\nthe Administrative Procedure Act, 5 U.S.C. § 500 et seq. (2000). FMCSA\\n\\nresponded with a motion to dismiss for lack of subject matter jurisdiction pursuant\\n\\nto Federal Rule of Civil Procedure 12(b)(1). While the motion to dismiss was\\n\\npending, Flat Creek received a letter from FMCSA’s Alabama Division notifying it\\n\\n\\n 6\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 7 of 13\\n\\n\\nof an impending on-site compliance review. Seeking to head off that review, Flat\\n\\nCreek filed an emergency motion for a preliminary injunction. Flat Creek’s\\n\\nmotion was denied, and the review went ahead as scheduled.\\n\\n Following the compliance review, FMCSA initially advised Flat Creek that\\n\\nits safety rating would be downgraded from Satisfactory to Conditional. FMCSA\\n\\nargued to the district court that the case was unripe because the new Conditional\\n\\nrating was not yet final. A month later, however, FMCSA notified the district\\n\\ncourt that the agency had reviewed Flat Creek’s downgraded safety rating sua\\n\\nsponte, removed a violation incorrectly included in the calculation, and restored the\\n\\nrating to Satisfactory. 1\\n\\n The district court granted FMCSA’s Rule 12(b)(1) motion on the ground that\\n\\nthe Hobbs Act, 28 U.S.C. § 2342(3)(A), vested the courts of appeals with exclusive\\n\\n\\n\\n\\n1\\n Because Flat Creek’s safety rating was upgraded during the course of this litigation, its most\\nrecent “Satisfactory” mark is not reflected in its complaint. Flat Creek contends that the district\\ncourt erred when it said that it was engaging in a “facial attack” analysis of subject matter\\njurisdiction—which limits a court to a plaintiff’s allegations—and then proceeded to look\\nbeyond the complaint for proof that Flat Creek ultimately received a “Satisfactory” rating.\\nRanging beyond the complaint, Flat Creek asserts, is permissible only in the case of a “factual\\nattack” on subject matter jurisdiction. See Garcia v. Copenhaver, Bell & Assoc., 104 F.3d 1256,\\n1260–61 (11th Cir. 1997) (citing Lawrence v. Dunbar, 919 F.2d 1525, 1528–29 (11th Cir.\\n1990)). But, where the extra-complaint fact does not implicate the merits of the plaintiff’s case,\\n“the trial court is free to weigh the evidence and satisfy itself as to the existence of its power to\\nhear the case.” Garcia, 104 F.3d at 1261 (quoting Lawrence, 919 F.2d at 1529). Moreover, and\\nin any event—and dispositively here—the fact that Flat Creek’s safety rating is now\\n“Satisfactory” is undisputed. See Br. of Appellant at 21 (“Flat Creek’s … “Satisfactory” safety\\nrating [is] ultimately the result of the March 28, 2017 compliance review.”).\\n\\n 7\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 8 of 13\\n\\n\\njurisdiction to provide Flat Creek the injunctive relief that it had requested. 2 We\\n\\nfind it unnecessary to decide the Hobbs Act question, because we conclude that\\n\\nFlat Creek has failed to establish standing to sue.\\n\\n II\\n\\n We review de novo whether a party has standing. See Perry v. Cable News\\n\\nNetwork, Inc., 854 F.3d 1336, 1339 (11th Cir. 2017). Flat Creek contends that it\\n\\nhas standing to sue because it was injured in two ways: first, its most recent safety\\n\\nrating—which originally came back “Conditional” but was thereafter upgraded to\\n\\n“Satisfactory”—and second, by the ongoing potential for agency bias in the\\n\\nconduct of compliance reviews. We hold that the injuries that Flat Creek alleges\\n\\ndo not establish the requisite standing.\\n\\n The doctrine of standing is “an essential and unchanging part” of the case-\\n\\nor-controversy requirement embodied in Article III of the Constitution. Lujan v.\\n\\nDefenders of Wildlife, 504 U.S. 555, 560 (1992). The “‘irreducible constitutional\\n\\n\\n\\n2\\n Not that Hobbs Act. See 18 U.S.C. § 1951. This one vests exclusive jurisdiction in the courts\\nof appeals\\n\\n to enjoin, set aside, suspend (in whole or in part), or to determine the validity of\\n … all rules, regulations, or final orders of the Secretary of Transportation issued\\n … pursuant to part B or C of subtitle IV, subchapter III of chapter 311, chapter\\n 313, or chapter 315 of title 49.\\n\\n28 U.S.C. § 2342(3)(A) (emphasis added). The question that we excuse ourselves from deciding\\ntoday is whether Flat Creek’s challenges are sufficiently broad that they, in effect, contest the\\nvalidity of an agency rule, regulation, or final order.\\n\\n 8\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 9 of 13\\n\\n\\nminimum’ of standing” requires a plaintiff to show that he “(1) suffered an injury\\n\\nin fact, (2) that is fairly traceable to the challenged conduct of the defendant, and\\n\\n(3) that is likely to be redressed by a favorable judicial decision.” Spokeo, Inc. v.\\n\\nRobins, 136 S. Ct. 1540, 1547 (2016) (quoting Lujan, 504 U.S. at 560–61). “The\\n\\nplaintiff, as the party invoking federal jurisdiction, bears the burden of establishing\\n\\nthese elements.” Id. And because standing doctrine is intended to “confine[] the\\n\\nfederal courts to a properly judicial role,” id., we take seriously the requirement\\n\\nthat a plaintiff clearly demonstrate each requirement. Finally, and importantly\\n\\nhere, the Supreme Court has made clear that “Article III demands that an ‘actual\\n\\ncontroversy’ persist throughout all stages of litigation” and, therefore, that standing\\n\\nrequirements “must be met by persons seeking appellate review, just as [they] must\\n\\nbe met by persons appearing in courts of first instance.” Hollingsworth v. Perry,\\n\\n570 U.S. 693, 705 (2013) (quoting Already, LLC v. Nike, Inc., 568 U.S. 85, 90–91\\n\\n(2013), and Arizonans for Official English v. Arizona, 520 U.S. 43, 64 (1997)).\\n\\n “First and foremost” among the standing doctrine’s requirements is “injury\\n\\nin fact.” Spokeo, 136 S. Ct. at 1547 (quoting Steel Co. v. Citizens for a Better\\n\\nEnv’t, 523 U.S. 83, 103 (1998)). In order to satisfy the injury-in-fact requirement,\\n\\n“a plaintiff must show that he or she suffered ‘an invasion of a legally protected\\n\\ninterest’” that is both (1) “‘concrete and particularized’” and (2) “‘actual or\\n\\nimminent.’” Id. at 1548 (quoting Lujan, 504 U.S. at 560). For an injury to be\\n\\n\\n 9\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 10 of 13\\n\\n\\n“concrete,” “it must actually exist”—that is, it must be “‘real,’ and not ‘abstract.’”\\n\\nId. (quoting Webster’s Third New International Dictionary 472 (1971)). And for\\n\\nan injury to be “particularized,” “it ‘must affect the plaintiff in a personal and\\n\\nindividual way.’” Id. (quoting Lujan, 504 U.S. at 560).\\n\\n Flat Creek’s allegations don’t meet the constitutional standard. To begin\\n\\nwith the most obvious point, Flat Creek has no standing to pursue its once-upon-a-\\n\\ntime pre-enforcement effort to prevent FMCSA from conducting a compliance\\n\\nreview. While Flat Creek’s case was pending in the district court, the compliance\\n\\nreview went forward, and all now agree that Flat Creek received a Satisfactory\\n\\nsafety rating, the highest possible mark. Flat Creek certainly suffered no\\n\\ncognizable injury as a result of a passing rating. See Ezzell Trucking, Inc. v. Fed.\\n\\nMotor Carrier Safety Admin., 309 F.3d 24, 25–26 (D.C. Cir. 2002) (dismissing\\n\\ncarrier’s challenge for lack of standing under similar circumstances).3\\n\\n Separately, and notwithstanding its Satisfactory rating, Flat Creek alleges\\n\\nthat it continues to suffer present injury because it remains subject to an enhanced\\n\\nthreat of future compliance reviews at the hands of (in its view) a biased agency.\\n\\nIn particular, Flat Creek asserts that FMCSA has an “improper on[going] prejudice\\n\\n\\n\\n3\\n Alternatively, one might view this aspect of Flat Creek’s lawsuit as moot, in that it “no longer\\npresent[s] a case or controversy under Article III, § 2 of the Constitution”—as it must “through\\nall stages of federal judicial proceedings, trial and appellate.” Spencer v. Kemna, 523 U.S. 1, 7\\n(1998).\\n\\n 10\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 11 of 13\\n\\n\\nand bias against [Charles] Patterson, Sr. and Flat Creek” and that FMCSA will use\\n\\nfuture compliance reviews “as a pretext for [its] real but illegal purpose of\\n\\nfabricating regulatory violations” and ultimately “terminating Flat Creek’s\\n\\noperations.” Compl. at ¶¶ 58–59. These allegations fail to satisfy the\\n\\nconstitutional test. The injury that Flat Creek asserts—designation as a “High\\n\\nRisk” carrier, subject to an increased likelihood of compliance reviews—is neither\\n\\n“concrete” nor “imminent,” but rather “conjectural” and “hypothetical.” Spokeo,\\n\\n136 S. Ct. at 1548. That is so for two related reasons. First, as a matter of sheer\\n\\ntiming, Flat Creek can’t be designated “High Risk” for a full 18 months after an\\n\\nonsite investigation. See FMCSA Notification of Changes to the Definition of High\\n\\nRisk Motor Carrier, 81 Fed. Reg. 11875, 11875 (March 6, 2016) (“Non-passenger\\n\\ncarriers are considered ‘High Risk’ if they have two or more” safety categories “at\\n\\nor above the 90th percentile for two consecutive months and they have not\\n\\nreceived an onsite investigation in the previous 18 months.” (emphasis added)).\\n\\nAs already noted, during the course of this litigation, in April 2017, the\\n\\nAdministration conducted an onsite investigation of Flat Creek—meaning that Flat\\n\\nCreek wasn’t even eligible for a “High Risk” classification until October 2018.\\n\\nFlat Creek has given us no indication during the pendency of this appeal that any\\n\\nsuch contingency has materialized. Cf. Whitmore v. Arkansas, 495 U.S. 149, 158\\n\\n\\n\\n\\n 11\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 12 of 13\\n\\n\\n(1990) (holding that “[a]llegations of possible future injury” do not confer Article\\n\\nIII standing).\\n\\n Second, even after the 18-month period runs, a carrier can be deemed “High\\n\\nRisk” only if additional conditions obtain. In particular, before a carrier can be\\n\\ndesignated “High Risk,” it must be determined that the carrier scores at or above\\n\\nthe 90th percentile on two of the following metrics: (1) unsafe driving, (2) fatigued\\n\\ndriving, (3) vehicle maintenance, and (4) crash history. See 81 Fed. Reg. 11875,\\n\\n11876 Table 2. Again, so far as we can tell from the record and Flat Creek’s\\n\\narguments to us, there is no indication that any of those conditions has been\\n\\nsatisfied.4\\n\\n Because Flat Creek has shown neither concreteness nor imminence, it has\\n\\nfailed to establish that it has suffered a cognizable injury in fact. Accordingly, it\\n\\nlacks standing to sue.\\n\\n * * *\\n\\n\\n\\n\\n4\\n Note that, just as Flat Creek’s challenge to the April 2017 compliance review could be deemed\\nmoot—in addition to insufficiently injurious for standing purposes—its allegation that it faces\\nfuture compliance reviews at some unspecified time down the road might be thought to be\\nunripe—in addition to impermissibly hypothetical and conjectural for standing purposes. See,\\ne.g., Texas v. United States, 523 U.S. 296, 300 (1998) (holding that a claim that “rests upon\\ncontingent future events that may not occur as anticipated, or indeed may not occur at all” is not\\nripe for adjudication).\\n\\n 12\\n\\f Case: 17-14670 Date Filed: 05/09/2019 Page: 13 of 13\\n\\n\\n Flat Creek has failed to establish the requisite standing to sue under Article\\n\\nIII of the Constitution. We lack jurisdiction to address its claim, and therefore\\n\\nAFFIRM the district court’s dismissal of Flat Creek’s complaint.\\n\\n\\n\\n\\n 13\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2278,"cells":{"id":{"kind":"number","value":8443998,"string":"8,443,998"},"name":{"kind":"string","value":"Anthony PIAZZA, as personal representative of the Estate of Ricky DeAngelo Hinkle, Nyreekis Jarnell Hunter, as personal representative of the Estate of Ricky DeAngelo Hinkle v. JEFFERSON COUNTY, ALABAMA, an Alabama county, individually, Mike Hale, Ron Eddings, Habimana Dukuzumuremyi, each individually"},"name_abbreviation":{"kind":"string","value":"Piazza v. Jefferson Cnty."},"decision_date":{"kind":"string","value":"2019-05-09"},"docket_number":{"kind":"string","value":"No. 18-10487"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Gilman, Newsom, Tjoflat\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415432/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"GILMAN"},"judge2":{"kind":"string","value":"NEWSOM"},"judge3":{"kind":"string","value":"TJOFLAT"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8443998/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Anthony PIAZZA, as personal representative of the Estate of Ricky DeAngelo Hinkle, Nyreekis Jarnell Hunter, as personal representative of the Estate of Ricky DeAngelo Hinkle v. JEFFERSON COUNTY, ALABAMA, an Alabama county, individually, Mike Hale, Ron Eddings, Habimana Dukuzumuremyi, each individually\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-09\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Anthony PIAZZA, as personal representative of the Estate of Ricky DeAngelo Hinkle, Nyreekis Jarnell Hunter, as personal representative of the Estate of Ricky DeAngelo Hinkle v. JEFFERSON COUNTY, ALABAMA, an Alabama county, individually, Mike Hale, Ron Eddings, Habimana Dukuzumuremyi, each individually\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-09\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2279,"cells":{"id":{"kind":"number","value":4618970,"string":"4,618,970"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellee, v. Isabel Yero GRIMON, Defendant-Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Isabel Yero Grimon"},"decision_date":{"kind":"string","value":"2019-05-13"},"docket_number":{"kind":"string","value":"17-15011"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Marcus, Grant, Hull\", \"parties\": \"\", \"opinions\": [{\"author\": \"HULL, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-15011 Date Filed: 05/13/2019 Page: 1 of 15\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15011\\n ________________________\\n\\n D.C. Docket No. 1:17-cr-20221-JEM-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\n versus\\n\\nISABEL YERO GRIMON,\\n\\n Defendant-Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 13, 2019)\\n\\nBefore MARCUS, GRANT and HULL, Circuit Judges.\\n\\nHULL, Circuit Judge:\\n\\n After pleading guilty, Isabel Yero Grimon appeals her convictions for\\n\\npossessing 15 or more unauthorized access devices and aggravated identity theft.\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 2 of 15\\n\\n\\nDefendant Grimon argues that the factual proffer supporting her guilty plea was\\n\\ninsufficient to establish that the unauthorized access devices she possessed affected\\n\\ninterstate commerce and, therefore, the district court lacked subject matter\\n\\njurisdiction. The question presented is whether the district court has subject matter\\n\\njurisdiction over a criminal case to accept a guilty plea where: (1) the indictment\\n\\ncharges a violation of a valid federal criminal statute and sets forth the interstate\\n\\ncommerce element of the crime; (2) the factual proffer for the guilty plea states the\\n\\ngovernment at trial would prove that the defendant’s conduct affected interstate\\n\\ncommerce; but (3) the factual proffer does not contain any underlying facts\\n\\nexplaining how the interstate commerce nexus was satisfied.\\n\\n After review, and with the benefit of oral argument, we conclude that the\\n\\ninterstate commence element in § 1029(a)(3) is not “jurisdictional” in the sense of\\n\\nbearing on whether the district court has subject matter jurisdiction to adjudicate a\\n\\ncase, and thus the government’s alleged failure to prove sufficiently the interstate\\n\\ncommerce nexus does not deprive the district court of its subject matter jurisdiction\\n\\nover Grimon’s criminal case. Thus, we affirm Grimon’s convictions.\\n\\n I. BACKGROUND\\n\\nA. Arrest\\n\\n On January 18, 2017, officers conducted a traffic stop of Grimon’s vehicle\\n\\nafter observing her swerving between lanes and determining, through a records\\n\\n\\n 2\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 3 of 15\\n\\n\\ncheck, that there was an active warrant for her arrest out of Texas. Grimon was\\n\\narrested on the active warrant, and officers conducted a search incident to that\\n\\narrest.\\n\\n During the search, officers found 19 blank credit cards in Grimon’s vehicle,\\n\\n16 of which were encoded with account numbers issued to 10 other persons.\\n\\nOfficers also recovered a thumb drive from Grimon, which contained 134 credit\\n\\ncard account numbers issued to other persons. Grimon admitted that (1) she knew\\n\\nthe blank cards were re-encoded with credit card account numbers issued to other\\n\\npersons, (2) the credit card numbers on the thumb drive did not belong to her, and\\n\\n(3) she was not authorized to possess those account numbers by their owners.\\n\\nB. Indictment and Plea\\n\\n In March 2017, a federal grand jury charged Grimon with (1) one count of\\n\\npossession of 15 or more unauthorized access devices, in violation of 18 U.S.C.\\n\\n§ 1029(a)(3) (Count 1), and (2) three counts of aggravated identity theft, in\\n\\nviolation of 18 U.S.C. § 1028A(a)(1) (Counts 2-4). Count 1 specifically charged\\n\\nthat Grimon knowingly, and with intent to defraud, possessed 15 or more\\n\\nunauthorized access devices and that “said conduct affect[ed] interstate and foreign\\n\\ncommerce.”\\n\\n In July 2017, pursuant to a written plea agreement, Grimon pled guilty to\\n\\nCounts 1 and 2 of the indictment, and the government agreed to dismiss Counts 3\\n\\n\\n 3\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 4 of 15\\n\\n\\nand 4. In connection with her plea agreement, Grimon executed a factual proffer\\n\\ndetailing the offense conduct described above. As to all of the elements of Count\\n\\n1, Grimon’s factual proffer stated that, had the case gone to trial, the government\\n\\nwould have proved beyond a reasonable doubt that Grimon “did knowingly, and\\n\\nwith intent to defraud, possess fifteen (15) or more devices which are counterfeit\\n\\nand unauthorized access devices, said conduct affecting interstate and foreign\\n\\ncommerce.”\\n\\n At the change of plea hearing, Grimon confirmed, through an interpreter,\\n\\nthat she received a copy of the indictment and had an opportunity to fully discuss\\n\\nthe charges with her attorney. The government summarized the charges in Counts\\n\\n1 and 2. In doing so, the government explicitly stated with respect to Count 1 that\\n\\none of the elements of the offense “is that the Defendant’s conduct in some way\\n\\naffected commerce between one state and other states or between a state of the\\n\\nUnited States and a foreign country.” Grimon then confirmed that she understood\\n\\nthe charges to which she was pleading guilty. The government also read the\\n\\nfactual proffer into the record. That proffer included a stipulation that the\\n\\ngovernment would have proven at trial that Grimon “did knowingly and with intent\\n\\nto defraud, possess 15 or more devices which are counterfeit and unauthorized\\n\\naccess devices, said conduct affecting interstate and foreign commerce.”\\n\\n\\n\\n\\n 4\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 5 of 15\\n\\n\\n After this recitation, through an interpreter, Grimon agreed that the\\n\\ngovernment’s recitation of the facts was correct and that it could prove those facts\\n\\nat trial. Grimon also confirmed that she had read and discussed the factual proffer\\n\\nwith her attorney before signing it. Grimon’s attorney stated that he was bilingual\\n\\nand was able to translate the factual proffer into Spanish for Grimon, that he\\n\\nexplained the factual proffer to her, and that he was confident she understood its\\n\\ncontents.\\n\\n Grimon pled guilty to Counts 1 and 2, and the district court accepted her\\n\\nplea. The district court found that Grimon was “fully competent and capable of\\n\\nentering an informed plea” and that “her pleas of guilty [were] knowing and\\n\\nvoluntary pleas supported by an independent basis in fact containing each of the\\n\\nessential elements of the offenses.”\\n\\nC. Sentence\\n\\n Following a sentencing hearing, the district court sentenced Grimon to 12\\n\\nmonths’ imprisonment on her § 1029(a)(3) access device conviction in Count 1,\\n\\nfollowed by a mandatory consecutive term of 24 months’ imprisonment on her\\n\\n§ 1028A(a)(1) aggravated identity theft conviction in Count 2. Grimon’s total\\n\\nsentence is thus 36 months’ imprisonment. At that time, the district court\\n\\ndismissed Counts 3 and 4 of the indictment.\\n\\n\\n\\n\\n 5\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 6 of 15\\n\\n\\n Grimon now appeals her convictions.1\\n\\n II. DISCUSSION\\n\\n On appeal, Grimon argues that the district court lacked subject matter\\n\\njurisdiction over her offenses because the factual proffer (1) merely stipulated to\\n\\nthe interstate commerce element of her access device offense and (2) did not\\n\\ncontain any underlying facts showing that her possession of counterfeit credit cards\\n\\nand account numbers affected interstate commerce. Grimon stresses that the credit\\n\\ncards were never used.\\n\\n The government responds that its indictment charged Grimon with violating\\n\\na valid federal statute, alleged an offense against the United States and, therefore,\\n\\ninvoked the district court’s subject matter jurisdiction. The government argues that\\n\\neven if Grimon’s stipulation—that her conduct affected interstate commerce—was\\n\\nan insufficient factual basis for the interstate commerce element of her offense, that\\n\\ndid not deprive the district court of subject matter jurisdiction to accept her plea.\\n\\n Whether the district court had “subject matter jurisdiction is a question of\\n\\nlaw that we review de novo even when raised for the first time on appeal.” United\\n\\nStates v. Iguaran, 821 F.3d 1335, 1336 (11th Cir. 2016).\\n\\n\\n\\n\\n 1\\n On appeal, Grimon does not challenge the district court’s sentencing guidelines\\ncalculations or the procedural or substantive reasonableness of her sentence.\\n 6\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 7 of 15\\n\\n\\nA. Subject Matter Jurisdiction\\n\\n “Subject matter jurisdiction,” which Congress bestows on the lower federal\\n\\ncourts by statute, “defines the court’s authority to hear a given type of case.”\\n\\nUnited States v. Morton, 467 U.S. 822, 828, 104 S. Ct. 2769, 2773 (1984); United\\n\\nStates v. Brown, 752 F.3d 1344, 1348 (11th Cir. 2014). In the context of federal\\n\\ncrimes, Congress has granted federal district courts original jurisdiction “of all\\n\\noffenses against the laws of the United States.” Brown, 752 F.3d at 1348; 18\\n\\nU.S.C. § 3231. As such, “[s]o long as the indictment charges the defendant with\\n\\nviolating a valid federal statute as enacted in the United States Code, it alleges ‘an\\n\\noffense against the laws of the United States,’ and, thereby, invokes the district\\n\\ncourt’s subject-matter jurisdiction.” Brown, 752 F.3d at 1354; see also Alikhani v.\\n\\nUnited States, 200 F.3d 732, 734–35 (11th Cir. 2000). An effect on interstate\\n\\ncommerce may be required for Congress to have authority under the Commerce\\n\\nClause to forbid the conduct and make it a federal crime in the first place. United\\n\\nStates v. Lopez, 514 U.S. 549, 562, 115 S. Ct. 1624, 1631 (1995). But if an\\n\\nindictment itself alleges a violation of a valid federal statute, the district court has\\n\\nsubject matter jurisdiction of that case.\\n\\n In contrast to subject matter jurisdiction, some federal statutes do contain\\n\\nwhat is referred to as a “jurisdictional element”—that is, an element of the offense\\n\\nrequiring the government to prove that the defendant’s offense had some nexus\\n\\n\\n 7\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 8 of 15\\n\\n\\nwith interstate or foreign commerce. See, e.g., United States v. Suarez, 893 F.3d\\n\\n1330, 1333 (11th Cir. 2018) (“This statute contains a jurisdictional element—the\\n\\noffense, in the case of an attempt, ‘would have affected interstate or foreign\\n\\ncommerce.’” (quoting 18 U.S.C. § 2332a(a)(2)(D))). In this very case,\\n\\n§ 1029(a)(3), under which Grimon was convicted in Count 1, contains such an\\n\\ninterstate commerce element. 18 U.S.C. § 1029(a)(3). Specifically, § 1029(a)(3)\\n\\nprovides that whoever “knowingly and with intent to defraud possesses fifteen or\\n\\nmore devices which are counterfeit or unauthorized access devices . . . shall, if the\\n\\noffense affects interstate or foreign commerce, be punished as provided in\\n\\nsubsection (c) of this section.” Id. (emphasis added).\\n\\n Nonetheless, interstate commerce jurisdictional elements, such as\\n\\n§ 1029(a)(3)’s, are not “jurisdictional” in the sense of bearing on whether or not\\n\\nthe district court has subject matter jurisdiction or authority to adjudicate the case.\\n\\nSee Alikhani, 200 F.3d at 735. Rather, the interstate commerce element is\\n\\n“jurisdictional” only in the sense that it relates to the power of Congress to regulate\\n\\nthe forbidden conduct. See id.; see also Lopez, 514 U.S. at 561-62, 115 S. Ct. at\\n\\n1631 (indicating that interstate commerce elements are meant to limit the reach of\\n\\nfederal statutes to ensure the conduct they regulate falls within Congress’s\\n\\nCommerce Clause powers).\\n\\n\\n\\n\\n 8\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 9 of 15\\n\\n\\n This Court has therefore explained that, when it comes to federal criminal\\n\\nstatutes requiring an interstate commerce nexus, the government’s failure to\\n\\nsufficiently allege or prove the interstate commerce element does not deprive the\\n\\ndistrict court of its subject matter jurisdiction over the criminal case. Alikhani, 200\\n\\nF.3d at 735. This Court in Alikhani reasoned that, while “[a]n effect on interstate\\n\\ncommerce may be required for Congress to have authority under the Commerce\\n\\nClause to forbid certain conduct,” that “does not imply that a district court faced\\n\\nwith an insufficient interstate-commerce nexus loses subject-matter jurisdiction of\\n\\nthe case.” Id. Stated differently, even if an indictment fails to allege sufficient\\n\\nfacts to support, or the government does not present sufficient evidence to prove,\\n\\nan interstate commerce nexus, the district court still has subject matter jurisdiction\\n\\nto adjudicate the case under § 3231, including, for example, the power to dismiss\\n\\nthe indictment for failure to allege facts showing the defendant committed the\\n\\ncharged offense. See id.; see also Brown, 752 F.3d at 1348-49 (discussing\\n\\nAlikhani).\\n\\n Here, Grimon makes the same argument this Court explicitly rejected in\\n\\nAlikhani. Grimon asserts that because her stipulated factual proffer merely stated\\n\\nthat her § 1029(a)(3) offense affected interstate commerce, without providing\\n\\nsupporting facts to explain how her conduct affected interstate commerce, the\\n\\ndistrict court lacked subject matter jurisdiction over her case. But as this Court\\n\\n\\n 9\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 10 of 15\\n\\n\\nexplained in Alikhani, the government’s alleged failure to sufficiently establish an\\n\\ninterstate commerce nexus does not deprive the district court of its subject matter\\n\\njurisdiction under § 3231. See Alikhani, 200 F.3d at 735. All that was required for\\n\\nthe district court to exercise subject matter jurisdiction over Grimon’s case was an\\n\\nindictment charging her with a violation of a valid federal law enacted in the\\n\\nUnited States Code, and the indictment here did just that. See Brown, 752 F.3d at\\n\\n1354. The indictment tracked the statutory language in § 1029(a)(3), charging that\\n\\nGrimon:\\n\\n did knowingly, and with intent to defraud, possess fifteen (15) or more\\n counterfeit and unauthorized access devices, that is, counterfeit credit\\n cards encoded with account numbers issued to other persons and credit\\n card account numbers issued to other persons, said conduct affecting\\n interstate and foreign commerce, in violation of Title 18, United States\\n Code, Sections 1029(a)(3) and 2.\\n\\nWhether that indictment sufficiently alleged, or Grimon’s subsequent factual\\n\\nproffer sufficiently demonstrated, an interstate nexus is merely a non-jurisdictional\\n\\nchallenge to the sufficiency of the evidence as to that element of the offense and\\n\\nhas no bearing on the district court’s power to adjudicate her case or subject matter\\n\\njurisdiction. See Alikhani, 200 F.3d at 735. Thus, we reject Grimon’s claim that\\n\\nthe district court lacked subject matter jurisdiction to accept her plea.\\n\\nB. Iguaran\\n\\n We recognize that Grimon relies on this Court’s decision in United States v.\\n\\nIguaran, 821 F.3d 1335 (11th Cir. 2016). But as we explain below, that reliance is\\n 10\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 11 of 15\\n\\n\\nmisplaced. Iguaran dealt with a wholly different statutory scheme, which, unlike\\n\\n§ 1029(a)(3), specifically requires the district court to make a preliminary\\n\\ndetermination regarding subject matter jurisdiction—not just an interstate\\n\\ncommerce “jurisdictional element”—before proceeding with a case.\\n\\n In Iguaran, the defendant pled guilty to a cocaine conspiracy offense under\\n\\nthe Maritime Drug Law Enforcement Act (“MDLEA”). Id. at 1336. Among other\\n\\nthings, the statutory text of the MDLEA “makes it a crime to conspire to distribute\\n\\na controlled substance while on board ‘a vessel subject to the jurisdiction of the\\n\\nUnited States.’” Id. (quoting 46 U.S.C. §§ 70503(a)(1), 70506(b)). Unlike the\\n\\ninterstate commerce element in § 1029(a)(3), this “vessel subject to the jurisdiction\\n\\nof the United States” requirement in the MDLEA is “jurisdictional” in the true,\\n\\nsubject matter jurisdiction sense of the word. See id. Specifically, the MDLEA\\n\\nexpressly states that “‘[j]urisdiction of the United States with respect to a vessel\\n\\nsubject to this chapter is not an element of an offense.’” Id. (quoting 46 U.S.C.\\n\\n§ 70504(a)). Instead, “‘[j]urisdictional issues arising under this chapter are\\n\\npreliminary questions of law to be determined solely by the trial judge.’” Id.\\n\\n(quoting 46 U.S.C. § 70504(a)).\\n\\n In light of this statutory language in the MDLEA, this Court has “interpreted\\n\\nthe on board a vessel subject to the jurisdiction of the United States” provision “as\\n\\na congressionally imposed limit on courts’ subject matter jurisdiction, akin to the\\n\\n\\n 11\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 12 of 15\\n\\n\\namount-in-controversy requirement contained in 28 U.S.C. § 1332.” Id. (internal\\n\\nquotation marks and citation omitted). Consequently, for a district court to have\\n\\nadjudicatory authority over a charge that the defendant conspired to violate a\\n\\nsubstantive crime defined in the MDLEA, the government must make a\\n\\npreliminary showing that the vessel was, when apprehended, subject to the\\n\\njurisdiction of the United States. Id.\\n\\n In Iguaran, this Court vacated the defendant’s guilty plea because the district\\n\\ncourt did not make any factual findings with respect to its subject matter\\n\\njurisdiction under the MDLEA, and the record contained no facts from which such\\n\\njurisdiction could be determined. See id. at 1337–38. We then remanded the case\\n\\nto the district court for the limited purpose of determining whether subject matter\\n\\njurisdiction existed, after affording both parties an opportunity to present evidence\\n\\nbearing on whether Iguaran’s vessel was subject to the jurisdiction of the United\\n\\nStates. Id. at 1338.\\n\\n Though Grimon is correct that this Court held in Iguaran that parties may not\\n\\nstipulate to jurisdiction, but rather only to underlying facts that bear on the\\n\\njurisdictional inquiry, that holding is simply irrelevant to her case. Id. at 1337.\\n\\nIguaran involved the MDLEA, where the statutory text made clear that\\n\\n“jurisdiction” is not merely an element of the offense. See id. at 1336\\n\\n(“‘Jurisdiction of the United States with respect to a vessel subject to this chapter is\\n\\n\\n 12\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 13 of 15\\n\\n\\nnot an element of an offense.’” (emphasis added) (quoting 46 U.S.C. § 70504(a))).\\n\\nIguaran, as explained above, dealt with a statutory requirement that was truly\\n\\n“jurisdictional”—that is, without facts showing that Iguaran’s vessel was subject to\\n\\nthe jurisdiction of the United States, the district court in that case had no authority\\n\\nto adjudicate his case. Id.\\n\\n Here, by contrast, § 1029(a)(3) did not require the district court to determine\\n\\nthat Grimon’s offense affected interstate commerce to have subject matter\\n\\njurisdiction. See 18 U.S.C. § 1029(a)(3). Rather, the interstate nexus requirement\\n\\nwas simply one of several elements of Grimon’s § 1029(a)(3) offense that the\\n\\ngovernment had to prove. See id.; United States v. Klopf, 423 F.3d 1228, 1240\\n\\n(11th Cir. 2005) (indicating that an effect on interstate or foreign commerce is an\\n\\nelement for offenses under § 1029(a)). Neither Iguaran nor any other case cited by\\n\\nGrimon has held that this interstate nexus requirement is akin to the amount in\\n\\ncontroversy requirement in 28 U.S.C. § 1332 or to the jurisdictional requirement in\\n\\nthe MDLEA. And we squarely hold that it is not. So, whether the government\\n\\nproved the interstate commerce nexus or failed to prove it, the district court still\\n\\nhad subject matter jurisdiction over Grimon’s case and her Count 1 conviction.\\n\\nSee Alikhani, 200 F.3d at 735.\\n\\n As to her aggravated identity theft conviction in Count 2, Grimon’s statute\\n\\nof conviction, 18 U.S.C. § 1028A(a)(1), itself does not contain an interstate\\n\\n\\n 13\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 14 of 15\\n\\n\\ncommerce element. See 18 U.S.C. § 1028A. However, because a conviction\\n\\nunder § 1028A is predicated on the unlawful transfer, possession, or use of a\\n\\nmeans of identification “during and in relation to [an enumerated] felony\\n\\nviolation,” Grimon argues that, if the district court lacked subject matter\\n\\njurisdiction over the § 1029(a)(3) offense in Count 1, it likewise lacked subject\\n\\nmatter jurisdiction over the § 1028A(a)(1) offense in Count 2. For the reasons\\n\\nstated above, we reject Grimon’s jurisdiction claim as to Count 2 as well.\\n\\nC. No Other Claim\\n\\n As a final matter, Grimon’s brief on appeal did not raise any error or\\n\\nargument other than the subject matter jurisdictional one addressed above. More\\n\\nspecifically, as the government points out, Grimon has not raised on appeal, and\\n\\nhas therefore abandoned, any claim or argument that the alleged insufficiency of\\n\\nthe factual proffer as to the interstate commerce element violated Federal Rule of\\n\\nCriminal Procedure 11 or rendered her plea unknowing or involuntary. See United\\n\\nStates v. Jernigan, 341 F.3d 1273, 1283 n.8 (11th Cir. 2003) (explaining that issues\\n\\nnot raised on appeal are deemed abandoned).\\n\\n Accordingly, we do not address whether any alleged insufficiency in\\n\\nGrimon’s factual proffer as to the interstate commerce element of her § 1029(a)(3)\\n\\noffense invalidated her guilty plea. Because Grimon has raised no claim of Rule\\n\\n11 error, we also do not address the government’s argument that the doctrine of\\n\\n\\n 14\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 15 of 15\\n\\n\\ninvited error applies because Grimon agreed in her factual proffer that the\\n\\ngovernment could have established at trial that her conduct affected interstate or\\n\\nforeign commerce.\\n\\n III. CONCLUSION\\n\\n For the foregoing reasons, we affirm Grimon’s two convictions.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 15\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4396223/\", \"author_raw\": \"HULL, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"MARCUS"},"judge2":{"kind":"string","value":"GRANT"},"judge3":{"kind":"string","value":"HULL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4618970/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Isabel Yero GRIMON, Defendant-Appellant.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-13\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-15011 Date Filed: 05/13/2019 Page: 1 of 15\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-15011\n ________________________\n\n D.C. Docket No. 1:17-cr-20221-JEM-1\n\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff-Appellee,\n\n versus\n\nISABEL YERO GRIMON,\n\n Defendant-Appellant.\n\n ________________________\n\n Appeal from the United States District Court\n for the Southern District of Florida\n ________________________\n\n (May 13, 2019)\n\nBefore MARCUS, GRANT and HULL, Circuit Judges.\n\nHULL, Circuit Judge:\n\n After pleading guilty, Isabel Yero Grimon appeals her convictions for\n\npossessing 15 or more unauthorized access devices and aggravated identity theft.\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 2 of 15\n\n\nDefendant Grimon argues that the factual proffer supporting her guilty plea was\n\ninsufficient to establish that the unauthorized access devices she possessed affected\n\ninterstate commerce and, therefore, the district court lacked subject matter\n\njurisdiction. The question presented is whether the district court has subject matter\n\njurisdiction over a criminal case to accept a guilty plea where: (1) the indictment\n\ncharges a violation of a valid federal criminal statute and sets forth the interstate\n\ncommerce element of the crime; (2) the factual proffer for the guilty plea states the\n\ngovernment at trial would prove that the defendant’s conduct affected interstate\n\ncommerce; but (3) the factual proffer does not contain any underlying facts\n\nexplaining how the interstate commerce nexus was satisfied.\n\n After review, and with the benefit of oral argument, we conclude that the\n\ninterstate commence element in § 1029(a)(3) is not “jurisdictional” in the sense of\n\nbearing on whether the district court has subject matter jurisdiction to adjudicate a\n\ncase, and thus the government’s alleged failure to prove sufficiently the interstate\n\ncommerce nexus does not deprive the district court of its subject matter jurisdiction\n\nover Grimon’s criminal case. Thus, we affirm Grimon’s convictions.\n\n I. BACKGROUND\n\nA. Arrest\n\n On January 18, 2017, officers conducted a traffic stop of Grimon’s vehicle\n\nafter observing her swerving between lanes and determining, through a records\n\n\n 2\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 3 of 15\n\n\ncheck, that there was an active warrant for her arrest out of Texas. Grimon was\n\narrested on the active warrant, and officers conducted a search incident to that\n\narrest.\n\n During the search, officers found 19 blank credit cards in Grimon’s vehicle,\n\n16 of which were encoded with account numbers issued to 10 other persons.\n\nOfficers also recovered a thumb drive from Grimon, which contained 134 credit\n\ncard account numbers issued to other persons. Grimon admitted that (1) she knew\n\nthe blank cards were re-encoded with credit card account numbers issued to other\n\npersons, (2) the credit card numbers on the thumb drive did not belong to her, and\n\n(3) she was not authorized to possess those account numbers by their owners.\n\nB. Indictment and Plea\n\n In March 2017, a federal grand jury charged Grimon with (1) one count of\n\npossession of 15 or more unauthorized access devices, in violation of 18 U.S.C.\n\n§ 1029(a)(3) (Count 1), and (2) three counts of aggravated identity theft, in\n\nviolation of 18 U.S.C. § 1028A(a)(1) (Counts 2-4). Count 1 specifically charged\n\nthat Grimon knowingly, and with intent to defraud, possessed 15 or more\n\nunauthorized access devices and that “said conduct affect[ed] interstate and foreign\n\ncommerce.”\n\n In July 2017, pursuant to a written plea agreement, Grimon pled guilty to\n\nCounts 1 and 2 of the indictment, and the government agreed to dismiss Counts 3\n\n\n 3\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 4 of 15\n\n\nand 4. In connection with her plea agreement, Grimon executed a factual proffer\n\ndetailing the offense conduct described above. As to all of the elements of Count\n\n1, Grimon’s factual proffer stated that, had the case gone to trial, the government\n\nwould have proved beyond a reasonable doubt that Grimon “did knowingly, and\n\nwith intent to defraud, possess fifteen (15) or more devices which are counterfeit\n\nand unauthorized access devices, said conduct affecting interstate and foreign\n\ncommerce.”\n\n At the change of plea hearing, Grimon confirmed, through an interpreter,\n\nthat she received a copy of the indictment and had an opportunity to fully discuss\n\nthe charges with her attorney. The government summarized the charges in Counts\n\n1 and 2. In doing so, the government explicitly stated with respect to Count 1 that\n\none of the elements of the offense “is that the Defendant’s conduct in some way\n\naffected commerce between one state and other states or between a state of the\n\nUnited States and a foreign country.” Grimon then confirmed that she understood\n\nthe charges to which she was pleading guilty. The government also read the\n\nfactual proffer into the record. That proffer included a stipulation that the\n\ngovernment would have proven at trial that Grimon “did knowingly and with intent\n\nto defraud, possess 15 or more devices which are counterfeit and unauthorized\n\naccess devices, said conduct affecting interstate and foreign commerce.”\n\n\n\n\n 4\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 5 of 15\n\n\n After this recitation, through an interpreter, Grimon agreed that the\n\ngovernment’s recitation of the facts was correct and that it could prove those facts\n\nat trial. Grimon also confirmed that she had read and discussed the factual proffer\n\nwith her attorney before signing it. Grimon’s attorney stated that he was bilingual\n\nand was able to translate the factual proffer into Spanish for Grimon, that he\n\nexplained the factual proffer to her, and that he was confident she understood its\n\ncontents.\n\n Grimon pled guilty to Counts 1 and 2, and the district court accepted her\n\nplea. The district court found that Grimon was “fully competent and capable of\n\nentering an informed plea” and that “her pleas of guilty [were] knowing and\n\nvoluntary pleas supported by an independent basis in fact containing each of the\n\nessential elements of the offenses.”\n\nC. Sentence\n\n Following a sentencing hearing, the district court sentenced Grimon to 12\n\nmonths’ imprisonment on her § 1029(a)(3) access device conviction in Count 1,\n\nfollowed by a mandatory consecutive term of 24 months’ imprisonment on her\n\n§ 1028A(a)(1) aggravated identity theft conviction in Count 2. Grimon’s total\n\nsentence is thus 36 months’ imprisonment. At that time, the district court\n\ndismissed Counts 3 and 4 of the indictment.\n\n\n\n\n 5\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 6 of 15\n\n\n Grimon now appeals her convictions.1\n\n II. DISCUSSION\n\n On appeal, Grimon argues that the district court lacked subject matter\n\njurisdiction over her offenses because the factual proffer (1) merely stipulated to\n\nthe interstate commerce element of her access device offense and (2) did not\n\ncontain any underlying facts showing that her possession of counterfeit credit cards\n\nand account numbers affected interstate commerce. Grimon stresses that the credit\n\ncards were never used.\n\n The government responds that its indictment charged Grimon with violating\n\na valid federal statute, alleged an offense against the United States and, therefore,\n\ninvoked the district court’s subject matter jurisdiction. The government argues that\n\neven if Grimon’s stipulation—that her conduct affected interstate commerce—was\n\nan insufficient factual basis for the interstate commerce element of her offense, that\n\ndid not deprive the district court of subject matter jurisdiction to accept her plea.\n\n Whether the district court had “subject matter jurisdiction is a question of\n\nlaw that we review de novo even when raised for the first time on appeal.” United\n\nStates v. Iguaran, 821 F.3d 1335, 1336 (11th Cir. 2016).\n\n\n\n\n 1\n On appeal, Grimon does not challenge the district court’s sentencing guidelines\ncalculations or the procedural or substantive reasonableness of her sentence.\n 6\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 7 of 15\n\n\nA. Subject Matter Jurisdiction\n\n “Subject matter jurisdiction,” which Congress bestows on the lower federal\n\ncourts by statute, “defines the court’s authority to hear a given type of case.”\n\nUnited States v. Morton, 467 U.S. 822, 828, 104 S. Ct. 2769, 2773 (1984); United\n\nStates v. Brown, 752 F.3d 1344, 1348 (11th Cir. 2014). In the context of federal\n\ncrimes, Congress has granted federal district courts original jurisdiction “of all\n\noffenses against the laws of the United States.” Brown, 752 F.3d at 1348; 18\n\nU.S.C. § 3231. As such, “[s]o long as the indictment charges the defendant with\n\nviolating a valid federal statute as enacted in the United States Code, it alleges ‘an\n\noffense against the laws of the United States,’ and, thereby, invokes the district\n\ncourt’s subject-matter jurisdiction.” Brown, 752 F.3d at 1354; see also Alikhani v.\n\nUnited States, 200 F.3d 732, 734–35 (11th Cir. 2000). An effect on interstate\n\ncommerce may be required for Congress to have authority under the Commerce\n\nClause to forbid the conduct and make it a federal crime in the first place. United\n\nStates v. Lopez, 514 U.S. 549, 562, 115 S. Ct. 1624, 1631 (1995). But if an\n\nindictment itself alleges a violation of a valid federal statute, the district court has\n\nsubject matter jurisdiction of that case.\n\n In contrast to subject matter jurisdiction, some federal statutes do contain\n\nwhat is referred to as a “jurisdictional element”—that is, an element of the offense\n\nrequiring the government to prove that the defendant’s offense had some nexus\n\n\n 7\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 8 of 15\n\n\nwith interstate or foreign commerce. See, e.g., United States v. Suarez, 893 F.3d\n\n1330, 1333 (11th Cir. 2018) (“This statute contains a jurisdictional element—the\n\noffense, in the case of an attempt, ‘would have affected interstate or foreign\n\ncommerce.’” (quoting 18 U.S.C. § 2332a(a)(2)(D))). In this very case,\n\n§ 1029(a)(3), under which Grimon was convicted in Count 1, contains such an\n\ninterstate commerce element. 18 U.S.C. § 1029(a)(3). Specifically, § 1029(a)(3)\n\nprovides that whoever “knowingly and with intent to defraud possesses fifteen or\n\nmore devices which are counterfeit or unauthorized access devices . . . shall, if the\n\noffense affects interstate or foreign commerce, be punished as provided in\n\nsubsection (c) of this section.” Id. (emphasis added).\n\n Nonetheless, interstate commerce jurisdictional elements, such as\n\n§ 1029(a)(3)’s, are not “jurisdictional” in the sense of bearing on whether or not\n\nthe district court has subject matter jurisdiction or authority to adjudicate the case.\n\nSee Alikhani, 200 F.3d at 735. Rather, the interstate commerce element is\n\n“jurisdictional” only in the sense that it relates to the power of Congress to regulate\n\nthe forbidden conduct. See id.; see also Lopez, 514 U.S. at 561-62, 115 S. Ct. at\n\n1631 (indicating that interstate commerce elements are meant to limit the reach of\n\nfederal statutes to ensure the conduct they regulate falls within Congress’s\n\nCommerce Clause powers).\n\n\n\n\n 8\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 9 of 15\n\n\n This Court has therefore explained that, when it comes to federal criminal\n\nstatutes requiring an interstate commerce nexus, the government’s failure to\n\nsufficiently allege or prove the interstate commerce element does not deprive the\n\ndistrict court of its subject matter jurisdiction over the criminal case. Alikhani, 200\n\nF.3d at 735. This Court in Alikhani reasoned that, while “[a]n effect on interstate\n\ncommerce may be required for Congress to have authority under the Commerce\n\nClause to forbid certain conduct,” that “does not imply that a district court faced\n\nwith an insufficient interstate-commerce nexus loses subject-matter jurisdiction of\n\nthe case.” Id. Stated differently, even if an indictment fails to allege sufficient\n\nfacts to support, or the government does not present sufficient evidence to prove,\n\nan interstate commerce nexus, the district court still has subject matter jurisdiction\n\nto adjudicate the case under § 3231, including, for example, the power to dismiss\n\nthe indictment for failure to allege facts showing the defendant committed the\n\ncharged offense. See id.; see also Brown, 752 F.3d at 1348-49 (discussing\n\nAlikhani).\n\n Here, Grimon makes the same argument this Court explicitly rejected in\n\nAlikhani. Grimon asserts that because her stipulated factual proffer merely stated\n\nthat her § 1029(a)(3) offense affected interstate commerce, without providing\n\nsupporting facts to explain how her conduct affected interstate commerce, the\n\ndistrict court lacked subject matter jurisdiction over her case. But as this Court\n\n\n 9\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 10 of 15\n\n\nexplained in Alikhani, the government’s alleged failure to sufficiently establish an\n\ninterstate commerce nexus does not deprive the district court of its subject matter\n\njurisdiction under § 3231. See Alikhani, 200 F.3d at 735. All that was required for\n\nthe district court to exercise subject matter jurisdiction over Grimon’s case was an\n\nindictment charging her with a violation of a valid federal law enacted in the\n\nUnited States Code, and the indictment here did just that. See Brown, 752 F.3d at\n\n1354. The indictment tracked the statutory language in § 1029(a)(3), charging that\n\nGrimon:\n\n did knowingly, and with intent to defraud, possess fifteen (15) or more\n counterfeit and unauthorized access devices, that is, counterfeit credit\n cards encoded with account numbers issued to other persons and credit\n card account numbers issued to other persons, said conduct affecting\n interstate and foreign commerce, in violation of Title 18, United States\n Code, Sections 1029(a)(3) and 2.\n\nWhether that indictment sufficiently alleged, or Grimon’s subsequent factual\n\nproffer sufficiently demonstrated, an interstate nexus is merely a non-jurisdictional\n\nchallenge to the sufficiency of the evidence as to that element of the offense and\n\nhas no bearing on the district court’s power to adjudicate her case or subject matter\n\njurisdiction. See Alikhani, 200 F.3d at 735. Thus, we reject Grimon’s claim that\n\nthe district court lacked subject matter jurisdiction to accept her plea.\n\nB. Iguaran\n\n We recognize that Grimon relies on this Court’s decision in United States v.\n\nIguaran, 821 F.3d 1335 (11th Cir. 2016). But as we explain below, that reliance is\n 10\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 11 of 15\n\n\nmisplaced. Iguaran dealt with a wholly different statutory scheme, which, unlike\n\n§ 1029(a)(3), specifically requires the district court to make a preliminary\n\ndetermination regarding subject matter jurisdiction—not just an interstate\n\ncommerce “jurisdictional element”—before proceeding with a case.\n\n In Iguaran, the defendant pled guilty to a cocaine conspiracy offense under\n\nthe Maritime Drug Law Enforcement Act (“MDLEA”). Id. at 1336. Among other\n\nthings, the statutory text of the MDLEA “makes it a crime to conspire to distribute\n\na controlled substance while on board ‘a vessel subject to the jurisdiction of the\n\nUnited States.’” Id. (quoting 46 U.S.C. §§ 70503(a)(1), 70506(b)). Unlike the\n\ninterstate commerce element in § 1029(a)(3), this “vessel subject to the jurisdiction\n\nof the United States” requirement in the MDLEA is “jurisdictional” in the true,\n\nsubject matter jurisdiction sense of the word. See id. Specifically, the MDLEA\n\nexpressly states that “‘[j]urisdiction of the United States with respect to a vessel\n\nsubject to this chapter is not an element of an offense.’” Id. (quoting 46 U.S.C.\n\n§ 70504(a)). Instead, “‘[j]urisdictional issues arising under this chapter are\n\npreliminary questions of law to be determined solely by the trial judge.’” Id.\n\n(quoting 46 U.S.C. § 70504(a)).\n\n In light of this statutory language in the MDLEA, this Court has “interpreted\n\nthe on board a vessel subject to the jurisdiction of the United States” provision “as\n\na congressionally imposed limit on courts’ subject matter jurisdiction, akin to the\n\n\n 11\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 12 of 15\n\n\namount-in-controversy requirement contained in 28 U.S.C. § 1332.” Id. (internal\n\nquotation marks and citation omitted). Consequently, for a district court to have\n\nadjudicatory authority over a charge that the defendant conspired to violate a\n\nsubstantive crime defined in the MDLEA, the government must make a\n\npreliminary showing that the vessel was, when apprehended, subject to the\n\njurisdiction of the United States. Id.\n\n In Iguaran, this Court vacated the defendant’s guilty plea because the district\n\ncourt did not make any factual findings with respect to its subject matter\n\njurisdiction under the MDLEA, and the record contained no facts from which such\n\njurisdiction could be determined. See id. at 1337–38. We then remanded the case\n\nto the district court for the limited purpose of determining whether subject matter\n\njurisdiction existed, after affording both parties an opportunity to present evidence\n\nbearing on whether Iguaran’s vessel was subject to the jurisdiction of the United\n\nStates. Id. at 1338.\n\n Though Grimon is correct that this Court held in Iguaran that parties may not\n\nstipulate to jurisdiction, but rather only to underlying facts that bear on the\n\njurisdictional inquiry, that holding is simply irrelevant to her case. Id. at 1337.\n\nIguaran involved the MDLEA, where the statutory text made clear that\n\n“jurisdiction” is not merely an element of the offense. See id. at 1336\n\n(“‘Jurisdiction of the United States with respect to a vessel subject to this chapter is\n\n\n 12\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 13 of 15\n\n\nnot an element of an offense.’” (emphasis added) (quoting 46 U.S.C. § 70504(a))).\n\nIguaran, as explained above, dealt with a statutory requirement that was truly\n\n“jurisdictional”—that is, without facts showing that Iguaran’s vessel was subject to\n\nthe jurisdiction of the United States, the district court in that case had no authority\n\nto adjudicate his case. Id.\n\n Here, by contrast, § 1029(a)(3) did not require the district court to determine\n\nthat Grimon’s offense affected interstate commerce to have subject matter\n\njurisdiction. See 18 U.S.C. § 1029(a)(3). Rather, the interstate nexus requirement\n\nwas simply one of several elements of Grimon’s § 1029(a)(3) offense that the\n\ngovernment had to prove. See id.; United States v. Klopf, 423 F.3d 1228, 1240\n\n(11th Cir. 2005) (indicating that an effect on interstate or foreign commerce is an\n\nelement for offenses under § 1029(a)). Neither Iguaran nor any other case cited by\n\nGrimon has held that this interstate nexus requirement is akin to the amount in\n\ncontroversy requirement in 28 U.S.C. § 1332 or to the jurisdictional requirement in\n\nthe MDLEA. And we squarely hold that it is not. So, whether the government\n\nproved the interstate commerce nexus or failed to prove it, the district court still\n\nhad subject matter jurisdiction over Grimon’s case and her Count 1 conviction.\n\nSee Alikhani, 200 F.3d at 735.\n\n As to her aggravated identity theft conviction in Count 2, Grimon’s statute\n\nof conviction, 18 U.S.C. § 1028A(a)(1), itself does not contain an interstate\n\n\n 13\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 14 of 15\n\n\ncommerce element. See 18 U.S.C. § 1028A. However, because a conviction\n\nunder § 1028A is predicated on the unlawful transfer, possession, or use of a\n\nmeans of identification “during and in relation to [an enumerated] felony\n\nviolation,” Grimon argues that, if the district court lacked subject matter\n\njurisdiction over the § 1029(a)(3) offense in Count 1, it likewise lacked subject\n\nmatter jurisdiction over the § 1028A(a)(1) offense in Count 2. For the reasons\n\nstated above, we reject Grimon’s jurisdiction claim as to Count 2 as well.\n\nC. No Other Claim\n\n As a final matter, Grimon’s brief on appeal did not raise any error or\n\nargument other than the subject matter jurisdictional one addressed above. More\n\nspecifically, as the government points out, Grimon has not raised on appeal, and\n\nhas therefore abandoned, any claim or argument that the alleged insufficiency of\n\nthe factual proffer as to the interstate commerce element violated Federal Rule of\n\nCriminal Procedure 11 or rendered her plea unknowing or involuntary. See United\n\nStates v. Jernigan, 341 F.3d 1273, 1283 n.8 (11th Cir. 2003) (explaining that issues\n\nnot raised on appeal are deemed abandoned).\n\n Accordingly, we do not address whether any alleged insufficiency in\n\nGrimon’s factual proffer as to the interstate commerce element of her § 1029(a)(3)\n\noffense invalidated her guilty plea. Because Grimon has raised no claim of Rule\n\n11 error, we also do not address the government’s argument that the doctrine of\n\n\n 14\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 15 of 15\n\n\ninvited error applies because Grimon agreed in her factual proffer that the\n\ngovernment could have established at trial that her conduct affected interstate or\n\nforeign commerce.\n\n III. CONCLUSION\n\n For the foregoing reasons, we affirm Grimon’s two convictions.\n\n AFFIRMED.\n\n\n\n\n 15\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellee, v. Isabel Yero GRIMON, Defendant-Appellant.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-13\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-15011 Date Filed: 05/13/2019 Page: 1 of 15\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15011\\n ________________________\\n\\n D.C. Docket No. 1:17-cr-20221-JEM-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\n versus\\n\\nISABEL YERO GRIMON,\\n\\n Defendant-Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 13, 2019)\\n\\nBefore MARCUS, GRANT and HULL, Circuit Judges.\\n\\nHULL, Circuit Judge:\\n\\n After pleading guilty, Isabel Yero Grimon appeals her convictions for\\n\\npossessing 15 or more unauthorized access devices and aggravated identity theft.\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 2 of 15\\n\\n\\nDefendant Grimon argues that the factual proffer supporting her guilty plea was\\n\\ninsufficient to establish that the unauthorized access devices she possessed affected\\n\\ninterstate commerce and, therefore, the district court lacked subject matter\\n\\njurisdiction. The question presented is whether the district court has subject matter\\n\\njurisdiction over a criminal case to accept a guilty plea where: (1) the indictment\\n\\ncharges a violation of a valid federal criminal statute and sets forth the interstate\\n\\ncommerce element of the crime; (2) the factual proffer for the guilty plea states the\\n\\ngovernment at trial would prove that the defendant’s conduct affected interstate\\n\\ncommerce; but (3) the factual proffer does not contain any underlying facts\\n\\nexplaining how the interstate commerce nexus was satisfied.\\n\\n After review, and with the benefit of oral argument, we conclude that the\\n\\ninterstate commence element in § 1029(a)(3) is not “jurisdictional” in the sense of\\n\\nbearing on whether the district court has subject matter jurisdiction to adjudicate a\\n\\ncase, and thus the government’s alleged failure to prove sufficiently the interstate\\n\\ncommerce nexus does not deprive the district court of its subject matter jurisdiction\\n\\nover Grimon’s criminal case. Thus, we affirm Grimon’s convictions.\\n\\n I. BACKGROUND\\n\\nA. Arrest\\n\\n On January 18, 2017, officers conducted a traffic stop of Grimon’s vehicle\\n\\nafter observing her swerving between lanes and determining, through a records\\n\\n\\n 2\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 3 of 15\\n\\n\\ncheck, that there was an active warrant for her arrest out of Texas. Grimon was\\n\\narrested on the active warrant, and officers conducted a search incident to that\\n\\narrest.\\n\\n During the search, officers found 19 blank credit cards in Grimon’s vehicle,\\n\\n16 of which were encoded with account numbers issued to 10 other persons.\\n\\nOfficers also recovered a thumb drive from Grimon, which contained 134 credit\\n\\ncard account numbers issued to other persons. Grimon admitted that (1) she knew\\n\\nthe blank cards were re-encoded with credit card account numbers issued to other\\n\\npersons, (2) the credit card numbers on the thumb drive did not belong to her, and\\n\\n(3) she was not authorized to possess those account numbers by their owners.\\n\\nB. Indictment and Plea\\n\\n In March 2017, a federal grand jury charged Grimon with (1) one count of\\n\\npossession of 15 or more unauthorized access devices, in violation of 18 U.S.C.\\n\\n§ 1029(a)(3) (Count 1), and (2) three counts of aggravated identity theft, in\\n\\nviolation of 18 U.S.C. § 1028A(a)(1) (Counts 2-4). Count 1 specifically charged\\n\\nthat Grimon knowingly, and with intent to defraud, possessed 15 or more\\n\\nunauthorized access devices and that “said conduct affect[ed] interstate and foreign\\n\\ncommerce.”\\n\\n In July 2017, pursuant to a written plea agreement, Grimon pled guilty to\\n\\nCounts 1 and 2 of the indictment, and the government agreed to dismiss Counts 3\\n\\n\\n 3\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 4 of 15\\n\\n\\nand 4. In connection with her plea agreement, Grimon executed a factual proffer\\n\\ndetailing the offense conduct described above. As to all of the elements of Count\\n\\n1, Grimon’s factual proffer stated that, had the case gone to trial, the government\\n\\nwould have proved beyond a reasonable doubt that Grimon “did knowingly, and\\n\\nwith intent to defraud, possess fifteen (15) or more devices which are counterfeit\\n\\nand unauthorized access devices, said conduct affecting interstate and foreign\\n\\ncommerce.”\\n\\n At the change of plea hearing, Grimon confirmed, through an interpreter,\\n\\nthat she received a copy of the indictment and had an opportunity to fully discuss\\n\\nthe charges with her attorney. The government summarized the charges in Counts\\n\\n1 and 2. In doing so, the government explicitly stated with respect to Count 1 that\\n\\none of the elements of the offense “is that the Defendant’s conduct in some way\\n\\naffected commerce between one state and other states or between a state of the\\n\\nUnited States and a foreign country.” Grimon then confirmed that she understood\\n\\nthe charges to which she was pleading guilty. The government also read the\\n\\nfactual proffer into the record. That proffer included a stipulation that the\\n\\ngovernment would have proven at trial that Grimon “did knowingly and with intent\\n\\nto defraud, possess 15 or more devices which are counterfeit and unauthorized\\n\\naccess devices, said conduct affecting interstate and foreign commerce.”\\n\\n\\n\\n\\n 4\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 5 of 15\\n\\n\\n After this recitation, through an interpreter, Grimon agreed that the\\n\\ngovernment’s recitation of the facts was correct and that it could prove those facts\\n\\nat trial. Grimon also confirmed that she had read and discussed the factual proffer\\n\\nwith her attorney before signing it. Grimon’s attorney stated that he was bilingual\\n\\nand was able to translate the factual proffer into Spanish for Grimon, that he\\n\\nexplained the factual proffer to her, and that he was confident she understood its\\n\\ncontents.\\n\\n Grimon pled guilty to Counts 1 and 2, and the district court accepted her\\n\\nplea. The district court found that Grimon was “fully competent and capable of\\n\\nentering an informed plea” and that “her pleas of guilty [were] knowing and\\n\\nvoluntary pleas supported by an independent basis in fact containing each of the\\n\\nessential elements of the offenses.”\\n\\nC. Sentence\\n\\n Following a sentencing hearing, the district court sentenced Grimon to 12\\n\\nmonths’ imprisonment on her § 1029(a)(3) access device conviction in Count 1,\\n\\nfollowed by a mandatory consecutive term of 24 months’ imprisonment on her\\n\\n§ 1028A(a)(1) aggravated identity theft conviction in Count 2. Grimon’s total\\n\\nsentence is thus 36 months’ imprisonment. At that time, the district court\\n\\ndismissed Counts 3 and 4 of the indictment.\\n\\n\\n\\n\\n 5\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 6 of 15\\n\\n\\n Grimon now appeals her convictions.1\\n\\n II. DISCUSSION\\n\\n On appeal, Grimon argues that the district court lacked subject matter\\n\\njurisdiction over her offenses because the factual proffer (1) merely stipulated to\\n\\nthe interstate commerce element of her access device offense and (2) did not\\n\\ncontain any underlying facts showing that her possession of counterfeit credit cards\\n\\nand account numbers affected interstate commerce. Grimon stresses that the credit\\n\\ncards were never used.\\n\\n The government responds that its indictment charged Grimon with violating\\n\\na valid federal statute, alleged an offense against the United States and, therefore,\\n\\ninvoked the district court’s subject matter jurisdiction. The government argues that\\n\\neven if Grimon’s stipulation—that her conduct affected interstate commerce—was\\n\\nan insufficient factual basis for the interstate commerce element of her offense, that\\n\\ndid not deprive the district court of subject matter jurisdiction to accept her plea.\\n\\n Whether the district court had “subject matter jurisdiction is a question of\\n\\nlaw that we review de novo even when raised for the first time on appeal.” United\\n\\nStates v. Iguaran, 821 F.3d 1335, 1336 (11th Cir. 2016).\\n\\n\\n\\n\\n 1\\n On appeal, Grimon does not challenge the district court’s sentencing guidelines\\ncalculations or the procedural or substantive reasonableness of her sentence.\\n 6\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 7 of 15\\n\\n\\nA. Subject Matter Jurisdiction\\n\\n “Subject matter jurisdiction,” which Congress bestows on the lower federal\\n\\ncourts by statute, “defines the court’s authority to hear a given type of case.”\\n\\nUnited States v. Morton, 467 U.S. 822, 828, 104 S. Ct. 2769, 2773 (1984); United\\n\\nStates v. Brown, 752 F.3d 1344, 1348 (11th Cir. 2014). In the context of federal\\n\\ncrimes, Congress has granted federal district courts original jurisdiction “of all\\n\\noffenses against the laws of the United States.” Brown, 752 F.3d at 1348; 18\\n\\nU.S.C. § 3231. As such, “[s]o long as the indictment charges the defendant with\\n\\nviolating a valid federal statute as enacted in the United States Code, it alleges ‘an\\n\\noffense against the laws of the United States,’ and, thereby, invokes the district\\n\\ncourt’s subject-matter jurisdiction.” Brown, 752 F.3d at 1354; see also Alikhani v.\\n\\nUnited States, 200 F.3d 732, 734–35 (11th Cir. 2000). An effect on interstate\\n\\ncommerce may be required for Congress to have authority under the Commerce\\n\\nClause to forbid the conduct and make it a federal crime in the first place. United\\n\\nStates v. Lopez, 514 U.S. 549, 562, 115 S. Ct. 1624, 1631 (1995). But if an\\n\\nindictment itself alleges a violation of a valid federal statute, the district court has\\n\\nsubject matter jurisdiction of that case.\\n\\n In contrast to subject matter jurisdiction, some federal statutes do contain\\n\\nwhat is referred to as a “jurisdictional element”—that is, an element of the offense\\n\\nrequiring the government to prove that the defendant’s offense had some nexus\\n\\n\\n 7\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 8 of 15\\n\\n\\nwith interstate or foreign commerce. See, e.g., United States v. Suarez, 893 F.3d\\n\\n1330, 1333 (11th Cir. 2018) (“This statute contains a jurisdictional element—the\\n\\noffense, in the case of an attempt, ‘would have affected interstate or foreign\\n\\ncommerce.’” (quoting 18 U.S.C. § 2332a(a)(2)(D))). In this very case,\\n\\n§ 1029(a)(3), under which Grimon was convicted in Count 1, contains such an\\n\\ninterstate commerce element. 18 U.S.C. § 1029(a)(3). Specifically, § 1029(a)(3)\\n\\nprovides that whoever “knowingly and with intent to defraud possesses fifteen or\\n\\nmore devices which are counterfeit or unauthorized access devices . . . shall, if the\\n\\noffense affects interstate or foreign commerce, be punished as provided in\\n\\nsubsection (c) of this section.” Id. (emphasis added).\\n\\n Nonetheless, interstate commerce jurisdictional elements, such as\\n\\n§ 1029(a)(3)’s, are not “jurisdictional” in the sense of bearing on whether or not\\n\\nthe district court has subject matter jurisdiction or authority to adjudicate the case.\\n\\nSee Alikhani, 200 F.3d at 735. Rather, the interstate commerce element is\\n\\n“jurisdictional” only in the sense that it relates to the power of Congress to regulate\\n\\nthe forbidden conduct. See id.; see also Lopez, 514 U.S. at 561-62, 115 S. Ct. at\\n\\n1631 (indicating that interstate commerce elements are meant to limit the reach of\\n\\nfederal statutes to ensure the conduct they regulate falls within Congress’s\\n\\nCommerce Clause powers).\\n\\n\\n\\n\\n 8\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 9 of 15\\n\\n\\n This Court has therefore explained that, when it comes to federal criminal\\n\\nstatutes requiring an interstate commerce nexus, the government’s failure to\\n\\nsufficiently allege or prove the interstate commerce element does not deprive the\\n\\ndistrict court of its subject matter jurisdiction over the criminal case. Alikhani, 200\\n\\nF.3d at 735. This Court in Alikhani reasoned that, while “[a]n effect on interstate\\n\\ncommerce may be required for Congress to have authority under the Commerce\\n\\nClause to forbid certain conduct,” that “does not imply that a district court faced\\n\\nwith an insufficient interstate-commerce nexus loses subject-matter jurisdiction of\\n\\nthe case.” Id. Stated differently, even if an indictment fails to allege sufficient\\n\\nfacts to support, or the government does not present sufficient evidence to prove,\\n\\nan interstate commerce nexus, the district court still has subject matter jurisdiction\\n\\nto adjudicate the case under § 3231, including, for example, the power to dismiss\\n\\nthe indictment for failure to allege facts showing the defendant committed the\\n\\ncharged offense. See id.; see also Brown, 752 F.3d at 1348-49 (discussing\\n\\nAlikhani).\\n\\n Here, Grimon makes the same argument this Court explicitly rejected in\\n\\nAlikhani. Grimon asserts that because her stipulated factual proffer merely stated\\n\\nthat her § 1029(a)(3) offense affected interstate commerce, without providing\\n\\nsupporting facts to explain how her conduct affected interstate commerce, the\\n\\ndistrict court lacked subject matter jurisdiction over her case. But as this Court\\n\\n\\n 9\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 10 of 15\\n\\n\\nexplained in Alikhani, the government’s alleged failure to sufficiently establish an\\n\\ninterstate commerce nexus does not deprive the district court of its subject matter\\n\\njurisdiction under § 3231. See Alikhani, 200 F.3d at 735. All that was required for\\n\\nthe district court to exercise subject matter jurisdiction over Grimon’s case was an\\n\\nindictment charging her with a violation of a valid federal law enacted in the\\n\\nUnited States Code, and the indictment here did just that. See Brown, 752 F.3d at\\n\\n1354. The indictment tracked the statutory language in § 1029(a)(3), charging that\\n\\nGrimon:\\n\\n did knowingly, and with intent to defraud, possess fifteen (15) or more\\n counterfeit and unauthorized access devices, that is, counterfeit credit\\n cards encoded with account numbers issued to other persons and credit\\n card account numbers issued to other persons, said conduct affecting\\n interstate and foreign commerce, in violation of Title 18, United States\\n Code, Sections 1029(a)(3) and 2.\\n\\nWhether that indictment sufficiently alleged, or Grimon’s subsequent factual\\n\\nproffer sufficiently demonstrated, an interstate nexus is merely a non-jurisdictional\\n\\nchallenge to the sufficiency of the evidence as to that element of the offense and\\n\\nhas no bearing on the district court’s power to adjudicate her case or subject matter\\n\\njurisdiction. See Alikhani, 200 F.3d at 735. Thus, we reject Grimon’s claim that\\n\\nthe district court lacked subject matter jurisdiction to accept her plea.\\n\\nB. Iguaran\\n\\n We recognize that Grimon relies on this Court’s decision in United States v.\\n\\nIguaran, 821 F.3d 1335 (11th Cir. 2016). But as we explain below, that reliance is\\n 10\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 11 of 15\\n\\n\\nmisplaced. Iguaran dealt with a wholly different statutory scheme, which, unlike\\n\\n§ 1029(a)(3), specifically requires the district court to make a preliminary\\n\\ndetermination regarding subject matter jurisdiction—not just an interstate\\n\\ncommerce “jurisdictional element”—before proceeding with a case.\\n\\n In Iguaran, the defendant pled guilty to a cocaine conspiracy offense under\\n\\nthe Maritime Drug Law Enforcement Act (“MDLEA”). Id. at 1336. Among other\\n\\nthings, the statutory text of the MDLEA “makes it a crime to conspire to distribute\\n\\na controlled substance while on board ‘a vessel subject to the jurisdiction of the\\n\\nUnited States.’” Id. (quoting 46 U.S.C. §§ 70503(a)(1), 70506(b)). Unlike the\\n\\ninterstate commerce element in § 1029(a)(3), this “vessel subject to the jurisdiction\\n\\nof the United States” requirement in the MDLEA is “jurisdictional” in the true,\\n\\nsubject matter jurisdiction sense of the word. See id. Specifically, the MDLEA\\n\\nexpressly states that “‘[j]urisdiction of the United States with respect to a vessel\\n\\nsubject to this chapter is not an element of an offense.’” Id. (quoting 46 U.S.C.\\n\\n§ 70504(a)). Instead, “‘[j]urisdictional issues arising under this chapter are\\n\\npreliminary questions of law to be determined solely by the trial judge.’” Id.\\n\\n(quoting 46 U.S.C. § 70504(a)).\\n\\n In light of this statutory language in the MDLEA, this Court has “interpreted\\n\\nthe on board a vessel subject to the jurisdiction of the United States” provision “as\\n\\na congressionally imposed limit on courts’ subject matter jurisdiction, akin to the\\n\\n\\n 11\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 12 of 15\\n\\n\\namount-in-controversy requirement contained in 28 U.S.C. § 1332.” Id. (internal\\n\\nquotation marks and citation omitted). Consequently, for a district court to have\\n\\nadjudicatory authority over a charge that the defendant conspired to violate a\\n\\nsubstantive crime defined in the MDLEA, the government must make a\\n\\npreliminary showing that the vessel was, when apprehended, subject to the\\n\\njurisdiction of the United States. Id.\\n\\n In Iguaran, this Court vacated the defendant’s guilty plea because the district\\n\\ncourt did not make any factual findings with respect to its subject matter\\n\\njurisdiction under the MDLEA, and the record contained no facts from which such\\n\\njurisdiction could be determined. See id. at 1337–38. We then remanded the case\\n\\nto the district court for the limited purpose of determining whether subject matter\\n\\njurisdiction existed, after affording both parties an opportunity to present evidence\\n\\nbearing on whether Iguaran’s vessel was subject to the jurisdiction of the United\\n\\nStates. Id. at 1338.\\n\\n Though Grimon is correct that this Court held in Iguaran that parties may not\\n\\nstipulate to jurisdiction, but rather only to underlying facts that bear on the\\n\\njurisdictional inquiry, that holding is simply irrelevant to her case. Id. at 1337.\\n\\nIguaran involved the MDLEA, where the statutory text made clear that\\n\\n“jurisdiction” is not merely an element of the offense. See id. at 1336\\n\\n(“‘Jurisdiction of the United States with respect to a vessel subject to this chapter is\\n\\n\\n 12\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 13 of 15\\n\\n\\nnot an element of an offense.’” (emphasis added) (quoting 46 U.S.C. § 70504(a))).\\n\\nIguaran, as explained above, dealt with a statutory requirement that was truly\\n\\n“jurisdictional”—that is, without facts showing that Iguaran’s vessel was subject to\\n\\nthe jurisdiction of the United States, the district court in that case had no authority\\n\\nto adjudicate his case. Id.\\n\\n Here, by contrast, § 1029(a)(3) did not require the district court to determine\\n\\nthat Grimon’s offense affected interstate commerce to have subject matter\\n\\njurisdiction. See 18 U.S.C. § 1029(a)(3). Rather, the interstate nexus requirement\\n\\nwas simply one of several elements of Grimon’s § 1029(a)(3) offense that the\\n\\ngovernment had to prove. See id.; United States v. Klopf, 423 F.3d 1228, 1240\\n\\n(11th Cir. 2005) (indicating that an effect on interstate or foreign commerce is an\\n\\nelement for offenses under § 1029(a)). Neither Iguaran nor any other case cited by\\n\\nGrimon has held that this interstate nexus requirement is akin to the amount in\\n\\ncontroversy requirement in 28 U.S.C. § 1332 or to the jurisdictional requirement in\\n\\nthe MDLEA. And we squarely hold that it is not. So, whether the government\\n\\nproved the interstate commerce nexus or failed to prove it, the district court still\\n\\nhad subject matter jurisdiction over Grimon’s case and her Count 1 conviction.\\n\\nSee Alikhani, 200 F.3d at 735.\\n\\n As to her aggravated identity theft conviction in Count 2, Grimon’s statute\\n\\nof conviction, 18 U.S.C. § 1028A(a)(1), itself does not contain an interstate\\n\\n\\n 13\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 14 of 15\\n\\n\\ncommerce element. See 18 U.S.C. § 1028A. However, because a conviction\\n\\nunder § 1028A is predicated on the unlawful transfer, possession, or use of a\\n\\nmeans of identification “during and in relation to [an enumerated] felony\\n\\nviolation,” Grimon argues that, if the district court lacked subject matter\\n\\njurisdiction over the § 1029(a)(3) offense in Count 1, it likewise lacked subject\\n\\nmatter jurisdiction over the § 1028A(a)(1) offense in Count 2. For the reasons\\n\\nstated above, we reject Grimon’s jurisdiction claim as to Count 2 as well.\\n\\nC. No Other Claim\\n\\n As a final matter, Grimon’s brief on appeal did not raise any error or\\n\\nargument other than the subject matter jurisdictional one addressed above. More\\n\\nspecifically, as the government points out, Grimon has not raised on appeal, and\\n\\nhas therefore abandoned, any claim or argument that the alleged insufficiency of\\n\\nthe factual proffer as to the interstate commerce element violated Federal Rule of\\n\\nCriminal Procedure 11 or rendered her plea unknowing or involuntary. See United\\n\\nStates v. Jernigan, 341 F.3d 1273, 1283 n.8 (11th Cir. 2003) (explaining that issues\\n\\nnot raised on appeal are deemed abandoned).\\n\\n Accordingly, we do not address whether any alleged insufficiency in\\n\\nGrimon’s factual proffer as to the interstate commerce element of her § 1029(a)(3)\\n\\noffense invalidated her guilty plea. Because Grimon has raised no claim of Rule\\n\\n11 error, we also do not address the government’s argument that the doctrine of\\n\\n\\n 14\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 15 of 15\\n\\n\\ninvited error applies because Grimon agreed in her factual proffer that the\\n\\ngovernment could have established at trial that her conduct affected interstate or\\n\\nforeign commerce.\\n\\n III. CONCLUSION\\n\\n For the foregoing reasons, we affirm Grimon’s two convictions.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 15\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2280,"cells":{"id":{"kind":"number","value":4619841,"string":"4,619,841"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"United States v. Isabel Yero Grimon"},"decision_date":{"kind":"string","value":"2019-05-13"},"docket_number":{"kind":"string","value":"17-15011"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before MARCUS, GRANT and HULL, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"HULL, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-15011 Date Filed: 05/13/2019 Page: 1 of 15\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15011\\n ________________________\\n\\n D.C. Docket No. 1:17-cr-20221-JEM-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\n versus\\n\\nISABEL YERO GRIMON,\\n\\n Defendant-Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 13, 2019)\\n\\nBefore MARCUS, GRANT and HULL, Circuit Judges.\\n\\nHULL, Circuit Judge:\\n\\n After pleading guilty, Isabel Yero Grimon appeals her convictions for\\n\\npossessing 15 or more unauthorized access devices and aggravated identity theft.\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 2 of 15\\n\\n\\nDefendant Grimon argues that the factual proffer supporting her guilty plea was\\n\\ninsufficient to establish that the unauthorized access devices she possessed affected\\n\\ninterstate commerce and, therefore, the district court lacked subject matter\\n\\njurisdiction. The question presented is whether the district court has subject matter\\n\\njurisdiction over a criminal case to accept a guilty plea where: (1) the indictment\\n\\ncharges a violation of a valid federal criminal statute and sets forth the interstate\\n\\ncommerce element of the crime; (2) the factual proffer for the guilty plea states the\\n\\ngovernment at trial would prove that the defendant’s conduct affected interstate\\n\\ncommerce; but (3) the factual proffer does not contain any underlying facts\\n\\nexplaining how the interstate commerce nexus was satisfied.\\n\\n After review, and with the benefit of oral argument, we conclude that the\\n\\ninterstate commerce element in § 1029(a)(3) is not “jurisdictional” in the sense of\\n\\nbearing on whether the district court has subject matter jurisdiction to adjudicate a\\n\\ncase, and thus the government’s alleged failure to prove sufficiently the interstate\\n\\ncommerce nexus does not deprive the district court of its subject matter jurisdiction\\n\\nover Grimon’s criminal case. Thus, we affirm Grimon’s convictions.\\n\\n I. BACKGROUND\\n\\nA. Arrest\\n\\n On January 18, 2017, officers conducted a traffic stop of Grimon’s vehicle\\n\\nafter observing her swerving between lanes and determining, through a records\\n\\n\\n 2\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 3 of 15\\n\\n\\ncheck, that there was an active warrant for her arrest out of Texas. Grimon was\\n\\narrested on the active warrant, and officers conducted a search incident to that\\n\\narrest.\\n\\n During the search, officers found 19 blank credit cards in Grimon’s vehicle,\\n\\n16 of which were encoded with account numbers issued to 10 other persons.\\n\\nOfficers also recovered a thumb drive from Grimon, which contained 134 credit\\n\\ncard account numbers issued to other persons. Grimon admitted that (1) she knew\\n\\nthe blank cards were re-encoded with credit card account numbers issued to other\\n\\npersons, (2) the credit card numbers on the thumb drive did not belong to her, and\\n\\n(3) she was not authorized to possess those account numbers by their owners.\\n\\nB. Indictment and Plea\\n\\n In March 2017, a federal grand jury charged Grimon with (1) one count of\\n\\npossession of 15 or more unauthorized access devices, in violation of 18 U.S.C.\\n\\n§ 1029(a)(3) (Count 1), and (2) three counts of aggravated identity theft, in\\n\\nviolation of 18 U.S.C. § 1028A(a)(1) (Counts 2-4). Count 1 specifically charged\\n\\nthat Grimon knowingly, and with intent to defraud, possessed 15 or more\\n\\nunauthorized access devices and that “said conduct affect[ed] interstate and foreign\\n\\ncommerce.”\\n\\n In July 2017, pursuant to a written plea agreement, Grimon pled guilty to\\n\\nCounts 1 and 2 of the indictment, and the government agreed to dismiss Counts 3\\n\\n\\n 3\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 4 of 15\\n\\n\\nand 4. In connection with her plea agreement, Grimon executed a factual proffer\\n\\ndetailing the offense conduct described above. As to all of the elements of Count\\n\\n1, Grimon’s factual proffer stated that, had the case gone to trial, the government\\n\\nwould have proved beyond a reasonable doubt that Grimon “did knowingly, and\\n\\nwith intent to defraud, possess fifteen (15) or more devices which are counterfeit\\n\\nand unauthorized access devices, said conduct affecting interstate and foreign\\n\\ncommerce.”\\n\\n At the change of plea hearing, Grimon confirmed, through an interpreter,\\n\\nthat she received a copy of the indictment and had an opportunity to fully discuss\\n\\nthe charges with her attorney. The government summarized the charges in Counts\\n\\n1 and 2. In doing so, the government explicitly stated with respect to Count 1 that\\n\\none of the elements of the offense “is that the Defendant’s conduct in some way\\n\\naffected commerce between one state and other states or between a state of the\\n\\nUnited States and a foreign country.” Grimon then confirmed that she understood\\n\\nthe charges to which she was pleading guilty. The government also read the\\n\\nfactual proffer into the record. That proffer included a stipulation that the\\n\\ngovernment would have proven at trial that Grimon “did knowingly and with intent\\n\\nto defraud, possess 15 or more devices which are counterfeit and unauthorized\\n\\naccess devices, said conduct affecting interstate and foreign commerce.”\\n\\n\\n\\n\\n 4\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 5 of 15\\n\\n\\n After this recitation, through an interpreter, Grimon agreed that the\\n\\ngovernment’s recitation of the facts was correct and that it could prove those facts\\n\\nat trial. Grimon also confirmed that she had read and discussed the factual proffer\\n\\nwith her attorney before signing it. Grimon’s attorney stated that he was bilingual\\n\\nand was able to translate the factual proffer into Spanish for Grimon, that he\\n\\nexplained the factual proffer to her, and that he was confident she understood its\\n\\ncontents.\\n\\n Grimon pled guilty to Counts 1 and 2, and the district court accepted her\\n\\nplea. The district court found that Grimon was “fully competent and capable of\\n\\nentering an informed plea” and that “her pleas of guilty [were] knowing and\\n\\nvoluntary pleas supported by an independent basis in fact containing each of the\\n\\nessential elements of the offenses.”\\n\\nC. Sentence\\n\\n Following a sentencing hearing, the district court sentenced Grimon to 12\\n\\nmonths’ imprisonment on her § 1029(a)(3) access device conviction in Count 1,\\n\\nfollowed by a mandatory consecutive term of 24 months’ imprisonment on her\\n\\n§ 1028A(a)(1) aggravated identity theft conviction in Count 2. Grimon’s total\\n\\nsentence is thus 36 months’ imprisonment. At that time, the district court\\n\\ndismissed Counts 3 and 4 of the indictment.\\n\\n\\n\\n\\n 5\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 6 of 15\\n\\n\\n Grimon now appeals her convictions.1\\n\\n II. DISCUSSION\\n\\n On appeal, Grimon argues that the district court lacked subject matter\\n\\njurisdiction over her offenses because the factual proffer (1) merely stipulated to\\n\\nthe interstate commerce element of her access device offense and (2) did not\\n\\ncontain any underlying facts showing that her possession of counterfeit credit cards\\n\\nand account numbers affected interstate commerce. Grimon stresses that the credit\\n\\ncards were never used.\\n\\n The government responds that its indictment charged Grimon with violating\\n\\na valid federal statute, alleged an offense against the United States and, therefore,\\n\\ninvoked the district court’s subject matter jurisdiction. The government argues that\\n\\neven if Grimon’s stipulation—that her conduct affected interstate commerce—was\\n\\nan insufficient factual basis for the interstate commerce element of her offense, that\\n\\ndid not deprive the district court of subject matter jurisdiction to accept her plea.\\n\\n Whether the district court had “subject matter jurisdiction is a question of\\n\\nlaw that we review de novo even when raised for the first time on appeal.” United\\n\\nStates v. Iguaran, 821 F.3d 1335, 1336 (11th Cir. 2016).\\n\\nA. Subject Matter Jurisdiction\\n\\n\\n\\n 1\\n On appeal, Grimon does not challenge the district court’s sentencing guidelines\\ncalculations or the procedural or substantive reasonableness of her sentence.\\n 6\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 7 of 15\\n\\n\\n “Subject matter jurisdiction,” which Congress bestows on the lower federal\\n\\ncourts by statute, “defines the court’s authority to hear a given type of case.”\\n\\nUnited States v. Morton, 467 U.S. 822, 828, 104 S. Ct. 2769, 2773 (1984); United\\n\\nStates v. Brown, 752 F.3d 1344, 1348 (11th Cir. 2014). In the context of federal\\n\\ncrimes, Congress has granted federal district courts original jurisdiction “of all\\n\\noffenses against the laws of the United States.” Brown, 752 F.3d at 1348; 18\\n\\nU.S.C. § 3231. As such, “[s]o long as the indictment charges the defendant with\\n\\nviolating a valid federal statute as enacted in the United States Code, it alleges ‘an\\n\\noffense against the laws of the United States,’ and, thereby, invokes the district\\n\\ncourt’s subject-matter jurisdiction.” Brown, 752 F.3d at 1354; see also Alikhani v.\\n\\nUnited States, 200 F.3d 732, 734–35 (11th Cir. 2000). An effect on interstate\\n\\ncommerce may be required for Congress to have authority under the Commerce\\n\\nClause to forbid the conduct and make it a federal crime in the first place. United\\n\\nStates v. Lopez, 514 U.S. 549, 562, 115 S. Ct. 1624, 1631 (1995). But if an\\n\\nindictment itself alleges a violation of a valid federal statute, the district court has\\n\\nsubject matter jurisdiction of that case.\\n\\n In contrast to subject matter jurisdiction, some federal statutes do contain\\n\\nwhat is referred to as a “jurisdictional element”—that is, an element of the offense\\n\\nrequiring the government to prove that the defendant’s offense had some nexus\\n\\nwith interstate or foreign commerce. See, e.g., United States v. Suarez, 893 F.3d\\n\\n\\n 7\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 8 of 15\\n\\n\\n1330, 1333 (11th Cir. 2018) (“This statute contains a jurisdictional element—the\\n\\noffense, in the case of an attempt, ‘would have affected interstate or foreign\\n\\ncommerce.’” (quoting 18 U.S.C. § 2332a(a)(2)(D))). In this very case,\\n\\n§ 1029(a)(3), under which Grimon was convicted in Count 1, contains such an\\n\\ninterstate commerce element. 18 U.S.C. § 1029(a)(3). Specifically, § 1029(a)(3)\\n\\nprovides that whoever “knowingly and with intent to defraud possesses fifteen or\\n\\nmore devices which are counterfeit or unauthorized access devices . . . shall, if the\\n\\noffense affects interstate or foreign commerce, be punished as provided in\\n\\nsubsection (c) of this section.” Id. (emphasis added).\\n\\n Nonetheless, interstate commerce jurisdictional elements, such as\\n\\n§ 1029(a)(3)’s, are not “jurisdictional” in the sense of bearing on whether or not\\n\\nthe district court has subject matter jurisdiction or authority to adjudicate the case.\\n\\nSee Alikhani, 200 F.3d at 735. Rather, the interstate commerce element is\\n\\n“jurisdictional” only in the sense that it relates to the power of Congress to regulate\\n\\nthe forbidden conduct. See id.; see also Lopez, 514 U.S. at 561-62, 115 S. Ct. at\\n\\n1631 (indicating that interstate commerce elements are meant to limit the reach of\\n\\nfederal statutes to ensure the conduct they regulate falls within Congress’s\\n\\nCommerce Clause powers).\\n\\n This Court has therefore explained that, when it comes to federal criminal\\n\\nstatutes requiring an interstate commerce nexus, the government’s failure to\\n\\n\\n 8\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 9 of 15\\n\\n\\nsufficiently allege or prove the interstate commerce element does not deprive the\\n\\ndistrict court of its subject matter jurisdiction over the criminal case. Alikhani, 200\\n\\nF.3d at 735. This Court in Alikhani reasoned that, while “[a]n effect on interstate\\n\\ncommerce may be required for Congress to have authority under the Commerce\\n\\nClause to forbid certain conduct,” that “does not imply that a district court faced\\n\\nwith an insufficient interstate-commerce nexus loses subject-matter jurisdiction of\\n\\nthe case.” Id. Stated differently, even if an indictment fails to allege sufficient\\n\\nfacts to support, or the government does not present sufficient evidence to prove,\\n\\nan interstate commerce nexus, the district court still has subject matter jurisdiction\\n\\nto adjudicate the case under § 3231, including, for example, the power to dismiss\\n\\nthe indictment for failure to allege facts showing the defendant committed the\\n\\ncharged offense. See id.; see also Brown, 752 F.3d at 1348-49 (discussing\\n\\nAlikhani).\\n\\n Here, Grimon makes the same argument this Court explicitly rejected in\\n\\nAlikhani. Grimon asserts that because her stipulated factual proffer merely stated\\n\\nthat her § 1029(a)(3) offense affected interstate commerce, without providing\\n\\nsupporting facts to explain how her conduct affected interstate commerce, the\\n\\ndistrict court lacked subject matter jurisdiction over her case. But as this Court\\n\\nexplained in Alikhani, the government’s alleged failure to sufficiently establish an\\n\\ninterstate commerce nexus does not deprive the district court of its subject matter\\n\\n\\n 9\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 10 of 15\\n\\n\\njurisdiction under § 3231. See Alikhani, 200 F.3d at 735. All that was required for\\n\\nthe district court to exercise subject matter jurisdiction over Grimon’s case was an\\n\\nindictment charging her with a violation of a valid federal law enacted in the\\n\\nUnited States Code, and the indictment here did just that. See Brown, 752 F.3d at\\n\\n1354. The indictment tracked the statutory language in § 1029(a)(3), charging that\\n\\nGrimon:\\n\\n did knowingly, and with intent to defraud, possess fifteen (15) or more\\n counterfeit and unauthorized access devices, that is, counterfeit credit\\n cards encoded with account numbers issued to other persons and credit\\n card account numbers issued to other persons, said conduct affecting\\n interstate and foreign commerce, in violation of Title 18, United States\\n Code, Sections 1029(a)(3) and 2.\\n\\nWhether that indictment sufficiently alleged, or Grimon’s subsequent factual\\n\\nproffer sufficiently demonstrated, an interstate nexus is merely a non-jurisdictional\\n\\nchallenge to the sufficiency of the evidence as to that element of the offense and\\n\\nhas no bearing on the district court’s power to adjudicate her case or subject matter\\n\\njurisdiction. See Alikhani, 200 F.3d at 735. Thus, we reject Grimon’s claim that\\n\\nthe district court lacked subject matter jurisdiction to accept her plea.\\n\\nB. Iguaran\\n\\n We recognize that Grimon relies on this Court’s decision in United States v.\\n\\nIguaran, 821 F.3d 1335 (11th Cir. 2016). But as we explain below, that reliance is\\n\\nmisplaced. Iguaran dealt with a wholly different statutory scheme, which, unlike\\n\\n§ 1029(a)(3), specifically requires the district court to make a preliminary\\n 10\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 11 of 15\\n\\n\\ndetermination regarding subject matter jurisdiction—not just an interstate\\n\\ncommerce “jurisdictional element”—before proceeding with a case.\\n\\n In Iguaran, the defendant pled guilty to a cocaine conspiracy offense under\\n\\nthe Maritime Drug Law Enforcement Act (“MDLEA”). Id. at 1336. Among other\\n\\nthings, the statutory text of the MDLEA “makes it a crime to conspire to distribute\\n\\na controlled substance while on board ‘a vessel subject to the jurisdiction of the\\n\\nUnited States.’” Id. (quoting 46 U.S.C. §§ 70503(a)(1), 70506(b)). Unlike the\\n\\ninterstate commerce element in § 1029(a)(3), this “vessel subject to the jurisdiction\\n\\nof the United States” requirement in the MDLEA is “jurisdictional” in the true,\\n\\nsubject matter jurisdiction sense of the word. See id. Specifically, the MDLEA\\n\\nexpressly states that “‘[j]urisdiction of the United States with respect to a vessel\\n\\nsubject to this chapter is not an element of an offense.’” Id. (quoting 46 U.S.C.\\n\\n§ 70504(a)). Instead, “‘[j]urisdictional issues arising under this chapter are\\n\\npreliminary questions of law to be determined solely by the trial judge.’” Id.\\n\\n(quoting 46 U.S.C. § 70504(a)).\\n\\n In light of this statutory language in the MDLEA, this Court has “interpreted\\n\\nthe on board a vessel subject to the jurisdiction of the United States” provision “as\\n\\na congressionally imposed limit on courts’ subject matter jurisdiction, akin to the\\n\\namount-in-controversy requirement contained in 28 U.S.C. § 1332.” Id. (internal\\n\\nquotation marks and citation omitted). Consequently, for a district court to have\\n\\n\\n 11\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 12 of 15\\n\\n\\nadjudicatory authority over a charge that the defendant conspired to violate a\\n\\nsubstantive crime defined in the MDLEA, the government must make a\\n\\npreliminary showing that the vessel was, when apprehended, subject to the\\n\\njurisdiction of the United States. Id.\\n\\n In Iguaran, this Court vacated the defendant’s guilty plea because the district\\n\\ncourt did not make any factual findings with respect to its subject matter\\n\\njurisdiction under the MDLEA, and the record contained no facts from which such\\n\\njurisdiction could be determined. See id. at 1337–38. We then remanded the case\\n\\nto the district court for the limited purpose of determining whether subject matter\\n\\njurisdiction existed, after affording both parties an opportunity to present evidence\\n\\nbearing on whether Iguaran’s vessel was subject to the jurisdiction of the United\\n\\nStates. Id. at 1338.\\n\\n Though Grimon is correct that this Court held in Iguaran that parties may not\\n\\nstipulate to jurisdiction, but rather only to underlying facts that bear on the\\n\\njurisdictional inquiry, that holding is simply irrelevant to her case. Id. at 1337.\\n\\nIguaran involved the MDLEA, where the statutory text made clear that\\n\\n“jurisdiction” is not merely an element of the offense. See id. at 1336\\n\\n(“‘Jurisdiction of the United States with respect to a vessel subject to this chapter is\\n\\nnot an element of an offense.’” (emphasis added) (quoting 46 U.S.C. § 70504(a))).\\n\\nIguaran, as explained above, dealt with a statutory requirement that was truly\\n\\n\\n 12\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 13 of 15\\n\\n\\n“jurisdictional”—that is, without facts showing that Iguaran’s vessel was subject to\\n\\nthe jurisdiction of the United States, the district court in that case had no authority\\n\\nto adjudicate his case. Id.\\n\\n Here, by contrast, § 1029(a)(3) did not require the district court to determine\\n\\nthat Grimon’s offense affected interstate commerce to have subject matter\\n\\njurisdiction. See 18 U.S.C. § 1029(a)(3). Rather, the interstate nexus requirement\\n\\nwas simply one of several elements of Grimon’s § 1029(a)(3) offense that the\\n\\ngovernment had to prove. See id.; United States v. Klopf, 423 F.3d 1228, 1240\\n\\n(11th Cir. 2005) (indicating that an effect on interstate or foreign commerce is an\\n\\nelement for offenses under § 1029(a)). Neither Iguaran nor any other case cited by\\n\\nGrimon has held that this interstate nexus requirement is akin to the amount in\\n\\ncontroversy requirement in 28 U.S.C. § 1332 or to the jurisdictional requirement in\\n\\nthe MDLEA. And we squarely hold that it is not. So, whether the government\\n\\nproved the interstate commerce nexus or failed to prove it, the district court still\\n\\nhad subject matter jurisdiction over Grimon’s case and her Count 1 conviction.\\n\\nSee Alikhani, 200 F.3d at 735.\\n\\n As to her aggravated identity theft conviction in Count 2, Grimon’s statute\\n\\nof conviction, 18 U.S.C. § 1028A(a)(1), itself does not contain an interstate\\n\\ncommerce element. See 18 U.S.C. § 1028A. However, because a conviction\\n\\nunder § 1028A is predicated on the unlawful transfer, possession, or use of a\\n\\n\\n 13\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 14 of 15\\n\\n\\nmeans of identification “during and in relation to [an enumerated] felony\\n\\nviolation,” Grimon argues that, if the district court lacked subject matter\\n\\njurisdiction over the § 1029(a)(3) offense in Count 1, it likewise lacked subject\\n\\nmatter jurisdiction over the § 1028A(a)(1) offense in Count 2. For the reasons\\n\\nstated above, we reject Grimon’s jurisdiction claim as to Count 2 as well.\\n\\nC. No Other Claim\\n\\n As a final matter, Grimon’s brief on appeal did not raise any error or\\n\\nargument other than the subject matter jurisdictional one addressed above. More\\n\\nspecifically, as the government points out, Grimon has not raised on appeal, and\\n\\nhas therefore abandoned, any claim or argument that the alleged insufficiency of\\n\\nthe factual proffer as to the interstate commerce element violated Federal Rule of\\n\\nCriminal Procedure 11 or rendered her plea unknowing or involuntary. See United\\n\\nStates v. Jernigan, 341 F.3d 1273, 1283 n.8 (11th Cir. 2003) (explaining that issues\\n\\nnot raised on appeal are deemed abandoned).\\n\\n Accordingly, we do not address whether any alleged insufficiency in\\n\\nGrimon’s factual proffer as to the interstate commerce element of her § 1029(a)(3)\\n\\noffense invalidated her guilty plea. Because Grimon has raised no claim of Rule\\n\\n11 error, we also do not address the government’s argument that the doctrine of\\n\\ninvited error applies because Grimon agreed in her factual proffer that the\\n\\n\\n\\n\\n 14\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 15 of 15\\n\\n\\ngovernment could have established at trial that her conduct affected interstate or\\n\\nforeign commerce.\\n\\n III. CONCLUSION\\n\\n For the foregoing reasons, we affirm Grimon’s two convictions.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 15\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4397094/\", \"author_raw\": \"HULL, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"MARCUS"},"judge2":{"kind":"string","value":"GRANT"},"judge3":{"kind":"string","value":"HULL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"MARCUS\": \", Circuit\", \"GRANT\": \", Circuit\", \"HULL\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4619841/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. Isabel Yero Grimon\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-13\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-15011 Date Filed: 05/13/2019 Page: 1 of 15\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-15011\n ________________________\n\n D.C. Docket No. 1:17-cr-20221-JEM-1\n\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff-Appellee,\n\n versus\n\nISABEL YERO GRIMON,\n\n Defendant-Appellant.\n\n ________________________\n\n Appeal from the United States District Court\n for the Southern District of Florida\n ________________________\n\n (May 13, 2019)\n\nBefore MARCUS, GRANT and HULL, Circuit Judges.\n\nHULL, Circuit Judge:\n\n After pleading guilty, Isabel Yero Grimon appeals her convictions for\n\npossessing 15 or more unauthorized access devices and aggravated identity theft.\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 2 of 15\n\n\nDefendant Grimon argues that the factual proffer supporting her guilty plea was\n\ninsufficient to establish that the unauthorized access devices she possessed affected\n\ninterstate commerce and, therefore, the district court lacked subject matter\n\njurisdiction. The question presented is whether the district court has subject matter\n\njurisdiction over a criminal case to accept a guilty plea where: (1) the indictment\n\ncharges a violation of a valid federal criminal statute and sets forth the interstate\n\ncommerce element of the crime; (2) the factual proffer for the guilty plea states the\n\ngovernment at trial would prove that the defendant’s conduct affected interstate\n\ncommerce; but (3) the factual proffer does not contain any underlying facts\n\nexplaining how the interstate commerce nexus was satisfied.\n\n After review, and with the benefit of oral argument, we conclude that the\n\ninterstate commerce element in § 1029(a)(3) is not “jurisdictional” in the sense of\n\nbearing on whether the district court has subject matter jurisdiction to adjudicate a\n\ncase, and thus the government’s alleged failure to prove sufficiently the interstate\n\ncommerce nexus does not deprive the district court of its subject matter jurisdiction\n\nover Grimon’s criminal case. Thus, we affirm Grimon’s convictions.\n\n I. BACKGROUND\n\nA. Arrest\n\n On January 18, 2017, officers conducted a traffic stop of Grimon’s vehicle\n\nafter observing her swerving between lanes and determining, through a records\n\n\n 2\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 3 of 15\n\n\ncheck, that there was an active warrant for her arrest out of Texas. Grimon was\n\narrested on the active warrant, and officers conducted a search incident to that\n\narrest.\n\n During the search, officers found 19 blank credit cards in Grimon’s vehicle,\n\n16 of which were encoded with account numbers issued to 10 other persons.\n\nOfficers also recovered a thumb drive from Grimon, which contained 134 credit\n\ncard account numbers issued to other persons. Grimon admitted that (1) she knew\n\nthe blank cards were re-encoded with credit card account numbers issued to other\n\npersons, (2) the credit card numbers on the thumb drive did not belong to her, and\n\n(3) she was not authorized to possess those account numbers by their owners.\n\nB. Indictment and Plea\n\n In March 2017, a federal grand jury charged Grimon with (1) one count of\n\npossession of 15 or more unauthorized access devices, in violation of 18 U.S.C.\n\n§ 1029(a)(3) (Count 1), and (2) three counts of aggravated identity theft, in\n\nviolation of 18 U.S.C. § 1028A(a)(1) (Counts 2-4). Count 1 specifically charged\n\nthat Grimon knowingly, and with intent to defraud, possessed 15 or more\n\nunauthorized access devices and that “said conduct affect[ed] interstate and foreign\n\ncommerce.”\n\n In July 2017, pursuant to a written plea agreement, Grimon pled guilty to\n\nCounts 1 and 2 of the indictment, and the government agreed to dismiss Counts 3\n\n\n 3\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 4 of 15\n\n\nand 4. In connection with her plea agreement, Grimon executed a factual proffer\n\ndetailing the offense conduct described above. As to all of the elements of Count\n\n1, Grimon’s factual proffer stated that, had the case gone to trial, the government\n\nwould have proved beyond a reasonable doubt that Grimon “did knowingly, and\n\nwith intent to defraud, possess fifteen (15) or more devices which are counterfeit\n\nand unauthorized access devices, said conduct affecting interstate and foreign\n\ncommerce.”\n\n At the change of plea hearing, Grimon confirmed, through an interpreter,\n\nthat she received a copy of the indictment and had an opportunity to fully discuss\n\nthe charges with her attorney. The government summarized the charges in Counts\n\n1 and 2. In doing so, the government explicitly stated with respect to Count 1 that\n\none of the elements of the offense “is that the Defendant’s conduct in some way\n\naffected commerce between one state and other states or between a state of the\n\nUnited States and a foreign country.” Grimon then confirmed that she understood\n\nthe charges to which she was pleading guilty. The government also read the\n\nfactual proffer into the record. That proffer included a stipulation that the\n\ngovernment would have proven at trial that Grimon “did knowingly and with intent\n\nto defraud, possess 15 or more devices which are counterfeit and unauthorized\n\naccess devices, said conduct affecting interstate and foreign commerce.”\n\n\n\n\n 4\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 5 of 15\n\n\n After this recitation, through an interpreter, Grimon agreed that the\n\ngovernment’s recitation of the facts was correct and that it could prove those facts\n\nat trial. Grimon also confirmed that she had read and discussed the factual proffer\n\nwith her attorney before signing it. Grimon’s attorney stated that he was bilingual\n\nand was able to translate the factual proffer into Spanish for Grimon, that he\n\nexplained the factual proffer to her, and that he was confident she understood its\n\ncontents.\n\n Grimon pled guilty to Counts 1 and 2, and the district court accepted her\n\nplea. The district court found that Grimon was “fully competent and capable of\n\nentering an informed plea” and that “her pleas of guilty [were] knowing and\n\nvoluntary pleas supported by an independent basis in fact containing each of the\n\nessential elements of the offenses.”\n\nC. Sentence\n\n Following a sentencing hearing, the district court sentenced Grimon to 12\n\nmonths’ imprisonment on her § 1029(a)(3) access device conviction in Count 1,\n\nfollowed by a mandatory consecutive term of 24 months’ imprisonment on her\n\n§ 1028A(a)(1) aggravated identity theft conviction in Count 2. Grimon’s total\n\nsentence is thus 36 months’ imprisonment. At that time, the district court\n\ndismissed Counts 3 and 4 of the indictment.\n\n\n\n\n 5\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 6 of 15\n\n\n Grimon now appeals her convictions.1\n\n II. DISCUSSION\n\n On appeal, Grimon argues that the district court lacked subject matter\n\njurisdiction over her offenses because the factual proffer (1) merely stipulated to\n\nthe interstate commerce element of her access device offense and (2) did not\n\ncontain any underlying facts showing that her possession of counterfeit credit cards\n\nand account numbers affected interstate commerce. Grimon stresses that the credit\n\ncards were never used.\n\n The government responds that its indictment charged Grimon with violating\n\na valid federal statute, alleged an offense against the United States and, therefore,\n\ninvoked the district court’s subject matter jurisdiction. The government argues that\n\neven if Grimon’s stipulation—that her conduct affected interstate commerce—was\n\nan insufficient factual basis for the interstate commerce element of her offense, that\n\ndid not deprive the district court of subject matter jurisdiction to accept her plea.\n\n Whether the district court had “subject matter jurisdiction is a question of\n\nlaw that we review de novo even when raised for the first time on appeal.” United\n\nStates v. Iguaran, 821 F.3d 1335, 1336 (11th Cir. 2016).\n\nA. Subject Matter Jurisdiction\n\n\n\n 1\n On appeal, Grimon does not challenge the district court’s sentencing guidelines\ncalculations or the procedural or substantive reasonableness of her sentence.\n 6\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 7 of 15\n\n\n “Subject matter jurisdiction,” which Congress bestows on the lower federal\n\ncourts by statute, “defines the court’s authority to hear a given type of case.”\n\nUnited States v. Morton, 467 U.S. 822, 828, 104 S. Ct. 2769, 2773 (1984); United\n\nStates v. Brown, 752 F.3d 1344, 1348 (11th Cir. 2014). In the context of federal\n\ncrimes, Congress has granted federal district courts original jurisdiction “of all\n\noffenses against the laws of the United States.” Brown, 752 F.3d at 1348; 18\n\nU.S.C. § 3231. As such, “[s]o long as the indictment charges the defendant with\n\nviolating a valid federal statute as enacted in the United States Code, it alleges ‘an\n\noffense against the laws of the United States,’ and, thereby, invokes the district\n\ncourt’s subject-matter jurisdiction.” Brown, 752 F.3d at 1354; see also Alikhani v.\n\nUnited States, 200 F.3d 732, 734–35 (11th Cir. 2000). An effect on interstate\n\ncommerce may be required for Congress to have authority under the Commerce\n\nClause to forbid the conduct and make it a federal crime in the first place. United\n\nStates v. Lopez, 514 U.S. 549, 562, 115 S. Ct. 1624, 1631 (1995). But if an\n\nindictment itself alleges a violation of a valid federal statute, the district court has\n\nsubject matter jurisdiction of that case.\n\n In contrast to subject matter jurisdiction, some federal statutes do contain\n\nwhat is referred to as a “jurisdictional element”—that is, an element of the offense\n\nrequiring the government to prove that the defendant’s offense had some nexus\n\nwith interstate or foreign commerce. See, e.g., United States v. Suarez, 893 F.3d\n\n\n 7\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 8 of 15\n\n\n1330, 1333 (11th Cir. 2018) (“This statute contains a jurisdictional element—the\n\noffense, in the case of an attempt, ‘would have affected interstate or foreign\n\ncommerce.’” (quoting 18 U.S.C. § 2332a(a)(2)(D))). In this very case,\n\n§ 1029(a)(3), under which Grimon was convicted in Count 1, contains such an\n\ninterstate commerce element. 18 U.S.C. § 1029(a)(3). Specifically, § 1029(a)(3)\n\nprovides that whoever “knowingly and with intent to defraud possesses fifteen or\n\nmore devices which are counterfeit or unauthorized access devices . . . shall, if the\n\noffense affects interstate or foreign commerce, be punished as provided in\n\nsubsection (c) of this section.” Id. (emphasis added).\n\n Nonetheless, interstate commerce jurisdictional elements, such as\n\n§ 1029(a)(3)’s, are not “jurisdictional” in the sense of bearing on whether or not\n\nthe district court has subject matter jurisdiction or authority to adjudicate the case.\n\nSee Alikhani, 200 F.3d at 735. Rather, the interstate commerce element is\n\n“jurisdictional” only in the sense that it relates to the power of Congress to regulate\n\nthe forbidden conduct. See id.; see also Lopez, 514 U.S. at 561-62, 115 S. Ct. at\n\n1631 (indicating that interstate commerce elements are meant to limit the reach of\n\nfederal statutes to ensure the conduct they regulate falls within Congress’s\n\nCommerce Clause powers).\n\n This Court has therefore explained that, when it comes to federal criminal\n\nstatutes requiring an interstate commerce nexus, the government’s failure to\n\n\n 8\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 9 of 15\n\n\nsufficiently allege or prove the interstate commerce element does not deprive the\n\ndistrict court of its subject matter jurisdiction over the criminal case. Alikhani, 200\n\nF.3d at 735. This Court in Alikhani reasoned that, while “[a]n effect on interstate\n\ncommerce may be required for Congress to have authority under the Commerce\n\nClause to forbid certain conduct,” that “does not imply that a district court faced\n\nwith an insufficient interstate-commerce nexus loses subject-matter jurisdiction of\n\nthe case.” Id. Stated differently, even if an indictment fails to allege sufficient\n\nfacts to support, or the government does not present sufficient evidence to prove,\n\nan interstate commerce nexus, the district court still has subject matter jurisdiction\n\nto adjudicate the case under § 3231, including, for example, the power to dismiss\n\nthe indictment for failure to allege facts showing the defendant committed the\n\ncharged offense. See id.; see also Brown, 752 F.3d at 1348-49 (discussing\n\nAlikhani).\n\n Here, Grimon makes the same argument this Court explicitly rejected in\n\nAlikhani. Grimon asserts that because her stipulated factual proffer merely stated\n\nthat her § 1029(a)(3) offense affected interstate commerce, without providing\n\nsupporting facts to explain how her conduct affected interstate commerce, the\n\ndistrict court lacked subject matter jurisdiction over her case. But as this Court\n\nexplained in Alikhani, the government’s alleged failure to sufficiently establish an\n\ninterstate commerce nexus does not deprive the district court of its subject matter\n\n\n 9\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 10 of 15\n\n\njurisdiction under § 3231. See Alikhani, 200 F.3d at 735. All that was required for\n\nthe district court to exercise subject matter jurisdiction over Grimon’s case was an\n\nindictment charging her with a violation of a valid federal law enacted in the\n\nUnited States Code, and the indictment here did just that. See Brown, 752 F.3d at\n\n1354. The indictment tracked the statutory language in § 1029(a)(3), charging that\n\nGrimon:\n\n did knowingly, and with intent to defraud, possess fifteen (15) or more\n counterfeit and unauthorized access devices, that is, counterfeit credit\n cards encoded with account numbers issued to other persons and credit\n card account numbers issued to other persons, said conduct affecting\n interstate and foreign commerce, in violation of Title 18, United States\n Code, Sections 1029(a)(3) and 2.\n\nWhether that indictment sufficiently alleged, or Grimon’s subsequent factual\n\nproffer sufficiently demonstrated, an interstate nexus is merely a non-jurisdictional\n\nchallenge to the sufficiency of the evidence as to that element of the offense and\n\nhas no bearing on the district court’s power to adjudicate her case or subject matter\n\njurisdiction. See Alikhani, 200 F.3d at 735. Thus, we reject Grimon’s claim that\n\nthe district court lacked subject matter jurisdiction to accept her plea.\n\nB. Iguaran\n\n We recognize that Grimon relies on this Court’s decision in United States v.\n\nIguaran, 821 F.3d 1335 (11th Cir. 2016). But as we explain below, that reliance is\n\nmisplaced. Iguaran dealt with a wholly different statutory scheme, which, unlike\n\n§ 1029(a)(3), specifically requires the district court to make a preliminary\n 10\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 11 of 15\n\n\ndetermination regarding subject matter jurisdiction—not just an interstate\n\ncommerce “jurisdictional element”—before proceeding with a case.\n\n In Iguaran, the defendant pled guilty to a cocaine conspiracy offense under\n\nthe Maritime Drug Law Enforcement Act (“MDLEA”). Id. at 1336. Among other\n\nthings, the statutory text of the MDLEA “makes it a crime to conspire to distribute\n\na controlled substance while on board ‘a vessel subject to the jurisdiction of the\n\nUnited States.’” Id. (quoting 46 U.S.C. §§ 70503(a)(1), 70506(b)). Unlike the\n\ninterstate commerce element in § 1029(a)(3), this “vessel subject to the jurisdiction\n\nof the United States” requirement in the MDLEA is “jurisdictional” in the true,\n\nsubject matter jurisdiction sense of the word. See id. Specifically, the MDLEA\n\nexpressly states that “‘[j]urisdiction of the United States with respect to a vessel\n\nsubject to this chapter is not an element of an offense.’” Id. (quoting 46 U.S.C.\n\n§ 70504(a)). Instead, “‘[j]urisdictional issues arising under this chapter are\n\npreliminary questions of law to be determined solely by the trial judge.’” Id.\n\n(quoting 46 U.S.C. § 70504(a)).\n\n In light of this statutory language in the MDLEA, this Court has “interpreted\n\nthe on board a vessel subject to the jurisdiction of the United States” provision “as\n\na congressionally imposed limit on courts’ subject matter jurisdiction, akin to the\n\namount-in-controversy requirement contained in 28 U.S.C. § 1332.” Id. (internal\n\nquotation marks and citation omitted). Consequently, for a district court to have\n\n\n 11\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 12 of 15\n\n\nadjudicatory authority over a charge that the defendant conspired to violate a\n\nsubstantive crime defined in the MDLEA, the government must make a\n\npreliminary showing that the vessel was, when apprehended, subject to the\n\njurisdiction of the United States. Id.\n\n In Iguaran, this Court vacated the defendant’s guilty plea because the district\n\ncourt did not make any factual findings with respect to its subject matter\n\njurisdiction under the MDLEA, and the record contained no facts from which such\n\njurisdiction could be determined. See id. at 1337–38. We then remanded the case\n\nto the district court for the limited purpose of determining whether subject matter\n\njurisdiction existed, after affording both parties an opportunity to present evidence\n\nbearing on whether Iguaran’s vessel was subject to the jurisdiction of the United\n\nStates. Id. at 1338.\n\n Though Grimon is correct that this Court held in Iguaran that parties may not\n\nstipulate to jurisdiction, but rather only to underlying facts that bear on the\n\njurisdictional inquiry, that holding is simply irrelevant to her case. Id. at 1337.\n\nIguaran involved the MDLEA, where the statutory text made clear that\n\n“jurisdiction” is not merely an element of the offense. See id. at 1336\n\n(“‘Jurisdiction of the United States with respect to a vessel subject to this chapter is\n\nnot an element of an offense.’” (emphasis added) (quoting 46 U.S.C. § 70504(a))).\n\nIguaran, as explained above, dealt with a statutory requirement that was truly\n\n\n 12\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 13 of 15\n\n\n“jurisdictional”—that is, without facts showing that Iguaran’s vessel was subject to\n\nthe jurisdiction of the United States, the district court in that case had no authority\n\nto adjudicate his case. Id.\n\n Here, by contrast, § 1029(a)(3) did not require the district court to determine\n\nthat Grimon’s offense affected interstate commerce to have subject matter\n\njurisdiction. See 18 U.S.C. § 1029(a)(3). Rather, the interstate nexus requirement\n\nwas simply one of several elements of Grimon’s § 1029(a)(3) offense that the\n\ngovernment had to prove. See id.; United States v. Klopf, 423 F.3d 1228, 1240\n\n(11th Cir. 2005) (indicating that an effect on interstate or foreign commerce is an\n\nelement for offenses under § 1029(a)). Neither Iguaran nor any other case cited by\n\nGrimon has held that this interstate nexus requirement is akin to the amount in\n\ncontroversy requirement in 28 U.S.C. § 1332 or to the jurisdictional requirement in\n\nthe MDLEA. And we squarely hold that it is not. So, whether the government\n\nproved the interstate commerce nexus or failed to prove it, the district court still\n\nhad subject matter jurisdiction over Grimon’s case and her Count 1 conviction.\n\nSee Alikhani, 200 F.3d at 735.\n\n As to her aggravated identity theft conviction in Count 2, Grimon’s statute\n\nof conviction, 18 U.S.C. § 1028A(a)(1), itself does not contain an interstate\n\ncommerce element. See 18 U.S.C. § 1028A. However, because a conviction\n\nunder § 1028A is predicated on the unlawful transfer, possession, or use of a\n\n\n 13\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 14 of 15\n\n\nmeans of identification “during and in relation to [an enumerated] felony\n\nviolation,” Grimon argues that, if the district court lacked subject matter\n\njurisdiction over the § 1029(a)(3) offense in Count 1, it likewise lacked subject\n\nmatter jurisdiction over the § 1028A(a)(1) offense in Count 2. For the reasons\n\nstated above, we reject Grimon’s jurisdiction claim as to Count 2 as well.\n\nC. No Other Claim\n\n As a final matter, Grimon’s brief on appeal did not raise any error or\n\nargument other than the subject matter jurisdictional one addressed above. More\n\nspecifically, as the government points out, Grimon has not raised on appeal, and\n\nhas therefore abandoned, any claim or argument that the alleged insufficiency of\n\nthe factual proffer as to the interstate commerce element violated Federal Rule of\n\nCriminal Procedure 11 or rendered her plea unknowing or involuntary. See United\n\nStates v. Jernigan, 341 F.3d 1273, 1283 n.8 (11th Cir. 2003) (explaining that issues\n\nnot raised on appeal are deemed abandoned).\n\n Accordingly, we do not address whether any alleged insufficiency in\n\nGrimon’s factual proffer as to the interstate commerce element of her § 1029(a)(3)\n\noffense invalidated her guilty plea. Because Grimon has raised no claim of Rule\n\n11 error, we also do not address the government’s argument that the doctrine of\n\ninvited error applies because Grimon agreed in her factual proffer that the\n\n\n\n\n 14\n\f Case: 17-15011 Date Filed: 05/13/2019 Page: 15 of 15\n\n\ngovernment could have established at trial that her conduct affected interstate or\n\nforeign commerce.\n\n III. CONCLUSION\n\n For the foregoing reasons, we affirm Grimon’s two convictions.\n\n AFFIRMED.\n\n\n\n\n 15\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Isabel Yero Grimon\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-13\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-15011 Date Filed: 05/13/2019 Page: 1 of 15\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15011\\n ________________________\\n\\n D.C. Docket No. 1:17-cr-20221-JEM-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellee,\\n\\n versus\\n\\nISABEL YERO GRIMON,\\n\\n Defendant-Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 13, 2019)\\n\\nBefore MARCUS, GRANT and HULL, Circuit Judges.\\n\\nHULL, Circuit Judge:\\n\\n After pleading guilty, Isabel Yero Grimon appeals her convictions for\\n\\npossessing 15 or more unauthorized access devices and aggravated identity theft.\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 2 of 15\\n\\n\\nDefendant Grimon argues that the factual proffer supporting her guilty plea was\\n\\ninsufficient to establish that the unauthorized access devices she possessed affected\\n\\ninterstate commerce and, therefore, the district court lacked subject matter\\n\\njurisdiction. The question presented is whether the district court has subject matter\\n\\njurisdiction over a criminal case to accept a guilty plea where: (1) the indictment\\n\\ncharges a violation of a valid federal criminal statute and sets forth the interstate\\n\\ncommerce element of the crime; (2) the factual proffer for the guilty plea states the\\n\\ngovernment at trial would prove that the defendant’s conduct affected interstate\\n\\ncommerce; but (3) the factual proffer does not contain any underlying facts\\n\\nexplaining how the interstate commerce nexus was satisfied.\\n\\n After review, and with the benefit of oral argument, we conclude that the\\n\\ninterstate commerce element in § 1029(a)(3) is not “jurisdictional” in the sense of\\n\\nbearing on whether the district court has subject matter jurisdiction to adjudicate a\\n\\ncase, and thus the government’s alleged failure to prove sufficiently the interstate\\n\\ncommerce nexus does not deprive the district court of its subject matter jurisdiction\\n\\nover Grimon’s criminal case. Thus, we affirm Grimon’s convictions.\\n\\n I. BACKGROUND\\n\\nA. Arrest\\n\\n On January 18, 2017, officers conducted a traffic stop of Grimon’s vehicle\\n\\nafter observing her swerving between lanes and determining, through a records\\n\\n\\n 2\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 3 of 15\\n\\n\\ncheck, that there was an active warrant for her arrest out of Texas. Grimon was\\n\\narrested on the active warrant, and officers conducted a search incident to that\\n\\narrest.\\n\\n During the search, officers found 19 blank credit cards in Grimon’s vehicle,\\n\\n16 of which were encoded with account numbers issued to 10 other persons.\\n\\nOfficers also recovered a thumb drive from Grimon, which contained 134 credit\\n\\ncard account numbers issued to other persons. Grimon admitted that (1) she knew\\n\\nthe blank cards were re-encoded with credit card account numbers issued to other\\n\\npersons, (2) the credit card numbers on the thumb drive did not belong to her, and\\n\\n(3) she was not authorized to possess those account numbers by their owners.\\n\\nB. Indictment and Plea\\n\\n In March 2017, a federal grand jury charged Grimon with (1) one count of\\n\\npossession of 15 or more unauthorized access devices, in violation of 18 U.S.C.\\n\\n§ 1029(a)(3) (Count 1), and (2) three counts of aggravated identity theft, in\\n\\nviolation of 18 U.S.C. § 1028A(a)(1) (Counts 2-4). Count 1 specifically charged\\n\\nthat Grimon knowingly, and with intent to defraud, possessed 15 or more\\n\\nunauthorized access devices and that “said conduct affect[ed] interstate and foreign\\n\\ncommerce.”\\n\\n In July 2017, pursuant to a written plea agreement, Grimon pled guilty to\\n\\nCounts 1 and 2 of the indictment, and the government agreed to dismiss Counts 3\\n\\n\\n 3\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 4 of 15\\n\\n\\nand 4. In connection with her plea agreement, Grimon executed a factual proffer\\n\\ndetailing the offense conduct described above. As to all of the elements of Count\\n\\n1, Grimon’s factual proffer stated that, had the case gone to trial, the government\\n\\nwould have proved beyond a reasonable doubt that Grimon “did knowingly, and\\n\\nwith intent to defraud, possess fifteen (15) or more devices which are counterfeit\\n\\nand unauthorized access devices, said conduct affecting interstate and foreign\\n\\ncommerce.”\\n\\n At the change of plea hearing, Grimon confirmed, through an interpreter,\\n\\nthat she received a copy of the indictment and had an opportunity to fully discuss\\n\\nthe charges with her attorney. The government summarized the charges in Counts\\n\\n1 and 2. In doing so, the government explicitly stated with respect to Count 1 that\\n\\none of the elements of the offense “is that the Defendant’s conduct in some way\\n\\naffected commerce between one state and other states or between a state of the\\n\\nUnited States and a foreign country.” Grimon then confirmed that she understood\\n\\nthe charges to which she was pleading guilty. The government also read the\\n\\nfactual proffer into the record. That proffer included a stipulation that the\\n\\ngovernment would have proven at trial that Grimon “did knowingly and with intent\\n\\nto defraud, possess 15 or more devices which are counterfeit and unauthorized\\n\\naccess devices, said conduct affecting interstate and foreign commerce.”\\n\\n\\n\\n\\n 4\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 5 of 15\\n\\n\\n After this recitation, through an interpreter, Grimon agreed that the\\n\\ngovernment’s recitation of the facts was correct and that it could prove those facts\\n\\nat trial. Grimon also confirmed that she had read and discussed the factual proffer\\n\\nwith her attorney before signing it. Grimon’s attorney stated that he was bilingual\\n\\nand was able to translate the factual proffer into Spanish for Grimon, that he\\n\\nexplained the factual proffer to her, and that he was confident she understood its\\n\\ncontents.\\n\\n Grimon pled guilty to Counts 1 and 2, and the district court accepted her\\n\\nplea. The district court found that Grimon was “fully competent and capable of\\n\\nentering an informed plea” and that “her pleas of guilty [were] knowing and\\n\\nvoluntary pleas supported by an independent basis in fact containing each of the\\n\\nessential elements of the offenses.”\\n\\nC. Sentence\\n\\n Following a sentencing hearing, the district court sentenced Grimon to 12\\n\\nmonths’ imprisonment on her § 1029(a)(3) access device conviction in Count 1,\\n\\nfollowed by a mandatory consecutive term of 24 months’ imprisonment on her\\n\\n§ 1028A(a)(1) aggravated identity theft conviction in Count 2. Grimon’s total\\n\\nsentence is thus 36 months’ imprisonment. At that time, the district court\\n\\ndismissed Counts 3 and 4 of the indictment.\\n\\n\\n\\n\\n 5\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 6 of 15\\n\\n\\n Grimon now appeals her convictions.1\\n\\n II. DISCUSSION\\n\\n On appeal, Grimon argues that the district court lacked subject matter\\n\\njurisdiction over her offenses because the factual proffer (1) merely stipulated to\\n\\nthe interstate commerce element of her access device offense and (2) did not\\n\\ncontain any underlying facts showing that her possession of counterfeit credit cards\\n\\nand account numbers affected interstate commerce. Grimon stresses that the credit\\n\\ncards were never used.\\n\\n The government responds that its indictment charged Grimon with violating\\n\\na valid federal statute, alleged an offense against the United States and, therefore,\\n\\ninvoked the district court’s subject matter jurisdiction. The government argues that\\n\\neven if Grimon’s stipulation—that her conduct affected interstate commerce—was\\n\\nan insufficient factual basis for the interstate commerce element of her offense, that\\n\\ndid not deprive the district court of subject matter jurisdiction to accept her plea.\\n\\n Whether the district court had “subject matter jurisdiction is a question of\\n\\nlaw that we review de novo even when raised for the first time on appeal.” United\\n\\nStates v. Iguaran, 821 F.3d 1335, 1336 (11th Cir. 2016).\\n\\nA. Subject Matter Jurisdiction\\n\\n\\n\\n 1\\n On appeal, Grimon does not challenge the district court’s sentencing guidelines\\ncalculations or the procedural or substantive reasonableness of her sentence.\\n 6\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 7 of 15\\n\\n\\n “Subject matter jurisdiction,” which Congress bestows on the lower federal\\n\\ncourts by statute, “defines the court’s authority to hear a given type of case.”\\n\\nUnited States v. Morton, 467 U.S. 822, 828, 104 S. Ct. 2769, 2773 (1984); United\\n\\nStates v. Brown, 752 F.3d 1344, 1348 (11th Cir. 2014). In the context of federal\\n\\ncrimes, Congress has granted federal district courts original jurisdiction “of all\\n\\noffenses against the laws of the United States.” Brown, 752 F.3d at 1348; 18\\n\\nU.S.C. § 3231. As such, “[s]o long as the indictment charges the defendant with\\n\\nviolating a valid federal statute as enacted in the United States Code, it alleges ‘an\\n\\noffense against the laws of the United States,’ and, thereby, invokes the district\\n\\ncourt’s subject-matter jurisdiction.” Brown, 752 F.3d at 1354; see also Alikhani v.\\n\\nUnited States, 200 F.3d 732, 734–35 (11th Cir. 2000). An effect on interstate\\n\\ncommerce may be required for Congress to have authority under the Commerce\\n\\nClause to forbid the conduct and make it a federal crime in the first place. United\\n\\nStates v. Lopez, 514 U.S. 549, 562, 115 S. Ct. 1624, 1631 (1995). But if an\\n\\nindictment itself alleges a violation of a valid federal statute, the district court has\\n\\nsubject matter jurisdiction of that case.\\n\\n In contrast to subject matter jurisdiction, some federal statutes do contain\\n\\nwhat is referred to as a “jurisdictional element”—that is, an element of the offense\\n\\nrequiring the government to prove that the defendant’s offense had some nexus\\n\\nwith interstate or foreign commerce. See, e.g., United States v. Suarez, 893 F.3d\\n\\n\\n 7\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 8 of 15\\n\\n\\n1330, 1333 (11th Cir. 2018) (“This statute contains a jurisdictional element—the\\n\\noffense, in the case of an attempt, ‘would have affected interstate or foreign\\n\\ncommerce.’” (quoting 18 U.S.C. § 2332a(a)(2)(D))). In this very case,\\n\\n§ 1029(a)(3), under which Grimon was convicted in Count 1, contains such an\\n\\ninterstate commerce element. 18 U.S.C. § 1029(a)(3). Specifically, § 1029(a)(3)\\n\\nprovides that whoever “knowingly and with intent to defraud possesses fifteen or\\n\\nmore devices which are counterfeit or unauthorized access devices . . . shall, if the\\n\\noffense affects interstate or foreign commerce, be punished as provided in\\n\\nsubsection (c) of this section.” Id. (emphasis added).\\n\\n Nonetheless, interstate commerce jurisdictional elements, such as\\n\\n§ 1029(a)(3)’s, are not “jurisdictional” in the sense of bearing on whether or not\\n\\nthe district court has subject matter jurisdiction or authority to adjudicate the case.\\n\\nSee Alikhani, 200 F.3d at 735. Rather, the interstate commerce element is\\n\\n“jurisdictional” only in the sense that it relates to the power of Congress to regulate\\n\\nthe forbidden conduct. See id.; see also Lopez, 514 U.S. at 561-62, 115 S. Ct. at\\n\\n1631 (indicating that interstate commerce elements are meant to limit the reach of\\n\\nfederal statutes to ensure the conduct they regulate falls within Congress’s\\n\\nCommerce Clause powers).\\n\\n This Court has therefore explained that, when it comes to federal criminal\\n\\nstatutes requiring an interstate commerce nexus, the government’s failure to\\n\\n\\n 8\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 9 of 15\\n\\n\\nsufficiently allege or prove the interstate commerce element does not deprive the\\n\\ndistrict court of its subject matter jurisdiction over the criminal case. Alikhani, 200\\n\\nF.3d at 735. This Court in Alikhani reasoned that, while “[a]n effect on interstate\\n\\ncommerce may be required for Congress to have authority under the Commerce\\n\\nClause to forbid certain conduct,” that “does not imply that a district court faced\\n\\nwith an insufficient interstate-commerce nexus loses subject-matter jurisdiction of\\n\\nthe case.” Id. Stated differently, even if an indictment fails to allege sufficient\\n\\nfacts to support, or the government does not present sufficient evidence to prove,\\n\\nan interstate commerce nexus, the district court still has subject matter jurisdiction\\n\\nto adjudicate the case under § 3231, including, for example, the power to dismiss\\n\\nthe indictment for failure to allege facts showing the defendant committed the\\n\\ncharged offense. See id.; see also Brown, 752 F.3d at 1348-49 (discussing\\n\\nAlikhani).\\n\\n Here, Grimon makes the same argument this Court explicitly rejected in\\n\\nAlikhani. Grimon asserts that because her stipulated factual proffer merely stated\\n\\nthat her § 1029(a)(3) offense affected interstate commerce, without providing\\n\\nsupporting facts to explain how her conduct affected interstate commerce, the\\n\\ndistrict court lacked subject matter jurisdiction over her case. But as this Court\\n\\nexplained in Alikhani, the government’s alleged failure to sufficiently establish an\\n\\ninterstate commerce nexus does not deprive the district court of its subject matter\\n\\n\\n 9\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 10 of 15\\n\\n\\njurisdiction under § 3231. See Alikhani, 200 F.3d at 735. All that was required for\\n\\nthe district court to exercise subject matter jurisdiction over Grimon’s case was an\\n\\nindictment charging her with a violation of a valid federal law enacted in the\\n\\nUnited States Code, and the indictment here did just that. See Brown, 752 F.3d at\\n\\n1354. The indictment tracked the statutory language in § 1029(a)(3), charging that\\n\\nGrimon:\\n\\n did knowingly, and with intent to defraud, possess fifteen (15) or more\\n counterfeit and unauthorized access devices, that is, counterfeit credit\\n cards encoded with account numbers issued to other persons and credit\\n card account numbers issued to other persons, said conduct affecting\\n interstate and foreign commerce, in violation of Title 18, United States\\n Code, Sections 1029(a)(3) and 2.\\n\\nWhether that indictment sufficiently alleged, or Grimon’s subsequent factual\\n\\nproffer sufficiently demonstrated, an interstate nexus is merely a non-jurisdictional\\n\\nchallenge to the sufficiency of the evidence as to that element of the offense and\\n\\nhas no bearing on the district court’s power to adjudicate her case or subject matter\\n\\njurisdiction. See Alikhani, 200 F.3d at 735. Thus, we reject Grimon’s claim that\\n\\nthe district court lacked subject matter jurisdiction to accept her plea.\\n\\nB. Iguaran\\n\\n We recognize that Grimon relies on this Court’s decision in United States v.\\n\\nIguaran, 821 F.3d 1335 (11th Cir. 2016). But as we explain below, that reliance is\\n\\nmisplaced. Iguaran dealt with a wholly different statutory scheme, which, unlike\\n\\n§ 1029(a)(3), specifically requires the district court to make a preliminary\\n 10\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 11 of 15\\n\\n\\ndetermination regarding subject matter jurisdiction—not just an interstate\\n\\ncommerce “jurisdictional element”—before proceeding with a case.\\n\\n In Iguaran, the defendant pled guilty to a cocaine conspiracy offense under\\n\\nthe Maritime Drug Law Enforcement Act (“MDLEA”). Id. at 1336. Among other\\n\\nthings, the statutory text of the MDLEA “makes it a crime to conspire to distribute\\n\\na controlled substance while on board ‘a vessel subject to the jurisdiction of the\\n\\nUnited States.’” Id. (quoting 46 U.S.C. §§ 70503(a)(1), 70506(b)). Unlike the\\n\\ninterstate commerce element in § 1029(a)(3), this “vessel subject to the jurisdiction\\n\\nof the United States” requirement in the MDLEA is “jurisdictional” in the true,\\n\\nsubject matter jurisdiction sense of the word. See id. Specifically, the MDLEA\\n\\nexpressly states that “‘[j]urisdiction of the United States with respect to a vessel\\n\\nsubject to this chapter is not an element of an offense.’” Id. (quoting 46 U.S.C.\\n\\n§ 70504(a)). Instead, “‘[j]urisdictional issues arising under this chapter are\\n\\npreliminary questions of law to be determined solely by the trial judge.’” Id.\\n\\n(quoting 46 U.S.C. § 70504(a)).\\n\\n In light of this statutory language in the MDLEA, this Court has “interpreted\\n\\nthe on board a vessel subject to the jurisdiction of the United States” provision “as\\n\\na congressionally imposed limit on courts’ subject matter jurisdiction, akin to the\\n\\namount-in-controversy requirement contained in 28 U.S.C. § 1332.” Id. (internal\\n\\nquotation marks and citation omitted). Consequently, for a district court to have\\n\\n\\n 11\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 12 of 15\\n\\n\\nadjudicatory authority over a charge that the defendant conspired to violate a\\n\\nsubstantive crime defined in the MDLEA, the government must make a\\n\\npreliminary showing that the vessel was, when apprehended, subject to the\\n\\njurisdiction of the United States. Id.\\n\\n In Iguaran, this Court vacated the defendant’s guilty plea because the district\\n\\ncourt did not make any factual findings with respect to its subject matter\\n\\njurisdiction under the MDLEA, and the record contained no facts from which such\\n\\njurisdiction could be determined. See id. at 1337–38. We then remanded the case\\n\\nto the district court for the limited purpose of determining whether subject matter\\n\\njurisdiction existed, after affording both parties an opportunity to present evidence\\n\\nbearing on whether Iguaran’s vessel was subject to the jurisdiction of the United\\n\\nStates. Id. at 1338.\\n\\n Though Grimon is correct that this Court held in Iguaran that parties may not\\n\\nstipulate to jurisdiction, but rather only to underlying facts that bear on the\\n\\njurisdictional inquiry, that holding is simply irrelevant to her case. Id. at 1337.\\n\\nIguaran involved the MDLEA, where the statutory text made clear that\\n\\n“jurisdiction” is not merely an element of the offense. See id. at 1336\\n\\n(“‘Jurisdiction of the United States with respect to a vessel subject to this chapter is\\n\\nnot an element of an offense.’” (emphasis added) (quoting 46 U.S.C. § 70504(a))).\\n\\nIguaran, as explained above, dealt with a statutory requirement that was truly\\n\\n\\n 12\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 13 of 15\\n\\n\\n“jurisdictional”—that is, without facts showing that Iguaran’s vessel was subject to\\n\\nthe jurisdiction of the United States, the district court in that case had no authority\\n\\nto adjudicate his case. Id.\\n\\n Here, by contrast, § 1029(a)(3) did not require the district court to determine\\n\\nthat Grimon’s offense affected interstate commerce to have subject matter\\n\\njurisdiction. See 18 U.S.C. § 1029(a)(3). Rather, the interstate nexus requirement\\n\\nwas simply one of several elements of Grimon’s § 1029(a)(3) offense that the\\n\\ngovernment had to prove. See id.; United States v. Klopf, 423 F.3d 1228, 1240\\n\\n(11th Cir. 2005) (indicating that an effect on interstate or foreign commerce is an\\n\\nelement for offenses under § 1029(a)). Neither Iguaran nor any other case cited by\\n\\nGrimon has held that this interstate nexus requirement is akin to the amount in\\n\\ncontroversy requirement in 28 U.S.C. § 1332 or to the jurisdictional requirement in\\n\\nthe MDLEA. And we squarely hold that it is not. So, whether the government\\n\\nproved the interstate commerce nexus or failed to prove it, the district court still\\n\\nhad subject matter jurisdiction over Grimon’s case and her Count 1 conviction.\\n\\nSee Alikhani, 200 F.3d at 735.\\n\\n As to her aggravated identity theft conviction in Count 2, Grimon’s statute\\n\\nof conviction, 18 U.S.C. § 1028A(a)(1), itself does not contain an interstate\\n\\ncommerce element. See 18 U.S.C. § 1028A. However, because a conviction\\n\\nunder § 1028A is predicated on the unlawful transfer, possession, or use of a\\n\\n\\n 13\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 14 of 15\\n\\n\\nmeans of identification “during and in relation to [an enumerated] felony\\n\\nviolation,” Grimon argues that, if the district court lacked subject matter\\n\\njurisdiction over the § 1029(a)(3) offense in Count 1, it likewise lacked subject\\n\\nmatter jurisdiction over the § 1028A(a)(1) offense in Count 2. For the reasons\\n\\nstated above, we reject Grimon’s jurisdiction claim as to Count 2 as well.\\n\\nC. No Other Claim\\n\\n As a final matter, Grimon’s brief on appeal did not raise any error or\\n\\nargument other than the subject matter jurisdictional one addressed above. More\\n\\nspecifically, as the government points out, Grimon has not raised on appeal, and\\n\\nhas therefore abandoned, any claim or argument that the alleged insufficiency of\\n\\nthe factual proffer as to the interstate commerce element violated Federal Rule of\\n\\nCriminal Procedure 11 or rendered her plea unknowing or involuntary. See United\\n\\nStates v. Jernigan, 341 F.3d 1273, 1283 n.8 (11th Cir. 2003) (explaining that issues\\n\\nnot raised on appeal are deemed abandoned).\\n\\n Accordingly, we do not address whether any alleged insufficiency in\\n\\nGrimon’s factual proffer as to the interstate commerce element of her § 1029(a)(3)\\n\\noffense invalidated her guilty plea. Because Grimon has raised no claim of Rule\\n\\n11 error, we also do not address the government’s argument that the doctrine of\\n\\ninvited error applies because Grimon agreed in her factual proffer that the\\n\\n\\n\\n\\n 14\\n\\f Case: 17-15011 Date Filed: 05/13/2019 Page: 15 of 15\\n\\n\\ngovernment could have established at trial that her conduct affected interstate or\\n\\nforeign commerce.\\n\\n III. CONCLUSION\\n\\n For the foregoing reasons, we affirm Grimon’s two convictions.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 15\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2281,"cells":{"id":{"kind":"number","value":4619840,"string":"4,619,840"},"name":{"kind":"string","value":"ALLIANT TAX CREDIT 31, INC, a Florida Corporation, Alliant Tax Credit Fund XXVII, Ltd., a Florida Limited Partnership, Alliant Tax Credit Tax Credit XXVII, Inc, a Florida Corporation, Alliant Tax Credit XI, Inc., a Florida Corporation, Alliant Tax Credit XI, Ltd., a Florida Limited Partnership, Plaintiffs - Counter Defendants - Appellees - Cross Appellants, v. M. Vincent MURPHY, III, Multifamily Housing Developers, L.L.C., a Georgia Limited Liability Company, Community Management Services, Inc., a Georgia Corporation, Gazebo Park Apartments of Acworth, LLC, a Georgia Limited Liability Company, Defendants - Appellants - Cross Appellees, Marilyn Murphy, Defendant - Counter Claimant - Appellant - Cross Appellee."},"name_abbreviation":{"kind":"string","value":"Alliant Tax Credit 31, Inc. v. M. Vincent Murphy, III"},"decision_date":{"kind":"string","value":"2019-05-15"},"docket_number":{"kind":"string","value":"15-14634"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Tjoflat, Pryor, Murphy\", \"parties\": \"\", \"opinions\": [{\"author\": \"TJOFLAT, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 15-14634 Date Filed: 05/15/2019 Page: 1 of 37\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 15-14634\\n ________________________\\n\\n D.C. Docket No. 1:11-cv-00832-RWS\\n\\n\\n\\nALLIANT TAX CREDIT 31, INC,\\na Florida corporation,\\nALLIANT TAX CREDIT FUND XXVII, LTD.,\\na Florida limited partnership,\\nALLIANT TAX CREDIT TAX CREDIT XXVII, INC,\\na Florida corporation,\\nALLIANT TAX CREDIT XI, INC.,\\na Florida corporation,\\nALLIANT TAX CREDIT XI, LTD.,\\na Florida limited partnership,\\n\\n Plaintiffs - Counter Defendants – Appellees -\\n Cross Appellants,\\n\\n versus\\n\\nM. VINCENT MURPHY, III,\\nMULTIFAMILY HOUSING DEVELOPERS, L.L.C.,\\na Georgia limited liability company,\\nCOMMUNITY MANAGEMENT SERVICES, INC.,\\na Georgia corporation,\\nGAZEBO PARK APARTMENTS OF ACWORTH, LLC,\\na Georgia limited liability company,\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 2 of 37\\n\\n\\n Defendants - Appellants - Cross Appellees,\\n\\nMARILYN MURPHY,\\n\\n Defendant - Counter Claimant - Appellant -\\n Cross Appellee.\\n\\n ________________________\\n\\n Appeals from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 15, 2019)\\n\\nBefore TJOFLAT and WILLIAM PRYOR, Circuit Judges, and MURPHY, *\\nDistrict Judge.\\n\\nTJOFLAT, Circuit Judge:\\n\\n This fraudulent-transfer case, like many such cases, is a suit about a suit. In\\n\\nthe first suit, Plaintiffs obtained a judgment in federal district court in Kentucky for\\n\\nbreach of a partnership contract. But when Plaintiffs tried to collect, they\\n\\ndiscovered that the once-wealthy Defendant was figuratively penniless. The\\n\\nsurprised Plaintiffs surmised that Defendant had colluded with his former wife to\\n\\nfraudulently transfer his assets to her (or to entities under her control) as part of\\n\\ntheir divorce settlement. So Plaintiffs sued—again—this time in federal district\\n\\ncourt in Georgia—to recover their judgment under Georgia’s fraudulent-transfer\\n\\n\\n\\n *\\n Honorable Stephen J. Murphy, III, United States District Court for the Eastern District\\nof Michigan, sitting by designation.\\n\\n\\n 2\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 3 of 37\\n\\n\\nstatute. Agreeing with Plaintiffs that fraudulent transfers had occurred, a jury\\n\\nreturned a verdict in their favor. The District Court entered judgment accordingly,\\n\\nand this appeal and cross-appeal followed.\\n\\n I.\\n\\n A.\\n\\n 1.\\n\\n The run-up to this suit began when Plaintiffs, five entities that we\\n\\ncollectively refer to as “Alliant,” 1 lent Defendant M. Vincent Murphy, III\\n\\ninvestment capital to build low-income housing units that were never completed.\\n\\nSo Alliant sued him and other guarantors of the debt in federal court in the Eastern\\n\\nDistrict of Kentucky for breach of their partnership contract. Alliant was joined in\\n\\nthat suit by Alliant Tax Credit Fund 31-A, Ltd. (“Alliant 31-A”), which also lent\\n\\ninvestment capital to Vincent. 2 Alliant and Alliant 31-A prevailed, and the District\\n\\nCourt for the Eastern District of Kentucky entered a judgment (the “Kentucky\\n\\njudgment”) in their favor for $8,946,643. Vincent appealed, and the Court of\\n\\n\\n\\n\\n 1\\n The full names are Alliant Tax Credit 31, L.L.C. (“Alliant 31”), Alliant Tax Credit Fund\\nXXVII, Ltd. (“Alliant XXVII, Ltd.”), Alliant Tax Credit Fund XXVII, L.L.C. (“Alliant XXVII,\\nL.L.C.”), Alliant Tax Credit XI, L.L.C. (“Alliant XI, L.L.C.”), and Alliant Tax Credit XI, Ltd.\\n(“Alliant XI, Ltd.”).\\n 2\\n Alliant 31-A was dismissed by the District Court for the Northern District of Georgia\\nbecause its presence would have destroyed subject-matter jurisdiction. For this reason (and\\nothers that will become clear), we treat Alliant 31-A separately.\\n\\n\\n 3\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 4 of 37\\n\\n\\nAppeals for the Sixth Circuit affirmed. Alliant Tax Credit Fund 31-A, Ltd. v.\\n\\nMurphy, 494 F. App’x 561, 563 (6th Cir. 2012).\\n\\n But the fraudulent activity that gave rise to this suit began before the\\n\\nKentucky judgment was entered.\\n\\n Vincent and his wife, Marilyn Murphy, had earlier divorced in the Superior\\n\\nCourt of Fulton County, Georgia. The divorce decree incorporated a settlement\\n\\nagreement between them. As part of the agreement, Marilyn received from\\n\\nVincent several millions of dollars in cash and commercial paper, stock shares, a\\n\\nmountain cabin, household furnishings, and an apartment complex. These assets\\n\\nare the basis for the fraudulent-transfer action here. When Alliant sought to collect\\n\\non the Kentucky judgment, it found that Vincent was judgment proof. So it sued\\n\\nVincent for a second time.\\n\\n Alliant (but not Alliant 31-A) brought this action against Vincent, Marilyn,\\n\\nMultifamily Housing Developers, L.L.C. (“Multifamily Housing”), and\\n\\nCommunity Management Services, Inc. (“CMS”), 3 in the District Court for the\\n\\nNorthern District of Georgia under the Uniform Fraudulent Transfers Act (the\\n\\n“UFTA”), O.C.G.A. §§ 18-2-70 to 80 (2010), amended by the Uniform Voidable\\n\\n\\n\\n\\n 3\\n Alliant alleged that Multifamily Housing and CMS, both of which Marilyn controlled,\\nwere also fraudulent transferees of some of Vincent’s assets.\\n\\n\\n 4\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 5 of 37\\n\\n\\nTransactions Act (the “UVTA”), O.C.G.A. §§ 18-2-70 to 85 (2015).4 The UFTA,\\n\\na quintessential fraudulent-transfer statute, allows creditors to void certain asset\\n\\ntransfers made by a debtor with the purpose of immunizing itself from collection.\\n\\nSee O.C.G.A. § 18-2-77 (2010). Alliant claimed that the Murphys’ divorce\\n\\nsettlement and Vincent’s asset transfers to Defendants were ruses to evade\\n\\nVincent’s creditors and thus sought to void those transfers. The case proceeded to\\n\\ntrial, and a jury returned an itemized verdict for Alliant after having found that\\n\\ntwenty-three transfers from Vincent to Defendants were fraudulent. The jury also\\n\\nfound that the Murphys were subject to punitive damages but that only Vincent had\\n\\nacted with the “specific intent to cause harm.” It awarded $1,000,000 in punitive\\n\\ndamages against him and $100,000 in punitive damages against Marilyn.\\n\\n 2.\\n\\n After the jury returned its verdict, the District Court for the Northern District\\n\\nof Georgia entered a final judgment (the “Georgia judgment”) for Alliant. Before\\n\\ndescribing what the judgment provided, we pause momentarily to note the\\n\\nremedies available under the UFTA.\\n\\n\\n 4\\n Georgia’s General Assembly amended the UFTA in 2015. See Uniform Voidable\\nTransactions Act, 2015 Ga. Laws 1019 (codified at O.C.G.A. §§ 18-2-70 to 85 (2018)). As part\\nof the amendment, the General Assembly changed the name of the statute. Some of the\\namendments are consequential to issues we must decide on appeal. But the parties agree—and\\nwe follow their lead—the UFTA is the version of the law we must apply. We discuss the\\nUVTA—note the “V” in place of the “F”—at various points throughout this opinion; we make\\nclear when we reference that currently enacted version of the statute.\\n\\n\\n 5\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 6 of 37\\n\\n\\n The UFTA provides creditors with both equitable and legal remedies. The\\n\\ncreditor may obtain, as an equitable remedy, “[a]voidance of the transfer . . . to the\\n\\nextent necessary to satisfy the creditor’s claim.” See id. § 18-2-77(a)(1). Or it may\\n\\nobtain, as a legal remedy, “judgment [against the transferee] for the value of the\\n\\nasset transferred . . . or the amount necessary to satisfy the creditor’s claim,\\n\\nwhichever is less.” See id. § 18-2-78(b).\\n\\n Alliant did not seek avoidance of any of the transfers made. Nor realistically\\n\\ncould it: Most of Vincent’s transfers were in the form of cash that has since been\\n\\nturned into proceeds that are likely untraceable. Rather, it sought a money\\n\\njudgment for the value of the assets transferred. Said differently, it sought the\\n\\nlegal remedy available under the UFTA.\\n\\n The Georgia judgment, which purported to implement the jury’s verdict,\\n\\nprovided that Alliant would receive the sum of $10,137,285.84, which consisted of\\n\\nthe amount of the Kentucky judgment ($8,946,643), interest on that judgment\\n\\n($90,642.84), and the punitive-damages awards against Vincent and Marilyn\\n\\n($1,000,000 and $100,000, respectively). The District Court for the Northern\\n\\nDistrict of Georgia also issued a writ of execution that directed the U.S. Marshal to\\n\\nseize Defendants’ assets to satisfy the judgment. 5\\n\\n\\n 5\\n In ordering the U.S. Marshal to seize the items identified in the judgment, the District\\nCourt appeared to be entering an in rem judgment, as if Alliant had brought suit against the\\nfraudulently conveyed assets or their proceeds themselves. The Court should have entered an in\\n\\n\\n 6\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 7 of 37\\n\\n\\n 3.\\n\\n Following the entry of the Georgia judgment, Marilyn satisfied the judgment\\n\\nin full, and Alliant moved to alter or amend the judgment, see Fed. R. Civ. P. 60, to\\n\\nallow prejudgment interest under Georgia law. The District Court for the Northern\\n\\nDistrict of Georgia denied this motion, reasoning that (1) Alliant’s UFTA claim\\n\\nwas unliquidated—that is, not reduced to a fixed sum—until the Georgia judgment\\n\\nwas entered and (2) under Georgia law, entitlement to prejudgment interest for\\n\\nunliquidated claims requires compliance with the Unliquidated Damages Interest\\n\\nAct, O.C.G.A. § 51-12-14 (2018), whose procedures Alliant had not followed.\\n\\nDefendants appealed the judgment entered pursuant to the verdict, and Alliant\\n\\ncross-appealed the order denying prejudgment interest.\\n\\n B.\\n\\n This appeal and cross-appeal require us to decide numerous discrete issues.\\n\\nWe first take up justiciability problems in Part II. We then turn to the merits,\\n\\naddressing Defendants’ arguments on appeal in Parts III through V and Alliant’s\\n\\narguments on cross-appeal in Part VI. We conclude in Part VII.\\n\\n II.\\n\\n\\n\\npersonam judgment against Vincent and Marilyn individually and issued writs of execution\\nagainst their assets or writs of garnishment against their accounts. This error does not matter for\\nour purposes, however, because the parties treated the judgment as though it were entered in\\npersonam.\\n\\n\\n 7\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 8 of 37\\n\\n\\n We begin by addressing two jurisdictional bars to the District Court’s power\\n\\nto entertain this suit: mootness and subject-matter jurisdiction.6 We then address\\n\\nnon-jurisdictional bars. Defendants challenge the Court’s decision not to abstain\\n\\nfrom exercising its jurisdiction on three prudential grounds. First, that even if the\\n\\nparties are diverse of citizenship, this case falls within the domestic-relations\\n\\nexception to diversity jurisdiction. Second, that by entertaining this suit, the Court\\n\\nviolated the Rooker-Feldman doctrine. 7 And third, that Alliant is collaterally\\n\\nestopped from attacking the transfers as fraudulent.\\n\\n A.\\n\\n The first question, given Marilyn’s full satisfaction of the Georgia judgment:\\n\\nAre this appeal and cross-appeal moot? After oral argument, we asked the parties\\n\\nto brief this question and having reviewed their responses, we are satisfied that the\\n\\ncase remains a case or controversy within the meaning of Article III. See U.S.\\n\\nConst. art. III, § 2, cl. 1.\\n\\n “What matters [for mootness] is whether the parties’ actions objectively\\n\\nmanifest an intent to abandon the issues on appeal.” RES-GA Cobblestone, LLC v.\\n\\nBlake Constr. & Dev., LLC, 718 F.3d 1308, 1315 (11th Cir. 2013). So payment\\n\\n\\n\\n 6\\n Unless otherwise stated, our use of “District Court” from this point forward refers to the\\nCourt below—the District Court for the Northern District of Georgia.\\n 7\\n Rooker v. Fid. Tr. Co., 263 U.S. 413, 44 S. Ct. 149 (1923), and D.C. Court of Appeals v.\\nFeldman, 460 U.S. 462, 103 S. Ct. 1303 (1983).\\n\\n\\n 8\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 9 of 37\\n\\n\\nmoots an appeal “only if the parties mutually intended a final settlement of all the\\n\\nclaims in dispute and a termination of the litigation.” McGowan v. King, Inc., 616\\n\\nF.2d 745, 747 (5th Cir. 1980) (per curiam). 8\\n\\n This case continues to breathe life. In Alvarez Perez v. Sanford-Orlando\\n\\nKennel Club, Inc., 518 F.3d 1302 (11th Cir. 2008), we applied the Supreme\\n\\nCourt’s decision in United States v. Hougham, 364 U.S. 310, 81 S. Ct. 13 (1960),\\n\\nand held that an appeal and cross-appeal situated much like the ones before us\\n\\ntoday were not moot. There, the plaintiff’s counsel signed satisfaction-of-\\n\\njudgment documents that were subsequently filed in the district court, but the\\n\\nplaintiff did not expressly reserve his right to appeal. 518 F.3d at 1305. But there,\\n\\nas here, the parties “continued to pursue their appeals.” Id. at 1307. There, as\\n\\nhere, the parties “filed supplemental letter briefs addressing the merits.” Id. And\\n\\nthere, as here, a party “inform[ed] us of a change in status involving one of the\\n\\ndefendants.” Id. In other words, “[i]nstead of filing a motion to dismiss the appeal\\n\\nas soon as a satisfaction was filed in the district court, both parties continued to\\n\\nlitigate the case in this Court as though nothing had changed.” Id. at 1308.\\n\\n In fact, Marilyn merely did the effective equivalent of posting a supersedeas\\n\\nbond—an act that by itself does not moot a case. See Fed. R. Civ. P. 62(b).\\n\\n\\n 8\\n In Bonner v. City of Prichard, 661 F.2d 1206 (11th Cir. 1981) (en banc), this Court\\nadopted as binding precedent all decisions of the former Fifth Circuit handed down prior to\\nOctober 1, 1981.\\n\\n\\n 9\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 10 of 37\\n\\n\\n When a judgment is appealed, both the winning and losing parties face risk\\n\\nin the period between the time judgment is entered and the time it is affirmed or\\n\\nreversed. The winning party seeks immediate satisfaction of the judgment because\\n\\nassets available at the time judgment is entered might disappear by the time it is\\n\\naffirmed. And the losing party seeks delayed satisfaction of judgment for a\\n\\nparallel reason: Assets available at the time judgment is entered might disappear by\\n\\nthe time it is reversed. A supersedeas bond insures both parties against these\\n\\nrespective risks. It permits a judgment debtor to “avoid the risk of satisfying the\\n\\njudgment only to find that restitution is impossible after reversal on appeal” and\\n\\n“secures the prevailing party against any loss sustained as a result of being forced\\n\\nto forgo execution on a judgment during the course of an ineffectual appeal.”\\n\\nPoplar Grove Planting & Ref. Co. v. Bache Halsey Stuart, Inc., 600 F.2d 1189,\\n\\n1191 (5th Cir. 1979).\\n\\n But posting a supersedeas bond does not moot an appeal. See Dale M. ex\\n\\nrel. Alice M. v. Bd. of Educ. of Bradley-Bourbonnais High Sch. Dist. No. 307, 237\\n\\nF.3d 813, 815 (7th Cir. 2001) (Posner, J.) (“A judgment creditor who pays the\\n\\njudgment pending appeal instead of posting a supersedeas bond (which would\\n\\nautomatically stay collection) is entitled to the return of its money if the decision is\\n\\nreversed, and so the payment does not moot the appeal unless the appellant has\\n\\nrelinquished his right to seek repayment if he wins.” (citation omitted)).\\n\\n\\n\\n 10\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 11 of 37\\n\\n\\n Marilyn’s choice to pay the judgment does not render this case moot any\\n\\nmore than would her decision to post a supersedeas bond; she simply waived the\\n\\nprotection a bond would provide. Cf. 11 Charles Alan Wright et al., Federal\\n\\nPractice and Procedure § 2905, at 724−25 (3d ed. 2012) (“[A] person who cannot\\n\\nfurnish a supersedeas bond does not lose the right to appeal, although he does\\n\\nassume the risk of getting his money back again if the judgment is reversed.”).\\n\\n In short, the “objective manifestations of both parties clearly indicate that\\n\\nthey intended to pursue their positions in the appeal and cross-appeal.” Alvarez\\n\\nPerez, 518 F.3d at 1308. We turn now to subject-matter jurisdiction.\\n\\n B.\\n\\n Defendants maintain that the District Court lacked jurisdiction to entertain\\n\\nthe dispute because the parties were not diverse of citizenship.\\n\\n The District Court’s subject-matter jurisdiction has continued to present\\n\\ndifficulties in this case. Defendants appealed the Georgia judgment, and two\\n\\nmonths later, this Court sua sponte asked the parties to address subject-matter\\n\\njurisdiction because diversity jurisdiction was not evident from the pleadings. In\\n\\nresponse, Alliant moved to amend its complaint to simply allege the citizenships of\\n\\nall relevant entities. Defendants, in turn, moved to remand the case to the District\\n\\nCourt for a factual determination of subject-matter jurisdiction in the first instance.\\n\\nAfter reviewing the parties’ responses and motions, we remanded the case to the\\n\\n\\n\\n 11\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 12 of 37\\n\\n\\nDistrict Court so that it might “fully resolve the question of the court’s subject-\\n\\nmatter jurisdiction over this action.” Alliant Tax Credit Fund 31-A, Ltd. v.\\n\\nMurphy, No. 15-14634-GG, slip op. at 1 (11th Cir. Apr. 10, 2017) (per curiam).\\n\\n On remand, Alliant filed a memorandum on Plaintiffs’ citizenships.\\n\\nPlaintiffs are a mixture of limited-liability companies and limited partnerships. 9\\n\\nSome of Plaintiffs’ members and partners are natural persons, but some are other\\n\\nlimited-liability companies, other partnerships, corporations, banks, and trusts.\\n\\nAlliant traced these entities’ citizenships, too. It included with its memorandum to\\n\\nthe District Court affidavits, declarations, and authenticated documents.\\n\\nDefendants responded that Alliant’s submissions were insufficient to confirm that\\n\\nall relevant entities were accounted for, as well as to confirm those entities’\\n\\ncitizenships. The Court observed that though Alliant had initially claimed that the\\n\\nsole citizenship of all five Plaintiffs was Florida, Alliant conceded in its\\n\\nmemorandum that Plaintiffs were also citizens of California, Delaware, the District\\n\\nof Columbia, Illinois, Nebraska, New York, Ohio, and Texas. So the Court\\n\\nrequired further documentary evidence of citizenship. For natural persons, it asked\\n\\nfor drivers licenses; for corporations, it asked for annual reports and articles of\\n\\nincorporation or governance documents; for limited partnerships and limited-\\n\\n\\n\\n 9\\n Alliant 31, L.L.C., Alliant XXVII, L.L.C., and Alliant XI, L.L.C. are limited-liability\\ncompanies. Alliant XXVII, Ltd. and Alliant XI, Ltd. are limited partnerships.\\n\\n\\n 12\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 13 of 37\\n\\n\\nliability companies, it asked for agreements; for banks, it asked for articles of\\n\\nassociation; and for trusts, it asked for organizational documents.\\n\\n After this jurisdictional discovery was complete, the District Court set out its\\n\\nfindings as to the parties’ citizenships:\\n\\nPlaintiffs\\n\\n • Alliant 31 was a citizen of Florida, California, and Illinois.\\n\\n • Alliant XXVII, Ltd. was a citizen of Florida, California, Illinois, and the\\n District of Columbia.\\n\\n • Alliant XXVII, L.L.C. was a citizen of Florida, California, and Illinois.\\n\\n • Alliant XI, L.L.C. was a citizen of Florida, California, and Illinois.\\n\\n • Alliant XI, Ltd. was a citizen of Florida, California, Illinois, Delaware,\\n New York, Texas, Nevada, and Ohio.\\n\\nDefendants\\n\\n • Vincent was a citizen of Georgia.\\n\\n • CMS was a citizen of Georgia.\\n\\n • Multifamily Housing was a citizen of Georgia.\\n\\n • Marilyn was a citizen of Georgia.\\n\\nAs such, it concluded that Alliant had established subject-matter jurisdiction by a\\n\\npreponderance of the evidence.\\n\\n Defendants, still unsatisfied that diversity jurisdiction was present, moved\\n\\nthis Court for leave to file supplemental briefing on the District Court’s factual\\n\\n\\n 13\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 14 of 37\\n\\n\\nfindings, its failure to sustain evidentiary objections, its admission into evidence of\\n\\nunreliable documents, and its failure to allow adversarial discovery. We granted\\n\\nDefendants’ motion, Alliant Tax Credit Fund 31-A, Ltd. v. Murphy, No. 15-14634-\\n\\nGG, slip op. at 2 (11th Cir. Nov. 9, 2017) (single-judge order), and now address\\n\\nthese jurisdictional issues.\\n\\n 1.\\n\\n First, Defendants argue that the record contains insufficient evidence to\\n\\nsupport the District Court’s findings on the citizenships of two inter vivos trusts,\\n\\nwhose names we have redacted.10 They contend that the trusts’ citizenships derive\\n\\nfrom their beneficiaries and that Alliant has not fully accounted for those\\n\\nbeneficiaries.\\n\\n Whether subject-matter jurisdiction exists presents a mixed question of law\\n\\nand fact. We review de novo a district court’s legal conclusions. Calderon v.\\n\\nBaker Concrete Constr., Inc., 771 F.3d 807, 810 (11th Cir. 2014). But we review\\n\\nfor clear error “any factual determinations necessary to establish jurisdiction,”\\n\\nDudley v. Eli Lilly & Co., 778 F.3d 909, 911 (11th Cir. 2014), including “findings\\n\\nregarding domicile,” McCormick v. Aderholt, 293 F.3d 1254, 1257 (11th Cir.\\n\\n2002) (per curiam). The party invoking federal jurisdiction “must prove, by a\\n\\n\\n 10\\n These trusts are members of a limited-liability company that is a member of another\\nlimited-liability company that is a partner of a limited partnership that in turn is a member or\\npartner of each of the five Plaintiffs in this case.\\n\\n\\n 14\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 15 of 37\\n\\n\\npreponderance of the evidence, facts supporting the exercise of jurisdiction.”\\n\\nCaron v. NCL (Bahamas), Ltd., 910 F.3d 1359, 1363–64 (11th Cir. 2018).\\n\\n A “traditional trust” holds the citizenship of its trustee, not of its\\n\\nbeneficiaries. See Americold Realty Tr. v. Conagra Foods, Inc., 136 S. Ct. 1012,\\n\\n1016 (2016); see also Raymond Loubier Irrevocable Tr. v. Loubier, 858 F.3d 719,\\n\\n730 (2d Cir. 2017) (“[F]or . . . traditional trusts, it is the citizenship of the trustees\\n\\nholding the legal right to sue on behalf of the trusts, not that of beneficiaries, that is\\n\\nrelevant to jurisdiction.”). A “traditional trust . . . generally describes a fiduciary\\n\\nrelationship regarding property where the trust cannot sue and be sued as an entity\\n\\nunder state law.” Wang ex rel. Wong v. New Mighty U.S. Tr., 843 F.3d 487, 495\\n\\n(D.C. Cir. 2016). So whether a trust is “traditional” requires us to refer to the “law\\n\\nof the state where the trust is formed.” Id.; see also, e.g., id. (holding that under\\n\\nDistrict of Columbia law, a trust lacked separate “juridical person status” and thus\\n\\ncould not “sue and be sued as an entity”); Loubier, 858 F.3d at 731 (holding that\\n\\nunder Florida law, a trust was not a “distinct juridical entit[y]” and thus was\\n\\n“incapable of being haled into court except through [its] trustee[]”).\\n\\n The two trusts here were formed in Wisconsin, and under Wisconsin law, a\\n\\ntrust is represented in litigation through its trustee. See Wis. Stat. § 701.0106\\n\\n(stating that the trust code incorporates the “common law of trusts”). Because the\\n\\ncode does not confer “juridical person status” on a trust itself, see New Mighty U.S.\\n\\n\\n\\n 15\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 16 of 37\\n\\n\\nTr., 843 F.3d at 495, the trusts are traditional trusts whose citizenships are those of\\n\\ntheir trustees. The trustee of both trusts is a natural person who is domiciled in\\n\\nFlorida. As such, she is a Florida citizen. See McCormick, 293 F.3d at 1257.\\n\\n In short, Alliant has proven diversity jurisdiction by a preponderance of the\\n\\nevidence because if the trustee is diverse of Defendants, the trusts themselves are\\n\\ntoo.\\n\\n 2.\\n\\n Second, Defendants argue that the District Court erred by admitting the\\n\\nsworn affidavits of three persons who held leadership positions with various\\n\\nmembers or partners of the five Plaintiffs. We review a district court’s admission\\n\\nof evidence for abuse of discretion. Williams v. Mast Biosurgery USA, Inc., 644\\n\\nF.3d 1312, 1316 (11th Cir. 2011).\\n\\n Defendants argue that the affidavits lack foundation, see Fed. R. Evid. 602,\\n\\nbecause the affiants failed to state that only they could change the memberships of\\n\\ntheir respective entities. But the relevant question for foundation purposes is\\n\\nwhether the affiants had “personal knowledge” of the matter sworn to. See id.\\n\\nEach person laid a foundation for his respective affidavit by stating his position\\n\\nwith the relevant entity and that he had access to that entity’s records. As leaders,\\n\\nrather than as minor functionaries, they were well within their wheelhouses to\\n\\n\\n\\n\\n 16\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 17 of 37\\n\\n\\nswear to the entities’ compositions. Defendants’ argument goes to the weight of\\n\\nthe evidence, not to its admissibility.\\n\\n In short, the District Court was well within its discretion to admit the\\n\\naffidavits.\\n\\n 3.\\n\\n Third, Defendants challenge the operating agreements for Alliant XXVII,\\n\\nL.L.C. and Alliant XI, L.L.C. on which one affiant relies. They point to missing or\\n\\nwholly redacted pages and font inconsistencies among the pages. As such, they\\n\\nargue that the documents were inadmissible because they could not be\\n\\nauthenticated, see Fed. R. Evid. 901, and because they were hearsay that did not\\n\\ncomport with the business-records exception, see Fed. R. Evid. 803(6).\\n\\n We need not reach these issues because even in a record devoid of this\\n\\nevidence, the District Court’s factual findings on these entities’ citizenships was\\n\\nnot clearly erroneous. For both entities, Alliant submitted the later-issued\\n\\ncertificates of conversion from corporations to limited-liability companies. Those\\n\\ndocuments indicate that both Alliant XXVII, L.L.C. and Alliant XI, L.L.C. have\\n\\nonly one member and one general partner. So Defendants’ theory that other\\n\\nentities lurk in those entities’ structures is unfounded.\\n\\n 4.\\n\\n\\n\\n\\n 17\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 18 of 37\\n\\n\\n Fourth, Defendants argue that the District Court should have permitted them\\n\\nto obtain through additional jurisdictional discovery (1) the documentary evidence\\n\\nthat Alliant filed in Alliant Tax Credit Fund XVI, Ltd. v. Thomasville Community\\n\\nHousing, LLC, 713 F. App’x 821 (11th Cir. 2017) (per curiam), 11 and (2) a copy of\\n\\nthe partnership agreement between Alliant 31 and Alliant 31-A. 12 We review a\\n\\ndistrict court’s denial of jurisdictional discovery for abuse of discretion.\\n\\nCulverhouse v. Paulson & Co., 813 F.3d 991, 993 (11th Cir. 2016).\\n\\n Defendants’ underlying grievance is that Alliant cannot be trusted because it\\n\\nhas misrepresented its citizenship in other litigation, including litigation in this\\n\\ncircuit. And because one district judge in this circuit required certain documents of\\n\\nAlliant, the District Judge in this (unrelated) case should have too.\\n\\n To be sure, parties have a “‘qualified right to jurisdictional discovery,’\\n\\nmeaning that a district court abuses its discretion if it completely denies a party\\n\\njurisdictional discovery.” Am. Civil Liberties Union of Fla., Inc. v. City of\\n\\n\\n\\n\\n 11\\n Alliant XI, L.L.C., a Plaintiff here, was also a party to that case.\\n 12\\n We deal with this second request later. Defendants argue that the record contains\\ninsufficient evidence that Alliant 31 meets the amount-in-controversy requirement. See 28\\nU.S.C. § 1332(a) (requiring that a controversy “exceed[] the sum or value of $75,000, exclusive\\nof interest and costs”). Alliant 31 and Alliant 31-A were awarded $1,478,489 via the Kentucky\\njudgment. Defendants claim that each has partial ownership in that amount and that Alliant 31\\nhas not proven that its own interest is at least $75,000. We explain later on, however, that\\nAlliant 31 was entitled to sue for the full amount because it was a joint−judgment creditor. See\\ninfra p. 25. As such, the amount-in-controversy requirement is met.\\n\\n\\n 18\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 19 of 37\\n\\n\\nSarasota, 859 F.3d 1337, 1341 (11th Cir. 2017) (citations omitted) (quoting Eaton\\n\\nv. Dorchester Dev., Inc., 692 F.2d 727, 729 n.7 (11th Cir. 1982)).\\n\\n The District Court here did not abuse its discretion. It did not “completely\\n\\ndeny” Defendants jurisdictional discovery. To the contrary, it ordered Alliant to\\n\\nproduce additional documentary evidence after we remanded the case. Moreover,\\n\\njust because one judge permitted a discovery request does not mean another judge\\n\\nwas obligated to do so. Defendants overlook a basic principle of appellate review:\\n\\nTwo district judges can reach two different determinations of what discovery to\\n\\npermit, and under abuse-of-discretion review, we are required to affirm both\\n\\ndecisions unless one judge has “made a clear error of judgment” or “applied the\\n\\nwrong legal standard.” See Josendis v. Wall to Wall Residence Repairs, Inc., 662\\n\\nF.3d 1292, 1307 (11th Cir. 2011) (quoting Guideone Elite Ins. Co. v. Old Cutler\\n\\nPresbyterian Church, Inc., 420 F.3d 1317, 1325 (11th Cir. 2005)); see also id. at\\n\\n1306−07 (“Discretion means the district court has a ‘range of choice, and that its\\n\\ndecision will not be disturbed as long as it stays within that range and is not\\n\\ninfluenced by any mistake of law.’” (quoting Betty K Agencies, Ltd. v. M/V\\n\\nMonada, 432 F.3d 1333, 1337 (11th Cir. 2005))). In other words, one district\\n\\njudge is not required to follow his brethren in lockstep on discovery matters, just as\\n\\nhe is not required to follow him in lockstep on any other decision. See United\\n\\nStates v. Cerceda, 172 F.3d 806, 812 n.6 (11th Cir. 1999) (en banc) (per curiam)\\n\\n\\n\\n 19\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 20 of 37\\n\\n\\n(“The opinion of a district court carries no precedential weight, even within the\\n\\nsame district.”). So we do not evaluate this Judge’s decision in light of another’s\\n\\ndecision.\\n\\n In short, nothing about the District Court’s finding of subject-matter\\n\\njurisdiction, procedurally or substantively, permits reversal. The Court’s\\n\\nfactfinding was not clearly erroneous. Its evidentiary conclusions were not legally\\n\\nincorrect. And its decision not to entertain additional discovery was not an abuse\\n\\nof discretion.\\n\\n That’s it for the jurisdictional wrinkles, but Defendants offer three other\\n\\nreasons for why the District Court should have evaded the merits.\\n\\n C.\\n\\n Defendants maintain that the District Court was required to abstain under the\\n\\ndomestic-relations exception to diversity jurisdiction. We review for abuse of a\\n\\ndiscretion a district court’s abstention decision under the domestic-relations\\n\\nexception. Stone v. Wall, 135 F.3d 1438, 1441 (11th Cir. 1998) (per curiam),\\n\\ncertified question answered, 734 So. 2d 1038 (Fla. 1999). 13\\n\\n “The federal judiciary has traditionally abstained from deciding cases\\n\\nconcerning domestic relations.” Ingram v. Hayes, 866 F.2d 368, 369 (11th Cir.\\n\\n\\n\\n 13\\n Though Stone involved a decision to abstain, we see no reason to differently review a\\ndecision not to abstain.\\n\\n\\n 20\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 21 of 37\\n\\n\\n1988) (per curiam). The doctrine imposes two limits on our power. First, we may\\n\\nnot “issue divorce, alimony, and child custody decrees.” Stone, 135 F.3d at 1440\\n\\n(quoting Ankenbrandt v. Richards, 504 U.S. 689, 703, 112 S. Ct. 2206, 2215\\n\\n(1992)). Second, “even when subject-matter jurisdiction might be proper,” we\\n\\nabstain from exercising jurisdiction when “sufficient grounds” exist. Id.\\n\\n Here, the District Court did not issue a divorce, alimony, or child-custody\\n\\ndecree. And Defendants do not cite—and our research does not reveal—a single\\n\\ncase when this Court has held that abstention was appropriate when a party to the\\n\\nfederal-court proceeding was not a party to the state-court proceeding. Cf., e.g., id.\\n\\nat 1441 (“The exception enunciated in Ingram is to be read narrowly and does\\n\\nnot—at least, ordinarily—include third parties in its scope.”). In Stone, for\\n\\nexample, we held that abstention was inappropriate when a father and his daughter\\n\\nsued the father’s ex-sister- and ex-mother-in-law for tortious interference of his\\n\\ncustodial rights. Id. Those defendants were not parties to the state-court\\n\\nproceeding and “had no legal claim of custody whatsoever.” Id. Alliant was not a\\n\\nparty to the divorce proceedings in the Georgia Superior Court and like the Stone\\n\\nplaintiffs, did nothing more than “charge[] Defendants with a tort.” See id. at\\n\\n1440.\\n\\n In short, the District Court did not abuse its discretion in exercising diversity\\n\\njurisdiction. Cf. Kirby v. Mellenger, 830 F.2d 176, 179 (11th Cir. 1987) (per\\n\\n\\n\\n 21\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 22 of 37\\n\\n\\ncuriam) (“The less a case is a ‘core’ domestic relations case, e.g., one for a divorce\\n\\nor a simple child custody dispute, the less discretion the district court has to refuse\\n\\nto exercise its jurisdiction.”).\\n\\n D.\\n\\n Defendants argue that Alliant is collaterally estopped from proving that\\n\\nMarilyn did not give “reasonably equivalent value” for the transfers, which is an\\n\\nelement of a UFTA claim. See O.C.G.A. § 18-2-74(a)(2) (2010). In adjudicating\\n\\nthe Murphys’ divorce, the Georgia Superior Court was required to ensure that the\\n\\ndistribution of property between them was “equitable.” See Payson v. Payson, 552\\n\\nS.E.2d 839, 841 (Ga. 2001); see also O.C.G.A. § 19-5-13 (2018). Defendants\\n\\ninsist that Alliant cannot now challenge the transfers as fraudulent under the UFTA\\n\\nbecause the Superior Court already decided that issue in their favor.\\n\\n Under the full-faith-and-credit statute, see 28 U.S.C. § 1738, a district court\\n\\nmust afford “preclusive effect to a state court judgment to the same extent as\\n\\nwould courts of the state in which the judgment was entered.” Graham v. R.J.\\n\\nReynolds Tobacco Co., 857 F.3d 1169, 1181 (11th Cir. 2017) (en banc) (quoting\\n\\nKahn v. Smith Barney Shearson Inc., 115 F.3d 930, 933 (11th Cir. 1997)), cert.\\n\\ndenied, 138 S. Ct. 646 (2018). So we look to the preclusive effect that Georgia law\\n\\nwould give the divorce decree. Under Georgia law, issue preclusion, or collateral\\n\\n\\n\\n\\n 22\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 23 of 37\\n\\n\\nestoppel by another name, requires “identity of the parties or their privies.”\\n\\nWaldroup v. Greene Cty. Hosp. Auth., 463 S.E.2d 5, 7 (Ga. 1995) (per curiam).\\n\\n Nothing about the divorce decree precludes Alliant from challenging the\\n\\nadequacy of value that Marilyn gave for the transfers because it was not a party to\\n\\nthe divorce proceeding. And neither Vincent nor Marilyn represented Alliant’s\\n\\ninterests when they fraudulently transferred assets between themselves to\\n\\nimmunize Vincent from collection. Cf. Smith v. Wood, 154 S.E.2d 646, 649–50\\n\\n(Ga. Ct. App. 1967) (“Privity connotes those who are in law so connected with a\\n\\nparty to the judgment as to have such an identity of interest that the party to the\\n\\njudgment represented the same legal right . . . .” (emphasis added) (quoting Hixson\\n\\nv. Kansas City, 239 S.W.2d 341, 344 (Mo. 1951) (en banc))).\\n\\n E.\\n\\n Defendants relatedly argue that the District Court was required to abstain\\n\\nbecause Alliant’s suit is a collateral attack on a provision of the divorce decree—\\n\\nnamely the Georgia Superior Court’s determination that the distribution of\\n\\nproperty was fair to the parties. Defendants’ argument, though unartfully\\n\\narticulated, is that the Rooker-Feldman doctrine applies. Rooker-Feldman bars a\\n\\n“party losing in state court . . . from seeking what in substance would be appellate\\n\\nreview of the state judgment in a United States district court, based on the losing\\n\\nparty’s claim that the state judgment itself violates the loser’s federal rights.”\\n\\n\\n\\n 23\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 24 of 37\\n\\n\\nJohnson v. De Grandy, 512 U.S. 997, 1005–06, 114 S. Ct. 2647, 2654 (1994). But\\n\\nAlliant was not a party to the divorce proceeding, so Rooker-Feldman has no\\n\\napplication here. See id. at 1006, 114 S. Ct. at 2654 (holding that Rooker-Feldman\\n\\nwas inapplicable when a party in federal court was “not a party in the state court”\\n\\nbecause it was in “no position” to seek review of the state court’s judgment and\\n\\nthus “[did] not directly attack[] it in [the federal] proceeding”). 14\\n\\n Having found that the District Court was permitted to entertain this suit, we\\n\\nnow turn to the first merits question: whether the Court awarded one Plaintiff,\\n\\nAlliant 31, relief to which it was not entitled.\\n\\n III.\\n\\n Defendants argue that $1,478,489 of the Georgia judgment against it was\\n\\nimproper because Alliant 31 was not allowed to collect any of that amount without\\n\\njoining Alliant 31-A as a co-plaintiff. As explained, Alliant 31-A was dismissed\\n\\nearlier in the litigation. See supra note 2. By way of background, the Kentucky\\n\\njudgment was for $8,946,643 overall. As part of that overall total, however, the\\n\\nDistrict Court for the Eastern District of Kentucky awarded relief to Alliant 31 and\\n\\n\\n 14\\n Furthermore, it is unclear whether Rooker-Feldman even applies to a privy. See Lance\\nv. Dennis, 546 U.S. 459, 466 n.2, 126 S. Ct. 1198, 1202 n.2 (2006) (per curiam) (“[W]e need not\\naddress whether there are any circumstances, however limited, in which Rooker–Feldman may\\nbe applied against a party not named in an earlier state proceeding—e.g., where an estate takes a\\nde facto appeal in a district court of an earlier state decision involving the decedent.”). We do\\nnot reach this question because as we already explained, Alliant was not a privy to the divorce\\nproceedings. See supra pp. 22−23.\\n\\n\\n 24\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 25 of 37\\n\\n\\nAlliant 31-A in an amount of $1,478,489. Defendants argue that Alliant 31 (1) was\\n\\npermitted to prosecute a UFTA claim for its share of the $1,478,489 only and (2)\\n\\nbecause it failed to establish that share, it was entitled to collect none of it. To\\n\\nassess this argument, we describe the property interests that Alliant 31 had in the\\n\\nKentucky judgment that it could enforce in this UFTA action.\\n\\n To determine the meaning of a judgment, we apply “[o]rdinary principles of\\n\\nconstruction.” Gurley v. Lindsley, 459 F.2d 268, 275 (5th Cir.), mandate\\n\\nwithdrawn, 466 F.2d 498 (5th Cir. 1972) (per curiam).\\n\\n The Kentucky judgment, on its face, states that “[j]udgment is hereby\\n\\nentered in favor of Plaintiffs, Alliant Tax Credit Fund 31-A, Ltd. . . . and Alliant\\n\\nTax Credit 31, Inc.” Alliant Tax Credit Fund 31-A, Ltd. v. Nicholasville Cmty.\\n\\nHous., LLC, No. 5:07-cv-00388-KKC-REW, slip op. at 1 (E.D. Ky. Aug. 31, 2010)\\n\\n(order amending judgment), ECF No. 204. Through this judgment, Alliant 31 and\\n\\nAlliant 31-A became joint−judgment creditors because the legal right to enforce\\n\\nthe judgment was entered in each of their favors. As a joint creditor, Alliant 31\\n\\nhad a claim to the full $1,478,489 because a joint creditor “is entitled, along with\\n\\nanother creditor, to demand payment from a debtor.” Joint Creditor, Black’s Law\\n\\nDictionary 375 (7th ed. 1999). The District Court committed no error when it\\n\\nawarded Alliant this amount. Though Alliant 31-A might have a claim to part of\\n\\n\\n\\n\\n 25\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 26 of 37\\n\\n\\nthe $1,478,489, and though it might have a contribution action against Alliant 31,\\n\\nnothing prevented Alliant 31 from suing for the full amount.\\n\\n We turn now to the burden of proof under the UFTA.\\n\\n IV.\\n\\n Defendants argue that the District Court erroneously instructed the jury on\\n\\nthe burden of proof, stating that the correct burden under the UFTA is clear-and-\\n\\nconvincing evidence, not a preponderance of the evidence.15 We disagree that a\\n\\nUFTA claim is subject to this heightened burden of proof.\\n\\n First, preponderance of the evidence is the default standard in civil\\n\\nproceedings. O.C.G.A. § 24-14-3 (2018). Tellingly, Georgia law expressly carves\\n\\nout two civil actions that are subject to the clear-and-convincing standard, neither\\n\\nof which are actions under the UFTA. Id. (first citing id. § 51-1-29.5 (medical\\n\\nmalpractice claims arising out of emergency care); then citing id. § 51-12-5.1\\n\\n(punitive-damages claims)). Because Georgia’s General Assembly subjected two\\n\\nspecific causes of action to the clear-and-convincing standard, we decline to infer\\n\\nthat claims under the UFTA are also exempted from the preponderance-of-\\n\\nevidence default. Cf. Estate of Cummings v. Davenport, 906 F.3d 934, 942 (11th\\n\\n\\n\\n 15\\n Georgia’s General Assembly amended the UFTA in 2015 and changed the statute’s\\nname to the UVTA. In so doing, it specifically provided that preponderance is the burden of\\nproof. O.C.G.A. § 18-2-74(d) (2018); see also id. § 18-2-75(d). The parties agree we must\\napply the UFTA, however, which lacks this enunciation.\\n\\n\\n 26\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 27 of 37\\n\\n\\nCir. 2018) (“The expression of one thing implies the exclusion of others.”\\n\\n(alteration omitted) (quoting Antonin Scalia & Bryan A. Garner, Reading Law:\\n\\nThe Interpretation of Legal Texts § 10, at 107 (2012))), petition for cert. filed, No.\\n\\n18-1191 (U.S. Mar. 13, 2019).\\n\\n Second, the UVTA merely clarifies what had always been the law under the\\n\\nUFTA. Cf. Piamba Cortes v. Am. Airlines, Inc., 177 F.3d 1272, 1283 (11th Cir.\\n\\n1999) (“[A]n amendment containing new language may be intended ‘to clarify\\n\\nexisting law . . . .’” (quoting United States v. Sepulveda, 115 F.3d 882, 885 n.5\\n\\n(11th Cir. 1997))). The official commentary to the Uniform Law Commission’s\\n\\nVoidable Transactions Act, which Georgia’s UVTA was modeled on, explains that\\n\\nthe UVTA “rejects [states] that have imposed an extraordinary [evidentiary]\\n\\nstandard, typically ‘clear and convincing evidence.’” 16 Unif. Voidable\\n\\nTransactions Act § 4 cmt. n.10 (Unif. Law Comm’n 2014). Defendants give us no\\n\\nreason to believe that Georgia was one such state. Indeed, they point to no\\n\\ndecision applying Georgia law that has ever imposed a higher burden of proof in a\\n\\nfraudulent-transfer action.\\n\\n In short, the District Court correctly instructed the jury on the burden of\\n\\nproof. With that issue decided, we turn to the punitive-damages awards.\\n\\n\\n\\n 16\\n Georgia courts look to this commentary when interpreting Georgia’s fraudulent-\\ntransfer law. Bishop v. Patton, 706 S.E.2d 634, 640 (Ga. 2011).\\n\\n\\n 27\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 28 of 37\\n\\n\\n V.\\n\\n Defendants argue that the punitive-damages awards were improper because\\n\\npunitive damages may be awarded only in addition to compensatory damages,\\n\\nwhich were not awarded here. Marilyn argues alternatively that even if punitive\\n\\ndamages were proper, the District Court erred by forcing her to pay the award\\n\\nagainst Vincent from her kitty.\\n\\n A.\\n\\n In addition to recovering the value of its claim, a fraudulent-transfer creditor\\n\\ncan also recover compensatory damages—that is, damages that result from the\\n\\nfraudulent transfer itself. Defendants submit that Alliant could not recover\\n\\npunitive damages because it was awarded no compensatory damages. Neither the\\n\\npunitive-damages statute, the caselaw, nor the policy that underpins punitive\\n\\ndamages supports their argument.\\n\\n Alliant invoked the District Court’s diversity jurisdiction, which requires us\\n\\nto apply Georgia substantive law. Erie R.R. Co. v. Tompkins, 304 U.S. 64, 78, 58\\n\\nS. Ct. 817, 822 (1938). In determining the contents of Georgia law, decisions of\\n\\nthe Supreme Court of Georgia and the Georgia Court of Appeals control. See\\n\\nBravo v. United States, 577 F.3d 1324, 1325 (11th Cir. 2009) (per curiam)\\n\\n(“[F]ederal courts are bound by decisions of a state’s intermediate appellate courts\\n\\nunless there is persuasive evidence that the highest state court would rule\\n\\n\\n\\n 28\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 29 of 37\\n\\n\\notherwise.” (quoting King v. Order of United Commercial Travelers of Am., 333\\n\\nU.S. 153, 158, 68 S. Ct. 488, 491 (1948))).\\n\\n The punitive-damages statute articulates two restrictions on punitive\\n\\ndamages, neither of which is violated by the awards here. A court may award\\n\\npunitive damages “only in such tort actions in which it is proven by clear and\\n\\nconvincing evidence that the defendant’s actions showed . . . fraud.” O.C.G.A.\\n\\n§ 51-12-5.1(b) (2018). As relevant here, moreover, an award of punitive damages\\n\\nmay not exceed $250,000 unless the defendant “acted, or failed to act, with the\\n\\nspecific intent to cause harm.” Id. §§ 51-12-5.1(f), (g). Check and check: The jury\\n\\nfound fraud by clear-and-convincing evidence. And it found that Vincent had\\n\\nacted with specific intent to cause harm. Because the jury did not find that Marilyn\\n\\nhad acted with specific intent to cause harm, the punitive damages against her were\\n\\nproperly capped at the statutory maximum of $250,000.\\n\\n The Georgia Court of Appeals has repeatedly stated, moreover, that punitive\\n\\ndamages are available in fraudulent-transfer actions without once stating that\\n\\ncompensatory damages are a prerequisite to recovering them. See Interfinancial\\n\\nMidtown, Inc. v. Choate Constr. Co., 806 S.E.2d 255, 264 (Ga. Ct. App. 2017)\\n\\n(“Georgia law allowing the recovery of general and punitive damages for\\n\\nfraudulent conveyances survived the enactment of Georgia’s UFTA.”); Stinchcomb\\n\\nv. Wright, 628 S.E.2d 211, 215 (Ga. Ct. App. 2006) (“Punitive damages may be\\n\\n\\n\\n 29\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 30 of 37\\n\\n\\nawarded upon a finding of conversion or fraudulent conveyance.”); Cavin v.\\n\\nBrown, 538 S.E.2d 802, 806 (Ga. Ct. App. 2000) (“[P]unitive damages are\\n\\navailable in fraudulent conveyance actions . . . .”).\\n\\n Stinchcomb in particular negates Defendants’ theory that compensatory\\n\\ndamages are a prerequisite for punitive damages. The defendant there argued that\\n\\nan award of attorneys’ fees and punitive damages was improper because the jury\\n\\nhad awarded only specific performance, not compensatory damages. 628 S.E.2d at\\n\\n215. The court rejected that argument, holding, “Since the [plaintiffs] proved their\\n\\nclaims of fraudulent conveyance and were awarded specific performance, the trial\\n\\ncourt’s award of attorney fees and punitive damages was proper.” Id. at 215–16.\\n\\nVincent and Marilyn state that the award of specific performance distinguishes that\\n\\ncase from this case. As an initial matter, that assertion is factually incorrect\\n\\nbecause the District Court ordered Marilyn to turn over the fraudulently transferred\\n\\nassets or their proceeds. But even if the Court had invoked the legal remedy under\\n\\nthe UFTA, as it should have, Stinchcomb would still control. Whether a court\\n\\norders turnover of the assets or enters a money judgment for their value hinges\\n\\nonly on whether the assets or their proceeds are traceable. If they are, turnover is\\n\\nappropriate; if they aren’t, a money judgment should be entered. Either way, the\\n\\nneed to deter the transfer is the same. We explain this idea more below.\\n\\n\\n\\n\\n 30\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 31 of 37\\n\\n\\n One policy of punitive damages is deterrence. 1 Dan B. Dobbs, Dobbs Law\\n\\nof Remedies § 3.11(3), at 475−76 (2d ed. 1993). Without punitive damages,\\n\\nnothing other than costs would deter a debtor from attempting to fraudulently\\n\\ntransfer his assets. If he gets caught, so be it: The cost would simply be what was\\n\\nowed in the first place. See, e.g., SE Prop. Holdings, LLC v. Judkins, No. 1:17-\\n\\nCV-00413-TM-B, 2019 WL 177981, at *10 (S.D. Ala. Jan. 11, 2019) (“Without an\\n\\naward of punitive damages or attorneys’ fees, there would be no deterrence to a\\n\\ndebtor weighing whether to make a fraudulent transfer. This is because the debtor\\n\\nwould only lose the same asset he would have lost if he had not made a fraudulent\\n\\ntransfer.”); Kekona v. Bornemann, 349 P.3d 361, 372 (Haw. 2015) (“[A]t worst the\\n\\nfraudulent debtor is forced to pay what he or she already owed. Without the\\n\\npossibility of significant punitive damages, it would be difficult to deter this\\n\\nconduct.”). It thus makes sense that the UFTA would permit recovery for punitive\\n\\ndamages. See Dobbs, supra, § 3.11(10), at 516 (“[T]he need for punishment or\\n\\ndeterrence may be increased by reason of the very fact that the defendant will have\\n\\nno liability for compensatory damages.”).\\n\\n In short, the absence of compensatory damages did not preclude the award\\n\\nof punitive damages.\\n\\n B.\\n\\n\\n\\n\\n 31\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 32 of 37\\n\\n\\n Marilyn’s alternative argument—that she should not be responsible for\\n\\npaying Vincent’s punitive-damages award—is meritorious.\\n\\n Under the UFTA, a creditor may obtain “judgment [against the transferee]\\n\\nfor the value of the asset transferred . . . or the amount necessary to satisfy the\\n\\ncreditor’s claim, whichever is less.” O.C.G.A. § 18-2-78(b) (2010). After the jury\\n\\nreturned its verdict, the District Court should have entered two judgments—one\\n\\nagainst Marilyn (the transferee) and one against Vincent (the transferor):\\n\\n • A money judgment against Marilyn for $9,137,285.84 (the amount of the\\n claim, plus her $100,000 in punitive damages).\\n\\n • A money judgment against Vincent for $1,000,000 (the amount of his\\n punitive damages).\\n\\nThe Court erred when it required Marilyn to pay Vincent’s money judgment—\\n\\nawarded for his wrongdoings, mind you—out of her pocket. But Alliant\\n\\ncomplicates what seems to be a straightforward result.\\n\\n Alliant asserts that its “claim” within the meaning of § 18-2-78(b) includes\\n\\nthe $100,000 in punitive damages awarded against Vincent. Said differently, the\\n\\nDistrict Court should have entered a single money judgment against Marilyn, the\\n\\nentirety of which she would be personally responsible for. We are unsurprised that\\n\\nAlliant brings us not one case from any jurisdiction where a court has interpreted a\\n\\nfraudulent-transfer “claim” to include damages awarded for the transfer itself. We\\n\\nundertake our own analysis, however, and for two reasons, we cannot agree with\\n\\n\\n 32\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 33 of 37\\n\\n\\nAlliant’s assertion. First, a fraudulent-transfer action is derivative of some other\\n\\nright to relief. Alliant’s approach would collapse into one the action and the claim\\n\\nthat gave rise to that action. And second, the UVTA, which Georgia’s General\\n\\nAssembly replaced the UFTA with in 2015, confirms that “claim” excludes relief\\n\\nawarded for the fraudulent transfer itself. We discuss both reasons in turn.\\n\\n First, a fraudulent-transfer action is predicated on a claim that already exists.\\n\\nSee Dobbs, supra, § 2.8(1), at 191−92. Alliant incurred a claim to the amount of\\n\\nthe Kentucky judgment. Alliant then brought this UFTA action to recover the\\n\\nvalue of that claim. In the process, Alliant incurred a new, second claim against\\n\\nVincent when the Georgia jury awarded Alliant punitive damages for Vincent’s\\n\\nfraud. This second claim is extrinsic to the claim on which the UFTA action was\\n\\npredicated.\\n\\n Second, the UVTA confirms that “claim” under the UFTA cannot\\n\\nencompass relief for the fraudulent transfer itself. Cf. Piamba Cortes, 177 F.3d at\\n\\n1283 (“[A]n amendment containing new language may be intended ‘to clarify\\n\\nexisting law.’” (quoting Sepulveda, 115 F.3d at 885 n.5)). In replacing the UFTA\\n\\nwith the UVTA, Georgia’s General Assembly amended the definition of claim to\\n\\ninclude the following italicized language: “‘Claim,’ except for claim for relief,\\n\\nmeans a right to payment . . . .” O.C.G.A. § 18-2-71(3) (2018) (emphasis added).\\n\\nThe UVTA thus distinguishes “claim” and “claim for relief.” Whereas the “claim\\n\\n\\n\\n 33\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 34 of 37\\n\\n\\nfor relief” is the UFTA action itself, “claim” is the predicate on which that action is\\n\\nbased. As described below, this change merely clarified what had already been the\\n\\nlaw under the UFTA.\\n\\n Georgia’s General Assembly inserted into the UVTA two new subsections\\n\\non burden-of-proof and choice-of-law rules that govern a fraudulent-transfer\\n\\naction. These subsections are the only places where “claim for relief” appears in\\n\\nthe UVTA. They provide that\\n\\n • a UVTA plaintiff “has the burden of proving the elements of the claim\\n for relief by a preponderance of the evidence” and that\\n\\n • “[a] cause of action in the nature of a claim for relief under [the UVTA]\\n is governed by the law of the jurisdiction in which the debtor is located\\n when the transfer is made or the obligation is incurred.”\\n\\nId. §§ 18-2-74(d), -80(b) (emphasis added). But inserting these two subsections\\n\\nwould risk confusion under Alliant’s reading of “claim”: Do the burden-of-proof\\n\\nand choice-of-law rules apply to the UFTA action, the predicate claim, or both?\\n\\nRecognizing this risk, the General Assembly amended the definition of “claim” to\\n\\nmake explicit what had long been implicit: The “claim for relief” and the “claim”\\n\\nare two separate things. Cf. Scalia & Garner, supra, § 40, at 257 (stating that the\\n\\n“presumption that a change in language produces a change in meaning” does not\\n\\napply when codifications “revise the wording of the prior statute to provide for\\n\\nconsistency of expression”).\\n\\n\\n\\n\\n 34\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 35 of 37\\n\\n\\n In short, because Alliant’s claim did not include the punitive damages\\n\\nawarded against Vincent, the Georgia judgment is reversed to the extent it allowed\\n\\nAlliant to recover those damages from Marilyn. We now turn to Alliant’s cross-\\n\\nappeal.\\n\\n VI.\\n\\n Alliant cross-appeals the District Court’s denial of prejudgment interest\\n\\nunder Georgia law from the date the Kentucky judgment was entered to the date\\n\\nthe Georgia judgment was entered.\\n\\n Recall that the District Court awarded Alliant post-judgment interest. Under\\n\\nfederal law, the Kentucky judgment accrued interest from the moment that\\n\\njudgment was entered until it was paid. See 28 U.S.C. § 1961. By the time the\\n\\nGeorgia judgment incorporated the Kentucky judgment, the post-judgment interest\\n\\non the latter had accrued to $90,642.89. No one disputes that Alliant is entitled to\\n\\nthat amount. But Alliant wants prejudgment interest, too. The parties agree that\\n\\nAlliant’s entitlement to prejudgment interest hinges on Alliant’s UFTA claim\\n\\nbeing “liquidated” under Georgia law. We explain below that the claim was not\\n\\nliquidated as to Marilyn—from whom recovery must be had—so the Court was\\n\\ncorrect to deny Alliant prejudgment interest.\\n\\n Absent “affirmative countervailing federal interests,” the availability and\\n\\namount of prejudgment interest is governed by state law. AIG Baker Sterling\\n\\n\\n\\n 35\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 36 of 37\\n\\n\\nHeights, LLC v. Am. Multi-Cinema, Inc., 508 F.3d 995, 1001–02 (11th Cir. 2007)\\n\\n(quoting Esfeld v. Costa Crociere, S.P.A., 289 F.3d 1300, 1307 (11th Cir. 2002)).\\n\\nUnder Georgia law, “[a]ll liquidated demands, where by agreement or otherwise\\n\\nthe sum to be paid is fixed or certain, bear interest from the time the party shall\\n\\nbecome liable and bound to pay them; if payable on demand, they shall bear\\n\\ninterest from the time of the demand.” O.C.G.A. § 7-4-15 (2018). “[T]he sole\\n\\nprerequisite for an award of prejudgment interest on a liquidated claim is that a\\n\\ndemand be made before the entry of final judgment, so that the opposing party has\\n\\nan opportunity to contest an award of interest.” Gwinnett County v. Old Peachtree\\n\\nPartners, LLC, 764 S.E.2d 193, 200 (Ga. Ct. App. 2014).\\n\\n The only point in dispute is whether Alliant’s claim to the amount of the\\n\\nKentucky judgment was liquidated.\\n\\n A sum is liquidated when it is “fixed or certain based on . . . operation of\\n\\nlaw.” Those Certain Underwriters at Lloyds London v. DTI Logistics, Inc., 686\\n\\nS.E.2d 333, 339 (Ga. Ct. App. 2009). The full amount of the Kentucky judgment,\\n\\n$8,946,643, was fixed by law as to Vincent on the date the District Court for the\\n\\nEastern District of Kentucky entered judgment for that amount against him. But\\n\\nMarilyn is a different story. The conduct for which Marilyn is liable is receipt of\\n\\nthe transferred assets when she (1) did not act in good faith and (2) did not give\\n\\nreasonably equivalent value for them. See O.C.G.A. § 18-2-78(a) (2010). Because\\n\\n\\n\\n 36\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 37 of 37\\n\\n\\nthe jury was required to determine the values of each of those assets, the amount\\n\\nfor which she is personally liable did not become liquidated until the District Court\\n\\nentered the Georgia judgment.\\n\\n In short, Alliant is not entitled to any prejudgment interest under Georgia\\n\\nlaw because its claim for $8,946,643 was not previously liquidated as to Marilyn.\\n\\n VII.\\n\\n For these reasons, the District Court’s judgment is AFFIRMED in part and\\n\\nREVERSED in part. We REMAND for further proceedings not inconsistent with\\n\\nthis opinion.\\n\\n SO ORDERED.\\n\\n\\n\\n\\n 37\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4397093/\", \"author_raw\": \"TJOFLAT, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"TJOFLAT"},"judge2":{"kind":"string","value":"PRYOR"},"judge3":{"kind":"string","value":"MURPHY"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4619840/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: ALLIANT TAX CREDIT 31, INC, a Florida Corporation, Alliant Tax Credit Fund XXVII, Ltd., a Florida Limited Partnership, Alliant Tax Credit Tax Credit XXVII, Inc, a Florida Corporation, Alliant Tax Credit XI, Inc., a Florida Corporation, Alliant Tax Credit XI, Ltd., a Florida Limited Partnership, Plaintiffs - Counter Defendants - Appellees - Cross Appellants, v. M. Vincent MURPHY, III, Multifamily Housing Developers, L.L.C., a Georgia Limited Liability Company, Community Management Services, Inc., a Georgia Corporation, Gazebo Park Apartments of Acworth, LLC, a Georgia Limited Liability Company, Defendants - Appellants - Cross Appellees, Marilyn Murphy, Defendant - Counter Claimant - Appellant - Cross Appellee.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-15\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 15-14634 Date Filed: 05/15/2019 Page: 1 of 37\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 15-14634\n ________________________\n\n D.C. Docket No. 1:11-cv-00832-RWS\n\n\n\nALLIANT TAX CREDIT 31, INC,\na Florida corporation,\nALLIANT TAX CREDIT FUND XXVII, LTD.,\na Florida limited partnership,\nALLIANT TAX CREDIT TAX CREDIT XXVII, INC,\na Florida corporation,\nALLIANT TAX CREDIT XI, INC.,\na Florida corporation,\nALLIANT TAX CREDIT XI, LTD.,\na Florida limited partnership,\n\n Plaintiffs - Counter Defendants – Appellees -\n Cross Appellants,\n\n versus\n\nM. VINCENT MURPHY, III,\nMULTIFAMILY HOUSING DEVELOPERS, L.L.C.,\na Georgia limited liability company,\nCOMMUNITY MANAGEMENT SERVICES, INC.,\na Georgia corporation,\nGAZEBO PARK APARTMENTS OF ACWORTH, LLC,\na Georgia limited liability company,\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 2 of 37\n\n\n Defendants - Appellants - Cross Appellees,\n\nMARILYN MURPHY,\n\n Defendant - Counter Claimant - Appellant -\n Cross Appellee.\n\n ________________________\n\n Appeals from the United States District Court\n for the Northern District of Georgia\n ________________________\n\n (May 15, 2019)\n\nBefore TJOFLAT and WILLIAM PRYOR, Circuit Judges, and MURPHY, *\nDistrict Judge.\n\nTJOFLAT, Circuit Judge:\n\n This fraudulent-transfer case, like many such cases, is a suit about a suit. In\n\nthe first suit, Plaintiffs obtained a judgment in federal district court in Kentucky for\n\nbreach of a partnership contract. But when Plaintiffs tried to collect, they\n\ndiscovered that the once-wealthy Defendant was figuratively penniless. The\n\nsurprised Plaintiffs surmised that Defendant had colluded with his former wife to\n\nfraudulently transfer his assets to her (or to entities under her control) as part of\n\ntheir divorce settlement. So Plaintiffs sued—again—this time in federal district\n\ncourt in Georgia—to recover their judgment under Georgia’s fraudulent-transfer\n\n\n\n *\n Honorable Stephen J. Murphy, III, United States District Court for the Eastern District\nof Michigan, sitting by designation.\n\n\n 2\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 3 of 37\n\n\nstatute. Agreeing with Plaintiffs that fraudulent transfers had occurred, a jury\n\nreturned a verdict in their favor. The District Court entered judgment accordingly,\n\nand this appeal and cross-appeal followed.\n\n I.\n\n A.\n\n 1.\n\n The run-up to this suit began when Plaintiffs, five entities that we\n\ncollectively refer to as “Alliant,” 1 lent Defendant M. Vincent Murphy, III\n\ninvestment capital to build low-income housing units that were never completed.\n\nSo Alliant sued him and other guarantors of the debt in federal court in the Eastern\n\nDistrict of Kentucky for breach of their partnership contract. Alliant was joined in\n\nthat suit by Alliant Tax Credit Fund 31-A, Ltd. (“Alliant 31-A”), which also lent\n\ninvestment capital to Vincent. 2 Alliant and Alliant 31-A prevailed, and the District\n\nCourt for the Eastern District of Kentucky entered a judgment (the “Kentucky\n\njudgment”) in their favor for $8,946,643. Vincent appealed, and the Court of\n\n\n\n\n 1\n The full names are Alliant Tax Credit 31, L.L.C. (“Alliant 31”), Alliant Tax Credit Fund\nXXVII, Ltd. (“Alliant XXVII, Ltd.”), Alliant Tax Credit Fund XXVII, L.L.C. (“Alliant XXVII,\nL.L.C.”), Alliant Tax Credit XI, L.L.C. (“Alliant XI, L.L.C.”), and Alliant Tax Credit XI, Ltd.\n(“Alliant XI, Ltd.”).\n 2\n Alliant 31-A was dismissed by the District Court for the Northern District of Georgia\nbecause its presence would have destroyed subject-matter jurisdiction. For this reason (and\nothers that will become clear), we treat Alliant 31-A separately.\n\n\n 3\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 4 of 37\n\n\nAppeals for the Sixth Circuit affirmed. Alliant Tax Credit Fund 31-A, Ltd. v.\n\nMurphy, 494 F. App’x 561, 563 (6th Cir. 2012).\n\n But the fraudulent activity that gave rise to this suit began before the\n\nKentucky judgment was entered.\n\n Vincent and his wife, Marilyn Murphy, had earlier divorced in the Superior\n\nCourt of Fulton County, Georgia. The divorce decree incorporated a settlement\n\nagreement between them. As part of the agreement, Marilyn received from\n\nVincent several millions of dollars in cash and commercial paper, stock shares, a\n\nmountain cabin, household furnishings, and an apartment complex. These assets\n\nare the basis for the fraudulent-transfer action here. When Alliant sought to collect\n\non the Kentucky judgment, it found that Vincent was judgment proof. So it sued\n\nVincent for a second time.\n\n Alliant (but not Alliant 31-A) brought this action against Vincent, Marilyn,\n\nMultifamily Housing Developers, L.L.C. (“Multifamily Housing”), and\n\nCommunity Management Services, Inc. (“CMS”), 3 in the District Court for the\n\nNorthern District of Georgia under the Uniform Fraudulent Transfers Act (the\n\n“UFTA”), O.C.G.A. §§ 18-2-70 to 80 (2010), amended by the Uniform Voidable\n\n\n\n\n 3\n Alliant alleged that Multifamily Housing and CMS, both of which Marilyn controlled,\nwere also fraudulent transferees of some of Vincent’s assets.\n\n\n 4\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 5 of 37\n\n\nTransactions Act (the “UVTA”), O.C.G.A. §§ 18-2-70 to 85 (2015).4 The UFTA,\n\na quintessential fraudulent-transfer statute, allows creditors to void certain asset\n\ntransfers made by a debtor with the purpose of immunizing itself from collection.\n\nSee O.C.G.A. § 18-2-77 (2010). Alliant claimed that the Murphys’ divorce\n\nsettlement and Vincent’s asset transfers to Defendants were ruses to evade\n\nVincent’s creditors and thus sought to void those transfers. The case proceeded to\n\ntrial, and a jury returned an itemized verdict for Alliant after having found that\n\ntwenty-three transfers from Vincent to Defendants were fraudulent. The jury also\n\nfound that the Murphys were subject to punitive damages but that only Vincent had\n\nacted with the “specific intent to cause harm.” It awarded $1,000,000 in punitive\n\ndamages against him and $100,000 in punitive damages against Marilyn.\n\n 2.\n\n After the jury returned its verdict, the District Court for the Northern District\n\nof Georgia entered a final judgment (the “Georgia judgment”) for Alliant. Before\n\ndescribing what the judgment provided, we pause momentarily to note the\n\nremedies available under the UFTA.\n\n\n 4\n Georgia’s General Assembly amended the UFTA in 2015. See Uniform Voidable\nTransactions Act, 2015 Ga. Laws 1019 (codified at O.C.G.A. §§ 18-2-70 to 85 (2018)). As part\nof the amendment, the General Assembly changed the name of the statute. Some of the\namendments are consequential to issues we must decide on appeal. But the parties agree—and\nwe follow their lead—the UFTA is the version of the law we must apply. We discuss the\nUVTA—note the “V” in place of the “F”—at various points throughout this opinion; we make\nclear when we reference that currently enacted version of the statute.\n\n\n 5\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 6 of 37\n\n\n The UFTA provides creditors with both equitable and legal remedies. The\n\ncreditor may obtain, as an equitable remedy, “[a]voidance of the transfer . . . to the\n\nextent necessary to satisfy the creditor’s claim.” See id. § 18-2-77(a)(1). Or it may\n\nobtain, as a legal remedy, “judgment [against the transferee] for the value of the\n\nasset transferred . . . or the amount necessary to satisfy the creditor’s claim,\n\nwhichever is less.” See id. § 18-2-78(b).\n\n Alliant did not seek avoidance of any of the transfers made. Nor realistically\n\ncould it: Most of Vincent’s transfers were in the form of cash that has since been\n\nturned into proceeds that are likely untraceable. Rather, it sought a money\n\njudgment for the value of the assets transferred. Said differently, it sought the\n\nlegal remedy available under the UFTA.\n\n The Georgia judgment, which purported to implement the jury’s verdict,\n\nprovided that Alliant would receive the sum of $10,137,285.84, which consisted of\n\nthe amount of the Kentucky judgment ($8,946,643), interest on that judgment\n\n($90,642.84), and the punitive-damages awards against Vincent and Marilyn\n\n($1,000,000 and $100,000, respectively). The District Court for the Northern\n\nDistrict of Georgia also issued a writ of execution that directed the U.S. Marshal to\n\nseize Defendants’ assets to satisfy the judgment. 5\n\n\n 5\n In ordering the U.S. Marshal to seize the items identified in the judgment, the District\nCourt appeared to be entering an in rem judgment, as if Alliant had brought suit against the\nfraudulently conveyed assets or their proceeds themselves. The Court should have entered an in\n\n\n 6\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 7 of 37\n\n\n 3.\n\n Following the entry of the Georgia judgment, Marilyn satisfied the judgment\n\nin full, and Alliant moved to alter or amend the judgment, see Fed. R. Civ. P. 60, to\n\nallow prejudgment interest under Georgia law. The District Court for the Northern\n\nDistrict of Georgia denied this motion, reasoning that (1) Alliant’s UFTA claim\n\nwas unliquidated—that is, not reduced to a fixed sum—until the Georgia judgment\n\nwas entered and (2) under Georgia law, entitlement to prejudgment interest for\n\nunliquidated claims requires compliance with the Unliquidated Damages Interest\n\nAct, O.C.G.A. § 51-12-14 (2018), whose procedures Alliant had not followed.\n\nDefendants appealed the judgment entered pursuant to the verdict, and Alliant\n\ncross-appealed the order denying prejudgment interest.\n\n B.\n\n This appeal and cross-appeal require us to decide numerous discrete issues.\n\nWe first take up justiciability problems in Part II. We then turn to the merits,\n\naddressing Defendants’ arguments on appeal in Parts III through V and Alliant’s\n\narguments on cross-appeal in Part VI. We conclude in Part VII.\n\n II.\n\n\n\npersonam judgment against Vincent and Marilyn individually and issued writs of execution\nagainst their assets or writs of garnishment against their accounts. This error does not matter for\nour purposes, however, because the parties treated the judgment as though it were entered in\npersonam.\n\n\n 7\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 8 of 37\n\n\n We begin by addressing two jurisdictional bars to the District Court’s power\n\nto entertain this suit: mootness and subject-matter jurisdiction.6 We then address\n\nnon-jurisdictional bars. Defendants challenge the Court’s decision not to abstain\n\nfrom exercising its jurisdiction on three prudential grounds. First, that even if the\n\nparties are diverse of citizenship, this case falls within the domestic-relations\n\nexception to diversity jurisdiction. Second, that by entertaining this suit, the Court\n\nviolated the Rooker-Feldman doctrine. 7 And third, that Alliant is collaterally\n\nestopped from attacking the transfers as fraudulent.\n\n A.\n\n The first question, given Marilyn’s full satisfaction of the Georgia judgment:\n\nAre this appeal and cross-appeal moot? After oral argument, we asked the parties\n\nto brief this question and having reviewed their responses, we are satisfied that the\n\ncase remains a case or controversy within the meaning of Article III. See U.S.\n\nConst. art. III, § 2, cl. 1.\n\n “What matters [for mootness] is whether the parties’ actions objectively\n\nmanifest an intent to abandon the issues on appeal.” RES-GA Cobblestone, LLC v.\n\nBlake Constr. & Dev., LLC, 718 F.3d 1308, 1315 (11th Cir. 2013). So payment\n\n\n\n 6\n Unless otherwise stated, our use of “District Court” from this point forward refers to the\nCourt below—the District Court for the Northern District of Georgia.\n 7\n Rooker v. Fid. Tr. Co., 263 U.S. 413, 44 S. Ct. 149 (1923), and D.C. Court of Appeals v.\nFeldman, 460 U.S. 462, 103 S. Ct. 1303 (1983).\n\n\n 8\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 9 of 37\n\n\nmoots an appeal “only if the parties mutually intended a final settlement of all the\n\nclaims in dispute and a termination of the litigation.” McGowan v. King, Inc., 616\n\nF.2d 745, 747 (5th Cir. 1980) (per curiam). 8\n\n This case continues to breathe life. In Alvarez Perez v. Sanford-Orlando\n\nKennel Club, Inc., 518 F.3d 1302 (11th Cir. 2008), we applied the Supreme\n\nCourt’s decision in United States v. Hougham, 364 U.S. 310, 81 S. Ct. 13 (1960),\n\nand held that an appeal and cross-appeal situated much like the ones before us\n\ntoday were not moot. There, the plaintiff’s counsel signed satisfaction-of-\n\njudgment documents that were subsequently filed in the district court, but the\n\nplaintiff did not expressly reserve his right to appeal. 518 F.3d at 1305. But there,\n\nas here, the parties “continued to pursue their appeals.” Id. at 1307. There, as\n\nhere, the parties “filed supplemental letter briefs addressing the merits.” Id. And\n\nthere, as here, a party “inform[ed] us of a change in status involving one of the\n\ndefendants.” Id. In other words, “[i]nstead of filing a motion to dismiss the appeal\n\nas soon as a satisfaction was filed in the district court, both parties continued to\n\nlitigate the case in this Court as though nothing had changed.” Id. at 1308.\n\n In fact, Marilyn merely did the effective equivalent of posting a supersedeas\n\nbond—an act that by itself does not moot a case. See Fed. R. Civ. P. 62(b).\n\n\n 8\n In Bonner v. City of Prichard, 661 F.2d 1206 (11th Cir. 1981) (en banc), this Court\nadopted as binding precedent all decisions of the former Fifth Circuit handed down prior to\nOctober 1, 1981.\n\n\n 9\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 10 of 37\n\n\n When a judgment is appealed, both the winning and losing parties face risk\n\nin the period between the time judgment is entered and the time it is affirmed or\n\nreversed. The winning party seeks immediate satisfaction of the judgment because\n\nassets available at the time judgment is entered might disappear by the time it is\n\naffirmed. And the losing party seeks delayed satisfaction of judgment for a\n\nparallel reason: Assets available at the time judgment is entered might disappear by\n\nthe time it is reversed. A supersedeas bond insures both parties against these\n\nrespective risks. It permits a judgment debtor to “avoid the risk of satisfying the\n\njudgment only to find that restitution is impossible after reversal on appeal” and\n\n“secures the prevailing party against any loss sustained as a result of being forced\n\nto forgo execution on a judgment during the course of an ineffectual appeal.”\n\nPoplar Grove Planting & Ref. Co. v. Bache Halsey Stuart, Inc., 600 F.2d 1189,\n\n1191 (5th Cir. 1979).\n\n But posting a supersedeas bond does not moot an appeal. See Dale M. ex\n\nrel. Alice M. v. Bd. of Educ. of Bradley-Bourbonnais High Sch. Dist. No. 307, 237\n\nF.3d 813, 815 (7th Cir. 2001) (Posner, J.) (“A judgment creditor who pays the\n\njudgment pending appeal instead of posting a supersedeas bond (which would\n\nautomatically stay collection) is entitled to the return of its money if the decision is\n\nreversed, and so the payment does not moot the appeal unless the appellant has\n\nrelinquished his right to seek repayment if he wins.” (citation omitted)).\n\n\n\n 10\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 11 of 37\n\n\n Marilyn’s choice to pay the judgment does not render this case moot any\n\nmore than would her decision to post a supersedeas bond; she simply waived the\n\nprotection a bond would provide. Cf. 11 Charles Alan Wright et al., Federal\n\nPractice and Procedure § 2905, at 724−25 (3d ed. 2012) (“[A] person who cannot\n\nfurnish a supersedeas bond does not lose the right to appeal, although he does\n\nassume the risk of getting his money back again if the judgment is reversed.”).\n\n In short, the “objective manifestations of both parties clearly indicate that\n\nthey intended to pursue their positions in the appeal and cross-appeal.” Alvarez\n\nPerez, 518 F.3d at 1308. We turn now to subject-matter jurisdiction.\n\n B.\n\n Defendants maintain that the District Court lacked jurisdiction to entertain\n\nthe dispute because the parties were not diverse of citizenship.\n\n The District Court’s subject-matter jurisdiction has continued to present\n\ndifficulties in this case. Defendants appealed the Georgia judgment, and two\n\nmonths later, this Court sua sponte asked the parties to address subject-matter\n\njurisdiction because diversity jurisdiction was not evident from the pleadings. In\n\nresponse, Alliant moved to amend its complaint to simply allege the citizenships of\n\nall relevant entities. Defendants, in turn, moved to remand the case to the District\n\nCourt for a factual determination of subject-matter jurisdiction in the first instance.\n\nAfter reviewing the parties’ responses and motions, we remanded the case to the\n\n\n\n 11\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 12 of 37\n\n\nDistrict Court so that it might “fully resolve the question of the court’s subject-\n\nmatter jurisdiction over this action.” Alliant Tax Credit Fund 31-A, Ltd. v.\n\nMurphy, No. 15-14634-GG, slip op. at 1 (11th Cir. Apr. 10, 2017) (per curiam).\n\n On remand, Alliant filed a memorandum on Plaintiffs’ citizenships.\n\nPlaintiffs are a mixture of limited-liability companies and limited partnerships. 9\n\nSome of Plaintiffs’ members and partners are natural persons, but some are other\n\nlimited-liability companies, other partnerships, corporations, banks, and trusts.\n\nAlliant traced these entities’ citizenships, too. It included with its memorandum to\n\nthe District Court affidavits, declarations, and authenticated documents.\n\nDefendants responded that Alliant’s submissions were insufficient to confirm that\n\nall relevant entities were accounted for, as well as to confirm those entities’\n\ncitizenships. The Court observed that though Alliant had initially claimed that the\n\nsole citizenship of all five Plaintiffs was Florida, Alliant conceded in its\n\nmemorandum that Plaintiffs were also citizens of California, Delaware, the District\n\nof Columbia, Illinois, Nebraska, New York, Ohio, and Texas. So the Court\n\nrequired further documentary evidence of citizenship. For natural persons, it asked\n\nfor drivers licenses; for corporations, it asked for annual reports and articles of\n\nincorporation or governance documents; for limited partnerships and limited-\n\n\n\n 9\n Alliant 31, L.L.C., Alliant XXVII, L.L.C., and Alliant XI, L.L.C. are limited-liability\ncompanies. Alliant XXVII, Ltd. and Alliant XI, Ltd. are limited partnerships.\n\n\n 12\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 13 of 37\n\n\nliability companies, it asked for agreements; for banks, it asked for articles of\n\nassociation; and for trusts, it asked for organizational documents.\n\n After this jurisdictional discovery was complete, the District Court set out its\n\nfindings as to the parties’ citizenships:\n\nPlaintiffs\n\n • Alliant 31 was a citizen of Florida, California, and Illinois.\n\n • Alliant XXVII, Ltd. was a citizen of Florida, California, Illinois, and the\n District of Columbia.\n\n • Alliant XXVII, L.L.C. was a citizen of Florida, California, and Illinois.\n\n • Alliant XI, L.L.C. was a citizen of Florida, California, and Illinois.\n\n • Alliant XI, Ltd. was a citizen of Florida, California, Illinois, Delaware,\n New York, Texas, Nevada, and Ohio.\n\nDefendants\n\n • Vincent was a citizen of Georgia.\n\n • CMS was a citizen of Georgia.\n\n • Multifamily Housing was a citizen of Georgia.\n\n • Marilyn was a citizen of Georgia.\n\nAs such, it concluded that Alliant had established subject-matter jurisdiction by a\n\npreponderance of the evidence.\n\n Defendants, still unsatisfied that diversity jurisdiction was present, moved\n\nthis Court for leave to file supplemental briefing on the District Court’s factual\n\n\n 13\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 14 of 37\n\n\nfindings, its failure to sustain evidentiary objections, its admission into evidence of\n\nunreliable documents, and its failure to allow adversarial discovery. We granted\n\nDefendants’ motion, Alliant Tax Credit Fund 31-A, Ltd. v. Murphy, No. 15-14634-\n\nGG, slip op. at 2 (11th Cir. Nov. 9, 2017) (single-judge order), and now address\n\nthese jurisdictional issues.\n\n 1.\n\n First, Defendants argue that the record contains insufficient evidence to\n\nsupport the District Court’s findings on the citizenships of two inter vivos trusts,\n\nwhose names we have redacted.10 They contend that the trusts’ citizenships derive\n\nfrom their beneficiaries and that Alliant has not fully accounted for those\n\nbeneficiaries.\n\n Whether subject-matter jurisdiction exists presents a mixed question of law\n\nand fact. We review de novo a district court’s legal conclusions. Calderon v.\n\nBaker Concrete Constr., Inc., 771 F.3d 807, 810 (11th Cir. 2014). But we review\n\nfor clear error “any factual determinations necessary to establish jurisdiction,”\n\nDudley v. Eli Lilly & Co., 778 F.3d 909, 911 (11th Cir. 2014), including “findings\n\nregarding domicile,” McCormick v. Aderholt, 293 F.3d 1254, 1257 (11th Cir.\n\n2002) (per curiam). The party invoking federal jurisdiction “must prove, by a\n\n\n 10\n These trusts are members of a limited-liability company that is a member of another\nlimited-liability company that is a partner of a limited partnership that in turn is a member or\npartner of each of the five Plaintiffs in this case.\n\n\n 14\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 15 of 37\n\n\npreponderance of the evidence, facts supporting the exercise of jurisdiction.”\n\nCaron v. NCL (Bahamas), Ltd., 910 F.3d 1359, 1363–64 (11th Cir. 2018).\n\n A “traditional trust” holds the citizenship of its trustee, not of its\n\nbeneficiaries. See Americold Realty Tr. v. Conagra Foods, Inc., 136 S. Ct. 1012,\n\n1016 (2016); see also Raymond Loubier Irrevocable Tr. v. Loubier, 858 F.3d 719,\n\n730 (2d Cir. 2017) (“[F]or . . . traditional trusts, it is the citizenship of the trustees\n\nholding the legal right to sue on behalf of the trusts, not that of beneficiaries, that is\n\nrelevant to jurisdiction.”). A “traditional trust . . . generally describes a fiduciary\n\nrelationship regarding property where the trust cannot sue and be sued as an entity\n\nunder state law.” Wang ex rel. Wong v. New Mighty U.S. Tr., 843 F.3d 487, 495\n\n(D.C. Cir. 2016). So whether a trust is “traditional” requires us to refer to the “law\n\nof the state where the trust is formed.” Id.; see also, e.g., id. (holding that under\n\nDistrict of Columbia law, a trust lacked separate “juridical person status” and thus\n\ncould not “sue and be sued as an entity”); Loubier, 858 F.3d at 731 (holding that\n\nunder Florida law, a trust was not a “distinct juridical entit[y]” and thus was\n\n“incapable of being haled into court except through [its] trustee[]”).\n\n The two trusts here were formed in Wisconsin, and under Wisconsin law, a\n\ntrust is represented in litigation through its trustee. See Wis. Stat. § 701.0106\n\n(stating that the trust code incorporates the “common law of trusts”). Because the\n\ncode does not confer “juridical person status” on a trust itself, see New Mighty U.S.\n\n\n\n 15\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 16 of 37\n\n\nTr., 843 F.3d at 495, the trusts are traditional trusts whose citizenships are those of\n\ntheir trustees. The trustee of both trusts is a natural person who is domiciled in\n\nFlorida. As such, she is a Florida citizen. See McCormick, 293 F.3d at 1257.\n\n In short, Alliant has proven diversity jurisdiction by a preponderance of the\n\nevidence because if the trustee is diverse of Defendants, the trusts themselves are\n\ntoo.\n\n 2.\n\n Second, Defendants argue that the District Court erred by admitting the\n\nsworn affidavits of three persons who held leadership positions with various\n\nmembers or partners of the five Plaintiffs. We review a district court’s admission\n\nof evidence for abuse of discretion. Williams v. Mast Biosurgery USA, Inc., 644\n\nF.3d 1312, 1316 (11th Cir. 2011).\n\n Defendants argue that the affidavits lack foundation, see Fed. R. Evid. 602,\n\nbecause the affiants failed to state that only they could change the memberships of\n\ntheir respective entities. But the relevant question for foundation purposes is\n\nwhether the affiants had “personal knowledge” of the matter sworn to. See id.\n\nEach person laid a foundation for his respective affidavit by stating his position\n\nwith the relevant entity and that he had access to that entity’s records. As leaders,\n\nrather than as minor functionaries, they were well within their wheelhouses to\n\n\n\n\n 16\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 17 of 37\n\n\nswear to the entities’ compositions. Defendants’ argument goes to the weight of\n\nthe evidence, not to its admissibility.\n\n In short, the District Court was well within its discretion to admit the\n\naffidavits.\n\n 3.\n\n Third, Defendants challenge the operating agreements for Alliant XXVII,\n\nL.L.C. and Alliant XI, L.L.C. on which one affiant relies. They point to missing or\n\nwholly redacted pages and font inconsistencies among the pages. As such, they\n\nargue that the documents were inadmissible because they could not be\n\nauthenticated, see Fed. R. Evid. 901, and because they were hearsay that did not\n\ncomport with the business-records exception, see Fed. R. Evid. 803(6).\n\n We need not reach these issues because even in a record devoid of this\n\nevidence, the District Court’s factual findings on these entities’ citizenships was\n\nnot clearly erroneous. For both entities, Alliant submitted the later-issued\n\ncertificates of conversion from corporations to limited-liability companies. Those\n\ndocuments indicate that both Alliant XXVII, L.L.C. and Alliant XI, L.L.C. have\n\nonly one member and one general partner. So Defendants’ theory that other\n\nentities lurk in those entities’ structures is unfounded.\n\n 4.\n\n\n\n\n 17\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 18 of 37\n\n\n Fourth, Defendants argue that the District Court should have permitted them\n\nto obtain through additional jurisdictional discovery (1) the documentary evidence\n\nthat Alliant filed in Alliant Tax Credit Fund XVI, Ltd. v. Thomasville Community\n\nHousing, LLC, 713 F. App’x 821 (11th Cir. 2017) (per curiam), 11 and (2) a copy of\n\nthe partnership agreement between Alliant 31 and Alliant 31-A. 12 We review a\n\ndistrict court’s denial of jurisdictional discovery for abuse of discretion.\n\nCulverhouse v. Paulson & Co., 813 F.3d 991, 993 (11th Cir. 2016).\n\n Defendants’ underlying grievance is that Alliant cannot be trusted because it\n\nhas misrepresented its citizenship in other litigation, including litigation in this\n\ncircuit. And because one district judge in this circuit required certain documents of\n\nAlliant, the District Judge in this (unrelated) case should have too.\n\n To be sure, parties have a “‘qualified right to jurisdictional discovery,’\n\nmeaning that a district court abuses its discretion if it completely denies a party\n\njurisdictional discovery.” Am. Civil Liberties Union of Fla., Inc. v. City of\n\n\n\n\n 11\n Alliant XI, L.L.C., a Plaintiff here, was also a party to that case.\n 12\n We deal with this second request later. Defendants argue that the record contains\ninsufficient evidence that Alliant 31 meets the amount-in-controversy requirement. See 28\nU.S.C. § 1332(a) (requiring that a controversy “exceed[] the sum or value of $75,000, exclusive\nof interest and costs”). Alliant 31 and Alliant 31-A were awarded $1,478,489 via the Kentucky\njudgment. Defendants claim that each has partial ownership in that amount and that Alliant 31\nhas not proven that its own interest is at least $75,000. We explain later on, however, that\nAlliant 31 was entitled to sue for the full amount because it was a joint−judgment creditor. See\ninfra p. 25. As such, the amount-in-controversy requirement is met.\n\n\n 18\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 19 of 37\n\n\nSarasota, 859 F.3d 1337, 1341 (11th Cir. 2017) (citations omitted) (quoting Eaton\n\nv. Dorchester Dev., Inc., 692 F.2d 727, 729 n.7 (11th Cir. 1982)).\n\n The District Court here did not abuse its discretion. It did not “completely\n\ndeny” Defendants jurisdictional discovery. To the contrary, it ordered Alliant to\n\nproduce additional documentary evidence after we remanded the case. Moreover,\n\njust because one judge permitted a discovery request does not mean another judge\n\nwas obligated to do so. Defendants overlook a basic principle of appellate review:\n\nTwo district judges can reach two different determinations of what discovery to\n\npermit, and under abuse-of-discretion review, we are required to affirm both\n\ndecisions unless one judge has “made a clear error of judgment” or “applied the\n\nwrong legal standard.” See Josendis v. Wall to Wall Residence Repairs, Inc., 662\n\nF.3d 1292, 1307 (11th Cir. 2011) (quoting Guideone Elite Ins. Co. v. Old Cutler\n\nPresbyterian Church, Inc., 420 F.3d 1317, 1325 (11th Cir. 2005)); see also id. at\n\n1306−07 (“Discretion means the district court has a ‘range of choice, and that its\n\ndecision will not be disturbed as long as it stays within that range and is not\n\ninfluenced by any mistake of law.’” (quoting Betty K Agencies, Ltd. v. M/V\n\nMonada, 432 F.3d 1333, 1337 (11th Cir. 2005))). In other words, one district\n\njudge is not required to follow his brethren in lockstep on discovery matters, just as\n\nhe is not required to follow him in lockstep on any other decision. See United\n\nStates v. Cerceda, 172 F.3d 806, 812 n.6 (11th Cir. 1999) (en banc) (per curiam)\n\n\n\n 19\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 20 of 37\n\n\n(“The opinion of a district court carries no precedential weight, even within the\n\nsame district.”). So we do not evaluate this Judge’s decision in light of another’s\n\ndecision.\n\n In short, nothing about the District Court’s finding of subject-matter\n\njurisdiction, procedurally or substantively, permits reversal. The Court’s\n\nfactfinding was not clearly erroneous. Its evidentiary conclusions were not legally\n\nincorrect. And its decision not to entertain additional discovery was not an abuse\n\nof discretion.\n\n That’s it for the jurisdictional wrinkles, but Defendants offer three other\n\nreasons for why the District Court should have evaded the merits.\n\n C.\n\n Defendants maintain that the District Court was required to abstain under the\n\ndomestic-relations exception to diversity jurisdiction. We review for abuse of a\n\ndiscretion a district court’s abstention decision under the domestic-relations\n\nexception. Stone v. Wall, 135 F.3d 1438, 1441 (11th Cir. 1998) (per curiam),\n\ncertified question answered, 734 So. 2d 1038 (Fla. 1999). 13\n\n “The federal judiciary has traditionally abstained from deciding cases\n\nconcerning domestic relations.” Ingram v. Hayes, 866 F.2d 368, 369 (11th Cir.\n\n\n\n 13\n Though Stone involved a decision to abstain, we see no reason to differently review a\ndecision not to abstain.\n\n\n 20\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 21 of 37\n\n\n1988) (per curiam). The doctrine imposes two limits on our power. First, we may\n\nnot “issue divorce, alimony, and child custody decrees.” Stone, 135 F.3d at 1440\n\n(quoting Ankenbrandt v. Richards, 504 U.S. 689, 703, 112 S. Ct. 2206, 2215\n\n(1992)). Second, “even when subject-matter jurisdiction might be proper,” we\n\nabstain from exercising jurisdiction when “sufficient grounds” exist. Id.\n\n Here, the District Court did not issue a divorce, alimony, or child-custody\n\ndecree. And Defendants do not cite—and our research does not reveal—a single\n\ncase when this Court has held that abstention was appropriate when a party to the\n\nfederal-court proceeding was not a party to the state-court proceeding. Cf., e.g., id.\n\nat 1441 (“The exception enunciated in Ingram is to be read narrowly and does\n\nnot—at least, ordinarily—include third parties in its scope.”). In Stone, for\n\nexample, we held that abstention was inappropriate when a father and his daughter\n\nsued the father’s ex-sister- and ex-mother-in-law for tortious interference of his\n\ncustodial rights. Id. Those defendants were not parties to the state-court\n\nproceeding and “had no legal claim of custody whatsoever.” Id. Alliant was not a\n\nparty to the divorce proceedings in the Georgia Superior Court and like the Stone\n\nplaintiffs, did nothing more than “charge[] Defendants with a tort.” See id. at\n\n1440.\n\n In short, the District Court did not abuse its discretion in exercising diversity\n\njurisdiction. Cf. Kirby v. Mellenger, 830 F.2d 176, 179 (11th Cir. 1987) (per\n\n\n\n 21\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 22 of 37\n\n\ncuriam) (“The less a case is a ‘core’ domestic relations case, e.g., one for a divorce\n\nor a simple child custody dispute, the less discretion the district court has to refuse\n\nto exercise its jurisdiction.”).\n\n D.\n\n Defendants argue that Alliant is collaterally estopped from proving that\n\nMarilyn did not give “reasonably equivalent value” for the transfers, which is an\n\nelement of a UFTA claim. See O.C.G.A. § 18-2-74(a)(2) (2010). In adjudicating\n\nthe Murphys’ divorce, the Georgia Superior Court was required to ensure that the\n\ndistribution of property between them was “equitable.” See Payson v. Payson, 552\n\nS.E.2d 839, 841 (Ga. 2001); see also O.C.G.A. § 19-5-13 (2018). Defendants\n\ninsist that Alliant cannot now challenge the transfers as fraudulent under the UFTA\n\nbecause the Superior Court already decided that issue in their favor.\n\n Under the full-faith-and-credit statute, see 28 U.S.C. § 1738, a district court\n\nmust afford “preclusive effect to a state court judgment to the same extent as\n\nwould courts of the state in which the judgment was entered.” Graham v. R.J.\n\nReynolds Tobacco Co., 857 F.3d 1169, 1181 (11th Cir. 2017) (en banc) (quoting\n\nKahn v. Smith Barney Shearson Inc., 115 F.3d 930, 933 (11th Cir. 1997)), cert.\n\ndenied, 138 S. Ct. 646 (2018). So we look to the preclusive effect that Georgia law\n\nwould give the divorce decree. Under Georgia law, issue preclusion, or collateral\n\n\n\n\n 22\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 23 of 37\n\n\nestoppel by another name, requires “identity of the parties or their privies.”\n\nWaldroup v. Greene Cty. Hosp. Auth., 463 S.E.2d 5, 7 (Ga. 1995) (per curiam).\n\n Nothing about the divorce decree precludes Alliant from challenging the\n\nadequacy of value that Marilyn gave for the transfers because it was not a party to\n\nthe divorce proceeding. And neither Vincent nor Marilyn represented Alliant’s\n\ninterests when they fraudulently transferred assets between themselves to\n\nimmunize Vincent from collection. Cf. Smith v. Wood, 154 S.E.2d 646, 649–50\n\n(Ga. Ct. App. 1967) (“Privity connotes those who are in law so connected with a\n\nparty to the judgment as to have such an identity of interest that the party to the\n\njudgment represented the same legal right . . . .” (emphasis added) (quoting Hixson\n\nv. Kansas City, 239 S.W.2d 341, 344 (Mo. 1951) (en banc))).\n\n E.\n\n Defendants relatedly argue that the District Court was required to abstain\n\nbecause Alliant’s suit is a collateral attack on a provision of the divorce decree—\n\nnamely the Georgia Superior Court’s determination that the distribution of\n\nproperty was fair to the parties. Defendants’ argument, though unartfully\n\narticulated, is that the Rooker-Feldman doctrine applies. Rooker-Feldman bars a\n\n“party losing in state court . . . from seeking what in substance would be appellate\n\nreview of the state judgment in a United States district court, based on the losing\n\nparty’s claim that the state judgment itself violates the loser’s federal rights.”\n\n\n\n 23\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 24 of 37\n\n\nJohnson v. De Grandy, 512 U.S. 997, 1005–06, 114 S. Ct. 2647, 2654 (1994). But\n\nAlliant was not a party to the divorce proceeding, so Rooker-Feldman has no\n\napplication here. See id. at 1006, 114 S. Ct. at 2654 (holding that Rooker-Feldman\n\nwas inapplicable when a party in federal court was “not a party in the state court”\n\nbecause it was in “no position” to seek review of the state court’s judgment and\n\nthus “[did] not directly attack[] it in [the federal] proceeding”). 14\n\n Having found that the District Court was permitted to entertain this suit, we\n\nnow turn to the first merits question: whether the Court awarded one Plaintiff,\n\nAlliant 31, relief to which it was not entitled.\n\n III.\n\n Defendants argue that $1,478,489 of the Georgia judgment against it was\n\nimproper because Alliant 31 was not allowed to collect any of that amount without\n\njoining Alliant 31-A as a co-plaintiff. As explained, Alliant 31-A was dismissed\n\nearlier in the litigation. See supra note 2. By way of background, the Kentucky\n\njudgment was for $8,946,643 overall. As part of that overall total, however, the\n\nDistrict Court for the Eastern District of Kentucky awarded relief to Alliant 31 and\n\n\n 14\n Furthermore, it is unclear whether Rooker-Feldman even applies to a privy. See Lance\nv. Dennis, 546 U.S. 459, 466 n.2, 126 S. Ct. 1198, 1202 n.2 (2006) (per curiam) (“[W]e need not\naddress whether there are any circumstances, however limited, in which Rooker–Feldman may\nbe applied against a party not named in an earlier state proceeding—e.g., where an estate takes a\nde facto appeal in a district court of an earlier state decision involving the decedent.”). We do\nnot reach this question because as we already explained, Alliant was not a privy to the divorce\nproceedings. See supra pp. 22−23.\n\n\n 24\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 25 of 37\n\n\nAlliant 31-A in an amount of $1,478,489. Defendants argue that Alliant 31 (1) was\n\npermitted to prosecute a UFTA claim for its share of the $1,478,489 only and (2)\n\nbecause it failed to establish that share, it was entitled to collect none of it. To\n\nassess this argument, we describe the property interests that Alliant 31 had in the\n\nKentucky judgment that it could enforce in this UFTA action.\n\n To determine the meaning of a judgment, we apply “[o]rdinary principles of\n\nconstruction.” Gurley v. Lindsley, 459 F.2d 268, 275 (5th Cir.), mandate\n\nwithdrawn, 466 F.2d 498 (5th Cir. 1972) (per curiam).\n\n The Kentucky judgment, on its face, states that “[j]udgment is hereby\n\nentered in favor of Plaintiffs, Alliant Tax Credit Fund 31-A, Ltd. . . . and Alliant\n\nTax Credit 31, Inc.” Alliant Tax Credit Fund 31-A, Ltd. v. Nicholasville Cmty.\n\nHous., LLC, No. 5:07-cv-00388-KKC-REW, slip op. at 1 (E.D. Ky. Aug. 31, 2010)\n\n(order amending judgment), ECF No. 204. Through this judgment, Alliant 31 and\n\nAlliant 31-A became joint−judgment creditors because the legal right to enforce\n\nthe judgment was entered in each of their favors. As a joint creditor, Alliant 31\n\nhad a claim to the full $1,478,489 because a joint creditor “is entitled, along with\n\nanother creditor, to demand payment from a debtor.” Joint Creditor, Black’s Law\n\nDictionary 375 (7th ed. 1999). The District Court committed no error when it\n\nawarded Alliant this amount. Though Alliant 31-A might have a claim to part of\n\n\n\n\n 25\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 26 of 37\n\n\nthe $1,478,489, and though it might have a contribution action against Alliant 31,\n\nnothing prevented Alliant 31 from suing for the full amount.\n\n We turn now to the burden of proof under the UFTA.\n\n IV.\n\n Defendants argue that the District Court erroneously instructed the jury on\n\nthe burden of proof, stating that the correct burden under the UFTA is clear-and-\n\nconvincing evidence, not a preponderance of the evidence.15 We disagree that a\n\nUFTA claim is subject to this heightened burden of proof.\n\n First, preponderance of the evidence is the default standard in civil\n\nproceedings. O.C.G.A. § 24-14-3 (2018). Tellingly, Georgia law expressly carves\n\nout two civil actions that are subject to the clear-and-convincing standard, neither\n\nof which are actions under the UFTA. Id. (first citing id. § 51-1-29.5 (medical\n\nmalpractice claims arising out of emergency care); then citing id. § 51-12-5.1\n\n(punitive-damages claims)). Because Georgia’s General Assembly subjected two\n\nspecific causes of action to the clear-and-convincing standard, we decline to infer\n\nthat claims under the UFTA are also exempted from the preponderance-of-\n\nevidence default. Cf. Estate of Cummings v. Davenport, 906 F.3d 934, 942 (11th\n\n\n\n 15\n Georgia’s General Assembly amended the UFTA in 2015 and changed the statute’s\nname to the UVTA. In so doing, it specifically provided that preponderance is the burden of\nproof. O.C.G.A. § 18-2-74(d) (2018); see also id. § 18-2-75(d). The parties agree we must\napply the UFTA, however, which lacks this enunciation.\n\n\n 26\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 27 of 37\n\n\nCir. 2018) (“The expression of one thing implies the exclusion of others.”\n\n(alteration omitted) (quoting Antonin Scalia & Bryan A. Garner, Reading Law:\n\nThe Interpretation of Legal Texts § 10, at 107 (2012))), petition for cert. filed, No.\n\n18-1191 (U.S. Mar. 13, 2019).\n\n Second, the UVTA merely clarifies what had always been the law under the\n\nUFTA. Cf. Piamba Cortes v. Am. Airlines, Inc., 177 F.3d 1272, 1283 (11th Cir.\n\n1999) (“[A]n amendment containing new language may be intended ‘to clarify\n\nexisting law . . . .’” (quoting United States v. Sepulveda, 115 F.3d 882, 885 n.5\n\n(11th Cir. 1997))). The official commentary to the Uniform Law Commission’s\n\nVoidable Transactions Act, which Georgia’s UVTA was modeled on, explains that\n\nthe UVTA “rejects [states] that have imposed an extraordinary [evidentiary]\n\nstandard, typically ‘clear and convincing evidence.’” 16 Unif. Voidable\n\nTransactions Act § 4 cmt. n.10 (Unif. Law Comm’n 2014). Defendants give us no\n\nreason to believe that Georgia was one such state. Indeed, they point to no\n\ndecision applying Georgia law that has ever imposed a higher burden of proof in a\n\nfraudulent-transfer action.\n\n In short, the District Court correctly instructed the jury on the burden of\n\nproof. With that issue decided, we turn to the punitive-damages awards.\n\n\n\n 16\n Georgia courts look to this commentary when interpreting Georgia’s fraudulent-\ntransfer law. Bishop v. Patton, 706 S.E.2d 634, 640 (Ga. 2011).\n\n\n 27\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 28 of 37\n\n\n V.\n\n Defendants argue that the punitive-damages awards were improper because\n\npunitive damages may be awarded only in addition to compensatory damages,\n\nwhich were not awarded here. Marilyn argues alternatively that even if punitive\n\ndamages were proper, the District Court erred by forcing her to pay the award\n\nagainst Vincent from her kitty.\n\n A.\n\n In addition to recovering the value of its claim, a fraudulent-transfer creditor\n\ncan also recover compensatory damages—that is, damages that result from the\n\nfraudulent transfer itself. Defendants submit that Alliant could not recover\n\npunitive damages because it was awarded no compensatory damages. Neither the\n\npunitive-damages statute, the caselaw, nor the policy that underpins punitive\n\ndamages supports their argument.\n\n Alliant invoked the District Court’s diversity jurisdiction, which requires us\n\nto apply Georgia substantive law. Erie R.R. Co. v. Tompkins, 304 U.S. 64, 78, 58\n\nS. Ct. 817, 822 (1938). In determining the contents of Georgia law, decisions of\n\nthe Supreme Court of Georgia and the Georgia Court of Appeals control. See\n\nBravo v. United States, 577 F.3d 1324, 1325 (11th Cir. 2009) (per curiam)\n\n(“[F]ederal courts are bound by decisions of a state’s intermediate appellate courts\n\nunless there is persuasive evidence that the highest state court would rule\n\n\n\n 28\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 29 of 37\n\n\notherwise.” (quoting King v. Order of United Commercial Travelers of Am., 333\n\nU.S. 153, 158, 68 S. Ct. 488, 491 (1948))).\n\n The punitive-damages statute articulates two restrictions on punitive\n\ndamages, neither of which is violated by the awards here. A court may award\n\npunitive damages “only in such tort actions in which it is proven by clear and\n\nconvincing evidence that the defendant’s actions showed . . . fraud.” O.C.G.A.\n\n§ 51-12-5.1(b) (2018). As relevant here, moreover, an award of punitive damages\n\nmay not exceed $250,000 unless the defendant “acted, or failed to act, with the\n\nspecific intent to cause harm.” Id. §§ 51-12-5.1(f), (g). Check and check: The jury\n\nfound fraud by clear-and-convincing evidence. And it found that Vincent had\n\nacted with specific intent to cause harm. Because the jury did not find that Marilyn\n\nhad acted with specific intent to cause harm, the punitive damages against her were\n\nproperly capped at the statutory maximum of $250,000.\n\n The Georgia Court of Appeals has repeatedly stated, moreover, that punitive\n\ndamages are available in fraudulent-transfer actions without once stating that\n\ncompensatory damages are a prerequisite to recovering them. See Interfinancial\n\nMidtown, Inc. v. Choate Constr. Co., 806 S.E.2d 255, 264 (Ga. Ct. App. 2017)\n\n(“Georgia law allowing the recovery of general and punitive damages for\n\nfraudulent conveyances survived the enactment of Georgia’s UFTA.”); Stinchcomb\n\nv. Wright, 628 S.E.2d 211, 215 (Ga. Ct. App. 2006) (“Punitive damages may be\n\n\n\n 29\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 30 of 37\n\n\nawarded upon a finding of conversion or fraudulent conveyance.”); Cavin v.\n\nBrown, 538 S.E.2d 802, 806 (Ga. Ct. App. 2000) (“[P]unitive damages are\n\navailable in fraudulent conveyance actions . . . .”).\n\n Stinchcomb in particular negates Defendants’ theory that compensatory\n\ndamages are a prerequisite for punitive damages. The defendant there argued that\n\nan award of attorneys’ fees and punitive damages was improper because the jury\n\nhad awarded only specific performance, not compensatory damages. 628 S.E.2d at\n\n215. The court rejected that argument, holding, “Since the [plaintiffs] proved their\n\nclaims of fraudulent conveyance and were awarded specific performance, the trial\n\ncourt’s award of attorney fees and punitive damages was proper.” Id. at 215–16.\n\nVincent and Marilyn state that the award of specific performance distinguishes that\n\ncase from this case. As an initial matter, that assertion is factually incorrect\n\nbecause the District Court ordered Marilyn to turn over the fraudulently transferred\n\nassets or their proceeds. But even if the Court had invoked the legal remedy under\n\nthe UFTA, as it should have, Stinchcomb would still control. Whether a court\n\norders turnover of the assets or enters a money judgment for their value hinges\n\nonly on whether the assets or their proceeds are traceable. If they are, turnover is\n\nappropriate; if they aren’t, a money judgment should be entered. Either way, the\n\nneed to deter the transfer is the same. We explain this idea more below.\n\n\n\n\n 30\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 31 of 37\n\n\n One policy of punitive damages is deterrence. 1 Dan B. Dobbs, Dobbs Law\n\nof Remedies § 3.11(3), at 475−76 (2d ed. 1993). Without punitive damages,\n\nnothing other than costs would deter a debtor from attempting to fraudulently\n\ntransfer his assets. If he gets caught, so be it: The cost would simply be what was\n\nowed in the first place. See, e.g., SE Prop. Holdings, LLC v. Judkins, No. 1:17-\n\nCV-00413-TM-B, 2019 WL 177981, at *10 (S.D. Ala. Jan. 11, 2019) (“Without an\n\naward of punitive damages or attorneys’ fees, there would be no deterrence to a\n\ndebtor weighing whether to make a fraudulent transfer. This is because the debtor\n\nwould only lose the same asset he would have lost if he had not made a fraudulent\n\ntransfer.”); Kekona v. Bornemann, 349 P.3d 361, 372 (Haw. 2015) (“[A]t worst the\n\nfraudulent debtor is forced to pay what he or she already owed. Without the\n\npossibility of significant punitive damages, it would be difficult to deter this\n\nconduct.”). It thus makes sense that the UFTA would permit recovery for punitive\n\ndamages. See Dobbs, supra, § 3.11(10), at 516 (“[T]he need for punishment or\n\ndeterrence may be increased by reason of the very fact that the defendant will have\n\nno liability for compensatory damages.”).\n\n In short, the absence of compensatory damages did not preclude the award\n\nof punitive damages.\n\n B.\n\n\n\n\n 31\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 32 of 37\n\n\n Marilyn’s alternative argument—that she should not be responsible for\n\npaying Vincent’s punitive-damages award—is meritorious.\n\n Under the UFTA, a creditor may obtain “judgment [against the transferee]\n\nfor the value of the asset transferred . . . or the amount necessary to satisfy the\n\ncreditor’s claim, whichever is less.” O.C.G.A. § 18-2-78(b) (2010). After the jury\n\nreturned its verdict, the District Court should have entered two judgments—one\n\nagainst Marilyn (the transferee) and one against Vincent (the transferor):\n\n • A money judgment against Marilyn for $9,137,285.84 (the amount of the\n claim, plus her $100,000 in punitive damages).\n\n • A money judgment against Vincent for $1,000,000 (the amount of his\n punitive damages).\n\nThe Court erred when it required Marilyn to pay Vincent’s money judgment—\n\nawarded for his wrongdoings, mind you—out of her pocket. But Alliant\n\ncomplicates what seems to be a straightforward result.\n\n Alliant asserts that its “claim” within the meaning of § 18-2-78(b) includes\n\nthe $100,000 in punitive damages awarded against Vincent. Said differently, the\n\nDistrict Court should have entered a single money judgment against Marilyn, the\n\nentirety of which she would be personally responsible for. We are unsurprised that\n\nAlliant brings us not one case from any jurisdiction where a court has interpreted a\n\nfraudulent-transfer “claim” to include damages awarded for the transfer itself. We\n\nundertake our own analysis, however, and for two reasons, we cannot agree with\n\n\n 32\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 33 of 37\n\n\nAlliant’s assertion. First, a fraudulent-transfer action is derivative of some other\n\nright to relief. Alliant’s approach would collapse into one the action and the claim\n\nthat gave rise to that action. And second, the UVTA, which Georgia’s General\n\nAssembly replaced the UFTA with in 2015, confirms that “claim” excludes relief\n\nawarded for the fraudulent transfer itself. We discuss both reasons in turn.\n\n First, a fraudulent-transfer action is predicated on a claim that already exists.\n\nSee Dobbs, supra, § 2.8(1), at 191−92. Alliant incurred a claim to the amount of\n\nthe Kentucky judgment. Alliant then brought this UFTA action to recover the\n\nvalue of that claim. In the process, Alliant incurred a new, second claim against\n\nVincent when the Georgia jury awarded Alliant punitive damages for Vincent’s\n\nfraud. This second claim is extrinsic to the claim on which the UFTA action was\n\npredicated.\n\n Second, the UVTA confirms that “claim” under the UFTA cannot\n\nencompass relief for the fraudulent transfer itself. Cf. Piamba Cortes, 177 F.3d at\n\n1283 (“[A]n amendment containing new language may be intended ‘to clarify\n\nexisting law.’” (quoting Sepulveda, 115 F.3d at 885 n.5)). In replacing the UFTA\n\nwith the UVTA, Georgia’s General Assembly amended the definition of claim to\n\ninclude the following italicized language: “‘Claim,’ except for claim for relief,\n\nmeans a right to payment . . . .” O.C.G.A. § 18-2-71(3) (2018) (emphasis added).\n\nThe UVTA thus distinguishes “claim” and “claim for relief.” Whereas the “claim\n\n\n\n 33\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 34 of 37\n\n\nfor relief” is the UFTA action itself, “claim” is the predicate on which that action is\n\nbased. As described below, this change merely clarified what had already been the\n\nlaw under the UFTA.\n\n Georgia’s General Assembly inserted into the UVTA two new subsections\n\non burden-of-proof and choice-of-law rules that govern a fraudulent-transfer\n\naction. These subsections are the only places where “claim for relief” appears in\n\nthe UVTA. They provide that\n\n • a UVTA plaintiff “has the burden of proving the elements of the claim\n for relief by a preponderance of the evidence” and that\n\n • “[a] cause of action in the nature of a claim for relief under [the UVTA]\n is governed by the law of the jurisdiction in which the debtor is located\n when the transfer is made or the obligation is incurred.”\n\nId. §§ 18-2-74(d), -80(b) (emphasis added). But inserting these two subsections\n\nwould risk confusion under Alliant’s reading of “claim”: Do the burden-of-proof\n\nand choice-of-law rules apply to the UFTA action, the predicate claim, or both?\n\nRecognizing this risk, the General Assembly amended the definition of “claim” to\n\nmake explicit what had long been implicit: The “claim for relief” and the “claim”\n\nare two separate things. Cf. Scalia & Garner, supra, § 40, at 257 (stating that the\n\n“presumption that a change in language produces a change in meaning” does not\n\napply when codifications “revise the wording of the prior statute to provide for\n\nconsistency of expression”).\n\n\n\n\n 34\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 35 of 37\n\n\n In short, because Alliant’s claim did not include the punitive damages\n\nawarded against Vincent, the Georgia judgment is reversed to the extent it allowed\n\nAlliant to recover those damages from Marilyn. We now turn to Alliant’s cross-\n\nappeal.\n\n VI.\n\n Alliant cross-appeals the District Court’s denial of prejudgment interest\n\nunder Georgia law from the date the Kentucky judgment was entered to the date\n\nthe Georgia judgment was entered.\n\n Recall that the District Court awarded Alliant post-judgment interest. Under\n\nfederal law, the Kentucky judgment accrued interest from the moment that\n\njudgment was entered until it was paid. See 28 U.S.C. § 1961. By the time the\n\nGeorgia judgment incorporated the Kentucky judgment, the post-judgment interest\n\non the latter had accrued to $90,642.89. No one disputes that Alliant is entitled to\n\nthat amount. But Alliant wants prejudgment interest, too. The parties agree that\n\nAlliant’s entitlement to prejudgment interest hinges on Alliant’s UFTA claim\n\nbeing “liquidated” under Georgia law. We explain below that the claim was not\n\nliquidated as to Marilyn—from whom recovery must be had—so the Court was\n\ncorrect to deny Alliant prejudgment interest.\n\n Absent “affirmative countervailing federal interests,” the availability and\n\namount of prejudgment interest is governed by state law. AIG Baker Sterling\n\n\n\n 35\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 36 of 37\n\n\nHeights, LLC v. Am. Multi-Cinema, Inc., 508 F.3d 995, 1001–02 (11th Cir. 2007)\n\n(quoting Esfeld v. Costa Crociere, S.P.A., 289 F.3d 1300, 1307 (11th Cir. 2002)).\n\nUnder Georgia law, “[a]ll liquidated demands, where by agreement or otherwise\n\nthe sum to be paid is fixed or certain, bear interest from the time the party shall\n\nbecome liable and bound to pay them; if payable on demand, they shall bear\n\ninterest from the time of the demand.” O.C.G.A. § 7-4-15 (2018). “[T]he sole\n\nprerequisite for an award of prejudgment interest on a liquidated claim is that a\n\ndemand be made before the entry of final judgment, so that the opposing party has\n\nan opportunity to contest an award of interest.” Gwinnett County v. Old Peachtree\n\nPartners, LLC, 764 S.E.2d 193, 200 (Ga. Ct. App. 2014).\n\n The only point in dispute is whether Alliant’s claim to the amount of the\n\nKentucky judgment was liquidated.\n\n A sum is liquidated when it is “fixed or certain based on . . . operation of\n\nlaw.” Those Certain Underwriters at Lloyds London v. DTI Logistics, Inc., 686\n\nS.E.2d 333, 339 (Ga. Ct. App. 2009). The full amount of the Kentucky judgment,\n\n$8,946,643, was fixed by law as to Vincent on the date the District Court for the\n\nEastern District of Kentucky entered judgment for that amount against him. But\n\nMarilyn is a different story. The conduct for which Marilyn is liable is receipt of\n\nthe transferred assets when she (1) did not act in good faith and (2) did not give\n\nreasonably equivalent value for them. See O.C.G.A. § 18-2-78(a) (2010). Because\n\n\n\n 36\n\f Case: 15-14634 Date Filed: 05/15/2019 Page: 37 of 37\n\n\nthe jury was required to determine the values of each of those assets, the amount\n\nfor which she is personally liable did not become liquidated until the District Court\n\nentered the Georgia judgment.\n\n In short, Alliant is not entitled to any prejudgment interest under Georgia\n\nlaw because its claim for $8,946,643 was not previously liquidated as to Marilyn.\n\n VII.\n\n For these reasons, the District Court’s judgment is AFFIRMED in part and\n\nREVERSED in part. We REMAND for further proceedings not inconsistent with\n\nthis opinion.\n\n SO ORDERED.\n\n\n\n\n 37\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: ALLIANT TAX CREDIT 31, INC, a Florida Corporation, Alliant Tax Credit Fund XXVII, Ltd., a Florida Limited Partnership, Alliant Tax Credit Tax Credit XXVII, Inc, a Florida Corporation, Alliant Tax Credit XI, Inc., a Florida Corporation, Alliant Tax Credit XI, Ltd., a Florida Limited Partnership, Plaintiffs - Counter Defendants - Appellees - Cross Appellants, v. M. Vincent MURPHY, III, Multifamily Housing Developers, L.L.C., a Georgia Limited Liability Company, Community Management Services, Inc., a Georgia Corporation, Gazebo Park Apartments of Acworth, LLC, a Georgia Limited Liability Company, Defendants - Appellants - Cross Appellees, Marilyn Murphy, Defendant - Counter Claimant - Appellant - Cross Appellee.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-15\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 15-14634 Date Filed: 05/15/2019 Page: 1 of 37\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 15-14634\\n ________________________\\n\\n D.C. Docket No. 1:11-cv-00832-RWS\\n\\n\\n\\nALLIANT TAX CREDIT 31, INC,\\na Florida corporation,\\nALLIANT TAX CREDIT FUND XXVII, LTD.,\\na Florida limited partnership,\\nALLIANT TAX CREDIT TAX CREDIT XXVII, INC,\\na Florida corporation,\\nALLIANT TAX CREDIT XI, INC.,\\na Florida corporation,\\nALLIANT TAX CREDIT XI, LTD.,\\na Florida limited partnership,\\n\\n Plaintiffs - Counter Defendants – Appellees -\\n Cross Appellants,\\n\\n versus\\n\\nM. VINCENT MURPHY, III,\\nMULTIFAMILY HOUSING DEVELOPERS, L.L.C.,\\na Georgia limited liability company,\\nCOMMUNITY MANAGEMENT SERVICES, INC.,\\na Georgia corporation,\\nGAZEBO PARK APARTMENTS OF ACWORTH, LLC,\\na Georgia limited liability company,\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 2 of 37\\n\\n\\n Defendants - Appellants - Cross Appellees,\\n\\nMARILYN MURPHY,\\n\\n Defendant - Counter Claimant - Appellant -\\n Cross Appellee.\\n\\n ________________________\\n\\n Appeals from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 15, 2019)\\n\\nBefore TJOFLAT and WILLIAM PRYOR, Circuit Judges, and MURPHY, *\\nDistrict Judge.\\n\\nTJOFLAT, Circuit Judge:\\n\\n This fraudulent-transfer case, like many such cases, is a suit about a suit. In\\n\\nthe first suit, Plaintiffs obtained a judgment in federal district court in Kentucky for\\n\\nbreach of a partnership contract. But when Plaintiffs tried to collect, they\\n\\ndiscovered that the once-wealthy Defendant was figuratively penniless. The\\n\\nsurprised Plaintiffs surmised that Defendant had colluded with his former wife to\\n\\nfraudulently transfer his assets to her (or to entities under her control) as part of\\n\\ntheir divorce settlement. So Plaintiffs sued—again—this time in federal district\\n\\ncourt in Georgia—to recover their judgment under Georgia’s fraudulent-transfer\\n\\n\\n\\n *\\n Honorable Stephen J. Murphy, III, United States District Court for the Eastern District\\nof Michigan, sitting by designation.\\n\\n\\n 2\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 3 of 37\\n\\n\\nstatute. Agreeing with Plaintiffs that fraudulent transfers had occurred, a jury\\n\\nreturned a verdict in their favor. The District Court entered judgment accordingly,\\n\\nand this appeal and cross-appeal followed.\\n\\n I.\\n\\n A.\\n\\n 1.\\n\\n The run-up to this suit began when Plaintiffs, five entities that we\\n\\ncollectively refer to as “Alliant,” 1 lent Defendant M. Vincent Murphy, III\\n\\ninvestment capital to build low-income housing units that were never completed.\\n\\nSo Alliant sued him and other guarantors of the debt in federal court in the Eastern\\n\\nDistrict of Kentucky for breach of their partnership contract. Alliant was joined in\\n\\nthat suit by Alliant Tax Credit Fund 31-A, Ltd. (“Alliant 31-A”), which also lent\\n\\ninvestment capital to Vincent. 2 Alliant and Alliant 31-A prevailed, and the District\\n\\nCourt for the Eastern District of Kentucky entered a judgment (the “Kentucky\\n\\njudgment”) in their favor for $8,946,643. Vincent appealed, and the Court of\\n\\n\\n\\n\\n 1\\n The full names are Alliant Tax Credit 31, L.L.C. (“Alliant 31”), Alliant Tax Credit Fund\\nXXVII, Ltd. (“Alliant XXVII, Ltd.”), Alliant Tax Credit Fund XXVII, L.L.C. (“Alliant XXVII,\\nL.L.C.”), Alliant Tax Credit XI, L.L.C. (“Alliant XI, L.L.C.”), and Alliant Tax Credit XI, Ltd.\\n(“Alliant XI, Ltd.”).\\n 2\\n Alliant 31-A was dismissed by the District Court for the Northern District of Georgia\\nbecause its presence would have destroyed subject-matter jurisdiction. For this reason (and\\nothers that will become clear), we treat Alliant 31-A separately.\\n\\n\\n 3\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 4 of 37\\n\\n\\nAppeals for the Sixth Circuit affirmed. Alliant Tax Credit Fund 31-A, Ltd. v.\\n\\nMurphy, 494 F. App’x 561, 563 (6th Cir. 2012).\\n\\n But the fraudulent activity that gave rise to this suit began before the\\n\\nKentucky judgment was entered.\\n\\n Vincent and his wife, Marilyn Murphy, had earlier divorced in the Superior\\n\\nCourt of Fulton County, Georgia. The divorce decree incorporated a settlement\\n\\nagreement between them. As part of the agreement, Marilyn received from\\n\\nVincent several millions of dollars in cash and commercial paper, stock shares, a\\n\\nmountain cabin, household furnishings, and an apartment complex. These assets\\n\\nare the basis for the fraudulent-transfer action here. When Alliant sought to collect\\n\\non the Kentucky judgment, it found that Vincent was judgment proof. So it sued\\n\\nVincent for a second time.\\n\\n Alliant (but not Alliant 31-A) brought this action against Vincent, Marilyn,\\n\\nMultifamily Housing Developers, L.L.C. (“Multifamily Housing”), and\\n\\nCommunity Management Services, Inc. (“CMS”), 3 in the District Court for the\\n\\nNorthern District of Georgia under the Uniform Fraudulent Transfers Act (the\\n\\n“UFTA”), O.C.G.A. §§ 18-2-70 to 80 (2010), amended by the Uniform Voidable\\n\\n\\n\\n\\n 3\\n Alliant alleged that Multifamily Housing and CMS, both of which Marilyn controlled,\\nwere also fraudulent transferees of some of Vincent’s assets.\\n\\n\\n 4\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 5 of 37\\n\\n\\nTransactions Act (the “UVTA”), O.C.G.A. §§ 18-2-70 to 85 (2015).4 The UFTA,\\n\\na quintessential fraudulent-transfer statute, allows creditors to void certain asset\\n\\ntransfers made by a debtor with the purpose of immunizing itself from collection.\\n\\nSee O.C.G.A. § 18-2-77 (2010). Alliant claimed that the Murphys’ divorce\\n\\nsettlement and Vincent’s asset transfers to Defendants were ruses to evade\\n\\nVincent’s creditors and thus sought to void those transfers. The case proceeded to\\n\\ntrial, and a jury returned an itemized verdict for Alliant after having found that\\n\\ntwenty-three transfers from Vincent to Defendants were fraudulent. The jury also\\n\\nfound that the Murphys were subject to punitive damages but that only Vincent had\\n\\nacted with the “specific intent to cause harm.” It awarded $1,000,000 in punitive\\n\\ndamages against him and $100,000 in punitive damages against Marilyn.\\n\\n 2.\\n\\n After the jury returned its verdict, the District Court for the Northern District\\n\\nof Georgia entered a final judgment (the “Georgia judgment”) for Alliant. Before\\n\\ndescribing what the judgment provided, we pause momentarily to note the\\n\\nremedies available under the UFTA.\\n\\n\\n 4\\n Georgia’s General Assembly amended the UFTA in 2015. See Uniform Voidable\\nTransactions Act, 2015 Ga. Laws 1019 (codified at O.C.G.A. §§ 18-2-70 to 85 (2018)). As part\\nof the amendment, the General Assembly changed the name of the statute. Some of the\\namendments are consequential to issues we must decide on appeal. But the parties agree—and\\nwe follow their lead—the UFTA is the version of the law we must apply. We discuss the\\nUVTA—note the “V” in place of the “F”—at various points throughout this opinion; we make\\nclear when we reference that currently enacted version of the statute.\\n\\n\\n 5\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 6 of 37\\n\\n\\n The UFTA provides creditors with both equitable and legal remedies. The\\n\\ncreditor may obtain, as an equitable remedy, “[a]voidance of the transfer . . . to the\\n\\nextent necessary to satisfy the creditor’s claim.” See id. § 18-2-77(a)(1). Or it may\\n\\nobtain, as a legal remedy, “judgment [against the transferee] for the value of the\\n\\nasset transferred . . . or the amount necessary to satisfy the creditor’s claim,\\n\\nwhichever is less.” See id. § 18-2-78(b).\\n\\n Alliant did not seek avoidance of any of the transfers made. Nor realistically\\n\\ncould it: Most of Vincent’s transfers were in the form of cash that has since been\\n\\nturned into proceeds that are likely untraceable. Rather, it sought a money\\n\\njudgment for the value of the assets transferred. Said differently, it sought the\\n\\nlegal remedy available under the UFTA.\\n\\n The Georgia judgment, which purported to implement the jury’s verdict,\\n\\nprovided that Alliant would receive the sum of $10,137,285.84, which consisted of\\n\\nthe amount of the Kentucky judgment ($8,946,643), interest on that judgment\\n\\n($90,642.84), and the punitive-damages awards against Vincent and Marilyn\\n\\n($1,000,000 and $100,000, respectively). The District Court for the Northern\\n\\nDistrict of Georgia also issued a writ of execution that directed the U.S. Marshal to\\n\\nseize Defendants’ assets to satisfy the judgment. 5\\n\\n\\n 5\\n In ordering the U.S. Marshal to seize the items identified in the judgment, the District\\nCourt appeared to be entering an in rem judgment, as if Alliant had brought suit against the\\nfraudulently conveyed assets or their proceeds themselves. The Court should have entered an in\\n\\n\\n 6\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 7 of 37\\n\\n\\n 3.\\n\\n Following the entry of the Georgia judgment, Marilyn satisfied the judgment\\n\\nin full, and Alliant moved to alter or amend the judgment, see Fed. R. Civ. P. 60, to\\n\\nallow prejudgment interest under Georgia law. The District Court for the Northern\\n\\nDistrict of Georgia denied this motion, reasoning that (1) Alliant’s UFTA claim\\n\\nwas unliquidated—that is, not reduced to a fixed sum—until the Georgia judgment\\n\\nwas entered and (2) under Georgia law, entitlement to prejudgment interest for\\n\\nunliquidated claims requires compliance with the Unliquidated Damages Interest\\n\\nAct, O.C.G.A. § 51-12-14 (2018), whose procedures Alliant had not followed.\\n\\nDefendants appealed the judgment entered pursuant to the verdict, and Alliant\\n\\ncross-appealed the order denying prejudgment interest.\\n\\n B.\\n\\n This appeal and cross-appeal require us to decide numerous discrete issues.\\n\\nWe first take up justiciability problems in Part II. We then turn to the merits,\\n\\naddressing Defendants’ arguments on appeal in Parts III through V and Alliant’s\\n\\narguments on cross-appeal in Part VI. We conclude in Part VII.\\n\\n II.\\n\\n\\n\\npersonam judgment against Vincent and Marilyn individually and issued writs of execution\\nagainst their assets or writs of garnishment against their accounts. This error does not matter for\\nour purposes, however, because the parties treated the judgment as though it were entered in\\npersonam.\\n\\n\\n 7\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 8 of 37\\n\\n\\n We begin by addressing two jurisdictional bars to the District Court’s power\\n\\nto entertain this suit: mootness and subject-matter jurisdiction.6 We then address\\n\\nnon-jurisdictional bars. Defendants challenge the Court’s decision not to abstain\\n\\nfrom exercising its jurisdiction on three prudential grounds. First, that even if the\\n\\nparties are diverse of citizenship, this case falls within the domestic-relations\\n\\nexception to diversity jurisdiction. Second, that by entertaining this suit, the Court\\n\\nviolated the Rooker-Feldman doctrine. 7 And third, that Alliant is collaterally\\n\\nestopped from attacking the transfers as fraudulent.\\n\\n A.\\n\\n The first question, given Marilyn’s full satisfaction of the Georgia judgment:\\n\\nAre this appeal and cross-appeal moot? After oral argument, we asked the parties\\n\\nto brief this question and having reviewed their responses, we are satisfied that the\\n\\ncase remains a case or controversy within the meaning of Article III. See U.S.\\n\\nConst. art. III, § 2, cl. 1.\\n\\n “What matters [for mootness] is whether the parties’ actions objectively\\n\\nmanifest an intent to abandon the issues on appeal.” RES-GA Cobblestone, LLC v.\\n\\nBlake Constr. & Dev., LLC, 718 F.3d 1308, 1315 (11th Cir. 2013). So payment\\n\\n\\n\\n 6\\n Unless otherwise stated, our use of “District Court” from this point forward refers to the\\nCourt below—the District Court for the Northern District of Georgia.\\n 7\\n Rooker v. Fid. Tr. Co., 263 U.S. 413, 44 S. Ct. 149 (1923), and D.C. Court of Appeals v.\\nFeldman, 460 U.S. 462, 103 S. Ct. 1303 (1983).\\n\\n\\n 8\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 9 of 37\\n\\n\\nmoots an appeal “only if the parties mutually intended a final settlement of all the\\n\\nclaims in dispute and a termination of the litigation.” McGowan v. King, Inc., 616\\n\\nF.2d 745, 747 (5th Cir. 1980) (per curiam). 8\\n\\n This case continues to breathe life. In Alvarez Perez v. Sanford-Orlando\\n\\nKennel Club, Inc., 518 F.3d 1302 (11th Cir. 2008), we applied the Supreme\\n\\nCourt’s decision in United States v. Hougham, 364 U.S. 310, 81 S. Ct. 13 (1960),\\n\\nand held that an appeal and cross-appeal situated much like the ones before us\\n\\ntoday were not moot. There, the plaintiff’s counsel signed satisfaction-of-\\n\\njudgment documents that were subsequently filed in the district court, but the\\n\\nplaintiff did not expressly reserve his right to appeal. 518 F.3d at 1305. But there,\\n\\nas here, the parties “continued to pursue their appeals.” Id. at 1307. There, as\\n\\nhere, the parties “filed supplemental letter briefs addressing the merits.” Id. And\\n\\nthere, as here, a party “inform[ed] us of a change in status involving one of the\\n\\ndefendants.” Id. In other words, “[i]nstead of filing a motion to dismiss the appeal\\n\\nas soon as a satisfaction was filed in the district court, both parties continued to\\n\\nlitigate the case in this Court as though nothing had changed.” Id. at 1308.\\n\\n In fact, Marilyn merely did the effective equivalent of posting a supersedeas\\n\\nbond—an act that by itself does not moot a case. See Fed. R. Civ. P. 62(b).\\n\\n\\n 8\\n In Bonner v. City of Prichard, 661 F.2d 1206 (11th Cir. 1981) (en banc), this Court\\nadopted as binding precedent all decisions of the former Fifth Circuit handed down prior to\\nOctober 1, 1981.\\n\\n\\n 9\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 10 of 37\\n\\n\\n When a judgment is appealed, both the winning and losing parties face risk\\n\\nin the period between the time judgment is entered and the time it is affirmed or\\n\\nreversed. The winning party seeks immediate satisfaction of the judgment because\\n\\nassets available at the time judgment is entered might disappear by the time it is\\n\\naffirmed. And the losing party seeks delayed satisfaction of judgment for a\\n\\nparallel reason: Assets available at the time judgment is entered might disappear by\\n\\nthe time it is reversed. A supersedeas bond insures both parties against these\\n\\nrespective risks. It permits a judgment debtor to “avoid the risk of satisfying the\\n\\njudgment only to find that restitution is impossible after reversal on appeal” and\\n\\n“secures the prevailing party against any loss sustained as a result of being forced\\n\\nto forgo execution on a judgment during the course of an ineffectual appeal.”\\n\\nPoplar Grove Planting & Ref. Co. v. Bache Halsey Stuart, Inc., 600 F.2d 1189,\\n\\n1191 (5th Cir. 1979).\\n\\n But posting a supersedeas bond does not moot an appeal. See Dale M. ex\\n\\nrel. Alice M. v. Bd. of Educ. of Bradley-Bourbonnais High Sch. Dist. No. 307, 237\\n\\nF.3d 813, 815 (7th Cir. 2001) (Posner, J.) (“A judgment creditor who pays the\\n\\njudgment pending appeal instead of posting a supersedeas bond (which would\\n\\nautomatically stay collection) is entitled to the return of its money if the decision is\\n\\nreversed, and so the payment does not moot the appeal unless the appellant has\\n\\nrelinquished his right to seek repayment if he wins.” (citation omitted)).\\n\\n\\n\\n 10\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 11 of 37\\n\\n\\n Marilyn’s choice to pay the judgment does not render this case moot any\\n\\nmore than would her decision to post a supersedeas bond; she simply waived the\\n\\nprotection a bond would provide. Cf. 11 Charles Alan Wright et al., Federal\\n\\nPractice and Procedure § 2905, at 724−25 (3d ed. 2012) (“[A] person who cannot\\n\\nfurnish a supersedeas bond does not lose the right to appeal, although he does\\n\\nassume the risk of getting his money back again if the judgment is reversed.”).\\n\\n In short, the “objective manifestations of both parties clearly indicate that\\n\\nthey intended to pursue their positions in the appeal and cross-appeal.” Alvarez\\n\\nPerez, 518 F.3d at 1308. We turn now to subject-matter jurisdiction.\\n\\n B.\\n\\n Defendants maintain that the District Court lacked jurisdiction to entertain\\n\\nthe dispute because the parties were not diverse of citizenship.\\n\\n The District Court’s subject-matter jurisdiction has continued to present\\n\\ndifficulties in this case. Defendants appealed the Georgia judgment, and two\\n\\nmonths later, this Court sua sponte asked the parties to address subject-matter\\n\\njurisdiction because diversity jurisdiction was not evident from the pleadings. In\\n\\nresponse, Alliant moved to amend its complaint to simply allege the citizenships of\\n\\nall relevant entities. Defendants, in turn, moved to remand the case to the District\\n\\nCourt for a factual determination of subject-matter jurisdiction in the first instance.\\n\\nAfter reviewing the parties’ responses and motions, we remanded the case to the\\n\\n\\n\\n 11\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 12 of 37\\n\\n\\nDistrict Court so that it might “fully resolve the question of the court’s subject-\\n\\nmatter jurisdiction over this action.” Alliant Tax Credit Fund 31-A, Ltd. v.\\n\\nMurphy, No. 15-14634-GG, slip op. at 1 (11th Cir. Apr. 10, 2017) (per curiam).\\n\\n On remand, Alliant filed a memorandum on Plaintiffs’ citizenships.\\n\\nPlaintiffs are a mixture of limited-liability companies and limited partnerships. 9\\n\\nSome of Plaintiffs’ members and partners are natural persons, but some are other\\n\\nlimited-liability companies, other partnerships, corporations, banks, and trusts.\\n\\nAlliant traced these entities’ citizenships, too. It included with its memorandum to\\n\\nthe District Court affidavits, declarations, and authenticated documents.\\n\\nDefendants responded that Alliant’s submissions were insufficient to confirm that\\n\\nall relevant entities were accounted for, as well as to confirm those entities’\\n\\ncitizenships. The Court observed that though Alliant had initially claimed that the\\n\\nsole citizenship of all five Plaintiffs was Florida, Alliant conceded in its\\n\\nmemorandum that Plaintiffs were also citizens of California, Delaware, the District\\n\\nof Columbia, Illinois, Nebraska, New York, Ohio, and Texas. So the Court\\n\\nrequired further documentary evidence of citizenship. For natural persons, it asked\\n\\nfor drivers licenses; for corporations, it asked for annual reports and articles of\\n\\nincorporation or governance documents; for limited partnerships and limited-\\n\\n\\n\\n 9\\n Alliant 31, L.L.C., Alliant XXVII, L.L.C., and Alliant XI, L.L.C. are limited-liability\\ncompanies. Alliant XXVII, Ltd. and Alliant XI, Ltd. are limited partnerships.\\n\\n\\n 12\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 13 of 37\\n\\n\\nliability companies, it asked for agreements; for banks, it asked for articles of\\n\\nassociation; and for trusts, it asked for organizational documents.\\n\\n After this jurisdictional discovery was complete, the District Court set out its\\n\\nfindings as to the parties’ citizenships:\\n\\nPlaintiffs\\n\\n • Alliant 31 was a citizen of Florida, California, and Illinois.\\n\\n • Alliant XXVII, Ltd. was a citizen of Florida, California, Illinois, and the\\n District of Columbia.\\n\\n • Alliant XXVII, L.L.C. was a citizen of Florida, California, and Illinois.\\n\\n • Alliant XI, L.L.C. was a citizen of Florida, California, and Illinois.\\n\\n • Alliant XI, Ltd. was a citizen of Florida, California, Illinois, Delaware,\\n New York, Texas, Nevada, and Ohio.\\n\\nDefendants\\n\\n • Vincent was a citizen of Georgia.\\n\\n • CMS was a citizen of Georgia.\\n\\n • Multifamily Housing was a citizen of Georgia.\\n\\n • Marilyn was a citizen of Georgia.\\n\\nAs such, it concluded that Alliant had established subject-matter jurisdiction by a\\n\\npreponderance of the evidence.\\n\\n Defendants, still unsatisfied that diversity jurisdiction was present, moved\\n\\nthis Court for leave to file supplemental briefing on the District Court’s factual\\n\\n\\n 13\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 14 of 37\\n\\n\\nfindings, its failure to sustain evidentiary objections, its admission into evidence of\\n\\nunreliable documents, and its failure to allow adversarial discovery. We granted\\n\\nDefendants’ motion, Alliant Tax Credit Fund 31-A, Ltd. v. Murphy, No. 15-14634-\\n\\nGG, slip op. at 2 (11th Cir. Nov. 9, 2017) (single-judge order), and now address\\n\\nthese jurisdictional issues.\\n\\n 1.\\n\\n First, Defendants argue that the record contains insufficient evidence to\\n\\nsupport the District Court’s findings on the citizenships of two inter vivos trusts,\\n\\nwhose names we have redacted.10 They contend that the trusts’ citizenships derive\\n\\nfrom their beneficiaries and that Alliant has not fully accounted for those\\n\\nbeneficiaries.\\n\\n Whether subject-matter jurisdiction exists presents a mixed question of law\\n\\nand fact. We review de novo a district court’s legal conclusions. Calderon v.\\n\\nBaker Concrete Constr., Inc., 771 F.3d 807, 810 (11th Cir. 2014). But we review\\n\\nfor clear error “any factual determinations necessary to establish jurisdiction,”\\n\\nDudley v. Eli Lilly & Co., 778 F.3d 909, 911 (11th Cir. 2014), including “findings\\n\\nregarding domicile,” McCormick v. Aderholt, 293 F.3d 1254, 1257 (11th Cir.\\n\\n2002) (per curiam). The party invoking federal jurisdiction “must prove, by a\\n\\n\\n 10\\n These trusts are members of a limited-liability company that is a member of another\\nlimited-liability company that is a partner of a limited partnership that in turn is a member or\\npartner of each of the five Plaintiffs in this case.\\n\\n\\n 14\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 15 of 37\\n\\n\\npreponderance of the evidence, facts supporting the exercise of jurisdiction.”\\n\\nCaron v. NCL (Bahamas), Ltd., 910 F.3d 1359, 1363–64 (11th Cir. 2018).\\n\\n A “traditional trust” holds the citizenship of its trustee, not of its\\n\\nbeneficiaries. See Americold Realty Tr. v. Conagra Foods, Inc., 136 S. Ct. 1012,\\n\\n1016 (2016); see also Raymond Loubier Irrevocable Tr. v. Loubier, 858 F.3d 719,\\n\\n730 (2d Cir. 2017) (“[F]or . . . traditional trusts, it is the citizenship of the trustees\\n\\nholding the legal right to sue on behalf of the trusts, not that of beneficiaries, that is\\n\\nrelevant to jurisdiction.”). A “traditional trust . . . generally describes a fiduciary\\n\\nrelationship regarding property where the trust cannot sue and be sued as an entity\\n\\nunder state law.” Wang ex rel. Wong v. New Mighty U.S. Tr., 843 F.3d 487, 495\\n\\n(D.C. Cir. 2016). So whether a trust is “traditional” requires us to refer to the “law\\n\\nof the state where the trust is formed.” Id.; see also, e.g., id. (holding that under\\n\\nDistrict of Columbia law, a trust lacked separate “juridical person status” and thus\\n\\ncould not “sue and be sued as an entity”); Loubier, 858 F.3d at 731 (holding that\\n\\nunder Florida law, a trust was not a “distinct juridical entit[y]” and thus was\\n\\n“incapable of being haled into court except through [its] trustee[]”).\\n\\n The two trusts here were formed in Wisconsin, and under Wisconsin law, a\\n\\ntrust is represented in litigation through its trustee. See Wis. Stat. § 701.0106\\n\\n(stating that the trust code incorporates the “common law of trusts”). Because the\\n\\ncode does not confer “juridical person status” on a trust itself, see New Mighty U.S.\\n\\n\\n\\n 15\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 16 of 37\\n\\n\\nTr., 843 F.3d at 495, the trusts are traditional trusts whose citizenships are those of\\n\\ntheir trustees. The trustee of both trusts is a natural person who is domiciled in\\n\\nFlorida. As such, she is a Florida citizen. See McCormick, 293 F.3d at 1257.\\n\\n In short, Alliant has proven diversity jurisdiction by a preponderance of the\\n\\nevidence because if the trustee is diverse of Defendants, the trusts themselves are\\n\\ntoo.\\n\\n 2.\\n\\n Second, Defendants argue that the District Court erred by admitting the\\n\\nsworn affidavits of three persons who held leadership positions with various\\n\\nmembers or partners of the five Plaintiffs. We review a district court’s admission\\n\\nof evidence for abuse of discretion. Williams v. Mast Biosurgery USA, Inc., 644\\n\\nF.3d 1312, 1316 (11th Cir. 2011).\\n\\n Defendants argue that the affidavits lack foundation, see Fed. R. Evid. 602,\\n\\nbecause the affiants failed to state that only they could change the memberships of\\n\\ntheir respective entities. But the relevant question for foundation purposes is\\n\\nwhether the affiants had “personal knowledge” of the matter sworn to. See id.\\n\\nEach person laid a foundation for his respective affidavit by stating his position\\n\\nwith the relevant entity and that he had access to that entity’s records. As leaders,\\n\\nrather than as minor functionaries, they were well within their wheelhouses to\\n\\n\\n\\n\\n 16\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 17 of 37\\n\\n\\nswear to the entities’ compositions. Defendants’ argument goes to the weight of\\n\\nthe evidence, not to its admissibility.\\n\\n In short, the District Court was well within its discretion to admit the\\n\\naffidavits.\\n\\n 3.\\n\\n Third, Defendants challenge the operating agreements for Alliant XXVII,\\n\\nL.L.C. and Alliant XI, L.L.C. on which one affiant relies. They point to missing or\\n\\nwholly redacted pages and font inconsistencies among the pages. As such, they\\n\\nargue that the documents were inadmissible because they could not be\\n\\nauthenticated, see Fed. R. Evid. 901, and because they were hearsay that did not\\n\\ncomport with the business-records exception, see Fed. R. Evid. 803(6).\\n\\n We need not reach these issues because even in a record devoid of this\\n\\nevidence, the District Court’s factual findings on these entities’ citizenships was\\n\\nnot clearly erroneous. For both entities, Alliant submitted the later-issued\\n\\ncertificates of conversion from corporations to limited-liability companies. Those\\n\\ndocuments indicate that both Alliant XXVII, L.L.C. and Alliant XI, L.L.C. have\\n\\nonly one member and one general partner. So Defendants’ theory that other\\n\\nentities lurk in those entities’ structures is unfounded.\\n\\n 4.\\n\\n\\n\\n\\n 17\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 18 of 37\\n\\n\\n Fourth, Defendants argue that the District Court should have permitted them\\n\\nto obtain through additional jurisdictional discovery (1) the documentary evidence\\n\\nthat Alliant filed in Alliant Tax Credit Fund XVI, Ltd. v. Thomasville Community\\n\\nHousing, LLC, 713 F. App’x 821 (11th Cir. 2017) (per curiam), 11 and (2) a copy of\\n\\nthe partnership agreement between Alliant 31 and Alliant 31-A. 12 We review a\\n\\ndistrict court’s denial of jurisdictional discovery for abuse of discretion.\\n\\nCulverhouse v. Paulson & Co., 813 F.3d 991, 993 (11th Cir. 2016).\\n\\n Defendants’ underlying grievance is that Alliant cannot be trusted because it\\n\\nhas misrepresented its citizenship in other litigation, including litigation in this\\n\\ncircuit. And because one district judge in this circuit required certain documents of\\n\\nAlliant, the District Judge in this (unrelated) case should have too.\\n\\n To be sure, parties have a “‘qualified right to jurisdictional discovery,’\\n\\nmeaning that a district court abuses its discretion if it completely denies a party\\n\\njurisdictional discovery.” Am. Civil Liberties Union of Fla., Inc. v. City of\\n\\n\\n\\n\\n 11\\n Alliant XI, L.L.C., a Plaintiff here, was also a party to that case.\\n 12\\n We deal with this second request later. Defendants argue that the record contains\\ninsufficient evidence that Alliant 31 meets the amount-in-controversy requirement. See 28\\nU.S.C. § 1332(a) (requiring that a controversy “exceed[] the sum or value of $75,000, exclusive\\nof interest and costs”). Alliant 31 and Alliant 31-A were awarded $1,478,489 via the Kentucky\\njudgment. Defendants claim that each has partial ownership in that amount and that Alliant 31\\nhas not proven that its own interest is at least $75,000. We explain later on, however, that\\nAlliant 31 was entitled to sue for the full amount because it was a joint−judgment creditor. See\\ninfra p. 25. As such, the amount-in-controversy requirement is met.\\n\\n\\n 18\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 19 of 37\\n\\n\\nSarasota, 859 F.3d 1337, 1341 (11th Cir. 2017) (citations omitted) (quoting Eaton\\n\\nv. Dorchester Dev., Inc., 692 F.2d 727, 729 n.7 (11th Cir. 1982)).\\n\\n The District Court here did not abuse its discretion. It did not “completely\\n\\ndeny” Defendants jurisdictional discovery. To the contrary, it ordered Alliant to\\n\\nproduce additional documentary evidence after we remanded the case. Moreover,\\n\\njust because one judge permitted a discovery request does not mean another judge\\n\\nwas obligated to do so. Defendants overlook a basic principle of appellate review:\\n\\nTwo district judges can reach two different determinations of what discovery to\\n\\npermit, and under abuse-of-discretion review, we are required to affirm both\\n\\ndecisions unless one judge has “made a clear error of judgment” or “applied the\\n\\nwrong legal standard.” See Josendis v. Wall to Wall Residence Repairs, Inc., 662\\n\\nF.3d 1292, 1307 (11th Cir. 2011) (quoting Guideone Elite Ins. Co. v. Old Cutler\\n\\nPresbyterian Church, Inc., 420 F.3d 1317, 1325 (11th Cir. 2005)); see also id. at\\n\\n1306−07 (“Discretion means the district court has a ‘range of choice, and that its\\n\\ndecision will not be disturbed as long as it stays within that range and is not\\n\\ninfluenced by any mistake of law.’” (quoting Betty K Agencies, Ltd. v. M/V\\n\\nMonada, 432 F.3d 1333, 1337 (11th Cir. 2005))). In other words, one district\\n\\njudge is not required to follow his brethren in lockstep on discovery matters, just as\\n\\nhe is not required to follow him in lockstep on any other decision. See United\\n\\nStates v. Cerceda, 172 F.3d 806, 812 n.6 (11th Cir. 1999) (en banc) (per curiam)\\n\\n\\n\\n 19\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 20 of 37\\n\\n\\n(“The opinion of a district court carries no precedential weight, even within the\\n\\nsame district.”). So we do not evaluate this Judge’s decision in light of another’s\\n\\ndecision.\\n\\n In short, nothing about the District Court’s finding of subject-matter\\n\\njurisdiction, procedurally or substantively, permits reversal. The Court’s\\n\\nfactfinding was not clearly erroneous. Its evidentiary conclusions were not legally\\n\\nincorrect. And its decision not to entertain additional discovery was not an abuse\\n\\nof discretion.\\n\\n That’s it for the jurisdictional wrinkles, but Defendants offer three other\\n\\nreasons for why the District Court should have evaded the merits.\\n\\n C.\\n\\n Defendants maintain that the District Court was required to abstain under the\\n\\ndomestic-relations exception to diversity jurisdiction. We review for abuse of a\\n\\ndiscretion a district court’s abstention decision under the domestic-relations\\n\\nexception. Stone v. Wall, 135 F.3d 1438, 1441 (11th Cir. 1998) (per curiam),\\n\\ncertified question answered, 734 So. 2d 1038 (Fla. 1999). 13\\n\\n “The federal judiciary has traditionally abstained from deciding cases\\n\\nconcerning domestic relations.” Ingram v. Hayes, 866 F.2d 368, 369 (11th Cir.\\n\\n\\n\\n 13\\n Though Stone involved a decision to abstain, we see no reason to differently review a\\ndecision not to abstain.\\n\\n\\n 20\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 21 of 37\\n\\n\\n1988) (per curiam). The doctrine imposes two limits on our power. First, we may\\n\\nnot “issue divorce, alimony, and child custody decrees.” Stone, 135 F.3d at 1440\\n\\n(quoting Ankenbrandt v. Richards, 504 U.S. 689, 703, 112 S. Ct. 2206, 2215\\n\\n(1992)). Second, “even when subject-matter jurisdiction might be proper,” we\\n\\nabstain from exercising jurisdiction when “sufficient grounds” exist. Id.\\n\\n Here, the District Court did not issue a divorce, alimony, or child-custody\\n\\ndecree. And Defendants do not cite—and our research does not reveal—a single\\n\\ncase when this Court has held that abstention was appropriate when a party to the\\n\\nfederal-court proceeding was not a party to the state-court proceeding. Cf., e.g., id.\\n\\nat 1441 (“The exception enunciated in Ingram is to be read narrowly and does\\n\\nnot—at least, ordinarily—include third parties in its scope.”). In Stone, for\\n\\nexample, we held that abstention was inappropriate when a father and his daughter\\n\\nsued the father’s ex-sister- and ex-mother-in-law for tortious interference of his\\n\\ncustodial rights. Id. Those defendants were not parties to the state-court\\n\\nproceeding and “had no legal claim of custody whatsoever.” Id. Alliant was not a\\n\\nparty to the divorce proceedings in the Georgia Superior Court and like the Stone\\n\\nplaintiffs, did nothing more than “charge[] Defendants with a tort.” See id. at\\n\\n1440.\\n\\n In short, the District Court did not abuse its discretion in exercising diversity\\n\\njurisdiction. Cf. Kirby v. Mellenger, 830 F.2d 176, 179 (11th Cir. 1987) (per\\n\\n\\n\\n 21\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 22 of 37\\n\\n\\ncuriam) (“The less a case is a ‘core’ domestic relations case, e.g., one for a divorce\\n\\nor a simple child custody dispute, the less discretion the district court has to refuse\\n\\nto exercise its jurisdiction.”).\\n\\n D.\\n\\n Defendants argue that Alliant is collaterally estopped from proving that\\n\\nMarilyn did not give “reasonably equivalent value” for the transfers, which is an\\n\\nelement of a UFTA claim. See O.C.G.A. § 18-2-74(a)(2) (2010). In adjudicating\\n\\nthe Murphys’ divorce, the Georgia Superior Court was required to ensure that the\\n\\ndistribution of property between them was “equitable.” See Payson v. Payson, 552\\n\\nS.E.2d 839, 841 (Ga. 2001); see also O.C.G.A. § 19-5-13 (2018). Defendants\\n\\ninsist that Alliant cannot now challenge the transfers as fraudulent under the UFTA\\n\\nbecause the Superior Court already decided that issue in their favor.\\n\\n Under the full-faith-and-credit statute, see 28 U.S.C. § 1738, a district court\\n\\nmust afford “preclusive effect to a state court judgment to the same extent as\\n\\nwould courts of the state in which the judgment was entered.” Graham v. R.J.\\n\\nReynolds Tobacco Co., 857 F.3d 1169, 1181 (11th Cir. 2017) (en banc) (quoting\\n\\nKahn v. Smith Barney Shearson Inc., 115 F.3d 930, 933 (11th Cir. 1997)), cert.\\n\\ndenied, 138 S. Ct. 646 (2018). So we look to the preclusive effect that Georgia law\\n\\nwould give the divorce decree. Under Georgia law, issue preclusion, or collateral\\n\\n\\n\\n\\n 22\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 23 of 37\\n\\n\\nestoppel by another name, requires “identity of the parties or their privies.”\\n\\nWaldroup v. Greene Cty. Hosp. Auth., 463 S.E.2d 5, 7 (Ga. 1995) (per curiam).\\n\\n Nothing about the divorce decree precludes Alliant from challenging the\\n\\nadequacy of value that Marilyn gave for the transfers because it was not a party to\\n\\nthe divorce proceeding. And neither Vincent nor Marilyn represented Alliant’s\\n\\ninterests when they fraudulently transferred assets between themselves to\\n\\nimmunize Vincent from collection. Cf. Smith v. Wood, 154 S.E.2d 646, 649–50\\n\\n(Ga. Ct. App. 1967) (“Privity connotes those who are in law so connected with a\\n\\nparty to the judgment as to have such an identity of interest that the party to the\\n\\njudgment represented the same legal right . . . .” (emphasis added) (quoting Hixson\\n\\nv. Kansas City, 239 S.W.2d 341, 344 (Mo. 1951) (en banc))).\\n\\n E.\\n\\n Defendants relatedly argue that the District Court was required to abstain\\n\\nbecause Alliant’s suit is a collateral attack on a provision of the divorce decree—\\n\\nnamely the Georgia Superior Court’s determination that the distribution of\\n\\nproperty was fair to the parties. Defendants’ argument, though unartfully\\n\\narticulated, is that the Rooker-Feldman doctrine applies. Rooker-Feldman bars a\\n\\n“party losing in state court . . . from seeking what in substance would be appellate\\n\\nreview of the state judgment in a United States district court, based on the losing\\n\\nparty’s claim that the state judgment itself violates the loser’s federal rights.”\\n\\n\\n\\n 23\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 24 of 37\\n\\n\\nJohnson v. De Grandy, 512 U.S. 997, 1005–06, 114 S. Ct. 2647, 2654 (1994). But\\n\\nAlliant was not a party to the divorce proceeding, so Rooker-Feldman has no\\n\\napplication here. See id. at 1006, 114 S. Ct. at 2654 (holding that Rooker-Feldman\\n\\nwas inapplicable when a party in federal court was “not a party in the state court”\\n\\nbecause it was in “no position” to seek review of the state court’s judgment and\\n\\nthus “[did] not directly attack[] it in [the federal] proceeding”). 14\\n\\n Having found that the District Court was permitted to entertain this suit, we\\n\\nnow turn to the first merits question: whether the Court awarded one Plaintiff,\\n\\nAlliant 31, relief to which it was not entitled.\\n\\n III.\\n\\n Defendants argue that $1,478,489 of the Georgia judgment against it was\\n\\nimproper because Alliant 31 was not allowed to collect any of that amount without\\n\\njoining Alliant 31-A as a co-plaintiff. As explained, Alliant 31-A was dismissed\\n\\nearlier in the litigation. See supra note 2. By way of background, the Kentucky\\n\\njudgment was for $8,946,643 overall. As part of that overall total, however, the\\n\\nDistrict Court for the Eastern District of Kentucky awarded relief to Alliant 31 and\\n\\n\\n 14\\n Furthermore, it is unclear whether Rooker-Feldman even applies to a privy. See Lance\\nv. Dennis, 546 U.S. 459, 466 n.2, 126 S. Ct. 1198, 1202 n.2 (2006) (per curiam) (“[W]e need not\\naddress whether there are any circumstances, however limited, in which Rooker–Feldman may\\nbe applied against a party not named in an earlier state proceeding—e.g., where an estate takes a\\nde facto appeal in a district court of an earlier state decision involving the decedent.”). We do\\nnot reach this question because as we already explained, Alliant was not a privy to the divorce\\nproceedings. See supra pp. 22−23.\\n\\n\\n 24\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 25 of 37\\n\\n\\nAlliant 31-A in an amount of $1,478,489. Defendants argue that Alliant 31 (1) was\\n\\npermitted to prosecute a UFTA claim for its share of the $1,478,489 only and (2)\\n\\nbecause it failed to establish that share, it was entitled to collect none of it. To\\n\\nassess this argument, we describe the property interests that Alliant 31 had in the\\n\\nKentucky judgment that it could enforce in this UFTA action.\\n\\n To determine the meaning of a judgment, we apply “[o]rdinary principles of\\n\\nconstruction.” Gurley v. Lindsley, 459 F.2d 268, 275 (5th Cir.), mandate\\n\\nwithdrawn, 466 F.2d 498 (5th Cir. 1972) (per curiam).\\n\\n The Kentucky judgment, on its face, states that “[j]udgment is hereby\\n\\nentered in favor of Plaintiffs, Alliant Tax Credit Fund 31-A, Ltd. . . . and Alliant\\n\\nTax Credit 31, Inc.” Alliant Tax Credit Fund 31-A, Ltd. v. Nicholasville Cmty.\\n\\nHous., LLC, No. 5:07-cv-00388-KKC-REW, slip op. at 1 (E.D. Ky. Aug. 31, 2010)\\n\\n(order amending judgment), ECF No. 204. Through this judgment, Alliant 31 and\\n\\nAlliant 31-A became joint−judgment creditors because the legal right to enforce\\n\\nthe judgment was entered in each of their favors. As a joint creditor, Alliant 31\\n\\nhad a claim to the full $1,478,489 because a joint creditor “is entitled, along with\\n\\nanother creditor, to demand payment from a debtor.” Joint Creditor, Black’s Law\\n\\nDictionary 375 (7th ed. 1999). The District Court committed no error when it\\n\\nawarded Alliant this amount. Though Alliant 31-A might have a claim to part of\\n\\n\\n\\n\\n 25\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 26 of 37\\n\\n\\nthe $1,478,489, and though it might have a contribution action against Alliant 31,\\n\\nnothing prevented Alliant 31 from suing for the full amount.\\n\\n We turn now to the burden of proof under the UFTA.\\n\\n IV.\\n\\n Defendants argue that the District Court erroneously instructed the jury on\\n\\nthe burden of proof, stating that the correct burden under the UFTA is clear-and-\\n\\nconvincing evidence, not a preponderance of the evidence.15 We disagree that a\\n\\nUFTA claim is subject to this heightened burden of proof.\\n\\n First, preponderance of the evidence is the default standard in civil\\n\\nproceedings. O.C.G.A. § 24-14-3 (2018). Tellingly, Georgia law expressly carves\\n\\nout two civil actions that are subject to the clear-and-convincing standard, neither\\n\\nof which are actions under the UFTA. Id. (first citing id. § 51-1-29.5 (medical\\n\\nmalpractice claims arising out of emergency care); then citing id. § 51-12-5.1\\n\\n(punitive-damages claims)). Because Georgia’s General Assembly subjected two\\n\\nspecific causes of action to the clear-and-convincing standard, we decline to infer\\n\\nthat claims under the UFTA are also exempted from the preponderance-of-\\n\\nevidence default. Cf. Estate of Cummings v. Davenport, 906 F.3d 934, 942 (11th\\n\\n\\n\\n 15\\n Georgia’s General Assembly amended the UFTA in 2015 and changed the statute’s\\nname to the UVTA. In so doing, it specifically provided that preponderance is the burden of\\nproof. O.C.G.A. § 18-2-74(d) (2018); see also id. § 18-2-75(d). The parties agree we must\\napply the UFTA, however, which lacks this enunciation.\\n\\n\\n 26\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 27 of 37\\n\\n\\nCir. 2018) (“The expression of one thing implies the exclusion of others.”\\n\\n(alteration omitted) (quoting Antonin Scalia & Bryan A. Garner, Reading Law:\\n\\nThe Interpretation of Legal Texts § 10, at 107 (2012))), petition for cert. filed, No.\\n\\n18-1191 (U.S. Mar. 13, 2019).\\n\\n Second, the UVTA merely clarifies what had always been the law under the\\n\\nUFTA. Cf. Piamba Cortes v. Am. Airlines, Inc., 177 F.3d 1272, 1283 (11th Cir.\\n\\n1999) (“[A]n amendment containing new language may be intended ‘to clarify\\n\\nexisting law . . . .’” (quoting United States v. Sepulveda, 115 F.3d 882, 885 n.5\\n\\n(11th Cir. 1997))). The official commentary to the Uniform Law Commission’s\\n\\nVoidable Transactions Act, which Georgia’s UVTA was modeled on, explains that\\n\\nthe UVTA “rejects [states] that have imposed an extraordinary [evidentiary]\\n\\nstandard, typically ‘clear and convincing evidence.’” 16 Unif. Voidable\\n\\nTransactions Act § 4 cmt. n.10 (Unif. Law Comm’n 2014). Defendants give us no\\n\\nreason to believe that Georgia was one such state. Indeed, they point to no\\n\\ndecision applying Georgia law that has ever imposed a higher burden of proof in a\\n\\nfraudulent-transfer action.\\n\\n In short, the District Court correctly instructed the jury on the burden of\\n\\nproof. With that issue decided, we turn to the punitive-damages awards.\\n\\n\\n\\n 16\\n Georgia courts look to this commentary when interpreting Georgia’s fraudulent-\\ntransfer law. Bishop v. Patton, 706 S.E.2d 634, 640 (Ga. 2011).\\n\\n\\n 27\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 28 of 37\\n\\n\\n V.\\n\\n Defendants argue that the punitive-damages awards were improper because\\n\\npunitive damages may be awarded only in addition to compensatory damages,\\n\\nwhich were not awarded here. Marilyn argues alternatively that even if punitive\\n\\ndamages were proper, the District Court erred by forcing her to pay the award\\n\\nagainst Vincent from her kitty.\\n\\n A.\\n\\n In addition to recovering the value of its claim, a fraudulent-transfer creditor\\n\\ncan also recover compensatory damages—that is, damages that result from the\\n\\nfraudulent transfer itself. Defendants submit that Alliant could not recover\\n\\npunitive damages because it was awarded no compensatory damages. Neither the\\n\\npunitive-damages statute, the caselaw, nor the policy that underpins punitive\\n\\ndamages supports their argument.\\n\\n Alliant invoked the District Court’s diversity jurisdiction, which requires us\\n\\nto apply Georgia substantive law. Erie R.R. Co. v. Tompkins, 304 U.S. 64, 78, 58\\n\\nS. Ct. 817, 822 (1938). In determining the contents of Georgia law, decisions of\\n\\nthe Supreme Court of Georgia and the Georgia Court of Appeals control. See\\n\\nBravo v. United States, 577 F.3d 1324, 1325 (11th Cir. 2009) (per curiam)\\n\\n(“[F]ederal courts are bound by decisions of a state’s intermediate appellate courts\\n\\nunless there is persuasive evidence that the highest state court would rule\\n\\n\\n\\n 28\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 29 of 37\\n\\n\\notherwise.” (quoting King v. Order of United Commercial Travelers of Am., 333\\n\\nU.S. 153, 158, 68 S. Ct. 488, 491 (1948))).\\n\\n The punitive-damages statute articulates two restrictions on punitive\\n\\ndamages, neither of which is violated by the awards here. A court may award\\n\\npunitive damages “only in such tort actions in which it is proven by clear and\\n\\nconvincing evidence that the defendant’s actions showed . . . fraud.” O.C.G.A.\\n\\n§ 51-12-5.1(b) (2018). As relevant here, moreover, an award of punitive damages\\n\\nmay not exceed $250,000 unless the defendant “acted, or failed to act, with the\\n\\nspecific intent to cause harm.” Id. §§ 51-12-5.1(f), (g). Check and check: The jury\\n\\nfound fraud by clear-and-convincing evidence. And it found that Vincent had\\n\\nacted with specific intent to cause harm. Because the jury did not find that Marilyn\\n\\nhad acted with specific intent to cause harm, the punitive damages against her were\\n\\nproperly capped at the statutory maximum of $250,000.\\n\\n The Georgia Court of Appeals has repeatedly stated, moreover, that punitive\\n\\ndamages are available in fraudulent-transfer actions without once stating that\\n\\ncompensatory damages are a prerequisite to recovering them. See Interfinancial\\n\\nMidtown, Inc. v. Choate Constr. Co., 806 S.E.2d 255, 264 (Ga. Ct. App. 2017)\\n\\n(“Georgia law allowing the recovery of general and punitive damages for\\n\\nfraudulent conveyances survived the enactment of Georgia’s UFTA.”); Stinchcomb\\n\\nv. Wright, 628 S.E.2d 211, 215 (Ga. Ct. App. 2006) (“Punitive damages may be\\n\\n\\n\\n 29\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 30 of 37\\n\\n\\nawarded upon a finding of conversion or fraudulent conveyance.”); Cavin v.\\n\\nBrown, 538 S.E.2d 802, 806 (Ga. Ct. App. 2000) (“[P]unitive damages are\\n\\navailable in fraudulent conveyance actions . . . .”).\\n\\n Stinchcomb in particular negates Defendants’ theory that compensatory\\n\\ndamages are a prerequisite for punitive damages. The defendant there argued that\\n\\nan award of attorneys’ fees and punitive damages was improper because the jury\\n\\nhad awarded only specific performance, not compensatory damages. 628 S.E.2d at\\n\\n215. The court rejected that argument, holding, “Since the [plaintiffs] proved their\\n\\nclaims of fraudulent conveyance and were awarded specific performance, the trial\\n\\ncourt’s award of attorney fees and punitive damages was proper.” Id. at 215–16.\\n\\nVincent and Marilyn state that the award of specific performance distinguishes that\\n\\ncase from this case. As an initial matter, that assertion is factually incorrect\\n\\nbecause the District Court ordered Marilyn to turn over the fraudulently transferred\\n\\nassets or their proceeds. But even if the Court had invoked the legal remedy under\\n\\nthe UFTA, as it should have, Stinchcomb would still control. Whether a court\\n\\norders turnover of the assets or enters a money judgment for their value hinges\\n\\nonly on whether the assets or their proceeds are traceable. If they are, turnover is\\n\\nappropriate; if they aren’t, a money judgment should be entered. Either way, the\\n\\nneed to deter the transfer is the same. We explain this idea more below.\\n\\n\\n\\n\\n 30\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 31 of 37\\n\\n\\n One policy of punitive damages is deterrence. 1 Dan B. Dobbs, Dobbs Law\\n\\nof Remedies § 3.11(3), at 475−76 (2d ed. 1993). Without punitive damages,\\n\\nnothing other than costs would deter a debtor from attempting to fraudulently\\n\\ntransfer his assets. If he gets caught, so be it: The cost would simply be what was\\n\\nowed in the first place. See, e.g., SE Prop. Holdings, LLC v. Judkins, No. 1:17-\\n\\nCV-00413-TM-B, 2019 WL 177981, at *10 (S.D. Ala. Jan. 11, 2019) (“Without an\\n\\naward of punitive damages or attorneys’ fees, there would be no deterrence to a\\n\\ndebtor weighing whether to make a fraudulent transfer. This is because the debtor\\n\\nwould only lose the same asset he would have lost if he had not made a fraudulent\\n\\ntransfer.”); Kekona v. Bornemann, 349 P.3d 361, 372 (Haw. 2015) (“[A]t worst the\\n\\nfraudulent debtor is forced to pay what he or she already owed. Without the\\n\\npossibility of significant punitive damages, it would be difficult to deter this\\n\\nconduct.”). It thus makes sense that the UFTA would permit recovery for punitive\\n\\ndamages. See Dobbs, supra, § 3.11(10), at 516 (“[T]he need for punishment or\\n\\ndeterrence may be increased by reason of the very fact that the defendant will have\\n\\nno liability for compensatory damages.”).\\n\\n In short, the absence of compensatory damages did not preclude the award\\n\\nof punitive damages.\\n\\n B.\\n\\n\\n\\n\\n 31\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 32 of 37\\n\\n\\n Marilyn’s alternative argument—that she should not be responsible for\\n\\npaying Vincent’s punitive-damages award—is meritorious.\\n\\n Under the UFTA, a creditor may obtain “judgment [against the transferee]\\n\\nfor the value of the asset transferred . . . or the amount necessary to satisfy the\\n\\ncreditor’s claim, whichever is less.” O.C.G.A. § 18-2-78(b) (2010). After the jury\\n\\nreturned its verdict, the District Court should have entered two judgments—one\\n\\nagainst Marilyn (the transferee) and one against Vincent (the transferor):\\n\\n • A money judgment against Marilyn for $9,137,285.84 (the amount of the\\n claim, plus her $100,000 in punitive damages).\\n\\n • A money judgment against Vincent for $1,000,000 (the amount of his\\n punitive damages).\\n\\nThe Court erred when it required Marilyn to pay Vincent’s money judgment—\\n\\nawarded for his wrongdoings, mind you—out of her pocket. But Alliant\\n\\ncomplicates what seems to be a straightforward result.\\n\\n Alliant asserts that its “claim” within the meaning of § 18-2-78(b) includes\\n\\nthe $100,000 in punitive damages awarded against Vincent. Said differently, the\\n\\nDistrict Court should have entered a single money judgment against Marilyn, the\\n\\nentirety of which she would be personally responsible for. We are unsurprised that\\n\\nAlliant brings us not one case from any jurisdiction where a court has interpreted a\\n\\nfraudulent-transfer “claim” to include damages awarded for the transfer itself. We\\n\\nundertake our own analysis, however, and for two reasons, we cannot agree with\\n\\n\\n 32\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 33 of 37\\n\\n\\nAlliant’s assertion. First, a fraudulent-transfer action is derivative of some other\\n\\nright to relief. Alliant’s approach would collapse into one the action and the claim\\n\\nthat gave rise to that action. And second, the UVTA, which Georgia’s General\\n\\nAssembly replaced the UFTA with in 2015, confirms that “claim” excludes relief\\n\\nawarded for the fraudulent transfer itself. We discuss both reasons in turn.\\n\\n First, a fraudulent-transfer action is predicated on a claim that already exists.\\n\\nSee Dobbs, supra, § 2.8(1), at 191−92. Alliant incurred a claim to the amount of\\n\\nthe Kentucky judgment. Alliant then brought this UFTA action to recover the\\n\\nvalue of that claim. In the process, Alliant incurred a new, second claim against\\n\\nVincent when the Georgia jury awarded Alliant punitive damages for Vincent’s\\n\\nfraud. This second claim is extrinsic to the claim on which the UFTA action was\\n\\npredicated.\\n\\n Second, the UVTA confirms that “claim” under the UFTA cannot\\n\\nencompass relief for the fraudulent transfer itself. Cf. Piamba Cortes, 177 F.3d at\\n\\n1283 (“[A]n amendment containing new language may be intended ‘to clarify\\n\\nexisting law.’” (quoting Sepulveda, 115 F.3d at 885 n.5)). In replacing the UFTA\\n\\nwith the UVTA, Georgia’s General Assembly amended the definition of claim to\\n\\ninclude the following italicized language: “‘Claim,’ except for claim for relief,\\n\\nmeans a right to payment . . . .” O.C.G.A. § 18-2-71(3) (2018) (emphasis added).\\n\\nThe UVTA thus distinguishes “claim” and “claim for relief.” Whereas the “claim\\n\\n\\n\\n 33\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 34 of 37\\n\\n\\nfor relief” is the UFTA action itself, “claim” is the predicate on which that action is\\n\\nbased. As described below, this change merely clarified what had already been the\\n\\nlaw under the UFTA.\\n\\n Georgia’s General Assembly inserted into the UVTA two new subsections\\n\\non burden-of-proof and choice-of-law rules that govern a fraudulent-transfer\\n\\naction. These subsections are the only places where “claim for relief” appears in\\n\\nthe UVTA. They provide that\\n\\n • a UVTA plaintiff “has the burden of proving the elements of the claim\\n for relief by a preponderance of the evidence” and that\\n\\n • “[a] cause of action in the nature of a claim for relief under [the UVTA]\\n is governed by the law of the jurisdiction in which the debtor is located\\n when the transfer is made or the obligation is incurred.”\\n\\nId. §§ 18-2-74(d), -80(b) (emphasis added). But inserting these two subsections\\n\\nwould risk confusion under Alliant’s reading of “claim”: Do the burden-of-proof\\n\\nand choice-of-law rules apply to the UFTA action, the predicate claim, or both?\\n\\nRecognizing this risk, the General Assembly amended the definition of “claim” to\\n\\nmake explicit what had long been implicit: The “claim for relief” and the “claim”\\n\\nare two separate things. Cf. Scalia & Garner, supra, § 40, at 257 (stating that the\\n\\n“presumption that a change in language produces a change in meaning” does not\\n\\napply when codifications “revise the wording of the prior statute to provide for\\n\\nconsistency of expression”).\\n\\n\\n\\n\\n 34\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 35 of 37\\n\\n\\n In short, because Alliant’s claim did not include the punitive damages\\n\\nawarded against Vincent, the Georgia judgment is reversed to the extent it allowed\\n\\nAlliant to recover those damages from Marilyn. We now turn to Alliant’s cross-\\n\\nappeal.\\n\\n VI.\\n\\n Alliant cross-appeals the District Court’s denial of prejudgment interest\\n\\nunder Georgia law from the date the Kentucky judgment was entered to the date\\n\\nthe Georgia judgment was entered.\\n\\n Recall that the District Court awarded Alliant post-judgment interest. Under\\n\\nfederal law, the Kentucky judgment accrued interest from the moment that\\n\\njudgment was entered until it was paid. See 28 U.S.C. § 1961. By the time the\\n\\nGeorgia judgment incorporated the Kentucky judgment, the post-judgment interest\\n\\non the latter had accrued to $90,642.89. No one disputes that Alliant is entitled to\\n\\nthat amount. But Alliant wants prejudgment interest, too. The parties agree that\\n\\nAlliant’s entitlement to prejudgment interest hinges on Alliant’s UFTA claim\\n\\nbeing “liquidated” under Georgia law. We explain below that the claim was not\\n\\nliquidated as to Marilyn—from whom recovery must be had—so the Court was\\n\\ncorrect to deny Alliant prejudgment interest.\\n\\n Absent “affirmative countervailing federal interests,” the availability and\\n\\namount of prejudgment interest is governed by state law. AIG Baker Sterling\\n\\n\\n\\n 35\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 36 of 37\\n\\n\\nHeights, LLC v. Am. Multi-Cinema, Inc., 508 F.3d 995, 1001–02 (11th Cir. 2007)\\n\\n(quoting Esfeld v. Costa Crociere, S.P.A., 289 F.3d 1300, 1307 (11th Cir. 2002)).\\n\\nUnder Georgia law, “[a]ll liquidated demands, where by agreement or otherwise\\n\\nthe sum to be paid is fixed or certain, bear interest from the time the party shall\\n\\nbecome liable and bound to pay them; if payable on demand, they shall bear\\n\\ninterest from the time of the demand.” O.C.G.A. § 7-4-15 (2018). “[T]he sole\\n\\nprerequisite for an award of prejudgment interest on a liquidated claim is that a\\n\\ndemand be made before the entry of final judgment, so that the opposing party has\\n\\nan opportunity to contest an award of interest.” Gwinnett County v. Old Peachtree\\n\\nPartners, LLC, 764 S.E.2d 193, 200 (Ga. Ct. App. 2014).\\n\\n The only point in dispute is whether Alliant’s claim to the amount of the\\n\\nKentucky judgment was liquidated.\\n\\n A sum is liquidated when it is “fixed or certain based on . . . operation of\\n\\nlaw.” Those Certain Underwriters at Lloyds London v. DTI Logistics, Inc., 686\\n\\nS.E.2d 333, 339 (Ga. Ct. App. 2009). The full amount of the Kentucky judgment,\\n\\n$8,946,643, was fixed by law as to Vincent on the date the District Court for the\\n\\nEastern District of Kentucky entered judgment for that amount against him. But\\n\\nMarilyn is a different story. The conduct for which Marilyn is liable is receipt of\\n\\nthe transferred assets when she (1) did not act in good faith and (2) did not give\\n\\nreasonably equivalent value for them. See O.C.G.A. § 18-2-78(a) (2010). Because\\n\\n\\n\\n 36\\n\\f Case: 15-14634 Date Filed: 05/15/2019 Page: 37 of 37\\n\\n\\nthe jury was required to determine the values of each of those assets, the amount\\n\\nfor which she is personally liable did not become liquidated until the District Court\\n\\nentered the Georgia judgment.\\n\\n In short, Alliant is not entitled to any prejudgment interest under Georgia\\n\\nlaw because its claim for $8,946,643 was not previously liquidated as to Marilyn.\\n\\n VII.\\n\\n For these reasons, the District Court’s judgment is AFFIRMED in part and\\n\\nREVERSED in part. We REMAND for further proceedings not inconsistent with\\n\\nthis opinion.\\n\\n SO ORDERED.\\n\\n\\n\\n\\n 37\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2282,"cells":{"id":{"kind":"number","value":4620939,"string":"4,620,939"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Rickey Thompson v. United States"},"decision_date":{"kind":"string","value":"2019-05-17"},"docket_number":{"kind":"string","value":"18-10488"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before WILLIAM PRYOR, GRANT and HULL, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"HULL, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-10488 Date Filed: 05/17/2019 Page: 1 of 12\\n\\n\\n [PUBLISH]\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-10488\\n Non-Argument Calendar\\n ________________________\\n\\n D.C. Docket Nos. 9:16-cv-81071-WPD,\\n 9:07-cr-80036-WPD-1\\n\\n\\nRICKEY THOMPSON,\\n\\n Petitioner-Appellant,\\n\\n versus\\n\\nUNITED STATES OF AMERICA,\\n\\n Respondent-Appellee.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 17, 2019)\\n\\nBefore WILLIAM PRYOR, GRANT and HULL, Circuit Judges.\\n\\nHULL, Circuit Judge:\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 2 of 12\\n\\n\\n Rickey Thompson, a federal prisoner proceeding with counsel, appeals the\\n\\ndistrict court’s denial of his authorized second 28 U.S.C. § 2255 motion to vacate.\\n\\nIn this appeal, Thompson argues that his two 18 U.S.C. § 924(c) firearm\\n\\nconvictions are invalid in light of Johnson v. United States, 576 U.S. ___, 135 S.\\n\\nCt. 2551 (2015), and Sessions v. Dimaya, 584 U.S. ___, 138 S. Ct. 1204 (2018).\\n\\nSpecifically, Thompson contends that his predicate second-degree murder offenses\\n\\nunder 18 U.S.C. § 1111 do not qualify as crimes of violence after Johnson.\\n\\n After careful review of the parties’ briefs and the record, we conclude\\n\\nThompson’s two federal second-degree murder convictions qualify as crimes of\\n\\nviolence under both § 924(c)’s residual and elements clauses. Thus, we affirm the\\n\\ndistrict court’s denial of Thompson’s authorized second § 2255 motion.1\\n\\n I. BACKGROUND\\n\\nA. Convictions, Direct Appeal, and First § 2255 Motion\\n\\n In 2008, a federal jury convicted Thompson, a Bahamian boat captain, and a\\n\\ncodefendant of 30 counts arising out of a drug- and alien-smuggling conspiracy.\\n\\nRelevant to this appeal, during two boat trips in 2006, Thompson pointed a firearm\\n\\nat passengers on the boat whom he had agreed to smuggle into the United States.\\n\\n\\n\\n\\n 1\\n In reviewing a denial of a motion to vacate under § 2255, we review the district court’s\\nlegal conclusions de novo and its findings of fact for clear error. Stoufflet v. United States, 757\\nF.3d 1236, 1239 (11th Cir. 2014).\\n\\n\\n 2\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 3 of 12\\n\\n\\nWhen the passengers said they could not swim, Thompson forced them to jump, or\\n\\npushed them, from his boat into deep water off the coast of Jupiter Island, Florida,\\n\\nwhere three of them drowned.\\n\\n Based on this conduct, Thompson was convicted of three counts of second-\\n\\ndegree murder, in violation of 18 U.S.C. § 1111, and two counts of carrying and\\n\\nbrandishing a firearm during and in relation to a crime of violence, in violation of\\n\\n18 U.S.C. § 924(c)(1)(A)(ii). For the purposes of § 924(c), a “crime of violence”\\n\\nmeans an offense that is a felony and:\\n\\n (A) has as an element the use, attempted use, or threatened use of\\n physical force against the person or property of another, or\\n\\n (B) that by its nature, involves a substantial risk that physical force\\n against the person or property of another may be used in the\\n course of committing the offense.\\n\\n18 U.S.C. § 924(c)(3)(A), (B). We refer to § 924(c)(3)(A) as the “elements clause”\\n\\nand § 924(c)(3)(B) as the “residual clause.” Ovalles v. United States, 905 F.3d\\n\\n1231, 1234 (11th Cir. 2018) (en banc) (“Ovalles II”). Here, as charged in his\\n\\nindictment, Thompson’s companion crimes of violence: (1) for his § 924(c)\\n\\nfirearm conviction in Count 28 was his two second-degree murder convictions in\\n\\nCounts 19 and 20 for the deaths of Roselyne Lubin and Alnert Charles; and (2) for\\n\\nhis § 924(c) firearm conviction in Count 29 was his second-degree murder\\n\\nconviction in Count 21 for the death of Nigel Warren.\\n\\n\\n\\n 3\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 4 of 12\\n\\n\\n Thompson received a total life sentence on all 30 counts, including, inter\\n\\nalia, three concurrent life sentences for the second-degree murder offenses in\\n\\nCounts 19, 20 and 21, a consecutive seven-year sentence for the first § 924(c)\\n\\nfirearm offense in Count 28, and a consecutive 25-year sentence for the second\\n\\n§ 924(c) firearm offense in Count 29. On direct appeal, this Court affirmed\\n\\nThompson’s convictions and sentences, United States v. Thompson, 363 F. App’x\\n\\n737, 738 (11th Cir. Feb. 3, 2010), and later affirmed the district court’s denial of\\n\\nThompson’s first § 2255 motion, Thompson v. United States, 608 F. App’x 726,\\n\\n727 (11th Cir. 2015).\\n\\nB. Authorized Second § 2255 Motion\\n\\n In June 2016, Thompson pro se filed in this Court an application for leave to\\n\\nfile a second or successive § 2255 motion asserting, inter alia, that his § 924(c)\\n\\nconvictions were invalid based on the Supreme Court’s recently decided Johnson.\\n\\nIn Johnson, the Supreme Court struck down the residual clause of the Armed\\n\\nCareer Criminal Act (“ACCA”) as unconstitutionally vague.2 576 U.S. at ___, 135\\n\\nS. Ct. at 2555-58, 2563. The Supreme Court later held that Johnson announced a\\n\\n\\n\\n 2\\n The ACCA provides for a mandatory minimum 15-year sentence when a defendant\\nconvicted under 18 U.S.C. § 922(g) has three or more prior convictions for a “violent felony.”\\n18 U.S.C. § 924(e)(1). The ACCA defines a “violent felony,” in relevant part, as any crime\\npunishable by a term of imprisonment exceeding one year that “otherwise involves conduct that\\npresents a serious potential risk of physical injury to another,” also known as the ACCA’s\\nresidual clause. Id. § 924(e)(2)(B); see also United States v. Owens, 672 F.3d 966, 968 (11th\\nCir. 2012).\\n 4\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 5 of 12\\n\\n\\nnew substantive rule that applies retroactively to cases on collateral review. Welch\\n\\nv. United States, 578 U.S. ___, ___, 136 S. Ct. 1257, 1268 (2016). More recently,\\n\\nin Dimaya, the Supreme Court applied Johnson and struck down as\\n\\nunconstitutionally vague the definition of “crime of violence” in 18 U.S.C. § 16(b),\\n\\nwhich is textually identical to § 924(c)’s residual clause, as incorporated into the\\n\\nImmigration and Nationality Act. 584 U.S. at ___, 138 S. Ct. at 1210-11, 1213-16,\\n\\n1218-23.\\n\\n In his June 2016 application, Thompson, relying on Johnson, argued that his\\n\\nfederal second-degree murder convictions could not qualify as crimes of violence:\\n\\n(1) under § 924(c)’s residual clause because it, like the ACCA’s residual clause,\\n\\nwas unconstitutionally vague; or (2) under § 924(c)’s elements clause because 18\\n\\nU.S.C. § 1111 does not involve the requisite use of physical force.\\n\\n This Court granted Thompson’s application as to his Johnson-based claim,\\n\\nconcluding that he had made a prima facie showing that the statutory criteria in 28\\n\\nU.S.C. § 2255(h) had been met. The Court noted that at that time it was unsettled\\n\\nwhether Johnson applied to § 924(c)’s residual clause and that the Court had not\\n\\nexplicitly ruled on whether a federal § 1111 second-degree murder is a crime of\\n\\nviolence under § 924(c). In re Thompson, No. 16-13797 (11th Cir. July 11, 2016).\\n\\n Once back in the district court, Thompson was appointed counsel.\\n\\nThompson’s now-authorized, second § 2255 motion, amended by counsel,\\n\\n\\n 5\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 6 of 12\\n\\n\\ncontended that Thompson was actually innocent of his § 924(c) convictions\\n\\nbecause his predicate second-degree murder convictions were no longer crimes of\\n\\nviolence in light of Johnson.\\n\\n The district court concluded that Johnson did not apply to § 924(c)’s residual\\n\\nclause, citing this Court’s panel decision in Ovalles v. United States, 861 F.3d\\n\\n1257 (11th Cir. 2017) (“Ovalles I”), vacated on reh’g en banc, 889 F.3d 1259 (11th\\n\\nCir. 2018). Alternatively, the district court concluded that second-degree murder\\n\\nqualified as a crime of violence under § 924(c)’s elements clause. Accordingly,\\n\\nthe district court denied Thompson’s second § 2255 motion on the merits but\\n\\ngranted him a certificate of appealability on whether second-degree murder is a\\n\\ncrime of violence for purposes of a § 924(c) firearm conviction.\\n\\n II. THOMPSON’S § 924(c) CLAIM\\n\\nA. Residual Clause in § 924(c)(3)(B)\\n\\n While Thompson’s current appeal was pending, this Court sitting en banc\\n\\nheld in Ovalles II that § 924(c)(3)(B)’s residual clause is not unconstitutionally\\n\\nvague under Johnson and Dimaya. See 905 F.3d at 1233-34, 1252-53 (interpreting\\n\\nthe text in § 924(c)(3)(B) to incorporate a conduct-based approach that avoids the\\n\\nconstitutional vagueness concerns that invalidated the statutory provisions in\\n\\nJohnson and Dimaya). Subsequently, given Ovalles II held § 924(c) is not\\n\\nunconstitutionally vague under Johnson and Dimaya, this Court has held a federal\\n\\n\\n 6\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 7 of 12\\n\\n\\nprisoner’s authorized successive § 2255 motion asserting a vagueness challenge to\\n\\n§ 924(c)’s residual clause does not satisfy § 2255(h)’s requirements because:\\n\\n(1) those decisions do not supply a rule of constitutional law that is applicable to\\n\\n§ 924(c); and (2) any challenge to the district court’s use of the categorical\\n\\napproach in applying § 924(c)’s residual clause raises a statutory, not a\\n\\nconstitutional, claim. See Solomon v. United States, 911 F.3d 1356, 1358-59,\\n\\n1361 (11th Cir. 2019) (citing In re Garrett, 908 F.3d 686, 688-89 (11th Cir. 2018)).\\n\\nThus, Ovalles II and Garrett “foreclose even the most generous reading of [the\\n\\nmovant’s] challenges, both constitutional and statutory.” Id. at 1361.3\\n\\n Thompson now concedes that his claim that § 924(c)’s residual clause is\\n\\nunconstitutionally vague is foreclosed by Ovalles II, and he states that he raises it\\n\\nmerely to preserve it in case the Supreme Court takes up the issue. 4 Notably too,\\n\\nThompson does not contend that his second-degree murder convictions fail to\\n\\n\\n\\n 3\\n Although this Court authorized Thompson’s proposed second § 2255 motion, that was\\nonly a threshold determination, and the district court was required to consider de novo whether\\nthe statutory criteria have been met. See Jordan v. Sec’y, Dep’t of Corrs., 485 F.3d 1351, 1357-\\n58 (11th Cir. 2007). This appeal is the Court’s “‘first hard look’ at whether the § 2255(h)\\nrequirements have been met.” See Solomon, 911 F.3d at 1361.\\n 4\\n Shortly before Thompson filed his appeal brief, the Supreme Court granted a petition for\\na writ of certiorari in United States v. Davis, 903 F.3d 483 (5th Cir. 2018), cert granted, No. 18-\\n431, 139 S. Ct. 782 (U.S. Jan. 4, 2019). The Supreme Court recently heard argument in Davis on\\nwhether § 924(c)’s residual clause is unconstitutionally vague, and a decision is forthcoming.\\nRegardless, we are required to apply Ovalles II as binding precedent, as a grant of certiorari does\\nnot constitute a change in the law or a basis for relief. See Gissendaner v. Comm’r, Ga. Dep’t of\\nCorrs., 779 F.3d 1275, 1284 (11th Cir. 2015).\\n\\n\\n 7\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 8 of 12\\n\\n\\nqualify under § 924(c)’s residual clause using the conduct-based approach adopted\\n\\nin Ovalles II. Indeed, Counts 19, 20, and 21 of the indictment expressly charged\\n\\nthat Thompson “with malice aforethought, did unlawfully kill” the victims by\\n\\nordering each victim, “who could not swim, to jump from a boat into the waters of\\n\\nthe Atlantic Ocean,” and the jury found Thompson guilty of those counts. That\\n\\nconduct alone satisfies § 924(c)’s residual clause, which encompasses felonies that\\n\\n“involve[ ] conduct that presents a serious potential risk of physical injury to\\n\\nanother.” See 18 U.S.C. § 924(e)(2)(B)(ii).\\n\\n For these reasons, the district court did not err in denying Thompson’s\\n\\nauthorized second § 2255 motion to the extent it challenged § 924(c)’s residual\\n\\nclause.\\n\\nB. Elements Clause in § 924(c)(3)(A)\\n\\n Also while Thompson’s appeal was pending, this Court held that both\\n\\nattempted first-degree and second-degree murder under Florida law categorically\\n\\nqualify as violent felonies under the ACCA’s elements clause. See United States\\n\\nv. Jones, 906 F.3d 1325, 1326-27 (11th Cir. 2018) (Florida second-degree murder);\\n\\nHylor v. United States, 896 F.3d 1219, 1220-21 (11th Cir. 2018) (Florida\\n\\nattempted first-degree murder). As explained below, those precedents drive the\\n\\noutcome here because a federal second-degree murder offense is not materially\\n\\ndifferent from Florida’s second-degree murder offense.\\n\\n\\n 8\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 9 of 12\\n\\n\\n Under Florida law, second-degree murder is “[t]he unlawful killing of a\\n\\nhuman being, when perpetrated by any act imminently dangerous to another and\\n\\nevincing a depraved mind regardless of human life, although without any\\n\\npremeditated design to effect the death of any particular individual.” Jones, 906\\n\\nF.3d at 1328 (alterations in original); see Fla. Stat. § 782.04(2). “The only\\n\\nmeaningful difference between first- and second-degree murder in Florida is that\\n\\nfirst-degree murder requires the element of premeditation, while second-degree\\n\\nmurder does not.” Id. at 1329; see Fla. Stat. § 782.04(1)(a).\\n\\n In Jones, this Court determined that Florida’s second-degree murder offense\\n\\nhas as an element the use of physical force. 906 F.3d at 1328-29. The Court relied\\n\\non Hylor, which held that Florida attempted first-degree murder was categorically\\n\\na violent felony under the ACCA’s elements clause and rejected an argument that\\n\\nattempted murder by poisoning did not involve physical force. Id. The Jones\\n\\nCourt stated that binding precedent in this Court and the Supreme Court made clear\\n\\nthat even indirect force, such as the use of poison to kill someone, involved the use\\n\\nof violent force capable of causing physical pain or injury to a person, as required\\n\\nfor the ACCA’s elements clause. Id. The Court further explained that the\\n\\nlanguage of the elements clause “asks about actions constituting an offense, rather\\n\\nthan the mental state of the actor committing the offense.” Id. at 1329. Therefore,\\n\\nthe mens rea distinction between first- and second-degree murder (i.e., the element\\n\\n\\n 9\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 10 of 12\\n\\n\\nof premeditation) “makes no difference” to the determination of whether the\\n\\nACCA’s elements clause applies. Id.\\n\\n Thompson acknowledges that this Court’s decision in Jones is controlling\\n\\nprecedent and that, under Jones, federal second-degree murder, like Florida\\n\\nsecond-degree murder, categorically qualifies under § 924(c)’s nearly identical\\n\\nelements clause. We agree with Thompson and the government and conclude that,\\n\\neven if the Supreme Court overturns Ovalles II, that will not help Thompson\\n\\nbecause, under the reasoning in Jones, his federal second-degree murder\\n\\nconvictions categorically qualify as crimes of violence under § 924(c)’s elements\\n\\nclause.\\n\\n Under federal law, first- and second- degree murder are defined as follows:\\n\\n Murder is the unlawful killing of a human being with malice\\n aforethought. Every murder perpetrated by poison, lying in wait, or any\\n other kind of willful, deliberate, malicious, and premeditated killing; or\\n committed in the perpetration of, or attempt to perpetrate, any arson,\\n escape, murder, kidnapping, treason, espionage, sabotage, aggravated\\n sexual abuse or sexual abuse, child abuse, burglary, or robbery; or\\n perpetrated as part of a pattern or practice of assault or torture against a\\n child or children; or perpetrated from a premeditated design unlawfully\\n and maliciously to effect the death of any human being other than him\\n who is killed, is murder in the first degree.\\n\\n Any other murder is murder in the second degree.\\n18 U.S.C. § 1111(a). To convict a defendant of second-degree murder under\\n\\n§ 1111(a), the government must prove beyond a reasonable doubt that: (1) the\\n\\nvictim was killed; (2) the defendant caused the victim’s death with malice\\n\\n 10\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 11 of 12\\n\\n\\naforethought; and (3) the killing occurred in the special maritime or territorial\\n\\njurisdiction of the United States. See United States v. McRae, 593 F.2d 700, 704\\n\\n(5th Cir. 1979); 11th Cir. Crim. Pattern Jury Instr. O45.3 (second-degree murder).\\n\\nIn other words, every federal second-degree murder requires the defendant to\\n\\nactually kill the victim with malice aforethought. As with Florida law, the\\n\\ndistinction between first- and second-degree murder under federal law is\\n\\npremeditation. See Lewis v. United States, 523 U.S. 155, 158, 118 S. Ct. 1135,\\n\\n1138 (1998); 11th Cir. Crim. Pattern Jury Instr. O45.3.\\n\\n Because second-degree murder under § 1111(a) is not materially\\n\\ndistinguishable from Florida second-degree murder, Jones controls our\\n\\ndetermination that federal second-degree murder has as an element the use of\\n\\nphysical force and categorically qualifies as a crime of violence under § 924(c)’s\\n\\nelements clause. See United States v. Kaley, 579 F.3d 1246, 1255 (11th Cir. 2009)\\n\\n(explaining that under our prior panel precedent rule, we are bound by a prior\\n\\npanel’s holding until it is overruled by the Supreme Court or this Court sitting en\\n\\nbanc).\\n\\n Even if we were not bound by Jones, however, we would conclude that\\n\\nfederal second-degree murder qualifies under § 924(c)’s elements clause. At a\\n\\nminimum, federal second-degree murder has as an element the killing of a human\\n\\nbeing with malice aforethought. See 18 U.S.C. § 1111(a). Because § 1111(a), by\\n\\n\\n 11\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 12 of 12\\n\\n\\nits plain terms, criminalizes the actual killing of another person, the level of force\\n\\nused must necessarily be capable of causing physical pain or injury. See Curtis\\n\\nJohnson v. United States, 559 U.S. 133, 140, 130 S. Ct. 1265, 1271 (2010)\\n\\n(concluding that the phrase “physical force” in the ACCA’s elements clause\\n\\n“means violent force—that is, force capable of causing physical pain or injury to\\n\\nanother person”); see also Stokeling v. United States, 586 U.S. ___, 139 S. Ct. 544,\\n\\n552-53 (2019) (reaffirming Curtis Johnson’s “capable” standard for the definition\\n\\nof physical force); United States v. Vail-Bailon, 868 F.3d 1293, 1299, 1303 (11th\\n\\nCir. 2017) (en banc) (holding that Florida felony battery qualifies as a crime of\\n\\nviolence under U.S.S.G. § 2L1.2’s analogous elements clause because the offense\\n\\nrequires great bodily harm to the victim, which “necessarily constitutes force\\n\\ncapable of causing pain or injury”). Thus, regardless of any vagueness challenge\\n\\nto § 924(c)(3)(B)’s residual clause, second-degree murder under § 1111(a)\\n\\ncategorically qualifies as a crime of violence under § 924(c)(3)(A)’s elements\\n\\nclause.\\n\\n For all these reasons, we affirm the district court’s denial of Thompson’s\\n\\nauthorized second § 2255 motion.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 12\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4398192/\", \"author_raw\": \"HULL, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILLIAM PRYOR"},"judge2":{"kind":"string","value":"GRANT"},"judge3":{"kind":"string","value":"HULL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"WILLIAM PRYOR\": \", Circuit\", \"GRANT\": \", Circuit\", \"HULL\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4620939/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Rickey Thompson v. United States\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-17\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-10488 Date Filed: 05/17/2019 Page: 1 of 12\n\n\n [PUBLISH]\n\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 18-10488\n Non-Argument Calendar\n ________________________\n\n D.C. Docket Nos. 9:16-cv-81071-WPD,\n 9:07-cr-80036-WPD-1\n\n\nRICKEY THOMPSON,\n\n Petitioner-Appellant,\n\n versus\n\nUNITED STATES OF AMERICA,\n\n Respondent-Appellee.\n\n ________________________\n\n Appeal from the United States District Court\n for the Southern District of Florida\n ________________________\n\n (May 17, 2019)\n\nBefore WILLIAM PRYOR, GRANT and HULL, Circuit Judges.\n\nHULL, Circuit Judge:\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 2 of 12\n\n\n Rickey Thompson, a federal prisoner proceeding with counsel, appeals the\n\ndistrict court’s denial of his authorized second 28 U.S.C. § 2255 motion to vacate.\n\nIn this appeal, Thompson argues that his two 18 U.S.C. § 924(c) firearm\n\nconvictions are invalid in light of Johnson v. United States, 576 U.S. ___, 135 S.\n\nCt. 2551 (2015), and Sessions v. Dimaya, 584 U.S. ___, 138 S. Ct. 1204 (2018).\n\nSpecifically, Thompson contends that his predicate second-degree murder offenses\n\nunder 18 U.S.C. § 1111 do not qualify as crimes of violence after Johnson.\n\n After careful review of the parties’ briefs and the record, we conclude\n\nThompson’s two federal second-degree murder convictions qualify as crimes of\n\nviolence under both § 924(c)’s residual and elements clauses. Thus, we affirm the\n\ndistrict court’s denial of Thompson’s authorized second § 2255 motion.1\n\n I. BACKGROUND\n\nA. Convictions, Direct Appeal, and First § 2255 Motion\n\n In 2008, a federal jury convicted Thompson, a Bahamian boat captain, and a\n\ncodefendant of 30 counts arising out of a drug- and alien-smuggling conspiracy.\n\nRelevant to this appeal, during two boat trips in 2006, Thompson pointed a firearm\n\nat passengers on the boat whom he had agreed to smuggle into the United States.\n\n\n\n\n 1\n In reviewing a denial of a motion to vacate under § 2255, we review the district court’s\nlegal conclusions de novo and its findings of fact for clear error. Stoufflet v. United States, 757\nF.3d 1236, 1239 (11th Cir. 2014).\n\n\n 2\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 3 of 12\n\n\nWhen the passengers said they could not swim, Thompson forced them to jump, or\n\npushed them, from his boat into deep water off the coast of Jupiter Island, Florida,\n\nwhere three of them drowned.\n\n Based on this conduct, Thompson was convicted of three counts of second-\n\ndegree murder, in violation of 18 U.S.C. § 1111, and two counts of carrying and\n\nbrandishing a firearm during and in relation to a crime of violence, in violation of\n\n18 U.S.C. § 924(c)(1)(A)(ii). For the purposes of § 924(c), a “crime of violence”\n\nmeans an offense that is a felony and:\n\n (A) has as an element the use, attempted use, or threatened use of\n physical force against the person or property of another, or\n\n (B) that by its nature, involves a substantial risk that physical force\n against the person or property of another may be used in the\n course of committing the offense.\n\n18 U.S.C. § 924(c)(3)(A), (B). We refer to § 924(c)(3)(A) as the “elements clause”\n\nand § 924(c)(3)(B) as the “residual clause.” Ovalles v. United States, 905 F.3d\n\n1231, 1234 (11th Cir. 2018) (en banc) (“Ovalles II”). Here, as charged in his\n\nindictment, Thompson’s companion crimes of violence: (1) for his § 924(c)\n\nfirearm conviction in Count 28 was his two second-degree murder convictions in\n\nCounts 19 and 20 for the deaths of Roselyne Lubin and Alnert Charles; and (2) for\n\nhis § 924(c) firearm conviction in Count 29 was his second-degree murder\n\nconviction in Count 21 for the death of Nigel Warren.\n\n\n\n 3\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 4 of 12\n\n\n Thompson received a total life sentence on all 30 counts, including, inter\n\nalia, three concurrent life sentences for the second-degree murder offenses in\n\nCounts 19, 20 and 21, a consecutive seven-year sentence for the first § 924(c)\n\nfirearm offense in Count 28, and a consecutive 25-year sentence for the second\n\n§ 924(c) firearm offense in Count 29. On direct appeal, this Court affirmed\n\nThompson’s convictions and sentences, United States v. Thompson, 363 F. App’x\n\n737, 738 (11th Cir. Feb. 3, 2010), and later affirmed the district court’s denial of\n\nThompson’s first § 2255 motion, Thompson v. United States, 608 F. App’x 726,\n\n727 (11th Cir. 2015).\n\nB. Authorized Second § 2255 Motion\n\n In June 2016, Thompson pro se filed in this Court an application for leave to\n\nfile a second or successive § 2255 motion asserting, inter alia, that his § 924(c)\n\nconvictions were invalid based on the Supreme Court’s recently decided Johnson.\n\nIn Johnson, the Supreme Court struck down the residual clause of the Armed\n\nCareer Criminal Act (“ACCA”) as unconstitutionally vague.2 576 U.S. at ___, 135\n\nS. Ct. at 2555-58, 2563. The Supreme Court later held that Johnson announced a\n\n\n\n 2\n The ACCA provides for a mandatory minimum 15-year sentence when a defendant\nconvicted under 18 U.S.C. § 922(g) has three or more prior convictions for a “violent felony.”\n18 U.S.C. § 924(e)(1). The ACCA defines a “violent felony,” in relevant part, as any crime\npunishable by a term of imprisonment exceeding one year that “otherwise involves conduct that\npresents a serious potential risk of physical injury to another,” also known as the ACCA’s\nresidual clause. Id. § 924(e)(2)(B); see also United States v. Owens, 672 F.3d 966, 968 (11th\nCir. 2012).\n 4\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 5 of 12\n\n\nnew substantive rule that applies retroactively to cases on collateral review. Welch\n\nv. United States, 578 U.S. ___, ___, 136 S. Ct. 1257, 1268 (2016). More recently,\n\nin Dimaya, the Supreme Court applied Johnson and struck down as\n\nunconstitutionally vague the definition of “crime of violence” in 18 U.S.C. § 16(b),\n\nwhich is textually identical to § 924(c)’s residual clause, as incorporated into the\n\nImmigration and Nationality Act. 584 U.S. at ___, 138 S. Ct. at 1210-11, 1213-16,\n\n1218-23.\n\n In his June 2016 application, Thompson, relying on Johnson, argued that his\n\nfederal second-degree murder convictions could not qualify as crimes of violence:\n\n(1) under § 924(c)’s residual clause because it, like the ACCA’s residual clause,\n\nwas unconstitutionally vague; or (2) under § 924(c)’s elements clause because 18\n\nU.S.C. § 1111 does not involve the requisite use of physical force.\n\n This Court granted Thompson’s application as to his Johnson-based claim,\n\nconcluding that he had made a prima facie showing that the statutory criteria in 28\n\nU.S.C. § 2255(h) had been met. The Court noted that at that time it was unsettled\n\nwhether Johnson applied to § 924(c)’s residual clause and that the Court had not\n\nexplicitly ruled on whether a federal § 1111 second-degree murder is a crime of\n\nviolence under § 924(c). In re Thompson, No. 16-13797 (11th Cir. July 11, 2016).\n\n Once back in the district court, Thompson was appointed counsel.\n\nThompson’s now-authorized, second § 2255 motion, amended by counsel,\n\n\n 5\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 6 of 12\n\n\ncontended that Thompson was actually innocent of his § 924(c) convictions\n\nbecause his predicate second-degree murder convictions were no longer crimes of\n\nviolence in light of Johnson.\n\n The district court concluded that Johnson did not apply to § 924(c)’s residual\n\nclause, citing this Court’s panel decision in Ovalles v. United States, 861 F.3d\n\n1257 (11th Cir. 2017) (“Ovalles I”), vacated on reh’g en banc, 889 F.3d 1259 (11th\n\nCir. 2018). Alternatively, the district court concluded that second-degree murder\n\nqualified as a crime of violence under § 924(c)’s elements clause. Accordingly,\n\nthe district court denied Thompson’s second § 2255 motion on the merits but\n\ngranted him a certificate of appealability on whether second-degree murder is a\n\ncrime of violence for purposes of a § 924(c) firearm conviction.\n\n II. THOMPSON’S § 924(c) CLAIM\n\nA. Residual Clause in § 924(c)(3)(B)\n\n While Thompson’s current appeal was pending, this Court sitting en banc\n\nheld in Ovalles II that § 924(c)(3)(B)’s residual clause is not unconstitutionally\n\nvague under Johnson and Dimaya. See 905 F.3d at 1233-34, 1252-53 (interpreting\n\nthe text in § 924(c)(3)(B) to incorporate a conduct-based approach that avoids the\n\nconstitutional vagueness concerns that invalidated the statutory provisions in\n\nJohnson and Dimaya). Subsequently, given Ovalles II held § 924(c) is not\n\nunconstitutionally vague under Johnson and Dimaya, this Court has held a federal\n\n\n 6\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 7 of 12\n\n\nprisoner’s authorized successive § 2255 motion asserting a vagueness challenge to\n\n§ 924(c)’s residual clause does not satisfy § 2255(h)’s requirements because:\n\n(1) those decisions do not supply a rule of constitutional law that is applicable to\n\n§ 924(c); and (2) any challenge to the district court’s use of the categorical\n\napproach in applying § 924(c)’s residual clause raises a statutory, not a\n\nconstitutional, claim. See Solomon v. United States, 911 F.3d 1356, 1358-59,\n\n1361 (11th Cir. 2019) (citing In re Garrett, 908 F.3d 686, 688-89 (11th Cir. 2018)).\n\nThus, Ovalles II and Garrett “foreclose even the most generous reading of [the\n\nmovant’s] challenges, both constitutional and statutory.” Id. at 1361.3\n\n Thompson now concedes that his claim that § 924(c)’s residual clause is\n\nunconstitutionally vague is foreclosed by Ovalles II, and he states that he raises it\n\nmerely to preserve it in case the Supreme Court takes up the issue. 4 Notably too,\n\nThompson does not contend that his second-degree murder convictions fail to\n\n\n\n 3\n Although this Court authorized Thompson’s proposed second § 2255 motion, that was\nonly a threshold determination, and the district court was required to consider de novo whether\nthe statutory criteria have been met. See Jordan v. Sec’y, Dep’t of Corrs., 485 F.3d 1351, 1357-\n58 (11th Cir. 2007). This appeal is the Court’s “‘first hard look’ at whether the § 2255(h)\nrequirements have been met.” See Solomon, 911 F.3d at 1361.\n 4\n Shortly before Thompson filed his appeal brief, the Supreme Court granted a petition for\na writ of certiorari in United States v. Davis, 903 F.3d 483 (5th Cir. 2018), cert granted, No. 18-\n431, 139 S. Ct. 782 (U.S. Jan. 4, 2019). The Supreme Court recently heard argument in Davis on\nwhether § 924(c)’s residual clause is unconstitutionally vague, and a decision is forthcoming.\nRegardless, we are required to apply Ovalles II as binding precedent, as a grant of certiorari does\nnot constitute a change in the law or a basis for relief. See Gissendaner v. Comm’r, Ga. Dep’t of\nCorrs., 779 F.3d 1275, 1284 (11th Cir. 2015).\n\n\n 7\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 8 of 12\n\n\nqualify under § 924(c)’s residual clause using the conduct-based approach adopted\n\nin Ovalles II. Indeed, Counts 19, 20, and 21 of the indictment expressly charged\n\nthat Thompson “with malice aforethought, did unlawfully kill” the victims by\n\nordering each victim, “who could not swim, to jump from a boat into the waters of\n\nthe Atlantic Ocean,” and the jury found Thompson guilty of those counts. That\n\nconduct alone satisfies § 924(c)’s residual clause, which encompasses felonies that\n\n“involve[ ] conduct that presents a serious potential risk of physical injury to\n\nanother.” See 18 U.S.C. § 924(e)(2)(B)(ii).\n\n For these reasons, the district court did not err in denying Thompson’s\n\nauthorized second § 2255 motion to the extent it challenged § 924(c)’s residual\n\nclause.\n\nB. Elements Clause in § 924(c)(3)(A)\n\n Also while Thompson’s appeal was pending, this Court held that both\n\nattempted first-degree and second-degree murder under Florida law categorically\n\nqualify as violent felonies under the ACCA’s elements clause. See United States\n\nv. Jones, 906 F.3d 1325, 1326-27 (11th Cir. 2018) (Florida second-degree murder);\n\nHylor v. United States, 896 F.3d 1219, 1220-21 (11th Cir. 2018) (Florida\n\nattempted first-degree murder). As explained below, those precedents drive the\n\noutcome here because a federal second-degree murder offense is not materially\n\ndifferent from Florida’s second-degree murder offense.\n\n\n 8\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 9 of 12\n\n\n Under Florida law, second-degree murder is “[t]he unlawful killing of a\n\nhuman being, when perpetrated by any act imminently dangerous to another and\n\nevincing a depraved mind regardless of human life, although without any\n\npremeditated design to effect the death of any particular individual.” Jones, 906\n\nF.3d at 1328 (alterations in original); see Fla. Stat. § 782.04(2). “The only\n\nmeaningful difference between first- and second-degree murder in Florida is that\n\nfirst-degree murder requires the element of premeditation, while second-degree\n\nmurder does not.” Id. at 1329; see Fla. Stat. § 782.04(1)(a).\n\n In Jones, this Court determined that Florida’s second-degree murder offense\n\nhas as an element the use of physical force. 906 F.3d at 1328-29. The Court relied\n\non Hylor, which held that Florida attempted first-degree murder was categorically\n\na violent felony under the ACCA’s elements clause and rejected an argument that\n\nattempted murder by poisoning did not involve physical force. Id. The Jones\n\nCourt stated that binding precedent in this Court and the Supreme Court made clear\n\nthat even indirect force, such as the use of poison to kill someone, involved the use\n\nof violent force capable of causing physical pain or injury to a person, as required\n\nfor the ACCA’s elements clause. Id. The Court further explained that the\n\nlanguage of the elements clause “asks about actions constituting an offense, rather\n\nthan the mental state of the actor committing the offense.” Id. at 1329. Therefore,\n\nthe mens rea distinction between first- and second-degree murder (i.e., the element\n\n\n 9\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 10 of 12\n\n\nof premeditation) “makes no difference” to the determination of whether the\n\nACCA’s elements clause applies. Id.\n\n Thompson acknowledges that this Court’s decision in Jones is controlling\n\nprecedent and that, under Jones, federal second-degree murder, like Florida\n\nsecond-degree murder, categorically qualifies under § 924(c)’s nearly identical\n\nelements clause. We agree with Thompson and the government and conclude that,\n\neven if the Supreme Court overturns Ovalles II, that will not help Thompson\n\nbecause, under the reasoning in Jones, his federal second-degree murder\n\nconvictions categorically qualify as crimes of violence under § 924(c)’s elements\n\nclause.\n\n Under federal law, first- and second- degree murder are defined as follows:\n\n Murder is the unlawful killing of a human being with malice\n aforethought. Every murder perpetrated by poison, lying in wait, or any\n other kind of willful, deliberate, malicious, and premeditated killing; or\n committed in the perpetration of, or attempt to perpetrate, any arson,\n escape, murder, kidnapping, treason, espionage, sabotage, aggravated\n sexual abuse or sexual abuse, child abuse, burglary, or robbery; or\n perpetrated as part of a pattern or practice of assault or torture against a\n child or children; or perpetrated from a premeditated design unlawfully\n and maliciously to effect the death of any human being other than him\n who is killed, is murder in the first degree.\n\n Any other murder is murder in the second degree.\n18 U.S.C. § 1111(a). To convict a defendant of second-degree murder under\n\n§ 1111(a), the government must prove beyond a reasonable doubt that: (1) the\n\nvictim was killed; (2) the defendant caused the victim’s death with malice\n\n 10\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 11 of 12\n\n\naforethought; and (3) the killing occurred in the special maritime or territorial\n\njurisdiction of the United States. See United States v. McRae, 593 F.2d 700, 704\n\n(5th Cir. 1979); 11th Cir. Crim. Pattern Jury Instr. O45.3 (second-degree murder).\n\nIn other words, every federal second-degree murder requires the defendant to\n\nactually kill the victim with malice aforethought. As with Florida law, the\n\ndistinction between first- and second-degree murder under federal law is\n\npremeditation. See Lewis v. United States, 523 U.S. 155, 158, 118 S. Ct. 1135,\n\n1138 (1998); 11th Cir. Crim. Pattern Jury Instr. O45.3.\n\n Because second-degree murder under § 1111(a) is not materially\n\ndistinguishable from Florida second-degree murder, Jones controls our\n\ndetermination that federal second-degree murder has as an element the use of\n\nphysical force and categorically qualifies as a crime of violence under § 924(c)’s\n\nelements clause. See United States v. Kaley, 579 F.3d 1246, 1255 (11th Cir. 2009)\n\n(explaining that under our prior panel precedent rule, we are bound by a prior\n\npanel’s holding until it is overruled by the Supreme Court or this Court sitting en\n\nbanc).\n\n Even if we were not bound by Jones, however, we would conclude that\n\nfederal second-degree murder qualifies under § 924(c)’s elements clause. At a\n\nminimum, federal second-degree murder has as an element the killing of a human\n\nbeing with malice aforethought. See 18 U.S.C. § 1111(a). Because § 1111(a), by\n\n\n 11\n\f Case: 18-10488 Date Filed: 05/17/2019 Page: 12 of 12\n\n\nits plain terms, criminalizes the actual killing of another person, the level of force\n\nused must necessarily be capable of causing physical pain or injury. See Curtis\n\nJohnson v. United States, 559 U.S. 133, 140, 130 S. Ct. 1265, 1271 (2010)\n\n(concluding that the phrase “physical force” in the ACCA’s elements clause\n\n“means violent force—that is, force capable of causing physical pain or injury to\n\nanother person”); see also Stokeling v. United States, 586 U.S. ___, 139 S. Ct. 544,\n\n552-53 (2019) (reaffirming Curtis Johnson’s “capable” standard for the definition\n\nof physical force); United States v. Vail-Bailon, 868 F.3d 1293, 1299, 1303 (11th\n\nCir. 2017) (en banc) (holding that Florida felony battery qualifies as a crime of\n\nviolence under U.S.S.G. § 2L1.2’s analogous elements clause because the offense\n\nrequires great bodily harm to the victim, which “necessarily constitutes force\n\ncapable of causing pain or injury”). Thus, regardless of any vagueness challenge\n\nto § 924(c)(3)(B)’s residual clause, second-degree murder under § 1111(a)\n\ncategorically qualifies as a crime of violence under § 924(c)(3)(A)’s elements\n\nclause.\n\n For all these reasons, we affirm the district court’s denial of Thompson’s\n\nauthorized second § 2255 motion.\n\n AFFIRMED.\n\n\n\n\n 12\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Rickey Thompson v. United States\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-17\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-10488 Date Filed: 05/17/2019 Page: 1 of 12\\n\\n\\n [PUBLISH]\\n\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-10488\\n Non-Argument Calendar\\n ________________________\\n\\n D.C. Docket Nos. 9:16-cv-81071-WPD,\\n 9:07-cr-80036-WPD-1\\n\\n\\nRICKEY THOMPSON,\\n\\n Petitioner-Appellant,\\n\\n versus\\n\\nUNITED STATES OF AMERICA,\\n\\n Respondent-Appellee.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 17, 2019)\\n\\nBefore WILLIAM PRYOR, GRANT and HULL, Circuit Judges.\\n\\nHULL, Circuit Judge:\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 2 of 12\\n\\n\\n Rickey Thompson, a federal prisoner proceeding with counsel, appeals the\\n\\ndistrict court’s denial of his authorized second 28 U.S.C. § 2255 motion to vacate.\\n\\nIn this appeal, Thompson argues that his two 18 U.S.C. § 924(c) firearm\\n\\nconvictions are invalid in light of Johnson v. United States, 576 U.S. ___, 135 S.\\n\\nCt. 2551 (2015), and Sessions v. Dimaya, 584 U.S. ___, 138 S. Ct. 1204 (2018).\\n\\nSpecifically, Thompson contends that his predicate second-degree murder offenses\\n\\nunder 18 U.S.C. § 1111 do not qualify as crimes of violence after Johnson.\\n\\n After careful review of the parties’ briefs and the record, we conclude\\n\\nThompson’s two federal second-degree murder convictions qualify as crimes of\\n\\nviolence under both § 924(c)’s residual and elements clauses. Thus, we affirm the\\n\\ndistrict court’s denial of Thompson’s authorized second § 2255 motion.1\\n\\n I. BACKGROUND\\n\\nA. Convictions, Direct Appeal, and First § 2255 Motion\\n\\n In 2008, a federal jury convicted Thompson, a Bahamian boat captain, and a\\n\\ncodefendant of 30 counts arising out of a drug- and alien-smuggling conspiracy.\\n\\nRelevant to this appeal, during two boat trips in 2006, Thompson pointed a firearm\\n\\nat passengers on the boat whom he had agreed to smuggle into the United States.\\n\\n\\n\\n\\n 1\\n In reviewing a denial of a motion to vacate under § 2255, we review the district court’s\\nlegal conclusions de novo and its findings of fact for clear error. Stoufflet v. United States, 757\\nF.3d 1236, 1239 (11th Cir. 2014).\\n\\n\\n 2\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 3 of 12\\n\\n\\nWhen the passengers said they could not swim, Thompson forced them to jump, or\\n\\npushed them, from his boat into deep water off the coast of Jupiter Island, Florida,\\n\\nwhere three of them drowned.\\n\\n Based on this conduct, Thompson was convicted of three counts of second-\\n\\ndegree murder, in violation of 18 U.S.C. § 1111, and two counts of carrying and\\n\\nbrandishing a firearm during and in relation to a crime of violence, in violation of\\n\\n18 U.S.C. § 924(c)(1)(A)(ii). For the purposes of § 924(c), a “crime of violence”\\n\\nmeans an offense that is a felony and:\\n\\n (A) has as an element the use, attempted use, or threatened use of\\n physical force against the person or property of another, or\\n\\n (B) that by its nature, involves a substantial risk that physical force\\n against the person or property of another may be used in the\\n course of committing the offense.\\n\\n18 U.S.C. § 924(c)(3)(A), (B). We refer to § 924(c)(3)(A) as the “elements clause”\\n\\nand § 924(c)(3)(B) as the “residual clause.” Ovalles v. United States, 905 F.3d\\n\\n1231, 1234 (11th Cir. 2018) (en banc) (“Ovalles II”). Here, as charged in his\\n\\nindictment, Thompson’s companion crimes of violence: (1) for his § 924(c)\\n\\nfirearm conviction in Count 28 was his two second-degree murder convictions in\\n\\nCounts 19 and 20 for the deaths of Roselyne Lubin and Alnert Charles; and (2) for\\n\\nhis § 924(c) firearm conviction in Count 29 was his second-degree murder\\n\\nconviction in Count 21 for the death of Nigel Warren.\\n\\n\\n\\n 3\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 4 of 12\\n\\n\\n Thompson received a total life sentence on all 30 counts, including, inter\\n\\nalia, three concurrent life sentences for the second-degree murder offenses in\\n\\nCounts 19, 20 and 21, a consecutive seven-year sentence for the first § 924(c)\\n\\nfirearm offense in Count 28, and a consecutive 25-year sentence for the second\\n\\n§ 924(c) firearm offense in Count 29. On direct appeal, this Court affirmed\\n\\nThompson’s convictions and sentences, United States v. Thompson, 363 F. App’x\\n\\n737, 738 (11th Cir. Feb. 3, 2010), and later affirmed the district court’s denial of\\n\\nThompson’s first § 2255 motion, Thompson v. United States, 608 F. App’x 726,\\n\\n727 (11th Cir. 2015).\\n\\nB. Authorized Second § 2255 Motion\\n\\n In June 2016, Thompson pro se filed in this Court an application for leave to\\n\\nfile a second or successive § 2255 motion asserting, inter alia, that his § 924(c)\\n\\nconvictions were invalid based on the Supreme Court’s recently decided Johnson.\\n\\nIn Johnson, the Supreme Court struck down the residual clause of the Armed\\n\\nCareer Criminal Act (“ACCA”) as unconstitutionally vague.2 576 U.S. at ___, 135\\n\\nS. Ct. at 2555-58, 2563. The Supreme Court later held that Johnson announced a\\n\\n\\n\\n 2\\n The ACCA provides for a mandatory minimum 15-year sentence when a defendant\\nconvicted under 18 U.S.C. § 922(g) has three or more prior convictions for a “violent felony.”\\n18 U.S.C. § 924(e)(1). The ACCA defines a “violent felony,” in relevant part, as any crime\\npunishable by a term of imprisonment exceeding one year that “otherwise involves conduct that\\npresents a serious potential risk of physical injury to another,” also known as the ACCA’s\\nresidual clause. Id. § 924(e)(2)(B); see also United States v. Owens, 672 F.3d 966, 968 (11th\\nCir. 2012).\\n 4\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 5 of 12\\n\\n\\nnew substantive rule that applies retroactively to cases on collateral review. Welch\\n\\nv. United States, 578 U.S. ___, ___, 136 S. Ct. 1257, 1268 (2016). More recently,\\n\\nin Dimaya, the Supreme Court applied Johnson and struck down as\\n\\nunconstitutionally vague the definition of “crime of violence” in 18 U.S.C. § 16(b),\\n\\nwhich is textually identical to § 924(c)’s residual clause, as incorporated into the\\n\\nImmigration and Nationality Act. 584 U.S. at ___, 138 S. Ct. at 1210-11, 1213-16,\\n\\n1218-23.\\n\\n In his June 2016 application, Thompson, relying on Johnson, argued that his\\n\\nfederal second-degree murder convictions could not qualify as crimes of violence:\\n\\n(1) under § 924(c)’s residual clause because it, like the ACCA’s residual clause,\\n\\nwas unconstitutionally vague; or (2) under § 924(c)’s elements clause because 18\\n\\nU.S.C. § 1111 does not involve the requisite use of physical force.\\n\\n This Court granted Thompson’s application as to his Johnson-based claim,\\n\\nconcluding that he had made a prima facie showing that the statutory criteria in 28\\n\\nU.S.C. § 2255(h) had been met. The Court noted that at that time it was unsettled\\n\\nwhether Johnson applied to § 924(c)’s residual clause and that the Court had not\\n\\nexplicitly ruled on whether a federal § 1111 second-degree murder is a crime of\\n\\nviolence under § 924(c). In re Thompson, No. 16-13797 (11th Cir. July 11, 2016).\\n\\n Once back in the district court, Thompson was appointed counsel.\\n\\nThompson’s now-authorized, second § 2255 motion, amended by counsel,\\n\\n\\n 5\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 6 of 12\\n\\n\\ncontended that Thompson was actually innocent of his § 924(c) convictions\\n\\nbecause his predicate second-degree murder convictions were no longer crimes of\\n\\nviolence in light of Johnson.\\n\\n The district court concluded that Johnson did not apply to § 924(c)’s residual\\n\\nclause, citing this Court’s panel decision in Ovalles v. United States, 861 F.3d\\n\\n1257 (11th Cir. 2017) (“Ovalles I”), vacated on reh’g en banc, 889 F.3d 1259 (11th\\n\\nCir. 2018). Alternatively, the district court concluded that second-degree murder\\n\\nqualified as a crime of violence under § 924(c)’s elements clause. Accordingly,\\n\\nthe district court denied Thompson’s second § 2255 motion on the merits but\\n\\ngranted him a certificate of appealability on whether second-degree murder is a\\n\\ncrime of violence for purposes of a § 924(c) firearm conviction.\\n\\n II. THOMPSON’S § 924(c) CLAIM\\n\\nA. Residual Clause in § 924(c)(3)(B)\\n\\n While Thompson’s current appeal was pending, this Court sitting en banc\\n\\nheld in Ovalles II that § 924(c)(3)(B)’s residual clause is not unconstitutionally\\n\\nvague under Johnson and Dimaya. See 905 F.3d at 1233-34, 1252-53 (interpreting\\n\\nthe text in § 924(c)(3)(B) to incorporate a conduct-based approach that avoids the\\n\\nconstitutional vagueness concerns that invalidated the statutory provisions in\\n\\nJohnson and Dimaya). Subsequently, given Ovalles II held § 924(c) is not\\n\\nunconstitutionally vague under Johnson and Dimaya, this Court has held a federal\\n\\n\\n 6\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 7 of 12\\n\\n\\nprisoner’s authorized successive § 2255 motion asserting a vagueness challenge to\\n\\n§ 924(c)’s residual clause does not satisfy § 2255(h)’s requirements because:\\n\\n(1) those decisions do not supply a rule of constitutional law that is applicable to\\n\\n§ 924(c); and (2) any challenge to the district court’s use of the categorical\\n\\napproach in applying § 924(c)’s residual clause raises a statutory, not a\\n\\nconstitutional, claim. See Solomon v. United States, 911 F.3d 1356, 1358-59,\\n\\n1361 (11th Cir. 2019) (citing In re Garrett, 908 F.3d 686, 688-89 (11th Cir. 2018)).\\n\\nThus, Ovalles II and Garrett “foreclose even the most generous reading of [the\\n\\nmovant’s] challenges, both constitutional and statutory.” Id. at 1361.3\\n\\n Thompson now concedes that his claim that § 924(c)’s residual clause is\\n\\nunconstitutionally vague is foreclosed by Ovalles II, and he states that he raises it\\n\\nmerely to preserve it in case the Supreme Court takes up the issue. 4 Notably too,\\n\\nThompson does not contend that his second-degree murder convictions fail to\\n\\n\\n\\n 3\\n Although this Court authorized Thompson’s proposed second § 2255 motion, that was\\nonly a threshold determination, and the district court was required to consider de novo whether\\nthe statutory criteria have been met. See Jordan v. Sec’y, Dep’t of Corrs., 485 F.3d 1351, 1357-\\n58 (11th Cir. 2007). This appeal is the Court’s “‘first hard look’ at whether the § 2255(h)\\nrequirements have been met.” See Solomon, 911 F.3d at 1361.\\n 4\\n Shortly before Thompson filed his appeal brief, the Supreme Court granted a petition for\\na writ of certiorari in United States v. Davis, 903 F.3d 483 (5th Cir. 2018), cert granted, No. 18-\\n431, 139 S. Ct. 782 (U.S. Jan. 4, 2019). The Supreme Court recently heard argument in Davis on\\nwhether § 924(c)’s residual clause is unconstitutionally vague, and a decision is forthcoming.\\nRegardless, we are required to apply Ovalles II as binding precedent, as a grant of certiorari does\\nnot constitute a change in the law or a basis for relief. See Gissendaner v. Comm’r, Ga. Dep’t of\\nCorrs., 779 F.3d 1275, 1284 (11th Cir. 2015).\\n\\n\\n 7\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 8 of 12\\n\\n\\nqualify under § 924(c)’s residual clause using the conduct-based approach adopted\\n\\nin Ovalles II. Indeed, Counts 19, 20, and 21 of the indictment expressly charged\\n\\nthat Thompson “with malice aforethought, did unlawfully kill” the victims by\\n\\nordering each victim, “who could not swim, to jump from a boat into the waters of\\n\\nthe Atlantic Ocean,” and the jury found Thompson guilty of those counts. That\\n\\nconduct alone satisfies § 924(c)’s residual clause, which encompasses felonies that\\n\\n“involve[ ] conduct that presents a serious potential risk of physical injury to\\n\\nanother.” See 18 U.S.C. § 924(e)(2)(B)(ii).\\n\\n For these reasons, the district court did not err in denying Thompson’s\\n\\nauthorized second § 2255 motion to the extent it challenged § 924(c)’s residual\\n\\nclause.\\n\\nB. Elements Clause in § 924(c)(3)(A)\\n\\n Also while Thompson’s appeal was pending, this Court held that both\\n\\nattempted first-degree and second-degree murder under Florida law categorically\\n\\nqualify as violent felonies under the ACCA’s elements clause. See United States\\n\\nv. Jones, 906 F.3d 1325, 1326-27 (11th Cir. 2018) (Florida second-degree murder);\\n\\nHylor v. United States, 896 F.3d 1219, 1220-21 (11th Cir. 2018) (Florida\\n\\nattempted first-degree murder). As explained below, those precedents drive the\\n\\noutcome here because a federal second-degree murder offense is not materially\\n\\ndifferent from Florida’s second-degree murder offense.\\n\\n\\n 8\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 9 of 12\\n\\n\\n Under Florida law, second-degree murder is “[t]he unlawful killing of a\\n\\nhuman being, when perpetrated by any act imminently dangerous to another and\\n\\nevincing a depraved mind regardless of human life, although without any\\n\\npremeditated design to effect the death of any particular individual.” Jones, 906\\n\\nF.3d at 1328 (alterations in original); see Fla. Stat. § 782.04(2). “The only\\n\\nmeaningful difference between first- and second-degree murder in Florida is that\\n\\nfirst-degree murder requires the element of premeditation, while second-degree\\n\\nmurder does not.” Id. at 1329; see Fla. Stat. § 782.04(1)(a).\\n\\n In Jones, this Court determined that Florida’s second-degree murder offense\\n\\nhas as an element the use of physical force. 906 F.3d at 1328-29. The Court relied\\n\\non Hylor, which held that Florida attempted first-degree murder was categorically\\n\\na violent felony under the ACCA’s elements clause and rejected an argument that\\n\\nattempted murder by poisoning did not involve physical force. Id. The Jones\\n\\nCourt stated that binding precedent in this Court and the Supreme Court made clear\\n\\nthat even indirect force, such as the use of poison to kill someone, involved the use\\n\\nof violent force capable of causing physical pain or injury to a person, as required\\n\\nfor the ACCA’s elements clause. Id. The Court further explained that the\\n\\nlanguage of the elements clause “asks about actions constituting an offense, rather\\n\\nthan the mental state of the actor committing the offense.” Id. at 1329. Therefore,\\n\\nthe mens rea distinction between first- and second-degree murder (i.e., the element\\n\\n\\n 9\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 10 of 12\\n\\n\\nof premeditation) “makes no difference” to the determination of whether the\\n\\nACCA’s elements clause applies. Id.\\n\\n Thompson acknowledges that this Court’s decision in Jones is controlling\\n\\nprecedent and that, under Jones, federal second-degree murder, like Florida\\n\\nsecond-degree murder, categorically qualifies under § 924(c)’s nearly identical\\n\\nelements clause. We agree with Thompson and the government and conclude that,\\n\\neven if the Supreme Court overturns Ovalles II, that will not help Thompson\\n\\nbecause, under the reasoning in Jones, his federal second-degree murder\\n\\nconvictions categorically qualify as crimes of violence under § 924(c)’s elements\\n\\nclause.\\n\\n Under federal law, first- and second- degree murder are defined as follows:\\n\\n Murder is the unlawful killing of a human being with malice\\n aforethought. Every murder perpetrated by poison, lying in wait, or any\\n other kind of willful, deliberate, malicious, and premeditated killing; or\\n committed in the perpetration of, or attempt to perpetrate, any arson,\\n escape, murder, kidnapping, treason, espionage, sabotage, aggravated\\n sexual abuse or sexual abuse, child abuse, burglary, or robbery; or\\n perpetrated as part of a pattern or practice of assault or torture against a\\n child or children; or perpetrated from a premeditated design unlawfully\\n and maliciously to effect the death of any human being other than him\\n who is killed, is murder in the first degree.\\n\\n Any other murder is murder in the second degree.\\n18 U.S.C. § 1111(a). To convict a defendant of second-degree murder under\\n\\n§ 1111(a), the government must prove beyond a reasonable doubt that: (1) the\\n\\nvictim was killed; (2) the defendant caused the victim’s death with malice\\n\\n 10\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 11 of 12\\n\\n\\naforethought; and (3) the killing occurred in the special maritime or territorial\\n\\njurisdiction of the United States. See United States v. McRae, 593 F.2d 700, 704\\n\\n(5th Cir. 1979); 11th Cir. Crim. Pattern Jury Instr. O45.3 (second-degree murder).\\n\\nIn other words, every federal second-degree murder requires the defendant to\\n\\nactually kill the victim with malice aforethought. As with Florida law, the\\n\\ndistinction between first- and second-degree murder under federal law is\\n\\npremeditation. See Lewis v. United States, 523 U.S. 155, 158, 118 S. Ct. 1135,\\n\\n1138 (1998); 11th Cir. Crim. Pattern Jury Instr. O45.3.\\n\\n Because second-degree murder under § 1111(a) is not materially\\n\\ndistinguishable from Florida second-degree murder, Jones controls our\\n\\ndetermination that federal second-degree murder has as an element the use of\\n\\nphysical force and categorically qualifies as a crime of violence under § 924(c)’s\\n\\nelements clause. See United States v. Kaley, 579 F.3d 1246, 1255 (11th Cir. 2009)\\n\\n(explaining that under our prior panel precedent rule, we are bound by a prior\\n\\npanel’s holding until it is overruled by the Supreme Court or this Court sitting en\\n\\nbanc).\\n\\n Even if we were not bound by Jones, however, we would conclude that\\n\\nfederal second-degree murder qualifies under § 924(c)’s elements clause. At a\\n\\nminimum, federal second-degree murder has as an element the killing of a human\\n\\nbeing with malice aforethought. See 18 U.S.C. § 1111(a). Because § 1111(a), by\\n\\n\\n 11\\n\\f Case: 18-10488 Date Filed: 05/17/2019 Page: 12 of 12\\n\\n\\nits plain terms, criminalizes the actual killing of another person, the level of force\\n\\nused must necessarily be capable of causing physical pain or injury. See Curtis\\n\\nJohnson v. United States, 559 U.S. 133, 140, 130 S. Ct. 1265, 1271 (2010)\\n\\n(concluding that the phrase “physical force” in the ACCA’s elements clause\\n\\n“means violent force—that is, force capable of causing physical pain or injury to\\n\\nanother person”); see also Stokeling v. United States, 586 U.S. ___, 139 S. Ct. 544,\\n\\n552-53 (2019) (reaffirming Curtis Johnson’s “capable” standard for the definition\\n\\nof physical force); United States v. Vail-Bailon, 868 F.3d 1293, 1299, 1303 (11th\\n\\nCir. 2017) (en banc) (holding that Florida felony battery qualifies as a crime of\\n\\nviolence under U.S.S.G. § 2L1.2’s analogous elements clause because the offense\\n\\nrequires great bodily harm to the victim, which “necessarily constitutes force\\n\\ncapable of causing pain or injury”). Thus, regardless of any vagueness challenge\\n\\nto § 924(c)(3)(B)’s residual clause, second-degree murder under § 1111(a)\\n\\ncategorically qualifies as a crime of violence under § 924(c)(3)(A)’s elements\\n\\nclause.\\n\\n For all these reasons, we affirm the district court’s denial of Thompson’s\\n\\nauthorized second § 2255 motion.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 12\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2283,"cells":{"id":{"kind":"number","value":8444004,"string":"8,444,004"},"name":{"kind":"string","value":"Rickey THOMPSON v. United States"},"name_abbreviation":{"kind":"string","value":"Thompson v. United States"},"decision_date":{"kind":"string","value":"2019-05-17"},"docket_number":{"kind":"string","value":"No. 18-10488"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Grant, Hull, Pryor\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/8415439/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"GRANT"},"judge2":{"kind":"string","value":"HULL"},"judge3":{"kind":"string","value":"PRYOR"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/8444004/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Rickey THOMPSON v. United States\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-17\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Rickey THOMPSON v. United States\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-17\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2284,"cells":{"id":{"kind":"number","value":4621540,"string":"4,621,540"},"name":{"kind":"string","value":"PLAYNATION PLAY SYSTEMS, INC., D.B.A. Gorilla Playsets, Plaintiff-Appellee, v. VELEX CORPORATION, D.B.A. Gorilla Gym, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"PlayNation Play Systems, Inc. v. Velex Corporation"},"decision_date":{"kind":"string","value":"2019-05-21"},"docket_number":{"kind":"string","value":"17-15226"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wilson, Branch, Anderson\", \"parties\": \"\", \"opinions\": [{\"author\": \"WILSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-15226 Date Filed: 05/21/2019 Page: 1 of 19\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15226\\n ________________________\\n\\n D.C. Docket No. 1:14-cv-01046-RWS\\n\\n\\n\\nPLAYNATION PLAY SYSTEMS, INC.,\\nd.b.a. Gorilla Playsets,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nVELEX CORPORATION,\\nd.b.a. Gorilla Gym,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 21, 2019)\\n\\nBefore WILSON, BRANCH, and ANDERSON, Circuit Judges.\\n\\nWILSON, Circuit Judge:\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 2 of 19\\n\\n\\n The parties to this appeal both chose a gorilla as the face of their respective\\n\\nbrands. Litigation ensued. PlayNation Play Systems, Inc. sued Velex Corporation\\n\\nfor trademark infringement. The district court conducted a bench trial and entered\\n\\njudgment for PlayNation. Velex now appeals, arguing that the district court erred\\n\\nin finding trademark infringement, awarding damages to PlayNation, and\\n\\ncancelling Velex’s trademark registration. After careful review and with the\\n\\nbenefit of oral argument, we affirm the district court’s decisions on Velex’s\\n\\nliability for trademark infringement and cancellation of Velex’s trademark. We\\n\\nvacate and remand, however, on the district court’s determination of damages\\n\\nbased on Velex’s willful infringement.\\n\\n I. Factual Background\\n\\n PlayNation has sold children’s outdoor playground equipment, including\\n\\nswing sets and attachable swings, ropes, and rings, under its “Gorilla Playsets”\\n\\nbrand since 2002. PlayNation owns three registered trademarks for Gorilla\\n\\nPlaysets, two registered in 2004 and another in 2014. 1 Velex sells “Gorilla Gym”\\n\\ndoorway pull-up bars and various attachable accessories for children, including\\n\\n\\n\\n1\\n PlayNation’s mark:\\n\\n\\n\\n\\n 2\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 3 of 19\\n\\n\\nswings, ropes, and rings, under its “Gorilla Gym” brand. Velex successfully\\n\\nregistered a trademark for Gorilla Gym in 2014. 2 Both PlayNation and Velex’s\\n\\ntrademarks are registered in Class 28, the broad class of goods for games and other\\n\\nplaythings.\\n\\n II. Trademark Infringement\\n\\n Velex first argues that the district court erred by concluding that consumers\\n\\nwould likely be confused by Velex’s use of the Gorilla Gym mark. In an appeal\\n\\nfrom a bench trial, we review a district court’s conclusions of law de novo and its\\n\\nfactual findings for clear error. Tartell v. S. Fla. Sinus & Allergy Ctr., Inc., 790\\n\\nF.3d 1253, 1257 (11th Cir. 2015). A factual finding is clearly erroneous if, after\\n\\nviewing the totality of the evidence, the court is left with a definite and firm\\n\\nconviction that a mistake was made. Id.\\n\\n Under the Lanham Act, 15 U.S.C. § 1114(1), a defendant is liable for\\n\\ntrademark infringement if the plaintiff shows (1) that its mark has priority and (2)\\n\\nthat the defendant’s mark is likely to cause consumer confusion. Frehling Enter.,\\n\\nInc. v. Int’l Select Grp., Inc., 192 F.3d 1330, 1335 (11th Cir. 1999). Velex\\n\\n\\n2\\n Velex’s mark:\\n\\n\\n\\n\\n 3\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 4 of 19\\n\\n\\nstipulated to the priority of PlayNation’s mark. We thus need only consider\\n\\nwhether the district court clearly erred in finding that Velex’s mark was likely to\\n\\ncause consumer confusion. In making that determination, we weigh seven factors:\\n\\n(1) the strength of the plaintiff’s mark; (2) the similarity of the marks; (3) the\\n\\nsimilarity of the products the marks represent; (4) the similarity of the parties’\\n\\nretail outlets and customers; (5) the similarity of advertising media; (6) the\\n\\ndefendant’s intent; and (7) actual confusion. Lone Star Steakhouse & Saloon, Inc.\\n\\nv. Longhorn Steaks, Inc., 122 F.3d 1379, 1382 (11th Cir. 1997).\\n\\n We review for clear error both a district court’s ultimate decision on\\n\\nlikelihood of confusion and its findings on each factor. Frehling, 192 F.3d at\\n\\n1335. Of these factors, the strength of the mark and actual confusion are the most\\n\\nprobative. Id. The district court held that each factor except the defendant’s intent\\n\\nweighed in favor of confusion. Velex challenges the district court’s determination\\n\\non the other factors and argues that the district court should have adopted two new\\n\\nfactors.\\n\\n A. Strength of PlayNation’s Mark\\n\\n “Classifying the type of mark Plaintiff has determines whether it is strong or\\n\\nweak. The stronger the mark, the greater the scope of protection accorded it, the\\n\\nweaker the mark, the less trademark protection it receives. There are four\\n\\ncategories of marks: (1) generic, (2) descriptive, (3) suggestive, and (4) arbitrary.”\\n\\n\\n 4\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 5 of 19\\n\\n\\nFrehling, 192 F.3d at 1335 (internal citations omitted). Suggestive marks are\\n\\nstronger and accordingly receive greater protection. Id. “Suggestive marks subtly\\n\\nconnote something about the service so that a customer could use his or her\\n\\nimagination and determine the nature of the service.” Freedom Sav. Loan Ass’n v.\\n\\nWay, 757 F.2d 1176, 1182 n.5 (11th Cir. 1985). The district court determined that\\n\\nPlayNation’s Gorilla Playsets mark was “descriptive or suggestive.” The products\\n\\nPlayNation sells under the mark are, of course, not designed for or used by gorillas.\\n\\nAt a minimum, the connection between the mark and the product requires some\\n\\nimagination. See Caliber Auto. Liquidators, Inc. v. Premier Chrysler, Jeep,\\n\\nDodge, LLC, 605 F.3d 931, 938 (11th Cir. 2010) (“A suggestive mark refers to\\n\\nsome characteristic of the goods, but requires a leap of the imagination to get from\\n\\nthe mark to the product [e.g., Penguin Refrigerators].”) (quotation marks omitted).\\n\\n The district court also reasoned that other factors increased the strength of\\n\\nPlayNation’s mark. See Frehling, 192 F.3d at 1336. First, PlayNation has\\n\\nextensively used the mark in commerce since 2002. PlayNation engaged in\\n\\nsignificant nationwide advertising and promotion using its Gorilla Playsets mark.\\n\\nThe district court found that this widespread use indicated consumer recognition,\\n\\nwhich enhances the strength of a mark. See John H. Harland Co. v. Clarke\\n\\nChecks, Inc., 711 F.2d 966, 974 n.13 (11th Cir. 1983) (noting that a mark may, “by\\n\\nreason of subsequent use and promotion, acquire such distinctiveness that it can\\n\\n\\n 5\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 6 of 19\\n\\n\\nfunction as a significant indication of a particular producer as source of the goods\\n\\nwith which it is used”). 3\\n\\n Second, the parties agree that PlayNation’s mark has been registered with\\n\\nthe Patent and Trademark Office for at least five years and is thus incontestable.\\n\\nFrehling, 192 F.3d at 1336. An incontestable mark “is presumed to be at least\\n\\ndescriptive with secondary meaning, and therefore a relatively strong mark.”\\n\\nDieter v. B & H Indus. of Southwest Fla., Inc., 880 F.3d 322, 329 (11th Cir. 1989);\\n\\nsee also Frehling, 192 F.3d at 1336.\\n\\n Finally, the lack of extensive third-party use also strengthens PlayNation’s\\n\\nmark. Frehling, 192 F.3d at 1336. Velex argues that the mark is weak because\\n\\nroughly thirty other registered marks in Class 28 contain the word “gorilla.” But\\n\\nnone of those gorilla marks were used on play equipment. And similar marks used\\n\\nby third parties in unrelated businesses or markets do not diminish the strength of a\\n\\nmark in a particular market. See Safeway Stores, Inc. v. Safeway Disc. Drugs, Inc.,\\n\\n\\n\\n\\n3\\n We have held that “in isolation, evidence of promotion efforts is not sufficient to establish a\\nmark’s commercial strength because it tells us precious little about the efficacy of those efforts in\\ncreating marketplace recognition . . . .” Fla. Int’l Univ. Bd. of Trustees v. Fla. Nat’l Univ., Inc.,\\n830 F.3d 1242, 1259 (11th Cir. 2016) (first emphasis added) (holding that “[t]here simply was\\nnot sufficient evidence of commercial strength in the record to require the district court to ignore\\nthe substantial third-party usage.”). But this “circumstantial evidence of advertising and\\npromotion,” id. (quotations omitted), is not the only evidence of the strength of PlayNation’s\\nmark. Accordingly, the district court did not err in finding PlayNation’s advertising and\\npromotion expenditures contributed to the strength of its mark.\\n\\n\\n 6\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 7 of 19\\n\\n\\n675 F.2d 1160, 1167 (11th Cir. 1982) (finding that twenty marks containing one of\\n\\nthe same words as the plaintiff’s mark did “not significantly diminish the strength\\n\\nof the [plaintiff’s] mark” because the other marks were used by “businesses not\\n\\nclosely related” to the plaintiff’s business), abrogated on other grounds, Tobinick\\n\\nv. Novella, 884 F.3d 1110 (11th Cir. 2018); cf. Sovereign Military Hospitaller\\n\\nOrder of Saint John of Jerusalem of Rhodes & of Malta v. Fla. Priory of the\\n\\nKnights Hospitallers of the Sovereign Order of Saint John of Jerusalem, Knights of\\n\\nMalta, The Ecumenical Order, 809 F.3d 1171, 1186 (11th Cir. 2015) (“That other\\n\\norganizations use parts of the Sovereign Order’s word marks is not persuasive\\n\\nevidence of third-party use.”).\\n\\n The district court did not clearly err in determining that PlayNation’s Gorilla\\n\\nPlaysets mark was strong.\\n\\n B. Actual Confusion\\n\\n “It is undisputed that evidence of actual confusion is the best evidence of a\\n\\nlikelihood of confusion.” Frehling, 192 F.3d at 1340. The actual confusion\\n\\ninquiry turns on both the number of instances of confusion and the type of person\\n\\nconfused. Caliber Auto., 605 F.3d at 936. While numerous instances of actual\\n\\nconfusion add greater weight in favor of confusion, “the quantum of evidence\\n\\nneeded to show actual confusion is relatively small.” Id. at 937 (quotation marks\\n\\n\\n\\n\\n 7\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 8 of 19\\n\\n\\nomitted). Evidence that ultimate consumers were actually confused deserves\\n\\n“special attention.” Id. at 936–37.\\n\\n The district court determined that the actual confusion factor weighed in\\n\\nfavor of a likelihood of confusion. PlayNation produced two ultimate purchasers\\n\\nof PlayNation’s Gorilla Playsets swing sets who contacted Velex for customer\\n\\nservice. The consumers believed Velex manufactured both Gorilla Gym and\\n\\nGorilla Playsets products. Consumers also posted on retail websites selling Gorilla\\n\\nPlaysets swings and trapeze bars asking if those items work “with the Gorilla Gym\\n\\nindoors.” Velex argues this evidence was insufficient to establish actual confusion\\n\\nbecause the two consumers were careless and uninformed. 4 Velex points to\\n\\nportions of the consumers’ testimony in which they confuse the names of the two\\n\\ncompanies and misremember which name was on the packaging and website they\\n\\nlooked at before calling Velex. Velex asserts that a prudent consumer would have\\n\\n\\n\\n4\\n Velex argues that the two consumers calling the wrong phone number amounts to “initial\\ninterest confusion,” a doctrine we have not yet accepted as actionable under the Lanham Act.\\nSee Suntree Tech., Inc. v. Ecosense Intern., Inc., 693 F.3d 1338, 1347 (11th Cir. 2012). But\\nVelex misunderstands initial interest confusion, which occurs when an alleged infringer pulls a\\nsort of bait and switch. The infringer uses another’s trademark (or an imitation of it) to capture\\nconsumers’ initial interest, leading the consumers to the infringer’s website or call center, for\\nexample. But then the consumers, aware they are not actually dealing with the trademark holder,\\ndecide to purchase the infringer’s other good or service. See N. Am. Med. Corp. v. Axiom\\nWorldwide, Inc., 522 F.3d 1211, 1221 (11th Cir. 2008). That situation did not occur here. These\\nwere instances of source confusion. The consumers testified that they believed Gorilla Gym and\\nGorilla Playsets were produced by the same company. See id. at 1222 n.9 (“‘Source confusion’\\nexists because consumers are likely to be confused as to whether [the infringer’s] products have\\nthe same source or sponsor as [the trademark holder’s] or whether there is some other affiliation\\nor relationship between the two.”).\\n 8\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 9 of 19\\n\\n\\nexamined the packaging, read the product warranty, or researched the product on\\n\\nthe internet. Velex argues that had the consumers been so diligent, they would\\n\\nhave discovered that PlayNation—not Velex—manufactured the product they\\n\\npurchased.\\n\\n First, nothing in the actual confusion analysis requires the plaintiff to\\n\\nproduce the most careful consumer, who diligently researched and meticulously\\n\\nexamined the inner and outer packing to determine the provenance of the product\\n\\nshe purchased. It only requires that the consumers be reasonably prudent. The\\n\\ndistrict court found the consumers’ testimony probative. That the district court\\n\\nmade that determination even though the two witnesses confused the names of the\\n\\ntwo brands or failed to examine the packing before mistakenly calling Velex for\\n\\nhelp does not amount to clear error.\\n\\n Second, the number of instances and the type of consumer also support the\\n\\ndistrict court’s actual confusion finding. The customers PlayNation identified are\\n\\nultimate consumers of the product, to which we give special weight. And the\\n\\nnumber of instances need not be large to be probative of confusion. See Safeway\\n\\nStores, 675 F.2d at 1167 (finding one instance of actual customer confusion\\n\\nsufficient and holding that “[a]lthough the number of instances is small, the people\\n\\nconfused are precisely those whose confusion is most significant”).\\n\\n\\n\\n\\n 9\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 10 of 19\\n\\n\\n The district court thus did not clearly err in holding that the actual confusion\\n\\nfactor weighed in favor of a likelihood of confusion.\\n\\n C. Similarity of Marks\\n\\n To determine if two marks are similar, the court “considers the overall\\n\\nimpressions that the marks create, including the sound, appearance, and manner in\\n\\nwhich they are used.” Frehling, 192 F.3d at 1337. The dominant portion of both\\n\\nmarks is an image of a large gorilla and the word “gorilla.” The other words,\\n\\n“playset” in one and “gym” in the other, are very similar and do not contribute to\\n\\ndistinctiveness. See id. (holding that “a mark may be surrounded by additional\\n\\nwords of lesser importance and not have its strength diluted”). The colors and\\n\\nfonts are different, and the gorillas are in different areas and positions in the marks.\\n\\nBut even so, given the similarity in the type of gorilla, size of gorilla, and the\\n\\nalmost indistinguishable words used in the two marks, those differences do not\\n\\nmake the district court’s decision clearly erroneous.\\n\\n D. Similarity of Products, Retail Outlets, and Advertising\\n\\n The district court did not clearly err in finding that the products, retail\\n\\noutlets, and advertising of PlayNation and Velex were sufficiently similar to weigh\\n\\nin favor of confusion. First, the products are highly similar. The test for similar\\n\\nproducts is “whether the products are the kind that the public attributes to a single\\n\\nsource, not whether or not the purchasing public can readily distinguish between\\n\\n\\n 10\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 11 of 19\\n\\n\\nthe products of the respective parties.” Frehling, 192 F.3d at 1338. Velex argues\\n\\nthat it sells only outdoor products, while PlayNation sells only indoor products.\\n\\nBut the question is not whether there is a distinguishing characteristic, but whether\\n\\nthe goods are so related that a consumer would believe that a single producer made\\n\\nboth. See E. Remy Martin & Co., S.A. v. Shaw-Ross Int’l Imports, Inc., 756 F.2d\\n\\n1525, 1530 (11th Cir. 1985) (holding that it was not unreasonable for consumers to\\n\\nconclude that a maker of wine could also produce brandy). Both PlayNation and\\n\\nVelex sold a core unit with separate attachable accessories for children, including\\n\\nswings, ropes, and rings. These are sufficiently similar to support the district\\n\\ncourt’s finding.\\n\\n Second, the retail outlets are similar. “This factor takes into consideration\\n\\nwhere, how, and to whom the parties’ products are sold.” Frehling, 192 F.3d at\\n\\n1339. But “[d]irect competition between the parties is not required for this factor\\n\\nto weigh in favor of likelihood of confusion.” Id. Both Playnation and Velex sold\\n\\ntheir products through substantially similar retail outlets, including big box stores,\\n\\ntheir own websites, and other online retailers like Amazon and Walmart. Velex\\n\\nargues that because PlayNation also sells its products through dealers, their retail\\n\\noutlets are dissimilar. But here again, exact parallels are not required, and one\\n\\ndistinct retail outlet does not amount to clear error.\\n\\n\\n\\n\\n 11\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 12 of 19\\n\\n\\n Third, PlayNation and Velex engaged in similar advertising. “This factor\\n\\nlooks to each party’s method of advertising.” Id. at 1339. “[T]he standard is\\n\\nwhether there is likely to be significant enough overlap in the readership of the\\n\\npublications in which the parties advertise that a possibility of confusion could\\n\\nresult.” Id. at 1340. PlayNation and Velex both advertised using their own\\n\\nwebsites, television, and the internet—including Google and Amazon keyword\\n\\nadvertising, Facebook, and YouTube.\\n\\n While there may be some evidence to support dissimilar products, retail\\n\\noutlets, and advertising, they are not enough to compel an alternative finding under\\n\\nclear error review.\\n\\n These factors are not exclusive. Courts do not have to consider every factor\\n\\nin every case. Swatch Watch, S.A. v. Taxor, Inc., 785 F.2d 956, 958 (11th Cir.\\n\\n1986). Courts may also consider other probative evidence that does not fit within\\n\\nthe factors. Id.\\n\\n E. New Factors\\n\\n Velex proposes two new factors the district court should have considered:\\n\\nfirst, that Velex had a valid federal trademark registration that covered the\\n\\ninfringing products, and second, that PlayNation failed to produce survey evidence\\n\\nsuggesting consumer confusion.\\n\\n\\n\\n\\n 12\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 13 of 19\\n\\n\\n To support adoption of its first proposed factor, Velex argues that it ought to\\n\\nhave the right to rely on decisions of the government—here, the Patent and\\n\\nTrademark Office (PTO). Velex relies on the Supreme Court’s decision in B&B\\n\\nHardware, Inc. v. Hargis Indus., Inc., 135 S. Ct. 1293 (2015). In B&B Hardware,\\n\\nthe Supreme Court held that the likelihood of confusion standard used by the PTO\\n\\nfor determining whether to register a new mark and the standard used by courts in\\n\\ntrademark infringement cases are “the same.” 135 S. Ct. at 1306–07. But the\\n\\nSupreme Court made that conclusion in determining whether issue preclusion\\n\\napplied. Id. The Court held that issue preclusion applied to a district court\\n\\ndeciding a Lanham Act trademark infringement claim when the Trademark Trial\\n\\nand Appeal Board (TTAB) had previously decided the parties’ marks were not\\n\\nconfusingly similar for purposes of registration. Id. at 1307. There is no such\\n\\nfinding by the PTO or TTAB in this case because PlayNation did not object to\\n\\nVelex’s registration or litigate the issue before the TTAB. Issue preclusion does\\n\\nnot bind PlayNation, because it was not a party to any prior proceeding. Cf.\\n\\nTampa Bay Water v. HDR Eng’g, Inc., 731 F.3d 1171, 1179 (11th Cir. 2013),\\n\\noverruled on other grounds by CSX Transp., Inc. v. Gen. Mills, Inc., 846 F.3d\\n\\n1333, 1340 (11th Cir. 2017).\\n\\n B&B Hardware does not suggest that, absent a prior administrative finding,\\n\\na district court deciding a trademark infringement action is bound—or even ought\\n\\n\\n 13\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 14 of 19\\n\\n\\nto be persuaded—by the PTO’s registration of the defendant’s mark. Id.\\n\\n(“[D]istrict courts can cancel registrations during infringement litigation, just as\\n\\nthey can adjudicate infringement in suits seeking judicial review of registration\\n\\ndecisions.”). To the contrary, the Lanham Act expressly gives district courts the\\n\\npower to cancel federal trademarks issued by the PTO when they violate the\\n\\nLanham Act. See 15 U.S.C. § 1119. Absent issue preclusion, it was not clearly\\n\\nerroneous for the district court not to consider the PTO’s decision to approve\\n\\nVelex’s trademark as a factor.\\n\\n It was similarly not clearly erroneous for the district court not to consider\\n\\nVelex’s second proposed factor: lack of survey evidence. Lack of survey evidence\\n\\ndoes not weigh against the plaintiff when determining likelihood of confusion. See\\n\\nFrehling, 192 F.3d at 1341 n.5 (“This Circuit . . . has moved away from relying on\\n\\nsurvey evidence” and “the failure to adduce such evidence is not damaging to [a\\n\\nplaintiff’s] case.”). We are not persuaded by Velex’s reliance on Hickson Corp. v.\\n\\nN. Crossarm Co., 357 F.3d 1256 (11th Cir. 2004). Hickson was a false advertising\\n\\ncase, not a trademark infringement case. Unlike in a trademark infringement\\n\\naction, a plaintiff attempting to establish a misleading advertisement under the\\n\\nLanham Act “must present evidence of deception in the form of consumer surveys,\\n\\nmarket research, expert testimony, or other evidence.” Hickson, 357 F.3d at 1261\\n\\n\\n\\n\\n 14\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 15 of 19\\n\\n\\n(internal quotation marks omitted). There is no similar requirement for trademark\\n\\ninfringement, and we decline to impose one here.\\n\\n The district court did not clearly err in holding that Velex infringed on\\n\\nPlayNation’s trademark.\\n\\n III. Remedies\\n\\n Velex argues that the district court erred in fashioning a remedy in this case\\n\\nby first, awarding PlayNation damages based on an accounting of Velex’s profits,\\n\\nand second, cancelling Velex’s trademark registration. We review a district court’s\\n\\ndecision to grant relief, including cancelling a party’s trademark registration, for\\n\\nabuse of discretion. See Planetary Motion, Inc. v. Techsplosion, Inc., 261 F.3d\\n\\n1188, 1203 (11th Cir. 2001).\\n\\n A. Damages\\n\\n The Lanham Act allows a successful plaintiff to recover the defendant’s\\n\\nprofits. 15 U.S.C. § 1117(a). “In assessing profits the plaintiff shall be required to\\n\\nprove defendant’s sales only; defendant must prove all elements of cost or\\n\\ndeduction claimed.” Id. “The Act confers upon the district court a wide scope of\\n\\ndiscretion to determine the proper relief due an injured party.” Burger King Corp.\\n\\nv. Mason, 855 F.2d 779, 781 (11th Cir. 1988) (per curiam). An accounting of a\\n\\ndefendant’s profits is appropriate where: (1) the defendant’s conduct was willful\\n\\nand deliberate, (2) the defendant was unjustly enriched, or (3) it is necessary to\\n\\n\\n 15\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 16 of 19\\n\\n\\ndeter future conduct. Howard Johnson Co., Inc. v. Khimani, 892 F.2d 1512, 1521\\n\\n(11th Cir. 1990). Conduct is willful if the infringer was “knowingly and\\n\\ndeliberately cashing in upon the good will of [the infringed].” Burger King, 855\\n\\nF.3d at 781.\\n\\n The district court concluded that Velex willfully infringed on PlayNation’s\\n\\ntrademark based solely on Velex’s continued sale of its Gorilla Gym products after\\n\\nit was served with PlayNation’s complaint. The district court reasoned that\\n\\nPlayNation’s complaint put Velex’s on notice that it was allegedly infringing on\\n\\nPlayNation’s trademark. But when it received PlayNation’s complaint, Velex had\\n\\na valid registered trademark on Gorilla Gym. PlayNation did not obtain a\\n\\npreliminary injunction, and at the time, no court had adjudicated whether Velex\\n\\nwas infringing on PlayNation’s trademark.\\n\\n Under the district court’s construction of willfulness, a valid trademark\\n\\nholder risks losing all of its profits if it does not immediately cease selling its\\n\\ntrademarked product upon receiving a complaint indicating it may be violating the\\n\\nlaw. The district court determined that at the time Velex obtained its trademark,\\n\\nVelex did not intend to infringe on PlayNation’s trademark. And from the time\\n\\nVelex obtained its trademark to the time the district court made its final\\n\\ndetermination, there was no further adjudication that Velex was infringing. This\\n\\ncontinued sale under the color of a valid federal trademark cannot alone establish\\n\\n\\n 16\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 17 of 19\\n\\n\\nwillfulness. See cf. Maltina Corp. v. Cawy Bottling Co., Inc., 613 F.2d 582, 587\\n\\n(5th Cir. 1980) (finding willfulness that justified an accounting of profits where the\\n\\ninfringer used the infringing mark after the patent office refused to register it based\\n\\non the confusing similarity of the plaintiff’s registered mark).\\n\\n There may have been other evidence of willfulness, but the district court did\\n\\nnot rely it in its decision. The district court also relied solely on the willfulness\\n\\ntheory to support its accounting of profits. The other two theories for supporting\\n\\nan accounting of profits, deterrence and unjust enrichment, do not depend “upon a\\n\\nhigher showing of culpability on the part of defendant, who is purposely using the\\n\\ntrademark.” Burger King, 855 F.2d at 781. Remand is appropriate so that the\\n\\ndistrict court may consider whether other evidence of willfulness exists and\\n\\nwhether those alternative theories support an accounting of profits.\\n\\n B. Cancelling Trademark Registration\\n\\n District courts have discretion to order the cancelation of a federal trademark\\n\\nregistration in whole or in part. 15 U.S.C. § 1119. Cancelling a trademark\\n\\nregistration is appropriate where the plaintiff shows (1) that it had standing to\\n\\npetition for cancellation because it was likely to be damaged by the infringer’s\\n\\ncontinued use of the infringing mark, and (2) that there were valid grounds for\\n\\ndiscontinuing registration. Coach House Rest., Inc. v. Coach & Six Rests., Inc.,\\n\\n934 F.2d 1551, 1557 (11th Cir. 1991). PlayNation’s federal registration of its mark\\n\\n\\n 17\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 18 of 19\\n\\n\\nsatisfies the first element. See id. at 1557–58. PlayNation must show only the\\n\\nsecond element—a valid ground for cancelling registration.\\n\\n If the “mark at issue has been on the federal Principal Register in registrant’s\\n\\nname for less than five years, the mark may be cancelled if petitioner can prove\\n\\nthat the registration should have been barred in the first instance under Lanham Act\\n\\n§ 2.” Id. at 1558. “In order to cancel a registration under Lanham Act Section\\n\\n2(d) in this case, petitioner must prove . . . that the registered mark is likely to\\n\\ncause confusion when used in connection with the services of registrant.” Id. at\\n\\n1559. Establishing trademark infringement thus satisfies the second cancellation\\n\\nrequirement.\\n\\n Having concluded that Velex infringed on PlayNation’s trademark, it was\\n\\nnot an abuse of discretion for the district court to cancel Velex’s trademark\\n\\nregistration.\\n\\n IV. Conclusion\\n\\n The district court did not clearly err in holding that Velex infringed on\\n\\nPlayNation’s trademark. The district court similarly did not err in canceling\\n\\nVelex’s trademark registration on that basis. But the district court did abuse its\\n\\ndiscretion in holding that PlayNation was entitled to an accounting of Velex’s\\n\\nprofits due to willful infringement based solely on Velex’s continued lawful use of\\n\\nits mark after Velex was served with the complaint in this action. As a result, we\\n\\n\\n 18\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 19 of 19\\n\\n\\nvacate the district court’s judgment on that issue, and remand for further\\n\\nproceedings consistent with this opinion.\\n\\n AFFIRMED IN PART, VACATED AND REMANDED IN PART.\\n\\n\\n\\n\\n 19\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4398793/\", \"author_raw\": \"WILSON, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILSON"},"judge2":{"kind":"string","value":"BRANCH"},"judge3":{"kind":"string","value":"ANDERSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4621540/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: PLAYNATION PLAY SYSTEMS, INC., D.B.A. Gorilla Playsets, Plaintiff-Appellee, v. VELEX CORPORATION, D.B.A. Gorilla Gym, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-21\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-15226 Date Filed: 05/21/2019 Page: 1 of 19\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-15226\n ________________________\n\n D.C. Docket No. 1:14-cv-01046-RWS\n\n\n\nPLAYNATION PLAY SYSTEMS, INC.,\nd.b.a. Gorilla Playsets,\n\n Plaintiff - Appellee,\n\nversus\n\nVELEX CORPORATION,\nd.b.a. Gorilla Gym,\n\n Defendant - Appellant.\n\n ________________________\n\n Appeal from the United States District Court\n for the Northern District of Georgia\n ________________________\n\n (May 21, 2019)\n\nBefore WILSON, BRANCH, and ANDERSON, Circuit Judges.\n\nWILSON, Circuit Judge:\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 2 of 19\n\n\n The parties to this appeal both chose a gorilla as the face of their respective\n\nbrands. Litigation ensued. PlayNation Play Systems, Inc. sued Velex Corporation\n\nfor trademark infringement. The district court conducted a bench trial and entered\n\njudgment for PlayNation. Velex now appeals, arguing that the district court erred\n\nin finding trademark infringement, awarding damages to PlayNation, and\n\ncancelling Velex’s trademark registration. After careful review and with the\n\nbenefit of oral argument, we affirm the district court’s decisions on Velex’s\n\nliability for trademark infringement and cancellation of Velex’s trademark. We\n\nvacate and remand, however, on the district court’s determination of damages\n\nbased on Velex’s willful infringement.\n\n I. Factual Background\n\n PlayNation has sold children’s outdoor playground equipment, including\n\nswing sets and attachable swings, ropes, and rings, under its “Gorilla Playsets”\n\nbrand since 2002. PlayNation owns three registered trademarks for Gorilla\n\nPlaysets, two registered in 2004 and another in 2014. 1 Velex sells “Gorilla Gym”\n\ndoorway pull-up bars and various attachable accessories for children, including\n\n\n\n1\n PlayNation’s mark:\n\n\n\n\n 2\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 3 of 19\n\n\nswings, ropes, and rings, under its “Gorilla Gym” brand. Velex successfully\n\nregistered a trademark for Gorilla Gym in 2014. 2 Both PlayNation and Velex’s\n\ntrademarks are registered in Class 28, the broad class of goods for games and other\n\nplaythings.\n\n II. Trademark Infringement\n\n Velex first argues that the district court erred by concluding that consumers\n\nwould likely be confused by Velex’s use of the Gorilla Gym mark. In an appeal\n\nfrom a bench trial, we review a district court’s conclusions of law de novo and its\n\nfactual findings for clear error. Tartell v. S. Fla. Sinus & Allergy Ctr., Inc., 790\n\nF.3d 1253, 1257 (11th Cir. 2015). A factual finding is clearly erroneous if, after\n\nviewing the totality of the evidence, the court is left with a definite and firm\n\nconviction that a mistake was made. Id.\n\n Under the Lanham Act, 15 U.S.C. § 1114(1), a defendant is liable for\n\ntrademark infringement if the plaintiff shows (1) that its mark has priority and (2)\n\nthat the defendant’s mark is likely to cause consumer confusion. Frehling Enter.,\n\nInc. v. Int’l Select Grp., Inc., 192 F.3d 1330, 1335 (11th Cir. 1999). Velex\n\n\n2\n Velex’s mark:\n\n\n\n\n 3\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 4 of 19\n\n\nstipulated to the priority of PlayNation’s mark. We thus need only consider\n\nwhether the district court clearly erred in finding that Velex’s mark was likely to\n\ncause consumer confusion. In making that determination, we weigh seven factors:\n\n(1) the strength of the plaintiff’s mark; (2) the similarity of the marks; (3) the\n\nsimilarity of the products the marks represent; (4) the similarity of the parties’\n\nretail outlets and customers; (5) the similarity of advertising media; (6) the\n\ndefendant’s intent; and (7) actual confusion. Lone Star Steakhouse & Saloon, Inc.\n\nv. Longhorn Steaks, Inc., 122 F.3d 1379, 1382 (11th Cir. 1997).\n\n We review for clear error both a district court’s ultimate decision on\n\nlikelihood of confusion and its findings on each factor. Frehling, 192 F.3d at\n\n1335. Of these factors, the strength of the mark and actual confusion are the most\n\nprobative. Id. The district court held that each factor except the defendant’s intent\n\nweighed in favor of confusion. Velex challenges the district court’s determination\n\non the other factors and argues that the district court should have adopted two new\n\nfactors.\n\n A. Strength of PlayNation’s Mark\n\n “Classifying the type of mark Plaintiff has determines whether it is strong or\n\nweak. The stronger the mark, the greater the scope of protection accorded it, the\n\nweaker the mark, the less trademark protection it receives. There are four\n\ncategories of marks: (1) generic, (2) descriptive, (3) suggestive, and (4) arbitrary.”\n\n\n 4\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 5 of 19\n\n\nFrehling, 192 F.3d at 1335 (internal citations omitted). Suggestive marks are\n\nstronger and accordingly receive greater protection. Id. “Suggestive marks subtly\n\nconnote something about the service so that a customer could use his or her\n\nimagination and determine the nature of the service.” Freedom Sav. Loan Ass’n v.\n\nWay, 757 F.2d 1176, 1182 n.5 (11th Cir. 1985). The district court determined that\n\nPlayNation’s Gorilla Playsets mark was “descriptive or suggestive.” The products\n\nPlayNation sells under the mark are, of course, not designed for or used by gorillas.\n\nAt a minimum, the connection between the mark and the product requires some\n\nimagination. See Caliber Auto. Liquidators, Inc. v. Premier Chrysler, Jeep,\n\nDodge, LLC, 605 F.3d 931, 938 (11th Cir. 2010) (“A suggestive mark refers to\n\nsome characteristic of the goods, but requires a leap of the imagination to get from\n\nthe mark to the product [e.g., Penguin Refrigerators].”) (quotation marks omitted).\n\n The district court also reasoned that other factors increased the strength of\n\nPlayNation’s mark. See Frehling, 192 F.3d at 1336. First, PlayNation has\n\nextensively used the mark in commerce since 2002. PlayNation engaged in\n\nsignificant nationwide advertising and promotion using its Gorilla Playsets mark.\n\nThe district court found that this widespread use indicated consumer recognition,\n\nwhich enhances the strength of a mark. See John H. Harland Co. v. Clarke\n\nChecks, Inc., 711 F.2d 966, 974 n.13 (11th Cir. 1983) (noting that a mark may, “by\n\nreason of subsequent use and promotion, acquire such distinctiveness that it can\n\n\n 5\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 6 of 19\n\n\nfunction as a significant indication of a particular producer as source of the goods\n\nwith which it is used”). 3\n\n Second, the parties agree that PlayNation’s mark has been registered with\n\nthe Patent and Trademark Office for at least five years and is thus incontestable.\n\nFrehling, 192 F.3d at 1336. An incontestable mark “is presumed to be at least\n\ndescriptive with secondary meaning, and therefore a relatively strong mark.”\n\nDieter v. B & H Indus. of Southwest Fla., Inc., 880 F.3d 322, 329 (11th Cir. 1989);\n\nsee also Frehling, 192 F.3d at 1336.\n\n Finally, the lack of extensive third-party use also strengthens PlayNation’s\n\nmark. Frehling, 192 F.3d at 1336. Velex argues that the mark is weak because\n\nroughly thirty other registered marks in Class 28 contain the word “gorilla.” But\n\nnone of those gorilla marks were used on play equipment. And similar marks used\n\nby third parties in unrelated businesses or markets do not diminish the strength of a\n\nmark in a particular market. See Safeway Stores, Inc. v. Safeway Disc. Drugs, Inc.,\n\n\n\n\n3\n We have held that “in isolation, evidence of promotion efforts is not sufficient to establish a\nmark’s commercial strength because it tells us precious little about the efficacy of those efforts in\ncreating marketplace recognition . . . .” Fla. Int’l Univ. Bd. of Trustees v. Fla. Nat’l Univ., Inc.,\n830 F.3d 1242, 1259 (11th Cir. 2016) (first emphasis added) (holding that “[t]here simply was\nnot sufficient evidence of commercial strength in the record to require the district court to ignore\nthe substantial third-party usage.”). But this “circumstantial evidence of advertising and\npromotion,” id. (quotations omitted), is not the only evidence of the strength of PlayNation’s\nmark. Accordingly, the district court did not err in finding PlayNation’s advertising and\npromotion expenditures contributed to the strength of its mark.\n\n\n 6\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 7 of 19\n\n\n675 F.2d 1160, 1167 (11th Cir. 1982) (finding that twenty marks containing one of\n\nthe same words as the plaintiff’s mark did “not significantly diminish the strength\n\nof the [plaintiff’s] mark” because the other marks were used by “businesses not\n\nclosely related” to the plaintiff’s business), abrogated on other grounds, Tobinick\n\nv. Novella, 884 F.3d 1110 (11th Cir. 2018); cf. Sovereign Military Hospitaller\n\nOrder of Saint John of Jerusalem of Rhodes & of Malta v. Fla. Priory of the\n\nKnights Hospitallers of the Sovereign Order of Saint John of Jerusalem, Knights of\n\nMalta, The Ecumenical Order, 809 F.3d 1171, 1186 (11th Cir. 2015) (“That other\n\norganizations use parts of the Sovereign Order’s word marks is not persuasive\n\nevidence of third-party use.”).\n\n The district court did not clearly err in determining that PlayNation’s Gorilla\n\nPlaysets mark was strong.\n\n B. Actual Confusion\n\n “It is undisputed that evidence of actual confusion is the best evidence of a\n\nlikelihood of confusion.” Frehling, 192 F.3d at 1340. The actual confusion\n\ninquiry turns on both the number of instances of confusion and the type of person\n\nconfused. Caliber Auto., 605 F.3d at 936. While numerous instances of actual\n\nconfusion add greater weight in favor of confusion, “the quantum of evidence\n\nneeded to show actual confusion is relatively small.” Id. at 937 (quotation marks\n\n\n\n\n 7\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 8 of 19\n\n\nomitted). Evidence that ultimate consumers were actually confused deserves\n\n“special attention.” Id. at 936–37.\n\n The district court determined that the actual confusion factor weighed in\n\nfavor of a likelihood of confusion. PlayNation produced two ultimate purchasers\n\nof PlayNation’s Gorilla Playsets swing sets who contacted Velex for customer\n\nservice. The consumers believed Velex manufactured both Gorilla Gym and\n\nGorilla Playsets products. Consumers also posted on retail websites selling Gorilla\n\nPlaysets swings and trapeze bars asking if those items work “with the Gorilla Gym\n\nindoors.” Velex argues this evidence was insufficient to establish actual confusion\n\nbecause the two consumers were careless and uninformed. 4 Velex points to\n\nportions of the consumers’ testimony in which they confuse the names of the two\n\ncompanies and misremember which name was on the packaging and website they\n\nlooked at before calling Velex. Velex asserts that a prudent consumer would have\n\n\n\n4\n Velex argues that the two consumers calling the wrong phone number amounts to “initial\ninterest confusion,” a doctrine we have not yet accepted as actionable under the Lanham Act.\nSee Suntree Tech., Inc. v. Ecosense Intern., Inc., 693 F.3d 1338, 1347 (11th Cir. 2012). But\nVelex misunderstands initial interest confusion, which occurs when an alleged infringer pulls a\nsort of bait and switch. The infringer uses another’s trademark (or an imitation of it) to capture\nconsumers’ initial interest, leading the consumers to the infringer’s website or call center, for\nexample. But then the consumers, aware they are not actually dealing with the trademark holder,\ndecide to purchase the infringer’s other good or service. See N. Am. Med. Corp. v. Axiom\nWorldwide, Inc., 522 F.3d 1211, 1221 (11th Cir. 2008). That situation did not occur here. These\nwere instances of source confusion. The consumers testified that they believed Gorilla Gym and\nGorilla Playsets were produced by the same company. See id. at 1222 n.9 (“‘Source confusion’\nexists because consumers are likely to be confused as to whether [the infringer’s] products have\nthe same source or sponsor as [the trademark holder’s] or whether there is some other affiliation\nor relationship between the two.”).\n 8\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 9 of 19\n\n\nexamined the packaging, read the product warranty, or researched the product on\n\nthe internet. Velex argues that had the consumers been so diligent, they would\n\nhave discovered that PlayNation—not Velex—manufactured the product they\n\npurchased.\n\n First, nothing in the actual confusion analysis requires the plaintiff to\n\nproduce the most careful consumer, who diligently researched and meticulously\n\nexamined the inner and outer packing to determine the provenance of the product\n\nshe purchased. It only requires that the consumers be reasonably prudent. The\n\ndistrict court found the consumers’ testimony probative. That the district court\n\nmade that determination even though the two witnesses confused the names of the\n\ntwo brands or failed to examine the packing before mistakenly calling Velex for\n\nhelp does not amount to clear error.\n\n Second, the number of instances and the type of consumer also support the\n\ndistrict court’s actual confusion finding. The customers PlayNation identified are\n\nultimate consumers of the product, to which we give special weight. And the\n\nnumber of instances need not be large to be probative of confusion. See Safeway\n\nStores, 675 F.2d at 1167 (finding one instance of actual customer confusion\n\nsufficient and holding that “[a]lthough the number of instances is small, the people\n\nconfused are precisely those whose confusion is most significant”).\n\n\n\n\n 9\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 10 of 19\n\n\n The district court thus did not clearly err in holding that the actual confusion\n\nfactor weighed in favor of a likelihood of confusion.\n\n C. Similarity of Marks\n\n To determine if two marks are similar, the court “considers the overall\n\nimpressions that the marks create, including the sound, appearance, and manner in\n\nwhich they are used.” Frehling, 192 F.3d at 1337. The dominant portion of both\n\nmarks is an image of a large gorilla and the word “gorilla.” The other words,\n\n“playset” in one and “gym” in the other, are very similar and do not contribute to\n\ndistinctiveness. See id. (holding that “a mark may be surrounded by additional\n\nwords of lesser importance and not have its strength diluted”). The colors and\n\nfonts are different, and the gorillas are in different areas and positions in the marks.\n\nBut even so, given the similarity in the type of gorilla, size of gorilla, and the\n\nalmost indistinguishable words used in the two marks, those differences do not\n\nmake the district court’s decision clearly erroneous.\n\n D. Similarity of Products, Retail Outlets, and Advertising\n\n The district court did not clearly err in finding that the products, retail\n\noutlets, and advertising of PlayNation and Velex were sufficiently similar to weigh\n\nin favor of confusion. First, the products are highly similar. The test for similar\n\nproducts is “whether the products are the kind that the public attributes to a single\n\nsource, not whether or not the purchasing public can readily distinguish between\n\n\n 10\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 11 of 19\n\n\nthe products of the respective parties.” Frehling, 192 F.3d at 1338. Velex argues\n\nthat it sells only outdoor products, while PlayNation sells only indoor products.\n\nBut the question is not whether there is a distinguishing characteristic, but whether\n\nthe goods are so related that a consumer would believe that a single producer made\n\nboth. See E. Remy Martin & Co., S.A. v. Shaw-Ross Int’l Imports, Inc., 756 F.2d\n\n1525, 1530 (11th Cir. 1985) (holding that it was not unreasonable for consumers to\n\nconclude that a maker of wine could also produce brandy). Both PlayNation and\n\nVelex sold a core unit with separate attachable accessories for children, including\n\nswings, ropes, and rings. These are sufficiently similar to support the district\n\ncourt’s finding.\n\n Second, the retail outlets are similar. “This factor takes into consideration\n\nwhere, how, and to whom the parties’ products are sold.” Frehling, 192 F.3d at\n\n1339. But “[d]irect competition between the parties is not required for this factor\n\nto weigh in favor of likelihood of confusion.” Id. Both Playnation and Velex sold\n\ntheir products through substantially similar retail outlets, including big box stores,\n\ntheir own websites, and other online retailers like Amazon and Walmart. Velex\n\nargues that because PlayNation also sells its products through dealers, their retail\n\noutlets are dissimilar. But here again, exact parallels are not required, and one\n\ndistinct retail outlet does not amount to clear error.\n\n\n\n\n 11\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 12 of 19\n\n\n Third, PlayNation and Velex engaged in similar advertising. “This factor\n\nlooks to each party’s method of advertising.” Id. at 1339. “[T]he standard is\n\nwhether there is likely to be significant enough overlap in the readership of the\n\npublications in which the parties advertise that a possibility of confusion could\n\nresult.” Id. at 1340. PlayNation and Velex both advertised using their own\n\nwebsites, television, and the internet—including Google and Amazon keyword\n\nadvertising, Facebook, and YouTube.\n\n While there may be some evidence to support dissimilar products, retail\n\noutlets, and advertising, they are not enough to compel an alternative finding under\n\nclear error review.\n\n These factors are not exclusive. Courts do not have to consider every factor\n\nin every case. Swatch Watch, S.A. v. Taxor, Inc., 785 F.2d 956, 958 (11th Cir.\n\n1986). Courts may also consider other probative evidence that does not fit within\n\nthe factors. Id.\n\n E. New Factors\n\n Velex proposes two new factors the district court should have considered:\n\nfirst, that Velex had a valid federal trademark registration that covered the\n\ninfringing products, and second, that PlayNation failed to produce survey evidence\n\nsuggesting consumer confusion.\n\n\n\n\n 12\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 13 of 19\n\n\n To support adoption of its first proposed factor, Velex argues that it ought to\n\nhave the right to rely on decisions of the government—here, the Patent and\n\nTrademark Office (PTO). Velex relies on the Supreme Court’s decision in B&B\n\nHardware, Inc. v. Hargis Indus., Inc., 135 S. Ct. 1293 (2015). In B&B Hardware,\n\nthe Supreme Court held that the likelihood of confusion standard used by the PTO\n\nfor determining whether to register a new mark and the standard used by courts in\n\ntrademark infringement cases are “the same.” 135 S. Ct. at 1306–07. But the\n\nSupreme Court made that conclusion in determining whether issue preclusion\n\napplied. Id. The Court held that issue preclusion applied to a district court\n\ndeciding a Lanham Act trademark infringement claim when the Trademark Trial\n\nand Appeal Board (TTAB) had previously decided the parties’ marks were not\n\nconfusingly similar for purposes of registration. Id. at 1307. There is no such\n\nfinding by the PTO or TTAB in this case because PlayNation did not object to\n\nVelex’s registration or litigate the issue before the TTAB. Issue preclusion does\n\nnot bind PlayNation, because it was not a party to any prior proceeding. Cf.\n\nTampa Bay Water v. HDR Eng’g, Inc., 731 F.3d 1171, 1179 (11th Cir. 2013),\n\noverruled on other grounds by CSX Transp., Inc. v. Gen. Mills, Inc., 846 F.3d\n\n1333, 1340 (11th Cir. 2017).\n\n B&B Hardware does not suggest that, absent a prior administrative finding,\n\na district court deciding a trademark infringement action is bound—or even ought\n\n\n 13\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 14 of 19\n\n\nto be persuaded—by the PTO’s registration of the defendant’s mark. Id.\n\n(“[D]istrict courts can cancel registrations during infringement litigation, just as\n\nthey can adjudicate infringement in suits seeking judicial review of registration\n\ndecisions.”). To the contrary, the Lanham Act expressly gives district courts the\n\npower to cancel federal trademarks issued by the PTO when they violate the\n\nLanham Act. See 15 U.S.C. § 1119. Absent issue preclusion, it was not clearly\n\nerroneous for the district court not to consider the PTO’s decision to approve\n\nVelex’s trademark as a factor.\n\n It was similarly not clearly erroneous for the district court not to consider\n\nVelex’s second proposed factor: lack of survey evidence. Lack of survey evidence\n\ndoes not weigh against the plaintiff when determining likelihood of confusion. See\n\nFrehling, 192 F.3d at 1341 n.5 (“This Circuit . . . has moved away from relying on\n\nsurvey evidence” and “the failure to adduce such evidence is not damaging to [a\n\nplaintiff’s] case.”). We are not persuaded by Velex’s reliance on Hickson Corp. v.\n\nN. Crossarm Co., 357 F.3d 1256 (11th Cir. 2004). Hickson was a false advertising\n\ncase, not a trademark infringement case. Unlike in a trademark infringement\n\naction, a plaintiff attempting to establish a misleading advertisement under the\n\nLanham Act “must present evidence of deception in the form of consumer surveys,\n\nmarket research, expert testimony, or other evidence.” Hickson, 357 F.3d at 1261\n\n\n\n\n 14\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 15 of 19\n\n\n(internal quotation marks omitted). There is no similar requirement for trademark\n\ninfringement, and we decline to impose one here.\n\n The district court did not clearly err in holding that Velex infringed on\n\nPlayNation’s trademark.\n\n III. Remedies\n\n Velex argues that the district court erred in fashioning a remedy in this case\n\nby first, awarding PlayNation damages based on an accounting of Velex’s profits,\n\nand second, cancelling Velex’s trademark registration. We review a district court’s\n\ndecision to grant relief, including cancelling a party’s trademark registration, for\n\nabuse of discretion. See Planetary Motion, Inc. v. Techsplosion, Inc., 261 F.3d\n\n1188, 1203 (11th Cir. 2001).\n\n A. Damages\n\n The Lanham Act allows a successful plaintiff to recover the defendant’s\n\nprofits. 15 U.S.C. § 1117(a). “In assessing profits the plaintiff shall be required to\n\nprove defendant’s sales only; defendant must prove all elements of cost or\n\ndeduction claimed.” Id. “The Act confers upon the district court a wide scope of\n\ndiscretion to determine the proper relief due an injured party.” Burger King Corp.\n\nv. Mason, 855 F.2d 779, 781 (11th Cir. 1988) (per curiam). An accounting of a\n\ndefendant’s profits is appropriate where: (1) the defendant’s conduct was willful\n\nand deliberate, (2) the defendant was unjustly enriched, or (3) it is necessary to\n\n\n 15\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 16 of 19\n\n\ndeter future conduct. Howard Johnson Co., Inc. v. Khimani, 892 F.2d 1512, 1521\n\n(11th Cir. 1990). Conduct is willful if the infringer was “knowingly and\n\ndeliberately cashing in upon the good will of [the infringed].” Burger King, 855\n\nF.3d at 781.\n\n The district court concluded that Velex willfully infringed on PlayNation’s\n\ntrademark based solely on Velex’s continued sale of its Gorilla Gym products after\n\nit was served with PlayNation’s complaint. The district court reasoned that\n\nPlayNation’s complaint put Velex’s on notice that it was allegedly infringing on\n\nPlayNation’s trademark. But when it received PlayNation’s complaint, Velex had\n\na valid registered trademark on Gorilla Gym. PlayNation did not obtain a\n\npreliminary injunction, and at the time, no court had adjudicated whether Velex\n\nwas infringing on PlayNation’s trademark.\n\n Under the district court’s construction of willfulness, a valid trademark\n\nholder risks losing all of its profits if it does not immediately cease selling its\n\ntrademarked product upon receiving a complaint indicating it may be violating the\n\nlaw. The district court determined that at the time Velex obtained its trademark,\n\nVelex did not intend to infringe on PlayNation’s trademark. And from the time\n\nVelex obtained its trademark to the time the district court made its final\n\ndetermination, there was no further adjudication that Velex was infringing. This\n\ncontinued sale under the color of a valid federal trademark cannot alone establish\n\n\n 16\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 17 of 19\n\n\nwillfulness. See cf. Maltina Corp. v. Cawy Bottling Co., Inc., 613 F.2d 582, 587\n\n(5th Cir. 1980) (finding willfulness that justified an accounting of profits where the\n\ninfringer used the infringing mark after the patent office refused to register it based\n\non the confusing similarity of the plaintiff’s registered mark).\n\n There may have been other evidence of willfulness, but the district court did\n\nnot rely it in its decision. The district court also relied solely on the willfulness\n\ntheory to support its accounting of profits. The other two theories for supporting\n\nan accounting of profits, deterrence and unjust enrichment, do not depend “upon a\n\nhigher showing of culpability on the part of defendant, who is purposely using the\n\ntrademark.” Burger King, 855 F.2d at 781. Remand is appropriate so that the\n\ndistrict court may consider whether other evidence of willfulness exists and\n\nwhether those alternative theories support an accounting of profits.\n\n B. Cancelling Trademark Registration\n\n District courts have discretion to order the cancelation of a federal trademark\n\nregistration in whole or in part. 15 U.S.C. § 1119. Cancelling a trademark\n\nregistration is appropriate where the plaintiff shows (1) that it had standing to\n\npetition for cancellation because it was likely to be damaged by the infringer’s\n\ncontinued use of the infringing mark, and (2) that there were valid grounds for\n\ndiscontinuing registration. Coach House Rest., Inc. v. Coach & Six Rests., Inc.,\n\n934 F.2d 1551, 1557 (11th Cir. 1991). PlayNation’s federal registration of its mark\n\n\n 17\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 18 of 19\n\n\nsatisfies the first element. See id. at 1557–58. PlayNation must show only the\n\nsecond element—a valid ground for cancelling registration.\n\n If the “mark at issue has been on the federal Principal Register in registrant’s\n\nname for less than five years, the mark may be cancelled if petitioner can prove\n\nthat the registration should have been barred in the first instance under Lanham Act\n\n§ 2.” Id. at 1558. “In order to cancel a registration under Lanham Act Section\n\n2(d) in this case, petitioner must prove . . . that the registered mark is likely to\n\ncause confusion when used in connection with the services of registrant.” Id. at\n\n1559. Establishing trademark infringement thus satisfies the second cancellation\n\nrequirement.\n\n Having concluded that Velex infringed on PlayNation’s trademark, it was\n\nnot an abuse of discretion for the district court to cancel Velex’s trademark\n\nregistration.\n\n IV. Conclusion\n\n The district court did not clearly err in holding that Velex infringed on\n\nPlayNation’s trademark. The district court similarly did not err in canceling\n\nVelex’s trademark registration on that basis. But the district court did abuse its\n\ndiscretion in holding that PlayNation was entitled to an accounting of Velex’s\n\nprofits due to willful infringement based solely on Velex’s continued lawful use of\n\nits mark after Velex was served with the complaint in this action. As a result, we\n\n\n 18\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 19 of 19\n\n\nvacate the district court’s judgment on that issue, and remand for further\n\nproceedings consistent with this opinion.\n\n AFFIRMED IN PART, VACATED AND REMANDED IN PART.\n\n\n\n\n 19\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: PLAYNATION PLAY SYSTEMS, INC., D.B.A. Gorilla Playsets, Plaintiff-Appellee, v. VELEX CORPORATION, D.B.A. Gorilla Gym, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-21\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-15226 Date Filed: 05/21/2019 Page: 1 of 19\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15226\\n ________________________\\n\\n D.C. Docket No. 1:14-cv-01046-RWS\\n\\n\\n\\nPLAYNATION PLAY SYSTEMS, INC.,\\nd.b.a. Gorilla Playsets,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nVELEX CORPORATION,\\nd.b.a. Gorilla Gym,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 21, 2019)\\n\\nBefore WILSON, BRANCH, and ANDERSON, Circuit Judges.\\n\\nWILSON, Circuit Judge:\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 2 of 19\\n\\n\\n The parties to this appeal both chose a gorilla as the face of their respective\\n\\nbrands. Litigation ensued. PlayNation Play Systems, Inc. sued Velex Corporation\\n\\nfor trademark infringement. The district court conducted a bench trial and entered\\n\\njudgment for PlayNation. Velex now appeals, arguing that the district court erred\\n\\nin finding trademark infringement, awarding damages to PlayNation, and\\n\\ncancelling Velex’s trademark registration. After careful review and with the\\n\\nbenefit of oral argument, we affirm the district court’s decisions on Velex’s\\n\\nliability for trademark infringement and cancellation of Velex’s trademark. We\\n\\nvacate and remand, however, on the district court’s determination of damages\\n\\nbased on Velex’s willful infringement.\\n\\n I. Factual Background\\n\\n PlayNation has sold children’s outdoor playground equipment, including\\n\\nswing sets and attachable swings, ropes, and rings, under its “Gorilla Playsets”\\n\\nbrand since 2002. PlayNation owns three registered trademarks for Gorilla\\n\\nPlaysets, two registered in 2004 and another in 2014. 1 Velex sells “Gorilla Gym”\\n\\ndoorway pull-up bars and various attachable accessories for children, including\\n\\n\\n\\n1\\n PlayNation’s mark:\\n\\n\\n\\n\\n 2\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 3 of 19\\n\\n\\nswings, ropes, and rings, under its “Gorilla Gym” brand. Velex successfully\\n\\nregistered a trademark for Gorilla Gym in 2014. 2 Both PlayNation and Velex’s\\n\\ntrademarks are registered in Class 28, the broad class of goods for games and other\\n\\nplaythings.\\n\\n II. Trademark Infringement\\n\\n Velex first argues that the district court erred by concluding that consumers\\n\\nwould likely be confused by Velex’s use of the Gorilla Gym mark. In an appeal\\n\\nfrom a bench trial, we review a district court’s conclusions of law de novo and its\\n\\nfactual findings for clear error. Tartell v. S. Fla. Sinus & Allergy Ctr., Inc., 790\\n\\nF.3d 1253, 1257 (11th Cir. 2015). A factual finding is clearly erroneous if, after\\n\\nviewing the totality of the evidence, the court is left with a definite and firm\\n\\nconviction that a mistake was made. Id.\\n\\n Under the Lanham Act, 15 U.S.C. § 1114(1), a defendant is liable for\\n\\ntrademark infringement if the plaintiff shows (1) that its mark has priority and (2)\\n\\nthat the defendant’s mark is likely to cause consumer confusion. Frehling Enter.,\\n\\nInc. v. Int’l Select Grp., Inc., 192 F.3d 1330, 1335 (11th Cir. 1999). Velex\\n\\n\\n2\\n Velex’s mark:\\n\\n\\n\\n\\n 3\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 4 of 19\\n\\n\\nstipulated to the priority of PlayNation’s mark. We thus need only consider\\n\\nwhether the district court clearly erred in finding that Velex’s mark was likely to\\n\\ncause consumer confusion. In making that determination, we weigh seven factors:\\n\\n(1) the strength of the plaintiff’s mark; (2) the similarity of the marks; (3) the\\n\\nsimilarity of the products the marks represent; (4) the similarity of the parties’\\n\\nretail outlets and customers; (5) the similarity of advertising media; (6) the\\n\\ndefendant’s intent; and (7) actual confusion. Lone Star Steakhouse & Saloon, Inc.\\n\\nv. Longhorn Steaks, Inc., 122 F.3d 1379, 1382 (11th Cir. 1997).\\n\\n We review for clear error both a district court’s ultimate decision on\\n\\nlikelihood of confusion and its findings on each factor. Frehling, 192 F.3d at\\n\\n1335. Of these factors, the strength of the mark and actual confusion are the most\\n\\nprobative. Id. The district court held that each factor except the defendant’s intent\\n\\nweighed in favor of confusion. Velex challenges the district court’s determination\\n\\non the other factors and argues that the district court should have adopted two new\\n\\nfactors.\\n\\n A. Strength of PlayNation’s Mark\\n\\n “Classifying the type of mark Plaintiff has determines whether it is strong or\\n\\nweak. The stronger the mark, the greater the scope of protection accorded it, the\\n\\nweaker the mark, the less trademark protection it receives. There are four\\n\\ncategories of marks: (1) generic, (2) descriptive, (3) suggestive, and (4) arbitrary.”\\n\\n\\n 4\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 5 of 19\\n\\n\\nFrehling, 192 F.3d at 1335 (internal citations omitted). Suggestive marks are\\n\\nstronger and accordingly receive greater protection. Id. “Suggestive marks subtly\\n\\nconnote something about the service so that a customer could use his or her\\n\\nimagination and determine the nature of the service.” Freedom Sav. Loan Ass’n v.\\n\\nWay, 757 F.2d 1176, 1182 n.5 (11th Cir. 1985). The district court determined that\\n\\nPlayNation’s Gorilla Playsets mark was “descriptive or suggestive.” The products\\n\\nPlayNation sells under the mark are, of course, not designed for or used by gorillas.\\n\\nAt a minimum, the connection between the mark and the product requires some\\n\\nimagination. See Caliber Auto. Liquidators, Inc. v. Premier Chrysler, Jeep,\\n\\nDodge, LLC, 605 F.3d 931, 938 (11th Cir. 2010) (“A suggestive mark refers to\\n\\nsome characteristic of the goods, but requires a leap of the imagination to get from\\n\\nthe mark to the product [e.g., Penguin Refrigerators].”) (quotation marks omitted).\\n\\n The district court also reasoned that other factors increased the strength of\\n\\nPlayNation’s mark. See Frehling, 192 F.3d at 1336. First, PlayNation has\\n\\nextensively used the mark in commerce since 2002. PlayNation engaged in\\n\\nsignificant nationwide advertising and promotion using its Gorilla Playsets mark.\\n\\nThe district court found that this widespread use indicated consumer recognition,\\n\\nwhich enhances the strength of a mark. See John H. Harland Co. v. Clarke\\n\\nChecks, Inc., 711 F.2d 966, 974 n.13 (11th Cir. 1983) (noting that a mark may, “by\\n\\nreason of subsequent use and promotion, acquire such distinctiveness that it can\\n\\n\\n 5\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 6 of 19\\n\\n\\nfunction as a significant indication of a particular producer as source of the goods\\n\\nwith which it is used”). 3\\n\\n Second, the parties agree that PlayNation’s mark has been registered with\\n\\nthe Patent and Trademark Office for at least five years and is thus incontestable.\\n\\nFrehling, 192 F.3d at 1336. An incontestable mark “is presumed to be at least\\n\\ndescriptive with secondary meaning, and therefore a relatively strong mark.”\\n\\nDieter v. B & H Indus. of Southwest Fla., Inc., 880 F.3d 322, 329 (11th Cir. 1989);\\n\\nsee also Frehling, 192 F.3d at 1336.\\n\\n Finally, the lack of extensive third-party use also strengthens PlayNation’s\\n\\nmark. Frehling, 192 F.3d at 1336. Velex argues that the mark is weak because\\n\\nroughly thirty other registered marks in Class 28 contain the word “gorilla.” But\\n\\nnone of those gorilla marks were used on play equipment. And similar marks used\\n\\nby third parties in unrelated businesses or markets do not diminish the strength of a\\n\\nmark in a particular market. See Safeway Stores, Inc. v. Safeway Disc. Drugs, Inc.,\\n\\n\\n\\n\\n3\\n We have held that “in isolation, evidence of promotion efforts is not sufficient to establish a\\nmark’s commercial strength because it tells us precious little about the efficacy of those efforts in\\ncreating marketplace recognition . . . .” Fla. Int’l Univ. Bd. of Trustees v. Fla. Nat’l Univ., Inc.,\\n830 F.3d 1242, 1259 (11th Cir. 2016) (first emphasis added) (holding that “[t]here simply was\\nnot sufficient evidence of commercial strength in the record to require the district court to ignore\\nthe substantial third-party usage.”). But this “circumstantial evidence of advertising and\\npromotion,” id. (quotations omitted), is not the only evidence of the strength of PlayNation’s\\nmark. Accordingly, the district court did not err in finding PlayNation’s advertising and\\npromotion expenditures contributed to the strength of its mark.\\n\\n\\n 6\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 7 of 19\\n\\n\\n675 F.2d 1160, 1167 (11th Cir. 1982) (finding that twenty marks containing one of\\n\\nthe same words as the plaintiff’s mark did “not significantly diminish the strength\\n\\nof the [plaintiff’s] mark” because the other marks were used by “businesses not\\n\\nclosely related” to the plaintiff’s business), abrogated on other grounds, Tobinick\\n\\nv. Novella, 884 F.3d 1110 (11th Cir. 2018); cf. Sovereign Military Hospitaller\\n\\nOrder of Saint John of Jerusalem of Rhodes & of Malta v. Fla. Priory of the\\n\\nKnights Hospitallers of the Sovereign Order of Saint John of Jerusalem, Knights of\\n\\nMalta, The Ecumenical Order, 809 F.3d 1171, 1186 (11th Cir. 2015) (“That other\\n\\norganizations use parts of the Sovereign Order’s word marks is not persuasive\\n\\nevidence of third-party use.”).\\n\\n The district court did not clearly err in determining that PlayNation’s Gorilla\\n\\nPlaysets mark was strong.\\n\\n B. Actual Confusion\\n\\n “It is undisputed that evidence of actual confusion is the best evidence of a\\n\\nlikelihood of confusion.” Frehling, 192 F.3d at 1340. The actual confusion\\n\\ninquiry turns on both the number of instances of confusion and the type of person\\n\\nconfused. Caliber Auto., 605 F.3d at 936. While numerous instances of actual\\n\\nconfusion add greater weight in favor of confusion, “the quantum of evidence\\n\\nneeded to show actual confusion is relatively small.” Id. at 937 (quotation marks\\n\\n\\n\\n\\n 7\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 8 of 19\\n\\n\\nomitted). Evidence that ultimate consumers were actually confused deserves\\n\\n“special attention.” Id. at 936–37.\\n\\n The district court determined that the actual confusion factor weighed in\\n\\nfavor of a likelihood of confusion. PlayNation produced two ultimate purchasers\\n\\nof PlayNation’s Gorilla Playsets swing sets who contacted Velex for customer\\n\\nservice. The consumers believed Velex manufactured both Gorilla Gym and\\n\\nGorilla Playsets products. Consumers also posted on retail websites selling Gorilla\\n\\nPlaysets swings and trapeze bars asking if those items work “with the Gorilla Gym\\n\\nindoors.” Velex argues this evidence was insufficient to establish actual confusion\\n\\nbecause the two consumers were careless and uninformed. 4 Velex points to\\n\\nportions of the consumers’ testimony in which they confuse the names of the two\\n\\ncompanies and misremember which name was on the packaging and website they\\n\\nlooked at before calling Velex. Velex asserts that a prudent consumer would have\\n\\n\\n\\n4\\n Velex argues that the two consumers calling the wrong phone number amounts to “initial\\ninterest confusion,” a doctrine we have not yet accepted as actionable under the Lanham Act.\\nSee Suntree Tech., Inc. v. Ecosense Intern., Inc., 693 F.3d 1338, 1347 (11th Cir. 2012). But\\nVelex misunderstands initial interest confusion, which occurs when an alleged infringer pulls a\\nsort of bait and switch. The infringer uses another’s trademark (or an imitation of it) to capture\\nconsumers’ initial interest, leading the consumers to the infringer’s website or call center, for\\nexample. But then the consumers, aware they are not actually dealing with the trademark holder,\\ndecide to purchase the infringer’s other good or service. See N. Am. Med. Corp. v. Axiom\\nWorldwide, Inc., 522 F.3d 1211, 1221 (11th Cir. 2008). That situation did not occur here. These\\nwere instances of source confusion. The consumers testified that they believed Gorilla Gym and\\nGorilla Playsets were produced by the same company. See id. at 1222 n.9 (“‘Source confusion’\\nexists because consumers are likely to be confused as to whether [the infringer’s] products have\\nthe same source or sponsor as [the trademark holder’s] or whether there is some other affiliation\\nor relationship between the two.”).\\n 8\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 9 of 19\\n\\n\\nexamined the packaging, read the product warranty, or researched the product on\\n\\nthe internet. Velex argues that had the consumers been so diligent, they would\\n\\nhave discovered that PlayNation—not Velex—manufactured the product they\\n\\npurchased.\\n\\n First, nothing in the actual confusion analysis requires the plaintiff to\\n\\nproduce the most careful consumer, who diligently researched and meticulously\\n\\nexamined the inner and outer packing to determine the provenance of the product\\n\\nshe purchased. It only requires that the consumers be reasonably prudent. The\\n\\ndistrict court found the consumers’ testimony probative. That the district court\\n\\nmade that determination even though the two witnesses confused the names of the\\n\\ntwo brands or failed to examine the packing before mistakenly calling Velex for\\n\\nhelp does not amount to clear error.\\n\\n Second, the number of instances and the type of consumer also support the\\n\\ndistrict court’s actual confusion finding. The customers PlayNation identified are\\n\\nultimate consumers of the product, to which we give special weight. And the\\n\\nnumber of instances need not be large to be probative of confusion. See Safeway\\n\\nStores, 675 F.2d at 1167 (finding one instance of actual customer confusion\\n\\nsufficient and holding that “[a]lthough the number of instances is small, the people\\n\\nconfused are precisely those whose confusion is most significant”).\\n\\n\\n\\n\\n 9\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 10 of 19\\n\\n\\n The district court thus did not clearly err in holding that the actual confusion\\n\\nfactor weighed in favor of a likelihood of confusion.\\n\\n C. Similarity of Marks\\n\\n To determine if two marks are similar, the court “considers the overall\\n\\nimpressions that the marks create, including the sound, appearance, and manner in\\n\\nwhich they are used.” Frehling, 192 F.3d at 1337. The dominant portion of both\\n\\nmarks is an image of a large gorilla and the word “gorilla.” The other words,\\n\\n“playset” in one and “gym” in the other, are very similar and do not contribute to\\n\\ndistinctiveness. See id. (holding that “a mark may be surrounded by additional\\n\\nwords of lesser importance and not have its strength diluted”). The colors and\\n\\nfonts are different, and the gorillas are in different areas and positions in the marks.\\n\\nBut even so, given the similarity in the type of gorilla, size of gorilla, and the\\n\\nalmost indistinguishable words used in the two marks, those differences do not\\n\\nmake the district court’s decision clearly erroneous.\\n\\n D. Similarity of Products, Retail Outlets, and Advertising\\n\\n The district court did not clearly err in finding that the products, retail\\n\\noutlets, and advertising of PlayNation and Velex were sufficiently similar to weigh\\n\\nin favor of confusion. First, the products are highly similar. The test for similar\\n\\nproducts is “whether the products are the kind that the public attributes to a single\\n\\nsource, not whether or not the purchasing public can readily distinguish between\\n\\n\\n 10\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 11 of 19\\n\\n\\nthe products of the respective parties.” Frehling, 192 F.3d at 1338. Velex argues\\n\\nthat it sells only outdoor products, while PlayNation sells only indoor products.\\n\\nBut the question is not whether there is a distinguishing characteristic, but whether\\n\\nthe goods are so related that a consumer would believe that a single producer made\\n\\nboth. See E. Remy Martin & Co., S.A. v. Shaw-Ross Int’l Imports, Inc., 756 F.2d\\n\\n1525, 1530 (11th Cir. 1985) (holding that it was not unreasonable for consumers to\\n\\nconclude that a maker of wine could also produce brandy). Both PlayNation and\\n\\nVelex sold a core unit with separate attachable accessories for children, including\\n\\nswings, ropes, and rings. These are sufficiently similar to support the district\\n\\ncourt’s finding.\\n\\n Second, the retail outlets are similar. “This factor takes into consideration\\n\\nwhere, how, and to whom the parties’ products are sold.” Frehling, 192 F.3d at\\n\\n1339. But “[d]irect competition between the parties is not required for this factor\\n\\nto weigh in favor of likelihood of confusion.” Id. Both Playnation and Velex sold\\n\\ntheir products through substantially similar retail outlets, including big box stores,\\n\\ntheir own websites, and other online retailers like Amazon and Walmart. Velex\\n\\nargues that because PlayNation also sells its products through dealers, their retail\\n\\noutlets are dissimilar. But here again, exact parallels are not required, and one\\n\\ndistinct retail outlet does not amount to clear error.\\n\\n\\n\\n\\n 11\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 12 of 19\\n\\n\\n Third, PlayNation and Velex engaged in similar advertising. “This factor\\n\\nlooks to each party’s method of advertising.” Id. at 1339. “[T]he standard is\\n\\nwhether there is likely to be significant enough overlap in the readership of the\\n\\npublications in which the parties advertise that a possibility of confusion could\\n\\nresult.” Id. at 1340. PlayNation and Velex both advertised using their own\\n\\nwebsites, television, and the internet—including Google and Amazon keyword\\n\\nadvertising, Facebook, and YouTube.\\n\\n While there may be some evidence to support dissimilar products, retail\\n\\noutlets, and advertising, they are not enough to compel an alternative finding under\\n\\nclear error review.\\n\\n These factors are not exclusive. Courts do not have to consider every factor\\n\\nin every case. Swatch Watch, S.A. v. Taxor, Inc., 785 F.2d 956, 958 (11th Cir.\\n\\n1986). Courts may also consider other probative evidence that does not fit within\\n\\nthe factors. Id.\\n\\n E. New Factors\\n\\n Velex proposes two new factors the district court should have considered:\\n\\nfirst, that Velex had a valid federal trademark registration that covered the\\n\\ninfringing products, and second, that PlayNation failed to produce survey evidence\\n\\nsuggesting consumer confusion.\\n\\n\\n\\n\\n 12\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 13 of 19\\n\\n\\n To support adoption of its first proposed factor, Velex argues that it ought to\\n\\nhave the right to rely on decisions of the government—here, the Patent and\\n\\nTrademark Office (PTO). Velex relies on the Supreme Court’s decision in B&B\\n\\nHardware, Inc. v. Hargis Indus., Inc., 135 S. Ct. 1293 (2015). In B&B Hardware,\\n\\nthe Supreme Court held that the likelihood of confusion standard used by the PTO\\n\\nfor determining whether to register a new mark and the standard used by courts in\\n\\ntrademark infringement cases are “the same.” 135 S. Ct. at 1306–07. But the\\n\\nSupreme Court made that conclusion in determining whether issue preclusion\\n\\napplied. Id. The Court held that issue preclusion applied to a district court\\n\\ndeciding a Lanham Act trademark infringement claim when the Trademark Trial\\n\\nand Appeal Board (TTAB) had previously decided the parties’ marks were not\\n\\nconfusingly similar for purposes of registration. Id. at 1307. There is no such\\n\\nfinding by the PTO or TTAB in this case because PlayNation did not object to\\n\\nVelex’s registration or litigate the issue before the TTAB. Issue preclusion does\\n\\nnot bind PlayNation, because it was not a party to any prior proceeding. Cf.\\n\\nTampa Bay Water v. HDR Eng’g, Inc., 731 F.3d 1171, 1179 (11th Cir. 2013),\\n\\noverruled on other grounds by CSX Transp., Inc. v. Gen. Mills, Inc., 846 F.3d\\n\\n1333, 1340 (11th Cir. 2017).\\n\\n B&B Hardware does not suggest that, absent a prior administrative finding,\\n\\na district court deciding a trademark infringement action is bound—or even ought\\n\\n\\n 13\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 14 of 19\\n\\n\\nto be persuaded—by the PTO’s registration of the defendant’s mark. Id.\\n\\n(“[D]istrict courts can cancel registrations during infringement litigation, just as\\n\\nthey can adjudicate infringement in suits seeking judicial review of registration\\n\\ndecisions.”). To the contrary, the Lanham Act expressly gives district courts the\\n\\npower to cancel federal trademarks issued by the PTO when they violate the\\n\\nLanham Act. See 15 U.S.C. § 1119. Absent issue preclusion, it was not clearly\\n\\nerroneous for the district court not to consider the PTO’s decision to approve\\n\\nVelex’s trademark as a factor.\\n\\n It was similarly not clearly erroneous for the district court not to consider\\n\\nVelex’s second proposed factor: lack of survey evidence. Lack of survey evidence\\n\\ndoes not weigh against the plaintiff when determining likelihood of confusion. See\\n\\nFrehling, 192 F.3d at 1341 n.5 (“This Circuit . . . has moved away from relying on\\n\\nsurvey evidence” and “the failure to adduce such evidence is not damaging to [a\\n\\nplaintiff’s] case.”). We are not persuaded by Velex’s reliance on Hickson Corp. v.\\n\\nN. Crossarm Co., 357 F.3d 1256 (11th Cir. 2004). Hickson was a false advertising\\n\\ncase, not a trademark infringement case. Unlike in a trademark infringement\\n\\naction, a plaintiff attempting to establish a misleading advertisement under the\\n\\nLanham Act “must present evidence of deception in the form of consumer surveys,\\n\\nmarket research, expert testimony, or other evidence.” Hickson, 357 F.3d at 1261\\n\\n\\n\\n\\n 14\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 15 of 19\\n\\n\\n(internal quotation marks omitted). There is no similar requirement for trademark\\n\\ninfringement, and we decline to impose one here.\\n\\n The district court did not clearly err in holding that Velex infringed on\\n\\nPlayNation’s trademark.\\n\\n III. Remedies\\n\\n Velex argues that the district court erred in fashioning a remedy in this case\\n\\nby first, awarding PlayNation damages based on an accounting of Velex’s profits,\\n\\nand second, cancelling Velex’s trademark registration. We review a district court’s\\n\\ndecision to grant relief, including cancelling a party’s trademark registration, for\\n\\nabuse of discretion. See Planetary Motion, Inc. v. Techsplosion, Inc., 261 F.3d\\n\\n1188, 1203 (11th Cir. 2001).\\n\\n A. Damages\\n\\n The Lanham Act allows a successful plaintiff to recover the defendant’s\\n\\nprofits. 15 U.S.C. § 1117(a). “In assessing profits the plaintiff shall be required to\\n\\nprove defendant’s sales only; defendant must prove all elements of cost or\\n\\ndeduction claimed.” Id. “The Act confers upon the district court a wide scope of\\n\\ndiscretion to determine the proper relief due an injured party.” Burger King Corp.\\n\\nv. Mason, 855 F.2d 779, 781 (11th Cir. 1988) (per curiam). An accounting of a\\n\\ndefendant’s profits is appropriate where: (1) the defendant’s conduct was willful\\n\\nand deliberate, (2) the defendant was unjustly enriched, or (3) it is necessary to\\n\\n\\n 15\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 16 of 19\\n\\n\\ndeter future conduct. Howard Johnson Co., Inc. v. Khimani, 892 F.2d 1512, 1521\\n\\n(11th Cir. 1990). Conduct is willful if the infringer was “knowingly and\\n\\ndeliberately cashing in upon the good will of [the infringed].” Burger King, 855\\n\\nF.3d at 781.\\n\\n The district court concluded that Velex willfully infringed on PlayNation’s\\n\\ntrademark based solely on Velex’s continued sale of its Gorilla Gym products after\\n\\nit was served with PlayNation’s complaint. The district court reasoned that\\n\\nPlayNation’s complaint put Velex’s on notice that it was allegedly infringing on\\n\\nPlayNation’s trademark. But when it received PlayNation’s complaint, Velex had\\n\\na valid registered trademark on Gorilla Gym. PlayNation did not obtain a\\n\\npreliminary injunction, and at the time, no court had adjudicated whether Velex\\n\\nwas infringing on PlayNation’s trademark.\\n\\n Under the district court’s construction of willfulness, a valid trademark\\n\\nholder risks losing all of its profits if it does not immediately cease selling its\\n\\ntrademarked product upon receiving a complaint indicating it may be violating the\\n\\nlaw. The district court determined that at the time Velex obtained its trademark,\\n\\nVelex did not intend to infringe on PlayNation’s trademark. And from the time\\n\\nVelex obtained its trademark to the time the district court made its final\\n\\ndetermination, there was no further adjudication that Velex was infringing. This\\n\\ncontinued sale under the color of a valid federal trademark cannot alone establish\\n\\n\\n 16\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 17 of 19\\n\\n\\nwillfulness. See cf. Maltina Corp. v. Cawy Bottling Co., Inc., 613 F.2d 582, 587\\n\\n(5th Cir. 1980) (finding willfulness that justified an accounting of profits where the\\n\\ninfringer used the infringing mark after the patent office refused to register it based\\n\\non the confusing similarity of the plaintiff’s registered mark).\\n\\n There may have been other evidence of willfulness, but the district court did\\n\\nnot rely it in its decision. The district court also relied solely on the willfulness\\n\\ntheory to support its accounting of profits. The other two theories for supporting\\n\\nan accounting of profits, deterrence and unjust enrichment, do not depend “upon a\\n\\nhigher showing of culpability on the part of defendant, who is purposely using the\\n\\ntrademark.” Burger King, 855 F.2d at 781. Remand is appropriate so that the\\n\\ndistrict court may consider whether other evidence of willfulness exists and\\n\\nwhether those alternative theories support an accounting of profits.\\n\\n B. Cancelling Trademark Registration\\n\\n District courts have discretion to order the cancelation of a federal trademark\\n\\nregistration in whole or in part. 15 U.S.C. § 1119. Cancelling a trademark\\n\\nregistration is appropriate where the plaintiff shows (1) that it had standing to\\n\\npetition for cancellation because it was likely to be damaged by the infringer’s\\n\\ncontinued use of the infringing mark, and (2) that there were valid grounds for\\n\\ndiscontinuing registration. Coach House Rest., Inc. v. Coach & Six Rests., Inc.,\\n\\n934 F.2d 1551, 1557 (11th Cir. 1991). PlayNation’s federal registration of its mark\\n\\n\\n 17\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 18 of 19\\n\\n\\nsatisfies the first element. See id. at 1557–58. PlayNation must show only the\\n\\nsecond element—a valid ground for cancelling registration.\\n\\n If the “mark at issue has been on the federal Principal Register in registrant’s\\n\\nname for less than five years, the mark may be cancelled if petitioner can prove\\n\\nthat the registration should have been barred in the first instance under Lanham Act\\n\\n§ 2.” Id. at 1558. “In order to cancel a registration under Lanham Act Section\\n\\n2(d) in this case, petitioner must prove . . . that the registered mark is likely to\\n\\ncause confusion when used in connection with the services of registrant.” Id. at\\n\\n1559. Establishing trademark infringement thus satisfies the second cancellation\\n\\nrequirement.\\n\\n Having concluded that Velex infringed on PlayNation’s trademark, it was\\n\\nnot an abuse of discretion for the district court to cancel Velex’s trademark\\n\\nregistration.\\n\\n IV. Conclusion\\n\\n The district court did not clearly err in holding that Velex infringed on\\n\\nPlayNation’s trademark. The district court similarly did not err in canceling\\n\\nVelex’s trademark registration on that basis. But the district court did abuse its\\n\\ndiscretion in holding that PlayNation was entitled to an accounting of Velex’s\\n\\nprofits due to willful infringement based solely on Velex’s continued lawful use of\\n\\nits mark after Velex was served with the complaint in this action. As a result, we\\n\\n\\n 18\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 19 of 19\\n\\n\\nvacate the district court’s judgment on that issue, and remand for further\\n\\nproceedings consistent with this opinion.\\n\\n AFFIRMED IN PART, VACATED AND REMANDED IN PART.\\n\\n\\n\\n\\n 19\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2285,"cells":{"id":{"kind":"number","value":4621978,"string":"4,621,978"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"PlayNation Play Systems, Inc. v. Velex Corporation"},"decision_date":{"kind":"string","value":"2019-05-21"},"docket_number":{"kind":"string","value":"17-15226"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before WILSON, BRANCH, and ANDERSON, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"WILSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-15226 Date Filed: 05/21/2019 Page: 1 of 19\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15226\\n ________________________\\n\\n D.C. Docket No. 1:14-cv-01046-RWS\\n\\n\\n\\nPLAYNATION PLAY SYSTEMS, INC.,\\nd.b.a. Gorilla Playsets,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nVELEX CORPORATION,\\nd.b.a. Gorilla Gym,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 21, 2019)\\n\\nBefore WILSON, BRANCH, and ANDERSON, Circuit Judges.\\n\\nWILSON, Circuit Judge:\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 2 of 19\\n\\n\\n The parties to this appeal both chose a gorilla as the face of their respective\\n\\nbrands. Litigation ensued. PlayNation Play Systems, Inc. sued Velex Corporation\\n\\nfor trademark infringement. The district court conducted a bench trial and entered\\n\\njudgment for PlayNation. Velex now appeals, arguing that the district court erred\\n\\nin finding trademark infringement, awarding damages to PlayNation, and\\n\\ncancelling Velex’s trademark registration. After careful review and with the\\n\\nbenefit of oral argument, we affirm the district court’s decisions on Velex’s\\n\\nliability for trademark infringement and cancellation of Velex’s trademark. We\\n\\nvacate and remand, however, on the district court’s determination of damages\\n\\nbased on Velex’s willful infringement.\\n\\n I. Factual Background\\n\\n PlayNation has sold children’s outdoor playground equipment, including\\n\\nswing sets and attachable swings, ropes, and rings, under its “Gorilla Playsets”\\n\\nbrand since 2002. PlayNation owns three registered trademarks for Gorilla\\n\\nPlaysets, two registered in 2004 and another in 2014. 1 Velex sells “Gorilla Gym”\\n\\ndoorway pull-up bars and various attachable accessories for children, including\\n\\n\\n\\n1\\n PlayNation’s mark:\\n\\n\\n\\n\\n 2\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 3 of 19\\n\\n\\nswings, ropes, and rings, under its “Gorilla Gym” brand. Velex successfully\\n\\nregistered a trademark for Gorilla Gym in 2014. 2 Both PlayNation and Velex’s\\n\\ntrademarks are registered in Class 28, the broad class of goods for games and other\\n\\nplaythings.\\n\\n II. Trademark Infringement\\n\\n Velex first argues that the district court erred by concluding that consumers\\n\\nwould likely be confused by Velex’s use of the Gorilla Gym mark. In an appeal\\n\\nfrom a bench trial, we review a district court’s conclusions of law de novo and its\\n\\nfactual findings for clear error. Tartell v. S. Fla. Sinus & Allergy Ctr., Inc., 790\\n\\nF.3d 1253, 1257 (11th Cir. 2015). A factual finding is clearly erroneous if, after\\n\\nviewing the totality of the evidence, the court is left with a definite and firm\\n\\nconviction that a mistake was made. Id.\\n\\n Under the Lanham Act, 15 U.S.C. § 1114(1), a defendant is liable for\\n\\ntrademark infringement if the plaintiff shows (1) that its mark has priority and (2)\\n\\nthat the defendant’s mark is likely to cause consumer confusion. Frehling Enter.,\\n\\nInc. v. Int’l Select Grp., Inc., 192 F.3d 1330, 1335 (11th Cir. 1999). Velex\\n\\n\\n2\\n Velex’s mark:\\n\\n\\n\\n\\n 3\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 4 of 19\\n\\n\\nstipulated to the priority of PlayNation’s mark. We thus need only consider\\n\\nwhether the district court clearly erred in finding that Velex’s mark was likely to\\n\\ncause consumer confusion. In making that determination, we weigh seven factors:\\n\\n(1) the strength of the plaintiff’s mark; (2) the similarity of the marks; (3) the\\n\\nsimilarity of the products the marks represent; (4) the similarity of the parties’\\n\\nretail outlets and customers; (5) the similarity of advertising media; (6) the\\n\\ndefendant’s intent; and (7) actual confusion. Lone Star Steakhouse & Saloon, Inc.\\n\\nv. Longhorn Steaks, Inc., 122 F.3d 1379, 1382 (11th Cir. 1997).\\n\\n We review for clear error both a district court’s ultimate decision on\\n\\nlikelihood of confusion and its findings on each factor. Frehling, 192 F.3d at\\n\\n1335. Of these factors, the strength of the mark and actual confusion are the most\\n\\nprobative. Id. The district court held that each factor except the defendant’s intent\\n\\nweighed in favor of confusion. Velex challenges the district court’s determination\\n\\non the other factors and argues that the district court should have adopted two new\\n\\nfactors.\\n\\n A. Strength of PlayNation’s Mark\\n\\n “Classifying the type of mark Plaintiff has determines whether it is strong or\\n\\nweak. The stronger the mark, the greater the scope of protection accorded it, the\\n\\nweaker the mark, the less trademark protection it receives. There are four\\n\\ncategories of marks: (1) generic, (2) descriptive, (3) suggestive, and (4) arbitrary.”\\n\\n\\n 4\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 5 of 19\\n\\n\\nFrehling, 192 F.3d at 1335 (internal citations omitted). Suggestive marks are\\n\\nstronger and accordingly receive greater protection. Id. “Suggestive marks subtly\\n\\nconnote something about the service so that a customer could use his or her\\n\\nimagination and determine the nature of the service.” Freedom Sav. Loan Ass’n v.\\n\\nWay, 757 F.2d 1176, 1182 n.5 (11th Cir. 1985). The district court determined that\\n\\nPlayNation’s Gorilla Playsets mark was “descriptive or suggestive.” The products\\n\\nPlayNation sells under the mark are, of course, not designed for or used by gorillas.\\n\\nAt a minimum, the connection between the mark and the product requires some\\n\\nimagination. See Caliber Auto. Liquidators, Inc. v. Premier Chrysler, Jeep,\\n\\nDodge, LLC, 605 F.3d 931, 938 (11th Cir. 2010) (“A suggestive mark refers to\\n\\nsome characteristic of the goods, but requires a leap of the imagination to get from\\n\\nthe mark to the product [e.g., Penguin Refrigerators].”) (quotation marks omitted).\\n\\n The district court also reasoned that other factors increased the strength of\\n\\nPlayNation’s mark. See Frehling, 192 F.3d at 1336. First, PlayNation has\\n\\nextensively used the mark in commerce since 2002. PlayNation engaged in\\n\\nsignificant nationwide advertising and promotion using its Gorilla Playsets mark.\\n\\nThe district court found that this widespread use indicated consumer recognition,\\n\\nwhich enhances the strength of a mark. See John H. Harland Co. v. Clarke\\n\\nChecks, Inc., 711 F.2d 966, 974 n.13 (11th Cir. 1983) (noting that a mark may, “by\\n\\nreason of subsequent use and promotion, acquire such distinctiveness that it can\\n\\n\\n 5\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 6 of 19\\n\\n\\nfunction as a significant indication of a particular producer as source of the goods\\n\\nwith which it is used”). 3\\n\\n Second, the parties agree that PlayNation’s mark has been registered with\\n\\nthe Patent and Trademark Office for at least five years and is thus incontestable.\\n\\nFrehling, 192 F.3d at 1336. An incontestable mark “is presumed to be at least\\n\\ndescriptive with secondary meaning, and therefore a relatively strong mark.”\\n\\nDieter v. B & H Indus. of Southwest Fla., Inc., 880 F.3d 322, 329 (11th Cir. 1989);\\n\\nsee also Frehling, 192 F.3d at 1336.\\n\\n Finally, the lack of extensive third-party use also strengthens PlayNation’s\\n\\nmark. Frehling, 192 F.3d at 1336. Velex argues that the mark is weak because\\n\\nroughly thirty other registered marks in Class 28 contain the word “gorilla.” But\\n\\nnone of those gorilla marks were used on play equipment. And similar marks used\\n\\nby third parties in unrelated businesses or markets do not diminish the strength of a\\n\\nmark in a particular market. See Safeway Stores, Inc. v. Safeway Disc. Drugs, Inc.,\\n\\n\\n\\n\\n3\\n We have held that “in isolation, evidence of promotion efforts is not sufficient to establish a\\nmark’s commercial strength because it tells us precious little about the efficacy of those efforts in\\ncreating marketplace recognition . . . .” Fla. Int’l Univ. Bd. of Trustees v. Fla. Nat’l Univ., Inc.,\\n830 F.3d 1242, 1259 (11th Cir. 2016) (first emphasis added) (holding that “[t]here simply was\\nnot sufficient evidence of commercial strength in the record to require the district court to ignore\\nthe substantial third-party usage.”). But this “circumstantial evidence of advertising and\\npromotion,” id. (quotations omitted), is not the only evidence of the strength of PlayNation’s\\nmark. Accordingly, the district court did not err in finding PlayNation’s advertising and\\npromotion expenditures contributed to the strength of its mark.\\n\\n\\n 6\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 7 of 19\\n\\n\\n675 F.2d 1160, 1167 (11th Cir. 1982) (finding that twenty marks containing one of\\n\\nthe same words as the plaintiff’s mark did “not significantly diminish the strength\\n\\nof the [plaintiff’s] mark” because the other marks were used by “businesses not\\n\\nclosely related” to the plaintiff’s business), abrogated on other grounds, Tobinick\\n\\nv. Novella, 884 F.3d 1110 (11th Cir. 2018); cf. Sovereign Military Hospitaller\\n\\nOrder of Saint John of Jerusalem of Rhodes & of Malta v. Fla. Priory of the\\n\\nKnights Hospitallers of the Sovereign Order of Saint John of Jerusalem, Knights of\\n\\nMalta, The Ecumenical Order, 809 F.3d 1171, 1186 (11th Cir. 2015) (“That other\\n\\norganizations use parts of the Sovereign Order’s word marks is not persuasive\\n\\nevidence of third-party use.”).\\n\\n The district court did not clearly err in determining that PlayNation’s Gorilla\\n\\nPlaysets mark was strong.\\n\\n B. Actual Confusion\\n\\n “It is undisputed that evidence of actual confusion is the best evidence of a\\n\\nlikelihood of confusion.” Frehling, 192 F.3d at 1340. The actual confusion\\n\\ninquiry turns on both the number of instances of confusion and the type of person\\n\\nconfused. Caliber Auto., 605 F.3d at 936. While numerous instances of actual\\n\\nconfusion add greater weight in favor of confusion, “the quantum of evidence\\n\\nneeded to show actual confusion is relatively small.” Id. at 937 (quotation marks\\n\\n\\n\\n\\n 7\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 8 of 19\\n\\n\\nomitted). Evidence that ultimate consumers were actually confused deserves\\n\\n“special attention.” Id. at 936–37.\\n\\n The district court determined that the actual confusion factor weighed in\\n\\nfavor of a likelihood of confusion. PlayNation produced two ultimate purchasers\\n\\nof PlayNation’s Gorilla Playsets swing sets who contacted Velex for customer\\n\\nservice. The consumers believed Velex manufactured both Gorilla Gym and\\n\\nGorilla Playsets products. Consumers also posted on retail websites selling Gorilla\\n\\nPlaysets swings and trapeze bars asking if those items work “with the Gorilla Gym\\n\\nindoors.” Velex argues this evidence was insufficient to establish actual confusion\\n\\nbecause the two consumers were careless and uninformed. 4 Velex points to\\n\\nportions of the consumers’ testimony in which they confuse the names of the two\\n\\ncompanies and misremember which name was on the packaging and website they\\n\\nlooked at before calling Velex. Velex asserts that a prudent consumer would have\\n\\n\\n\\n4\\n Velex argues that the two consumers calling the wrong phone number amounts to “initial\\ninterest confusion,” a doctrine we have not yet accepted as actionable under the Lanham Act.\\nSee Suntree Tech., Inc. v. Ecosense Intern., Inc., 693 F.3d 1338, 1347 (11th Cir. 2012). But\\nVelex misunderstands initial interest confusion, which occurs when an alleged infringer pulls a\\nsort of bait and switch. The infringer uses another’s trademark (or an imitation of it) to capture\\nconsumers’ initial interest, leading the consumers to the infringer’s website or call center, for\\nexample. But then the consumers, aware they are not actually dealing with the trademark holder,\\ndecide to purchase the infringer’s other good or service. See N. Am. Med. Corp. v. Axiom\\nWorldwide, Inc., 522 F.3d 1211, 1221 (11th Cir. 2008). That situation did not occur here. These\\nwere instances of source confusion. The consumers testified that they believed Gorilla Gym and\\nGorilla Playsets were produced by the same company. See id. at 1222 n.9 (“‘Source confusion’\\nexists because consumers are likely to be confused as to whether [the infringer’s] products have\\nthe same source or sponsor as [the trademark holder’s] or whether there is some other affiliation\\nor relationship between the two.”).\\n 8\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 9 of 19\\n\\n\\nexamined the packaging, read the product warranty, or researched the product on\\n\\nthe internet. Velex argues that had the consumers been so diligent, they would\\n\\nhave discovered that PlayNation—not Velex—manufactured the product they\\n\\npurchased.\\n\\n First, nothing in the actual confusion analysis requires the plaintiff to\\n\\nproduce the most careful consumer, who diligently researched and meticulously\\n\\nexamined the inner and outer packing to determine the provenance of the product\\n\\nshe purchased. It only requires that the consumers be reasonably prudent. The\\n\\ndistrict court found the consumers’ testimony probative. That the district court\\n\\nmade that determination even though the two witnesses confused the names of the\\n\\ntwo brands or failed to examine the packing before mistakenly calling Velex for\\n\\nhelp does not amount to clear error.\\n\\n Second, the number of instances and the type of consumer also support the\\n\\ndistrict court’s actual confusion finding. The customers PlayNation identified are\\n\\nultimate consumers of the product, to which we give special weight. And the\\n\\nnumber of instances need not be large to be probative of confusion. See Safeway\\n\\nStores, 675 F.2d at 1167 (finding one instance of actual customer confusion\\n\\nsufficient and holding that “[a]lthough the number of instances is small, the people\\n\\nconfused are precisely those whose confusion is most significant”).\\n\\n\\n\\n\\n 9\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 10 of 19\\n\\n\\n The district court thus did not clearly err in holding that the actual confusion\\n\\nfactor weighed in favor of a likelihood of confusion.\\n\\n C. Similarity of Marks\\n\\n To determine if two marks are similar, the court “considers the overall\\n\\nimpressions that the marks create, including the sound, appearance, and manner in\\n\\nwhich they are used.” Frehling, 192 F.3d at 1337. The dominant portion of both\\n\\nmarks is an image of a large gorilla and the word “gorilla.” The other words,\\n\\n“playset” in one and “gym” in the other, are very similar and do not contribute to\\n\\ndistinctiveness. See id. (holding that “a mark may be surrounded by additional\\n\\nwords of lesser importance and not have its strength diluted”). The colors and\\n\\nfonts are different, and the gorillas are in different areas and positions in the marks.\\n\\nBut even so, given the similarity in the type of gorilla, size of gorilla, and the\\n\\nalmost indistinguishable words used in the two marks, those differences do not\\n\\nmake the district court’s decision clearly erroneous.\\n\\n D. Similarity of Products, Retail Outlets, and Advertising\\n\\n The district court did not clearly err in finding that the products, retail\\n\\noutlets, and advertising of PlayNation and Velex were sufficiently similar to weigh\\n\\nin favor of confusion. First, the products are highly similar. The test for similar\\n\\nproducts is “whether the products are the kind that the public attributes to a single\\n\\nsource, not whether or not the purchasing public can readily distinguish between\\n\\n\\n 10\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 11 of 19\\n\\n\\nthe products of the respective parties.” Frehling, 192 F.3d at 1338. Velex argues\\n\\nthat it sells only indoor products, while PlayNation sells only outdoor products.\\n\\nBut the question is not whether there is a distinguishing characteristic, but whether\\n\\nthe goods are so related that a consumer would believe that a single producer made\\n\\nboth. See E. Remy Martin & Co., S.A. v. Shaw-Ross Int’l Imports, Inc., 756 F.2d\\n\\n1525, 1530 (11th Cir. 1985) (holding that it was not unreasonable for consumers to\\n\\nconclude that a maker of wine could also produce brandy). Both PlayNation and\\n\\nVelex sold a core unit with separate attachable accessories for children, including\\n\\nswings, ropes, and rings. These are sufficiently similar to support the district\\n\\ncourt’s finding.\\n\\n Second, the retail outlets are similar. “This factor takes into consideration\\n\\nwhere, how, and to whom the parties’ products are sold.” Frehling, 192 F.3d at\\n\\n1339. But “[d]irect competition between the parties is not required for this factor\\n\\nto weigh in favor of likelihood of confusion.” Id. Both Playnation and Velex sold\\n\\ntheir products through substantially similar retail outlets, including big box stores,\\n\\ntheir own websites, and other online retailers like Amazon and Walmart. Velex\\n\\nargues that because PlayNation also sells its products through dealers, their retail\\n\\noutlets are dissimilar. But here again, exact parallels are not required, and one\\n\\ndistinct retail outlet does not amount to clear error.\\n\\n\\n\\n\\n 11\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 12 of 19\\n\\n\\n Third, PlayNation and Velex engaged in similar advertising. “This factor\\n\\nlooks to each party’s method of advertising.” Id. at 1339. “[T]he standard is\\n\\nwhether there is likely to be significant enough overlap in the readership of the\\n\\npublications in which the parties advertise that a possibility of confusion could\\n\\nresult.” Id. at 1340. PlayNation and Velex both advertised using their own\\n\\nwebsites, television, and the internet—including Google and Amazon keyword\\n\\nadvertising, Facebook, and YouTube.\\n\\n While there may be some evidence to support dissimilar products, retail\\n\\noutlets, and advertising, they are not enough to compel an alternative finding under\\n\\nclear error review.\\n\\n These factors are not exclusive. Courts do not have to consider every factor\\n\\nin every case. Swatch Watch, S.A. v. Taxor, Inc., 785 F.2d 956, 958 (11th Cir.\\n\\n1986). Courts may also consider other probative evidence that does not fit within\\n\\nthe factors. Id.\\n\\n E. New Factors\\n\\n Velex proposes two new factors the district court should have considered:\\n\\nfirst, that Velex had a valid federal trademark registration that covered the\\n\\ninfringing products, and second, that PlayNation failed to produce survey evidence\\n\\nsuggesting consumer confusion.\\n\\n\\n\\n\\n 12\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 13 of 19\\n\\n\\n To support adoption of its first proposed factor, Velex argues that it ought to\\n\\nhave the right to rely on decisions of the government—here, the Patent and\\n\\nTrademark Office (PTO). Velex relies on the Supreme Court’s decision in B&B\\n\\nHardware, Inc. v. Hargis Indus., Inc., 135 S. Ct. 1293 (2015). In B&B Hardware,\\n\\nthe Supreme Court held that the likelihood of confusion standard used by the PTO\\n\\nfor determining whether to register a new mark and the standard used by courts in\\n\\ntrademark infringement cases are “the same.” 135 S. Ct. at 1306–07. But the\\n\\nSupreme Court made that conclusion in determining whether issue preclusion\\n\\napplied. Id. The Court held that issue preclusion applied to a district court\\n\\ndeciding a Lanham Act trademark infringement claim when the Trademark Trial\\n\\nand Appeal Board (TTAB) had previously decided the parties’ marks were not\\n\\nconfusingly similar for purposes of registration. Id. at 1307. There is no such\\n\\nfinding by the PTO or TTAB in this case because PlayNation did not object to\\n\\nVelex’s registration or litigate the issue before the TTAB. Issue preclusion does\\n\\nnot bind PlayNation, because it was not a party to any prior proceeding. Cf.\\n\\nTampa Bay Water v. HDR Eng’g, Inc., 731 F.3d 1171, 1179 (11th Cir. 2013),\\n\\noverruled on other grounds by CSX Transp., Inc. v. Gen. Mills, Inc., 846 F.3d\\n\\n1333, 1340 (11th Cir. 2017).\\n\\n B&B Hardware does not suggest that, absent a prior administrative finding,\\n\\na district court deciding a trademark infringement action is bound—or even ought\\n\\n\\n 13\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 14 of 19\\n\\n\\nto be persuaded—by the PTO’s registration of the defendant’s mark. Id.\\n\\n(“[D]istrict courts can cancel registrations during infringement litigation, just as\\n\\nthey can adjudicate infringement in suits seeking judicial review of registration\\n\\ndecisions.”). To the contrary, the Lanham Act expressly gives district courts the\\n\\npower to cancel federal trademarks issued by the PTO when they violate the\\n\\nLanham Act. See 15 U.S.C. § 1119. Absent issue preclusion, it was not clearly\\n\\nerroneous for the district court not to consider the PTO’s decision to approve\\n\\nVelex’s trademark as a factor.\\n\\n It was similarly not clearly erroneous for the district court not to consider\\n\\nVelex’s second proposed factor: lack of survey evidence. Lack of survey evidence\\n\\ndoes not weigh against the plaintiff when determining likelihood of confusion. See\\n\\nFrehling, 192 F.3d at 1341 n.5 (“This Circuit . . . has moved away from relying on\\n\\nsurvey evidence” and “the failure to adduce such evidence is not damaging to [a\\n\\nplaintiff’s] case.”). We are not persuaded by Velex’s reliance on Hickson Corp. v.\\n\\nN. Crossarm Co., 357 F.3d 1256 (11th Cir. 2004). Hickson was a false advertising\\n\\ncase, not a trademark infringement case. Unlike in a trademark infringement\\n\\naction, a plaintiff attempting to establish a misleading advertisement under the\\n\\nLanham Act “must present evidence of deception in the form of consumer surveys,\\n\\nmarket research, expert testimony, or other evidence.” Hickson, 357 F.3d at 1261\\n\\n\\n\\n\\n 14\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 15 of 19\\n\\n\\n(internal quotation marks omitted). There is no similar requirement for trademark\\n\\ninfringement, and we decline to impose one here.\\n\\n The district court did not clearly err in holding that Velex infringed on\\n\\nPlayNation’s trademark.\\n\\n III. Remedies\\n\\n Velex argues that the district court erred in fashioning a remedy in this case\\n\\nby first, awarding PlayNation damages based on an accounting of Velex’s profits,\\n\\nand second, cancelling Velex’s trademark registration. We review a district court’s\\n\\ndecision to grant relief, including cancelling a party’s trademark registration, for\\n\\nabuse of discretion. See Planetary Motion, Inc. v. Techsplosion, Inc., 261 F.3d\\n\\n1188, 1203 (11th Cir. 2001).\\n\\n A. Damages\\n\\n The Lanham Act allows a successful plaintiff to recover the defendant’s\\n\\nprofits. 15 U.S.C. § 1117(a). “In assessing profits the plaintiff shall be required to\\n\\nprove defendant’s sales only; defendant must prove all elements of cost or\\n\\ndeduction claimed.” Id. “The Act confers upon the district court a wide scope of\\n\\ndiscretion to determine the proper relief due an injured party.” Burger King Corp.\\n\\nv. Mason, 855 F.2d 779, 781 (11th Cir. 1988) (per curiam). An accounting of a\\n\\ndefendant’s profits is appropriate where: (1) the defendant’s conduct was willful\\n\\nand deliberate, (2) the defendant was unjustly enriched, or (3) it is necessary to\\n\\n\\n 15\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 16 of 19\\n\\n\\ndeter future conduct. Howard Johnson Co., Inc. v. Khimani, 892 F.2d 1512, 1521\\n\\n(11th Cir. 1990). Conduct is willful if the infringer was “knowingly and\\n\\ndeliberately cashing in upon the good will of [the infringed].” Burger King, 855\\n\\nF.3d at 781.\\n\\n The district court concluded that Velex willfully infringed on PlayNation’s\\n\\ntrademark based solely on Velex’s continued sale of its Gorilla Gym products after\\n\\nit was served with PlayNation’s complaint. The district court reasoned that\\n\\nPlayNation’s complaint put Velex’s on notice that it was allegedly infringing on\\n\\nPlayNation’s trademark. But when it received PlayNation’s complaint, Velex had\\n\\na valid registered trademark on Gorilla Gym. PlayNation did not obtain a\\n\\npreliminary injunction, and at the time, no court had adjudicated whether Velex\\n\\nwas infringing on PlayNation’s trademark.\\n\\n Under the district court’s construction of willfulness, a valid trademark\\n\\nholder risks losing all of its profits if it does not immediately cease selling its\\n\\ntrademarked product upon receiving a complaint indicating it may be violating the\\n\\nlaw. The district court determined that at the time Velex obtained its trademark,\\n\\nVelex did not intend to infringe on PlayNation’s trademark. And from the time\\n\\nVelex obtained its trademark to the time the district court made its final\\n\\ndetermination, there was no further adjudication that Velex was infringing. This\\n\\ncontinued sale under the color of a valid federal trademark cannot alone establish\\n\\n\\n 16\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 17 of 19\\n\\n\\nwillfulness. See cf. Maltina Corp. v. Cawy Bottling Co., Inc., 613 F.2d 582, 587\\n\\n(5th Cir. 1980) (finding willfulness that justified an accounting of profits where the\\n\\ninfringer used the infringing mark after the patent office refused to register it based\\n\\non the confusing similarity of the plaintiff’s registered mark).\\n\\n There may have been other evidence of willfulness, but the district court did\\n\\nnot rely on it in its decision. The district court also relied solely on the willfulness\\n\\ntheory to support its accounting of profits. The other two theories for supporting\\n\\nan accounting of profits, deterrence and unjust enrichment, do not depend “upon a\\n\\nhigher showing of culpability on the part of defendant, who is purposely using the\\n\\ntrademark.” Burger King, 855 F.2d at 781. Remand is appropriate so that the\\n\\ndistrict court may consider whether other evidence of willfulness exists and\\n\\nwhether those alternative theories support an accounting of profits.\\n\\n B. Cancelling Trademark Registration\\n\\n District courts have discretion to order the cancelation of a federal trademark\\n\\nregistration in whole or in part. 15 U.S.C. § 1119. Cancelling a trademark\\n\\nregistration is appropriate where the plaintiff shows (1) that it had standing to\\n\\npetition for cancellation because it was likely to be damaged by the infringer’s\\n\\ncontinued use of the infringing mark, and (2) that there were valid grounds for\\n\\ndiscontinuing registration. Coach House Rest., Inc. v. Coach & Six Rests., Inc.,\\n\\n934 F.2d 1551, 1557 (11th Cir. 1991). PlayNation’s federal registration of its mark\\n\\n\\n 17\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 18 of 19\\n\\n\\nsatisfies the first element. See id. at 1557–58. PlayNation must show only the\\n\\nsecond element—a valid ground for cancelling registration.\\n\\n If the “mark at issue has been on the federal Principal Register in registrant’s\\n\\nname for less than five years, the mark may be cancelled if petitioner can prove\\n\\nthat the registration should have been barred in the first instance under Lanham Act\\n\\n§ 2.” Id. at 1558. “In order to cancel a registration under Lanham Act Section\\n\\n2(d) in this case, petitioner must prove . . . that the registered mark is likely to\\n\\ncause confusion when used in connection with the services of registrant.” Id. at\\n\\n1559. Establishing trademark infringement thus satisfies the second cancellation\\n\\nrequirement.\\n\\n Having concluded that Velex infringed on PlayNation’s trademark, it was\\n\\nnot an abuse of discretion for the district court to cancel Velex’s trademark\\n\\nregistration.\\n\\n IV. Conclusion\\n\\n The district court did not clearly err in holding that Velex infringed on\\n\\nPlayNation’s trademark. The district court similarly did not err in canceling\\n\\nVelex’s trademark registration on that basis. But the district court did abuse its\\n\\ndiscretion in holding that PlayNation was entitled to an accounting of Velex’s\\n\\nprofits due to willful infringement based solely on Velex’s continued lawful use of\\n\\nits mark after Velex was served with the complaint in this action. As a result, we\\n\\n\\n 18\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 19 of 19\\n\\n\\nvacate the district court’s judgment on that issue, and remand for further\\n\\nproceedings consistent with this opinion.\\n\\n AFFIRMED IN PART, VACATED AND REMANDED IN PART.\\n\\n\\n\\n\\n 19\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4399231/\", \"author_raw\": \"WILSON, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILSON"},"judge2":{"kind":"string","value":"BRANCH"},"judge3":{"kind":"string","value":"ANDERSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"WILSON\": \", Circuit\", \"BRANCH\": \", Circuit\", \"ANDERSON\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4621978/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: PlayNation Play Systems, Inc. v. Velex Corporation\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-21\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-15226 Date Filed: 05/21/2019 Page: 1 of 19\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-15226\n ________________________\n\n D.C. Docket No. 1:14-cv-01046-RWS\n\n\n\nPLAYNATION PLAY SYSTEMS, INC.,\nd.b.a. Gorilla Playsets,\n\n Plaintiff - Appellee,\n\nversus\n\nVELEX CORPORATION,\nd.b.a. Gorilla Gym,\n\n Defendant - Appellant.\n\n ________________________\n\n Appeal from the United States District Court\n for the Northern District of Georgia\n ________________________\n\n (May 21, 2019)\n\nBefore WILSON, BRANCH, and ANDERSON, Circuit Judges.\n\nWILSON, Circuit Judge:\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 2 of 19\n\n\n The parties to this appeal both chose a gorilla as the face of their respective\n\nbrands. Litigation ensued. PlayNation Play Systems, Inc. sued Velex Corporation\n\nfor trademark infringement. The district court conducted a bench trial and entered\n\njudgment for PlayNation. Velex now appeals, arguing that the district court erred\n\nin finding trademark infringement, awarding damages to PlayNation, and\n\ncancelling Velex’s trademark registration. After careful review and with the\n\nbenefit of oral argument, we affirm the district court’s decisions on Velex’s\n\nliability for trademark infringement and cancellation of Velex’s trademark. We\n\nvacate and remand, however, on the district court’s determination of damages\n\nbased on Velex’s willful infringement.\n\n I. Factual Background\n\n PlayNation has sold children’s outdoor playground equipment, including\n\nswing sets and attachable swings, ropes, and rings, under its “Gorilla Playsets”\n\nbrand since 2002. PlayNation owns three registered trademarks for Gorilla\n\nPlaysets, two registered in 2004 and another in 2014. 1 Velex sells “Gorilla Gym”\n\ndoorway pull-up bars and various attachable accessories for children, including\n\n\n\n1\n PlayNation’s mark:\n\n\n\n\n 2\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 3 of 19\n\n\nswings, ropes, and rings, under its “Gorilla Gym” brand. Velex successfully\n\nregistered a trademark for Gorilla Gym in 2014. 2 Both PlayNation and Velex’s\n\ntrademarks are registered in Class 28, the broad class of goods for games and other\n\nplaythings.\n\n II. Trademark Infringement\n\n Velex first argues that the district court erred by concluding that consumers\n\nwould likely be confused by Velex’s use of the Gorilla Gym mark. In an appeal\n\nfrom a bench trial, we review a district court’s conclusions of law de novo and its\n\nfactual findings for clear error. Tartell v. S. Fla. Sinus & Allergy Ctr., Inc., 790\n\nF.3d 1253, 1257 (11th Cir. 2015). A factual finding is clearly erroneous if, after\n\nviewing the totality of the evidence, the court is left with a definite and firm\n\nconviction that a mistake was made. Id.\n\n Under the Lanham Act, 15 U.S.C. § 1114(1), a defendant is liable for\n\ntrademark infringement if the plaintiff shows (1) that its mark has priority and (2)\n\nthat the defendant’s mark is likely to cause consumer confusion. Frehling Enter.,\n\nInc. v. Int’l Select Grp., Inc., 192 F.3d 1330, 1335 (11th Cir. 1999). Velex\n\n\n2\n Velex’s mark:\n\n\n\n\n 3\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 4 of 19\n\n\nstipulated to the priority of PlayNation’s mark. We thus need only consider\n\nwhether the district court clearly erred in finding that Velex’s mark was likely to\n\ncause consumer confusion. In making that determination, we weigh seven factors:\n\n(1) the strength of the plaintiff’s mark; (2) the similarity of the marks; (3) the\n\nsimilarity of the products the marks represent; (4) the similarity of the parties’\n\nretail outlets and customers; (5) the similarity of advertising media; (6) the\n\ndefendant’s intent; and (7) actual confusion. Lone Star Steakhouse & Saloon, Inc.\n\nv. Longhorn Steaks, Inc., 122 F.3d 1379, 1382 (11th Cir. 1997).\n\n We review for clear error both a district court’s ultimate decision on\n\nlikelihood of confusion and its findings on each factor. Frehling, 192 F.3d at\n\n1335. Of these factors, the strength of the mark and actual confusion are the most\n\nprobative. Id. The district court held that each factor except the defendant’s intent\n\nweighed in favor of confusion. Velex challenges the district court’s determination\n\non the other factors and argues that the district court should have adopted two new\n\nfactors.\n\n A. Strength of PlayNation’s Mark\n\n “Classifying the type of mark Plaintiff has determines whether it is strong or\n\nweak. The stronger the mark, the greater the scope of protection accorded it, the\n\nweaker the mark, the less trademark protection it receives. There are four\n\ncategories of marks: (1) generic, (2) descriptive, (3) suggestive, and (4) arbitrary.”\n\n\n 4\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 5 of 19\n\n\nFrehling, 192 F.3d at 1335 (internal citations omitted). Suggestive marks are\n\nstronger and accordingly receive greater protection. Id. “Suggestive marks subtly\n\nconnote something about the service so that a customer could use his or her\n\nimagination and determine the nature of the service.” Freedom Sav. Loan Ass’n v.\n\nWay, 757 F.2d 1176, 1182 n.5 (11th Cir. 1985). The district court determined that\n\nPlayNation’s Gorilla Playsets mark was “descriptive or suggestive.” The products\n\nPlayNation sells under the mark are, of course, not designed for or used by gorillas.\n\nAt a minimum, the connection between the mark and the product requires some\n\nimagination. See Caliber Auto. Liquidators, Inc. v. Premier Chrysler, Jeep,\n\nDodge, LLC, 605 F.3d 931, 938 (11th Cir. 2010) (“A suggestive mark refers to\n\nsome characteristic of the goods, but requires a leap of the imagination to get from\n\nthe mark to the product [e.g., Penguin Refrigerators].”) (quotation marks omitted).\n\n The district court also reasoned that other factors increased the strength of\n\nPlayNation’s mark. See Frehling, 192 F.3d at 1336. First, PlayNation has\n\nextensively used the mark in commerce since 2002. PlayNation engaged in\n\nsignificant nationwide advertising and promotion using its Gorilla Playsets mark.\n\nThe district court found that this widespread use indicated consumer recognition,\n\nwhich enhances the strength of a mark. See John H. Harland Co. v. Clarke\n\nChecks, Inc., 711 F.2d 966, 974 n.13 (11th Cir. 1983) (noting that a mark may, “by\n\nreason of subsequent use and promotion, acquire such distinctiveness that it can\n\n\n 5\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 6 of 19\n\n\nfunction as a significant indication of a particular producer as source of the goods\n\nwith which it is used”). 3\n\n Second, the parties agree that PlayNation’s mark has been registered with\n\nthe Patent and Trademark Office for at least five years and is thus incontestable.\n\nFrehling, 192 F.3d at 1336. An incontestable mark “is presumed to be at least\n\ndescriptive with secondary meaning, and therefore a relatively strong mark.”\n\nDieter v. B & H Indus. of Southwest Fla., Inc., 880 F.3d 322, 329 (11th Cir. 1989);\n\nsee also Frehling, 192 F.3d at 1336.\n\n Finally, the lack of extensive third-party use also strengthens PlayNation’s\n\nmark. Frehling, 192 F.3d at 1336. Velex argues that the mark is weak because\n\nroughly thirty other registered marks in Class 28 contain the word “gorilla.” But\n\nnone of those gorilla marks were used on play equipment. And similar marks used\n\nby third parties in unrelated businesses or markets do not diminish the strength of a\n\nmark in a particular market. See Safeway Stores, Inc. v. Safeway Disc. Drugs, Inc.,\n\n\n\n\n3\n We have held that “in isolation, evidence of promotion efforts is not sufficient to establish a\nmark’s commercial strength because it tells us precious little about the efficacy of those efforts in\ncreating marketplace recognition . . . .” Fla. Int’l Univ. Bd. of Trustees v. Fla. Nat’l Univ., Inc.,\n830 F.3d 1242, 1259 (11th Cir. 2016) (first emphasis added) (holding that “[t]here simply was\nnot sufficient evidence of commercial strength in the record to require the district court to ignore\nthe substantial third-party usage.”). But this “circumstantial evidence of advertising and\npromotion,” id. (quotations omitted), is not the only evidence of the strength of PlayNation’s\nmark. Accordingly, the district court did not err in finding PlayNation’s advertising and\npromotion expenditures contributed to the strength of its mark.\n\n\n 6\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 7 of 19\n\n\n675 F.2d 1160, 1167 (11th Cir. 1982) (finding that twenty marks containing one of\n\nthe same words as the plaintiff’s mark did “not significantly diminish the strength\n\nof the [plaintiff’s] mark” because the other marks were used by “businesses not\n\nclosely related” to the plaintiff’s business), abrogated on other grounds, Tobinick\n\nv. Novella, 884 F.3d 1110 (11th Cir. 2018); cf. Sovereign Military Hospitaller\n\nOrder of Saint John of Jerusalem of Rhodes & of Malta v. Fla. Priory of the\n\nKnights Hospitallers of the Sovereign Order of Saint John of Jerusalem, Knights of\n\nMalta, The Ecumenical Order, 809 F.3d 1171, 1186 (11th Cir. 2015) (“That other\n\norganizations use parts of the Sovereign Order’s word marks is not persuasive\n\nevidence of third-party use.”).\n\n The district court did not clearly err in determining that PlayNation’s Gorilla\n\nPlaysets mark was strong.\n\n B. Actual Confusion\n\n “It is undisputed that evidence of actual confusion is the best evidence of a\n\nlikelihood of confusion.” Frehling, 192 F.3d at 1340. The actual confusion\n\ninquiry turns on both the number of instances of confusion and the type of person\n\nconfused. Caliber Auto., 605 F.3d at 936. While numerous instances of actual\n\nconfusion add greater weight in favor of confusion, “the quantum of evidence\n\nneeded to show actual confusion is relatively small.” Id. at 937 (quotation marks\n\n\n\n\n 7\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 8 of 19\n\n\nomitted). Evidence that ultimate consumers were actually confused deserves\n\n“special attention.” Id. at 936–37.\n\n The district court determined that the actual confusion factor weighed in\n\nfavor of a likelihood of confusion. PlayNation produced two ultimate purchasers\n\nof PlayNation’s Gorilla Playsets swing sets who contacted Velex for customer\n\nservice. The consumers believed Velex manufactured both Gorilla Gym and\n\nGorilla Playsets products. Consumers also posted on retail websites selling Gorilla\n\nPlaysets swings and trapeze bars asking if those items work “with the Gorilla Gym\n\nindoors.” Velex argues this evidence was insufficient to establish actual confusion\n\nbecause the two consumers were careless and uninformed. 4 Velex points to\n\nportions of the consumers’ testimony in which they confuse the names of the two\n\ncompanies and misremember which name was on the packaging and website they\n\nlooked at before calling Velex. Velex asserts that a prudent consumer would have\n\n\n\n4\n Velex argues that the two consumers calling the wrong phone number amounts to “initial\ninterest confusion,” a doctrine we have not yet accepted as actionable under the Lanham Act.\nSee Suntree Tech., Inc. v. Ecosense Intern., Inc., 693 F.3d 1338, 1347 (11th Cir. 2012). But\nVelex misunderstands initial interest confusion, which occurs when an alleged infringer pulls a\nsort of bait and switch. The infringer uses another’s trademark (or an imitation of it) to capture\nconsumers’ initial interest, leading the consumers to the infringer’s website or call center, for\nexample. But then the consumers, aware they are not actually dealing with the trademark holder,\ndecide to purchase the infringer’s other good or service. See N. Am. Med. Corp. v. Axiom\nWorldwide, Inc., 522 F.3d 1211, 1221 (11th Cir. 2008). That situation did not occur here. These\nwere instances of source confusion. The consumers testified that they believed Gorilla Gym and\nGorilla Playsets were produced by the same company. See id. at 1222 n.9 (“‘Source confusion’\nexists because consumers are likely to be confused as to whether [the infringer’s] products have\nthe same source or sponsor as [the trademark holder’s] or whether there is some other affiliation\nor relationship between the two.”).\n 8\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 9 of 19\n\n\nexamined the packaging, read the product warranty, or researched the product on\n\nthe internet. Velex argues that had the consumers been so diligent, they would\n\nhave discovered that PlayNation—not Velex—manufactured the product they\n\npurchased.\n\n First, nothing in the actual confusion analysis requires the plaintiff to\n\nproduce the most careful consumer, who diligently researched and meticulously\n\nexamined the inner and outer packing to determine the provenance of the product\n\nshe purchased. It only requires that the consumers be reasonably prudent. The\n\ndistrict court found the consumers’ testimony probative. That the district court\n\nmade that determination even though the two witnesses confused the names of the\n\ntwo brands or failed to examine the packing before mistakenly calling Velex for\n\nhelp does not amount to clear error.\n\n Second, the number of instances and the type of consumer also support the\n\ndistrict court’s actual confusion finding. The customers PlayNation identified are\n\nultimate consumers of the product, to which we give special weight. And the\n\nnumber of instances need not be large to be probative of confusion. See Safeway\n\nStores, 675 F.2d at 1167 (finding one instance of actual customer confusion\n\nsufficient and holding that “[a]lthough the number of instances is small, the people\n\nconfused are precisely those whose confusion is most significant”).\n\n\n\n\n 9\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 10 of 19\n\n\n The district court thus did not clearly err in holding that the actual confusion\n\nfactor weighed in favor of a likelihood of confusion.\n\n C. Similarity of Marks\n\n To determine if two marks are similar, the court “considers the overall\n\nimpressions that the marks create, including the sound, appearance, and manner in\n\nwhich they are used.” Frehling, 192 F.3d at 1337. The dominant portion of both\n\nmarks is an image of a large gorilla and the word “gorilla.” The other words,\n\n“playset” in one and “gym” in the other, are very similar and do not contribute to\n\ndistinctiveness. See id. (holding that “a mark may be surrounded by additional\n\nwords of lesser importance and not have its strength diluted”). The colors and\n\nfonts are different, and the gorillas are in different areas and positions in the marks.\n\nBut even so, given the similarity in the type of gorilla, size of gorilla, and the\n\nalmost indistinguishable words used in the two marks, those differences do not\n\nmake the district court’s decision clearly erroneous.\n\n D. Similarity of Products, Retail Outlets, and Advertising\n\n The district court did not clearly err in finding that the products, retail\n\noutlets, and advertising of PlayNation and Velex were sufficiently similar to weigh\n\nin favor of confusion. First, the products are highly similar. The test for similar\n\nproducts is “whether the products are the kind that the public attributes to a single\n\nsource, not whether or not the purchasing public can readily distinguish between\n\n\n 10\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 11 of 19\n\n\nthe products of the respective parties.” Frehling, 192 F.3d at 1338. Velex argues\n\nthat it sells only indoor products, while PlayNation sells only outdoor products.\n\nBut the question is not whether there is a distinguishing characteristic, but whether\n\nthe goods are so related that a consumer would believe that a single producer made\n\nboth. See E. Remy Martin & Co., S.A. v. Shaw-Ross Int’l Imports, Inc., 756 F.2d\n\n1525, 1530 (11th Cir. 1985) (holding that it was not unreasonable for consumers to\n\nconclude that a maker of wine could also produce brandy). Both PlayNation and\n\nVelex sold a core unit with separate attachable accessories for children, including\n\nswings, ropes, and rings. These are sufficiently similar to support the district\n\ncourt’s finding.\n\n Second, the retail outlets are similar. “This factor takes into consideration\n\nwhere, how, and to whom the parties’ products are sold.” Frehling, 192 F.3d at\n\n1339. But “[d]irect competition between the parties is not required for this factor\n\nto weigh in favor of likelihood of confusion.” Id. Both Playnation and Velex sold\n\ntheir products through substantially similar retail outlets, including big box stores,\n\ntheir own websites, and other online retailers like Amazon and Walmart. Velex\n\nargues that because PlayNation also sells its products through dealers, their retail\n\noutlets are dissimilar. But here again, exact parallels are not required, and one\n\ndistinct retail outlet does not amount to clear error.\n\n\n\n\n 11\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 12 of 19\n\n\n Third, PlayNation and Velex engaged in similar advertising. “This factor\n\nlooks to each party’s method of advertising.” Id. at 1339. “[T]he standard is\n\nwhether there is likely to be significant enough overlap in the readership of the\n\npublications in which the parties advertise that a possibility of confusion could\n\nresult.” Id. at 1340. PlayNation and Velex both advertised using their own\n\nwebsites, television, and the internet—including Google and Amazon keyword\n\nadvertising, Facebook, and YouTube.\n\n While there may be some evidence to support dissimilar products, retail\n\noutlets, and advertising, they are not enough to compel an alternative finding under\n\nclear error review.\n\n These factors are not exclusive. Courts do not have to consider every factor\n\nin every case. Swatch Watch, S.A. v. Taxor, Inc., 785 F.2d 956, 958 (11th Cir.\n\n1986). Courts may also consider other probative evidence that does not fit within\n\nthe factors. Id.\n\n E. New Factors\n\n Velex proposes two new factors the district court should have considered:\n\nfirst, that Velex had a valid federal trademark registration that covered the\n\ninfringing products, and second, that PlayNation failed to produce survey evidence\n\nsuggesting consumer confusion.\n\n\n\n\n 12\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 13 of 19\n\n\n To support adoption of its first proposed factor, Velex argues that it ought to\n\nhave the right to rely on decisions of the government—here, the Patent and\n\nTrademark Office (PTO). Velex relies on the Supreme Court’s decision in B&B\n\nHardware, Inc. v. Hargis Indus., Inc., 135 S. Ct. 1293 (2015). In B&B Hardware,\n\nthe Supreme Court held that the likelihood of confusion standard used by the PTO\n\nfor determining whether to register a new mark and the standard used by courts in\n\ntrademark infringement cases are “the same.” 135 S. Ct. at 1306–07. But the\n\nSupreme Court made that conclusion in determining whether issue preclusion\n\napplied. Id. The Court held that issue preclusion applied to a district court\n\ndeciding a Lanham Act trademark infringement claim when the Trademark Trial\n\nand Appeal Board (TTAB) had previously decided the parties’ marks were not\n\nconfusingly similar for purposes of registration. Id. at 1307. There is no such\n\nfinding by the PTO or TTAB in this case because PlayNation did not object to\n\nVelex’s registration or litigate the issue before the TTAB. Issue preclusion does\n\nnot bind PlayNation, because it was not a party to any prior proceeding. Cf.\n\nTampa Bay Water v. HDR Eng’g, Inc., 731 F.3d 1171, 1179 (11th Cir. 2013),\n\noverruled on other grounds by CSX Transp., Inc. v. Gen. Mills, Inc., 846 F.3d\n\n1333, 1340 (11th Cir. 2017).\n\n B&B Hardware does not suggest that, absent a prior administrative finding,\n\na district court deciding a trademark infringement action is bound—or even ought\n\n\n 13\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 14 of 19\n\n\nto be persuaded—by the PTO’s registration of the defendant’s mark. Id.\n\n(“[D]istrict courts can cancel registrations during infringement litigation, just as\n\nthey can adjudicate infringement in suits seeking judicial review of registration\n\ndecisions.”). To the contrary, the Lanham Act expressly gives district courts the\n\npower to cancel federal trademarks issued by the PTO when they violate the\n\nLanham Act. See 15 U.S.C. § 1119. Absent issue preclusion, it was not clearly\n\nerroneous for the district court not to consider the PTO’s decision to approve\n\nVelex’s trademark as a factor.\n\n It was similarly not clearly erroneous for the district court not to consider\n\nVelex’s second proposed factor: lack of survey evidence. Lack of survey evidence\n\ndoes not weigh against the plaintiff when determining likelihood of confusion. See\n\nFrehling, 192 F.3d at 1341 n.5 (“This Circuit . . . has moved away from relying on\n\nsurvey evidence” and “the failure to adduce such evidence is not damaging to [a\n\nplaintiff’s] case.”). We are not persuaded by Velex’s reliance on Hickson Corp. v.\n\nN. Crossarm Co., 357 F.3d 1256 (11th Cir. 2004). Hickson was a false advertising\n\ncase, not a trademark infringement case. Unlike in a trademark infringement\n\naction, a plaintiff attempting to establish a misleading advertisement under the\n\nLanham Act “must present evidence of deception in the form of consumer surveys,\n\nmarket research, expert testimony, or other evidence.” Hickson, 357 F.3d at 1261\n\n\n\n\n 14\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 15 of 19\n\n\n(internal quotation marks omitted). There is no similar requirement for trademark\n\ninfringement, and we decline to impose one here.\n\n The district court did not clearly err in holding that Velex infringed on\n\nPlayNation’s trademark.\n\n III. Remedies\n\n Velex argues that the district court erred in fashioning a remedy in this case\n\nby first, awarding PlayNation damages based on an accounting of Velex’s profits,\n\nand second, cancelling Velex’s trademark registration. We review a district court’s\n\ndecision to grant relief, including cancelling a party’s trademark registration, for\n\nabuse of discretion. See Planetary Motion, Inc. v. Techsplosion, Inc., 261 F.3d\n\n1188, 1203 (11th Cir. 2001).\n\n A. Damages\n\n The Lanham Act allows a successful plaintiff to recover the defendant’s\n\nprofits. 15 U.S.C. § 1117(a). “In assessing profits the plaintiff shall be required to\n\nprove defendant’s sales only; defendant must prove all elements of cost or\n\ndeduction claimed.” Id. “The Act confers upon the district court a wide scope of\n\ndiscretion to determine the proper relief due an injured party.” Burger King Corp.\n\nv. Mason, 855 F.2d 779, 781 (11th Cir. 1988) (per curiam). An accounting of a\n\ndefendant’s profits is appropriate where: (1) the defendant’s conduct was willful\n\nand deliberate, (2) the defendant was unjustly enriched, or (3) it is necessary to\n\n\n 15\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 16 of 19\n\n\ndeter future conduct. Howard Johnson Co., Inc. v. Khimani, 892 F.2d 1512, 1521\n\n(11th Cir. 1990). Conduct is willful if the infringer was “knowingly and\n\ndeliberately cashing in upon the good will of [the infringed].” Burger King, 855\n\nF.3d at 781.\n\n The district court concluded that Velex willfully infringed on PlayNation’s\n\ntrademark based solely on Velex’s continued sale of its Gorilla Gym products after\n\nit was served with PlayNation’s complaint. The district court reasoned that\n\nPlayNation’s complaint put Velex’s on notice that it was allegedly infringing on\n\nPlayNation’s trademark. But when it received PlayNation’s complaint, Velex had\n\na valid registered trademark on Gorilla Gym. PlayNation did not obtain a\n\npreliminary injunction, and at the time, no court had adjudicated whether Velex\n\nwas infringing on PlayNation’s trademark.\n\n Under the district court’s construction of willfulness, a valid trademark\n\nholder risks losing all of its profits if it does not immediately cease selling its\n\ntrademarked product upon receiving a complaint indicating it may be violating the\n\nlaw. The district court determined that at the time Velex obtained its trademark,\n\nVelex did not intend to infringe on PlayNation’s trademark. And from the time\n\nVelex obtained its trademark to the time the district court made its final\n\ndetermination, there was no further adjudication that Velex was infringing. This\n\ncontinued sale under the color of a valid federal trademark cannot alone establish\n\n\n 16\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 17 of 19\n\n\nwillfulness. See cf. Maltina Corp. v. Cawy Bottling Co., Inc., 613 F.2d 582, 587\n\n(5th Cir. 1980) (finding willfulness that justified an accounting of profits where the\n\ninfringer used the infringing mark after the patent office refused to register it based\n\non the confusing similarity of the plaintiff’s registered mark).\n\n There may have been other evidence of willfulness, but the district court did\n\nnot rely on it in its decision. The district court also relied solely on the willfulness\n\ntheory to support its accounting of profits. The other two theories for supporting\n\nan accounting of profits, deterrence and unjust enrichment, do not depend “upon a\n\nhigher showing of culpability on the part of defendant, who is purposely using the\n\ntrademark.” Burger King, 855 F.2d at 781. Remand is appropriate so that the\n\ndistrict court may consider whether other evidence of willfulness exists and\n\nwhether those alternative theories support an accounting of profits.\n\n B. Cancelling Trademark Registration\n\n District courts have discretion to order the cancelation of a federal trademark\n\nregistration in whole or in part. 15 U.S.C. § 1119. Cancelling a trademark\n\nregistration is appropriate where the plaintiff shows (1) that it had standing to\n\npetition for cancellation because it was likely to be damaged by the infringer’s\n\ncontinued use of the infringing mark, and (2) that there were valid grounds for\n\ndiscontinuing registration. Coach House Rest., Inc. v. Coach & Six Rests., Inc.,\n\n934 F.2d 1551, 1557 (11th Cir. 1991). PlayNation’s federal registration of its mark\n\n\n 17\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 18 of 19\n\n\nsatisfies the first element. See id. at 1557–58. PlayNation must show only the\n\nsecond element—a valid ground for cancelling registration.\n\n If the “mark at issue has been on the federal Principal Register in registrant’s\n\nname for less than five years, the mark may be cancelled if petitioner can prove\n\nthat the registration should have been barred in the first instance under Lanham Act\n\n§ 2.” Id. at 1558. “In order to cancel a registration under Lanham Act Section\n\n2(d) in this case, petitioner must prove . . . that the registered mark is likely to\n\ncause confusion when used in connection with the services of registrant.” Id. at\n\n1559. Establishing trademark infringement thus satisfies the second cancellation\n\nrequirement.\n\n Having concluded that Velex infringed on PlayNation’s trademark, it was\n\nnot an abuse of discretion for the district court to cancel Velex’s trademark\n\nregistration.\n\n IV. Conclusion\n\n The district court did not clearly err in holding that Velex infringed on\n\nPlayNation’s trademark. The district court similarly did not err in canceling\n\nVelex’s trademark registration on that basis. But the district court did abuse its\n\ndiscretion in holding that PlayNation was entitled to an accounting of Velex’s\n\nprofits due to willful infringement based solely on Velex’s continued lawful use of\n\nits mark after Velex was served with the complaint in this action. As a result, we\n\n\n 18\n\f Case: 17-15226 Date Filed: 05/21/2019 Page: 19 of 19\n\n\nvacate the district court’s judgment on that issue, and remand for further\n\nproceedings consistent with this opinion.\n\n AFFIRMED IN PART, VACATED AND REMANDED IN PART.\n\n\n\n\n 19\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: PlayNation Play Systems, Inc. v. Velex Corporation\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-21\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-15226 Date Filed: 05/21/2019 Page: 1 of 19\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15226\\n ________________________\\n\\n D.C. Docket No. 1:14-cv-01046-RWS\\n\\n\\n\\nPLAYNATION PLAY SYSTEMS, INC.,\\nd.b.a. Gorilla Playsets,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nVELEX CORPORATION,\\nd.b.a. Gorilla Gym,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 21, 2019)\\n\\nBefore WILSON, BRANCH, and ANDERSON, Circuit Judges.\\n\\nWILSON, Circuit Judge:\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 2 of 19\\n\\n\\n The parties to this appeal both chose a gorilla as the face of their respective\\n\\nbrands. Litigation ensued. PlayNation Play Systems, Inc. sued Velex Corporation\\n\\nfor trademark infringement. The district court conducted a bench trial and entered\\n\\njudgment for PlayNation. Velex now appeals, arguing that the district court erred\\n\\nin finding trademark infringement, awarding damages to PlayNation, and\\n\\ncancelling Velex’s trademark registration. After careful review and with the\\n\\nbenefit of oral argument, we affirm the district court’s decisions on Velex’s\\n\\nliability for trademark infringement and cancellation of Velex’s trademark. We\\n\\nvacate and remand, however, on the district court’s determination of damages\\n\\nbased on Velex’s willful infringement.\\n\\n I. Factual Background\\n\\n PlayNation has sold children’s outdoor playground equipment, including\\n\\nswing sets and attachable swings, ropes, and rings, under its “Gorilla Playsets”\\n\\nbrand since 2002. PlayNation owns three registered trademarks for Gorilla\\n\\nPlaysets, two registered in 2004 and another in 2014. 1 Velex sells “Gorilla Gym”\\n\\ndoorway pull-up bars and various attachable accessories for children, including\\n\\n\\n\\n1\\n PlayNation’s mark:\\n\\n\\n\\n\\n 2\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 3 of 19\\n\\n\\nswings, ropes, and rings, under its “Gorilla Gym” brand. Velex successfully\\n\\nregistered a trademark for Gorilla Gym in 2014. 2 Both PlayNation and Velex’s\\n\\ntrademarks are registered in Class 28, the broad class of goods for games and other\\n\\nplaythings.\\n\\n II. Trademark Infringement\\n\\n Velex first argues that the district court erred by concluding that consumers\\n\\nwould likely be confused by Velex’s use of the Gorilla Gym mark. In an appeal\\n\\nfrom a bench trial, we review a district court’s conclusions of law de novo and its\\n\\nfactual findings for clear error. Tartell v. S. Fla. Sinus & Allergy Ctr., Inc., 790\\n\\nF.3d 1253, 1257 (11th Cir. 2015). A factual finding is clearly erroneous if, after\\n\\nviewing the totality of the evidence, the court is left with a definite and firm\\n\\nconviction that a mistake was made. Id.\\n\\n Under the Lanham Act, 15 U.S.C. § 1114(1), a defendant is liable for\\n\\ntrademark infringement if the plaintiff shows (1) that its mark has priority and (2)\\n\\nthat the defendant’s mark is likely to cause consumer confusion. Frehling Enter.,\\n\\nInc. v. Int’l Select Grp., Inc., 192 F.3d 1330, 1335 (11th Cir. 1999). Velex\\n\\n\\n2\\n Velex’s mark:\\n\\n\\n\\n\\n 3\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 4 of 19\\n\\n\\nstipulated to the priority of PlayNation’s mark. We thus need only consider\\n\\nwhether the district court clearly erred in finding that Velex’s mark was likely to\\n\\ncause consumer confusion. In making that determination, we weigh seven factors:\\n\\n(1) the strength of the plaintiff’s mark; (2) the similarity of the marks; (3) the\\n\\nsimilarity of the products the marks represent; (4) the similarity of the parties’\\n\\nretail outlets and customers; (5) the similarity of advertising media; (6) the\\n\\ndefendant’s intent; and (7) actual confusion. Lone Star Steakhouse & Saloon, Inc.\\n\\nv. Longhorn Steaks, Inc., 122 F.3d 1379, 1382 (11th Cir. 1997).\\n\\n We review for clear error both a district court’s ultimate decision on\\n\\nlikelihood of confusion and its findings on each factor. Frehling, 192 F.3d at\\n\\n1335. Of these factors, the strength of the mark and actual confusion are the most\\n\\nprobative. Id. The district court held that each factor except the defendant’s intent\\n\\nweighed in favor of confusion. Velex challenges the district court’s determination\\n\\non the other factors and argues that the district court should have adopted two new\\n\\nfactors.\\n\\n A. Strength of PlayNation’s Mark\\n\\n “Classifying the type of mark Plaintiff has determines whether it is strong or\\n\\nweak. The stronger the mark, the greater the scope of protection accorded it, the\\n\\nweaker the mark, the less trademark protection it receives. There are four\\n\\ncategories of marks: (1) generic, (2) descriptive, (3) suggestive, and (4) arbitrary.”\\n\\n\\n 4\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 5 of 19\\n\\n\\nFrehling, 192 F.3d at 1335 (internal citations omitted). Suggestive marks are\\n\\nstronger and accordingly receive greater protection. Id. “Suggestive marks subtly\\n\\nconnote something about the service so that a customer could use his or her\\n\\nimagination and determine the nature of the service.” Freedom Sav. Loan Ass’n v.\\n\\nWay, 757 F.2d 1176, 1182 n.5 (11th Cir. 1985). The district court determined that\\n\\nPlayNation’s Gorilla Playsets mark was “descriptive or suggestive.” The products\\n\\nPlayNation sells under the mark are, of course, not designed for or used by gorillas.\\n\\nAt a minimum, the connection between the mark and the product requires some\\n\\nimagination. See Caliber Auto. Liquidators, Inc. v. Premier Chrysler, Jeep,\\n\\nDodge, LLC, 605 F.3d 931, 938 (11th Cir. 2010) (“A suggestive mark refers to\\n\\nsome characteristic of the goods, but requires a leap of the imagination to get from\\n\\nthe mark to the product [e.g., Penguin Refrigerators].”) (quotation marks omitted).\\n\\n The district court also reasoned that other factors increased the strength of\\n\\nPlayNation’s mark. See Frehling, 192 F.3d at 1336. First, PlayNation has\\n\\nextensively used the mark in commerce since 2002. PlayNation engaged in\\n\\nsignificant nationwide advertising and promotion using its Gorilla Playsets mark.\\n\\nThe district court found that this widespread use indicated consumer recognition,\\n\\nwhich enhances the strength of a mark. See John H. Harland Co. v. Clarke\\n\\nChecks, Inc., 711 F.2d 966, 974 n.13 (11th Cir. 1983) (noting that a mark may, “by\\n\\nreason of subsequent use and promotion, acquire such distinctiveness that it can\\n\\n\\n 5\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 6 of 19\\n\\n\\nfunction as a significant indication of a particular producer as source of the goods\\n\\nwith which it is used”). 3\\n\\n Second, the parties agree that PlayNation’s mark has been registered with\\n\\nthe Patent and Trademark Office for at least five years and is thus incontestable.\\n\\nFrehling, 192 F.3d at 1336. An incontestable mark “is presumed to be at least\\n\\ndescriptive with secondary meaning, and therefore a relatively strong mark.”\\n\\nDieter v. B & H Indus. of Southwest Fla., Inc., 880 F.3d 322, 329 (11th Cir. 1989);\\n\\nsee also Frehling, 192 F.3d at 1336.\\n\\n Finally, the lack of extensive third-party use also strengthens PlayNation’s\\n\\nmark. Frehling, 192 F.3d at 1336. Velex argues that the mark is weak because\\n\\nroughly thirty other registered marks in Class 28 contain the word “gorilla.” But\\n\\nnone of those gorilla marks were used on play equipment. And similar marks used\\n\\nby third parties in unrelated businesses or markets do not diminish the strength of a\\n\\nmark in a particular market. See Safeway Stores, Inc. v. Safeway Disc. Drugs, Inc.,\\n\\n\\n\\n\\n3\\n We have held that “in isolation, evidence of promotion efforts is not sufficient to establish a\\nmark’s commercial strength because it tells us precious little about the efficacy of those efforts in\\ncreating marketplace recognition . . . .” Fla. Int’l Univ. Bd. of Trustees v. Fla. Nat’l Univ., Inc.,\\n830 F.3d 1242, 1259 (11th Cir. 2016) (first emphasis added) (holding that “[t]here simply was\\nnot sufficient evidence of commercial strength in the record to require the district court to ignore\\nthe substantial third-party usage.”). But this “circumstantial evidence of advertising and\\npromotion,” id. (quotations omitted), is not the only evidence of the strength of PlayNation’s\\nmark. Accordingly, the district court did not err in finding PlayNation’s advertising and\\npromotion expenditures contributed to the strength of its mark.\\n\\n\\n 6\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 7 of 19\\n\\n\\n675 F.2d 1160, 1167 (11th Cir. 1982) (finding that twenty marks containing one of\\n\\nthe same words as the plaintiff’s mark did “not significantly diminish the strength\\n\\nof the [plaintiff’s] mark” because the other marks were used by “businesses not\\n\\nclosely related” to the plaintiff’s business), abrogated on other grounds, Tobinick\\n\\nv. Novella, 884 F.3d 1110 (11th Cir. 2018); cf. Sovereign Military Hospitaller\\n\\nOrder of Saint John of Jerusalem of Rhodes & of Malta v. Fla. Priory of the\\n\\nKnights Hospitallers of the Sovereign Order of Saint John of Jerusalem, Knights of\\n\\nMalta, The Ecumenical Order, 809 F.3d 1171, 1186 (11th Cir. 2015) (“That other\\n\\norganizations use parts of the Sovereign Order’s word marks is not persuasive\\n\\nevidence of third-party use.”).\\n\\n The district court did not clearly err in determining that PlayNation’s Gorilla\\n\\nPlaysets mark was strong.\\n\\n B. Actual Confusion\\n\\n “It is undisputed that evidence of actual confusion is the best evidence of a\\n\\nlikelihood of confusion.” Frehling, 192 F.3d at 1340. The actual confusion\\n\\ninquiry turns on both the number of instances of confusion and the type of person\\n\\nconfused. Caliber Auto., 605 F.3d at 936. While numerous instances of actual\\n\\nconfusion add greater weight in favor of confusion, “the quantum of evidence\\n\\nneeded to show actual confusion is relatively small.” Id. at 937 (quotation marks\\n\\n\\n\\n\\n 7\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 8 of 19\\n\\n\\nomitted). Evidence that ultimate consumers were actually confused deserves\\n\\n“special attention.” Id. at 936–37.\\n\\n The district court determined that the actual confusion factor weighed in\\n\\nfavor of a likelihood of confusion. PlayNation produced two ultimate purchasers\\n\\nof PlayNation’s Gorilla Playsets swing sets who contacted Velex for customer\\n\\nservice. The consumers believed Velex manufactured both Gorilla Gym and\\n\\nGorilla Playsets products. Consumers also posted on retail websites selling Gorilla\\n\\nPlaysets swings and trapeze bars asking if those items work “with the Gorilla Gym\\n\\nindoors.” Velex argues this evidence was insufficient to establish actual confusion\\n\\nbecause the two consumers were careless and uninformed. 4 Velex points to\\n\\nportions of the consumers’ testimony in which they confuse the names of the two\\n\\ncompanies and misremember which name was on the packaging and website they\\n\\nlooked at before calling Velex. Velex asserts that a prudent consumer would have\\n\\n\\n\\n4\\n Velex argues that the two consumers calling the wrong phone number amounts to “initial\\ninterest confusion,” a doctrine we have not yet accepted as actionable under the Lanham Act.\\nSee Suntree Tech., Inc. v. Ecosense Intern., Inc., 693 F.3d 1338, 1347 (11th Cir. 2012). But\\nVelex misunderstands initial interest confusion, which occurs when an alleged infringer pulls a\\nsort of bait and switch. The infringer uses another’s trademark (or an imitation of it) to capture\\nconsumers’ initial interest, leading the consumers to the infringer’s website or call center, for\\nexample. But then the consumers, aware they are not actually dealing with the trademark holder,\\ndecide to purchase the infringer’s other good or service. See N. Am. Med. Corp. v. Axiom\\nWorldwide, Inc., 522 F.3d 1211, 1221 (11th Cir. 2008). That situation did not occur here. These\\nwere instances of source confusion. The consumers testified that they believed Gorilla Gym and\\nGorilla Playsets were produced by the same company. See id. at 1222 n.9 (“‘Source confusion’\\nexists because consumers are likely to be confused as to whether [the infringer’s] products have\\nthe same source or sponsor as [the trademark holder’s] or whether there is some other affiliation\\nor relationship between the two.”).\\n 8\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 9 of 19\\n\\n\\nexamined the packaging, read the product warranty, or researched the product on\\n\\nthe internet. Velex argues that had the consumers been so diligent, they would\\n\\nhave discovered that PlayNation—not Velex—manufactured the product they\\n\\npurchased.\\n\\n First, nothing in the actual confusion analysis requires the plaintiff to\\n\\nproduce the most careful consumer, who diligently researched and meticulously\\n\\nexamined the inner and outer packing to determine the provenance of the product\\n\\nshe purchased. It only requires that the consumers be reasonably prudent. The\\n\\ndistrict court found the consumers’ testimony probative. That the district court\\n\\nmade that determination even though the two witnesses confused the names of the\\n\\ntwo brands or failed to examine the packing before mistakenly calling Velex for\\n\\nhelp does not amount to clear error.\\n\\n Second, the number of instances and the type of consumer also support the\\n\\ndistrict court’s actual confusion finding. The customers PlayNation identified are\\n\\nultimate consumers of the product, to which we give special weight. And the\\n\\nnumber of instances need not be large to be probative of confusion. See Safeway\\n\\nStores, 675 F.2d at 1167 (finding one instance of actual customer confusion\\n\\nsufficient and holding that “[a]lthough the number of instances is small, the people\\n\\nconfused are precisely those whose confusion is most significant”).\\n\\n\\n\\n\\n 9\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 10 of 19\\n\\n\\n The district court thus did not clearly err in holding that the actual confusion\\n\\nfactor weighed in favor of a likelihood of confusion.\\n\\n C. Similarity of Marks\\n\\n To determine if two marks are similar, the court “considers the overall\\n\\nimpressions that the marks create, including the sound, appearance, and manner in\\n\\nwhich they are used.” Frehling, 192 F.3d at 1337. The dominant portion of both\\n\\nmarks is an image of a large gorilla and the word “gorilla.” The other words,\\n\\n“playset” in one and “gym” in the other, are very similar and do not contribute to\\n\\ndistinctiveness. See id. (holding that “a mark may be surrounded by additional\\n\\nwords of lesser importance and not have its strength diluted”). The colors and\\n\\nfonts are different, and the gorillas are in different areas and positions in the marks.\\n\\nBut even so, given the similarity in the type of gorilla, size of gorilla, and the\\n\\nalmost indistinguishable words used in the two marks, those differences do not\\n\\nmake the district court’s decision clearly erroneous.\\n\\n D. Similarity of Products, Retail Outlets, and Advertising\\n\\n The district court did not clearly err in finding that the products, retail\\n\\noutlets, and advertising of PlayNation and Velex were sufficiently similar to weigh\\n\\nin favor of confusion. First, the products are highly similar. The test for similar\\n\\nproducts is “whether the products are the kind that the public attributes to a single\\n\\nsource, not whether or not the purchasing public can readily distinguish between\\n\\n\\n 10\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 11 of 19\\n\\n\\nthe products of the respective parties.” Frehling, 192 F.3d at 1338. Velex argues\\n\\nthat it sells only indoor products, while PlayNation sells only outdoor products.\\n\\nBut the question is not whether there is a distinguishing characteristic, but whether\\n\\nthe goods are so related that a consumer would believe that a single producer made\\n\\nboth. See E. Remy Martin & Co., S.A. v. Shaw-Ross Int’l Imports, Inc., 756 F.2d\\n\\n1525, 1530 (11th Cir. 1985) (holding that it was not unreasonable for consumers to\\n\\nconclude that a maker of wine could also produce brandy). Both PlayNation and\\n\\nVelex sold a core unit with separate attachable accessories for children, including\\n\\nswings, ropes, and rings. These are sufficiently similar to support the district\\n\\ncourt’s finding.\\n\\n Second, the retail outlets are similar. “This factor takes into consideration\\n\\nwhere, how, and to whom the parties’ products are sold.” Frehling, 192 F.3d at\\n\\n1339. But “[d]irect competition between the parties is not required for this factor\\n\\nto weigh in favor of likelihood of confusion.” Id. Both Playnation and Velex sold\\n\\ntheir products through substantially similar retail outlets, including big box stores,\\n\\ntheir own websites, and other online retailers like Amazon and Walmart. Velex\\n\\nargues that because PlayNation also sells its products through dealers, their retail\\n\\noutlets are dissimilar. But here again, exact parallels are not required, and one\\n\\ndistinct retail outlet does not amount to clear error.\\n\\n\\n\\n\\n 11\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 12 of 19\\n\\n\\n Third, PlayNation and Velex engaged in similar advertising. “This factor\\n\\nlooks to each party’s method of advertising.” Id. at 1339. “[T]he standard is\\n\\nwhether there is likely to be significant enough overlap in the readership of the\\n\\npublications in which the parties advertise that a possibility of confusion could\\n\\nresult.” Id. at 1340. PlayNation and Velex both advertised using their own\\n\\nwebsites, television, and the internet—including Google and Amazon keyword\\n\\nadvertising, Facebook, and YouTube.\\n\\n While there may be some evidence to support dissimilar products, retail\\n\\noutlets, and advertising, they are not enough to compel an alternative finding under\\n\\nclear error review.\\n\\n These factors are not exclusive. Courts do not have to consider every factor\\n\\nin every case. Swatch Watch, S.A. v. Taxor, Inc., 785 F.2d 956, 958 (11th Cir.\\n\\n1986). Courts may also consider other probative evidence that does not fit within\\n\\nthe factors. Id.\\n\\n E. New Factors\\n\\n Velex proposes two new factors the district court should have considered:\\n\\nfirst, that Velex had a valid federal trademark registration that covered the\\n\\ninfringing products, and second, that PlayNation failed to produce survey evidence\\n\\nsuggesting consumer confusion.\\n\\n\\n\\n\\n 12\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 13 of 19\\n\\n\\n To support adoption of its first proposed factor, Velex argues that it ought to\\n\\nhave the right to rely on decisions of the government—here, the Patent and\\n\\nTrademark Office (PTO). Velex relies on the Supreme Court’s decision in B&B\\n\\nHardware, Inc. v. Hargis Indus., Inc., 135 S. Ct. 1293 (2015). In B&B Hardware,\\n\\nthe Supreme Court held that the likelihood of confusion standard used by the PTO\\n\\nfor determining whether to register a new mark and the standard used by courts in\\n\\ntrademark infringement cases are “the same.” 135 S. Ct. at 1306–07. But the\\n\\nSupreme Court made that conclusion in determining whether issue preclusion\\n\\napplied. Id. The Court held that issue preclusion applied to a district court\\n\\ndeciding a Lanham Act trademark infringement claim when the Trademark Trial\\n\\nand Appeal Board (TTAB) had previously decided the parties’ marks were not\\n\\nconfusingly similar for purposes of registration. Id. at 1307. There is no such\\n\\nfinding by the PTO or TTAB in this case because PlayNation did not object to\\n\\nVelex’s registration or litigate the issue before the TTAB. Issue preclusion does\\n\\nnot bind PlayNation, because it was not a party to any prior proceeding. Cf.\\n\\nTampa Bay Water v. HDR Eng’g, Inc., 731 F.3d 1171, 1179 (11th Cir. 2013),\\n\\noverruled on other grounds by CSX Transp., Inc. v. Gen. Mills, Inc., 846 F.3d\\n\\n1333, 1340 (11th Cir. 2017).\\n\\n B&B Hardware does not suggest that, absent a prior administrative finding,\\n\\na district court deciding a trademark infringement action is bound—or even ought\\n\\n\\n 13\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 14 of 19\\n\\n\\nto be persuaded—by the PTO’s registration of the defendant’s mark. Id.\\n\\n(“[D]istrict courts can cancel registrations during infringement litigation, just as\\n\\nthey can adjudicate infringement in suits seeking judicial review of registration\\n\\ndecisions.”). To the contrary, the Lanham Act expressly gives district courts the\\n\\npower to cancel federal trademarks issued by the PTO when they violate the\\n\\nLanham Act. See 15 U.S.C. § 1119. Absent issue preclusion, it was not clearly\\n\\nerroneous for the district court not to consider the PTO’s decision to approve\\n\\nVelex’s trademark as a factor.\\n\\n It was similarly not clearly erroneous for the district court not to consider\\n\\nVelex’s second proposed factor: lack of survey evidence. Lack of survey evidence\\n\\ndoes not weigh against the plaintiff when determining likelihood of confusion. See\\n\\nFrehling, 192 F.3d at 1341 n.5 (“This Circuit . . . has moved away from relying on\\n\\nsurvey evidence” and “the failure to adduce such evidence is not damaging to [a\\n\\nplaintiff’s] case.”). We are not persuaded by Velex’s reliance on Hickson Corp. v.\\n\\nN. Crossarm Co., 357 F.3d 1256 (11th Cir. 2004). Hickson was a false advertising\\n\\ncase, not a trademark infringement case. Unlike in a trademark infringement\\n\\naction, a plaintiff attempting to establish a misleading advertisement under the\\n\\nLanham Act “must present evidence of deception in the form of consumer surveys,\\n\\nmarket research, expert testimony, or other evidence.” Hickson, 357 F.3d at 1261\\n\\n\\n\\n\\n 14\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 15 of 19\\n\\n\\n(internal quotation marks omitted). There is no similar requirement for trademark\\n\\ninfringement, and we decline to impose one here.\\n\\n The district court did not clearly err in holding that Velex infringed on\\n\\nPlayNation’s trademark.\\n\\n III. Remedies\\n\\n Velex argues that the district court erred in fashioning a remedy in this case\\n\\nby first, awarding PlayNation damages based on an accounting of Velex’s profits,\\n\\nand second, cancelling Velex’s trademark registration. We review a district court’s\\n\\ndecision to grant relief, including cancelling a party’s trademark registration, for\\n\\nabuse of discretion. See Planetary Motion, Inc. v. Techsplosion, Inc., 261 F.3d\\n\\n1188, 1203 (11th Cir. 2001).\\n\\n A. Damages\\n\\n The Lanham Act allows a successful plaintiff to recover the defendant’s\\n\\nprofits. 15 U.S.C. § 1117(a). “In assessing profits the plaintiff shall be required to\\n\\nprove defendant’s sales only; defendant must prove all elements of cost or\\n\\ndeduction claimed.” Id. “The Act confers upon the district court a wide scope of\\n\\ndiscretion to determine the proper relief due an injured party.” Burger King Corp.\\n\\nv. Mason, 855 F.2d 779, 781 (11th Cir. 1988) (per curiam). An accounting of a\\n\\ndefendant’s profits is appropriate where: (1) the defendant’s conduct was willful\\n\\nand deliberate, (2) the defendant was unjustly enriched, or (3) it is necessary to\\n\\n\\n 15\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 16 of 19\\n\\n\\ndeter future conduct. Howard Johnson Co., Inc. v. Khimani, 892 F.2d 1512, 1521\\n\\n(11th Cir. 1990). Conduct is willful if the infringer was “knowingly and\\n\\ndeliberately cashing in upon the good will of [the infringed].” Burger King, 855\\n\\nF.3d at 781.\\n\\n The district court concluded that Velex willfully infringed on PlayNation’s\\n\\ntrademark based solely on Velex’s continued sale of its Gorilla Gym products after\\n\\nit was served with PlayNation’s complaint. The district court reasoned that\\n\\nPlayNation’s complaint put Velex’s on notice that it was allegedly infringing on\\n\\nPlayNation’s trademark. But when it received PlayNation’s complaint, Velex had\\n\\na valid registered trademark on Gorilla Gym. PlayNation did not obtain a\\n\\npreliminary injunction, and at the time, no court had adjudicated whether Velex\\n\\nwas infringing on PlayNation’s trademark.\\n\\n Under the district court’s construction of willfulness, a valid trademark\\n\\nholder risks losing all of its profits if it does not immediately cease selling its\\n\\ntrademarked product upon receiving a complaint indicating it may be violating the\\n\\nlaw. The district court determined that at the time Velex obtained its trademark,\\n\\nVelex did not intend to infringe on PlayNation’s trademark. And from the time\\n\\nVelex obtained its trademark to the time the district court made its final\\n\\ndetermination, there was no further adjudication that Velex was infringing. This\\n\\ncontinued sale under the color of a valid federal trademark cannot alone establish\\n\\n\\n 16\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 17 of 19\\n\\n\\nwillfulness. See cf. Maltina Corp. v. Cawy Bottling Co., Inc., 613 F.2d 582, 587\\n\\n(5th Cir. 1980) (finding willfulness that justified an accounting of profits where the\\n\\ninfringer used the infringing mark after the patent office refused to register it based\\n\\non the confusing similarity of the plaintiff’s registered mark).\\n\\n There may have been other evidence of willfulness, but the district court did\\n\\nnot rely on it in its decision. The district court also relied solely on the willfulness\\n\\ntheory to support its accounting of profits. The other two theories for supporting\\n\\nan accounting of profits, deterrence and unjust enrichment, do not depend “upon a\\n\\nhigher showing of culpability on the part of defendant, who is purposely using the\\n\\ntrademark.” Burger King, 855 F.2d at 781. Remand is appropriate so that the\\n\\ndistrict court may consider whether other evidence of willfulness exists and\\n\\nwhether those alternative theories support an accounting of profits.\\n\\n B. Cancelling Trademark Registration\\n\\n District courts have discretion to order the cancelation of a federal trademark\\n\\nregistration in whole or in part. 15 U.S.C. § 1119. Cancelling a trademark\\n\\nregistration is appropriate where the plaintiff shows (1) that it had standing to\\n\\npetition for cancellation because it was likely to be damaged by the infringer’s\\n\\ncontinued use of the infringing mark, and (2) that there were valid grounds for\\n\\ndiscontinuing registration. Coach House Rest., Inc. v. Coach & Six Rests., Inc.,\\n\\n934 F.2d 1551, 1557 (11th Cir. 1991). PlayNation’s federal registration of its mark\\n\\n\\n 17\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 18 of 19\\n\\n\\nsatisfies the first element. See id. at 1557–58. PlayNation must show only the\\n\\nsecond element—a valid ground for cancelling registration.\\n\\n If the “mark at issue has been on the federal Principal Register in registrant’s\\n\\nname for less than five years, the mark may be cancelled if petitioner can prove\\n\\nthat the registration should have been barred in the first instance under Lanham Act\\n\\n§ 2.” Id. at 1558. “In order to cancel a registration under Lanham Act Section\\n\\n2(d) in this case, petitioner must prove . . . that the registered mark is likely to\\n\\ncause confusion when used in connection with the services of registrant.” Id. at\\n\\n1559. Establishing trademark infringement thus satisfies the second cancellation\\n\\nrequirement.\\n\\n Having concluded that Velex infringed on PlayNation’s trademark, it was\\n\\nnot an abuse of discretion for the district court to cancel Velex’s trademark\\n\\nregistration.\\n\\n IV. Conclusion\\n\\n The district court did not clearly err in holding that Velex infringed on\\n\\nPlayNation’s trademark. The district court similarly did not err in canceling\\n\\nVelex’s trademark registration on that basis. But the district court did abuse its\\n\\ndiscretion in holding that PlayNation was entitled to an accounting of Velex’s\\n\\nprofits due to willful infringement based solely on Velex’s continued lawful use of\\n\\nits mark after Velex was served with the complaint in this action. As a result, we\\n\\n\\n 18\\n\\f Case: 17-15226 Date Filed: 05/21/2019 Page: 19 of 19\\n\\n\\nvacate the district court’s judgment on that issue, and remand for further\\n\\nproceedings consistent with this opinion.\\n\\n AFFIRMED IN PART, VACATED AND REMANDED IN PART.\\n\\n\\n\\n\\n 19\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2286,"cells":{"id":{"kind":"number","value":4621977,"string":"4,621,977"},"name":{"kind":"string","value":"Willie B. SMITH, III, Petitioner - Appellant, v. COMMISSIONER, ALABAMA DEPARTMENT OF CORRECTIONS, Respondent - Appellee."},"name_abbreviation":{"kind":"string","value":"Willie B. Smith, III v. Commissioner, Alabama Department of Corrections"},"decision_date":{"kind":"string","value":"2019-05-22"},"docket_number":{"kind":"string","value":"17-15043"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wilson, Martin, Jordan\", \"parties\": \"\", \"opinions\": [{\"author\": \"WILSON, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-15043 Date Filed: 05/22/2019 Page: 1 of 31\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15043\\n ________________________\\n\\n D.C. Docket No. 2:13-cv-00557-RDP\\n\\n\\n\\nWILLIE B. SMITH, III,\\n\\n Petitioner - Appellant,\\n\\nversus\\n\\nCOMMISSIONER, ALABAMA DEPARTMENT OF CORRECTIONS,\\n\\n Respondent - Appellee.\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Alabama\\n ________________________\\n\\n (May 22, 2019)\\n\\nBefore WILSON, MARTIN, and JORDAN, Circuit Judges.\\n\\nWILSON, Circuit Judge:\\n\\n Willie B. Smith III, a death row inmate, appeals the district court’s denial of\\n\\nhis 28 U.S.C. § 2254 habeas corpus petition. The district court granted Smith a\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 2 of 31\\n\\n\\ncertificate of appealability (COA) on whether he is intellectually disabled and thus\\n\\nineligible for the death penalty under Atkins v. Virginia, 536 U.S. 304 (2002). We\\n\\ngranted Smith’s request to expand the COA to include whether the prosecutor at\\n\\nSmith’s state trial struck jurors on the basis of gender, race, and national origin in\\n\\nviolation of the Sixth and Fourteenth Amendments under Batson v. Kentucky, 476\\n\\nU.S. 79 (1986), and J.E.B. v. Alabama, 511 U.S. 127 (1994). After careful review\\n\\nof the record and with the benefit of oral argument, we affirm the district court’s\\n\\ndenial of habeas relief.\\n\\n\\n I. Factual and Procedural Background\\n\\n In 1992, an Alabama jury found Smith guilty of capital murder. By a 10-2\\n\\nvote, the jury recommended that Smith be sentenced to death, which the court\\n\\nimposed.\\n\\n A. Jury Selection and Batson Hearing\\n\\n During jury selection in Smith’s trial, the state prosecutor used 14 of his 15\\n\\nperemptory strikes on women. The prosecutor also struck several black venire\\n\\nmembers and the sole Hispanic venire member. Smith’s counsel objected, arguing\\n\\nthat the prosecutor was discriminating on the basis of gender, race, and national\\n\\norigin. The state trial court held that Smith failed to make a prima facie showing\\n\\nof discrimination, and the trial proceeded. The ultimate jury was comprised of five\\n\\nwomen and seven men.\\n\\n 2\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 3 of 31\\n\\n\\n On direct appeal, the Alabama Court of Criminal Appeals (Alabama CCA)\\n\\nfound that Smith had provided sufficient evidence for a prima facie showing of\\n\\ngender-based discrimination under J.E.B. v. Alabama, 511 U.S. 127 (1994). See\\n\\nSmith v. State, 698 So. 2d 1166, 1169 (Ala. Crim. App. 1997). The Alabama CCA\\n\\nremanded the case for a hearing so that the prosecutor could present his reasons for\\n\\nthe strikes.\\n\\n On remand, the prosecutor offered explanations for each strike; those\\n\\nexplanations included employment, marital status, age, knowledge of criminal law,\\n\\nand work with various churches and religious groups. At the hearing, the\\n\\nprosecutor explained:\\n\\n I struck a lot of these [venire members] because they\\n worked in the church; Sunday School teachers and Sunday\\n School leaders, and things of that nature, and . . . I knew\\n the defense counsel, if it came to the second phase of the\\n sentencing hearing, would be asking the jurors to show\\n mercy. And, it was my opinion that this argument would\\n be receptive to someone who worked in the church and\\n was well versed in the Bible more than someone who was\\n not; be a female or male juror that was a strong worker in\\n the church. No male jurors that was [sic] left seated on the\\n jury worked in the church.\\n\\nIn response, Smith’s counsel argued that the prosecution did not strike everyone\\n\\nwho had religious affiliations 1 and questioned why the prosecution had not asked\\n\\n\\n1\\n At the hearing, Smith’s counsel did not identify any men with religious affiliations who were\\nnot struck by the prosecution. Smith’s counsel identified one woman, Ms. Parham, who may\\n\\n\\n 3\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 4 of 31\\n\\n\\nany follow-up questions about the venire members’ religious beliefs. Next, the\\n\\nprosecutor explained that he eliminated the sole Hispanic venire member because\\n\\nshe was young and did not respond to questions during voir dire; Smith’s counsel\\n\\nargued this explanation was insufficient.\\n\\n The state trial court ultimately found that the prosecutor’s reasons for\\n\\nstriking the female venire members were gender neutral, that those reasons were\\n\\ncredible, and that Smith had failed to prove that the prosecutor had acted in a\\n\\ndiscriminatory manner. On appeal after remand, the Alabama CCA affirmed.\\n\\nSmith v. State, 838 So. 2d 413 (Ala. Crim. App. 2002) (hereinafter Smith II). The\\n\\nSupreme Court denied Smith’s petition for writ of certiorari. Smith v. Alabama,\\n\\n537 U.S. 1090 (2002).\\n\\n B. Smith’s Post-Conviction Hearings\\n\\n Smith then filed a petition for state post-conviction relief under Alabama\\n\\nRule of Criminal Procedure 32. The petition included a claim of intellectual\\n\\ndisability, and the Rule 32 court conducted an evidentiary hearing on this claim.\\n\\n At the hearing, Dr. Salekin, Smith’s expert, testified that Smith scored a 64\\n\\non a full IQ test and exhibited adaptive deficits in several areas. Dr. Salekin also\\n\\n\\nhave worked in a church but was not struck by the prosecution. In later briefing at the trial court,\\nSmith identified John Hall, who served as a football coach for the Young Men’s Christian\\nAssociation (YMCA), but was not struck by the prosecution. Finally, in his appellate briefing,\\nSmith raised “Mr. Johnson,” an unidentified male member of the venire who stated that he\\nserved on his church’s board, but was not struck by the prosecution.\\n\\n\\n 4\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 5 of 31\\n\\n\\ntestified, however, that Smith scored relatively well on a separate test that assessed\\n\\nSmith’s language, reading, and mathematics skills, and that these particular results\\n\\nwere inconsistent with a diagnosis of intellectual disability. Dr. Salekin’s final\\n\\nopinion was that Smith was not intellectually disabled. Dr. Salekin also testified\\n\\nthat there was no national medical consensus on using the “Flynn Effect” to adjust\\n\\nIQ scores.2\\n\\n The state called Dr. King, who testified that Smith scored a 72 on a full IQ\\n\\ntest, including verbal score of 75 and nonverbal score of 74.3 Smith’s score on the\\n\\nverbal portion of Dr. King’s IQ test matched a previous score he achieved on the\\n\\nverbal portion of a partial IQ test administered by Dr. Blotcky, a court-appointed\\n\\npsychologist.4 Like Dr. Salekin, Dr. King’s final opinion was that Smith was not\\n\\nintellectually disabled, and he agreed that there was no national medical consensus\\n\\non using the Flynn Effect to adjust IQ scores.\\n\\n The Rule 32 court denied Smith’s Rule 32 petition, and the Alabama CCA\\n\\naffirmed. Smith v. State, 112 So. 3d 1108 (Ala. Crim. App. 2012) (Smith III), cert.\\n\\ndenied, Ex parte Smith, 112 So. 3d 1152 (Ala. 2012).\\n\\n C. Further Procedural History\\n\\n\\n\\n2\\n The “Flynn Effect” is a theory that contends that IQ scores have been increasing over time and\\nsuggests that IQ scores should be recalibrated in order to reflect this increase.\\n3\\n Dr. King also testified that, using a standard error of measurement, Smith’s IQ could have been\\nas low as 68 or as high as 77.\\n4\\n Dr. Blotcky never administered a full IQ test, for reasons that remain unexplained.\\n 5\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 6 of 31\\n\\n\\n Smith filed his original federal habeas petition in the Northern District of\\n\\nAlabama, which the district court denied. One day after denying Smith’s petition,\\n\\nthe district court reopened the action for the sole purpose of considering the effect,\\n\\nif any, of Moore v. Texas, 137 S. Ct. 1039 (2017), on Smith’s Atkins claim. After\\n\\nsupplemental briefing, the district court concluded that Moore did not apply\\n\\nretroactively and reaffirmed the denial of Smith’s petition. The district court\\n\\ngranted Smith a COA on his Atkins claim, and we granted him a COA on his\\n\\nBatson claim.\\n\\n II. Standard of Review\\n\\n We review de novo the district court’s denial of a 28 U.S.C. § 2254 petition.\\n\\nWard v. Hall, 592 F.3d 1144, 1155 (11th Cir. 2010). Because Smith filed his\\n\\npetition after April 24, 1996, this appeal is governed by the Antiterrorism and\\n\\nEffective Death Penalty Act of 1996 (AEDPA). AEDPA “establishes a highly\\n\\ndeferential standard for reviewing state court judgments.” Parker v. Sec’y, Dep’t.\\n\\nof Corr., 331 F.3d 764, 768 (11th Cir. 2003). Under AEDPA, a federal court may\\n\\nonly grant a writ of habeas corpus if the state court’s determination of a federal\\n\\nclaim was (1) “contrary to, or involved an unreasonable application of, clearly\\n\\nestablished Federal law” or (2) “was based on an unreasonable determination of\\n\\nthe facts in light of the evidence presented in the State court proceeding.” 28\\n\\nU.S.C. § 2254(d).\\n\\n\\n 6\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 7 of 31\\n\\n\\n The phrase “clearly established Federal law” encompasses only the holdings\\n\\nof the Supreme Court of the United States “as of the time of the relevant state-court\\n\\ndecision.” Williams v. Taylor, 529 U.S. 362, 412 (2000). Section 2254(d)\\n\\nprovides two separate bases for reviewing state court decisions—“the ‘contrary to’\\n\\nand ‘unreasonable application’ clauses articulate independent considerations a\\n\\nfederal court must consider.” Maharaj v. Sec’y, Dep’t of Corr., 432 F.3d 1292,\\n\\n1308 (11th Cir. 2005).\\n\\n A state court’s determination is “contrary to” clearly established federal law\\n\\n“if the state court arrives at a conclusion opposite to that reached by [the Supreme\\n\\nCourt] on a question of law or if the state court decides a case differently than [the\\n\\nSupreme Court] has on a set of materially indistinguishable facts.” Williams, 529\\n\\nU.S. at 413. A state court’s determination is “an unreasonable application” of\\n\\nclearly established federal law “if the state court identifies the correct governing\\n\\nlegal principle from [the Supreme Court’s] decisions but unreasonably applies that\\n\\nprinciple to the facts of the prisoner’s case.” Id. Reasonableness is objective, and\\n\\na federal court may not issue a writ of habeas corpus simply because it concludes\\n\\nin its independent judgment that the state court was incorrect. Id. at 410.\\n\\n Finally, under § 2254(d)(2), we presume that the state court’s findings of\\n\\nfact are correct unless rebutted by clear and convincing evidence. See 28 U.S.C. §\\n\\n2254(e)(1). “This deference requires that a federal habeas court more than simply\\n\\n\\n 7\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 8 of 31\\n\\n\\ndisagree with the state court before rejecting its factual determinations. Instead, it\\n\\nmust conclude that the state court’s findings lacked even fair support in the\\n\\nrecord.” Rose v. McNeil, 634 F.3d 1224, 1241 (11th Cir. 2011) (citations omitted).\\n\\n\\n III. Atkins Claim\\n\\n Smith first argues that the district court erred in holding that the Supreme\\n\\nCourt’s recent holding in Moore v. Texas did not apply retroactively to his\\n\\nintellectual disability claim. We agree with the district court that Moore is not\\n\\nretroactive. Smith also argues that the Alabama state courts unreasonably applied\\n\\nAtkins v. Virginia in evaluating his intellectual disability claim. After careful\\n\\nreview of the state court record and its order, we hold that the state court’s denial\\n\\nof his intellectual disability claim was not an unreasonable application of clearly\\n\\nestablished federal law.\\n\\n A. The Non-Retroactivity of Moore v. Texas\\n\\n In Atkins v. Virginia, the predecessor to Moore, the Supreme Court held that\\n\\nthe execution of individuals with intellectual disabilities violated the Eighth\\n\\nAmendment. 536 U.S. 304 (2002). But the Court did not define what it means to\\n\\nbe intellectually disabled, leaving that task to individual state legislatures and\\n\\ncourts. Id. at 317. In the years following Atkins, states developed different criteria\\n\\nfor assessing intellectual disability. Some states delineated a bright line threshold\\n\\nfor IQ scores, while others did not.\\n\\n 8\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 9 of 31\\n\\n\\n In Hall v. Florida, the Court clarified that a state court’s intellectual\\n\\ndisability determination should be “informed by the medical community's\\n\\ndiagnostic framework.” 572 U.S. 701, 721 (2014). This meant, among other\\n\\nthings, that courts must consider the standard error inherent in IQ tests when a\\n\\ndefendant’s test scores put him “within the clinically established range for\\n\\nintellectual-functioning deficits.” Moore, 137 S. Ct. at 1050; see also Hall, 572\\n\\nU.S. at 723. In those cases, defendants must be allowed to present additional\\n\\nevidence of intellectual disability, including testimony on adaptive deficits. Hall,\\n\\n572 U.S. at 723.\\n\\n In Moore, the Court expanded on Hall, reiterating that state courts do not\\n\\nhave “unfettered discretion” in their determination of whether a capital defendant\\n\\nis intellectually disabled. 137 S. Ct. at 1052. Specifically, Moore established that\\n\\nstates cannot disregard current clinical and medical standards in assessing whether\\n\\na capital defendant is intellectually disabled. In addition, the Court clarified that\\n\\nunder prevailing clinical standards, the focus of the adaptive functioning inquiry\\n\\nshould be an individual’s adaptive deficits—not adaptive strengths. Id. at\\n\\n1050−51. After Moore, states cannot “weigh” an individual’s adaptive strengths\\n\\nagainst his adaptive deficits.\\n\\n Because Moore was decided five years after the Alabama state courts\\n\\ndecided Smith’s Atkins claim, he concedes that Moore could not have been “clearly\\n\\n\\n 9\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 10 of 31\\n\\n\\nestablished Federal law” at that time. Smith instead argues that Moore announced\\n\\na new rule of constitutional law that should be applied retroactively under Teague\\n\\nv. Lane, 489 U.S. 288 (1989).\\n\\n New constitutional rules are generally not retroactive for cases on federal\\n\\nhabeas review. See id. To determine whether a rule is retroactive, we first decide\\n\\nif it is a new rule. Under Teague, “a case announces a new rule when it breaks\\n\\nnew ground or imposes a new obligation on the States or the Federal Government,”\\n\\nor when “the result was not dictated by [prior] precedent.” Id. at 301.\\n\\n If the rule is indeed new, we then decide whether it falls into one of\\n\\nTeague’s two exceptions to the general bar on retroactivity. The first exception is\\n\\nfor substantive rules of constitutional law that place an entire category of primary\\n\\nconduct beyond the reach of the criminal law, including “rules prohibiting a certain\\n\\ncategory of punishment for a class of defendants because of their status or\\n\\noffense.” See Penry v. Lynaugh, 492 U.S. 302, 330 (1989). The second exception\\n\\nis for “watershed rules of criminal procedure” that are necessary to the\\n\\nfundamental fairness of criminal proceedings. Teague, 489 U.S. at 311−12. It is\\n\\ngenerally very difficult to meet the requirements of the second exception. See,\\n\\ne.g., Saffle v. Parks, 494 U.S. 484, 495 (1990) (noting that the rule announced in\\n\\nGideon v. Wainwright, 372 U.S. 335 (1963), illustrates the type of rule meeting\\n\\nthis second exception).\\n\\n\\n 10\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 11 of 31\\n\\n\\n Smith argues that Moore falls under the first Teague exception because\\n\\nMoore announced a new substantive rule of constitutional law that prohibits “a\\n\\ncertain category of punishment for a class of defendants because of their status or\\n\\noffense.” Penry, 492 U.S. at 330. Smith argues that Moore, which requires states\\n\\nto consider the medical community’s current clinical standards to determine\\n\\nintellectual disability, effectively expands the class of people who are ineligible for\\n\\nthe death penalty. Smith argues that Moore’s holding was thus substantive—not\\n\\nprocedural. We disagree.\\n\\n Substantive rules “set forth categorical constitutional guarantees that place\\n\\ncertain criminal laws and punishments altogether beyond the State’s power to\\n\\nimpose,” while procedural rules “are designed to enhance the accuracy of a\\n\\nconviction or sentence by regulating the manner of determining the defendant’s\\n\\nculpability.” Montgomery v. Louisiana, 136 S. Ct. 718, 729–30 (2016) (internal\\n\\nquotation marks omitted). For example, rules that “allocate decisionmaking\\n\\nauthority” between judge and jury, or “regulate the evidence that the court could\\n\\nconsider in making its decision” are procedural. Welch v. United States, 136 S. Ct.\\n\\n1257, 1265 (2016).\\n\\n Moore established that states cannot disregard current clinical and medical\\n\\nstandards in assessing whether a capital defendant is intellectually disabled.\\n\\nMoore effectively narrowed the range of permissible methods—the procedure—\\n\\n\\n 11\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 12 of 31\\n\\n\\nthat states may use to determine intellectual disability. While Moore may have the\\n\\neffect of expanding the class of people ineligible for the death penalty, it merely\\n\\ndefined the appropriate manner for determining who belongs to that class of\\n\\ndefendants ineligible for the death penalty. Moore thus announced a new rule, but\\n\\nit is procedural, not substantive.5\\n\\n Because Moore announced a procedural rule, it can only be retroactive if it\\n\\nmeets Teague’s second exception. Doing so is extraordinarily rare. See, e.g.,\\n\\nSchriro v. Summerlin, 542 U.S. 348, 351–52 (2004). “To fall within this\\n\\nexception, a new rule must meet two requirements: Infringement of the rule must\\n\\n\\n\\n\\n5\\n In Kilgore v. Secretary, Florida Department of Corrections, this Court held that Hall is not a\\nsubstantive rule under Teague. 805 F.3d 1301, 1314 (11th Cir. 2015) (relying on In re Henry,\\n757 F.3d 1151, 1161 (11th Cir. 2014)). Alabama argues that we should rely on Kilgore’s\\nreasoning to conclude that Moore is likewise not a substantive rule under Teague. We decline to\\ndo so because the Supreme Court’s decision in Montgomery v. Louisiana undermined a core\\ncomponent of Kilgore’s retroactivity analysis, which Kilgore borrowed from In re Henry. In\\nKilgore, we reasoned that Hall was not substantive under Teague because it “guaranteed only a\\nchance to present evidence, not ultimate relief.” Kilgore, 805 F.3d at 1314; see also In re Henry,\\n757 F.3d at 1161. But Montgomery later deemed a rule substantive in nature—the rule of Miller\\nv. Alabama, 567 U.S. 460 (2012), which prohibited mandatory life without parole sentences for\\njuveniles—even though all that rule guaranteed was “[a] hearing where ‘youth and its attendant\\ncharacteristics’ are considered as sentencing factors,” not a shorter sentence or parole.\\nMontgomery, 136 S. Ct. at 735 (quoting Miller, 567 U.S. at 465). Montgomery thus stands for\\nthe proposition that a right can be substantive under Teague even if it only guarantees the chance\\nto present evidence in support of relief sought, not ultimate relief itself. See, e.g., In re Sapp,\\n827 F.3d 1334, 1340–41 (11th Cir. 2016) (Jordan, Rosenbaum, and Jill Pryor, JJ., concurring).\\nBecause Montgomery undermined the reasoning of Kilgore and In re Henry, we do not rely on\\nthem to reach our decision. See Chambers v. Thompson, 150 F.3d 1324, 1326 (11th Cir. 1998);\\nsee also Davis v. Singletary, 119 F.3d 1471, 1482 (11th Cir. 1997) (“To the extent of any\\ninconsistency between [our prior] pronouncements and the Supreme Court’s supervening ones,\\nof course, we are required to heed those of the Supreme Court.”).\\n\\n\\n 12\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 13 of 31\\n\\n\\nseriously diminish the likelihood of obtaining an accurate conviction [or sentence],\\n\\nand the rule must alter our understanding of the bedrock procedural elements\\n\\nessential to the fairness of a proceeding.” Tyler v. Cain, 533 U.S. 656, 665 (2001)\\n\\n(quotation omitted).\\n\\n Only Gideon v. Wainwright, 372 U.S. 335 (1963), which extended the right\\n\\nto counsel to criminal defendants, has been declared the kind of procedural rule\\n\\nthat altered the “bedrock procedural elements” essential to the fairness of a\\n\\nproceeding. See Beard v. Banks, 542 U.S. 406, 416−18 (2004) (noting that\\n\\nGideon’s holding was sweeping and broke with past precedent). The Supreme\\n\\nCourt has continually rejected retroactivity under Teague’s second exception for\\n\\nprocedural rules that do not have the “primacy” or “centrality” of Gideon. See,\\n\\ne.g., Wharton v. Bocking, 549 U.S. 406, 421 (2007) (rejecting retroactivity for\\n\\nCrawford v. Washington, 541 U.S. 36 (2004)); Schriro, 542 U.S. at 356−58\\n\\n(rejecting retroactivity for Ring v. Arizona, 546 U.S. 584 (2002)). Both Crawford 6\\n\\nand Ring7 were important holdings for the rights of criminal defendants, and yet\\n\\n\\n\\n\\n6\\n In Crawford v. Washington, 541 U.S. 36 (2004), the Supreme Court held that the Sixth\\nAmendment’s Confrontation Clause prohibits the state from introducing testimonial hearsay as\\nevidence against criminal defendants unless the declarant is unavailable and the defendant had a\\nprior opportunity to cross-examine the declarant.\\n7\\n In Ring v. Arizona, 536 U.S. 584 (2002), the Supreme Court held that the Sixth Amendment\\nguarantees criminal defendants the right to have a jury, not a sentencing judge, find the\\naggravating circumstances necessary for the imposition of the death penalty.\\n 13\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 14 of 31\\n\\n\\nthe Supreme Court held that neither altered the bedrock procedural elements\\n\\nessential to the fairness of a criminal proceeding, and thus neither was retroactive.\\n\\n Similarly, Moore is an important development. It provides guidance to\\n\\nstates attempting to comply with Atkins. But we cannot say that Moore altered the\\n\\nbedrock procedural elements essential to the fairness of a criminal proceeding in\\n\\nthe way that the Gideon rule did. Because Moore cannot meet the requirements of\\n\\nTeague’s second exception, it cannot be applied retroactively.\\n\\n B. Analysis of Smith’s Atkins Claim\\n\\n Smith argues that, even if Moore is not retroactive, the Alabama courts\\n\\nunreasonably applied Atkins v. Virginia to his intellectual disability claim.\\n\\n 1. The State Court Record\\n\\n Shortly after Atkins, the Alabama Supreme Court held that to be\\n\\nintellectually disabled under Atkins, a defendant must prove by a preponderance of\\n\\nthe evidence: (1) “significantly subaverage intellectual functioning (an IQ of 70 or\\n\\nbelow),” (2) “significant or substantial deficits in adaptive behavior,” and (3) that\\n\\nboth the subaverage intellectual functioning and the deficits in adaptive\\n\\nfunctioning manifested before the age of eighteen. Ex Parte Perkins, 851 So. 2d\\n\\n453, 456 (Ala. 2002).\\n\\n Smith raised his Atkins claim in his Rule 32 petition shortly after Perkins.\\n\\nThe Rule 32 court ultimately denied his petition, finding it relevant, but not\\n\\n\\n 14\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 15 of 31\\n\\n\\ndispositive, that no expert—not even Smith’s own expert—testified that Smith was\\n\\nintellectually disabled. The court then evaluated the Perkins factors and concluded\\n\\nthat Smith failed to prove by a preponderance of the evidence that he was\\n\\nintellectually disabled.\\n\\n First, the court determined that Smith failed to satisfy his burden of showing\\n\\nsignificantly subaverage intellectual functioning. The court noted that the experts\\n\\nhad presented conflicting evidence and testimony: Dr. Salekin reported that Smith\\n\\nhad an IQ of 64, while Dr. King reported an IQ of 72. The court ultimately\\n\\ncredited Dr. King’s IQ score as “probably more accurate” than Dr. Salekin’s score\\n\\nin part because Dr. King’s test resulted in a verbal IQ of 75, the same verbal IQ\\n\\nthat Smith received on a prior IQ test. The court also declined to adjust Smith’s IQ\\n\\nscores downward because the experts all testified that there was no national\\n\\nmedical consensus on using the Flynn Effect to adjust IQ scores.\\n\\n On the second Perkins prong, the court determined that Smith failed to\\n\\nsatisfy his burden of showing significant deficits in adaptive behavior. The court\\n\\nconcluded that, “[a]lthough [Smith] showed deficits in adaptive functioning based\\n\\nupon test results,” Smith did not show many deficits in his adaptive functioning “in\\n\\neveryday life” either before or after his crime. The court noted that Smith showed\\n\\nrelatively normal scores in functional academics and communication. And while\\n\\nhe did have some possible deficiencies, the court reasoned that those deficits were\\n\\n\\n 15\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 16 of 31\\n\\n\\nnot so significant that Smith could not succeed in school, work, or society in\\n\\ngeneral. The court also indicated that Smith’s ability to plan and conceal his crime\\n\\n“weigh[ed] against [him] in relation to the adaptive functioning requirement.”\\n\\n On appeal, the Alabama CCA affirmed, holding that the Rule 32 court did\\n\\nnot abuse its discretion in concluding that Smith had failed to prove that he was\\n\\nintellectually disabled. Smith III, 112 So. 3d at 1108. As the Alabama CCA\\n\\nsummarized, “[t]he greater weight of the evidence indicated that, although he\\n\\nsuffered with some mental deficiencies, they did not rise to the level at which an\\n\\nimpartial mind would conclude from the evidence that he was mentally retarded.”\\n\\nId. at 1130.\\n\\n As to intellectual functioning, the Alabama CCA found that the Rule 32\\n\\ncourt did not err in declining to apply the Flynn Effect or standard error to Smith’s\\n\\nIQ score. Id. at 1131. The Alabama CCA also endorsed the Rule 32 court’s\\n\\napproach to examining adaptive functioning, explaining that “[e]ven where there\\n\\nare indications of shortfalls in adaptive behavior, other relevant evidence may\\n\\nweigh against an overall finding of deficiency.” Id. at 1133. Because the Alabama\\n\\nCCA found that Smith failed to prove both significantly subaverage intellectual\\n\\nfunctioning and significant deficits in adaptive behavior, the court did not fully\\n\\naddress the third prong of Perkins—whether those shortfalls in intellectual and\\n\\nadaptive functioning had manifested before the age of eighteen.\\n\\n\\n 16\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 17 of 31\\n\\n\\n 2. Analysis Under 28 U.S.C. § 2254(d)(1)\\n\\n Smith argues that the Alabama state courts unreasonably applied Atkins v.\\n\\nVirginia to his intellectual disability claim by (1) determining that Smith’s IQ\\n\\nscores did not meet the standard for intellectual disability, (2) failing to consider\\n\\nthe standard error and Flynn Effect in assessing Smith’s IQ scores, and (3) giving\\n\\nmore weight to Smith’s adaptive strengths than to his adaptive deficits in assessing\\n\\nhis adaptive functioning.\\n\\n A state court’s determination is an unreasonable application of clearly\\n\\nestablished federal law “if the state court identifies the correct governing legal\\n\\nprinciple from this Court’s decisions but unreasonably applies that principle to the\\n\\nfacts of the [petitioner’s] case.” Williams v. Taylor, 529 U.S. 362, 413 (2000).\\n\\nThe difficulty for Smith—and other litigants mounting this challenge—is that\\n\\nAtkins set forth few legal governing principles for lower courts and states\\n\\nevaluating intellectual disability. The Supreme Court’s decision in Atkins did not\\n\\ndefine what it means to be intellectually disabled, instead leaving that task to the\\n\\nstates. See Atkins, 536 U.S. at 317. The Supreme Court itself recently explained\\n\\nthat “Atkins gave no comprehensive definition of ‘mental retardation’ for Eighth\\n\\nAmendment purposes.” Shoop v. Hill, 139 S. Ct. 504, 507 (2019).\\n\\n i. Intellectual Functioning\\n\\n\\n\\n\\n 17\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 18 of 31\\n\\n\\n Smith first argues that the Alabama state courts unreasonably applied Atkins\\n\\nv. Virginia by refusing to credit Dr. Salekin’s testimony that Smith had an IQ of 64\\n\\nand consequently determining that Smith’s IQ scores did not satisfy the first\\n\\nPerkins prong of subaverage intellectual functioning. According to Smith, “[t]he\\n\\nrefusal to use the IQ score of 64 in an average with the other scores, or otherwise\\n\\ndiscount [Dr. King’s] score of 72 based on the IQ score of 64, was an unreasonable\\n\\napplication of Atkins to the present case.” 8 Smith also argues it was an\\n\\nunreasonable application of Atkins to refuse to account for the Flynn Effect or\\n\\nstandard error when the state court evaluated Smith’s IQ.\\n\\n But Atkins did not set forth clearly established federal law on how states\\n\\nmust evaluate IQ scores in determining intellectual disability. “Atkins did not\\n\\ndefine intellectual disability, nor did it direct the states on how to define\\n\\nintellectual disability, nor, finally, did it provide the range of IQ scores that could\\n\\nbe indicative of intellectual disability.” Kilgore v. Sec’y, Fla. Dep’t of Corr., 805\\n\\n\\n\\n8\\n In his initial brief, Smith does not argue that the Alabama court’s decision to refuse to fully\\ncredit Dr. Salekin’s IQ score was an unreasonable determination of the facts under 28 U.S.C.\\n§ 2254(d)(2). Smith raises this argument only in his reply brief. We generally do not consider\\nissues and arguments raised for the first time in an appellant’s reply brief. See, e.g., United\\nStates v. Levy, 379 F.3d 1241, 1244 (11th Cir. 2004). In any event, it is unlikely that the state\\ncourt made an unreasonable factual determination in crediting Dr. King’s score over Dr.\\nSalekin’s score. While we agree that it might have been preferable to average both IQ scores\\nunder these circumstances, “a state-court factual determination is not unreasonable merely\\nbecause the federal habeas court would have reached a different conclusion in\\nthe first instance.” Wood v. Allen, 558 U.S. 290, 301 (2010). Here, the state court used an\\nadditional IQ score in the record—albeit a partial score—to corroborate Dr. King’s test. We\\ncannot say that the decision to do so was an unreasonable factual determination.\\n 18\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 19 of 31\\n\\n\\nF.3d 1301, 1311 (11th Cir. 2015); see also Bobby v. Bies, 556 U.S. 825, 831 (2009)\\n\\n(“[Atkins] did not provide definitive procedural or substantive guides for\\n\\ndetermining when a person who claims [intellectual disability] will be so impaired\\n\\nas to fall within [Atkins’ compass]” (internal citation and quotation marks\\n\\nomitted)). Without clear guidance from Atkins, the state court’s refusal to average\\n\\nIQ scores or to account for certain statistical adjustments was not an unreasonable\\n\\napplication of clearly established federal law.\\n\\n Smith’s specific argument about the state court’s failure to consider the\\n\\nstandard error is foreclosed by our precedent. As we explained in Kilgore,\\n\\n“[n]othing in Atkins suggested that a bright-line IQ cutoff of 70 ran afoul of the\\n\\nprohibition on executing the intellectually disabled.” 805 F.3d at 1312. In other\\n\\nwords, Atkins did not require states to consider the standard error in assessing IQ\\n\\nscores. That requirement did not emerge until Hall v. Florida, 572 U.S. 701\\n\\n(2014), well after the Alabama courts considered Smith’s case.\\n\\n Altogether, Smith’s arguments generally conflate what we have previously\\n\\npermitted in evaluating intellectual disability with what is required. While we\\n\\nhave previously said that the Flynn Effect may be considered in determining a\\n\\ndefendant’s IQ, see Thomas v. Allen, 607 F.3d 749, 753 (11th Cir. 2010), neither\\n\\nthis Court nor the Supreme Court has required courts to do so. Similarly, while we\\n\\nhave previously permitted district courts to average multiple IQ scores, see\\n\\n\\n 19\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 20 of 31\\n\\n\\nHolladay v. Allen, 555 F.3d 1346, 1357−58 (11th Cir. 2009), courts are not\\n\\nnecessarily required to do so.\\n\\n ii. Adaptive Functioning\\n\\n Next, Smith argues that the Alabama courts unreasonably applied Atkins by\\n\\nfavoring Smith’s adaptive strengths over his adaptive deficits. The Supreme Court\\n\\nrecently rejected this argument in Shoop v. Hill, 139 S. Ct. 504 (2019).\\n\\n In Hill v. Anderson, the Sixth Circuit held that Moore’s holding about\\n\\nadaptive strengths was clearly established law because Moore was “merely an\\n\\napplication of what was clearly established by Atkins.” 881 F.3d 483, 487 (6th Cir.\\n\\n2018). But the Supreme Court reversed the Sixth Circuit and soundly rejected this\\n\\nargument in Shoop, explaining that “Atkins did not definitively resolve how [the\\n\\nadaptive functioning prong] was to be evaluated but instead left its application in\\n\\nthe first instance to the State.” 139 S. Ct. at 508. Because Atkins did not provide\\n\\ndefinitive guidance to states on how to evaluate a petitioner’s adaptive functioning,\\n\\nthe Alabama courts here could not have unreasonably applied Atkins in choosing to\\n\\nweigh Smith’s adaptive strengths against his adaptive weaknesses.\\n\\n Smith’s success on this claim is a matter of timing. After Moore v. Texas, it\\n\\nis abundantly clear that states may not weigh a defendant’s adaptive strengths\\n\\nagainst his adaptive deficits. Doing so contradicts the medical community’s\\n\\ncurrent clinical standards. Moore, 137 S. Ct. at 1050−51. As the Supreme Court\\n\\n\\n 20\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 21 of 31\\n\\n\\nexplained in Moore, many individuals with intellectual disabilities have both\\n\\nadaptive deficits and adaptive strengths, and “significant limitations in conceptual,\\n\\nsocial, or practical adaptive skills [are] not outweighed by the potential strengths in\\n\\nsome adaptive skills.” Id. at 1050 (citation omitted).\\n\\n Alabama argues that the state court did not weigh Smith’s adaptive strengths\\n\\nagainst his adaptive deficits. We firmly disagree. Despite concluding that Smith\\n\\n“showed deficits in adaptive functioning based upon test results,” the state court\\n\\nconsidered other factors that weighed against “an overall finding of deficiency,”\\n\\ntreating the adaptive functioning prong like a balancing test. In particular, the state\\n\\ncourt considered Smith’s ability to conceal his crime, ability to take care of his\\n\\nmother, and his scores on certain mathematics and reading tests as adaptive\\n\\nstrengths that outweighed his apparent deficits. This approach was acceptable at\\n\\nthe time. But after Moore, it no longer is.\\n\\n IV. Batson Claim\\n\\n Smith argues that the prosecutor at his state trial struck jurors on the basis of\\n\\ngender and national origin 9 in violation of the Sixth and Fourteenth Amendments.\\n\\n\\n\\n9\\n At the district court, Smith also asserted a race discrimination claim because the prosecutor\\nused five of his peremptory strikes to eliminate black venire members. On appeal, however,\\nSmith makes only vague and passing reference to racial discrimination. Therefore, we address\\nonly his gender and national origin discrimination claims. See Sapuppo v. Allstate Floridian Ins.\\nCo., 739 F.3d 678, 681 (11th Cir. 2014) (noting that “an appellant abandons a claim when he\\neither makes only passing references to it or raises it in a perfunctory manner without supporting\\narguments and authority”).\\n 21\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 22 of 31\\n\\n\\nSee Batson v. Kentucky, 476 U.S. 79 (1986); J.E.B. v. Alabama, 511 U.S. 127\\n\\n(1994). After careful review, we hold that the state court’s denial of Smith’s\\n\\nclaims was not contrary to Batson and its progeny, an unreasonable application of\\n\\nBatson, or an unreasonable determination of the facts in light of the evidence\\n\\npresented to the state courts.\\n\\n A. Clearly Established Law\\n\\n Under the Equal Protection Clause, a criminal defendant has a constitutional\\n\\nright “to be tried by a jury whose members are selected pursuant to\\n\\nnondiscriminatory criteria.” Batson, 476 U.S. at 85–86. In Batson, the Supreme\\n\\nCourt set out a three-part test to “guide trial courts’ constitutional review of\\n\\nperemptory strikes.” Johnson v. California, 545 U.S. 162, 168 (2005). Under the\\n\\nthree-part test,\\n\\n [f]irst, the defendant must make out a prima facie case by\\n showing that the totality of the relevant facts gives rise to\\n an inference of discriminatory purpose. Second . . . the\\n burden shifts to the State to explain adequately the racial\\n exclusion by offering permissible race-neutral\\n justifications for the strikes. Third, if a race-neutral\\n explanation is tendered, the trial court must then\\n decide . . . whether the opponent of the strike has proved\\n purposeful racial discrimination.\\n\\nId. (internal quotation marks, citations, and footnotes omitted). At the first step, a\\n\\ndefendant makes a prima facie case of discrimination if the circumstances allow\\n\\nfor a permissible inference of discrimination. Id. at 162. At the second step, the\\n\\n\\n 22\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 23 of 31\\n\\n\\ncourt evaluates only the “facial validity of the prosecutor’s explanation,” and\\n\\nunless a discriminatory intent is “inherent in the prosecutor’s explanation, the\\n\\nreason offered will be deemed race neutral.” Purkett v. Elem, 514 U.S. 765, 768\\n\\n(1995) (quotation omitted). The third step “involves evaluating the persuasiveness\\n\\nof the justification” proffered by the prosecutor, and “[a]t that stage, implausible or\\n\\nfantastic justifications may (and probably will) be found to be pretexts for\\n\\npurposeful discrimination.” Id. Inconsistent and disparate treatment of venire\\n\\nmembers is evidence that the proffered reasons are post-strike excuses and not\\n\\nlegitimate race or gender-neutral justifications. See, e.g., Snyder v. Louisiana, 552\\n\\nU.S. 472, 483 (2008).\\n\\n The evaluation of a prosecutor’s race-neutral or gender-neutral explanation\\n\\nfor a strike under Batson is a “pure issue of fact . . . peculiarly within a trial judge’s\\n\\nprovince.” McNair v. Campbell, 416 F.3d 1291, 1310 (11th Cir. 2005) (quotation\\n\\nomitted). Even on direct review, a trial judge’s finding on intentional\\n\\ndiscrimination is entitled to “great deference.” See Batson, 476 U.S. at 98 n.21. At\\n\\nthe habeas stage, the burden is even higher; the petitioner must show “it was\\n\\nunreasonable to credit the prosecutor’s race-neutral explanations” under\\n\\n§ 2254(d)(2). Rice v. Collins, 546 U.S. 333, 338 (2006).\\n\\n B. Analysis of Smith’s Batson Claim\\n\\n\\n\\n\\n 23\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 24 of 31\\n\\n\\n Smith argues that the state court’s determination that he failed to prove\\n\\npurposeful discrimination was (1) an unreasonable determination of the facts under\\n\\n28 U.S.C. § 2254(d)(2) and (2) both contrary to and an unreasonable application of\\n\\nBatson and its progeny under 28 U.S.C. § 2254(d)(1). Before we address those\\n\\nclaims, we briefly review the state court record.\\n\\n 1. State Court Record\\n\\n On remand, the prosecutor offered explanations for striking each female\\n\\nvenire member. Those explanations included employment, marital status, age,\\n\\nknowledge of criminal law, and work with various churches and religious groups.\\n\\nIn its order on remand, the state trial court evaluated the prosecutor’s reasoning for\\n\\nstriking each female venire member. The trial court found that the prosecutor’s\\n\\nexplanation for each member was supported by the record. The court confirmed,\\n\\nfor example, that each woman allegedly struck for her religious affiliations stated\\n\\nduring voir dire, or indicated on her questionnaire, that she was active in her\\n\\nchurch or taught Sunday School. The court noted that excluding potential jurors\\n\\nwho were susceptible to mercy arguments was a sound trial strategy. Further,\\n\\nwhere the prosecutor explained a strike based on a venire member’s demeanor, the\\n\\ntrial court corroborated the prosecutor’s explanation with its own trial notes. The\\n\\nstate trial court ultimately held that the prosecutor’s reasons for striking the female\\n\\nvenire members were gender neutral, that those reasons were credible, and that\\n\\n\\n 24\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 25 of 31\\n\\n\\nSmith had failed to prove that the prosecutor had acted in a discriminatory\\n\\nmanner.10\\n\\n On appeal, the Alabama CCA concluded that the trial court’s determination\\n\\nwas not clearly erroneous. Smith II, 838 So. 2d at 436, 466. The Alabama CCA\\n\\nfocused its analysis on four women who, according to the prosecutor, were\\n\\neliminated because of their religious affiliations. The court noted that three of the\\n\\nfour women were Sunday School teachers; the other was a Counselor of Ministry.\\n\\nSee id. at 426−27.\\n\\n The Alabama CCA then acknowledged Smith’s argument that the\\n\\nprosecutor’s stated reason for striking these jurors was pretextual. The court\\n\\nconsidered, for example, Smith’s argument that several women who had been\\n\\neliminated for church involvement had also previously affirmed that their religious\\n\\nbeliefs would not preclude them from imposing a death sentence. The Alabama\\n\\nCCA also considered Smith’s argument that the prosecutor had not asked the\\n\\n\\n\\n\\n10\\n At the end of his order, the state trial court judge also noted that the prosecutor was “certainly\\nnot a person prone to strike minorities denounced in the Batson case and its progeny.” The judge\\nbased this conclusion on his “extensive in court experience with [the prosecutor] and close\\nacquaintanceship with others that know him.” We note that the court’s role in hearing a Batson\\nclaim is to evaluate whether the prosecutor’s stated reasons for excluding members of the jury\\nare credible and supported by the record, not to personally attest to the prosecutor’s character or\\nto provide its own reasons for why the prosecutor could not have discriminated in the present\\ncase. See Adkins v. Warden, Holman CF, 710 F.3d 1241, 1254 & n.11 (11th Cir. 2013)\\n(indicating that, at Batson’s third step, it is improper for the trial court to rely on its personal\\nexperience with and opinion about the reputation of a prosecutor where those facts are not in\\nevidence).\\n 25\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 26 of 31\\n\\n\\nwomen follow-up questions about their religious beliefs before striking them. But\\n\\nafter taking those arguments into account, the court found that Smith had not\\n\\nshown that the trial court’s credibility determination was clearly erroneous. The\\n\\nAlabama CCA thus affirmed the trial court’s finding that the prosecutor’s reasons\\n\\nfor striking the jurors were nondiscriminatory. Id. at 436.\\n\\n 2. Analysis Under 28 U.S.C. § 2254(d)(2)\\n\\n A prosecutor’s motive for striking a juror is a factual issue, Miller-El v.\\n\\nDretke, 545 U.S. 231, 240 (2005), and a state court’s factual findings are presumed\\n\\ncorrect on federal habeas corpus review. 28 U.S.C. §§ 2254(d)(2), (e)(1). In\\n\\nseeking habeas relief, Smith bears the burden of rebutting that presumption by\\n\\n“clear and convincing evidence.” Id. § 2254(e)(1).\\n\\n Smith first argues that he presented a strong prima facie case of gender\\n\\ndiscrimination where the prosecutor used 14 of his 15 strikes to eliminate women\\n\\nfrom the jury. We agree with Smith.11\\n\\n Smith then argues that the state court’s determination that the prosecutor’s\\n\\nreasons for striking the female venire members were nondiscriminatory was an\\n\\nunreasonable determination of the facts, particularly in light of the prosecutor’s\\n\\n\\n11\\n The district court found that Smith presented a relatively weak prima facie case of gender\\ndiscrimination in part because five women ultimately served on Smith’s jury. But the fact that\\nfive women remained on the jury after the prosecutor used nearly all his strikes to eliminate\\nwomen tells us more about the initial composition of the venire pool (and which juror slots in the\\nvenire were filled by women) than it does about the prosecutor’s state of mind.\\n\\n 26\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 27 of 31\\n\\n\\ninconsistent treatment of male and female venire members. Smith concentrates his\\n\\nargument on one man—misidentified in the trial transcript as “Mr. Johnson”—who\\n\\nstated during voir dire that he was a member of his church’s board. 12 The\\n\\nprosecutor did not use a strike on “Johnson,” which Smith argues is evidence that\\n\\nthe prosecutor’s explanation for striking these women was pretextual.\\n\\n In the years following Smith’s trial, no party has been able to determine\\n\\nJohnson’s true identity. Smith was thus unable to provide the state courts with any\\n\\nadditional information about Johnson that might have been used to determine\\n\\nwhether there were meaningful differences between him and the female venire\\n\\nmembers. We do not know Johnson’s other answers during voir dire, information\\n\\nabout his demeanor, or any other potentially relevant factors, such as his\\n\\noccupation. All that we know about Johnson is that he was a board member at his\\n\\nchurch.\\n\\n To succeed under § 2254(d)(2), Smith must show that it was unreasonable\\n\\nfor the state court to credit the prosecutor’s proffered explanations for the strikes.\\n\\nSee Rice, 546 U.S. at 338. Smith has not met this burden. While Smith’s evidence\\n\\nabout Johnson could have supported a finding that the prosecutor’s strikes were\\n\\n\\n\\n\\n12\\n The venire pool for Smith’s trial did not contain any member with the surname of Johnson,\\nand thus we assume this venire member was misidentified in the trial transcript.\\n 27\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 28 of 31\\n\\n\\ndiscriminatory, we do not think it mandated such a finding in light of the limited\\n\\nevidence presented to the state court.\\n\\n The Alabama CCA also grappled with some of Smith’s other arguments for\\n\\npretext. The court considered, for example, that some of the women allegedly\\n\\neliminated because of their church involvement had previously affirmed that their\\n\\nreligious beliefs would not preclude them from imposing the death penalty. But\\n\\nthe state court did not find that factor dispositive. Neither do we. The\\n\\nprosecution’s explanation at the Batson hearing was not that these potential jurors\\n\\nwould be unalterably unwilling to impose the death penalty, but that they would be\\n\\nparticularly receptive to Smith’s counsel’s request for mercy at the penalty phase\\n\\nof the trial. This is an acceptable justification for a peremptory strike.\\n\\n Importantly, the Alabama CCA ultimately affirmed the trial court’s\\n\\ncredibility determination only after noting that the trial court found that (1) the\\n\\nprosecutor’s reasons for striking venire members were supported by the record and\\n\\n(2) the prosecutor’s approach in excluding those who were susceptible to mercy\\n\\narguments was a sound trial strategy. Both factors are relevant in assessing a\\n\\nprosecutor’s credibility. See Miller-El v. Cockrell, 537 U.S. 322, 324 (2003)\\n\\n(“Credibility can be measured by, among other factors, the prosecutor’s demeanor;\\n\\nby how reasonable, or how improbable, the explanations are; and by whether the\\n\\nproffered rationale has some basis in accepted trial strategy.”).\\n\\n\\n 28\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 29 of 31\\n\\n\\n Ultimately, the record before us does not “compel the conclusion that the\\n\\ntrial court had no permissible alternative but to reject the prosecutor’s [gender]-\\n\\nneutral justifications.” Rice, 546 U.S. at 341. Because habeas review does not\\n\\nallow us to “supersede the trial court’s credibility determination” where the record\\n\\ndoes not compel a contrary conclusion, see id. at 341–42, we must deny Smith’s\\n\\nchallenge under § 2254(d)(2).\\n\\n 3. Analysis Under 28 U.S.C. § 2254(d)(1)\\n\\n Next, Smith argues that the state court’s holding was both contrary to Batson\\n\\nand its progeny and an unreasonable application of Batson under 28 U.S.C.\\n\\n§ 2254(d)(1). First, Smith argues that, contrary to Batson’s directive, the Alabama\\n\\nCCA simply accepted the prosecutor’s proffered explanations at face value. We\\n\\ndisagree. The Alabama CCA thoroughly documented the prosecutor’s reasons for\\n\\nstrikes, the trial court’s corroboration of the prosecutor’s stated reasons, and\\n\\nSmith’s arguments for why those reasons were pretextual. Only after conducting\\n\\nthis analysis did the Alabama CCA affirm the trial court’s credibility\\n\\ndetermination.13\\n\\n\\n\\n13\\n We acknowledge that in its opinion, the Alabama CCA did not specifically discuss Johnson.\\nBut the court did analyze whether the prosecutor’s explanation about striking jurors based on\\nchurch affiliation was pretextual. “Under Supreme Court and our Circuit precedent, a state\\ncourt’s written opinion is not required to mention every relevant fact or argument in order for\\nAEDPA deference to apply.” Lee v. Comm’r, Ala. Dep’t of Corr., 726 F.3d 1172, 1223 (11th\\nCir. 2013). Here, we do not think that the Alabama CCA was required to explicitly address\\nSmith’s arguments about Johnson given the limited evidence Smith provided about him.\\n 29\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 30 of 31\\n\\n\\n Next, Smith argues that the Alabama CCA erred in accepting the\\n\\nprosecution’s “arbitrary and vague” reasons for excluding Ms. Ramos, the only\\n\\nHispanic venire member. While Smith is correct that vague explanations may be\\n\\nlegally insufficient to rebut a prima facie case of discrimination, the prosecutor’s\\n\\nproffered reasons for striking Ms. Ramos—her youth and lack of participation in\\n\\nvoir dire—are relatively concrete and permissible14 reasons for exercising a\\n\\nperemptory strike. The trial record supports both explanations. And neither\\n\\nexplanation rises to the level of vagueness that we condemned in United States v.\\n\\nHorsley, 864 F.2d 1543 (11th Cir. 1989), on which Smith relies. 15\\n\\n Finally, Smith argues that it was improper for the trial court to consider its\\n\\nown observations about a venire member’s behavior. It would be improper for a\\n\\njudge to substitute its own reasoning for striking a venire member where the\\n\\nprosecution’s explanations do not suffice. See Dretke, 545 U.S. at 252. But that\\n\\ndid not occur here. On remand, the trial court noted its own observations about\\n\\nvenire members from voir dire, but it did so to corroborate the prosecutor’s own\\n\\nexplanations about a venire member’s demeanor—a method endorsed by the\\n\\nSupreme Court. See Snyder v. Louisiana, 552 U.S. 472, 477 (2008) (“[R]ace-\\n\\n\\n\\n\\n14\\n The Supreme Court has not extended Batson to peremptory challenges based on age. See, e.g.,\\nWeber v. Strippit, Inc., 186 F.3d 907, 911 (8th Cir. 1999), cert. denied, 528 U.S. 1078 (2000).\\n15\\n In United States v. Horsley, we held that a prosecutor’s statement that “I’ve just got a feeling\\nabout [the juror]” was too vague to rebut a prima facie case of discrimination. 864 F.2d at 1544.\\n 30\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 31 of 31\\n\\n\\nneutral reasons for peremptory challenges often invoke a juror’s demeanor\\n\\n(e.g., nervousness, inattention), making the trial court’s firsthand observations of\\n\\neven greater importance. In this situation, the trial court must evaluate . . . whether\\n\\nthe juror’s demeanor can credibly be said to have exhibited the basis for the strike\\n\\nattributed to the juror by the prosecutor.”).\\n\\n In sum, Smith has not established that the state court’s denial of his claims\\n\\nwas contrary to the standard laid out in Batson and its progeny, an unreasonable\\n\\napplication of Batson, or an unreasonable determination of the facts in light of the\\n\\nevidence presented to the state courts. We therefore affirm the district court’s\\n\\ndenial of Smith’s § 2254 petition.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 31\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4399230/\", \"author_raw\": \"WILSON, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILSON"},"judge2":{"kind":"string","value":"MARTIN"},"judge3":{"kind":"string","value":"JORDAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4621977/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Willie B. SMITH, III, Petitioner - Appellant, v. COMMISSIONER, ALABAMA DEPARTMENT OF CORRECTIONS, Respondent - Appellee.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-15043 Date Filed: 05/22/2019 Page: 1 of 31\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-15043\n ________________________\n\n D.C. Docket No. 2:13-cv-00557-RDP\n\n\n\nWILLIE B. SMITH, III,\n\n Petitioner - Appellant,\n\nversus\n\nCOMMISSIONER, ALABAMA DEPARTMENT OF CORRECTIONS,\n\n Respondent - Appellee.\n ________________________\n\n Appeal from the United States District Court\n for the Northern District of Alabama\n ________________________\n\n (May 22, 2019)\n\nBefore WILSON, MARTIN, and JORDAN, Circuit Judges.\n\nWILSON, Circuit Judge:\n\n Willie B. Smith III, a death row inmate, appeals the district court’s denial of\n\nhis 28 U.S.C. § 2254 habeas corpus petition. The district court granted Smith a\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 2 of 31\n\n\ncertificate of appealability (COA) on whether he is intellectually disabled and thus\n\nineligible for the death penalty under Atkins v. Virginia, 536 U.S. 304 (2002). We\n\ngranted Smith’s request to expand the COA to include whether the prosecutor at\n\nSmith’s state trial struck jurors on the basis of gender, race, and national origin in\n\nviolation of the Sixth and Fourteenth Amendments under Batson v. Kentucky, 476\n\nU.S. 79 (1986), and J.E.B. v. Alabama, 511 U.S. 127 (1994). After careful review\n\nof the record and with the benefit of oral argument, we affirm the district court’s\n\ndenial of habeas relief.\n\n\n I. Factual and Procedural Background\n\n In 1992, an Alabama jury found Smith guilty of capital murder. By a 10-2\n\nvote, the jury recommended that Smith be sentenced to death, which the court\n\nimposed.\n\n A. Jury Selection and Batson Hearing\n\n During jury selection in Smith’s trial, the state prosecutor used 14 of his 15\n\nperemptory strikes on women. The prosecutor also struck several black venire\n\nmembers and the sole Hispanic venire member. Smith’s counsel objected, arguing\n\nthat the prosecutor was discriminating on the basis of gender, race, and national\n\norigin. The state trial court held that Smith failed to make a prima facie showing\n\nof discrimination, and the trial proceeded. The ultimate jury was comprised of five\n\nwomen and seven men.\n\n 2\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 3 of 31\n\n\n On direct appeal, the Alabama Court of Criminal Appeals (Alabama CCA)\n\nfound that Smith had provided sufficient evidence for a prima facie showing of\n\ngender-based discrimination under J.E.B. v. Alabama, 511 U.S. 127 (1994). See\n\nSmith v. State, 698 So. 2d 1166, 1169 (Ala. Crim. App. 1997). The Alabama CCA\n\nremanded the case for a hearing so that the prosecutor could present his reasons for\n\nthe strikes.\n\n On remand, the prosecutor offered explanations for each strike; those\n\nexplanations included employment, marital status, age, knowledge of criminal law,\n\nand work with various churches and religious groups. At the hearing, the\n\nprosecutor explained:\n\n I struck a lot of these [venire members] because they\n worked in the church; Sunday School teachers and Sunday\n School leaders, and things of that nature, and . . . I knew\n the defense counsel, if it came to the second phase of the\n sentencing hearing, would be asking the jurors to show\n mercy. And, it was my opinion that this argument would\n be receptive to someone who worked in the church and\n was well versed in the Bible more than someone who was\n not; be a female or male juror that was a strong worker in\n the church. No male jurors that was [sic] left seated on the\n jury worked in the church.\n\nIn response, Smith’s counsel argued that the prosecution did not strike everyone\n\nwho had religious affiliations 1 and questioned why the prosecution had not asked\n\n\n1\n At the hearing, Smith’s counsel did not identify any men with religious affiliations who were\nnot struck by the prosecution. Smith’s counsel identified one woman, Ms. Parham, who may\n\n\n 3\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 4 of 31\n\n\nany follow-up questions about the venire members’ religious beliefs. Next, the\n\nprosecutor explained that he eliminated the sole Hispanic venire member because\n\nshe was young and did not respond to questions during voir dire; Smith’s counsel\n\nargued this explanation was insufficient.\n\n The state trial court ultimately found that the prosecutor’s reasons for\n\nstriking the female venire members were gender neutral, that those reasons were\n\ncredible, and that Smith had failed to prove that the prosecutor had acted in a\n\ndiscriminatory manner. On appeal after remand, the Alabama CCA affirmed.\n\nSmith v. State, 838 So. 2d 413 (Ala. Crim. App. 2002) (hereinafter Smith II). The\n\nSupreme Court denied Smith’s petition for writ of certiorari. Smith v. Alabama,\n\n537 U.S. 1090 (2002).\n\n B. Smith’s Post-Conviction Hearings\n\n Smith then filed a petition for state post-conviction relief under Alabama\n\nRule of Criminal Procedure 32. The petition included a claim of intellectual\n\ndisability, and the Rule 32 court conducted an evidentiary hearing on this claim.\n\n At the hearing, Dr. Salekin, Smith’s expert, testified that Smith scored a 64\n\non a full IQ test and exhibited adaptive deficits in several areas. Dr. Salekin also\n\n\nhave worked in a church but was not struck by the prosecution. In later briefing at the trial court,\nSmith identified John Hall, who served as a football coach for the Young Men’s Christian\nAssociation (YMCA), but was not struck by the prosecution. Finally, in his appellate briefing,\nSmith raised “Mr. Johnson,” an unidentified male member of the venire who stated that he\nserved on his church’s board, but was not struck by the prosecution.\n\n\n 4\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 5 of 31\n\n\ntestified, however, that Smith scored relatively well on a separate test that assessed\n\nSmith’s language, reading, and mathematics skills, and that these particular results\n\nwere inconsistent with a diagnosis of intellectual disability. Dr. Salekin’s final\n\nopinion was that Smith was not intellectually disabled. Dr. Salekin also testified\n\nthat there was no national medical consensus on using the “Flynn Effect” to adjust\n\nIQ scores.2\n\n The state called Dr. King, who testified that Smith scored a 72 on a full IQ\n\ntest, including verbal score of 75 and nonverbal score of 74.3 Smith’s score on the\n\nverbal portion of Dr. King’s IQ test matched a previous score he achieved on the\n\nverbal portion of a partial IQ test administered by Dr. Blotcky, a court-appointed\n\npsychologist.4 Like Dr. Salekin, Dr. King’s final opinion was that Smith was not\n\nintellectually disabled, and he agreed that there was no national medical consensus\n\non using the Flynn Effect to adjust IQ scores.\n\n The Rule 32 court denied Smith’s Rule 32 petition, and the Alabama CCA\n\naffirmed. Smith v. State, 112 So. 3d 1108 (Ala. Crim. App. 2012) (Smith III), cert.\n\ndenied, Ex parte Smith, 112 So. 3d 1152 (Ala. 2012).\n\n C. Further Procedural History\n\n\n\n2\n The “Flynn Effect” is a theory that contends that IQ scores have been increasing over time and\nsuggests that IQ scores should be recalibrated in order to reflect this increase.\n3\n Dr. King also testified that, using a standard error of measurement, Smith’s IQ could have been\nas low as 68 or as high as 77.\n4\n Dr. Blotcky never administered a full IQ test, for reasons that remain unexplained.\n 5\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 6 of 31\n\n\n Smith filed his original federal habeas petition in the Northern District of\n\nAlabama, which the district court denied. One day after denying Smith’s petition,\n\nthe district court reopened the action for the sole purpose of considering the effect,\n\nif any, of Moore v. Texas, 137 S. Ct. 1039 (2017), on Smith’s Atkins claim. After\n\nsupplemental briefing, the district court concluded that Moore did not apply\n\nretroactively and reaffirmed the denial of Smith’s petition. The district court\n\ngranted Smith a COA on his Atkins claim, and we granted him a COA on his\n\nBatson claim.\n\n II. Standard of Review\n\n We review de novo the district court’s denial of a 28 U.S.C. § 2254 petition.\n\nWard v. Hall, 592 F.3d 1144, 1155 (11th Cir. 2010). Because Smith filed his\n\npetition after April 24, 1996, this appeal is governed by the Antiterrorism and\n\nEffective Death Penalty Act of 1996 (AEDPA). AEDPA “establishes a highly\n\ndeferential standard for reviewing state court judgments.” Parker v. Sec’y, Dep’t.\n\nof Corr., 331 F.3d 764, 768 (11th Cir. 2003). Under AEDPA, a federal court may\n\nonly grant a writ of habeas corpus if the state court’s determination of a federal\n\nclaim was (1) “contrary to, or involved an unreasonable application of, clearly\n\nestablished Federal law” or (2) “was based on an unreasonable determination of\n\nthe facts in light of the evidence presented in the State court proceeding.” 28\n\nU.S.C. § 2254(d).\n\n\n 6\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 7 of 31\n\n\n The phrase “clearly established Federal law” encompasses only the holdings\n\nof the Supreme Court of the United States “as of the time of the relevant state-court\n\ndecision.” Williams v. Taylor, 529 U.S. 362, 412 (2000). Section 2254(d)\n\nprovides two separate bases for reviewing state court decisions—“the ‘contrary to’\n\nand ‘unreasonable application’ clauses articulate independent considerations a\n\nfederal court must consider.” Maharaj v. Sec’y, Dep’t of Corr., 432 F.3d 1292,\n\n1308 (11th Cir. 2005).\n\n A state court’s determination is “contrary to” clearly established federal law\n\n“if the state court arrives at a conclusion opposite to that reached by [the Supreme\n\nCourt] on a question of law or if the state court decides a case differently than [the\n\nSupreme Court] has on a set of materially indistinguishable facts.” Williams, 529\n\nU.S. at 413. A state court’s determination is “an unreasonable application” of\n\nclearly established federal law “if the state court identifies the correct governing\n\nlegal principle from [the Supreme Court’s] decisions but unreasonably applies that\n\nprinciple to the facts of the prisoner’s case.” Id. Reasonableness is objective, and\n\na federal court may not issue a writ of habeas corpus simply because it concludes\n\nin its independent judgment that the state court was incorrect. Id. at 410.\n\n Finally, under § 2254(d)(2), we presume that the state court’s findings of\n\nfact are correct unless rebutted by clear and convincing evidence. See 28 U.S.C. §\n\n2254(e)(1). “This deference requires that a federal habeas court more than simply\n\n\n 7\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 8 of 31\n\n\ndisagree with the state court before rejecting its factual determinations. Instead, it\n\nmust conclude that the state court’s findings lacked even fair support in the\n\nrecord.” Rose v. McNeil, 634 F.3d 1224, 1241 (11th Cir. 2011) (citations omitted).\n\n\n III. Atkins Claim\n\n Smith first argues that the district court erred in holding that the Supreme\n\nCourt’s recent holding in Moore v. Texas did not apply retroactively to his\n\nintellectual disability claim. We agree with the district court that Moore is not\n\nretroactive. Smith also argues that the Alabama state courts unreasonably applied\n\nAtkins v. Virginia in evaluating his intellectual disability claim. After careful\n\nreview of the state court record and its order, we hold that the state court’s denial\n\nof his intellectual disability claim was not an unreasonable application of clearly\n\nestablished federal law.\n\n A. The Non-Retroactivity of Moore v. Texas\n\n In Atkins v. Virginia, the predecessor to Moore, the Supreme Court held that\n\nthe execution of individuals with intellectual disabilities violated the Eighth\n\nAmendment. 536 U.S. 304 (2002). But the Court did not define what it means to\n\nbe intellectually disabled, leaving that task to individual state legislatures and\n\ncourts. Id. at 317. In the years following Atkins, states developed different criteria\n\nfor assessing intellectual disability. Some states delineated a bright line threshold\n\nfor IQ scores, while others did not.\n\n 8\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 9 of 31\n\n\n In Hall v. Florida, the Court clarified that a state court’s intellectual\n\ndisability determination should be “informed by the medical community's\n\ndiagnostic framework.” 572 U.S. 701, 721 (2014). This meant, among other\n\nthings, that courts must consider the standard error inherent in IQ tests when a\n\ndefendant’s test scores put him “within the clinically established range for\n\nintellectual-functioning deficits.” Moore, 137 S. Ct. at 1050; see also Hall, 572\n\nU.S. at 723. In those cases, defendants must be allowed to present additional\n\nevidence of intellectual disability, including testimony on adaptive deficits. Hall,\n\n572 U.S. at 723.\n\n In Moore, the Court expanded on Hall, reiterating that state courts do not\n\nhave “unfettered discretion” in their determination of whether a capital defendant\n\nis intellectually disabled. 137 S. Ct. at 1052. Specifically, Moore established that\n\nstates cannot disregard current clinical and medical standards in assessing whether\n\na capital defendant is intellectually disabled. In addition, the Court clarified that\n\nunder prevailing clinical standards, the focus of the adaptive functioning inquiry\n\nshould be an individual’s adaptive deficits—not adaptive strengths. Id. at\n\n1050−51. After Moore, states cannot “weigh” an individual’s adaptive strengths\n\nagainst his adaptive deficits.\n\n Because Moore was decided five years after the Alabama state courts\n\ndecided Smith’s Atkins claim, he concedes that Moore could not have been “clearly\n\n\n 9\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 10 of 31\n\n\nestablished Federal law” at that time. Smith instead argues that Moore announced\n\na new rule of constitutional law that should be applied retroactively under Teague\n\nv. Lane, 489 U.S. 288 (1989).\n\n New constitutional rules are generally not retroactive for cases on federal\n\nhabeas review. See id. To determine whether a rule is retroactive, we first decide\n\nif it is a new rule. Under Teague, “a case announces a new rule when it breaks\n\nnew ground or imposes a new obligation on the States or the Federal Government,”\n\nor when “the result was not dictated by [prior] precedent.” Id. at 301.\n\n If the rule is indeed new, we then decide whether it falls into one of\n\nTeague’s two exceptions to the general bar on retroactivity. The first exception is\n\nfor substantive rules of constitutional law that place an entire category of primary\n\nconduct beyond the reach of the criminal law, including “rules prohibiting a certain\n\ncategory of punishment for a class of defendants because of their status or\n\noffense.” See Penry v. Lynaugh, 492 U.S. 302, 330 (1989). The second exception\n\nis for “watershed rules of criminal procedure” that are necessary to the\n\nfundamental fairness of criminal proceedings. Teague, 489 U.S. at 311−12. It is\n\ngenerally very difficult to meet the requirements of the second exception. See,\n\ne.g., Saffle v. Parks, 494 U.S. 484, 495 (1990) (noting that the rule announced in\n\nGideon v. Wainwright, 372 U.S. 335 (1963), illustrates the type of rule meeting\n\nthis second exception).\n\n\n 10\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 11 of 31\n\n\n Smith argues that Moore falls under the first Teague exception because\n\nMoore announced a new substantive rule of constitutional law that prohibits “a\n\ncertain category of punishment for a class of defendants because of their status or\n\noffense.” Penry, 492 U.S. at 330. Smith argues that Moore, which requires states\n\nto consider the medical community’s current clinical standards to determine\n\nintellectual disability, effectively expands the class of people who are ineligible for\n\nthe death penalty. Smith argues that Moore’s holding was thus substantive—not\n\nprocedural. We disagree.\n\n Substantive rules “set forth categorical constitutional guarantees that place\n\ncertain criminal laws and punishments altogether beyond the State’s power to\n\nimpose,” while procedural rules “are designed to enhance the accuracy of a\n\nconviction or sentence by regulating the manner of determining the defendant’s\n\nculpability.” Montgomery v. Louisiana, 136 S. Ct. 718, 729–30 (2016) (internal\n\nquotation marks omitted). For example, rules that “allocate decisionmaking\n\nauthority” between judge and jury, or “regulate the evidence that the court could\n\nconsider in making its decision” are procedural. Welch v. United States, 136 S. Ct.\n\n1257, 1265 (2016).\n\n Moore established that states cannot disregard current clinical and medical\n\nstandards in assessing whether a capital defendant is intellectually disabled.\n\nMoore effectively narrowed the range of permissible methods—the procedure—\n\n\n 11\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 12 of 31\n\n\nthat states may use to determine intellectual disability. While Moore may have the\n\neffect of expanding the class of people ineligible for the death penalty, it merely\n\ndefined the appropriate manner for determining who belongs to that class of\n\ndefendants ineligible for the death penalty. Moore thus announced a new rule, but\n\nit is procedural, not substantive.5\n\n Because Moore announced a procedural rule, it can only be retroactive if it\n\nmeets Teague’s second exception. Doing so is extraordinarily rare. See, e.g.,\n\nSchriro v. Summerlin, 542 U.S. 348, 351–52 (2004). “To fall within this\n\nexception, a new rule must meet two requirements: Infringement of the rule must\n\n\n\n\n5\n In Kilgore v. Secretary, Florida Department of Corrections, this Court held that Hall is not a\nsubstantive rule under Teague. 805 F.3d 1301, 1314 (11th Cir. 2015) (relying on In re Henry,\n757 F.3d 1151, 1161 (11th Cir. 2014)). Alabama argues that we should rely on Kilgore’s\nreasoning to conclude that Moore is likewise not a substantive rule under Teague. We decline to\ndo so because the Supreme Court’s decision in Montgomery v. Louisiana undermined a core\ncomponent of Kilgore’s retroactivity analysis, which Kilgore borrowed from In re Henry. In\nKilgore, we reasoned that Hall was not substantive under Teague because it “guaranteed only a\nchance to present evidence, not ultimate relief.” Kilgore, 805 F.3d at 1314; see also In re Henry,\n757 F.3d at 1161. But Montgomery later deemed a rule substantive in nature—the rule of Miller\nv. Alabama, 567 U.S. 460 (2012), which prohibited mandatory life without parole sentences for\njuveniles—even though all that rule guaranteed was “[a] hearing where ‘youth and its attendant\ncharacteristics’ are considered as sentencing factors,” not a shorter sentence or parole.\nMontgomery, 136 S. Ct. at 735 (quoting Miller, 567 U.S. at 465). Montgomery thus stands for\nthe proposition that a right can be substantive under Teague even if it only guarantees the chance\nto present evidence in support of relief sought, not ultimate relief itself. See, e.g., In re Sapp,\n827 F.3d 1334, 1340–41 (11th Cir. 2016) (Jordan, Rosenbaum, and Jill Pryor, JJ., concurring).\nBecause Montgomery undermined the reasoning of Kilgore and In re Henry, we do not rely on\nthem to reach our decision. See Chambers v. Thompson, 150 F.3d 1324, 1326 (11th Cir. 1998);\nsee also Davis v. Singletary, 119 F.3d 1471, 1482 (11th Cir. 1997) (“To the extent of any\ninconsistency between [our prior] pronouncements and the Supreme Court’s supervening ones,\nof course, we are required to heed those of the Supreme Court.”).\n\n\n 12\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 13 of 31\n\n\nseriously diminish the likelihood of obtaining an accurate conviction [or sentence],\n\nand the rule must alter our understanding of the bedrock procedural elements\n\nessential to the fairness of a proceeding.” Tyler v. Cain, 533 U.S. 656, 665 (2001)\n\n(quotation omitted).\n\n Only Gideon v. Wainwright, 372 U.S. 335 (1963), which extended the right\n\nto counsel to criminal defendants, has been declared the kind of procedural rule\n\nthat altered the “bedrock procedural elements” essential to the fairness of a\n\nproceeding. See Beard v. Banks, 542 U.S. 406, 416−18 (2004) (noting that\n\nGideon’s holding was sweeping and broke with past precedent). The Supreme\n\nCourt has continually rejected retroactivity under Teague’s second exception for\n\nprocedural rules that do not have the “primacy” or “centrality” of Gideon. See,\n\ne.g., Wharton v. Bocking, 549 U.S. 406, 421 (2007) (rejecting retroactivity for\n\nCrawford v. Washington, 541 U.S. 36 (2004)); Schriro, 542 U.S. at 356−58\n\n(rejecting retroactivity for Ring v. Arizona, 546 U.S. 584 (2002)). Both Crawford 6\n\nand Ring7 were important holdings for the rights of criminal defendants, and yet\n\n\n\n\n6\n In Crawford v. Washington, 541 U.S. 36 (2004), the Supreme Court held that the Sixth\nAmendment’s Confrontation Clause prohibits the state from introducing testimonial hearsay as\nevidence against criminal defendants unless the declarant is unavailable and the defendant had a\nprior opportunity to cross-examine the declarant.\n7\n In Ring v. Arizona, 536 U.S. 584 (2002), the Supreme Court held that the Sixth Amendment\nguarantees criminal defendants the right to have a jury, not a sentencing judge, find the\naggravating circumstances necessary for the imposition of the death penalty.\n 13\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 14 of 31\n\n\nthe Supreme Court held that neither altered the bedrock procedural elements\n\nessential to the fairness of a criminal proceeding, and thus neither was retroactive.\n\n Similarly, Moore is an important development. It provides guidance to\n\nstates attempting to comply with Atkins. But we cannot say that Moore altered the\n\nbedrock procedural elements essential to the fairness of a criminal proceeding in\n\nthe way that the Gideon rule did. Because Moore cannot meet the requirements of\n\nTeague’s second exception, it cannot be applied retroactively.\n\n B. Analysis of Smith’s Atkins Claim\n\n Smith argues that, even if Moore is not retroactive, the Alabama courts\n\nunreasonably applied Atkins v. Virginia to his intellectual disability claim.\n\n 1. The State Court Record\n\n Shortly after Atkins, the Alabama Supreme Court held that to be\n\nintellectually disabled under Atkins, a defendant must prove by a preponderance of\n\nthe evidence: (1) “significantly subaverage intellectual functioning (an IQ of 70 or\n\nbelow),” (2) “significant or substantial deficits in adaptive behavior,” and (3) that\n\nboth the subaverage intellectual functioning and the deficits in adaptive\n\nfunctioning manifested before the age of eighteen. Ex Parte Perkins, 851 So. 2d\n\n453, 456 (Ala. 2002).\n\n Smith raised his Atkins claim in his Rule 32 petition shortly after Perkins.\n\nThe Rule 32 court ultimately denied his petition, finding it relevant, but not\n\n\n 14\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 15 of 31\n\n\ndispositive, that no expert—not even Smith’s own expert—testified that Smith was\n\nintellectually disabled. The court then evaluated the Perkins factors and concluded\n\nthat Smith failed to prove by a preponderance of the evidence that he was\n\nintellectually disabled.\n\n First, the court determined that Smith failed to satisfy his burden of showing\n\nsignificantly subaverage intellectual functioning. The court noted that the experts\n\nhad presented conflicting evidence and testimony: Dr. Salekin reported that Smith\n\nhad an IQ of 64, while Dr. King reported an IQ of 72. The court ultimately\n\ncredited Dr. King’s IQ score as “probably more accurate” than Dr. Salekin’s score\n\nin part because Dr. King’s test resulted in a verbal IQ of 75, the same verbal IQ\n\nthat Smith received on a prior IQ test. The court also declined to adjust Smith’s IQ\n\nscores downward because the experts all testified that there was no national\n\nmedical consensus on using the Flynn Effect to adjust IQ scores.\n\n On the second Perkins prong, the court determined that Smith failed to\n\nsatisfy his burden of showing significant deficits in adaptive behavior. The court\n\nconcluded that, “[a]lthough [Smith] showed deficits in adaptive functioning based\n\nupon test results,” Smith did not show many deficits in his adaptive functioning “in\n\neveryday life” either before or after his crime. The court noted that Smith showed\n\nrelatively normal scores in functional academics and communication. And while\n\nhe did have some possible deficiencies, the court reasoned that those deficits were\n\n\n 15\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 16 of 31\n\n\nnot so significant that Smith could not succeed in school, work, or society in\n\ngeneral. The court also indicated that Smith’s ability to plan and conceal his crime\n\n“weigh[ed] against [him] in relation to the adaptive functioning requirement.”\n\n On appeal, the Alabama CCA affirmed, holding that the Rule 32 court did\n\nnot abuse its discretion in concluding that Smith had failed to prove that he was\n\nintellectually disabled. Smith III, 112 So. 3d at 1108. As the Alabama CCA\n\nsummarized, “[t]he greater weight of the evidence indicated that, although he\n\nsuffered with some mental deficiencies, they did not rise to the level at which an\n\nimpartial mind would conclude from the evidence that he was mentally retarded.”\n\nId. at 1130.\n\n As to intellectual functioning, the Alabama CCA found that the Rule 32\n\ncourt did not err in declining to apply the Flynn Effect or standard error to Smith’s\n\nIQ score. Id. at 1131. The Alabama CCA also endorsed the Rule 32 court’s\n\napproach to examining adaptive functioning, explaining that “[e]ven where there\n\nare indications of shortfalls in adaptive behavior, other relevant evidence may\n\nweigh against an overall finding of deficiency.” Id. at 1133. Because the Alabama\n\nCCA found that Smith failed to prove both significantly subaverage intellectual\n\nfunctioning and significant deficits in adaptive behavior, the court did not fully\n\naddress the third prong of Perkins—whether those shortfalls in intellectual and\n\nadaptive functioning had manifested before the age of eighteen.\n\n\n 16\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 17 of 31\n\n\n 2. Analysis Under 28 U.S.C. § 2254(d)(1)\n\n Smith argues that the Alabama state courts unreasonably applied Atkins v.\n\nVirginia to his intellectual disability claim by (1) determining that Smith’s IQ\n\nscores did not meet the standard for intellectual disability, (2) failing to consider\n\nthe standard error and Flynn Effect in assessing Smith’s IQ scores, and (3) giving\n\nmore weight to Smith’s adaptive strengths than to his adaptive deficits in assessing\n\nhis adaptive functioning.\n\n A state court’s determination is an unreasonable application of clearly\n\nestablished federal law “if the state court identifies the correct governing legal\n\nprinciple from this Court’s decisions but unreasonably applies that principle to the\n\nfacts of the [petitioner’s] case.” Williams v. Taylor, 529 U.S. 362, 413 (2000).\n\nThe difficulty for Smith—and other litigants mounting this challenge—is that\n\nAtkins set forth few legal governing principles for lower courts and states\n\nevaluating intellectual disability. The Supreme Court’s decision in Atkins did not\n\ndefine what it means to be intellectually disabled, instead leaving that task to the\n\nstates. See Atkins, 536 U.S. at 317. The Supreme Court itself recently explained\n\nthat “Atkins gave no comprehensive definition of ‘mental retardation’ for Eighth\n\nAmendment purposes.” Shoop v. Hill, 139 S. Ct. 504, 507 (2019).\n\n i. Intellectual Functioning\n\n\n\n\n 17\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 18 of 31\n\n\n Smith first argues that the Alabama state courts unreasonably applied Atkins\n\nv. Virginia by refusing to credit Dr. Salekin’s testimony that Smith had an IQ of 64\n\nand consequently determining that Smith’s IQ scores did not satisfy the first\n\nPerkins prong of subaverage intellectual functioning. According to Smith, “[t]he\n\nrefusal to use the IQ score of 64 in an average with the other scores, or otherwise\n\ndiscount [Dr. King’s] score of 72 based on the IQ score of 64, was an unreasonable\n\napplication of Atkins to the present case.” 8 Smith also argues it was an\n\nunreasonable application of Atkins to refuse to account for the Flynn Effect or\n\nstandard error when the state court evaluated Smith’s IQ.\n\n But Atkins did not set forth clearly established federal law on how states\n\nmust evaluate IQ scores in determining intellectual disability. “Atkins did not\n\ndefine intellectual disability, nor did it direct the states on how to define\n\nintellectual disability, nor, finally, did it provide the range of IQ scores that could\n\nbe indicative of intellectual disability.” Kilgore v. Sec’y, Fla. Dep’t of Corr., 805\n\n\n\n8\n In his initial brief, Smith does not argue that the Alabama court’s decision to refuse to fully\ncredit Dr. Salekin’s IQ score was an unreasonable determination of the facts under 28 U.S.C.\n§ 2254(d)(2). Smith raises this argument only in his reply brief. We generally do not consider\nissues and arguments raised for the first time in an appellant’s reply brief. See, e.g., United\nStates v. Levy, 379 F.3d 1241, 1244 (11th Cir. 2004). In any event, it is unlikely that the state\ncourt made an unreasonable factual determination in crediting Dr. King’s score over Dr.\nSalekin’s score. While we agree that it might have been preferable to average both IQ scores\nunder these circumstances, “a state-court factual determination is not unreasonable merely\nbecause the federal habeas court would have reached a different conclusion in\nthe first instance.” Wood v. Allen, 558 U.S. 290, 301 (2010). Here, the state court used an\nadditional IQ score in the record—albeit a partial score—to corroborate Dr. King’s test. We\ncannot say that the decision to do so was an unreasonable factual determination.\n 18\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 19 of 31\n\n\nF.3d 1301, 1311 (11th Cir. 2015); see also Bobby v. Bies, 556 U.S. 825, 831 (2009)\n\n(“[Atkins] did not provide definitive procedural or substantive guides for\n\ndetermining when a person who claims [intellectual disability] will be so impaired\n\nas to fall within [Atkins’ compass]” (internal citation and quotation marks\n\nomitted)). Without clear guidance from Atkins, the state court’s refusal to average\n\nIQ scores or to account for certain statistical adjustments was not an unreasonable\n\napplication of clearly established federal law.\n\n Smith’s specific argument about the state court’s failure to consider the\n\nstandard error is foreclosed by our precedent. As we explained in Kilgore,\n\n“[n]othing in Atkins suggested that a bright-line IQ cutoff of 70 ran afoul of the\n\nprohibition on executing the intellectually disabled.” 805 F.3d at 1312. In other\n\nwords, Atkins did not require states to consider the standard error in assessing IQ\n\nscores. That requirement did not emerge until Hall v. Florida, 572 U.S. 701\n\n(2014), well after the Alabama courts considered Smith’s case.\n\n Altogether, Smith’s arguments generally conflate what we have previously\n\npermitted in evaluating intellectual disability with what is required. While we\n\nhave previously said that the Flynn Effect may be considered in determining a\n\ndefendant’s IQ, see Thomas v. Allen, 607 F.3d 749, 753 (11th Cir. 2010), neither\n\nthis Court nor the Supreme Court has required courts to do so. Similarly, while we\n\nhave previously permitted district courts to average multiple IQ scores, see\n\n\n 19\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 20 of 31\n\n\nHolladay v. Allen, 555 F.3d 1346, 1357−58 (11th Cir. 2009), courts are not\n\nnecessarily required to do so.\n\n ii. Adaptive Functioning\n\n Next, Smith argues that the Alabama courts unreasonably applied Atkins by\n\nfavoring Smith’s adaptive strengths over his adaptive deficits. The Supreme Court\n\nrecently rejected this argument in Shoop v. Hill, 139 S. Ct. 504 (2019).\n\n In Hill v. Anderson, the Sixth Circuit held that Moore’s holding about\n\nadaptive strengths was clearly established law because Moore was “merely an\n\napplication of what was clearly established by Atkins.” 881 F.3d 483, 487 (6th Cir.\n\n2018). But the Supreme Court reversed the Sixth Circuit and soundly rejected this\n\nargument in Shoop, explaining that “Atkins did not definitively resolve how [the\n\nadaptive functioning prong] was to be evaluated but instead left its application in\n\nthe first instance to the State.” 139 S. Ct. at 508. Because Atkins did not provide\n\ndefinitive guidance to states on how to evaluate a petitioner’s adaptive functioning,\n\nthe Alabama courts here could not have unreasonably applied Atkins in choosing to\n\nweigh Smith’s adaptive strengths against his adaptive weaknesses.\n\n Smith’s success on this claim is a matter of timing. After Moore v. Texas, it\n\nis abundantly clear that states may not weigh a defendant’s adaptive strengths\n\nagainst his adaptive deficits. Doing so contradicts the medical community’s\n\ncurrent clinical standards. Moore, 137 S. Ct. at 1050−51. As the Supreme Court\n\n\n 20\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 21 of 31\n\n\nexplained in Moore, many individuals with intellectual disabilities have both\n\nadaptive deficits and adaptive strengths, and “significant limitations in conceptual,\n\nsocial, or practical adaptive skills [are] not outweighed by the potential strengths in\n\nsome adaptive skills.” Id. at 1050 (citation omitted).\n\n Alabama argues that the state court did not weigh Smith’s adaptive strengths\n\nagainst his adaptive deficits. We firmly disagree. Despite concluding that Smith\n\n“showed deficits in adaptive functioning based upon test results,” the state court\n\nconsidered other factors that weighed against “an overall finding of deficiency,”\n\ntreating the adaptive functioning prong like a balancing test. In particular, the state\n\ncourt considered Smith’s ability to conceal his crime, ability to take care of his\n\nmother, and his scores on certain mathematics and reading tests as adaptive\n\nstrengths that outweighed his apparent deficits. This approach was acceptable at\n\nthe time. But after Moore, it no longer is.\n\n IV. Batson Claim\n\n Smith argues that the prosecutor at his state trial struck jurors on the basis of\n\ngender and national origin 9 in violation of the Sixth and Fourteenth Amendments.\n\n\n\n9\n At the district court, Smith also asserted a race discrimination claim because the prosecutor\nused five of his peremptory strikes to eliminate black venire members. On appeal, however,\nSmith makes only vague and passing reference to racial discrimination. Therefore, we address\nonly his gender and national origin discrimination claims. See Sapuppo v. Allstate Floridian Ins.\nCo., 739 F.3d 678, 681 (11th Cir. 2014) (noting that “an appellant abandons a claim when he\neither makes only passing references to it or raises it in a perfunctory manner without supporting\narguments and authority”).\n 21\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 22 of 31\n\n\nSee Batson v. Kentucky, 476 U.S. 79 (1986); J.E.B. v. Alabama, 511 U.S. 127\n\n(1994). After careful review, we hold that the state court’s denial of Smith’s\n\nclaims was not contrary to Batson and its progeny, an unreasonable application of\n\nBatson, or an unreasonable determination of the facts in light of the evidence\n\npresented to the state courts.\n\n A. Clearly Established Law\n\n Under the Equal Protection Clause, a criminal defendant has a constitutional\n\nright “to be tried by a jury whose members are selected pursuant to\n\nnondiscriminatory criteria.” Batson, 476 U.S. at 85–86. In Batson, the Supreme\n\nCourt set out a three-part test to “guide trial courts’ constitutional review of\n\nperemptory strikes.” Johnson v. California, 545 U.S. 162, 168 (2005). Under the\n\nthree-part test,\n\n [f]irst, the defendant must make out a prima facie case by\n showing that the totality of the relevant facts gives rise to\n an inference of discriminatory purpose. Second . . . the\n burden shifts to the State to explain adequately the racial\n exclusion by offering permissible race-neutral\n justifications for the strikes. Third, if a race-neutral\n explanation is tendered, the trial court must then\n decide . . . whether the opponent of the strike has proved\n purposeful racial discrimination.\n\nId. (internal quotation marks, citations, and footnotes omitted). At the first step, a\n\ndefendant makes a prima facie case of discrimination if the circumstances allow\n\nfor a permissible inference of discrimination. Id. at 162. At the second step, the\n\n\n 22\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 23 of 31\n\n\ncourt evaluates only the “facial validity of the prosecutor’s explanation,” and\n\nunless a discriminatory intent is “inherent in the prosecutor’s explanation, the\n\nreason offered will be deemed race neutral.” Purkett v. Elem, 514 U.S. 765, 768\n\n(1995) (quotation omitted). The third step “involves evaluating the persuasiveness\n\nof the justification” proffered by the prosecutor, and “[a]t that stage, implausible or\n\nfantastic justifications may (and probably will) be found to be pretexts for\n\npurposeful discrimination.” Id. Inconsistent and disparate treatment of venire\n\nmembers is evidence that the proffered reasons are post-strike excuses and not\n\nlegitimate race or gender-neutral justifications. See, e.g., Snyder v. Louisiana, 552\n\nU.S. 472, 483 (2008).\n\n The evaluation of a prosecutor’s race-neutral or gender-neutral explanation\n\nfor a strike under Batson is a “pure issue of fact . . . peculiarly within a trial judge’s\n\nprovince.” McNair v. Campbell, 416 F.3d 1291, 1310 (11th Cir. 2005) (quotation\n\nomitted). Even on direct review, a trial judge’s finding on intentional\n\ndiscrimination is entitled to “great deference.” See Batson, 476 U.S. at 98 n.21. At\n\nthe habeas stage, the burden is even higher; the petitioner must show “it was\n\nunreasonable to credit the prosecutor’s race-neutral explanations” under\n\n§ 2254(d)(2). Rice v. Collins, 546 U.S. 333, 338 (2006).\n\n B. Analysis of Smith’s Batson Claim\n\n\n\n\n 23\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 24 of 31\n\n\n Smith argues that the state court’s determination that he failed to prove\n\npurposeful discrimination was (1) an unreasonable determination of the facts under\n\n28 U.S.C. § 2254(d)(2) and (2) both contrary to and an unreasonable application of\n\nBatson and its progeny under 28 U.S.C. § 2254(d)(1). Before we address those\n\nclaims, we briefly review the state court record.\n\n 1. State Court Record\n\n On remand, the prosecutor offered explanations for striking each female\n\nvenire member. Those explanations included employment, marital status, age,\n\nknowledge of criminal law, and work with various churches and religious groups.\n\nIn its order on remand, the state trial court evaluated the prosecutor’s reasoning for\n\nstriking each female venire member. The trial court found that the prosecutor’s\n\nexplanation for each member was supported by the record. The court confirmed,\n\nfor example, that each woman allegedly struck for her religious affiliations stated\n\nduring voir dire, or indicated on her questionnaire, that she was active in her\n\nchurch or taught Sunday School. The court noted that excluding potential jurors\n\nwho were susceptible to mercy arguments was a sound trial strategy. Further,\n\nwhere the prosecutor explained a strike based on a venire member’s demeanor, the\n\ntrial court corroborated the prosecutor’s explanation with its own trial notes. The\n\nstate trial court ultimately held that the prosecutor’s reasons for striking the female\n\nvenire members were gender neutral, that those reasons were credible, and that\n\n\n 24\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 25 of 31\n\n\nSmith had failed to prove that the prosecutor had acted in a discriminatory\n\nmanner.10\n\n On appeal, the Alabama CCA concluded that the trial court’s determination\n\nwas not clearly erroneous. Smith II, 838 So. 2d at 436, 466. The Alabama CCA\n\nfocused its analysis on four women who, according to the prosecutor, were\n\neliminated because of their religious affiliations. The court noted that three of the\n\nfour women were Sunday School teachers; the other was a Counselor of Ministry.\n\nSee id. at 426−27.\n\n The Alabama CCA then acknowledged Smith’s argument that the\n\nprosecutor’s stated reason for striking these jurors was pretextual. The court\n\nconsidered, for example, Smith’s argument that several women who had been\n\neliminated for church involvement had also previously affirmed that their religious\n\nbeliefs would not preclude them from imposing a death sentence. The Alabama\n\nCCA also considered Smith’s argument that the prosecutor had not asked the\n\n\n\n\n10\n At the end of his order, the state trial court judge also noted that the prosecutor was “certainly\nnot a person prone to strike minorities denounced in the Batson case and its progeny.” The judge\nbased this conclusion on his “extensive in court experience with [the prosecutor] and close\nacquaintanceship with others that know him.” We note that the court’s role in hearing a Batson\nclaim is to evaluate whether the prosecutor’s stated reasons for excluding members of the jury\nare credible and supported by the record, not to personally attest to the prosecutor’s character or\nto provide its own reasons for why the prosecutor could not have discriminated in the present\ncase. See Adkins v. Warden, Holman CF, 710 F.3d 1241, 1254 & n.11 (11th Cir. 2013)\n(indicating that, at Batson’s third step, it is improper for the trial court to rely on its personal\nexperience with and opinion about the reputation of a prosecutor where those facts are not in\nevidence).\n 25\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 26 of 31\n\n\nwomen follow-up questions about their religious beliefs before striking them. But\n\nafter taking those arguments into account, the court found that Smith had not\n\nshown that the trial court’s credibility determination was clearly erroneous. The\n\nAlabama CCA thus affirmed the trial court’s finding that the prosecutor’s reasons\n\nfor striking the jurors were nondiscriminatory. Id. at 436.\n\n 2. Analysis Under 28 U.S.C. § 2254(d)(2)\n\n A prosecutor’s motive for striking a juror is a factual issue, Miller-El v.\n\nDretke, 545 U.S. 231, 240 (2005), and a state court’s factual findings are presumed\n\ncorrect on federal habeas corpus review. 28 U.S.C. §§ 2254(d)(2), (e)(1). In\n\nseeking habeas relief, Smith bears the burden of rebutting that presumption by\n\n“clear and convincing evidence.” Id. § 2254(e)(1).\n\n Smith first argues that he presented a strong prima facie case of gender\n\ndiscrimination where the prosecutor used 14 of his 15 strikes to eliminate women\n\nfrom the jury. We agree with Smith.11\n\n Smith then argues that the state court’s determination that the prosecutor’s\n\nreasons for striking the female venire members were nondiscriminatory was an\n\nunreasonable determination of the facts, particularly in light of the prosecutor’s\n\n\n11\n The district court found that Smith presented a relatively weak prima facie case of gender\ndiscrimination in part because five women ultimately served on Smith’s jury. But the fact that\nfive women remained on the jury after the prosecutor used nearly all his strikes to eliminate\nwomen tells us more about the initial composition of the venire pool (and which juror slots in the\nvenire were filled by women) than it does about the prosecutor’s state of mind.\n\n 26\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 27 of 31\n\n\ninconsistent treatment of male and female venire members. Smith concentrates his\n\nargument on one man—misidentified in the trial transcript as “Mr. Johnson”—who\n\nstated during voir dire that he was a member of his church’s board. 12 The\n\nprosecutor did not use a strike on “Johnson,” which Smith argues is evidence that\n\nthe prosecutor’s explanation for striking these women was pretextual.\n\n In the years following Smith’s trial, no party has been able to determine\n\nJohnson’s true identity. Smith was thus unable to provide the state courts with any\n\nadditional information about Johnson that might have been used to determine\n\nwhether there were meaningful differences between him and the female venire\n\nmembers. We do not know Johnson’s other answers during voir dire, information\n\nabout his demeanor, or any other potentially relevant factors, such as his\n\noccupation. All that we know about Johnson is that he was a board member at his\n\nchurch.\n\n To succeed under § 2254(d)(2), Smith must show that it was unreasonable\n\nfor the state court to credit the prosecutor’s proffered explanations for the strikes.\n\nSee Rice, 546 U.S. at 338. Smith has not met this burden. While Smith’s evidence\n\nabout Johnson could have supported a finding that the prosecutor’s strikes were\n\n\n\n\n12\n The venire pool for Smith’s trial did not contain any member with the surname of Johnson,\nand thus we assume this venire member was misidentified in the trial transcript.\n 27\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 28 of 31\n\n\ndiscriminatory, we do not think it mandated such a finding in light of the limited\n\nevidence presented to the state court.\n\n The Alabama CCA also grappled with some of Smith’s other arguments for\n\npretext. The court considered, for example, that some of the women allegedly\n\neliminated because of their church involvement had previously affirmed that their\n\nreligious beliefs would not preclude them from imposing the death penalty. But\n\nthe state court did not find that factor dispositive. Neither do we. The\n\nprosecution’s explanation at the Batson hearing was not that these potential jurors\n\nwould be unalterably unwilling to impose the death penalty, but that they would be\n\nparticularly receptive to Smith’s counsel’s request for mercy at the penalty phase\n\nof the trial. This is an acceptable justification for a peremptory strike.\n\n Importantly, the Alabama CCA ultimately affirmed the trial court’s\n\ncredibility determination only after noting that the trial court found that (1) the\n\nprosecutor’s reasons for striking venire members were supported by the record and\n\n(2) the prosecutor’s approach in excluding those who were susceptible to mercy\n\narguments was a sound trial strategy. Both factors are relevant in assessing a\n\nprosecutor’s credibility. See Miller-El v. Cockrell, 537 U.S. 322, 324 (2003)\n\n(“Credibility can be measured by, among other factors, the prosecutor’s demeanor;\n\nby how reasonable, or how improbable, the explanations are; and by whether the\n\nproffered rationale has some basis in accepted trial strategy.”).\n\n\n 28\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 29 of 31\n\n\n Ultimately, the record before us does not “compel the conclusion that the\n\ntrial court had no permissible alternative but to reject the prosecutor’s [gender]-\n\nneutral justifications.” Rice, 546 U.S. at 341. Because habeas review does not\n\nallow us to “supersede the trial court’s credibility determination” where the record\n\ndoes not compel a contrary conclusion, see id. at 341–42, we must deny Smith’s\n\nchallenge under § 2254(d)(2).\n\n 3. Analysis Under 28 U.S.C. § 2254(d)(1)\n\n Next, Smith argues that the state court’s holding was both contrary to Batson\n\nand its progeny and an unreasonable application of Batson under 28 U.S.C.\n\n§ 2254(d)(1). First, Smith argues that, contrary to Batson’s directive, the Alabama\n\nCCA simply accepted the prosecutor’s proffered explanations at face value. We\n\ndisagree. The Alabama CCA thoroughly documented the prosecutor’s reasons for\n\nstrikes, the trial court’s corroboration of the prosecutor’s stated reasons, and\n\nSmith’s arguments for why those reasons were pretextual. Only after conducting\n\nthis analysis did the Alabama CCA affirm the trial court’s credibility\n\ndetermination.13\n\n\n\n13\n We acknowledge that in its opinion, the Alabama CCA did not specifically discuss Johnson.\nBut the court did analyze whether the prosecutor’s explanation about striking jurors based on\nchurch affiliation was pretextual. “Under Supreme Court and our Circuit precedent, a state\ncourt’s written opinion is not required to mention every relevant fact or argument in order for\nAEDPA deference to apply.” Lee v. Comm’r, Ala. Dep’t of Corr., 726 F.3d 1172, 1223 (11th\nCir. 2013). Here, we do not think that the Alabama CCA was required to explicitly address\nSmith’s arguments about Johnson given the limited evidence Smith provided about him.\n 29\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 30 of 31\n\n\n Next, Smith argues that the Alabama CCA erred in accepting the\n\nprosecution’s “arbitrary and vague” reasons for excluding Ms. Ramos, the only\n\nHispanic venire member. While Smith is correct that vague explanations may be\n\nlegally insufficient to rebut a prima facie case of discrimination, the prosecutor’s\n\nproffered reasons for striking Ms. Ramos—her youth and lack of participation in\n\nvoir dire—are relatively concrete and permissible14 reasons for exercising a\n\nperemptory strike. The trial record supports both explanations. And neither\n\nexplanation rises to the level of vagueness that we condemned in United States v.\n\nHorsley, 864 F.2d 1543 (11th Cir. 1989), on which Smith relies. 15\n\n Finally, Smith argues that it was improper for the trial court to consider its\n\nown observations about a venire member’s behavior. It would be improper for a\n\njudge to substitute its own reasoning for striking a venire member where the\n\nprosecution’s explanations do not suffice. See Dretke, 545 U.S. at 252. But that\n\ndid not occur here. On remand, the trial court noted its own observations about\n\nvenire members from voir dire, but it did so to corroborate the prosecutor’s own\n\nexplanations about a venire member’s demeanor—a method endorsed by the\n\nSupreme Court. See Snyder v. Louisiana, 552 U.S. 472, 477 (2008) (“[R]ace-\n\n\n\n\n14\n The Supreme Court has not extended Batson to peremptory challenges based on age. See, e.g.,\nWeber v. Strippit, Inc., 186 F.3d 907, 911 (8th Cir. 1999), cert. denied, 528 U.S. 1078 (2000).\n15\n In United States v. Horsley, we held that a prosecutor’s statement that “I’ve just got a feeling\nabout [the juror]” was too vague to rebut a prima facie case of discrimination. 864 F.2d at 1544.\n 30\n\f Case: 17-15043 Date Filed: 05/22/2019 Page: 31 of 31\n\n\nneutral reasons for peremptory challenges often invoke a juror’s demeanor\n\n(e.g., nervousness, inattention), making the trial court’s firsthand observations of\n\neven greater importance. In this situation, the trial court must evaluate . . . whether\n\nthe juror’s demeanor can credibly be said to have exhibited the basis for the strike\n\nattributed to the juror by the prosecutor.”).\n\n In sum, Smith has not established that the state court’s denial of his claims\n\nwas contrary to the standard laid out in Batson and its progeny, an unreasonable\n\napplication of Batson, or an unreasonable determination of the facts in light of the\n\nevidence presented to the state courts. We therefore affirm the district court’s\n\ndenial of Smith’s § 2254 petition.\n\n AFFIRMED.\n\n\n\n\n 31\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Willie B. SMITH, III, Petitioner - Appellant, v. COMMISSIONER, ALABAMA DEPARTMENT OF CORRECTIONS, Respondent - Appellee.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-15043 Date Filed: 05/22/2019 Page: 1 of 31\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15043\\n ________________________\\n\\n D.C. Docket No. 2:13-cv-00557-RDP\\n\\n\\n\\nWILLIE B. SMITH, III,\\n\\n Petitioner - Appellant,\\n\\nversus\\n\\nCOMMISSIONER, ALABAMA DEPARTMENT OF CORRECTIONS,\\n\\n Respondent - Appellee.\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Alabama\\n ________________________\\n\\n (May 22, 2019)\\n\\nBefore WILSON, MARTIN, and JORDAN, Circuit Judges.\\n\\nWILSON, Circuit Judge:\\n\\n Willie B. Smith III, a death row inmate, appeals the district court’s denial of\\n\\nhis 28 U.S.C. § 2254 habeas corpus petition. The district court granted Smith a\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 2 of 31\\n\\n\\ncertificate of appealability (COA) on whether he is intellectually disabled and thus\\n\\nineligible for the death penalty under Atkins v. Virginia, 536 U.S. 304 (2002). We\\n\\ngranted Smith’s request to expand the COA to include whether the prosecutor at\\n\\nSmith’s state trial struck jurors on the basis of gender, race, and national origin in\\n\\nviolation of the Sixth and Fourteenth Amendments under Batson v. Kentucky, 476\\n\\nU.S. 79 (1986), and J.E.B. v. Alabama, 511 U.S. 127 (1994). After careful review\\n\\nof the record and with the benefit of oral argument, we affirm the district court’s\\n\\ndenial of habeas relief.\\n\\n\\n I. Factual and Procedural Background\\n\\n In 1992, an Alabama jury found Smith guilty of capital murder. By a 10-2\\n\\nvote, the jury recommended that Smith be sentenced to death, which the court\\n\\nimposed.\\n\\n A. Jury Selection and Batson Hearing\\n\\n During jury selection in Smith’s trial, the state prosecutor used 14 of his 15\\n\\nperemptory strikes on women. The prosecutor also struck several black venire\\n\\nmembers and the sole Hispanic venire member. Smith’s counsel objected, arguing\\n\\nthat the prosecutor was discriminating on the basis of gender, race, and national\\n\\norigin. The state trial court held that Smith failed to make a prima facie showing\\n\\nof discrimination, and the trial proceeded. The ultimate jury was comprised of five\\n\\nwomen and seven men.\\n\\n 2\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 3 of 31\\n\\n\\n On direct appeal, the Alabama Court of Criminal Appeals (Alabama CCA)\\n\\nfound that Smith had provided sufficient evidence for a prima facie showing of\\n\\ngender-based discrimination under J.E.B. v. Alabama, 511 U.S. 127 (1994). See\\n\\nSmith v. State, 698 So. 2d 1166, 1169 (Ala. Crim. App. 1997). The Alabama CCA\\n\\nremanded the case for a hearing so that the prosecutor could present his reasons for\\n\\nthe strikes.\\n\\n On remand, the prosecutor offered explanations for each strike; those\\n\\nexplanations included employment, marital status, age, knowledge of criminal law,\\n\\nand work with various churches and religious groups. At the hearing, the\\n\\nprosecutor explained:\\n\\n I struck a lot of these [venire members] because they\\n worked in the church; Sunday School teachers and Sunday\\n School leaders, and things of that nature, and . . . I knew\\n the defense counsel, if it came to the second phase of the\\n sentencing hearing, would be asking the jurors to show\\n mercy. And, it was my opinion that this argument would\\n be receptive to someone who worked in the church and\\n was well versed in the Bible more than someone who was\\n not; be a female or male juror that was a strong worker in\\n the church. No male jurors that was [sic] left seated on the\\n jury worked in the church.\\n\\nIn response, Smith’s counsel argued that the prosecution did not strike everyone\\n\\nwho had religious affiliations 1 and questioned why the prosecution had not asked\\n\\n\\n1\\n At the hearing, Smith’s counsel did not identify any men with religious affiliations who were\\nnot struck by the prosecution. Smith’s counsel identified one woman, Ms. Parham, who may\\n\\n\\n 3\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 4 of 31\\n\\n\\nany follow-up questions about the venire members’ religious beliefs. Next, the\\n\\nprosecutor explained that he eliminated the sole Hispanic venire member because\\n\\nshe was young and did not respond to questions during voir dire; Smith’s counsel\\n\\nargued this explanation was insufficient.\\n\\n The state trial court ultimately found that the prosecutor’s reasons for\\n\\nstriking the female venire members were gender neutral, that those reasons were\\n\\ncredible, and that Smith had failed to prove that the prosecutor had acted in a\\n\\ndiscriminatory manner. On appeal after remand, the Alabama CCA affirmed.\\n\\nSmith v. State, 838 So. 2d 413 (Ala. Crim. App. 2002) (hereinafter Smith II). The\\n\\nSupreme Court denied Smith’s petition for writ of certiorari. Smith v. Alabama,\\n\\n537 U.S. 1090 (2002).\\n\\n B. Smith’s Post-Conviction Hearings\\n\\n Smith then filed a petition for state post-conviction relief under Alabama\\n\\nRule of Criminal Procedure 32. The petition included a claim of intellectual\\n\\ndisability, and the Rule 32 court conducted an evidentiary hearing on this claim.\\n\\n At the hearing, Dr. Salekin, Smith’s expert, testified that Smith scored a 64\\n\\non a full IQ test and exhibited adaptive deficits in several areas. Dr. Salekin also\\n\\n\\nhave worked in a church but was not struck by the prosecution. In later briefing at the trial court,\\nSmith identified John Hall, who served as a football coach for the Young Men’s Christian\\nAssociation (YMCA), but was not struck by the prosecution. Finally, in his appellate briefing,\\nSmith raised “Mr. Johnson,” an unidentified male member of the venire who stated that he\\nserved on his church’s board, but was not struck by the prosecution.\\n\\n\\n 4\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 5 of 31\\n\\n\\ntestified, however, that Smith scored relatively well on a separate test that assessed\\n\\nSmith’s language, reading, and mathematics skills, and that these particular results\\n\\nwere inconsistent with a diagnosis of intellectual disability. Dr. Salekin’s final\\n\\nopinion was that Smith was not intellectually disabled. Dr. Salekin also testified\\n\\nthat there was no national medical consensus on using the “Flynn Effect” to adjust\\n\\nIQ scores.2\\n\\n The state called Dr. King, who testified that Smith scored a 72 on a full IQ\\n\\ntest, including verbal score of 75 and nonverbal score of 74.3 Smith’s score on the\\n\\nverbal portion of Dr. King’s IQ test matched a previous score he achieved on the\\n\\nverbal portion of a partial IQ test administered by Dr. Blotcky, a court-appointed\\n\\npsychologist.4 Like Dr. Salekin, Dr. King’s final opinion was that Smith was not\\n\\nintellectually disabled, and he agreed that there was no national medical consensus\\n\\non using the Flynn Effect to adjust IQ scores.\\n\\n The Rule 32 court denied Smith’s Rule 32 petition, and the Alabama CCA\\n\\naffirmed. Smith v. State, 112 So. 3d 1108 (Ala. Crim. App. 2012) (Smith III), cert.\\n\\ndenied, Ex parte Smith, 112 So. 3d 1152 (Ala. 2012).\\n\\n C. Further Procedural History\\n\\n\\n\\n2\\n The “Flynn Effect” is a theory that contends that IQ scores have been increasing over time and\\nsuggests that IQ scores should be recalibrated in order to reflect this increase.\\n3\\n Dr. King also testified that, using a standard error of measurement, Smith’s IQ could have been\\nas low as 68 or as high as 77.\\n4\\n Dr. Blotcky never administered a full IQ test, for reasons that remain unexplained.\\n 5\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 6 of 31\\n\\n\\n Smith filed his original federal habeas petition in the Northern District of\\n\\nAlabama, which the district court denied. One day after denying Smith’s petition,\\n\\nthe district court reopened the action for the sole purpose of considering the effect,\\n\\nif any, of Moore v. Texas, 137 S. Ct. 1039 (2017), on Smith’s Atkins claim. After\\n\\nsupplemental briefing, the district court concluded that Moore did not apply\\n\\nretroactively and reaffirmed the denial of Smith’s petition. The district court\\n\\ngranted Smith a COA on his Atkins claim, and we granted him a COA on his\\n\\nBatson claim.\\n\\n II. Standard of Review\\n\\n We review de novo the district court’s denial of a 28 U.S.C. § 2254 petition.\\n\\nWard v. Hall, 592 F.3d 1144, 1155 (11th Cir. 2010). Because Smith filed his\\n\\npetition after April 24, 1996, this appeal is governed by the Antiterrorism and\\n\\nEffective Death Penalty Act of 1996 (AEDPA). AEDPA “establishes a highly\\n\\ndeferential standard for reviewing state court judgments.” Parker v. Sec’y, Dep’t.\\n\\nof Corr., 331 F.3d 764, 768 (11th Cir. 2003). Under AEDPA, a federal court may\\n\\nonly grant a writ of habeas corpus if the state court’s determination of a federal\\n\\nclaim was (1) “contrary to, or involved an unreasonable application of, clearly\\n\\nestablished Federal law” or (2) “was based on an unreasonable determination of\\n\\nthe facts in light of the evidence presented in the State court proceeding.” 28\\n\\nU.S.C. § 2254(d).\\n\\n\\n 6\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 7 of 31\\n\\n\\n The phrase “clearly established Federal law” encompasses only the holdings\\n\\nof the Supreme Court of the United States “as of the time of the relevant state-court\\n\\ndecision.” Williams v. Taylor, 529 U.S. 362, 412 (2000). Section 2254(d)\\n\\nprovides two separate bases for reviewing state court decisions—“the ‘contrary to’\\n\\nand ‘unreasonable application’ clauses articulate independent considerations a\\n\\nfederal court must consider.” Maharaj v. Sec’y, Dep’t of Corr., 432 F.3d 1292,\\n\\n1308 (11th Cir. 2005).\\n\\n A state court’s determination is “contrary to” clearly established federal law\\n\\n“if the state court arrives at a conclusion opposite to that reached by [the Supreme\\n\\nCourt] on a question of law or if the state court decides a case differently than [the\\n\\nSupreme Court] has on a set of materially indistinguishable facts.” Williams, 529\\n\\nU.S. at 413. A state court’s determination is “an unreasonable application” of\\n\\nclearly established federal law “if the state court identifies the correct governing\\n\\nlegal principle from [the Supreme Court’s] decisions but unreasonably applies that\\n\\nprinciple to the facts of the prisoner’s case.” Id. Reasonableness is objective, and\\n\\na federal court may not issue a writ of habeas corpus simply because it concludes\\n\\nin its independent judgment that the state court was incorrect. Id. at 410.\\n\\n Finally, under § 2254(d)(2), we presume that the state court’s findings of\\n\\nfact are correct unless rebutted by clear and convincing evidence. See 28 U.S.C. §\\n\\n2254(e)(1). “This deference requires that a federal habeas court more than simply\\n\\n\\n 7\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 8 of 31\\n\\n\\ndisagree with the state court before rejecting its factual determinations. Instead, it\\n\\nmust conclude that the state court’s findings lacked even fair support in the\\n\\nrecord.” Rose v. McNeil, 634 F.3d 1224, 1241 (11th Cir. 2011) (citations omitted).\\n\\n\\n III. Atkins Claim\\n\\n Smith first argues that the district court erred in holding that the Supreme\\n\\nCourt’s recent holding in Moore v. Texas did not apply retroactively to his\\n\\nintellectual disability claim. We agree with the district court that Moore is not\\n\\nretroactive. Smith also argues that the Alabama state courts unreasonably applied\\n\\nAtkins v. Virginia in evaluating his intellectual disability claim. After careful\\n\\nreview of the state court record and its order, we hold that the state court’s denial\\n\\nof his intellectual disability claim was not an unreasonable application of clearly\\n\\nestablished federal law.\\n\\n A. The Non-Retroactivity of Moore v. Texas\\n\\n In Atkins v. Virginia, the predecessor to Moore, the Supreme Court held that\\n\\nthe execution of individuals with intellectual disabilities violated the Eighth\\n\\nAmendment. 536 U.S. 304 (2002). But the Court did not define what it means to\\n\\nbe intellectually disabled, leaving that task to individual state legislatures and\\n\\ncourts. Id. at 317. In the years following Atkins, states developed different criteria\\n\\nfor assessing intellectual disability. Some states delineated a bright line threshold\\n\\nfor IQ scores, while others did not.\\n\\n 8\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 9 of 31\\n\\n\\n In Hall v. Florida, the Court clarified that a state court’s intellectual\\n\\ndisability determination should be “informed by the medical community's\\n\\ndiagnostic framework.” 572 U.S. 701, 721 (2014). This meant, among other\\n\\nthings, that courts must consider the standard error inherent in IQ tests when a\\n\\ndefendant’s test scores put him “within the clinically established range for\\n\\nintellectual-functioning deficits.” Moore, 137 S. Ct. at 1050; see also Hall, 572\\n\\nU.S. at 723. In those cases, defendants must be allowed to present additional\\n\\nevidence of intellectual disability, including testimony on adaptive deficits. Hall,\\n\\n572 U.S. at 723.\\n\\n In Moore, the Court expanded on Hall, reiterating that state courts do not\\n\\nhave “unfettered discretion” in their determination of whether a capital defendant\\n\\nis intellectually disabled. 137 S. Ct. at 1052. Specifically, Moore established that\\n\\nstates cannot disregard current clinical and medical standards in assessing whether\\n\\na capital defendant is intellectually disabled. In addition, the Court clarified that\\n\\nunder prevailing clinical standards, the focus of the adaptive functioning inquiry\\n\\nshould be an individual’s adaptive deficits—not adaptive strengths. Id. at\\n\\n1050−51. After Moore, states cannot “weigh” an individual’s adaptive strengths\\n\\nagainst his adaptive deficits.\\n\\n Because Moore was decided five years after the Alabama state courts\\n\\ndecided Smith’s Atkins claim, he concedes that Moore could not have been “clearly\\n\\n\\n 9\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 10 of 31\\n\\n\\nestablished Federal law” at that time. Smith instead argues that Moore announced\\n\\na new rule of constitutional law that should be applied retroactively under Teague\\n\\nv. Lane, 489 U.S. 288 (1989).\\n\\n New constitutional rules are generally not retroactive for cases on federal\\n\\nhabeas review. See id. To determine whether a rule is retroactive, we first decide\\n\\nif it is a new rule. Under Teague, “a case announces a new rule when it breaks\\n\\nnew ground or imposes a new obligation on the States or the Federal Government,”\\n\\nor when “the result was not dictated by [prior] precedent.” Id. at 301.\\n\\n If the rule is indeed new, we then decide whether it falls into one of\\n\\nTeague’s two exceptions to the general bar on retroactivity. The first exception is\\n\\nfor substantive rules of constitutional law that place an entire category of primary\\n\\nconduct beyond the reach of the criminal law, including “rules prohibiting a certain\\n\\ncategory of punishment for a class of defendants because of their status or\\n\\noffense.” See Penry v. Lynaugh, 492 U.S. 302, 330 (1989). The second exception\\n\\nis for “watershed rules of criminal procedure” that are necessary to the\\n\\nfundamental fairness of criminal proceedings. Teague, 489 U.S. at 311−12. It is\\n\\ngenerally very difficult to meet the requirements of the second exception. See,\\n\\ne.g., Saffle v. Parks, 494 U.S. 484, 495 (1990) (noting that the rule announced in\\n\\nGideon v. Wainwright, 372 U.S. 335 (1963), illustrates the type of rule meeting\\n\\nthis second exception).\\n\\n\\n 10\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 11 of 31\\n\\n\\n Smith argues that Moore falls under the first Teague exception because\\n\\nMoore announced a new substantive rule of constitutional law that prohibits “a\\n\\ncertain category of punishment for a class of defendants because of their status or\\n\\noffense.” Penry, 492 U.S. at 330. Smith argues that Moore, which requires states\\n\\nto consider the medical community’s current clinical standards to determine\\n\\nintellectual disability, effectively expands the class of people who are ineligible for\\n\\nthe death penalty. Smith argues that Moore’s holding was thus substantive—not\\n\\nprocedural. We disagree.\\n\\n Substantive rules “set forth categorical constitutional guarantees that place\\n\\ncertain criminal laws and punishments altogether beyond the State’s power to\\n\\nimpose,” while procedural rules “are designed to enhance the accuracy of a\\n\\nconviction or sentence by regulating the manner of determining the defendant’s\\n\\nculpability.” Montgomery v. Louisiana, 136 S. Ct. 718, 729–30 (2016) (internal\\n\\nquotation marks omitted). For example, rules that “allocate decisionmaking\\n\\nauthority” between judge and jury, or “regulate the evidence that the court could\\n\\nconsider in making its decision” are procedural. Welch v. United States, 136 S. Ct.\\n\\n1257, 1265 (2016).\\n\\n Moore established that states cannot disregard current clinical and medical\\n\\nstandards in assessing whether a capital defendant is intellectually disabled.\\n\\nMoore effectively narrowed the range of permissible methods—the procedure—\\n\\n\\n 11\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 12 of 31\\n\\n\\nthat states may use to determine intellectual disability. While Moore may have the\\n\\neffect of expanding the class of people ineligible for the death penalty, it merely\\n\\ndefined the appropriate manner for determining who belongs to that class of\\n\\ndefendants ineligible for the death penalty. Moore thus announced a new rule, but\\n\\nit is procedural, not substantive.5\\n\\n Because Moore announced a procedural rule, it can only be retroactive if it\\n\\nmeets Teague’s second exception. Doing so is extraordinarily rare. See, e.g.,\\n\\nSchriro v. Summerlin, 542 U.S. 348, 351–52 (2004). “To fall within this\\n\\nexception, a new rule must meet two requirements: Infringement of the rule must\\n\\n\\n\\n\\n5\\n In Kilgore v. Secretary, Florida Department of Corrections, this Court held that Hall is not a\\nsubstantive rule under Teague. 805 F.3d 1301, 1314 (11th Cir. 2015) (relying on In re Henry,\\n757 F.3d 1151, 1161 (11th Cir. 2014)). Alabama argues that we should rely on Kilgore’s\\nreasoning to conclude that Moore is likewise not a substantive rule under Teague. We decline to\\ndo so because the Supreme Court’s decision in Montgomery v. Louisiana undermined a core\\ncomponent of Kilgore’s retroactivity analysis, which Kilgore borrowed from In re Henry. In\\nKilgore, we reasoned that Hall was not substantive under Teague because it “guaranteed only a\\nchance to present evidence, not ultimate relief.” Kilgore, 805 F.3d at 1314; see also In re Henry,\\n757 F.3d at 1161. But Montgomery later deemed a rule substantive in nature—the rule of Miller\\nv. Alabama, 567 U.S. 460 (2012), which prohibited mandatory life without parole sentences for\\njuveniles—even though all that rule guaranteed was “[a] hearing where ‘youth and its attendant\\ncharacteristics’ are considered as sentencing factors,” not a shorter sentence or parole.\\nMontgomery, 136 S. Ct. at 735 (quoting Miller, 567 U.S. at 465). Montgomery thus stands for\\nthe proposition that a right can be substantive under Teague even if it only guarantees the chance\\nto present evidence in support of relief sought, not ultimate relief itself. See, e.g., In re Sapp,\\n827 F.3d 1334, 1340–41 (11th Cir. 2016) (Jordan, Rosenbaum, and Jill Pryor, JJ., concurring).\\nBecause Montgomery undermined the reasoning of Kilgore and In re Henry, we do not rely on\\nthem to reach our decision. See Chambers v. Thompson, 150 F.3d 1324, 1326 (11th Cir. 1998);\\nsee also Davis v. Singletary, 119 F.3d 1471, 1482 (11th Cir. 1997) (“To the extent of any\\ninconsistency between [our prior] pronouncements and the Supreme Court’s supervening ones,\\nof course, we are required to heed those of the Supreme Court.”).\\n\\n\\n 12\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 13 of 31\\n\\n\\nseriously diminish the likelihood of obtaining an accurate conviction [or sentence],\\n\\nand the rule must alter our understanding of the bedrock procedural elements\\n\\nessential to the fairness of a proceeding.” Tyler v. Cain, 533 U.S. 656, 665 (2001)\\n\\n(quotation omitted).\\n\\n Only Gideon v. Wainwright, 372 U.S. 335 (1963), which extended the right\\n\\nto counsel to criminal defendants, has been declared the kind of procedural rule\\n\\nthat altered the “bedrock procedural elements” essential to the fairness of a\\n\\nproceeding. See Beard v. Banks, 542 U.S. 406, 416−18 (2004) (noting that\\n\\nGideon’s holding was sweeping and broke with past precedent). The Supreme\\n\\nCourt has continually rejected retroactivity under Teague’s second exception for\\n\\nprocedural rules that do not have the “primacy” or “centrality” of Gideon. See,\\n\\ne.g., Wharton v. Bocking, 549 U.S. 406, 421 (2007) (rejecting retroactivity for\\n\\nCrawford v. Washington, 541 U.S. 36 (2004)); Schriro, 542 U.S. at 356−58\\n\\n(rejecting retroactivity for Ring v. Arizona, 546 U.S. 584 (2002)). Both Crawford 6\\n\\nand Ring7 were important holdings for the rights of criminal defendants, and yet\\n\\n\\n\\n\\n6\\n In Crawford v. Washington, 541 U.S. 36 (2004), the Supreme Court held that the Sixth\\nAmendment’s Confrontation Clause prohibits the state from introducing testimonial hearsay as\\nevidence against criminal defendants unless the declarant is unavailable and the defendant had a\\nprior opportunity to cross-examine the declarant.\\n7\\n In Ring v. Arizona, 536 U.S. 584 (2002), the Supreme Court held that the Sixth Amendment\\nguarantees criminal defendants the right to have a jury, not a sentencing judge, find the\\naggravating circumstances necessary for the imposition of the death penalty.\\n 13\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 14 of 31\\n\\n\\nthe Supreme Court held that neither altered the bedrock procedural elements\\n\\nessential to the fairness of a criminal proceeding, and thus neither was retroactive.\\n\\n Similarly, Moore is an important development. It provides guidance to\\n\\nstates attempting to comply with Atkins. But we cannot say that Moore altered the\\n\\nbedrock procedural elements essential to the fairness of a criminal proceeding in\\n\\nthe way that the Gideon rule did. Because Moore cannot meet the requirements of\\n\\nTeague’s second exception, it cannot be applied retroactively.\\n\\n B. Analysis of Smith’s Atkins Claim\\n\\n Smith argues that, even if Moore is not retroactive, the Alabama courts\\n\\nunreasonably applied Atkins v. Virginia to his intellectual disability claim.\\n\\n 1. The State Court Record\\n\\n Shortly after Atkins, the Alabama Supreme Court held that to be\\n\\nintellectually disabled under Atkins, a defendant must prove by a preponderance of\\n\\nthe evidence: (1) “significantly subaverage intellectual functioning (an IQ of 70 or\\n\\nbelow),” (2) “significant or substantial deficits in adaptive behavior,” and (3) that\\n\\nboth the subaverage intellectual functioning and the deficits in adaptive\\n\\nfunctioning manifested before the age of eighteen. Ex Parte Perkins, 851 So. 2d\\n\\n453, 456 (Ala. 2002).\\n\\n Smith raised his Atkins claim in his Rule 32 petition shortly after Perkins.\\n\\nThe Rule 32 court ultimately denied his petition, finding it relevant, but not\\n\\n\\n 14\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 15 of 31\\n\\n\\ndispositive, that no expert—not even Smith’s own expert—testified that Smith was\\n\\nintellectually disabled. The court then evaluated the Perkins factors and concluded\\n\\nthat Smith failed to prove by a preponderance of the evidence that he was\\n\\nintellectually disabled.\\n\\n First, the court determined that Smith failed to satisfy his burden of showing\\n\\nsignificantly subaverage intellectual functioning. The court noted that the experts\\n\\nhad presented conflicting evidence and testimony: Dr. Salekin reported that Smith\\n\\nhad an IQ of 64, while Dr. King reported an IQ of 72. The court ultimately\\n\\ncredited Dr. King’s IQ score as “probably more accurate” than Dr. Salekin’s score\\n\\nin part because Dr. King’s test resulted in a verbal IQ of 75, the same verbal IQ\\n\\nthat Smith received on a prior IQ test. The court also declined to adjust Smith’s IQ\\n\\nscores downward because the experts all testified that there was no national\\n\\nmedical consensus on using the Flynn Effect to adjust IQ scores.\\n\\n On the second Perkins prong, the court determined that Smith failed to\\n\\nsatisfy his burden of showing significant deficits in adaptive behavior. The court\\n\\nconcluded that, “[a]lthough [Smith] showed deficits in adaptive functioning based\\n\\nupon test results,” Smith did not show many deficits in his adaptive functioning “in\\n\\neveryday life” either before or after his crime. The court noted that Smith showed\\n\\nrelatively normal scores in functional academics and communication. And while\\n\\nhe did have some possible deficiencies, the court reasoned that those deficits were\\n\\n\\n 15\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 16 of 31\\n\\n\\nnot so significant that Smith could not succeed in school, work, or society in\\n\\ngeneral. The court also indicated that Smith’s ability to plan and conceal his crime\\n\\n“weigh[ed] against [him] in relation to the adaptive functioning requirement.”\\n\\n On appeal, the Alabama CCA affirmed, holding that the Rule 32 court did\\n\\nnot abuse its discretion in concluding that Smith had failed to prove that he was\\n\\nintellectually disabled. Smith III, 112 So. 3d at 1108. As the Alabama CCA\\n\\nsummarized, “[t]he greater weight of the evidence indicated that, although he\\n\\nsuffered with some mental deficiencies, they did not rise to the level at which an\\n\\nimpartial mind would conclude from the evidence that he was mentally retarded.”\\n\\nId. at 1130.\\n\\n As to intellectual functioning, the Alabama CCA found that the Rule 32\\n\\ncourt did not err in declining to apply the Flynn Effect or standard error to Smith’s\\n\\nIQ score. Id. at 1131. The Alabama CCA also endorsed the Rule 32 court’s\\n\\napproach to examining adaptive functioning, explaining that “[e]ven where there\\n\\nare indications of shortfalls in adaptive behavior, other relevant evidence may\\n\\nweigh against an overall finding of deficiency.” Id. at 1133. Because the Alabama\\n\\nCCA found that Smith failed to prove both significantly subaverage intellectual\\n\\nfunctioning and significant deficits in adaptive behavior, the court did not fully\\n\\naddress the third prong of Perkins—whether those shortfalls in intellectual and\\n\\nadaptive functioning had manifested before the age of eighteen.\\n\\n\\n 16\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 17 of 31\\n\\n\\n 2. Analysis Under 28 U.S.C. § 2254(d)(1)\\n\\n Smith argues that the Alabama state courts unreasonably applied Atkins v.\\n\\nVirginia to his intellectual disability claim by (1) determining that Smith’s IQ\\n\\nscores did not meet the standard for intellectual disability, (2) failing to consider\\n\\nthe standard error and Flynn Effect in assessing Smith’s IQ scores, and (3) giving\\n\\nmore weight to Smith’s adaptive strengths than to his adaptive deficits in assessing\\n\\nhis adaptive functioning.\\n\\n A state court’s determination is an unreasonable application of clearly\\n\\nestablished federal law “if the state court identifies the correct governing legal\\n\\nprinciple from this Court’s decisions but unreasonably applies that principle to the\\n\\nfacts of the [petitioner’s] case.” Williams v. Taylor, 529 U.S. 362, 413 (2000).\\n\\nThe difficulty for Smith—and other litigants mounting this challenge—is that\\n\\nAtkins set forth few legal governing principles for lower courts and states\\n\\nevaluating intellectual disability. The Supreme Court’s decision in Atkins did not\\n\\ndefine what it means to be intellectually disabled, instead leaving that task to the\\n\\nstates. See Atkins, 536 U.S. at 317. The Supreme Court itself recently explained\\n\\nthat “Atkins gave no comprehensive definition of ‘mental retardation’ for Eighth\\n\\nAmendment purposes.” Shoop v. Hill, 139 S. Ct. 504, 507 (2019).\\n\\n i. Intellectual Functioning\\n\\n\\n\\n\\n 17\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 18 of 31\\n\\n\\n Smith first argues that the Alabama state courts unreasonably applied Atkins\\n\\nv. Virginia by refusing to credit Dr. Salekin’s testimony that Smith had an IQ of 64\\n\\nand consequently determining that Smith’s IQ scores did not satisfy the first\\n\\nPerkins prong of subaverage intellectual functioning. According to Smith, “[t]he\\n\\nrefusal to use the IQ score of 64 in an average with the other scores, or otherwise\\n\\ndiscount [Dr. King’s] score of 72 based on the IQ score of 64, was an unreasonable\\n\\napplication of Atkins to the present case.” 8 Smith also argues it was an\\n\\nunreasonable application of Atkins to refuse to account for the Flynn Effect or\\n\\nstandard error when the state court evaluated Smith’s IQ.\\n\\n But Atkins did not set forth clearly established federal law on how states\\n\\nmust evaluate IQ scores in determining intellectual disability. “Atkins did not\\n\\ndefine intellectual disability, nor did it direct the states on how to define\\n\\nintellectual disability, nor, finally, did it provide the range of IQ scores that could\\n\\nbe indicative of intellectual disability.” Kilgore v. Sec’y, Fla. Dep’t of Corr., 805\\n\\n\\n\\n8\\n In his initial brief, Smith does not argue that the Alabama court’s decision to refuse to fully\\ncredit Dr. Salekin’s IQ score was an unreasonable determination of the facts under 28 U.S.C.\\n§ 2254(d)(2). Smith raises this argument only in his reply brief. We generally do not consider\\nissues and arguments raised for the first time in an appellant’s reply brief. See, e.g., United\\nStates v. Levy, 379 F.3d 1241, 1244 (11th Cir. 2004). In any event, it is unlikely that the state\\ncourt made an unreasonable factual determination in crediting Dr. King’s score over Dr.\\nSalekin’s score. While we agree that it might have been preferable to average both IQ scores\\nunder these circumstances, “a state-court factual determination is not unreasonable merely\\nbecause the federal habeas court would have reached a different conclusion in\\nthe first instance.” Wood v. Allen, 558 U.S. 290, 301 (2010). Here, the state court used an\\nadditional IQ score in the record—albeit a partial score—to corroborate Dr. King’s test. We\\ncannot say that the decision to do so was an unreasonable factual determination.\\n 18\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 19 of 31\\n\\n\\nF.3d 1301, 1311 (11th Cir. 2015); see also Bobby v. Bies, 556 U.S. 825, 831 (2009)\\n\\n(“[Atkins] did not provide definitive procedural or substantive guides for\\n\\ndetermining when a person who claims [intellectual disability] will be so impaired\\n\\nas to fall within [Atkins’ compass]” (internal citation and quotation marks\\n\\nomitted)). Without clear guidance from Atkins, the state court’s refusal to average\\n\\nIQ scores or to account for certain statistical adjustments was not an unreasonable\\n\\napplication of clearly established federal law.\\n\\n Smith’s specific argument about the state court’s failure to consider the\\n\\nstandard error is foreclosed by our precedent. As we explained in Kilgore,\\n\\n“[n]othing in Atkins suggested that a bright-line IQ cutoff of 70 ran afoul of the\\n\\nprohibition on executing the intellectually disabled.” 805 F.3d at 1312. In other\\n\\nwords, Atkins did not require states to consider the standard error in assessing IQ\\n\\nscores. That requirement did not emerge until Hall v. Florida, 572 U.S. 701\\n\\n(2014), well after the Alabama courts considered Smith’s case.\\n\\n Altogether, Smith’s arguments generally conflate what we have previously\\n\\npermitted in evaluating intellectual disability with what is required. While we\\n\\nhave previously said that the Flynn Effect may be considered in determining a\\n\\ndefendant’s IQ, see Thomas v. Allen, 607 F.3d 749, 753 (11th Cir. 2010), neither\\n\\nthis Court nor the Supreme Court has required courts to do so. Similarly, while we\\n\\nhave previously permitted district courts to average multiple IQ scores, see\\n\\n\\n 19\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 20 of 31\\n\\n\\nHolladay v. Allen, 555 F.3d 1346, 1357−58 (11th Cir. 2009), courts are not\\n\\nnecessarily required to do so.\\n\\n ii. Adaptive Functioning\\n\\n Next, Smith argues that the Alabama courts unreasonably applied Atkins by\\n\\nfavoring Smith’s adaptive strengths over his adaptive deficits. The Supreme Court\\n\\nrecently rejected this argument in Shoop v. Hill, 139 S. Ct. 504 (2019).\\n\\n In Hill v. Anderson, the Sixth Circuit held that Moore’s holding about\\n\\nadaptive strengths was clearly established law because Moore was “merely an\\n\\napplication of what was clearly established by Atkins.” 881 F.3d 483, 487 (6th Cir.\\n\\n2018). But the Supreme Court reversed the Sixth Circuit and soundly rejected this\\n\\nargument in Shoop, explaining that “Atkins did not definitively resolve how [the\\n\\nadaptive functioning prong] was to be evaluated but instead left its application in\\n\\nthe first instance to the State.” 139 S. Ct. at 508. Because Atkins did not provide\\n\\ndefinitive guidance to states on how to evaluate a petitioner’s adaptive functioning,\\n\\nthe Alabama courts here could not have unreasonably applied Atkins in choosing to\\n\\nweigh Smith’s adaptive strengths against his adaptive weaknesses.\\n\\n Smith’s success on this claim is a matter of timing. After Moore v. Texas, it\\n\\nis abundantly clear that states may not weigh a defendant’s adaptive strengths\\n\\nagainst his adaptive deficits. Doing so contradicts the medical community’s\\n\\ncurrent clinical standards. Moore, 137 S. Ct. at 1050−51. As the Supreme Court\\n\\n\\n 20\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 21 of 31\\n\\n\\nexplained in Moore, many individuals with intellectual disabilities have both\\n\\nadaptive deficits and adaptive strengths, and “significant limitations in conceptual,\\n\\nsocial, or practical adaptive skills [are] not outweighed by the potential strengths in\\n\\nsome adaptive skills.” Id. at 1050 (citation omitted).\\n\\n Alabama argues that the state court did not weigh Smith’s adaptive strengths\\n\\nagainst his adaptive deficits. We firmly disagree. Despite concluding that Smith\\n\\n“showed deficits in adaptive functioning based upon test results,” the state court\\n\\nconsidered other factors that weighed against “an overall finding of deficiency,”\\n\\ntreating the adaptive functioning prong like a balancing test. In particular, the state\\n\\ncourt considered Smith’s ability to conceal his crime, ability to take care of his\\n\\nmother, and his scores on certain mathematics and reading tests as adaptive\\n\\nstrengths that outweighed his apparent deficits. This approach was acceptable at\\n\\nthe time. But after Moore, it no longer is.\\n\\n IV. Batson Claim\\n\\n Smith argues that the prosecutor at his state trial struck jurors on the basis of\\n\\ngender and national origin 9 in violation of the Sixth and Fourteenth Amendments.\\n\\n\\n\\n9\\n At the district court, Smith also asserted a race discrimination claim because the prosecutor\\nused five of his peremptory strikes to eliminate black venire members. On appeal, however,\\nSmith makes only vague and passing reference to racial discrimination. Therefore, we address\\nonly his gender and national origin discrimination claims. See Sapuppo v. Allstate Floridian Ins.\\nCo., 739 F.3d 678, 681 (11th Cir. 2014) (noting that “an appellant abandons a claim when he\\neither makes only passing references to it or raises it in a perfunctory manner without supporting\\narguments and authority”).\\n 21\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 22 of 31\\n\\n\\nSee Batson v. Kentucky, 476 U.S. 79 (1986); J.E.B. v. Alabama, 511 U.S. 127\\n\\n(1994). After careful review, we hold that the state court’s denial of Smith’s\\n\\nclaims was not contrary to Batson and its progeny, an unreasonable application of\\n\\nBatson, or an unreasonable determination of the facts in light of the evidence\\n\\npresented to the state courts.\\n\\n A. Clearly Established Law\\n\\n Under the Equal Protection Clause, a criminal defendant has a constitutional\\n\\nright “to be tried by a jury whose members are selected pursuant to\\n\\nnondiscriminatory criteria.” Batson, 476 U.S. at 85–86. In Batson, the Supreme\\n\\nCourt set out a three-part test to “guide trial courts’ constitutional review of\\n\\nperemptory strikes.” Johnson v. California, 545 U.S. 162, 168 (2005). Under the\\n\\nthree-part test,\\n\\n [f]irst, the defendant must make out a prima facie case by\\n showing that the totality of the relevant facts gives rise to\\n an inference of discriminatory purpose. Second . . . the\\n burden shifts to the State to explain adequately the racial\\n exclusion by offering permissible race-neutral\\n justifications for the strikes. Third, if a race-neutral\\n explanation is tendered, the trial court must then\\n decide . . . whether the opponent of the strike has proved\\n purposeful racial discrimination.\\n\\nId. (internal quotation marks, citations, and footnotes omitted). At the first step, a\\n\\ndefendant makes a prima facie case of discrimination if the circumstances allow\\n\\nfor a permissible inference of discrimination. Id. at 162. At the second step, the\\n\\n\\n 22\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 23 of 31\\n\\n\\ncourt evaluates only the “facial validity of the prosecutor’s explanation,” and\\n\\nunless a discriminatory intent is “inherent in the prosecutor’s explanation, the\\n\\nreason offered will be deemed race neutral.” Purkett v. Elem, 514 U.S. 765, 768\\n\\n(1995) (quotation omitted). The third step “involves evaluating the persuasiveness\\n\\nof the justification” proffered by the prosecutor, and “[a]t that stage, implausible or\\n\\nfantastic justifications may (and probably will) be found to be pretexts for\\n\\npurposeful discrimination.” Id. Inconsistent and disparate treatment of venire\\n\\nmembers is evidence that the proffered reasons are post-strike excuses and not\\n\\nlegitimate race or gender-neutral justifications. See, e.g., Snyder v. Louisiana, 552\\n\\nU.S. 472, 483 (2008).\\n\\n The evaluation of a prosecutor’s race-neutral or gender-neutral explanation\\n\\nfor a strike under Batson is a “pure issue of fact . . . peculiarly within a trial judge’s\\n\\nprovince.” McNair v. Campbell, 416 F.3d 1291, 1310 (11th Cir. 2005) (quotation\\n\\nomitted). Even on direct review, a trial judge’s finding on intentional\\n\\ndiscrimination is entitled to “great deference.” See Batson, 476 U.S. at 98 n.21. At\\n\\nthe habeas stage, the burden is even higher; the petitioner must show “it was\\n\\nunreasonable to credit the prosecutor’s race-neutral explanations” under\\n\\n§ 2254(d)(2). Rice v. Collins, 546 U.S. 333, 338 (2006).\\n\\n B. Analysis of Smith’s Batson Claim\\n\\n\\n\\n\\n 23\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 24 of 31\\n\\n\\n Smith argues that the state court’s determination that he failed to prove\\n\\npurposeful discrimination was (1) an unreasonable determination of the facts under\\n\\n28 U.S.C. § 2254(d)(2) and (2) both contrary to and an unreasonable application of\\n\\nBatson and its progeny under 28 U.S.C. § 2254(d)(1). Before we address those\\n\\nclaims, we briefly review the state court record.\\n\\n 1. State Court Record\\n\\n On remand, the prosecutor offered explanations for striking each female\\n\\nvenire member. Those explanations included employment, marital status, age,\\n\\nknowledge of criminal law, and work with various churches and religious groups.\\n\\nIn its order on remand, the state trial court evaluated the prosecutor’s reasoning for\\n\\nstriking each female venire member. The trial court found that the prosecutor’s\\n\\nexplanation for each member was supported by the record. The court confirmed,\\n\\nfor example, that each woman allegedly struck for her religious affiliations stated\\n\\nduring voir dire, or indicated on her questionnaire, that she was active in her\\n\\nchurch or taught Sunday School. The court noted that excluding potential jurors\\n\\nwho were susceptible to mercy arguments was a sound trial strategy. Further,\\n\\nwhere the prosecutor explained a strike based on a venire member’s demeanor, the\\n\\ntrial court corroborated the prosecutor’s explanation with its own trial notes. The\\n\\nstate trial court ultimately held that the prosecutor’s reasons for striking the female\\n\\nvenire members were gender neutral, that those reasons were credible, and that\\n\\n\\n 24\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 25 of 31\\n\\n\\nSmith had failed to prove that the prosecutor had acted in a discriminatory\\n\\nmanner.10\\n\\n On appeal, the Alabama CCA concluded that the trial court’s determination\\n\\nwas not clearly erroneous. Smith II, 838 So. 2d at 436, 466. The Alabama CCA\\n\\nfocused its analysis on four women who, according to the prosecutor, were\\n\\neliminated because of their religious affiliations. The court noted that three of the\\n\\nfour women were Sunday School teachers; the other was a Counselor of Ministry.\\n\\nSee id. at 426−27.\\n\\n The Alabama CCA then acknowledged Smith’s argument that the\\n\\nprosecutor’s stated reason for striking these jurors was pretextual. The court\\n\\nconsidered, for example, Smith’s argument that several women who had been\\n\\neliminated for church involvement had also previously affirmed that their religious\\n\\nbeliefs would not preclude them from imposing a death sentence. The Alabama\\n\\nCCA also considered Smith’s argument that the prosecutor had not asked the\\n\\n\\n\\n\\n10\\n At the end of his order, the state trial court judge also noted that the prosecutor was “certainly\\nnot a person prone to strike minorities denounced in the Batson case and its progeny.” The judge\\nbased this conclusion on his “extensive in court experience with [the prosecutor] and close\\nacquaintanceship with others that know him.” We note that the court’s role in hearing a Batson\\nclaim is to evaluate whether the prosecutor’s stated reasons for excluding members of the jury\\nare credible and supported by the record, not to personally attest to the prosecutor’s character or\\nto provide its own reasons for why the prosecutor could not have discriminated in the present\\ncase. See Adkins v. Warden, Holman CF, 710 F.3d 1241, 1254 & n.11 (11th Cir. 2013)\\n(indicating that, at Batson’s third step, it is improper for the trial court to rely on its personal\\nexperience with and opinion about the reputation of a prosecutor where those facts are not in\\nevidence).\\n 25\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 26 of 31\\n\\n\\nwomen follow-up questions about their religious beliefs before striking them. But\\n\\nafter taking those arguments into account, the court found that Smith had not\\n\\nshown that the trial court’s credibility determination was clearly erroneous. The\\n\\nAlabama CCA thus affirmed the trial court’s finding that the prosecutor’s reasons\\n\\nfor striking the jurors were nondiscriminatory. Id. at 436.\\n\\n 2. Analysis Under 28 U.S.C. § 2254(d)(2)\\n\\n A prosecutor’s motive for striking a juror is a factual issue, Miller-El v.\\n\\nDretke, 545 U.S. 231, 240 (2005), and a state court’s factual findings are presumed\\n\\ncorrect on federal habeas corpus review. 28 U.S.C. §§ 2254(d)(2), (e)(1). In\\n\\nseeking habeas relief, Smith bears the burden of rebutting that presumption by\\n\\n“clear and convincing evidence.” Id. § 2254(e)(1).\\n\\n Smith first argues that he presented a strong prima facie case of gender\\n\\ndiscrimination where the prosecutor used 14 of his 15 strikes to eliminate women\\n\\nfrom the jury. We agree with Smith.11\\n\\n Smith then argues that the state court’s determination that the prosecutor’s\\n\\nreasons for striking the female venire members were nondiscriminatory was an\\n\\nunreasonable determination of the facts, particularly in light of the prosecutor’s\\n\\n\\n11\\n The district court found that Smith presented a relatively weak prima facie case of gender\\ndiscrimination in part because five women ultimately served on Smith’s jury. But the fact that\\nfive women remained on the jury after the prosecutor used nearly all his strikes to eliminate\\nwomen tells us more about the initial composition of the venire pool (and which juror slots in the\\nvenire were filled by women) than it does about the prosecutor’s state of mind.\\n\\n 26\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 27 of 31\\n\\n\\ninconsistent treatment of male and female venire members. Smith concentrates his\\n\\nargument on one man—misidentified in the trial transcript as “Mr. Johnson”—who\\n\\nstated during voir dire that he was a member of his church’s board. 12 The\\n\\nprosecutor did not use a strike on “Johnson,” which Smith argues is evidence that\\n\\nthe prosecutor’s explanation for striking these women was pretextual.\\n\\n In the years following Smith’s trial, no party has been able to determine\\n\\nJohnson’s true identity. Smith was thus unable to provide the state courts with any\\n\\nadditional information about Johnson that might have been used to determine\\n\\nwhether there were meaningful differences between him and the female venire\\n\\nmembers. We do not know Johnson’s other answers during voir dire, information\\n\\nabout his demeanor, or any other potentially relevant factors, such as his\\n\\noccupation. All that we know about Johnson is that he was a board member at his\\n\\nchurch.\\n\\n To succeed under § 2254(d)(2), Smith must show that it was unreasonable\\n\\nfor the state court to credit the prosecutor’s proffered explanations for the strikes.\\n\\nSee Rice, 546 U.S. at 338. Smith has not met this burden. While Smith’s evidence\\n\\nabout Johnson could have supported a finding that the prosecutor’s strikes were\\n\\n\\n\\n\\n12\\n The venire pool for Smith’s trial did not contain any member with the surname of Johnson,\\nand thus we assume this venire member was misidentified in the trial transcript.\\n 27\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 28 of 31\\n\\n\\ndiscriminatory, we do not think it mandated such a finding in light of the limited\\n\\nevidence presented to the state court.\\n\\n The Alabama CCA also grappled with some of Smith’s other arguments for\\n\\npretext. The court considered, for example, that some of the women allegedly\\n\\neliminated because of their church involvement had previously affirmed that their\\n\\nreligious beliefs would not preclude them from imposing the death penalty. But\\n\\nthe state court did not find that factor dispositive. Neither do we. The\\n\\nprosecution’s explanation at the Batson hearing was not that these potential jurors\\n\\nwould be unalterably unwilling to impose the death penalty, but that they would be\\n\\nparticularly receptive to Smith’s counsel’s request for mercy at the penalty phase\\n\\nof the trial. This is an acceptable justification for a peremptory strike.\\n\\n Importantly, the Alabama CCA ultimately affirmed the trial court’s\\n\\ncredibility determination only after noting that the trial court found that (1) the\\n\\nprosecutor’s reasons for striking venire members were supported by the record and\\n\\n(2) the prosecutor’s approach in excluding those who were susceptible to mercy\\n\\narguments was a sound trial strategy. Both factors are relevant in assessing a\\n\\nprosecutor’s credibility. See Miller-El v. Cockrell, 537 U.S. 322, 324 (2003)\\n\\n(“Credibility can be measured by, among other factors, the prosecutor’s demeanor;\\n\\nby how reasonable, or how improbable, the explanations are; and by whether the\\n\\nproffered rationale has some basis in accepted trial strategy.”).\\n\\n\\n 28\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 29 of 31\\n\\n\\n Ultimately, the record before us does not “compel the conclusion that the\\n\\ntrial court had no permissible alternative but to reject the prosecutor’s [gender]-\\n\\nneutral justifications.” Rice, 546 U.S. at 341. Because habeas review does not\\n\\nallow us to “supersede the trial court’s credibility determination” where the record\\n\\ndoes not compel a contrary conclusion, see id. at 341–42, we must deny Smith’s\\n\\nchallenge under § 2254(d)(2).\\n\\n 3. Analysis Under 28 U.S.C. § 2254(d)(1)\\n\\n Next, Smith argues that the state court’s holding was both contrary to Batson\\n\\nand its progeny and an unreasonable application of Batson under 28 U.S.C.\\n\\n§ 2254(d)(1). First, Smith argues that, contrary to Batson’s directive, the Alabama\\n\\nCCA simply accepted the prosecutor’s proffered explanations at face value. We\\n\\ndisagree. The Alabama CCA thoroughly documented the prosecutor’s reasons for\\n\\nstrikes, the trial court’s corroboration of the prosecutor’s stated reasons, and\\n\\nSmith’s arguments for why those reasons were pretextual. Only after conducting\\n\\nthis analysis did the Alabama CCA affirm the trial court’s credibility\\n\\ndetermination.13\\n\\n\\n\\n13\\n We acknowledge that in its opinion, the Alabama CCA did not specifically discuss Johnson.\\nBut the court did analyze whether the prosecutor’s explanation about striking jurors based on\\nchurch affiliation was pretextual. “Under Supreme Court and our Circuit precedent, a state\\ncourt’s written opinion is not required to mention every relevant fact or argument in order for\\nAEDPA deference to apply.” Lee v. Comm’r, Ala. Dep’t of Corr., 726 F.3d 1172, 1223 (11th\\nCir. 2013). Here, we do not think that the Alabama CCA was required to explicitly address\\nSmith’s arguments about Johnson given the limited evidence Smith provided about him.\\n 29\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 30 of 31\\n\\n\\n Next, Smith argues that the Alabama CCA erred in accepting the\\n\\nprosecution’s “arbitrary and vague” reasons for excluding Ms. Ramos, the only\\n\\nHispanic venire member. While Smith is correct that vague explanations may be\\n\\nlegally insufficient to rebut a prima facie case of discrimination, the prosecutor’s\\n\\nproffered reasons for striking Ms. Ramos—her youth and lack of participation in\\n\\nvoir dire—are relatively concrete and permissible14 reasons for exercising a\\n\\nperemptory strike. The trial record supports both explanations. And neither\\n\\nexplanation rises to the level of vagueness that we condemned in United States v.\\n\\nHorsley, 864 F.2d 1543 (11th Cir. 1989), on which Smith relies. 15\\n\\n Finally, Smith argues that it was improper for the trial court to consider its\\n\\nown observations about a venire member’s behavior. It would be improper for a\\n\\njudge to substitute its own reasoning for striking a venire member where the\\n\\nprosecution’s explanations do not suffice. See Dretke, 545 U.S. at 252. But that\\n\\ndid not occur here. On remand, the trial court noted its own observations about\\n\\nvenire members from voir dire, but it did so to corroborate the prosecutor’s own\\n\\nexplanations about a venire member’s demeanor—a method endorsed by the\\n\\nSupreme Court. See Snyder v. Louisiana, 552 U.S. 472, 477 (2008) (“[R]ace-\\n\\n\\n\\n\\n14\\n The Supreme Court has not extended Batson to peremptory challenges based on age. See, e.g.,\\nWeber v. Strippit, Inc., 186 F.3d 907, 911 (8th Cir. 1999), cert. denied, 528 U.S. 1078 (2000).\\n15\\n In United States v. Horsley, we held that a prosecutor’s statement that “I’ve just got a feeling\\nabout [the juror]” was too vague to rebut a prima facie case of discrimination. 864 F.2d at 1544.\\n 30\\n\\f Case: 17-15043 Date Filed: 05/22/2019 Page: 31 of 31\\n\\n\\nneutral reasons for peremptory challenges often invoke a juror’s demeanor\\n\\n(e.g., nervousness, inattention), making the trial court’s firsthand observations of\\n\\neven greater importance. In this situation, the trial court must evaluate . . . whether\\n\\nthe juror’s demeanor can credibly be said to have exhibited the basis for the strike\\n\\nattributed to the juror by the prosecutor.”).\\n\\n In sum, Smith has not established that the state court’s denial of his claims\\n\\nwas contrary to the standard laid out in Batson and its progeny, an unreasonable\\n\\napplication of Batson, or an unreasonable determination of the facts in light of the\\n\\nevidence presented to the state courts. We therefore affirm the district court’s\\n\\ndenial of Smith’s § 2254 petition.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 31\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2287,"cells":{"id":{"kind":"number","value":4622317,"string":"4,622,317"},"name":{"kind":"string","value":"Bobby Joe LONG, Plaintiff-Appellant, v. SECRETARY, DEPARTMENT OF CORRECTIONS, Warden, Florida State Prison, John Does, as Designee of Barry Reddish, and/or Mark S. Inch, Defendants-Appellees."},"name_abbreviation":{"kind":"string","value":"Bobby Joe Long v. Secretary, Department of Corrections"},"decision_date":{"kind":"string","value":"2019-05-22"},"docket_number":{"kind":"string","value":"19-11942"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Carnes, Marcus, Jordan\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9888572/\", \"author_raw\": \"\"}, {\"author\": \"\", \"type\": \"030concurrence\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/9888573/\", \"author_raw\": \"\"}, {\"author\": \"ED CARNES, Chief Judge\", \"type\": \"010combined\", \"text\": \"Case: 19-11942 Date Filed: 05/22/2019 Page: 1 of 18\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 19-11942\\n ________________________\\n\\n D.C. Docket No. 8:19-cv-01193-MSS-AEP\\n\\n\\n\\nBOBBY JOE LONG,\\n\\n Plaintiff-Appellant,\\n\\n versus\\n\\nSECRETARY, DEPARTMENT OF CORRECTIONS, WARDEN, FLORIDA\\nSTATE PRISON, JOHN DOES, as designee of Barry Reddish, and/or Mark S.\\nInch,\\n\\n Defendants-Appellees.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Florida\\n ________________________\\n\\n (May 22, 2019)\\n\\nBefore ED CARNES, Chief Judge, MARCUS, and JORDAN, Circuit Judges.\\n\\nED CARNES, Chief Judge:\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 2 of 18\\n\\n\\n Bobby Joe Long kidnapped, sexually battered, and murdered Michelle\\n\\nDenise Simms. And at least seven more women. He brutalized others. After\\n\\npleading guilty, he was convicted and sentenced to death for the Simms murder.\\n\\nThat was more than 32 years ago. After his sentence was vacated and the case\\n\\nremanded, he was resentenced to death. That was more than 30 years ago.\\n\\n Seven days before Long is scheduled to be executed, he filed a 28 U.S.C.\\n\\n§ 1983 complaint in the United States District Court for the Middle District of\\n\\nFlorida. He also filed an emergency motion for a temporary restraining order,\\n\\npreliminary injunction, or stay of execution to prevent the State of Florida from\\n\\nexecuting him on May 23, 2019.\\n\\n I. PROCEDURAL HISTORY\\n\\n In September 1985, Long pleaded guilty to eight counts of first-degree\\n\\nmurder, nine counts of kidnapping, eight counts of sexual battery, and one\\n\\nprobation violation. Long v. State, 610 So. 2d 1268, 1269 (Fla. 1992). That plea\\n\\nincluded his admission that he kidnapped, sexually battered, and murdered\\n\\nMichelle Denise Simms. Id. The State of Florida agreed that it would not seek the\\n\\ndeath penalty for the other murders Long admitted committing. Id. A full penalty\\n\\nphase proceeding before a jury was held in the case involving the crimes Long\\n\\ncommitted against Simms. Long v. State, 529 So. 2d 286, 288, 291 (Fla. 1988).\\n\\n\\n\\n\\n 2\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 3 of 18\\n\\n\\nThe jury recommended the death penalty by a vote of eleven to one. Id. at 291.\\n\\nThe trial court adopted that recommendation and sentenced Long to death. Id.\\n\\n On direct appeal, the Florida Supreme Court affirmed Long’s convictions\\n\\nand sentences except for the death sentence. Id. at 291–93. It concluded that\\n\\nbecause the trial judge had found that one of Long’s prior convictions qualified as\\n\\nan aggravating factor, and that prior conviction had since been reversed and\\n\\nvacated by an appellate court as a result of a Miranda violation, Long was entitled\\n\\nto a new sentencing proceeding. Id. at 293. A resentencing trial was conducted\\n\\nbefore a new jury and in a new venue. See Long, 610 So. 2d at 1270. The jury\\n\\nrecommended death, this time unanimously. Id. at 1272. The trial court adopted\\n\\nthat recommendation and imposed the death penalty. Id. The Florida Supreme\\n\\nCourt affirmed, id. at 1275, and the United States Supreme Court denied Long’s\\n\\npetition for a writ of certiorari, Long v. Florida, 510 U.S. 832 (1993), making his\\n\\nconvictions and sentences final in 1993.\\n\\n Following the conclusion of his direct appeals, Long unsuccessfully sought\\n\\npostconviction relief in state court three times. See Long v. State, 235 So. 3d 293\\n\\n(Fla. 2018); Long v. State, 183 So. 3d 342 (Fla. 2016); Long v. State, 118 So. 3d\\n\\n798 (Fla. 2013). Long also filed a federal habeas petition in the district court in\\n\\n2013. The district court denied that petition on the merits, and this Court denied\\n\\nLong’s application for a certificate of appealability. See Long v. Sec’y, Fla. Dep’t\\n\\n\\n\\n 3\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 4 of 18\\n\\n\\nof Corr., No. 16-16259 (11th Cir. Jan. 4, 2017); Long v. Sec’y, Dep’t of Corr., No.\\n\\n8:13-cv-02069-T-27AEP (M.D. Fla. Aug. 30, 2016).\\n\\n After all of Long’s attempts at postconviction relief had been resolved\\n\\nconclusively against him, the Florida Commission on Offender Review initiated\\n\\nstate clemency proceedings in Long’s case. The Commission conducted\\n\\nproceedings and took the matter under submission in September 2018. After the\\n\\nCommission reported to the Governor, he denied clemency. Long was notified of\\n\\nthat decision in April 2019.\\n\\n The Governor signed Long’s death warrant on April 23, 2019, and the\\n\\nWarden set the execution date for May 23, 2019. Since then, Long has filed in the\\n\\nFlorida courts a flurry of motions, including two motions for a stay of execution, a\\n\\nmotion to dismiss his death warrant as defective, and a motion for postconviction\\n\\nrelief (the fourth one he had filed). He also filed a petition for habeas corpus in the\\n\\nFlorida Supreme Court. All of his motions and petitions have been denied.\\n\\n On May 8, 2019, Long filed in the United States District Court for the\\n\\nNorthern District of Florida a § 1983 complaint. In that complaint, he claims that\\n\\nthe State of Florida violated his federal statutory right to counsel by declining to\\n\\nallow his federally-appointed attorneys to appear at his interview in the state\\n\\nclemency proceedings and that the state-appointed attorney who was present and\\n\\nrepresented him at that interview rendered ineffective assistance of counsel in\\n\\n\\n\\n 4\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 5 of 18\\n\\n\\nviolation of the Sixth Amendment. Along with that § 1983 complaint, Long filed\\n\\nan emergency motion for a stay of execution. The district court denied that motion\\n\\non May 16, 2019. On May 20, 2019, Long filed a motion for reconsideration in\\n\\nthe district court, which it denied on May 21, 2019.\\n\\n In his complaint in this § 1983 proceeding, Long raises five claims. First, he\\n\\nclaims that Florida’s use of a three-drug protocol instead of a one-drug protocol\\n\\nviolates the Eighth Amendment. Second, he claims that Florida’s use of etomidate\\n\\nas the first drug in that three-drug protocol is facially unconstitutional because it\\n\\ncreates a risk of severe pain that is substantial when compared to the known and\\n\\navailable alternative of using the single drug pentobarbital. Third, he claims that\\n\\neven if the use of etomidate does not amount to cruel and unusual punishment in\\n\\nall cases, it does in his case because of his serious medical conditions (traumatic\\n\\nbrain injury and temporal lobe epilepsy).\\n\\n Fourth, he claims that the State violated his First, Fifth, Eighth, and\\n\\nFourteenth Amendment rights by objecting to his requests for public records and\\n\\nrefusing to answer his questions about the lethal injection protocol. And finally,\\n\\nLong claims that the Warden violated his First, Sixth, Eighth, and Fourteenth\\n\\nAmendment rights by refusing his requests to: (1) have an additional attorney\\n\\nwitness at his execution in lieu of a spiritual adviser, (2) permit Long’s attorneys to\\n\\nhave access to a phone during the execution, and (3) permit one of Long’s\\n\\n\\n 5\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 6 of 18\\n\\n\\nwitnesses to observe the insertion of the IV line that will be used to administer the\\n\\nlethal drugs.\\n\\n Along with his complaint, Long filed an emergency motion for a temporary\\n\\nrestraining order, preliminary injunction, or stay of execution. He requested that\\n\\nthe district court order the State to hold off on his execution until the court had\\n\\ntime to consider each of his claims (which, according to Long, would require\\n\\ndiscovery and an evidentiary hearing).\\n\\n The district court denied Long’s motion for a temporary restraining order,\\n\\npreliminary injunction, or stay of execution on May 19, 2019. It concluded that all\\n\\nof Long’s claims were barred by the doctrine of res judicata as a result of the\\n\\nFlorida Supreme Court’s decision in Long v. State, No. SC19-726, 2019 WL\\n\\n2150942 (Fla. May 17, 2019). For that reason, he could not show a substantial\\n\\nlikelihood of success on the merits. Long filed a notice of appeal the same day.\\n\\nOn May 20, 2019, he filed in this Court a motion for a stay of execution, or in the\\n\\nalternative, an expedited appeal. We granted his motion to expedite the appeal.\\n\\n On May 20, 2019, Long filed two petitions for a writ of certiorari in the\\n\\nUnited States Supreme Court, each accompanied by an application for a stay of\\n\\nexecution. One of those petitions seeks review of the Florida Supreme Court’s\\n\\ndenial of his state habeas petition. The other one seeks review of the Florida\\n\\nSupreme Court’s denial of his fourth motion for postconviction relief. In that one,\\n\\n\\n\\n 6\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 7 of 18\\n\\n\\nhe raises two claims that he also raised in the § 1983 lawsuit at issue in this appeal:\\n\\n(1) his claim about the Warden’s denial of his requests for exceptions to the\\n\\nDepartment of Corrections’ witness policy, and (2) his challenge to Florida’s use\\n\\nof etomidate in its lethal injection protocol.\\n\\n II. STANDARD OF REVIEW\\n\\n We review the district court’s denial of a motion for a temporary restraining\\n\\norder, preliminary injunction, or stay of execution only for abuse of discretion.\\n\\nGissendaner v. Comm’r, Ga. Dep’t of Corr., 779 F.3d 1275, 1280 (11th Cir. 2015)\\n\\n(temporary restraining order); Chavez v. Fla. SP Warden, 742 F.3d 1267, 1271\\n\\n(11th Cir. 2014) (preliminary injunction); Muhammad v. Sec’y, Fla. Dep’t of\\n\\nCorr., 739 F.3d 683, 688 (11th Cir. 2014) (stay of execution). A district court\\n\\nabuses its discretion if, among other things, “it applies an incorrect legal standard,\\n\\nfollows improper procedures in making the determination, or makes findings of\\n\\nfact that are clearly erroneous.” Grayson v. Warden, Comm’r, Ala. DOC, 869 F.3d\\n\\n1204, 1238 (11th Cir. 2017) (quotation marks omitted).\\n\\n A federal court may grant a temporary restraining order, preliminary\\n\\ninjunction, or a stay of execution only if the movant establishes that (1) he has a\\n\\nsubstantial likelihood of success on the merits, (2) he will suffer irreparable injury\\n\\nunless the injunction issues, (3) the injunction would not substantially harm the\\n\\nother litigant, and (4) if issued, the injunction would not be adverse to the public\\n\\n\\n\\n 7\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 8 of 18\\n\\n\\ninterest. Powell v. Thomas, 641 F.3d 1255, 1257 (11th Cir. 2011); see also\\n\\nGissendaner, 779 F.3d at 1280; Chavez, 742 F.3d at 1271.\\n\\n III. DISCUSSION\\n\\n A. Long’s Method of Execution Claims\\n\\n The district court did not abuse its discretion in declining to stay Long’s\\n\\nexecution on account of his three method of execution claims. Each of them is\\n\\nbarred for two independently adequate reasons. First, Long engaged in\\n\\ninexcusable delay in bringing the claims, which is enough to deny him the\\n\\nequitable remedy of a stay. And second, as the district court properly held, each of\\n\\nhis claims is barred by the doctrine of res judicata.\\n\\n 1. Inexcusable Delay\\n\\n Long is not entitled to a stay of execution “as a matter of course” simply\\n\\nbecause he brought a § 1983 claim. Hill v. McDonough, 547 U.S. 573, 583–84\\n\\n(2006). Instead, a stay of execution is an equitable remedy and all of the rules of\\n\\nequity apply. See Rutherford v. Crosby, 438 F.3d 1087, 1092 (11th Cir. 2006)\\n\\n(explaining that “where petitioner’s scheduled execution is imminent, there is no\\n\\npractical difference between denying a stay on equitable grounds and denying\\n\\ninjunctive relief on equitable grounds in a § 1983 lawsuit”), vacated on other\\n\\ngrounds, Rutherford v. McDonough, 547 U.S. 1204 (2006).\\n\\n\\n\\n\\n 8\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 9 of 18\\n\\n\\n One of those rules is that “[e]quity must take into consideration the State’s\\n\\nstrong interest in proceeding with its judgment” and an inmate’s “attempt at\\n\\nmanipulation.” Gomez v. U.S. Dist. Ct. for N. Dist. of Cal., 503 U.S. 653, 654\\n\\n(1992) (per curiam). As a result, before granting a stay of execution, a court must\\n\\n“consider not only the likelihood of success on the merits and the relative harms to\\n\\nthe parties, but also the extent to which the inmate has delayed unnecessarily in\\n\\nbringing the claim.” Nelson v. Campbell, 541 U.S. 637, 649–50 (2004). There is a\\n\\n“strong equitable presumption against the grant of a stay where a claim could have\\n\\nbeen brought at such a time as to allow consideration of the merits without\\n\\nrequiring entry of a stay.” Id. at 650.\\n\\n The Supreme Court has reiterated the importance of these principles three\\n\\ntimes this year. The first time was in February when a stay entered by this Court\\n\\nwas vacated by the Supreme Court. Dunn v. Ray, 139 S. Ct. 661 (2019). In\\n\\nvacating the stay, the Court quoted from Gomez: “A court may consider the last-\\n\\nminute nature of an application to stay execution in deciding whether to grant\\n\\nequitable relief.” Id. at 661 (quoting Gomez, 503 U.S. at 654).\\n\\n And then in April, when affirming the Eighth Circuit’s denial of an inmate’s\\n\\nas-applied challenge to the State’s method of execution, the Supreme Court\\n\\nexplicitly instructed lower courts that: “Courts should police carefully against\\n\\nattempts to use such challenges as tools to interpose unjustified delay. Last-minute\\n\\n\\n\\n 9\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 10 of 18\\n\\n\\nstays should be the extreme exception, not the norm, and the last-minute nature of\\n\\nan application that could have been brought earlier, or an applicant’s attempt at\\n\\nmanipulation, may be grounds for denial of a stay.” Bucklew v. Precythe, 139 S.\\n\\nCt. 1112, 1134 (2019) (quotation marks omitted).\\n\\n And later that same month, the Supreme Court vacated another stay of\\n\\nexecution that this Court had issued. Its decision to vacate the stay was based on\\n\\nthe fact that the inmate had delayed bringing his challenge to the State’s lethal\\n\\ninjection protocol until about two months before his scheduled execution, and then\\n\\nwaited until just a few hours before that execution to submit additional evidence.\\n\\nDunn v. Price, 139 S. Ct. 1312, 1312 (2019). The Supreme Court again relied on\\n\\nGomez to instruct courts to consider the last-minute nature of a stay in determining\\n\\nwhether equitable relief is appropriate. Id.\\n\\n Long’s case is not one of the “extreme exception[s]” in which a last-minute\\n\\nstay should be entered, but instead is within “the norm” where the “strong\\n\\nequitable presumption against the grant of a stay” applies. Bucklew, 139 S. Ct. at\\n\\n1134; Hill, 547 U.S. at 584 (quotation marks omitted).\\n\\n The first of Long’s method of execution claims is that Florida’s use of a\\n\\nthree-drug protocol instead of a one-drug protocol violates the Eighth Amendment.\\n\\nBut Florida has used a three-drug protocol since January 14, 2000, when it added\\n\\nlethal injection as a new method of execution. See Heynard v. Sec’y, DOC, 543\\n\\n\\n\\n 10\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 11 of 18\\n\\n\\nF.3d 644, 647 (11th Cir. 2014). Long has had nineteen years to challenge the use\\n\\nof a three-drug protocol. Nineteen years is too long to wait.\\n\\n To the extent that Long argues that a challenge to three-drug protocols\\n\\nwould not have been valid until now because other states have only recently begun\\n\\nusing one-drug protocols, that argument is belied by allegations in his own\\n\\ncomplaint. It alleges that at least four other states have “used a single-drug method\\n\\nfor executions since 2009.” Ten years is too long to wait.\\n\\n Long’s other two method of execution claims also suffer from his delay in\\n\\nbringing them. In those claims, he contends that Florida’s use of etomidate as the\\n\\nfirst drug in its three-drug protocol is unconstitutional regardless of the health of\\n\\nthe inmate, and that it is especially so as applied to him because of his serious\\n\\nmedical conditions.\\n\\n Florida adopted etomidate as the first drug in its three-drug protocol in\\n\\nJanuary of 2017, two years and four months ago. But Long waited until a week\\n\\nago to file this § 1983 challenge to it. Long alleges in his complaint that three of\\n\\nFlorida’s recent executions using etomidate show that the drug causes inmates\\n\\nsevere pain because it does not properly anesthetize them. To the extent that Long\\n\\nargues (and it is not clear that he does) that the delay in bringing his claims was\\n\\nbased on facts arising from those executions, his argument is not persuasive. The\\n\\nfirst of the three executions occurred on November 8, 2017, the second on\\n\\n\\n\\n 11\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 12 of 18\\n\\n\\nFebruary 22, 2018, and the last of them on December 13, 2018. A delay of five\\n\\nmonths, fifteen months, or eighteen months is too long.\\n\\n Long’s person-specific claim is that his medical conditions will complicate\\n\\nFlorida’s use of etomidate and may cause him unnecessary pain. But Long has\\n\\nknown about his medical conditions for decades. During his 1989 resentencing\\n\\ntrial, he presented as mitigating evidence the testimony of two medical experts\\n\\nabout his traumatic brain injury and temporal lobe epilepsy. See Long, 610 So. 2d\\n\\nat 1271–72. Any argument about how etomidate would be uniquely harmful to\\n\\nhim could have been raised as soon as Florida adopted etomidate as the first drug\\n\\nin its three-drug protocol. That happened in January 2017, two years and four\\n\\nmonths before Long brought this lawsuit.\\n\\n If Long had truly intended to challenge Florida’s lethal injection protocol\\n\\ninstead of just seeking to delay his execution, he would not have deliberately\\n\\nwaited to file this lawsuit until a decision on the merits would require entry of a\\n\\nstay. We have refused to grant stays in cases involving delayed filings before, and\\n\\nLong’s delay was even more pronounced and less justifiable. See e.g., Brooks v.\\n\\nWarden, 810 F.3d 812, 826 (11th Cir. 2016) (holding that an inmate was not\\n\\nentitled to a stay where he delayed filing his § 1983 challenge until eleven weeks\\n\\nbefore his execution); In re Hutcherson, 468 F.3d 747, 749–50 (11th Cir. 2006)\\n\\n(denying prisoner’s motion to stay his execution pending this Court’s resolution of\\n\\n\\n\\n 12\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 13 of 18\\n\\n\\nhis application for leave to file a successive petition because he waited until eight\\n\\ndays before his scheduled execution to file it and, as a result, his “need for a stay of\\n\\nexecution [was] directly attributable to his own failure to bring his claims to court\\n\\nin a timely fashion”); Diaz v. McDonough, 472 F.3d 849, 851 (11th Cir. 2006)\\n\\n(declining to grant a preliminary injunction so that an inmate could pursue an\\n\\nappeal because he filed his § 1983 complaint less than three days before his\\n\\nscheduled execution); cf. Jones v. Allen, 485 F.3d 635, 640 (11th Cir. 2007)\\n\\n(holding that inmate was not entitled to a stay of execution because he waited four\\n\\nyears after learning that the state intended to execute him by lethal injection to file\\n\\nhis § 1983 challenge).\\n\\n 2. Res Judicata\\n\\n Even if Long’s method of execution claims were not barred on equitable\\n\\ngrounds, the district court properly concluded that he could not show a likelihood\\n\\nof success on the merits because the claims are barred by the doctrine of res\\n\\njudicata. All of the claims Long raises in this § 1983 action were raised, or could\\n\\nhave been raised, in his fourth motion for postconviction relief, which the Florida\\n\\nSupreme Court rejected. See Long, 2019 WL 2150942, at *6–7.\\n\\n To the district court’s concise and correct discussion, we add one point,\\n\\nwhich responds to Long’s argument that applying the doctrine of res judicata\\n\\nwould work a manifest injustice in his case. He claims that because the state\\n\\n\\n\\n 13\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 14 of 18\\n\\n\\ncourts did not give him a hearing on the merits of his general challenge, and\\n\\nbecause the hearing that they did give him on his person-specific challenge was\\n\\n“severely restricted” due to the “extraordinarily constrained timeline” for the\\n\\nlitigation of his fourth postconviction motion, it would be unjust to give the Florida\\n\\nSupreme Court’s decision preclusive effect.\\n\\n There are three big problems with this argument. First, his position is\\n\\nunprecedented. Long has not pointed to a single published decision of the Florida\\n\\ncourts or this Court applying Florida law holding that it is a “manifest injustice” to\\n\\napply res judicata if the initial state court decision resolved a claim without\\n\\ngranting an evidentiary hearing. 1\\n\\n The second problem with Long’s position is that the “extraordinarily\\n\\nconstrained timeline” that he complains of is a direct result of his delay in filing his\\n\\nmethod of execution claims in state postconviction proceedings until after his\\n\\nexecution date had been set. As we have discussed, there is no reason why Long\\n\\ncould not have challenged Florida’s use of a three-drug protocol as early as 2000\\n\\n\\n\\n 1\\n The inapplicability of the precedent that Long cites and the unpersuasiveness of the\\narguments that he makes are illustrated by the following sentence and citation from his brief:\\n“This Court has declined to apply res judicata where an inmate was not given an evidentiary\\nhearing on his challenge in state court. See Chavez v. Sec’y, 742 F.3d 1267 (11th Cir. 2014).”\\nThat citation is disingenuous. The entire discussion of res judicata in the Chavez opinion\\nconsists of the following footnote: “In light of our conclusion that Chavez has not established a\\nsubstantial likelihood of success on the merits of any of his claims, we do not address and imply\\nno view about the State’s asserted defenses based on the statute of limitations, exhaustion of\\nadministrative remedies, and res judicata.” Chavez, 742 F.3d at 1273 n.5.\\n\\n\\n 14\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 15 of 18\\n\\n\\n(when Florida adopted lethal injection as a method of execution) or at least by\\n\\n2009 (when, according to the allegations in his complaint, a number of states had\\n\\nswitched to a one-drug protocol). And there is no reason why Long could not have\\n\\nchallenged Florida’s use of etomidate, both in general and specifically as to him,\\n\\nin January 2017, when the Florida Department of Corrections decided to use it as\\n\\nthe first drug in the three-drug protocol. It is worse than ironic for Long to argue\\n\\nthat the state court’s decision does not deserve res judicata effect because the state\\n\\ncourt had to render that decision under the time constraints that Long forced on it.\\n\\n There is another fundamental problem with Long’s arguments against the\\n\\napplication of res judicata. Reduced to its essence, his position is that the res\\n\\njudicata doctrine applies only if the court in which it is asserted agrees with the\\n\\ninitial court’s decision on de novo consideration. And, he says, we shouldn’t agree\\n\\nwith the decision of the Florida courts on these claims for a number of reasons.\\n\\nBut that is not the way that res judicata works. If it did, the doctrine would be\\n\\ntoothless, pointless, and fruitless. It would apply only when it made no difference.\\n\\nThe Florida courts have never suggested such a rule-devouring exception, and we\\n\\nwill not presume to create one for them here. See Kremer v. Chem. Constr. Corp.,\\n\\n456 U.S. 461, 481–82 (1982) (“It has long been established that [28 U.S.C.] § 1738\\n\\ndoes not allow federal courts to employ their own rules of res judicata in\\n\\ndetermining the effect of state judgments. Rather, it goes beyond the common law\\n\\n\\n\\n 15\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 16 of 18\\n\\n\\nand commands a federal court to accept the rules chosen by the State from which\\n\\nthe judgment is taken.”).\\n\\n B. Long’s Public Records and Witness Claims\\n\\n In addition to his three method of execution claims, Long contends that the\\n\\ndefendants violated his constitutional rights by (1) objecting to some of his public\\n\\nrecords requests and refusing to answer some of his questions about the lethal\\n\\ninjection protocol, and (2) denying his requests for exceptions to the Department of\\n\\nCorrections’ witness policies. As the district court already held, both of those\\n\\nclaims are also barred by the doctrine of res judicata. Long raised a public records\\n\\nclaim in the Florida courts, see Long, 2019 WL 2150942, at *6–7, and he could\\n\\nhave asserted any similar claims in the state court proceedings.\\n\\n There are many published decisions that support the district court’s ruling\\n\\nthat, under Florida law, res judicata bars claims that Long could have raised in the\\n\\nstate postconviction proceedings but didn’t. See, e.g., Topps v. State, 865 So. 2d\\n\\n1253, 1255 (Fla. 2004) (“The doctrine of res judicata bars relitigation in a\\n\\nsubsequent cause of action not only of claims raised, but also claims that could\\n\\nhave been raised.”); Fla. Dep’t of Transp. v. Juliano, 801 So. 2d 101, 105 (Fla.\\n\\n2001) (“Importantly, the doctrine of res judicata not only bars issues that were\\n\\nraised, but it also precludes consideration of issues that could have been raised but\\n\\nwere not raised in the first case.”); see also Vasquez v. YII Shipping Co., 692 F.3d\\n\\n\\n\\n 16\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 17 of 18\\n\\n\\n1192, 1199 (11th Cir. 2012) (applying Florida law to explain that “the purpose of\\n\\nres judicata is that a final judgment in a court of competent jurisdiction is absolute\\n\\nand settles all issues actually litigated in a proceeding as well as those issues that\\n\\ncould have been litigated.”) (quotation marks omitted). The district court was\\n\\nentirely correct in concluding that Long’s public records and witness claims are\\n\\nbarred by res judicata.\\n\\n IV. CONCLUSION\\n\\n We AFFIRM the district court’s denial of Long’s emergency motion for a\\n\\ntemporary restraining order, preliminary injunction, or stay of execution. We\\n\\nDENY Long’s motion for a stay of execution from this Court.\\n\\n\\n\\n\\n 17\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 18 of 18\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4399570/\", \"author_raw\": \"ED CARNES, Chief Judge\"}, {\"author\": \"JORDAN, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"JORDAN, Circuit Judge, concurring.\\n\\n The district court denied Mr. Long’s claims on res judicata grounds based on\\n\\nthe Florida Supreme Court’s decision in Long v. State, 2019 WL 2150942 (Fla. May\\n\\n17, 2019). I agree with the majority that the district court properly applied the\\n\\ndoctrine of res judicata, and therefore join Parts I, II, III.A.2, and III.B of its opinion.\\n\\nBecause our affirmance of the district court’s res judicata ruling conclusively\\n\\nresolves Mr. Long’s claims and requests for relief here, I find it unnecessary to\\n\\naddress the issue of delay.\\n\\n\\n\\n\\n 18\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4399570/\", \"author_raw\": \"JORDAN, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"CARNES"},"judge2":{"kind":"string","value":"MARCUS"},"judge3":{"kind":"string","value":"JORDAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":4,"string":"4"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":2,"string":"2"},"other_count":{"kind":"number","value":2,"string":"2"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4622317/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":1,"string":"1"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Bobby Joe LONG, Plaintiff-Appellant, v. SECRETARY, DEPARTMENT OF CORRECTIONS, Warden, Florida State Prison, John Does, as Designee of Barry Reddish, and/or Mark S. Inch, Defendants-Appellees.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nCase: 19-11942 Date Filed: 05/22/2019 Page: 1 of 18\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 19-11942\n ________________________\n\n D.C. Docket No. 8:19-cv-01193-MSS-AEP\n\n\n\nBOBBY JOE LONG,\n\n Plaintiff-Appellant,\n\n versus\n\nSECRETARY, DEPARTMENT OF CORRECTIONS, WARDEN, FLORIDA\nSTATE PRISON, JOHN DOES, as designee of Barry Reddish, and/or Mark S.\nInch,\n\n Defendants-Appellees.\n\n ________________________\n\n Appeal from the United States District Court\n for the Middle District of Florida\n ________________________\n\n (May 22, 2019)\n\nBefore ED CARNES, Chief Judge, MARCUS, and JORDAN, Circuit Judges.\n\nED CARNES, Chief Judge:\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 2 of 18\n\n\n Bobby Joe Long kidnapped, sexually battered, and murdered Michelle\n\nDenise Simms. And at least seven more women. He brutalized others. After\n\npleading guilty, he was convicted and sentenced to death for the Simms murder.\n\nThat was more than 32 years ago. After his sentence was vacated and the case\n\nremanded, he was resentenced to death. That was more than 30 years ago.\n\n Seven days before Long is scheduled to be executed, he filed a 28 U.S.C.\n\n§ 1983 complaint in the United States District Court for the Middle District of\n\nFlorida. He also filed an emergency motion for a temporary restraining order,\n\npreliminary injunction, or stay of execution to prevent the State of Florida from\n\nexecuting him on May 23, 2019.\n\n I. PROCEDURAL HISTORY\n\n In September 1985, Long pleaded guilty to eight counts of first-degree\n\nmurder, nine counts of kidnapping, eight counts of sexual battery, and one\n\nprobation violation. Long v. State, 610 So. 2d 1268, 1269 (Fla. 1992). That plea\n\nincluded his admission that he kidnapped, sexually battered, and murdered\n\nMichelle Denise Simms. Id. The State of Florida agreed that it would not seek the\n\ndeath penalty for the other murders Long admitted committing. Id. A full penalty\n\nphase proceeding before a jury was held in the case involving the crimes Long\n\ncommitted against Simms. Long v. State, 529 So. 2d 286, 288, 291 (Fla. 1988).\n\n\n\n\n 2\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 3 of 18\n\n\nThe jury recommended the death penalty by a vote of eleven to one. Id. at 291.\n\nThe trial court adopted that recommendation and sentenced Long to death. Id.\n\n On direct appeal, the Florida Supreme Court affirmed Long’s convictions\n\nand sentences except for the death sentence. Id. at 291–93. It concluded that\n\nbecause the trial judge had found that one of Long’s prior convictions qualified as\n\nan aggravating factor, and that prior conviction had since been reversed and\n\nvacated by an appellate court as a result of a Miranda violation, Long was entitled\n\nto a new sentencing proceeding. Id. at 293. A resentencing trial was conducted\n\nbefore a new jury and in a new venue. See Long, 610 So. 2d at 1270. The jury\n\nrecommended death, this time unanimously. Id. at 1272. The trial court adopted\n\nthat recommendation and imposed the death penalty. Id. The Florida Supreme\n\nCourt affirmed, id. at 1275, and the United States Supreme Court denied Long’s\n\npetition for a writ of certiorari, Long v. Florida, 510 U.S. 832 (1993), making his\n\nconvictions and sentences final in 1993.\n\n Following the conclusion of his direct appeals, Long unsuccessfully sought\n\npostconviction relief in state court three times. See Long v. State, 235 So. 3d 293\n\n(Fla. 2018); Long v. State, 183 So. 3d 342 (Fla. 2016); Long v. State, 118 So. 3d\n\n798 (Fla. 2013). Long also filed a federal habeas petition in the district court in\n\n2013. The district court denied that petition on the merits, and this Court denied\n\nLong’s application for a certificate of appealability. See Long v. Sec’y, Fla. Dep’t\n\n\n\n 3\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 4 of 18\n\n\nof Corr., No. 16-16259 (11th Cir. Jan. 4, 2017); Long v. Sec’y, Dep’t of Corr., No.\n\n8:13-cv-02069-T-27AEP (M.D. Fla. Aug. 30, 2016).\n\n After all of Long’s attempts at postconviction relief had been resolved\n\nconclusively against him, the Florida Commission on Offender Review initiated\n\nstate clemency proceedings in Long’s case. The Commission conducted\n\nproceedings and took the matter under submission in September 2018. After the\n\nCommission reported to the Governor, he denied clemency. Long was notified of\n\nthat decision in April 2019.\n\n The Governor signed Long’s death warrant on April 23, 2019, and the\n\nWarden set the execution date for May 23, 2019. Since then, Long has filed in the\n\nFlorida courts a flurry of motions, including two motions for a stay of execution, a\n\nmotion to dismiss his death warrant as defective, and a motion for postconviction\n\nrelief (the fourth one he had filed). He also filed a petition for habeas corpus in the\n\nFlorida Supreme Court. All of his motions and petitions have been denied.\n\n On May 8, 2019, Long filed in the United States District Court for the\n\nNorthern District of Florida a § 1983 complaint. In that complaint, he claims that\n\nthe State of Florida violated his federal statutory right to counsel by declining to\n\nallow his federally-appointed attorneys to appear at his interview in the state\n\nclemency proceedings and that the state-appointed attorney who was present and\n\nrepresented him at that interview rendered ineffective assistance of counsel in\n\n\n\n 4\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 5 of 18\n\n\nviolation of the Sixth Amendment. Along with that § 1983 complaint, Long filed\n\nan emergency motion for a stay of execution. The district court denied that motion\n\non May 16, 2019. On May 20, 2019, Long filed a motion for reconsideration in\n\nthe district court, which it denied on May 21, 2019.\n\n In his complaint in this § 1983 proceeding, Long raises five claims. First, he\n\nclaims that Florida’s use of a three-drug protocol instead of a one-drug protocol\n\nviolates the Eighth Amendment. Second, he claims that Florida’s use of etomidate\n\nas the first drug in that three-drug protocol is facially unconstitutional because it\n\ncreates a risk of severe pain that is substantial when compared to the known and\n\navailable alternative of using the single drug pentobarbital. Third, he claims that\n\neven if the use of etomidate does not amount to cruel and unusual punishment in\n\nall cases, it does in his case because of his serious medical conditions (traumatic\n\nbrain injury and temporal lobe epilepsy).\n\n Fourth, he claims that the State violated his First, Fifth, Eighth, and\n\nFourteenth Amendment rights by objecting to his requests for public records and\n\nrefusing to answer his questions about the lethal injection protocol. And finally,\n\nLong claims that the Warden violated his First, Sixth, Eighth, and Fourteenth\n\nAmendment rights by refusing his requests to: (1) have an additional attorney\n\nwitness at his execution in lieu of a spiritual adviser, (2) permit Long’s attorneys to\n\nhave access to a phone during the execution, and (3) permit one of Long’s\n\n\n 5\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 6 of 18\n\n\nwitnesses to observe the insertion of the IV line that will be used to administer the\n\nlethal drugs.\n\n Along with his complaint, Long filed an emergency motion for a temporary\n\nrestraining order, preliminary injunction, or stay of execution. He requested that\n\nthe district court order the State to hold off on his execution until the court had\n\ntime to consider each of his claims (which, according to Long, would require\n\ndiscovery and an evidentiary hearing).\n\n The district court denied Long’s motion for a temporary restraining order,\n\npreliminary injunction, or stay of execution on May 19, 2019. It concluded that all\n\nof Long’s claims were barred by the doctrine of res judicata as a result of the\n\nFlorida Supreme Court’s decision in Long v. State, No. SC19-726, 2019 WL\n\n2150942 (Fla. May 17, 2019). For that reason, he could not show a substantial\n\nlikelihood of success on the merits. Long filed a notice of appeal the same day.\n\nOn May 20, 2019, he filed in this Court a motion for a stay of execution, or in the\n\nalternative, an expedited appeal. We granted his motion to expedite the appeal.\n\n On May 20, 2019, Long filed two petitions for a writ of certiorari in the\n\nUnited States Supreme Court, each accompanied by an application for a stay of\n\nexecution. One of those petitions seeks review of the Florida Supreme Court’s\n\ndenial of his state habeas petition. The other one seeks review of the Florida\n\nSupreme Court’s denial of his fourth motion for postconviction relief. In that one,\n\n\n\n 6\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 7 of 18\n\n\nhe raises two claims that he also raised in the § 1983 lawsuit at issue in this appeal:\n\n(1) his claim about the Warden’s denial of his requests for exceptions to the\n\nDepartment of Corrections’ witness policy, and (2) his challenge to Florida’s use\n\nof etomidate in its lethal injection protocol.\n\n II. STANDARD OF REVIEW\n\n We review the district court’s denial of a motion for a temporary restraining\n\norder, preliminary injunction, or stay of execution only for abuse of discretion.\n\nGissendaner v. Comm’r, Ga. Dep’t of Corr., 779 F.3d 1275, 1280 (11th Cir. 2015)\n\n(temporary restraining order); Chavez v. Fla. SP Warden, 742 F.3d 1267, 1271\n\n(11th Cir. 2014) (preliminary injunction); Muhammad v. Sec’y, Fla. Dep’t of\n\nCorr., 739 F.3d 683, 688 (11th Cir. 2014) (stay of execution). A district court\n\nabuses its discretion if, among other things, “it applies an incorrect legal standard,\n\nfollows improper procedures in making the determination, or makes findings of\n\nfact that are clearly erroneous.” Grayson v. Warden, Comm’r, Ala. DOC, 869 F.3d\n\n1204, 1238 (11th Cir. 2017) (quotation marks omitted).\n\n A federal court may grant a temporary restraining order, preliminary\n\ninjunction, or a stay of execution only if the movant establishes that (1) he has a\n\nsubstantial likelihood of success on the merits, (2) he will suffer irreparable injury\n\nunless the injunction issues, (3) the injunction would not substantially harm the\n\nother litigant, and (4) if issued, the injunction would not be adverse to the public\n\n\n\n 7\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 8 of 18\n\n\ninterest. Powell v. Thomas, 641 F.3d 1255, 1257 (11th Cir. 2011); see also\n\nGissendaner, 779 F.3d at 1280; Chavez, 742 F.3d at 1271.\n\n III. DISCUSSION\n\n A. Long’s Method of Execution Claims\n\n The district court did not abuse its discretion in declining to stay Long’s\n\nexecution on account of his three method of execution claims. Each of them is\n\nbarred for two independently adequate reasons. First, Long engaged in\n\ninexcusable delay in bringing the claims, which is enough to deny him the\n\nequitable remedy of a stay. And second, as the district court properly held, each of\n\nhis claims is barred by the doctrine of res judicata.\n\n 1. Inexcusable Delay\n\n Long is not entitled to a stay of execution “as a matter of course” simply\n\nbecause he brought a § 1983 claim. Hill v. McDonough, 547 U.S. 573, 583–84\n\n(2006). Instead, a stay of execution is an equitable remedy and all of the rules of\n\nequity apply. See Rutherford v. Crosby, 438 F.3d 1087, 1092 (11th Cir. 2006)\n\n(explaining that “where petitioner’s scheduled execution is imminent, there is no\n\npractical difference between denying a stay on equitable grounds and denying\n\ninjunctive relief on equitable grounds in a § 1983 lawsuit”), vacated on other\n\ngrounds, Rutherford v. McDonough, 547 U.S. 1204 (2006).\n\n\n\n\n 8\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 9 of 18\n\n\n One of those rules is that “[e]quity must take into consideration the State’s\n\nstrong interest in proceeding with its judgment” and an inmate’s “attempt at\n\nmanipulation.” Gomez v. U.S. Dist. Ct. for N. Dist. of Cal., 503 U.S. 653, 654\n\n(1992) (per curiam). As a result, before granting a stay of execution, a court must\n\n“consider not only the likelihood of success on the merits and the relative harms to\n\nthe parties, but also the extent to which the inmate has delayed unnecessarily in\n\nbringing the claim.” Nelson v. Campbell, 541 U.S. 637, 649–50 (2004). There is a\n\n“strong equitable presumption against the grant of a stay where a claim could have\n\nbeen brought at such a time as to allow consideration of the merits without\n\nrequiring entry of a stay.” Id. at 650.\n\n The Supreme Court has reiterated the importance of these principles three\n\ntimes this year. The first time was in February when a stay entered by this Court\n\nwas vacated by the Supreme Court. Dunn v. Ray, 139 S. Ct. 661 (2019). In\n\nvacating the stay, the Court quoted from Gomez: “A court may consider the last-\n\nminute nature of an application to stay execution in deciding whether to grant\n\nequitable relief.” Id. at 661 (quoting Gomez, 503 U.S. at 654).\n\n And then in April, when affirming the Eighth Circuit’s denial of an inmate’s\n\nas-applied challenge to the State’s method of execution, the Supreme Court\n\nexplicitly instructed lower courts that: “Courts should police carefully against\n\nattempts to use such challenges as tools to interpose unjustified delay. Last-minute\n\n\n\n 9\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 10 of 18\n\n\nstays should be the extreme exception, not the norm, and the last-minute nature of\n\nan application that could have been brought earlier, or an applicant’s attempt at\n\nmanipulation, may be grounds for denial of a stay.” Bucklew v. Precythe, 139 S.\n\nCt. 1112, 1134 (2019) (quotation marks omitted).\n\n And later that same month, the Supreme Court vacated another stay of\n\nexecution that this Court had issued. Its decision to vacate the stay was based on\n\nthe fact that the inmate had delayed bringing his challenge to the State’s lethal\n\ninjection protocol until about two months before his scheduled execution, and then\n\nwaited until just a few hours before that execution to submit additional evidence.\n\nDunn v. Price, 139 S. Ct. 1312, 1312 (2019). The Supreme Court again relied on\n\nGomez to instruct courts to consider the last-minute nature of a stay in determining\n\nwhether equitable relief is appropriate. Id.\n\n Long’s case is not one of the “extreme exception[s]” in which a last-minute\n\nstay should be entered, but instead is within “the norm” where the “strong\n\nequitable presumption against the grant of a stay” applies. Bucklew, 139 S. Ct. at\n\n1134; Hill, 547 U.S. at 584 (quotation marks omitted).\n\n The first of Long’s method of execution claims is that Florida’s use of a\n\nthree-drug protocol instead of a one-drug protocol violates the Eighth Amendment.\n\nBut Florida has used a three-drug protocol since January 14, 2000, when it added\n\nlethal injection as a new method of execution. See Heynard v. Sec’y, DOC, 543\n\n\n\n 10\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 11 of 18\n\n\nF.3d 644, 647 (11th Cir. 2014). Long has had nineteen years to challenge the use\n\nof a three-drug protocol. Nineteen years is too long to wait.\n\n To the extent that Long argues that a challenge to three-drug protocols\n\nwould not have been valid until now because other states have only recently begun\n\nusing one-drug protocols, that argument is belied by allegations in his own\n\ncomplaint. It alleges that at least four other states have “used a single-drug method\n\nfor executions since 2009.” Ten years is too long to wait.\n\n Long’s other two method of execution claims also suffer from his delay in\n\nbringing them. In those claims, he contends that Florida’s use of etomidate as the\n\nfirst drug in its three-drug protocol is unconstitutional regardless of the health of\n\nthe inmate, and that it is especially so as applied to him because of his serious\n\nmedical conditions.\n\n Florida adopted etomidate as the first drug in its three-drug protocol in\n\nJanuary of 2017, two years and four months ago. But Long waited until a week\n\nago to file this § 1983 challenge to it. Long alleges in his complaint that three of\n\nFlorida’s recent executions using etomidate show that the drug causes inmates\n\nsevere pain because it does not properly anesthetize them. To the extent that Long\n\nargues (and it is not clear that he does) that the delay in bringing his claims was\n\nbased on facts arising from those executions, his argument is not persuasive. The\n\nfirst of the three executions occurred on November 8, 2017, the second on\n\n\n\n 11\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 12 of 18\n\n\nFebruary 22, 2018, and the last of them on December 13, 2018. A delay of five\n\nmonths, fifteen months, or eighteen months is too long.\n\n Long’s person-specific claim is that his medical conditions will complicate\n\nFlorida’s use of etomidate and may cause him unnecessary pain. But Long has\n\nknown about his medical conditions for decades. During his 1989 resentencing\n\ntrial, he presented as mitigating evidence the testimony of two medical experts\n\nabout his traumatic brain injury and temporal lobe epilepsy. See Long, 610 So. 2d\n\nat 1271–72. Any argument about how etomidate would be uniquely harmful to\n\nhim could have been raised as soon as Florida adopted etomidate as the first drug\n\nin its three-drug protocol. That happened in January 2017, two years and four\n\nmonths before Long brought this lawsuit.\n\n If Long had truly intended to challenge Florida’s lethal injection protocol\n\ninstead of just seeking to delay his execution, he would not have deliberately\n\nwaited to file this lawsuit until a decision on the merits would require entry of a\n\nstay. We have refused to grant stays in cases involving delayed filings before, and\n\nLong’s delay was even more pronounced and less justifiable. See e.g., Brooks v.\n\nWarden, 810 F.3d 812, 826 (11th Cir. 2016) (holding that an inmate was not\n\nentitled to a stay where he delayed filing his § 1983 challenge until eleven weeks\n\nbefore his execution); In re Hutcherson, 468 F.3d 747, 749–50 (11th Cir. 2006)\n\n(denying prisoner’s motion to stay his execution pending this Court’s resolution of\n\n\n\n 12\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 13 of 18\n\n\nhis application for leave to file a successive petition because he waited until eight\n\ndays before his scheduled execution to file it and, as a result, his “need for a stay of\n\nexecution [was] directly attributable to his own failure to bring his claims to court\n\nin a timely fashion”); Diaz v. McDonough, 472 F.3d 849, 851 (11th Cir. 2006)\n\n(declining to grant a preliminary injunction so that an inmate could pursue an\n\nappeal because he filed his § 1983 complaint less than three days before his\n\nscheduled execution); cf. Jones v. Allen, 485 F.3d 635, 640 (11th Cir. 2007)\n\n(holding that inmate was not entitled to a stay of execution because he waited four\n\nyears after learning that the state intended to execute him by lethal injection to file\n\nhis § 1983 challenge).\n\n 2. Res Judicata\n\n Even if Long’s method of execution claims were not barred on equitable\n\ngrounds, the district court properly concluded that he could not show a likelihood\n\nof success on the merits because the claims are barred by the doctrine of res\n\njudicata. All of the claims Long raises in this § 1983 action were raised, or could\n\nhave been raised, in his fourth motion for postconviction relief, which the Florida\n\nSupreme Court rejected. See Long, 2019 WL 2150942, at *6–7.\n\n To the district court’s concise and correct discussion, we add one point,\n\nwhich responds to Long’s argument that applying the doctrine of res judicata\n\nwould work a manifest injustice in his case. He claims that because the state\n\n\n\n 13\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 14 of 18\n\n\ncourts did not give him a hearing on the merits of his general challenge, and\n\nbecause the hearing that they did give him on his person-specific challenge was\n\n“severely restricted” due to the “extraordinarily constrained timeline” for the\n\nlitigation of his fourth postconviction motion, it would be unjust to give the Florida\n\nSupreme Court’s decision preclusive effect.\n\n There are three big problems with this argument. First, his position is\n\nunprecedented. Long has not pointed to a single published decision of the Florida\n\ncourts or this Court applying Florida law holding that it is a “manifest injustice” to\n\napply res judicata if the initial state court decision resolved a claim without\n\ngranting an evidentiary hearing. 1\n\n The second problem with Long’s position is that the “extraordinarily\n\nconstrained timeline” that he complains of is a direct result of his delay in filing his\n\nmethod of execution claims in state postconviction proceedings until after his\n\nexecution date had been set. As we have discussed, there is no reason why Long\n\ncould not have challenged Florida’s use of a three-drug protocol as early as 2000\n\n\n\n 1\n The inapplicability of the precedent that Long cites and the unpersuasiveness of the\narguments that he makes are illustrated by the following sentence and citation from his brief:\n“This Court has declined to apply res judicata where an inmate was not given an evidentiary\nhearing on his challenge in state court. See Chavez v. Sec’y, 742 F.3d 1267 (11th Cir. 2014).”\nThat citation is disingenuous. The entire discussion of res judicata in the Chavez opinion\nconsists of the following footnote: “In light of our conclusion that Chavez has not established a\nsubstantial likelihood of success on the merits of any of his claims, we do not address and imply\nno view about the State’s asserted defenses based on the statute of limitations, exhaustion of\nadministrative remedies, and res judicata.” Chavez, 742 F.3d at 1273 n.5.\n\n\n 14\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 15 of 18\n\n\n(when Florida adopted lethal injection as a method of execution) or at least by\n\n2009 (when, according to the allegations in his complaint, a number of states had\n\nswitched to a one-drug protocol). And there is no reason why Long could not have\n\nchallenged Florida’s use of etomidate, both in general and specifically as to him,\n\nin January 2017, when the Florida Department of Corrections decided to use it as\n\nthe first drug in the three-drug protocol. It is worse than ironic for Long to argue\n\nthat the state court’s decision does not deserve res judicata effect because the state\n\ncourt had to render that decision under the time constraints that Long forced on it.\n\n There is another fundamental problem with Long’s arguments against the\n\napplication of res judicata. Reduced to its essence, his position is that the res\n\njudicata doctrine applies only if the court in which it is asserted agrees with the\n\ninitial court’s decision on de novo consideration. And, he says, we shouldn’t agree\n\nwith the decision of the Florida courts on these claims for a number of reasons.\n\nBut that is not the way that res judicata works. If it did, the doctrine would be\n\ntoothless, pointless, and fruitless. It would apply only when it made no difference.\n\nThe Florida courts have never suggested such a rule-devouring exception, and we\n\nwill not presume to create one for them here. See Kremer v. Chem. Constr. Corp.,\n\n456 U.S. 461, 481–82 (1982) (“It has long been established that [28 U.S.C.] § 1738\n\ndoes not allow federal courts to employ their own rules of res judicata in\n\ndetermining the effect of state judgments. Rather, it goes beyond the common law\n\n\n\n 15\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 16 of 18\n\n\nand commands a federal court to accept the rules chosen by the State from which\n\nthe judgment is taken.”).\n\n B. Long’s Public Records and Witness Claims\n\n In addition to his three method of execution claims, Long contends that the\n\ndefendants violated his constitutional rights by (1) objecting to some of his public\n\nrecords requests and refusing to answer some of his questions about the lethal\n\ninjection protocol, and (2) denying his requests for exceptions to the Department of\n\nCorrections’ witness policies. As the district court already held, both of those\n\nclaims are also barred by the doctrine of res judicata. Long raised a public records\n\nclaim in the Florida courts, see Long, 2019 WL 2150942, at *6–7, and he could\n\nhave asserted any similar claims in the state court proceedings.\n\n There are many published decisions that support the district court’s ruling\n\nthat, under Florida law, res judicata bars claims that Long could have raised in the\n\nstate postconviction proceedings but didn’t. See, e.g., Topps v. State, 865 So. 2d\n\n1253, 1255 (Fla. 2004) (“The doctrine of res judicata bars relitigation in a\n\nsubsequent cause of action not only of claims raised, but also claims that could\n\nhave been raised.”); Fla. Dep’t of Transp. v. Juliano, 801 So. 2d 101, 105 (Fla.\n\n2001) (“Importantly, the doctrine of res judicata not only bars issues that were\n\nraised, but it also precludes consideration of issues that could have been raised but\n\nwere not raised in the first case.”); see also Vasquez v. YII Shipping Co., 692 F.3d\n\n\n\n 16\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 17 of 18\n\n\n1192, 1199 (11th Cir. 2012) (applying Florida law to explain that “the purpose of\n\nres judicata is that a final judgment in a court of competent jurisdiction is absolute\n\nand settles all issues actually litigated in a proceeding as well as those issues that\n\ncould have been litigated.”) (quotation marks omitted). The district court was\n\nentirely correct in concluding that Long’s public records and witness claims are\n\nbarred by res judicata.\n\n IV. CONCLUSION\n\n We AFFIRM the district court’s denial of Long’s emergency motion for a\n\ntemporary restraining order, preliminary injunction, or stay of execution. We\n\nDENY Long’s motion for a stay of execution from this Court.\n\n\n\n\n 17\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 18 of 18\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Bobby Joe LONG, Plaintiff-Appellant, v. SECRETARY, DEPARTMENT OF CORRECTIONS, Warden, Florida State Prison, John Does, as Designee of Barry Reddish, and/or Mark S. Inch, Defendants-Appellees.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 19-11942 Date Filed: 05/22/2019 Page: 1 of 18\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 19-11942\\n ________________________\\n\\n D.C. Docket No. 8:19-cv-01193-MSS-AEP\\n\\n\\n\\nBOBBY JOE LONG,\\n\\n Plaintiff-Appellant,\\n\\n versus\\n\\nSECRETARY, DEPARTMENT OF CORRECTIONS, WARDEN, FLORIDA\\nSTATE PRISON, JOHN DOES, as designee of Barry Reddish, and/or Mark S.\\nInch,\\n\\n Defendants-Appellees.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Florida\\n ________________________\\n\\n (May 22, 2019)\\n\\nBefore ED CARNES, Chief Judge, MARCUS, and JORDAN, Circuit Judges.\\n\\nED CARNES, Chief Judge:\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 2 of 18\\n\\n\\n Bobby Joe Long kidnapped, sexually battered, and murdered Michelle\\n\\nDenise Simms. And at least seven more women. He brutalized others. After\\n\\npleading guilty, he was convicted and sentenced to death for the Simms murder.\\n\\nThat was more than 32 years ago. After his sentence was vacated and the case\\n\\nremanded, he was resentenced to death. That was more than 30 years ago.\\n\\n Seven days before Long is scheduled to be executed, he filed a 28 U.S.C.\\n\\n§ 1983 complaint in the United States District Court for the Middle District of\\n\\nFlorida. He also filed an emergency motion for a temporary restraining order,\\n\\npreliminary injunction, or stay of execution to prevent the State of Florida from\\n\\nexecuting him on May 23, 2019.\\n\\n I. PROCEDURAL HISTORY\\n\\n In September 1985, Long pleaded guilty to eight counts of first-degree\\n\\nmurder, nine counts of kidnapping, eight counts of sexual battery, and one\\n\\nprobation violation. Long v. State, 610 So. 2d 1268, 1269 (Fla. 1992). That plea\\n\\nincluded his admission that he kidnapped, sexually battered, and murdered\\n\\nMichelle Denise Simms. Id. The State of Florida agreed that it would not seek the\\n\\ndeath penalty for the other murders Long admitted committing. Id. A full penalty\\n\\nphase proceeding before a jury was held in the case involving the crimes Long\\n\\ncommitted against Simms. Long v. State, 529 So. 2d 286, 288, 291 (Fla. 1988).\\n\\n\\n\\n\\n 2\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 3 of 18\\n\\n\\nThe jury recommended the death penalty by a vote of eleven to one. Id. at 291.\\n\\nThe trial court adopted that recommendation and sentenced Long to death. Id.\\n\\n On direct appeal, the Florida Supreme Court affirmed Long’s convictions\\n\\nand sentences except for the death sentence. Id. at 291–93. It concluded that\\n\\nbecause the trial judge had found that one of Long’s prior convictions qualified as\\n\\nan aggravating factor, and that prior conviction had since been reversed and\\n\\nvacated by an appellate court as a result of a Miranda violation, Long was entitled\\n\\nto a new sentencing proceeding. Id. at 293. A resentencing trial was conducted\\n\\nbefore a new jury and in a new venue. See Long, 610 So. 2d at 1270. The jury\\n\\nrecommended death, this time unanimously. Id. at 1272. The trial court adopted\\n\\nthat recommendation and imposed the death penalty. Id. The Florida Supreme\\n\\nCourt affirmed, id. at 1275, and the United States Supreme Court denied Long’s\\n\\npetition for a writ of certiorari, Long v. Florida, 510 U.S. 832 (1993), making his\\n\\nconvictions and sentences final in 1993.\\n\\n Following the conclusion of his direct appeals, Long unsuccessfully sought\\n\\npostconviction relief in state court three times. See Long v. State, 235 So. 3d 293\\n\\n(Fla. 2018); Long v. State, 183 So. 3d 342 (Fla. 2016); Long v. State, 118 So. 3d\\n\\n798 (Fla. 2013). Long also filed a federal habeas petition in the district court in\\n\\n2013. The district court denied that petition on the merits, and this Court denied\\n\\nLong’s application for a certificate of appealability. See Long v. Sec’y, Fla. Dep’t\\n\\n\\n\\n 3\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 4 of 18\\n\\n\\nof Corr., No. 16-16259 (11th Cir. Jan. 4, 2017); Long v. Sec’y, Dep’t of Corr., No.\\n\\n8:13-cv-02069-T-27AEP (M.D. Fla. Aug. 30, 2016).\\n\\n After all of Long’s attempts at postconviction relief had been resolved\\n\\nconclusively against him, the Florida Commission on Offender Review initiated\\n\\nstate clemency proceedings in Long’s case. The Commission conducted\\n\\nproceedings and took the matter under submission in September 2018. After the\\n\\nCommission reported to the Governor, he denied clemency. Long was notified of\\n\\nthat decision in April 2019.\\n\\n The Governor signed Long’s death warrant on April 23, 2019, and the\\n\\nWarden set the execution date for May 23, 2019. Since then, Long has filed in the\\n\\nFlorida courts a flurry of motions, including two motions for a stay of execution, a\\n\\nmotion to dismiss his death warrant as defective, and a motion for postconviction\\n\\nrelief (the fourth one he had filed). He also filed a petition for habeas corpus in the\\n\\nFlorida Supreme Court. All of his motions and petitions have been denied.\\n\\n On May 8, 2019, Long filed in the United States District Court for the\\n\\nNorthern District of Florida a § 1983 complaint. In that complaint, he claims that\\n\\nthe State of Florida violated his federal statutory right to counsel by declining to\\n\\nallow his federally-appointed attorneys to appear at his interview in the state\\n\\nclemency proceedings and that the state-appointed attorney who was present and\\n\\nrepresented him at that interview rendered ineffective assistance of counsel in\\n\\n\\n\\n 4\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 5 of 18\\n\\n\\nviolation of the Sixth Amendment. Along with that § 1983 complaint, Long filed\\n\\nan emergency motion for a stay of execution. The district court denied that motion\\n\\non May 16, 2019. On May 20, 2019, Long filed a motion for reconsideration in\\n\\nthe district court, which it denied on May 21, 2019.\\n\\n In his complaint in this § 1983 proceeding, Long raises five claims. First, he\\n\\nclaims that Florida’s use of a three-drug protocol instead of a one-drug protocol\\n\\nviolates the Eighth Amendment. Second, he claims that Florida’s use of etomidate\\n\\nas the first drug in that three-drug protocol is facially unconstitutional because it\\n\\ncreates a risk of severe pain that is substantial when compared to the known and\\n\\navailable alternative of using the single drug pentobarbital. Third, he claims that\\n\\neven if the use of etomidate does not amount to cruel and unusual punishment in\\n\\nall cases, it does in his case because of his serious medical conditions (traumatic\\n\\nbrain injury and temporal lobe epilepsy).\\n\\n Fourth, he claims that the State violated his First, Fifth, Eighth, and\\n\\nFourteenth Amendment rights by objecting to his requests for public records and\\n\\nrefusing to answer his questions about the lethal injection protocol. And finally,\\n\\nLong claims that the Warden violated his First, Sixth, Eighth, and Fourteenth\\n\\nAmendment rights by refusing his requests to: (1) have an additional attorney\\n\\nwitness at his execution in lieu of a spiritual adviser, (2) permit Long’s attorneys to\\n\\nhave access to a phone during the execution, and (3) permit one of Long’s\\n\\n\\n 5\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 6 of 18\\n\\n\\nwitnesses to observe the insertion of the IV line that will be used to administer the\\n\\nlethal drugs.\\n\\n Along with his complaint, Long filed an emergency motion for a temporary\\n\\nrestraining order, preliminary injunction, or stay of execution. He requested that\\n\\nthe district court order the State to hold off on his execution until the court had\\n\\ntime to consider each of his claims (which, according to Long, would require\\n\\ndiscovery and an evidentiary hearing).\\n\\n The district court denied Long’s motion for a temporary restraining order,\\n\\npreliminary injunction, or stay of execution on May 19, 2019. It concluded that all\\n\\nof Long’s claims were barred by the doctrine of res judicata as a result of the\\n\\nFlorida Supreme Court’s decision in Long v. State, No. SC19-726, 2019 WL\\n\\n2150942 (Fla. May 17, 2019). For that reason, he could not show a substantial\\n\\nlikelihood of success on the merits. Long filed a notice of appeal the same day.\\n\\nOn May 20, 2019, he filed in this Court a motion for a stay of execution, or in the\\n\\nalternative, an expedited appeal. We granted his motion to expedite the appeal.\\n\\n On May 20, 2019, Long filed two petitions for a writ of certiorari in the\\n\\nUnited States Supreme Court, each accompanied by an application for a stay of\\n\\nexecution. One of those petitions seeks review of the Florida Supreme Court’s\\n\\ndenial of his state habeas petition. The other one seeks review of the Florida\\n\\nSupreme Court’s denial of his fourth motion for postconviction relief. In that one,\\n\\n\\n\\n 6\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 7 of 18\\n\\n\\nhe raises two claims that he also raised in the § 1983 lawsuit at issue in this appeal:\\n\\n(1) his claim about the Warden’s denial of his requests for exceptions to the\\n\\nDepartment of Corrections’ witness policy, and (2) his challenge to Florida’s use\\n\\nof etomidate in its lethal injection protocol.\\n\\n II. STANDARD OF REVIEW\\n\\n We review the district court’s denial of a motion for a temporary restraining\\n\\norder, preliminary injunction, or stay of execution only for abuse of discretion.\\n\\nGissendaner v. Comm’r, Ga. Dep’t of Corr., 779 F.3d 1275, 1280 (11th Cir. 2015)\\n\\n(temporary restraining order); Chavez v. Fla. SP Warden, 742 F.3d 1267, 1271\\n\\n(11th Cir. 2014) (preliminary injunction); Muhammad v. Sec’y, Fla. Dep’t of\\n\\nCorr., 739 F.3d 683, 688 (11th Cir. 2014) (stay of execution). A district court\\n\\nabuses its discretion if, among other things, “it applies an incorrect legal standard,\\n\\nfollows improper procedures in making the determination, or makes findings of\\n\\nfact that are clearly erroneous.” Grayson v. Warden, Comm’r, Ala. DOC, 869 F.3d\\n\\n1204, 1238 (11th Cir. 2017) (quotation marks omitted).\\n\\n A federal court may grant a temporary restraining order, preliminary\\n\\ninjunction, or a stay of execution only if the movant establishes that (1) he has a\\n\\nsubstantial likelihood of success on the merits, (2) he will suffer irreparable injury\\n\\nunless the injunction issues, (3) the injunction would not substantially harm the\\n\\nother litigant, and (4) if issued, the injunction would not be adverse to the public\\n\\n\\n\\n 7\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 8 of 18\\n\\n\\ninterest. Powell v. Thomas, 641 F.3d 1255, 1257 (11th Cir. 2011); see also\\n\\nGissendaner, 779 F.3d at 1280; Chavez, 742 F.3d at 1271.\\n\\n III. DISCUSSION\\n\\n A. Long’s Method of Execution Claims\\n\\n The district court did not abuse its discretion in declining to stay Long’s\\n\\nexecution on account of his three method of execution claims. Each of them is\\n\\nbarred for two independently adequate reasons. First, Long engaged in\\n\\ninexcusable delay in bringing the claims, which is enough to deny him the\\n\\nequitable remedy of a stay. And second, as the district court properly held, each of\\n\\nhis claims is barred by the doctrine of res judicata.\\n\\n 1. Inexcusable Delay\\n\\n Long is not entitled to a stay of execution “as a matter of course” simply\\n\\nbecause he brought a § 1983 claim. Hill v. McDonough, 547 U.S. 573, 583–84\\n\\n(2006). Instead, a stay of execution is an equitable remedy and all of the rules of\\n\\nequity apply. See Rutherford v. Crosby, 438 F.3d 1087, 1092 (11th Cir. 2006)\\n\\n(explaining that “where petitioner’s scheduled execution is imminent, there is no\\n\\npractical difference between denying a stay on equitable grounds and denying\\n\\ninjunctive relief on equitable grounds in a § 1983 lawsuit”), vacated on other\\n\\ngrounds, Rutherford v. McDonough, 547 U.S. 1204 (2006).\\n\\n\\n\\n\\n 8\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 9 of 18\\n\\n\\n One of those rules is that “[e]quity must take into consideration the State’s\\n\\nstrong interest in proceeding with its judgment” and an inmate’s “attempt at\\n\\nmanipulation.” Gomez v. U.S. Dist. Ct. for N. Dist. of Cal., 503 U.S. 653, 654\\n\\n(1992) (per curiam). As a result, before granting a stay of execution, a court must\\n\\n“consider not only the likelihood of success on the merits and the relative harms to\\n\\nthe parties, but also the extent to which the inmate has delayed unnecessarily in\\n\\nbringing the claim.” Nelson v. Campbell, 541 U.S. 637, 649–50 (2004). There is a\\n\\n“strong equitable presumption against the grant of a stay where a claim could have\\n\\nbeen brought at such a time as to allow consideration of the merits without\\n\\nrequiring entry of a stay.” Id. at 650.\\n\\n The Supreme Court has reiterated the importance of these principles three\\n\\ntimes this year. The first time was in February when a stay entered by this Court\\n\\nwas vacated by the Supreme Court. Dunn v. Ray, 139 S. Ct. 661 (2019). In\\n\\nvacating the stay, the Court quoted from Gomez: “A court may consider the last-\\n\\nminute nature of an application to stay execution in deciding whether to grant\\n\\nequitable relief.” Id. at 661 (quoting Gomez, 503 U.S. at 654).\\n\\n And then in April, when affirming the Eighth Circuit’s denial of an inmate’s\\n\\nas-applied challenge to the State’s method of execution, the Supreme Court\\n\\nexplicitly instructed lower courts that: “Courts should police carefully against\\n\\nattempts to use such challenges as tools to interpose unjustified delay. Last-minute\\n\\n\\n\\n 9\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 10 of 18\\n\\n\\nstays should be the extreme exception, not the norm, and the last-minute nature of\\n\\nan application that could have been brought earlier, or an applicant’s attempt at\\n\\nmanipulation, may be grounds for denial of a stay.” Bucklew v. Precythe, 139 S.\\n\\nCt. 1112, 1134 (2019) (quotation marks omitted).\\n\\n And later that same month, the Supreme Court vacated another stay of\\n\\nexecution that this Court had issued. Its decision to vacate the stay was based on\\n\\nthe fact that the inmate had delayed bringing his challenge to the State’s lethal\\n\\ninjection protocol until about two months before his scheduled execution, and then\\n\\nwaited until just a few hours before that execution to submit additional evidence.\\n\\nDunn v. Price, 139 S. Ct. 1312, 1312 (2019). The Supreme Court again relied on\\n\\nGomez to instruct courts to consider the last-minute nature of a stay in determining\\n\\nwhether equitable relief is appropriate. Id.\\n\\n Long’s case is not one of the “extreme exception[s]” in which a last-minute\\n\\nstay should be entered, but instead is within “the norm” where the “strong\\n\\nequitable presumption against the grant of a stay” applies. Bucklew, 139 S. Ct. at\\n\\n1134; Hill, 547 U.S. at 584 (quotation marks omitted).\\n\\n The first of Long’s method of execution claims is that Florida’s use of a\\n\\nthree-drug protocol instead of a one-drug protocol violates the Eighth Amendment.\\n\\nBut Florida has used a three-drug protocol since January 14, 2000, when it added\\n\\nlethal injection as a new method of execution. See Heynard v. Sec’y, DOC, 543\\n\\n\\n\\n 10\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 11 of 18\\n\\n\\nF.3d 644, 647 (11th Cir. 2014). Long has had nineteen years to challenge the use\\n\\nof a three-drug protocol. Nineteen years is too long to wait.\\n\\n To the extent that Long argues that a challenge to three-drug protocols\\n\\nwould not have been valid until now because other states have only recently begun\\n\\nusing one-drug protocols, that argument is belied by allegations in his own\\n\\ncomplaint. It alleges that at least four other states have “used a single-drug method\\n\\nfor executions since 2009.” Ten years is too long to wait.\\n\\n Long’s other two method of execution claims also suffer from his delay in\\n\\nbringing them. In those claims, he contends that Florida’s use of etomidate as the\\n\\nfirst drug in its three-drug protocol is unconstitutional regardless of the health of\\n\\nthe inmate, and that it is especially so as applied to him because of his serious\\n\\nmedical conditions.\\n\\n Florida adopted etomidate as the first drug in its three-drug protocol in\\n\\nJanuary of 2017, two years and four months ago. But Long waited until a week\\n\\nago to file this § 1983 challenge to it. Long alleges in his complaint that three of\\n\\nFlorida’s recent executions using etomidate show that the drug causes inmates\\n\\nsevere pain because it does not properly anesthetize them. To the extent that Long\\n\\nargues (and it is not clear that he does) that the delay in bringing his claims was\\n\\nbased on facts arising from those executions, his argument is not persuasive. The\\n\\nfirst of the three executions occurred on November 8, 2017, the second on\\n\\n\\n\\n 11\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 12 of 18\\n\\n\\nFebruary 22, 2018, and the last of them on December 13, 2018. A delay of five\\n\\nmonths, fifteen months, or eighteen months is too long.\\n\\n Long’s person-specific claim is that his medical conditions will complicate\\n\\nFlorida’s use of etomidate and may cause him unnecessary pain. But Long has\\n\\nknown about his medical conditions for decades. During his 1989 resentencing\\n\\ntrial, he presented as mitigating evidence the testimony of two medical experts\\n\\nabout his traumatic brain injury and temporal lobe epilepsy. See Long, 610 So. 2d\\n\\nat 1271–72. Any argument about how etomidate would be uniquely harmful to\\n\\nhim could have been raised as soon as Florida adopted etomidate as the first drug\\n\\nin its three-drug protocol. That happened in January 2017, two years and four\\n\\nmonths before Long brought this lawsuit.\\n\\n If Long had truly intended to challenge Florida’s lethal injection protocol\\n\\ninstead of just seeking to delay his execution, he would not have deliberately\\n\\nwaited to file this lawsuit until a decision on the merits would require entry of a\\n\\nstay. We have refused to grant stays in cases involving delayed filings before, and\\n\\nLong’s delay was even more pronounced and less justifiable. See e.g., Brooks v.\\n\\nWarden, 810 F.3d 812, 826 (11th Cir. 2016) (holding that an inmate was not\\n\\nentitled to a stay where he delayed filing his § 1983 challenge until eleven weeks\\n\\nbefore his execution); In re Hutcherson, 468 F.3d 747, 749–50 (11th Cir. 2006)\\n\\n(denying prisoner’s motion to stay his execution pending this Court’s resolution of\\n\\n\\n\\n 12\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 13 of 18\\n\\n\\nhis application for leave to file a successive petition because he waited until eight\\n\\ndays before his scheduled execution to file it and, as a result, his “need for a stay of\\n\\nexecution [was] directly attributable to his own failure to bring his claims to court\\n\\nin a timely fashion”); Diaz v. McDonough, 472 F.3d 849, 851 (11th Cir. 2006)\\n\\n(declining to grant a preliminary injunction so that an inmate could pursue an\\n\\nappeal because he filed his § 1983 complaint less than three days before his\\n\\nscheduled execution); cf. Jones v. Allen, 485 F.3d 635, 640 (11th Cir. 2007)\\n\\n(holding that inmate was not entitled to a stay of execution because he waited four\\n\\nyears after learning that the state intended to execute him by lethal injection to file\\n\\nhis § 1983 challenge).\\n\\n 2. Res Judicata\\n\\n Even if Long’s method of execution claims were not barred on equitable\\n\\ngrounds, the district court properly concluded that he could not show a likelihood\\n\\nof success on the merits because the claims are barred by the doctrine of res\\n\\njudicata. All of the claims Long raises in this § 1983 action were raised, or could\\n\\nhave been raised, in his fourth motion for postconviction relief, which the Florida\\n\\nSupreme Court rejected. See Long, 2019 WL 2150942, at *6–7.\\n\\n To the district court’s concise and correct discussion, we add one point,\\n\\nwhich responds to Long’s argument that applying the doctrine of res judicata\\n\\nwould work a manifest injustice in his case. He claims that because the state\\n\\n\\n\\n 13\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 14 of 18\\n\\n\\ncourts did not give him a hearing on the merits of his general challenge, and\\n\\nbecause the hearing that they did give him on his person-specific challenge was\\n\\n“severely restricted” due to the “extraordinarily constrained timeline” for the\\n\\nlitigation of his fourth postconviction motion, it would be unjust to give the Florida\\n\\nSupreme Court’s decision preclusive effect.\\n\\n There are three big problems with this argument. First, his position is\\n\\nunprecedented. Long has not pointed to a single published decision of the Florida\\n\\ncourts or this Court applying Florida law holding that it is a “manifest injustice” to\\n\\napply res judicata if the initial state court decision resolved a claim without\\n\\ngranting an evidentiary hearing. 1\\n\\n The second problem with Long’s position is that the “extraordinarily\\n\\nconstrained timeline” that he complains of is a direct result of his delay in filing his\\n\\nmethod of execution claims in state postconviction proceedings until after his\\n\\nexecution date had been set. As we have discussed, there is no reason why Long\\n\\ncould not have challenged Florida’s use of a three-drug protocol as early as 2000\\n\\n\\n\\n 1\\n The inapplicability of the precedent that Long cites and the unpersuasiveness of the\\narguments that he makes are illustrated by the following sentence and citation from his brief:\\n“This Court has declined to apply res judicata where an inmate was not given an evidentiary\\nhearing on his challenge in state court. See Chavez v. Sec’y, 742 F.3d 1267 (11th Cir. 2014).”\\nThat citation is disingenuous. The entire discussion of res judicata in the Chavez opinion\\nconsists of the following footnote: “In light of our conclusion that Chavez has not established a\\nsubstantial likelihood of success on the merits of any of his claims, we do not address and imply\\nno view about the State’s asserted defenses based on the statute of limitations, exhaustion of\\nadministrative remedies, and res judicata.” Chavez, 742 F.3d at 1273 n.5.\\n\\n\\n 14\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 15 of 18\\n\\n\\n(when Florida adopted lethal injection as a method of execution) or at least by\\n\\n2009 (when, according to the allegations in his complaint, a number of states had\\n\\nswitched to a one-drug protocol). And there is no reason why Long could not have\\n\\nchallenged Florida’s use of etomidate, both in general and specifically as to him,\\n\\nin January 2017, when the Florida Department of Corrections decided to use it as\\n\\nthe first drug in the three-drug protocol. It is worse than ironic for Long to argue\\n\\nthat the state court’s decision does not deserve res judicata effect because the state\\n\\ncourt had to render that decision under the time constraints that Long forced on it.\\n\\n There is another fundamental problem with Long’s arguments against the\\n\\napplication of res judicata. Reduced to its essence, his position is that the res\\n\\njudicata doctrine applies only if the court in which it is asserted agrees with the\\n\\ninitial court’s decision on de novo consideration. And, he says, we shouldn’t agree\\n\\nwith the decision of the Florida courts on these claims for a number of reasons.\\n\\nBut that is not the way that res judicata works. If it did, the doctrine would be\\n\\ntoothless, pointless, and fruitless. It would apply only when it made no difference.\\n\\nThe Florida courts have never suggested such a rule-devouring exception, and we\\n\\nwill not presume to create one for them here. See Kremer v. Chem. Constr. Corp.,\\n\\n456 U.S. 461, 481–82 (1982) (“It has long been established that [28 U.S.C.] § 1738\\n\\ndoes not allow federal courts to employ their own rules of res judicata in\\n\\ndetermining the effect of state judgments. Rather, it goes beyond the common law\\n\\n\\n\\n 15\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 16 of 18\\n\\n\\nand commands a federal court to accept the rules chosen by the State from which\\n\\nthe judgment is taken.”).\\n\\n B. Long’s Public Records and Witness Claims\\n\\n In addition to his three method of execution claims, Long contends that the\\n\\ndefendants violated his constitutional rights by (1) objecting to some of his public\\n\\nrecords requests and refusing to answer some of his questions about the lethal\\n\\ninjection protocol, and (2) denying his requests for exceptions to the Department of\\n\\nCorrections’ witness policies. As the district court already held, both of those\\n\\nclaims are also barred by the doctrine of res judicata. Long raised a public records\\n\\nclaim in the Florida courts, see Long, 2019 WL 2150942, at *6–7, and he could\\n\\nhave asserted any similar claims in the state court proceedings.\\n\\n There are many published decisions that support the district court’s ruling\\n\\nthat, under Florida law, res judicata bars claims that Long could have raised in the\\n\\nstate postconviction proceedings but didn’t. See, e.g., Topps v. State, 865 So. 2d\\n\\n1253, 1255 (Fla. 2004) (“The doctrine of res judicata bars relitigation in a\\n\\nsubsequent cause of action not only of claims raised, but also claims that could\\n\\nhave been raised.”); Fla. Dep’t of Transp. v. Juliano, 801 So. 2d 101, 105 (Fla.\\n\\n2001) (“Importantly, the doctrine of res judicata not only bars issues that were\\n\\nraised, but it also precludes consideration of issues that could have been raised but\\n\\nwere not raised in the first case.”); see also Vasquez v. YII Shipping Co., 692 F.3d\\n\\n\\n\\n 16\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 17 of 18\\n\\n\\n1192, 1199 (11th Cir. 2012) (applying Florida law to explain that “the purpose of\\n\\nres judicata is that a final judgment in a court of competent jurisdiction is absolute\\n\\nand settles all issues actually litigated in a proceeding as well as those issues that\\n\\ncould have been litigated.”) (quotation marks omitted). The district court was\\n\\nentirely correct in concluding that Long’s public records and witness claims are\\n\\nbarred by res judicata.\\n\\n IV. CONCLUSION\\n\\n We AFFIRM the district court’s denial of Long’s emergency motion for a\\n\\ntemporary restraining order, preliminary injunction, or stay of execution. We\\n\\nDENY Long’s motion for a stay of execution from this Court.\\n\\n\\n\\n\\n 17\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 18 of 18\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2288,"cells":{"id":{"kind":"number","value":4622513,"string":"4,622,513"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"Bobby Joe Long v. Secretary, Department of Corrections"},"decision_date":{"kind":"string","value":"2019-05-22"},"docket_number":{"kind":"string","value":"19-11942"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before ED CARNES, Chief Judge, MARCUS, and JORDAN, Circuit Judges.\", \"parties\": \"\", \"opinions\": [{\"author\": \"ED CARNES, Chief Judge\", \"type\": \"010combined\", \"text\": \"Case: 19-11942 Date Filed: 05/22/2019 Page: 1 of 18\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 19-11942\\n ________________________\\n\\n D.C. Docket No. 8:19-cv-01193-MSS-AEP\\n\\n\\n\\nBOBBY JOE LONG,\\n\\n Plaintiff-Appellant,\\n\\n versus\\n\\nSECRETARY, DEPARTMENT OF CORRECTIONS, WARDEN, FLORIDA\\nSTATE PRISON, JOHN DOES, as designee of Barry Reddish, and/or Mark S.\\nInch,\\n\\n Defendants-Appellees.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Florida\\n ________________________\\n\\n (May 22, 2019)\\n\\nBefore ED CARNES, Chief Judge, MARCUS, and JORDAN, Circuit Judges.\\n\\nED CARNES, Chief Judge:\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 2 of 18\\n\\n\\n Bobby Joe Long kidnapped, sexually battered, and murdered Michelle\\n\\nDenise Simms. And at least seven more women. He brutalized others. After\\n\\npleading guilty, he was convicted and sentenced to death for the Simms murder.\\n\\nThat was more than 32 years ago. After his sentence was vacated and the case\\n\\nremanded, he was resentenced to death. That was more than 30 years ago.\\n\\n Seven days before Long is scheduled to be executed, he filed a 42 U.S.C.\\n\\n§ 1983 complaint in the United States District Court for the Middle District of\\n\\nFlorida. He also filed an emergency motion for a temporary restraining order,\\n\\npreliminary injunction, or stay of execution to prevent the State of Florida from\\n\\nexecuting him on May 23, 2019.\\n\\n I. PROCEDURAL HISTORY\\n\\n In September 1985, Long pleaded guilty to eight counts of first-degree\\n\\nmurder, nine counts of kidnapping, eight counts of sexual battery, and one\\n\\nprobation violation. Long v. State, 610 So. 2d 1268, 1269 (Fla. 1992). That plea\\n\\nincluded his admission that he kidnapped, sexually battered, and murdered\\n\\nMichelle Denise Simms. Id. The State of Florida agreed that it would not seek the\\n\\ndeath penalty for the other murders Long admitted committing. Id. A full penalty\\n\\nphase proceeding before a jury was held in the case involving the crimes Long\\n\\ncommitted against Simms. Long v. State, 529 So. 2d 286, 288, 291 (Fla. 1988).\\n\\n\\n\\n\\n 2\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 3 of 18\\n\\n\\nThe jury recommended the death penalty by a vote of eleven to one. Id. at 291.\\n\\nThe trial court adopted that recommendation and sentenced Long to death. Id.\\n\\n On direct appeal, the Florida Supreme Court affirmed Long’s convictions\\n\\nand sentences except for the death sentence. Id. at 291–93. It concluded that\\n\\nbecause the trial judge had found that one of Long’s prior convictions qualified as\\n\\nan aggravating factor, and that prior conviction had since been reversed and\\n\\nvacated by an appellate court as a result of a Miranda violation, Long was entitled\\n\\nto a new sentencing proceeding. Id. at 293. A resentencing trial was conducted\\n\\nbefore a new jury and in a new venue. See Long, 610 So. 2d at 1270. The jury\\n\\nrecommended death, this time unanimously. Id. at 1272. The trial court adopted\\n\\nthat recommendation and imposed the death penalty. Id. The Florida Supreme\\n\\nCourt affirmed, id. at 1275, and the United States Supreme Court denied Long’s\\n\\npetition for a writ of certiorari, Long v. Florida, 510 U.S. 832 (1993), making his\\n\\nconvictions and sentences final in 1993.\\n\\n Following the conclusion of his direct appeals, Long unsuccessfully sought\\n\\npostconviction relief in state court three times. See Long v. State, 235 So. 3d 293\\n\\n(Fla. 2018); Long v. State, 183 So. 3d 342 (Fla. 2016); Long v. State, 118 So. 3d\\n\\n798 (Fla. 2013). Long also filed a federal habeas petition in the district court in\\n\\n2013. The district court denied that petition on the merits, and this Court denied\\n\\nLong’s application for a certificate of appealability. See Long v. Sec’y, Fla. Dep’t\\n\\n\\n\\n 3\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 4 of 18\\n\\n\\nof Corr., No. 16-16259 (11th Cir. Jan. 4, 2017); Long v. Sec’y, Dep’t of Corr., No.\\n\\n8:13-cv-02069-T-27AEP (M.D. Fla. Aug. 30, 2016).\\n\\n After all of Long’s attempts at postconviction relief had been resolved\\n\\nconclusively against him, the Florida Commission on Offender Review initiated\\n\\nstate clemency proceedings in Long’s case. The Commission conducted\\n\\nproceedings and took the matter under submission in September 2018. After the\\n\\nCommission reported to the Governor, he denied clemency. Long was notified of\\n\\nthat decision in April 2019.\\n\\n The Governor signed Long’s death warrant on April 23, 2019, and the\\n\\nWarden set the execution date for May 23, 2019. Since then, Long has filed in the\\n\\nFlorida courts a flurry of motions, including two motions for a stay of execution, a\\n\\nmotion to dismiss his death warrant as defective, and a motion for postconviction\\n\\nrelief (the fourth one he had filed). He also filed a petition for habeas corpus in the\\n\\nFlorida Supreme Court. All of his motions and petitions have been denied.\\n\\n On May 8, 2019, Long filed in the United States District Court for the\\n\\nNorthern District of Florida a § 1983 complaint. In that complaint, he claims that\\n\\nthe State of Florida violated his federal statutory right to counsel by declining to\\n\\nallow his federally-appointed attorneys to appear at his interview in the state\\n\\nclemency proceedings and that the state-appointed attorney who was present and\\n\\nrepresented him at that interview rendered ineffective assistance of counsel in\\n\\n\\n\\n 4\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 5 of 18\\n\\n\\nviolation of the Sixth Amendment. Along with that § 1983 complaint, Long filed\\n\\nan emergency motion for a stay of execution. The district court denied that motion\\n\\non May 16, 2019. On May 20, 2019, Long filed a motion for reconsideration in\\n\\nthe district court, which it denied on May 21, 2019.\\n\\n In his complaint in this § 1983 proceeding, Long raises five claims. First, he\\n\\nclaims that Florida’s use of a three-drug protocol instead of a one-drug protocol\\n\\nviolates the Eighth Amendment. Second, he claims that Florida’s use of etomidate\\n\\nas the first drug in that three-drug protocol is facially unconstitutional because it\\n\\ncreates a risk of severe pain that is substantial when compared to the known and\\n\\navailable alternative of using the single drug pentobarbital. Third, he claims that\\n\\neven if the use of etomidate does not amount to cruel and unusual punishment in\\n\\nall cases, it does in his case because of his serious medical conditions (traumatic\\n\\nbrain injury and temporal lobe epilepsy).\\n\\n Fourth, he claims that the State violated his First, Fifth, Eighth, and\\n\\nFourteenth Amendment rights by objecting to his requests for public records and\\n\\nrefusing to answer his questions about the lethal injection protocol. And finally,\\n\\nLong claims that the Warden violated his First, Sixth, Eighth, and Fourteenth\\n\\nAmendment rights by refusing his requests to: (1) have an additional attorney\\n\\nwitness at his execution in lieu of a spiritual adviser, (2) permit Long’s attorneys to\\n\\nhave access to a phone during the execution, and (3) permit one of Long’s\\n\\n\\n 5\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 6 of 18\\n\\n\\nwitnesses to observe the insertion of the IV line that will be used to administer the\\n\\nlethal drugs.\\n\\n Along with his complaint, Long filed an emergency motion for a temporary\\n\\nrestraining order, preliminary injunction, or stay of execution. He requested that\\n\\nthe district court order the State to hold off on his execution until the court had\\n\\ntime to consider each of his claims (which, according to Long, would require\\n\\ndiscovery and an evidentiary hearing).\\n\\n The district court denied Long’s motion for a temporary restraining order,\\n\\npreliminary injunction, or stay of execution on May 19, 2019. It concluded that all\\n\\nof Long’s claims were barred by the doctrine of res judicata as a result of the\\n\\nFlorida Supreme Court’s decision in Long v. State, No. SC19-726, 2019 WL\\n\\n2150942 (Fla. May 17, 2019). For that reason, he could not show a substantial\\n\\nlikelihood of success on the merits. Long filed a notice of appeal the same day.\\n\\nOn May 20, 2019, he filed in this Court a motion for a stay of execution, or in the\\n\\nalternative, an expedited appeal. We granted his motion to expedite the appeal.\\n\\n On May 20, 2019, Long filed two petitions for a writ of certiorari in the\\n\\nUnited States Supreme Court, each accompanied by an application for a stay of\\n\\nexecution. One of those petitions seeks review of the Florida Supreme Court’s\\n\\ndenial of his state habeas petition. The other one seeks review of the Florida\\n\\nSupreme Court’s denial of his fourth motion for postconviction relief. In that one,\\n\\n\\n\\n 6\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 7 of 18\\n\\n\\nhe raises two claims that he also raised in the § 1983 lawsuit at issue in this appeal:\\n\\n(1) his claim about the Warden’s denial of his requests for exceptions to the\\n\\nDepartment of Corrections’ witness policy, and (2) his challenge to Florida’s use\\n\\nof etomidate in its lethal injection protocol.\\n\\n II. STANDARD OF REVIEW\\n\\n We review the district court’s denial of a motion for a temporary restraining\\n\\norder, preliminary injunction, or stay of execution only for abuse of discretion.\\n\\nGissendaner v. Comm’r, Ga. Dep’t of Corr., 779 F.3d 1275, 1280 (11th Cir. 2015)\\n\\n(temporary restraining order); Chavez v. Fla. SP Warden, 742 F.3d 1267, 1271\\n\\n(11th Cir. 2014) (preliminary injunction); Muhammad v. Sec’y, Fla. Dep’t of\\n\\nCorr., 739 F.3d 683, 688 (11th Cir. 2014) (stay of execution). A district court\\n\\nabuses its discretion if, among other things, “it applies an incorrect legal standard,\\n\\nfollows improper procedures in making the determination, or makes findings of\\n\\nfact that are clearly erroneous.” Grayson v. Warden, Comm’r, Ala. DOC, 869 F.3d\\n\\n1204, 1238 (11th Cir. 2017) (quotation marks omitted).\\n\\n A federal court may grant a temporary restraining order, preliminary\\n\\ninjunction, or a stay of execution only if the movant establishes that (1) he has a\\n\\nsubstantial likelihood of success on the merits, (2) he will suffer irreparable injury\\n\\nunless the injunction issues, (3) the injunction would not substantially harm the\\n\\nother litigant, and (4) if issued, the injunction would not be adverse to the public\\n\\n\\n\\n 7\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 8 of 18\\n\\n\\ninterest. Powell v. Thomas, 641 F.3d 1255, 1257 (11th Cir. 2011); see also\\n\\nGissendaner, 779 F.3d at 1280; Chavez, 742 F.3d at 1271.\\n\\n III. DISCUSSION\\n\\n A. Long’s Method of Execution Claims\\n\\n The district court did not abuse its discretion in declining to stay Long’s\\n\\nexecution on account of his three method of execution claims. Each of them is\\n\\nbarred for two independently adequate reasons. First, Long engaged in\\n\\ninexcusable delay in bringing the claims, which is enough to deny him the\\n\\nequitable remedy of a stay. And second, as the district court properly held, each of\\n\\nhis claims is barred by the doctrine of res judicata.\\n\\n 1. Inexcusable Delay\\n\\n Long is not entitled to a stay of execution “as a matter of course” simply\\n\\nbecause he brought a § 1983 claim. Hill v. McDonough, 547 U.S. 573, 583–84\\n\\n(2006). Instead, a stay of execution is an equitable remedy and all of the rules of\\n\\nequity apply. See Rutherford v. Crosby, 438 F.3d 1087, 1092 (11th Cir. 2006)\\n\\n(explaining that “where petitioner’s scheduled execution is imminent, there is no\\n\\npractical difference between denying a stay on equitable grounds and denying\\n\\ninjunctive relief on equitable grounds in a § 1983 lawsuit”), vacated on other\\n\\ngrounds, Rutherford v. McDonough, 547 U.S. 1204 (2006).\\n\\n\\n\\n\\n 8\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 9 of 18\\n\\n\\n One of those rules is that “[e]quity must take into consideration the State’s\\n\\nstrong interest in proceeding with its judgment” and an inmate’s “attempt at\\n\\nmanipulation.” Gomez v. U.S. Dist. Ct. for N. Dist. of Cal., 503 U.S. 653, 654\\n\\n(1992) (per curiam). As a result, before granting a stay of execution, a court must\\n\\n“consider not only the likelihood of success on the merits and the relative harms to\\n\\nthe parties, but also the extent to which the inmate has delayed unnecessarily in\\n\\nbringing the claim.” Nelson v. Campbell, 541 U.S. 637, 649–50 (2004). There is a\\n\\n“strong equitable presumption against the grant of a stay where a claim could have\\n\\nbeen brought at such a time as to allow consideration of the merits without\\n\\nrequiring entry of a stay.” Id. at 650.\\n\\n The Supreme Court has reiterated the importance of these principles three\\n\\ntimes this year. The first time was in February when a stay entered by this Court\\n\\nwas vacated by the Supreme Court. Dunn v. Ray, 139 S. Ct. 661 (2019). In\\n\\nvacating the stay, the Court quoted from Gomez: “A court may consider the last-\\n\\nminute nature of an application to stay execution in deciding whether to grant\\n\\nequitable relief.” Id. at 661 (quoting Gomez, 503 U.S. at 654).\\n\\n And then in April, when affirming the Eighth Circuit’s denial of an inmate’s\\n\\nas-applied challenge to the State’s method of execution, the Supreme Court\\n\\nexplicitly instructed lower courts that: “Courts should police carefully against\\n\\nattempts to use such challenges as tools to interpose unjustified delay. Last-minute\\n\\n\\n\\n 9\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 10 of 18\\n\\n\\nstays should be the extreme exception, not the norm, and the last-minute nature of\\n\\nan application that could have been brought earlier, or an applicant’s attempt at\\n\\nmanipulation, may be grounds for denial of a stay.” Bucklew v. Precythe, 139 S.\\n\\nCt. 1112, 1134 (2019) (quotation marks omitted).\\n\\n And later that same month, the Supreme Court vacated another stay of\\n\\nexecution that this Court had issued. Its decision to vacate the stay was based on\\n\\nthe fact that the inmate had delayed bringing his challenge to the State’s lethal\\n\\ninjection protocol until about two months before his scheduled execution, and then\\n\\nwaited until just a few hours before that execution to submit additional evidence.\\n\\nDunn v. Price, 139 S. Ct. 1312, 1312 (2019). The Supreme Court again relied on\\n\\nGomez to instruct courts to consider the last-minute nature of a stay in determining\\n\\nwhether equitable relief is appropriate. Id.\\n\\n Long’s case is not one of the “extreme exception[s]” in which a last-minute\\n\\nstay should be entered, but instead is within “the norm” where the “strong\\n\\nequitable presumption against the grant of a stay” applies. Bucklew, 139 S. Ct. at\\n\\n1134; Hill, 547 U.S. at 584 (quotation marks omitted).\\n\\n The first of Long’s method of execution claims is that Florida’s use of a\\n\\nthree-drug protocol instead of a one-drug protocol violates the Eighth Amendment.\\n\\nBut Florida has used a three-drug protocol since January 14, 2000, when it added\\n\\nlethal injection as a new method of execution. See Heynard v. Sec’y, DOC, 543\\n\\n\\n\\n 10\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 11 of 18\\n\\n\\nF.3d 644, 647 (11th Cir. 2014). Long has had nineteen years to challenge the use\\n\\nof a three-drug protocol. Nineteen years is too long to wait.\\n\\n To the extent that Long argues that a challenge to three-drug protocols\\n\\nwould not have been valid until now because other states have only recently begun\\n\\nusing one-drug protocols, that argument is belied by allegations in his own\\n\\ncomplaint. It alleges that at least four other states have “used a single-drug method\\n\\nfor executions since 2009.” Ten years is too long to wait.\\n\\n Long’s other two method of execution claims also suffer from his delay in\\n\\nbringing them. In those claims, he contends that Florida’s use of etomidate as the\\n\\nfirst drug in its three-drug protocol is unconstitutional regardless of the health of\\n\\nthe inmate, and that it is especially so as applied to him because of his serious\\n\\nmedical conditions.\\n\\n Florida adopted etomidate as the first drug in its three-drug protocol in\\n\\nJanuary of 2017, two years and four months ago. But Long waited until a week\\n\\nago to file this § 1983 challenge to it. Long alleges in his complaint that three of\\n\\nFlorida’s recent executions using etomidate show that the drug causes inmates\\n\\nsevere pain because it does not properly anesthetize them. To the extent that Long\\n\\nargues (and it is not clear that he does) that the delay in bringing his claims was\\n\\nbased on facts arising from those executions, his argument is not persuasive. The\\n\\nfirst of the three executions occurred on November 8, 2017, the second on\\n\\n\\n\\n 11\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 12 of 18\\n\\n\\nFebruary 22, 2018, and the last of them on December 13, 2018. A delay of five\\n\\nmonths, fifteen months, or eighteen months is too long.\\n\\n Long’s person-specific claim is that his medical conditions will complicate\\n\\nFlorida’s use of etomidate and may cause him unnecessary pain. But Long has\\n\\nknown about his medical conditions for decades. During his 1989 resentencing\\n\\ntrial, he presented as mitigating evidence the testimony of two medical experts\\n\\nabout his traumatic brain injury and temporal lobe epilepsy. See Long, 610 So. 2d\\n\\nat 1271–72. Any argument about how etomidate would be uniquely harmful to\\n\\nhim could have been raised as soon as Florida adopted etomidate as the first drug\\n\\nin its three-drug protocol. That happened in January 2017, two years and four\\n\\nmonths before Long brought this lawsuit.\\n\\n If Long had truly intended to challenge Florida’s lethal injection protocol\\n\\ninstead of just seeking to delay his execution, he would not have deliberately\\n\\nwaited to file this lawsuit until a decision on the merits would require entry of a\\n\\nstay. We have refused to grant stays in cases involving delayed filings before, and\\n\\nLong’s delay was even more pronounced and less justifiable. See e.g., Brooks v.\\n\\nWarden, 810 F.3d 812, 826 (11th Cir. 2016) (holding that an inmate was not\\n\\nentitled to a stay where he delayed filing his § 1983 challenge until eleven weeks\\n\\nbefore his execution); In re Hutcherson, 468 F.3d 747, 749–50 (11th Cir. 2006)\\n\\n(denying prisoner’s motion to stay his execution pending this Court’s resolution of\\n\\n\\n\\n 12\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 13 of 18\\n\\n\\nhis application for leave to file a successive petition because he waited until eight\\n\\ndays before his scheduled execution to file it and, as a result, his “need for a stay of\\n\\nexecution [was] directly attributable to his own failure to bring his claims to court\\n\\nin a timely fashion”); Diaz v. McDonough, 472 F.3d 849, 851 (11th Cir. 2006)\\n\\n(declining to grant a preliminary injunction so that an inmate could pursue an\\n\\nappeal because he filed his § 1983 complaint less than three days before his\\n\\nscheduled execution); cf. Jones v. Allen, 485 F.3d 635, 640 (11th Cir. 2007)\\n\\n(holding that inmate was not entitled to a stay of execution because he waited four\\n\\nyears after learning that the state intended to execute him by lethal injection to file\\n\\nhis § 1983 challenge).\\n\\n 2. Res Judicata\\n\\n Even if Long’s method of execution claims were not barred on equitable\\n\\ngrounds, the district court properly concluded that he could not show a likelihood\\n\\nof success on the merits because the claims are barred by the doctrine of res\\n\\njudicata. All of the claims Long raises in this § 1983 action were raised, or could\\n\\nhave been raised, in his fourth motion for postconviction relief, which the Florida\\n\\nSupreme Court rejected. See Long, 2019 WL 2150942, at *6–7.\\n\\n To the district court’s concise and correct discussion, we add one point,\\n\\nwhich responds to Long’s argument that applying the doctrine of res judicata\\n\\nwould work a manifest injustice in his case. He claims that because the state\\n\\n\\n\\n 13\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 14 of 18\\n\\n\\ncourts did not give him a hearing on the merits of his general challenge, and\\n\\nbecause the hearing that they did give him on his person-specific challenge was\\n\\n“severely restricted” due to the “extraordinarily constrained timeline” for the\\n\\nlitigation of his fourth postconviction motion, it would be unjust to give the Florida\\n\\nSupreme Court’s decision preclusive effect.\\n\\n There are three big problems with this argument. First, his position is\\n\\nunprecedented. Long has not pointed to a single published decision of the Florida\\n\\ncourts or this Court applying Florida law holding that it is a “manifest injustice” to\\n\\napply res judicata if the initial state court decision resolved a claim without\\n\\ngranting an evidentiary hearing. 1\\n\\n The second problem with Long’s position is that the “extraordinarily\\n\\nconstrained timeline” that he complains of is a direct result of his delay in filing his\\n\\nmethod of execution claims in state postconviction proceedings until after his\\n\\nexecution date had been set. As we have discussed, there is no reason why Long\\n\\ncould not have challenged Florida’s use of a three-drug protocol as early as 2000\\n\\n\\n\\n 1\\n The inapplicability of the precedent that Long cites and the unpersuasiveness of the\\narguments that he makes are illustrated by the following sentence and citation from his brief:\\n“This Court has declined to apply res judicata where an inmate was not given an evidentiary\\nhearing on his challenge in state court. See Chavez v. Sec’y, 742 F.3d 1267 (11th Cir. 2014).”\\nThat citation is disingenuous. The entire discussion of res judicata in the Chavez opinion\\nconsists of the following footnote: “In light of our conclusion that Chavez has not established a\\nsubstantial likelihood of success on the merits of any of his claims, we do not address and imply\\nno view about the State’s asserted defenses based on the statute of limitations, exhaustion of\\nadministrative remedies, and res judicata.” Chavez, 742 F.3d at 1273 n.5.\\n\\n\\n 14\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 15 of 18\\n\\n\\n(when Florida adopted lethal injection as a method of execution) or at least by\\n\\n2009 (when, according to the allegations in his complaint, a number of states had\\n\\nswitched to a one-drug protocol). And there is no reason why Long could not have\\n\\nchallenged Florida’s use of etomidate, both in general and specifically as to him,\\n\\nin January 2017, when the Florida Department of Corrections decided to use it as\\n\\nthe first drug in the three-drug protocol. It is worse than ironic for Long to argue\\n\\nthat the state court’s decision does not deserve res judicata effect because the state\\n\\ncourt had to render that decision under the time constraints that Long forced on it.\\n\\n There is another fundamental problem with Long’s arguments against the\\n\\napplication of res judicata. Reduced to its essence, his position is that the res\\n\\njudicata doctrine applies only if the court in which it is asserted agrees with the\\n\\ninitial court’s decision on de novo consideration. And, he says, we shouldn’t agree\\n\\nwith the decision of the Florida courts on these claims for a number of reasons.\\n\\nBut that is not the way that res judicata works. If it did, the doctrine would be\\n\\ntoothless, pointless, and fruitless. It would apply only when it made no difference.\\n\\nThe Florida courts have never suggested such a rule-devouring exception, and we\\n\\nwill not presume to create one for them here. See Kremer v. Chem. Constr. Corp.,\\n\\n456 U.S. 461, 481–82 (1982) (“It has long been established that [28 U.S.C.] § 1738\\n\\ndoes not allow federal courts to employ their own rules of res judicata in\\n\\ndetermining the effect of state judgments. Rather, it goes beyond the common law\\n\\n\\n\\n 15\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 16 of 18\\n\\n\\nand commands a federal court to accept the rules chosen by the State from which\\n\\nthe judgment is taken.”).\\n\\n B. Long’s Public Records and Witness Claims\\n\\n In addition to his three method of execution claims, Long contends that the\\n\\ndefendants violated his constitutional rights by (1) objecting to some of his public\\n\\nrecords requests and refusing to answer some of his questions about the lethal\\n\\ninjection protocol, and (2) denying his requests for exceptions to the Department of\\n\\nCorrections’ witness policies. As the district court already held, both of those\\n\\nclaims are also barred by the doctrine of res judicata. Long raised a public records\\n\\nclaim in the Florida courts, see Long, 2019 WL 2150942, at *6–7, and he could\\n\\nhave asserted any similar claims in the state court proceedings.\\n\\n There are many published decisions that support the district court’s ruling\\n\\nthat, under Florida law, res judicata bars claims that Long could have raised in the\\n\\nstate postconviction proceedings but didn’t. See, e.g., Topps v. State, 865 So. 2d\\n\\n1253, 1255 (Fla. 2004) (“The doctrine of res judicata bars relitigation in a\\n\\nsubsequent cause of action not only of claims raised, but also claims that could\\n\\nhave been raised.”); Fla. Dep’t of Transp. v. Juliano, 801 So. 2d 101, 105 (Fla.\\n\\n2001) (“Importantly, the doctrine of res judicata not only bars issues that were\\n\\nraised, but it also precludes consideration of issues that could have been raised but\\n\\nwere not raised in the first case.”); see also Vasquez v. YII Shipping Co., 692 F.3d\\n\\n\\n\\n 16\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 17 of 18\\n\\n\\n1192, 1199 (11th Cir. 2012) (applying Florida law to explain that “the purpose of\\n\\nres judicata is that a final judgment in a court of competent jurisdiction is absolute\\n\\nand settles all issues actually litigated in a proceeding as well as those issues that\\n\\ncould have been litigated.”) (quotation marks omitted). The district court was\\n\\nentirely correct in concluding that Long’s public records and witness claims are\\n\\nbarred by res judicata.\\n\\n IV. CONCLUSION\\n\\n We AFFIRM the district court’s denial of Long’s emergency motion for a\\n\\ntemporary restraining order, preliminary injunction, or stay of execution. We\\n\\nDENY Long’s motion for a stay of execution from this Court.\\n\\n\\n\\n\\n 17\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 18 of 18\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4399766/\", \"author_raw\": \"ED CARNES, Chief Judge\"}, {\"author\": \"JORDAN, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"JORDAN, Circuit Judge, concurring.\\n\\n The district court denied Mr. Long’s claims on res judicata grounds based on\\n\\nthe Florida Supreme Court’s decision in Long v. State, 2019 WL 2150942 (Fla. May\\n\\n17, 2019). I agree with the majority that the district court properly applied the\\n\\ndoctrine of res judicata, and therefore join Parts I, II, III.A.2, and III.B of its opinion.\\n\\nBecause our affirmance of the district court’s res judicata ruling conclusively\\n\\nresolves Mr. Long’s claims and requests for relief here, I find it unnecessary to\\n\\naddress the issue of delay.\\n\\n\\n\\n\\n 18\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4399766/\", \"author_raw\": \"JORDAN, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"ED CARNES"},"judge2":{"kind":"string","value":"MARCUS"},"judge3":{"kind":"string","value":"JORDAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"ED CARNES\": \", Chief\", \"MARCUS\": \", Circuit\", \"JORDAN\": \", Circuit\"}"},"opinions_count":{"kind":"number","value":2,"string":"2"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4622513/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Bobby Joe Long v. Secretary, Department of Corrections\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-22\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nCase: 19-11942 Date Filed: 05/22/2019 Page: 1 of 18\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 19-11942\n ________________________\n\n D.C. Docket No. 8:19-cv-01193-MSS-AEP\n\n\n\nBOBBY JOE LONG,\n\n Plaintiff-Appellant,\n\n versus\n\nSECRETARY, DEPARTMENT OF CORRECTIONS, WARDEN, FLORIDA\nSTATE PRISON, JOHN DOES, as designee of Barry Reddish, and/or Mark S.\nInch,\n\n Defendants-Appellees.\n\n ________________________\n\n Appeal from the United States District Court\n for the Middle District of Florida\n ________________________\n\n (May 22, 2019)\n\nBefore ED CARNES, Chief Judge, MARCUS, and JORDAN, Circuit Judges.\n\nED CARNES, Chief Judge:\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 2 of 18\n\n\n Bobby Joe Long kidnapped, sexually battered, and murdered Michelle\n\nDenise Simms. And at least seven more women. He brutalized others. After\n\npleading guilty, he was convicted and sentenced to death for the Simms murder.\n\nThat was more than 32 years ago. After his sentence was vacated and the case\n\nremanded, he was resentenced to death. That was more than 30 years ago.\n\n Seven days before Long is scheduled to be executed, he filed a 42 U.S.C.\n\n§ 1983 complaint in the United States District Court for the Middle District of\n\nFlorida. He also filed an emergency motion for a temporary restraining order,\n\npreliminary injunction, or stay of execution to prevent the State of Florida from\n\nexecuting him on May 23, 2019.\n\n I. PROCEDURAL HISTORY\n\n In September 1985, Long pleaded guilty to eight counts of first-degree\n\nmurder, nine counts of kidnapping, eight counts of sexual battery, and one\n\nprobation violation. Long v. State, 610 So. 2d 1268, 1269 (Fla. 1992). That plea\n\nincluded his admission that he kidnapped, sexually battered, and murdered\n\nMichelle Denise Simms. Id. The State of Florida agreed that it would not seek the\n\ndeath penalty for the other murders Long admitted committing. Id. A full penalty\n\nphase proceeding before a jury was held in the case involving the crimes Long\n\ncommitted against Simms. Long v. State, 529 So. 2d 286, 288, 291 (Fla. 1988).\n\n\n\n\n 2\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 3 of 18\n\n\nThe jury recommended the death penalty by a vote of eleven to one. Id. at 291.\n\nThe trial court adopted that recommendation and sentenced Long to death. Id.\n\n On direct appeal, the Florida Supreme Court affirmed Long’s convictions\n\nand sentences except for the death sentence. Id. at 291–93. It concluded that\n\nbecause the trial judge had found that one of Long’s prior convictions qualified as\n\nan aggravating factor, and that prior conviction had since been reversed and\n\nvacated by an appellate court as a result of a Miranda violation, Long was entitled\n\nto a new sentencing proceeding. Id. at 293. A resentencing trial was conducted\n\nbefore a new jury and in a new venue. See Long, 610 So. 2d at 1270. The jury\n\nrecommended death, this time unanimously. Id. at 1272. The trial court adopted\n\nthat recommendation and imposed the death penalty. Id. The Florida Supreme\n\nCourt affirmed, id. at 1275, and the United States Supreme Court denied Long’s\n\npetition for a writ of certiorari, Long v. Florida, 510 U.S. 832 (1993), making his\n\nconvictions and sentences final in 1993.\n\n Following the conclusion of his direct appeals, Long unsuccessfully sought\n\npostconviction relief in state court three times. See Long v. State, 235 So. 3d 293\n\n(Fla. 2018); Long v. State, 183 So. 3d 342 (Fla. 2016); Long v. State, 118 So. 3d\n\n798 (Fla. 2013). Long also filed a federal habeas petition in the district court in\n\n2013. The district court denied that petition on the merits, and this Court denied\n\nLong’s application for a certificate of appealability. See Long v. Sec’y, Fla. Dep’t\n\n\n\n 3\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 4 of 18\n\n\nof Corr., No. 16-16259 (11th Cir. Jan. 4, 2017); Long v. Sec’y, Dep’t of Corr., No.\n\n8:13-cv-02069-T-27AEP (M.D. Fla. Aug. 30, 2016).\n\n After all of Long’s attempts at postconviction relief had been resolved\n\nconclusively against him, the Florida Commission on Offender Review initiated\n\nstate clemency proceedings in Long’s case. The Commission conducted\n\nproceedings and took the matter under submission in September 2018. After the\n\nCommission reported to the Governor, he denied clemency. Long was notified of\n\nthat decision in April 2019.\n\n The Governor signed Long’s death warrant on April 23, 2019, and the\n\nWarden set the execution date for May 23, 2019. Since then, Long has filed in the\n\nFlorida courts a flurry of motions, including two motions for a stay of execution, a\n\nmotion to dismiss his death warrant as defective, and a motion for postconviction\n\nrelief (the fourth one he had filed). He also filed a petition for habeas corpus in the\n\nFlorida Supreme Court. All of his motions and petitions have been denied.\n\n On May 8, 2019, Long filed in the United States District Court for the\n\nNorthern District of Florida a § 1983 complaint. In that complaint, he claims that\n\nthe State of Florida violated his federal statutory right to counsel by declining to\n\nallow his federally-appointed attorneys to appear at his interview in the state\n\nclemency proceedings and that the state-appointed attorney who was present and\n\nrepresented him at that interview rendered ineffective assistance of counsel in\n\n\n\n 4\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 5 of 18\n\n\nviolation of the Sixth Amendment. Along with that § 1983 complaint, Long filed\n\nan emergency motion for a stay of execution. The district court denied that motion\n\non May 16, 2019. On May 20, 2019, Long filed a motion for reconsideration in\n\nthe district court, which it denied on May 21, 2019.\n\n In his complaint in this § 1983 proceeding, Long raises five claims. First, he\n\nclaims that Florida’s use of a three-drug protocol instead of a one-drug protocol\n\nviolates the Eighth Amendment. Second, he claims that Florida’s use of etomidate\n\nas the first drug in that three-drug protocol is facially unconstitutional because it\n\ncreates a risk of severe pain that is substantial when compared to the known and\n\navailable alternative of using the single drug pentobarbital. Third, he claims that\n\neven if the use of etomidate does not amount to cruel and unusual punishment in\n\nall cases, it does in his case because of his serious medical conditions (traumatic\n\nbrain injury and temporal lobe epilepsy).\n\n Fourth, he claims that the State violated his First, Fifth, Eighth, and\n\nFourteenth Amendment rights by objecting to his requests for public records and\n\nrefusing to answer his questions about the lethal injection protocol. And finally,\n\nLong claims that the Warden violated his First, Sixth, Eighth, and Fourteenth\n\nAmendment rights by refusing his requests to: (1) have an additional attorney\n\nwitness at his execution in lieu of a spiritual adviser, (2) permit Long’s attorneys to\n\nhave access to a phone during the execution, and (3) permit one of Long’s\n\n\n 5\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 6 of 18\n\n\nwitnesses to observe the insertion of the IV line that will be used to administer the\n\nlethal drugs.\n\n Along with his complaint, Long filed an emergency motion for a temporary\n\nrestraining order, preliminary injunction, or stay of execution. He requested that\n\nthe district court order the State to hold off on his execution until the court had\n\ntime to consider each of his claims (which, according to Long, would require\n\ndiscovery and an evidentiary hearing).\n\n The district court denied Long’s motion for a temporary restraining order,\n\npreliminary injunction, or stay of execution on May 19, 2019. It concluded that all\n\nof Long’s claims were barred by the doctrine of res judicata as a result of the\n\nFlorida Supreme Court’s decision in Long v. State, No. SC19-726, 2019 WL\n\n2150942 (Fla. May 17, 2019). For that reason, he could not show a substantial\n\nlikelihood of success on the merits. Long filed a notice of appeal the same day.\n\nOn May 20, 2019, he filed in this Court a motion for a stay of execution, or in the\n\nalternative, an expedited appeal. We granted his motion to expedite the appeal.\n\n On May 20, 2019, Long filed two petitions for a writ of certiorari in the\n\nUnited States Supreme Court, each accompanied by an application for a stay of\n\nexecution. One of those petitions seeks review of the Florida Supreme Court’s\n\ndenial of his state habeas petition. The other one seeks review of the Florida\n\nSupreme Court’s denial of his fourth motion for postconviction relief. In that one,\n\n\n\n 6\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 7 of 18\n\n\nhe raises two claims that he also raised in the § 1983 lawsuit at issue in this appeal:\n\n(1) his claim about the Warden’s denial of his requests for exceptions to the\n\nDepartment of Corrections’ witness policy, and (2) his challenge to Florida’s use\n\nof etomidate in its lethal injection protocol.\n\n II. STANDARD OF REVIEW\n\n We review the district court’s denial of a motion for a temporary restraining\n\norder, preliminary injunction, or stay of execution only for abuse of discretion.\n\nGissendaner v. Comm’r, Ga. Dep’t of Corr., 779 F.3d 1275, 1280 (11th Cir. 2015)\n\n(temporary restraining order); Chavez v. Fla. SP Warden, 742 F.3d 1267, 1271\n\n(11th Cir. 2014) (preliminary injunction); Muhammad v. Sec’y, Fla. Dep’t of\n\nCorr., 739 F.3d 683, 688 (11th Cir. 2014) (stay of execution). A district court\n\nabuses its discretion if, among other things, “it applies an incorrect legal standard,\n\nfollows improper procedures in making the determination, or makes findings of\n\nfact that are clearly erroneous.” Grayson v. Warden, Comm’r, Ala. DOC, 869 F.3d\n\n1204, 1238 (11th Cir. 2017) (quotation marks omitted).\n\n A federal court may grant a temporary restraining order, preliminary\n\ninjunction, or a stay of execution only if the movant establishes that (1) he has a\n\nsubstantial likelihood of success on the merits, (2) he will suffer irreparable injury\n\nunless the injunction issues, (3) the injunction would not substantially harm the\n\nother litigant, and (4) if issued, the injunction would not be adverse to the public\n\n\n\n 7\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 8 of 18\n\n\ninterest. Powell v. Thomas, 641 F.3d 1255, 1257 (11th Cir. 2011); see also\n\nGissendaner, 779 F.3d at 1280; Chavez, 742 F.3d at 1271.\n\n III. DISCUSSION\n\n A. Long’s Method of Execution Claims\n\n The district court did not abuse its discretion in declining to stay Long’s\n\nexecution on account of his three method of execution claims. Each of them is\n\nbarred for two independently adequate reasons. First, Long engaged in\n\ninexcusable delay in bringing the claims, which is enough to deny him the\n\nequitable remedy of a stay. And second, as the district court properly held, each of\n\nhis claims is barred by the doctrine of res judicata.\n\n 1. Inexcusable Delay\n\n Long is not entitled to a stay of execution “as a matter of course” simply\n\nbecause he brought a § 1983 claim. Hill v. McDonough, 547 U.S. 573, 583–84\n\n(2006). Instead, a stay of execution is an equitable remedy and all of the rules of\n\nequity apply. See Rutherford v. Crosby, 438 F.3d 1087, 1092 (11th Cir. 2006)\n\n(explaining that “where petitioner’s scheduled execution is imminent, there is no\n\npractical difference between denying a stay on equitable grounds and denying\n\ninjunctive relief on equitable grounds in a § 1983 lawsuit”), vacated on other\n\ngrounds, Rutherford v. McDonough, 547 U.S. 1204 (2006).\n\n\n\n\n 8\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 9 of 18\n\n\n One of those rules is that “[e]quity must take into consideration the State’s\n\nstrong interest in proceeding with its judgment” and an inmate’s “attempt at\n\nmanipulation.” Gomez v. U.S. Dist. Ct. for N. Dist. of Cal., 503 U.S. 653, 654\n\n(1992) (per curiam). As a result, before granting a stay of execution, a court must\n\n“consider not only the likelihood of success on the merits and the relative harms to\n\nthe parties, but also the extent to which the inmate has delayed unnecessarily in\n\nbringing the claim.” Nelson v. Campbell, 541 U.S. 637, 649–50 (2004). There is a\n\n“strong equitable presumption against the grant of a stay where a claim could have\n\nbeen brought at such a time as to allow consideration of the merits without\n\nrequiring entry of a stay.” Id. at 650.\n\n The Supreme Court has reiterated the importance of these principles three\n\ntimes this year. The first time was in February when a stay entered by this Court\n\nwas vacated by the Supreme Court. Dunn v. Ray, 139 S. Ct. 661 (2019). In\n\nvacating the stay, the Court quoted from Gomez: “A court may consider the last-\n\nminute nature of an application to stay execution in deciding whether to grant\n\nequitable relief.” Id. at 661 (quoting Gomez, 503 U.S. at 654).\n\n And then in April, when affirming the Eighth Circuit’s denial of an inmate’s\n\nas-applied challenge to the State’s method of execution, the Supreme Court\n\nexplicitly instructed lower courts that: “Courts should police carefully against\n\nattempts to use such challenges as tools to interpose unjustified delay. Last-minute\n\n\n\n 9\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 10 of 18\n\n\nstays should be the extreme exception, not the norm, and the last-minute nature of\n\nan application that could have been brought earlier, or an applicant’s attempt at\n\nmanipulation, may be grounds for denial of a stay.” Bucklew v. Precythe, 139 S.\n\nCt. 1112, 1134 (2019) (quotation marks omitted).\n\n And later that same month, the Supreme Court vacated another stay of\n\nexecution that this Court had issued. Its decision to vacate the stay was based on\n\nthe fact that the inmate had delayed bringing his challenge to the State’s lethal\n\ninjection protocol until about two months before his scheduled execution, and then\n\nwaited until just a few hours before that execution to submit additional evidence.\n\nDunn v. Price, 139 S. Ct. 1312, 1312 (2019). The Supreme Court again relied on\n\nGomez to instruct courts to consider the last-minute nature of a stay in determining\n\nwhether equitable relief is appropriate. Id.\n\n Long’s case is not one of the “extreme exception[s]” in which a last-minute\n\nstay should be entered, but instead is within “the norm” where the “strong\n\nequitable presumption against the grant of a stay” applies. Bucklew, 139 S. Ct. at\n\n1134; Hill, 547 U.S. at 584 (quotation marks omitted).\n\n The first of Long’s method of execution claims is that Florida’s use of a\n\nthree-drug protocol instead of a one-drug protocol violates the Eighth Amendment.\n\nBut Florida has used a three-drug protocol since January 14, 2000, when it added\n\nlethal injection as a new method of execution. See Heynard v. Sec’y, DOC, 543\n\n\n\n 10\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 11 of 18\n\n\nF.3d 644, 647 (11th Cir. 2014). Long has had nineteen years to challenge the use\n\nof a three-drug protocol. Nineteen years is too long to wait.\n\n To the extent that Long argues that a challenge to three-drug protocols\n\nwould not have been valid until now because other states have only recently begun\n\nusing one-drug protocols, that argument is belied by allegations in his own\n\ncomplaint. It alleges that at least four other states have “used a single-drug method\n\nfor executions since 2009.” Ten years is too long to wait.\n\n Long’s other two method of execution claims also suffer from his delay in\n\nbringing them. In those claims, he contends that Florida’s use of etomidate as the\n\nfirst drug in its three-drug protocol is unconstitutional regardless of the health of\n\nthe inmate, and that it is especially so as applied to him because of his serious\n\nmedical conditions.\n\n Florida adopted etomidate as the first drug in its three-drug protocol in\n\nJanuary of 2017, two years and four months ago. But Long waited until a week\n\nago to file this § 1983 challenge to it. Long alleges in his complaint that three of\n\nFlorida’s recent executions using etomidate show that the drug causes inmates\n\nsevere pain because it does not properly anesthetize them. To the extent that Long\n\nargues (and it is not clear that he does) that the delay in bringing his claims was\n\nbased on facts arising from those executions, his argument is not persuasive. The\n\nfirst of the three executions occurred on November 8, 2017, the second on\n\n\n\n 11\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 12 of 18\n\n\nFebruary 22, 2018, and the last of them on December 13, 2018. A delay of five\n\nmonths, fifteen months, or eighteen months is too long.\n\n Long’s person-specific claim is that his medical conditions will complicate\n\nFlorida’s use of etomidate and may cause him unnecessary pain. But Long has\n\nknown about his medical conditions for decades. During his 1989 resentencing\n\ntrial, he presented as mitigating evidence the testimony of two medical experts\n\nabout his traumatic brain injury and temporal lobe epilepsy. See Long, 610 So. 2d\n\nat 1271–72. Any argument about how etomidate would be uniquely harmful to\n\nhim could have been raised as soon as Florida adopted etomidate as the first drug\n\nin its three-drug protocol. That happened in January 2017, two years and four\n\nmonths before Long brought this lawsuit.\n\n If Long had truly intended to challenge Florida’s lethal injection protocol\n\ninstead of just seeking to delay his execution, he would not have deliberately\n\nwaited to file this lawsuit until a decision on the merits would require entry of a\n\nstay. We have refused to grant stays in cases involving delayed filings before, and\n\nLong’s delay was even more pronounced and less justifiable. See e.g., Brooks v.\n\nWarden, 810 F.3d 812, 826 (11th Cir. 2016) (holding that an inmate was not\n\nentitled to a stay where he delayed filing his § 1983 challenge until eleven weeks\n\nbefore his execution); In re Hutcherson, 468 F.3d 747, 749–50 (11th Cir. 2006)\n\n(denying prisoner’s motion to stay his execution pending this Court’s resolution of\n\n\n\n 12\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 13 of 18\n\n\nhis application for leave to file a successive petition because he waited until eight\n\ndays before his scheduled execution to file it and, as a result, his “need for a stay of\n\nexecution [was] directly attributable to his own failure to bring his claims to court\n\nin a timely fashion”); Diaz v. McDonough, 472 F.3d 849, 851 (11th Cir. 2006)\n\n(declining to grant a preliminary injunction so that an inmate could pursue an\n\nappeal because he filed his § 1983 complaint less than three days before his\n\nscheduled execution); cf. Jones v. Allen, 485 F.3d 635, 640 (11th Cir. 2007)\n\n(holding that inmate was not entitled to a stay of execution because he waited four\n\nyears after learning that the state intended to execute him by lethal injection to file\n\nhis § 1983 challenge).\n\n 2. Res Judicata\n\n Even if Long’s method of execution claims were not barred on equitable\n\ngrounds, the district court properly concluded that he could not show a likelihood\n\nof success on the merits because the claims are barred by the doctrine of res\n\njudicata. All of the claims Long raises in this § 1983 action were raised, or could\n\nhave been raised, in his fourth motion for postconviction relief, which the Florida\n\nSupreme Court rejected. See Long, 2019 WL 2150942, at *6–7.\n\n To the district court’s concise and correct discussion, we add one point,\n\nwhich responds to Long’s argument that applying the doctrine of res judicata\n\nwould work a manifest injustice in his case. He claims that because the state\n\n\n\n 13\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 14 of 18\n\n\ncourts did not give him a hearing on the merits of his general challenge, and\n\nbecause the hearing that they did give him on his person-specific challenge was\n\n“severely restricted” due to the “extraordinarily constrained timeline” for the\n\nlitigation of his fourth postconviction motion, it would be unjust to give the Florida\n\nSupreme Court’s decision preclusive effect.\n\n There are three big problems with this argument. First, his position is\n\nunprecedented. Long has not pointed to a single published decision of the Florida\n\ncourts or this Court applying Florida law holding that it is a “manifest injustice” to\n\napply res judicata if the initial state court decision resolved a claim without\n\ngranting an evidentiary hearing. 1\n\n The second problem with Long’s position is that the “extraordinarily\n\nconstrained timeline” that he complains of is a direct result of his delay in filing his\n\nmethod of execution claims in state postconviction proceedings until after his\n\nexecution date had been set. As we have discussed, there is no reason why Long\n\ncould not have challenged Florida’s use of a three-drug protocol as early as 2000\n\n\n\n 1\n The inapplicability of the precedent that Long cites and the unpersuasiveness of the\narguments that he makes are illustrated by the following sentence and citation from his brief:\n“This Court has declined to apply res judicata where an inmate was not given an evidentiary\nhearing on his challenge in state court. See Chavez v. Sec’y, 742 F.3d 1267 (11th Cir. 2014).”\nThat citation is disingenuous. The entire discussion of res judicata in the Chavez opinion\nconsists of the following footnote: “In light of our conclusion that Chavez has not established a\nsubstantial likelihood of success on the merits of any of his claims, we do not address and imply\nno view about the State’s asserted defenses based on the statute of limitations, exhaustion of\nadministrative remedies, and res judicata.” Chavez, 742 F.3d at 1273 n.5.\n\n\n 14\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 15 of 18\n\n\n(when Florida adopted lethal injection as a method of execution) or at least by\n\n2009 (when, according to the allegations in his complaint, a number of states had\n\nswitched to a one-drug protocol). And there is no reason why Long could not have\n\nchallenged Florida’s use of etomidate, both in general and specifically as to him,\n\nin January 2017, when the Florida Department of Corrections decided to use it as\n\nthe first drug in the three-drug protocol. It is worse than ironic for Long to argue\n\nthat the state court’s decision does not deserve res judicata effect because the state\n\ncourt had to render that decision under the time constraints that Long forced on it.\n\n There is another fundamental problem with Long’s arguments against the\n\napplication of res judicata. Reduced to its essence, his position is that the res\n\njudicata doctrine applies only if the court in which it is asserted agrees with the\n\ninitial court’s decision on de novo consideration. And, he says, we shouldn’t agree\n\nwith the decision of the Florida courts on these claims for a number of reasons.\n\nBut that is not the way that res judicata works. If it did, the doctrine would be\n\ntoothless, pointless, and fruitless. It would apply only when it made no difference.\n\nThe Florida courts have never suggested such a rule-devouring exception, and we\n\nwill not presume to create one for them here. See Kremer v. Chem. Constr. Corp.,\n\n456 U.S. 461, 481–82 (1982) (“It has long been established that [28 U.S.C.] § 1738\n\ndoes not allow federal courts to employ their own rules of res judicata in\n\ndetermining the effect of state judgments. Rather, it goes beyond the common law\n\n\n\n 15\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 16 of 18\n\n\nand commands a federal court to accept the rules chosen by the State from which\n\nthe judgment is taken.”).\n\n B. Long’s Public Records and Witness Claims\n\n In addition to his three method of execution claims, Long contends that the\n\ndefendants violated his constitutional rights by (1) objecting to some of his public\n\nrecords requests and refusing to answer some of his questions about the lethal\n\ninjection protocol, and (2) denying his requests for exceptions to the Department of\n\nCorrections’ witness policies. As the district court already held, both of those\n\nclaims are also barred by the doctrine of res judicata. Long raised a public records\n\nclaim in the Florida courts, see Long, 2019 WL 2150942, at *6–7, and he could\n\nhave asserted any similar claims in the state court proceedings.\n\n There are many published decisions that support the district court’s ruling\n\nthat, under Florida law, res judicata bars claims that Long could have raised in the\n\nstate postconviction proceedings but didn’t. See, e.g., Topps v. State, 865 So. 2d\n\n1253, 1255 (Fla. 2004) (“The doctrine of res judicata bars relitigation in a\n\nsubsequent cause of action not only of claims raised, but also claims that could\n\nhave been raised.”); Fla. Dep’t of Transp. v. Juliano, 801 So. 2d 101, 105 (Fla.\n\n2001) (“Importantly, the doctrine of res judicata not only bars issues that were\n\nraised, but it also precludes consideration of issues that could have been raised but\n\nwere not raised in the first case.”); see also Vasquez v. YII Shipping Co., 692 F.3d\n\n\n\n 16\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 17 of 18\n\n\n1192, 1199 (11th Cir. 2012) (applying Florida law to explain that “the purpose of\n\nres judicata is that a final judgment in a court of competent jurisdiction is absolute\n\nand settles all issues actually litigated in a proceeding as well as those issues that\n\ncould have been litigated.”) (quotation marks omitted). The district court was\n\nentirely correct in concluding that Long’s public records and witness claims are\n\nbarred by res judicata.\n\n IV. CONCLUSION\n\n We AFFIRM the district court’s denial of Long’s emergency motion for a\n\ntemporary restraining order, preliminary injunction, or stay of execution. We\n\nDENY Long’s motion for a stay of execution from this Court.\n\n\n\n\n 17\n\n Case: 19-11942 Date Filed: 05/22/2019 Page: 18 of 18\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Bobby Joe Long v. Secretary, Department of Corrections\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-22\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 19-11942 Date Filed: 05/22/2019 Page: 1 of 18\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 19-11942\\n ________________________\\n\\n D.C. Docket No. 8:19-cv-01193-MSS-AEP\\n\\n\\n\\nBOBBY JOE LONG,\\n\\n Plaintiff-Appellant,\\n\\n versus\\n\\nSECRETARY, DEPARTMENT OF CORRECTIONS, WARDEN, FLORIDA\\nSTATE PRISON, JOHN DOES, as designee of Barry Reddish, and/or Mark S.\\nInch,\\n\\n Defendants-Appellees.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Florida\\n ________________________\\n\\n (May 22, 2019)\\n\\nBefore ED CARNES, Chief Judge, MARCUS, and JORDAN, Circuit Judges.\\n\\nED CARNES, Chief Judge:\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 2 of 18\\n\\n\\n Bobby Joe Long kidnapped, sexually battered, and murdered Michelle\\n\\nDenise Simms. And at least seven more women. He brutalized others. After\\n\\npleading guilty, he was convicted and sentenced to death for the Simms murder.\\n\\nThat was more than 32 years ago. After his sentence was vacated and the case\\n\\nremanded, he was resentenced to death. That was more than 30 years ago.\\n\\n Seven days before Long is scheduled to be executed, he filed a 42 U.S.C.\\n\\n§ 1983 complaint in the United States District Court for the Middle District of\\n\\nFlorida. He also filed an emergency motion for a temporary restraining order,\\n\\npreliminary injunction, or stay of execution to prevent the State of Florida from\\n\\nexecuting him on May 23, 2019.\\n\\n I. PROCEDURAL HISTORY\\n\\n In September 1985, Long pleaded guilty to eight counts of first-degree\\n\\nmurder, nine counts of kidnapping, eight counts of sexual battery, and one\\n\\nprobation violation. Long v. State, 610 So. 2d 1268, 1269 (Fla. 1992). That plea\\n\\nincluded his admission that he kidnapped, sexually battered, and murdered\\n\\nMichelle Denise Simms. Id. The State of Florida agreed that it would not seek the\\n\\ndeath penalty for the other murders Long admitted committing. Id. A full penalty\\n\\nphase proceeding before a jury was held in the case involving the crimes Long\\n\\ncommitted against Simms. Long v. State, 529 So. 2d 286, 288, 291 (Fla. 1988).\\n\\n\\n\\n\\n 2\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 3 of 18\\n\\n\\nThe jury recommended the death penalty by a vote of eleven to one. Id. at 291.\\n\\nThe trial court adopted that recommendation and sentenced Long to death. Id.\\n\\n On direct appeal, the Florida Supreme Court affirmed Long’s convictions\\n\\nand sentences except for the death sentence. Id. at 291–93. It concluded that\\n\\nbecause the trial judge had found that one of Long’s prior convictions qualified as\\n\\nan aggravating factor, and that prior conviction had since been reversed and\\n\\nvacated by an appellate court as a result of a Miranda violation, Long was entitled\\n\\nto a new sentencing proceeding. Id. at 293. A resentencing trial was conducted\\n\\nbefore a new jury and in a new venue. See Long, 610 So. 2d at 1270. The jury\\n\\nrecommended death, this time unanimously. Id. at 1272. The trial court adopted\\n\\nthat recommendation and imposed the death penalty. Id. The Florida Supreme\\n\\nCourt affirmed, id. at 1275, and the United States Supreme Court denied Long’s\\n\\npetition for a writ of certiorari, Long v. Florida, 510 U.S. 832 (1993), making his\\n\\nconvictions and sentences final in 1993.\\n\\n Following the conclusion of his direct appeals, Long unsuccessfully sought\\n\\npostconviction relief in state court three times. See Long v. State, 235 So. 3d 293\\n\\n(Fla. 2018); Long v. State, 183 So. 3d 342 (Fla. 2016); Long v. State, 118 So. 3d\\n\\n798 (Fla. 2013). Long also filed a federal habeas petition in the district court in\\n\\n2013. The district court denied that petition on the merits, and this Court denied\\n\\nLong’s application for a certificate of appealability. See Long v. Sec’y, Fla. Dep’t\\n\\n\\n\\n 3\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 4 of 18\\n\\n\\nof Corr., No. 16-16259 (11th Cir. Jan. 4, 2017); Long v. Sec’y, Dep’t of Corr., No.\\n\\n8:13-cv-02069-T-27AEP (M.D. Fla. Aug. 30, 2016).\\n\\n After all of Long’s attempts at postconviction relief had been resolved\\n\\nconclusively against him, the Florida Commission on Offender Review initiated\\n\\nstate clemency proceedings in Long’s case. The Commission conducted\\n\\nproceedings and took the matter under submission in September 2018. After the\\n\\nCommission reported to the Governor, he denied clemency. Long was notified of\\n\\nthat decision in April 2019.\\n\\n The Governor signed Long’s death warrant on April 23, 2019, and the\\n\\nWarden set the execution date for May 23, 2019. Since then, Long has filed in the\\n\\nFlorida courts a flurry of motions, including two motions for a stay of execution, a\\n\\nmotion to dismiss his death warrant as defective, and a motion for postconviction\\n\\nrelief (the fourth one he had filed). He also filed a petition for habeas corpus in the\\n\\nFlorida Supreme Court. All of his motions and petitions have been denied.\\n\\n On May 8, 2019, Long filed in the United States District Court for the\\n\\nNorthern District of Florida a § 1983 complaint. In that complaint, he claims that\\n\\nthe State of Florida violated his federal statutory right to counsel by declining to\\n\\nallow his federally-appointed attorneys to appear at his interview in the state\\n\\nclemency proceedings and that the state-appointed attorney who was present and\\n\\nrepresented him at that interview rendered ineffective assistance of counsel in\\n\\n\\n\\n 4\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 5 of 18\\n\\n\\nviolation of the Sixth Amendment. Along with that § 1983 complaint, Long filed\\n\\nan emergency motion for a stay of execution. The district court denied that motion\\n\\non May 16, 2019. On May 20, 2019, Long filed a motion for reconsideration in\\n\\nthe district court, which it denied on May 21, 2019.\\n\\n In his complaint in this § 1983 proceeding, Long raises five claims. First, he\\n\\nclaims that Florida’s use of a three-drug protocol instead of a one-drug protocol\\n\\nviolates the Eighth Amendment. Second, he claims that Florida’s use of etomidate\\n\\nas the first drug in that three-drug protocol is facially unconstitutional because it\\n\\ncreates a risk of severe pain that is substantial when compared to the known and\\n\\navailable alternative of using the single drug pentobarbital. Third, he claims that\\n\\neven if the use of etomidate does not amount to cruel and unusual punishment in\\n\\nall cases, it does in his case because of his serious medical conditions (traumatic\\n\\nbrain injury and temporal lobe epilepsy).\\n\\n Fourth, he claims that the State violated his First, Fifth, Eighth, and\\n\\nFourteenth Amendment rights by objecting to his requests for public records and\\n\\nrefusing to answer his questions about the lethal injection protocol. And finally,\\n\\nLong claims that the Warden violated his First, Sixth, Eighth, and Fourteenth\\n\\nAmendment rights by refusing his requests to: (1) have an additional attorney\\n\\nwitness at his execution in lieu of a spiritual adviser, (2) permit Long’s attorneys to\\n\\nhave access to a phone during the execution, and (3) permit one of Long’s\\n\\n\\n 5\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 6 of 18\\n\\n\\nwitnesses to observe the insertion of the IV line that will be used to administer the\\n\\nlethal drugs.\\n\\n Along with his complaint, Long filed an emergency motion for a temporary\\n\\nrestraining order, preliminary injunction, or stay of execution. He requested that\\n\\nthe district court order the State to hold off on his execution until the court had\\n\\ntime to consider each of his claims (which, according to Long, would require\\n\\ndiscovery and an evidentiary hearing).\\n\\n The district court denied Long’s motion for a temporary restraining order,\\n\\npreliminary injunction, or stay of execution on May 19, 2019. It concluded that all\\n\\nof Long’s claims were barred by the doctrine of res judicata as a result of the\\n\\nFlorida Supreme Court’s decision in Long v. State, No. SC19-726, 2019 WL\\n\\n2150942 (Fla. May 17, 2019). For that reason, he could not show a substantial\\n\\nlikelihood of success on the merits. Long filed a notice of appeal the same day.\\n\\nOn May 20, 2019, he filed in this Court a motion for a stay of execution, or in the\\n\\nalternative, an expedited appeal. We granted his motion to expedite the appeal.\\n\\n On May 20, 2019, Long filed two petitions for a writ of certiorari in the\\n\\nUnited States Supreme Court, each accompanied by an application for a stay of\\n\\nexecution. One of those petitions seeks review of the Florida Supreme Court’s\\n\\ndenial of his state habeas petition. The other one seeks review of the Florida\\n\\nSupreme Court’s denial of his fourth motion for postconviction relief. In that one,\\n\\n\\n\\n 6\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 7 of 18\\n\\n\\nhe raises two claims that he also raised in the § 1983 lawsuit at issue in this appeal:\\n\\n(1) his claim about the Warden’s denial of his requests for exceptions to the\\n\\nDepartment of Corrections’ witness policy, and (2) his challenge to Florida’s use\\n\\nof etomidate in its lethal injection protocol.\\n\\n II. STANDARD OF REVIEW\\n\\n We review the district court’s denial of a motion for a temporary restraining\\n\\norder, preliminary injunction, or stay of execution only for abuse of discretion.\\n\\nGissendaner v. Comm’r, Ga. Dep’t of Corr., 779 F.3d 1275, 1280 (11th Cir. 2015)\\n\\n(temporary restraining order); Chavez v. Fla. SP Warden, 742 F.3d 1267, 1271\\n\\n(11th Cir. 2014) (preliminary injunction); Muhammad v. Sec’y, Fla. Dep’t of\\n\\nCorr., 739 F.3d 683, 688 (11th Cir. 2014) (stay of execution). A district court\\n\\nabuses its discretion if, among other things, “it applies an incorrect legal standard,\\n\\nfollows improper procedures in making the determination, or makes findings of\\n\\nfact that are clearly erroneous.” Grayson v. Warden, Comm’r, Ala. DOC, 869 F.3d\\n\\n1204, 1238 (11th Cir. 2017) (quotation marks omitted).\\n\\n A federal court may grant a temporary restraining order, preliminary\\n\\ninjunction, or a stay of execution only if the movant establishes that (1) he has a\\n\\nsubstantial likelihood of success on the merits, (2) he will suffer irreparable injury\\n\\nunless the injunction issues, (3) the injunction would not substantially harm the\\n\\nother litigant, and (4) if issued, the injunction would not be adverse to the public\\n\\n\\n\\n 7\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 8 of 18\\n\\n\\ninterest. Powell v. Thomas, 641 F.3d 1255, 1257 (11th Cir. 2011); see also\\n\\nGissendaner, 779 F.3d at 1280; Chavez, 742 F.3d at 1271.\\n\\n III. DISCUSSION\\n\\n A. Long’s Method of Execution Claims\\n\\n The district court did not abuse its discretion in declining to stay Long’s\\n\\nexecution on account of his three method of execution claims. Each of them is\\n\\nbarred for two independently adequate reasons. First, Long engaged in\\n\\ninexcusable delay in bringing the claims, which is enough to deny him the\\n\\nequitable remedy of a stay. And second, as the district court properly held, each of\\n\\nhis claims is barred by the doctrine of res judicata.\\n\\n 1. Inexcusable Delay\\n\\n Long is not entitled to a stay of execution “as a matter of course” simply\\n\\nbecause he brought a § 1983 claim. Hill v. McDonough, 547 U.S. 573, 583–84\\n\\n(2006). Instead, a stay of execution is an equitable remedy and all of the rules of\\n\\nequity apply. See Rutherford v. Crosby, 438 F.3d 1087, 1092 (11th Cir. 2006)\\n\\n(explaining that “where petitioner’s scheduled execution is imminent, there is no\\n\\npractical difference between denying a stay on equitable grounds and denying\\n\\ninjunctive relief on equitable grounds in a § 1983 lawsuit”), vacated on other\\n\\ngrounds, Rutherford v. McDonough, 547 U.S. 1204 (2006).\\n\\n\\n\\n\\n 8\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 9 of 18\\n\\n\\n One of those rules is that “[e]quity must take into consideration the State’s\\n\\nstrong interest in proceeding with its judgment” and an inmate’s “attempt at\\n\\nmanipulation.” Gomez v. U.S. Dist. Ct. for N. Dist. of Cal., 503 U.S. 653, 654\\n\\n(1992) (per curiam). As a result, before granting a stay of execution, a court must\\n\\n“consider not only the likelihood of success on the merits and the relative harms to\\n\\nthe parties, but also the extent to which the inmate has delayed unnecessarily in\\n\\nbringing the claim.” Nelson v. Campbell, 541 U.S. 637, 649–50 (2004). There is a\\n\\n“strong equitable presumption against the grant of a stay where a claim could have\\n\\nbeen brought at such a time as to allow consideration of the merits without\\n\\nrequiring entry of a stay.” Id. at 650.\\n\\n The Supreme Court has reiterated the importance of these principles three\\n\\ntimes this year. The first time was in February when a stay entered by this Court\\n\\nwas vacated by the Supreme Court. Dunn v. Ray, 139 S. Ct. 661 (2019). In\\n\\nvacating the stay, the Court quoted from Gomez: “A court may consider the last-\\n\\nminute nature of an application to stay execution in deciding whether to grant\\n\\nequitable relief.” Id. at 661 (quoting Gomez, 503 U.S. at 654).\\n\\n And then in April, when affirming the Eighth Circuit’s denial of an inmate’s\\n\\nas-applied challenge to the State’s method of execution, the Supreme Court\\n\\nexplicitly instructed lower courts that: “Courts should police carefully against\\n\\nattempts to use such challenges as tools to interpose unjustified delay. Last-minute\\n\\n\\n\\n 9\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 10 of 18\\n\\n\\nstays should be the extreme exception, not the norm, and the last-minute nature of\\n\\nan application that could have been brought earlier, or an applicant’s attempt at\\n\\nmanipulation, may be grounds for denial of a stay.” Bucklew v. Precythe, 139 S.\\n\\nCt. 1112, 1134 (2019) (quotation marks omitted).\\n\\n And later that same month, the Supreme Court vacated another stay of\\n\\nexecution that this Court had issued. Its decision to vacate the stay was based on\\n\\nthe fact that the inmate had delayed bringing his challenge to the State’s lethal\\n\\ninjection protocol until about two months before his scheduled execution, and then\\n\\nwaited until just a few hours before that execution to submit additional evidence.\\n\\nDunn v. Price, 139 S. Ct. 1312, 1312 (2019). The Supreme Court again relied on\\n\\nGomez to instruct courts to consider the last-minute nature of a stay in determining\\n\\nwhether equitable relief is appropriate. Id.\\n\\n Long’s case is not one of the “extreme exception[s]” in which a last-minute\\n\\nstay should be entered, but instead is within “the norm” where the “strong\\n\\nequitable presumption against the grant of a stay” applies. Bucklew, 139 S. Ct. at\\n\\n1134; Hill, 547 U.S. at 584 (quotation marks omitted).\\n\\n The first of Long’s method of execution claims is that Florida’s use of a\\n\\nthree-drug protocol instead of a one-drug protocol violates the Eighth Amendment.\\n\\nBut Florida has used a three-drug protocol since January 14, 2000, when it added\\n\\nlethal injection as a new method of execution. See Heynard v. Sec’y, DOC, 543\\n\\n\\n\\n 10\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 11 of 18\\n\\n\\nF.3d 644, 647 (11th Cir. 2014). Long has had nineteen years to challenge the use\\n\\nof a three-drug protocol. Nineteen years is too long to wait.\\n\\n To the extent that Long argues that a challenge to three-drug protocols\\n\\nwould not have been valid until now because other states have only recently begun\\n\\nusing one-drug protocols, that argument is belied by allegations in his own\\n\\ncomplaint. It alleges that at least four other states have “used a single-drug method\\n\\nfor executions since 2009.” Ten years is too long to wait.\\n\\n Long’s other two method of execution claims also suffer from his delay in\\n\\nbringing them. In those claims, he contends that Florida’s use of etomidate as the\\n\\nfirst drug in its three-drug protocol is unconstitutional regardless of the health of\\n\\nthe inmate, and that it is especially so as applied to him because of his serious\\n\\nmedical conditions.\\n\\n Florida adopted etomidate as the first drug in its three-drug protocol in\\n\\nJanuary of 2017, two years and four months ago. But Long waited until a week\\n\\nago to file this § 1983 challenge to it. Long alleges in his complaint that three of\\n\\nFlorida’s recent executions using etomidate show that the drug causes inmates\\n\\nsevere pain because it does not properly anesthetize them. To the extent that Long\\n\\nargues (and it is not clear that he does) that the delay in bringing his claims was\\n\\nbased on facts arising from those executions, his argument is not persuasive. The\\n\\nfirst of the three executions occurred on November 8, 2017, the second on\\n\\n\\n\\n 11\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 12 of 18\\n\\n\\nFebruary 22, 2018, and the last of them on December 13, 2018. A delay of five\\n\\nmonths, fifteen months, or eighteen months is too long.\\n\\n Long’s person-specific claim is that his medical conditions will complicate\\n\\nFlorida’s use of etomidate and may cause him unnecessary pain. But Long has\\n\\nknown about his medical conditions for decades. During his 1989 resentencing\\n\\ntrial, he presented as mitigating evidence the testimony of two medical experts\\n\\nabout his traumatic brain injury and temporal lobe epilepsy. See Long, 610 So. 2d\\n\\nat 1271–72. Any argument about how etomidate would be uniquely harmful to\\n\\nhim could have been raised as soon as Florida adopted etomidate as the first drug\\n\\nin its three-drug protocol. That happened in January 2017, two years and four\\n\\nmonths before Long brought this lawsuit.\\n\\n If Long had truly intended to challenge Florida’s lethal injection protocol\\n\\ninstead of just seeking to delay his execution, he would not have deliberately\\n\\nwaited to file this lawsuit until a decision on the merits would require entry of a\\n\\nstay. We have refused to grant stays in cases involving delayed filings before, and\\n\\nLong’s delay was even more pronounced and less justifiable. See e.g., Brooks v.\\n\\nWarden, 810 F.3d 812, 826 (11th Cir. 2016) (holding that an inmate was not\\n\\nentitled to a stay where he delayed filing his § 1983 challenge until eleven weeks\\n\\nbefore his execution); In re Hutcherson, 468 F.3d 747, 749–50 (11th Cir. 2006)\\n\\n(denying prisoner’s motion to stay his execution pending this Court’s resolution of\\n\\n\\n\\n 12\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 13 of 18\\n\\n\\nhis application for leave to file a successive petition because he waited until eight\\n\\ndays before his scheduled execution to file it and, as a result, his “need for a stay of\\n\\nexecution [was] directly attributable to his own failure to bring his claims to court\\n\\nin a timely fashion”); Diaz v. McDonough, 472 F.3d 849, 851 (11th Cir. 2006)\\n\\n(declining to grant a preliminary injunction so that an inmate could pursue an\\n\\nappeal because he filed his § 1983 complaint less than three days before his\\n\\nscheduled execution); cf. Jones v. Allen, 485 F.3d 635, 640 (11th Cir. 2007)\\n\\n(holding that inmate was not entitled to a stay of execution because he waited four\\n\\nyears after learning that the state intended to execute him by lethal injection to file\\n\\nhis § 1983 challenge).\\n\\n 2. Res Judicata\\n\\n Even if Long’s method of execution claims were not barred on equitable\\n\\ngrounds, the district court properly concluded that he could not show a likelihood\\n\\nof success on the merits because the claims are barred by the doctrine of res\\n\\njudicata. All of the claims Long raises in this § 1983 action were raised, or could\\n\\nhave been raised, in his fourth motion for postconviction relief, which the Florida\\n\\nSupreme Court rejected. See Long, 2019 WL 2150942, at *6–7.\\n\\n To the district court’s concise and correct discussion, we add one point,\\n\\nwhich responds to Long’s argument that applying the doctrine of res judicata\\n\\nwould work a manifest injustice in his case. He claims that because the state\\n\\n\\n\\n 13\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 14 of 18\\n\\n\\ncourts did not give him a hearing on the merits of his general challenge, and\\n\\nbecause the hearing that they did give him on his person-specific challenge was\\n\\n“severely restricted” due to the “extraordinarily constrained timeline” for the\\n\\nlitigation of his fourth postconviction motion, it would be unjust to give the Florida\\n\\nSupreme Court’s decision preclusive effect.\\n\\n There are three big problems with this argument. First, his position is\\n\\nunprecedented. Long has not pointed to a single published decision of the Florida\\n\\ncourts or this Court applying Florida law holding that it is a “manifest injustice” to\\n\\napply res judicata if the initial state court decision resolved a claim without\\n\\ngranting an evidentiary hearing. 1\\n\\n The second problem with Long’s position is that the “extraordinarily\\n\\nconstrained timeline” that he complains of is a direct result of his delay in filing his\\n\\nmethod of execution claims in state postconviction proceedings until after his\\n\\nexecution date had been set. As we have discussed, there is no reason why Long\\n\\ncould not have challenged Florida’s use of a three-drug protocol as early as 2000\\n\\n\\n\\n 1\\n The inapplicability of the precedent that Long cites and the unpersuasiveness of the\\narguments that he makes are illustrated by the following sentence and citation from his brief:\\n“This Court has declined to apply res judicata where an inmate was not given an evidentiary\\nhearing on his challenge in state court. See Chavez v. Sec’y, 742 F.3d 1267 (11th Cir. 2014).”\\nThat citation is disingenuous. The entire discussion of res judicata in the Chavez opinion\\nconsists of the following footnote: “In light of our conclusion that Chavez has not established a\\nsubstantial likelihood of success on the merits of any of his claims, we do not address and imply\\nno view about the State’s asserted defenses based on the statute of limitations, exhaustion of\\nadministrative remedies, and res judicata.” Chavez, 742 F.3d at 1273 n.5.\\n\\n\\n 14\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 15 of 18\\n\\n\\n(when Florida adopted lethal injection as a method of execution) or at least by\\n\\n2009 (when, according to the allegations in his complaint, a number of states had\\n\\nswitched to a one-drug protocol). And there is no reason why Long could not have\\n\\nchallenged Florida’s use of etomidate, both in general and specifically as to him,\\n\\nin January 2017, when the Florida Department of Corrections decided to use it as\\n\\nthe first drug in the three-drug protocol. It is worse than ironic for Long to argue\\n\\nthat the state court’s decision does not deserve res judicata effect because the state\\n\\ncourt had to render that decision under the time constraints that Long forced on it.\\n\\n There is another fundamental problem with Long’s arguments against the\\n\\napplication of res judicata. Reduced to its essence, his position is that the res\\n\\njudicata doctrine applies only if the court in which it is asserted agrees with the\\n\\ninitial court’s decision on de novo consideration. And, he says, we shouldn’t agree\\n\\nwith the decision of the Florida courts on these claims for a number of reasons.\\n\\nBut that is not the way that res judicata works. If it did, the doctrine would be\\n\\ntoothless, pointless, and fruitless. It would apply only when it made no difference.\\n\\nThe Florida courts have never suggested such a rule-devouring exception, and we\\n\\nwill not presume to create one for them here. See Kremer v. Chem. Constr. Corp.,\\n\\n456 U.S. 461, 481–82 (1982) (“It has long been established that [28 U.S.C.] § 1738\\n\\ndoes not allow federal courts to employ their own rules of res judicata in\\n\\ndetermining the effect of state judgments. Rather, it goes beyond the common law\\n\\n\\n\\n 15\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 16 of 18\\n\\n\\nand commands a federal court to accept the rules chosen by the State from which\\n\\nthe judgment is taken.”).\\n\\n B. Long’s Public Records and Witness Claims\\n\\n In addition to his three method of execution claims, Long contends that the\\n\\ndefendants violated his constitutional rights by (1) objecting to some of his public\\n\\nrecords requests and refusing to answer some of his questions about the lethal\\n\\ninjection protocol, and (2) denying his requests for exceptions to the Department of\\n\\nCorrections’ witness policies. As the district court already held, both of those\\n\\nclaims are also barred by the doctrine of res judicata. Long raised a public records\\n\\nclaim in the Florida courts, see Long, 2019 WL 2150942, at *6–7, and he could\\n\\nhave asserted any similar claims in the state court proceedings.\\n\\n There are many published decisions that support the district court’s ruling\\n\\nthat, under Florida law, res judicata bars claims that Long could have raised in the\\n\\nstate postconviction proceedings but didn’t. See, e.g., Topps v. State, 865 So. 2d\\n\\n1253, 1255 (Fla. 2004) (“The doctrine of res judicata bars relitigation in a\\n\\nsubsequent cause of action not only of claims raised, but also claims that could\\n\\nhave been raised.”); Fla. Dep’t of Transp. v. Juliano, 801 So. 2d 101, 105 (Fla.\\n\\n2001) (“Importantly, the doctrine of res judicata not only bars issues that were\\n\\nraised, but it also precludes consideration of issues that could have been raised but\\n\\nwere not raised in the first case.”); see also Vasquez v. YII Shipping Co., 692 F.3d\\n\\n\\n\\n 16\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 17 of 18\\n\\n\\n1192, 1199 (11th Cir. 2012) (applying Florida law to explain that “the purpose of\\n\\nres judicata is that a final judgment in a court of competent jurisdiction is absolute\\n\\nand settles all issues actually litigated in a proceeding as well as those issues that\\n\\ncould have been litigated.”) (quotation marks omitted). The district court was\\n\\nentirely correct in concluding that Long’s public records and witness claims are\\n\\nbarred by res judicata.\\n\\n IV. CONCLUSION\\n\\n We AFFIRM the district court’s denial of Long’s emergency motion for a\\n\\ntemporary restraining order, preliminary injunction, or stay of execution. We\\n\\nDENY Long’s motion for a stay of execution from this Court.\\n\\n\\n\\n\\n 17\\n\\n Case: 19-11942 Date Filed: 05/22/2019 Page: 18 of 18\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2289,"cells":{"id":{"kind":"number","value":4622512,"string":"4,622,512"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff-Appellant, v. ASKINS & MILLER ORTHOPAEDICS, P.A., Roland v. Askins, III, Philip H. Askins, Defendants-Appellees."},"name_abbreviation":{"kind":"string","value":"United States v. Askins & Miller Orthopaedics, P.A."},"decision_date":{"kind":"string","value":"2019-05-23"},"docket_number":{"kind":"string","value":"18-11434"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Marcus, Grant, Hull\", \"parties\": \"\", \"opinions\": [{\"author\": \"GRANT, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 18-11434 Date Filed: 05/23/2019 Page: 1 of 24\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-11434\\n ________________________\\n\\n D.C. Docket No. 8:17-cv-00092-JDW-MAP\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellant,\\n\\n versus\\n\\nASKINS & MILLER ORTHOPAEDICS, P.A.,\\nROLAND V. ASKINS, III,\\nPHILIP H. ASKINS,\\n\\n Defendants-Appellees.\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Florida\\n ________________________\\n\\n (May 23, 2019)\\nBefore MARCUS, GRANT, and HULL, Circuit Judges.\\nGRANT, Circuit Judge:\\n\\n The IRS says it needs a preliminary injunction against Askins & Miller\\nOrthopaedics—a serial employment-tax delinquent—to ensure that it gets its due\\nas taxes continue to pile up. It could just wait for nonpayment and later seek a\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 2 of 24\\n\\n\\n\\nmoney judgment, but if past is prologue, the money will be long gone before the\\nIRS can collect. Given the alternative of a valid but potentially useless action for\\n\\ndamages, does the IRS necessarily have an “adequate” remedy at law that puts an\\ninjunction out of the question? We conclude that it does not, so we vacate the\\ndistrict court’s order denying injunctive relief and remand for further proceedings.\\n I.\\n The facts in this case tell a cyclical and monotonous story about the IRS’s\\nyears-long battle against two brothers, but the long and short of it is this: Askins &\\n\\nMiller Orthopaedics habitually fails to pay its federal employment taxes, and the\\ngovernment seeks injunctive relief to make sure it gets paid going forward.\\n Askins & Miller is a Sarasota medical practice run by brothers Philip H.\\nAskins and Roland V. Askins III. As an employer, Askins & Miller is required\\nunder the tax laws to 1) withhold from its employees’ wages and pay over to the\\nIRS federal income and Federal Insurance Contributions Act (FICA) taxes, and 2)\\npay its own FICA taxes. These payments must be deposited in an appropriate\\nfederal depository bank. But since 2010, Askins & Miller has repeatedly failed to\\npay these taxes—both its own share of FICA taxes and the income and FICA taxes\\nit has withheld from its employees—to the IRS. Askins & Miller does not dispute\\nits tax liability; indeed, it has filed returns documenting it. It just fails, over and\\nover again, to pay.\\n The IRS has tried several collection strategies over the years. It started with\\nan effort to achieve voluntary compliance: IRS representatives have spoken with\\nthe Askins brothers “at least 34 times” since December 2010, including 27 in-\\n\\n 2\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 3 of 24\\n\\n\\n\\nperson meetings. Twice they entered into installment agreements that set up\\nmonthly payments to bring Askins & Miller back into compliance, but the\\n\\ncompany defaulted both times. Two other times, they warned Askins & Miller that\\ncontinued noncompliance could prompt the government to seek an injunction.\\n The IRS has employed more aggressive means as well. It served levies on\\n“approximately two dozen entities,” but most “responded by indicating that there\\nwere no funds available to satisfy the levies.” Three entities paid some money, but\\nnot nearly enough to satisfy Askins & Miller’s debts or to keep pace with its\\n\\naccrual of new liabilities. Additionally, the IRS’s ability to collect payments\\nthrough levies has been hampered by the defendants’ attempts to hide Askins &\\nMiller’s funds and to keep the balances in Askins & Miller’s accounts low.\\nBetween 2014 and 2016, the Askins brothers transferred money from Askins &\\nMiller to “RVA Trust,” which operates a private hunting club for the brothers, and\\n“RVA Investments,” an accounting business associated with their father. The IRS\\nalso discovered additional accounts at BankUnited and Stonegate Bank. It did not\\nseek to levy RVA Trust, RVA Investments, or the bank accounts because it\\ndiscovered them after this case had been referred to the Department of Justice and\\nbecause the IRS believed that “there is a substantial risk that any new levy would\\nresult in [the defendants] opening new undisclosed accounts and moving the\\nmoney there.”\\n Next up were the brothers’ personal assets: because the brothers ran Askins\\n& Miller and were responsible for its failure to pay the taxes, the IRS “assessed\\ntrust fund recovery penalties against Roland V. Askins III for tax periods in 2014–\\n\\n 3\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 4 of 24\\n\\n\\n\\n2016 and against Philip Askins for tax periods in 2009–2012 and 2014–2016.”\\nTrust fund recovery penalties allow the IRS to hold a company’s officers\\n\\npersonally liable for the taxes withheld from employees’ wages—which belong to\\nthe government and are merely held in trust by the company—when those officers\\nwillfully fail to remit the employees’ taxes to the IRS. The IRS issued levies to\\n“approximately 15 entities” associated with Roland, but only one entity made any\\npayments; that source was enough “to satisfy current trust fund recovery penalties\\nassessments [sic] against Roland,” but not enough “to keep pace with the rate at\\n\\nwhich the company” continued to accrue liabilities. The IRS levied\\n“approximately six entities” for Philip, but after one paid less than $2,000, Philip\\nclosed the account. The IRS does not believe the brothers have enough assets in\\ntheir own names to cover the debts, and even if they did, trust fund recovery\\npenalties cannot be used to cover Askins & Miller’s share of its own employment\\ntaxes (as distinct from employees’ taxes that were withheld from their paychecks).\\n The IRS “consistently” filed notices of federal tax liens, but this approach\\nwas a nonstarter: liens “are only valuable insofar as a taxpayer has property against\\nwhich the liens can be enforced,” and Askins & Miller “does not own any\\nsubstantial property.” For the same reason, the IRS considered but decided not to\\npursue asset seizure: the most promising target, a 2004 Cadillac worth $10,000,\\nwas apparently not worth the effort.\\n Feeling as if it had reached the end of its rope, the IRS sued Askins & Miller\\nand both brothers in 2017. It asserted two counts: one for permanent injunctive\\nrelief requiring Askins & Miller and the brothers to take specific steps to ensure\\n\\n 4\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 5 of 24\\n\\n\\n\\nthat future payments would be made before the brothers could divert the money,\\nand another for damages to account for outstanding liabilities between 2010 and\\n\\n2015. Relying on a declaration from one of its revenue officers, the IRS asked the\\ndistrict court to issue a preliminary injunction—largely mirroring the permanent\\ninjunction that it sought in its complaint—designed to prevent Askins & Miller\\nfrom incurring further tax liabilities while the litigation was still ongoing. But the\\ndistrict court denied the motion without prejudice because it found the declaration\\nconclusory, and because it thought the proposed injunction was “effectively an\\n\\n‘obey-the-law’ injunction.”\\n Trying again, the IRS submitted a more detailed declaration and additional\\nargument as to why the court should issue a preliminary injunction. It contended\\nthat the proposed injunction was not an “obey-the-law” one and that it lacked an\\nadequate remedy at law because all of its previous collection efforts had proven\\nunsuccessful. The IRS also argued that because the company appeared to be\\njudgment-proof, the money judgment it sought for past liabilities was likely\\nmeaningless. But again, the court declined: although the court found that three of\\nthe four factors for granting injunctive relief were “not seriously disputed,” it\\ndenied an injunction because it concluded that the availability of an action for\\ndamages was an adequate remedy at law and that the IRS therefore could not show\\nirreparable harm. The court also suggested that the injunction, at least as drafted\\nand proposed by the IRS, 1 was still, effectively, a disfavored “obey-the-law”\\n\\n1\\n The proposed injunction included seven terms:\\n\\n\\n\\n 5\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 6 of 24\\n\\n\\n\\ninjunction. The IRS appealed. See 28 U.S.C. § 1292(a)(1) (allowing for\\ninterlocutory appeal of orders denying an injunction). Since then, the district court\\n\\nhas granted summary judgment to the IRS on count two (the damages claim for\\ntaxes between 2010 and 2015), but it deferred ruling on count one (the request for\\na permanent injunction) because it concluded that the IRS’s appeal divested it of\\njurisdiction over that count. 2\\n\\n\\n (1) Defendants shall, for liabilities due on each employment tax return required to be\\n filed after the date of the preliminary injunction, pay over to the IRS all income and\\n Federal Insurance Contributions Act (“FICA”) taxes withheld from employees and\\n Askins & Miller’s own share of FICA taxes (collectively, “employment taxes”);\\n (2) Defendants shall segregate (i.e., hold separate and apart from all other funds) all\\n employment taxes of employees of Askins & Miller and shall, on a semiweekly\\n schedule, deposit them in an appropriate federal depository bank;\\n (3) Defendants shall not transfer any money or property to any other entity—except a\\n payroll processing company that is shown a copy of the injunction and is approved in\\n advance by Revenue Officer Richard Paulsen (or another employee designated by the\\n IRS)—to have that entity pay the salaries or wages of Askins & Miller’s employees.\\n If Defendants employ an approved payroll processing company, all transfers shall\\n include sufficient funds for the payroll processing company to make Askins &\\n Miller’s federal tax deposits, and Defendants shall provide the payroll processing\\n company with the authority and information necessary to make such deposits;\\n (4) Except for use of a payroll processing company in accordance with paragraph three\\n above, Defendants shall not assign any of Askins & Miller’s property or rights to\\n Askins & Miller’s property or make any disbursements from Askins & Miller’s\\n accounts before making all required deposits and paying all required outstanding\\n liabilities due on each employment tax return required to be filed after the date of the\\n preliminary injunction;\\n (5) Defendants shall sign and deliver affidavits to the IRS at 5971 Cattleridge Boulevard,\\n Suite 102-Mail Stop 5410, Sarasota, FL 34232, or to such other specific location as\\n directed by the IRS, within two banking days after each employment tax deposit is\\n due, stating that the requisite deposit was timely made;\\n (6) Defendant Roland V. Askins III shall notify the IRS of any new company or business\\n he may come to own or manage; and\\n (7) Defendant Philip H. Askins shall notify the IRS of any new company or business he\\n may come to own or manage.\\n2\\n The brothers did not materially dispute the IRS’s account of the facts before the district court,\\nnor do they do so on appeal. They did (and do), however, contest the IRS’s characterizations of\\n\\n\\n 6\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 7 of 24\\n\\n\\n\\n Meanwhile, the defendants’ delinquency continued: Askins & Miller racked\\nup more liabilities in 2017 even after the IRS sued, and the district court found that\\n\\nthe defendants have “a proclivity for unlawful conduct” and are “likely to continue\\nignoring” their tax obligations. In fact, other businesses associated with the\\nbrothers—RVA Trust and Gulfcoast Surgery Center—also fell behind on their\\nemployment taxes. The IRS represented to the district court that Askins & Miller\\nwas “accumulating new employment tax liabilities faster than the IRS’s ability to\\ncollect the outstanding obligations” and that its time spent playing cat-and-mouse\\n\\nover the years “constituted a substantial drain” on resources. Deeming an action\\nfor damages a Sisyphean task in these circumstances, the IRS contends on appeal\\nthat the district court should have granted a preliminary injunction because the IRS\\nhas no “adequate” remedy at law.\\n II.\\n Section 7402(a) of the Internal Revenue Code grants federal district courts\\nan array of powers to aid in enforcing the tax laws:\\n\\n\\n\\ntheir motivations and intent: in the brothers’ telling, it was bad business, not bad faith, that\\ncaused them to fall behind. Specifically, Philip Askins submitted a declaration to the district\\ncourt stating that Askins & Miller did not make “any decision never to pay withholding taxes,”\\nthat Askins & Miller has “consistently reported all of its tax liabilities,” and that “extreme\\nfinancial reversals and financial hardships” caused the business to fall behind on all of its debts.\\nPhilip also claimed that Askins & Miller never “sought to hide or avoid it’s [sic] liabilities either\\nto the IRS or to any of its other creditors” and that he had been truthful and open with the IRS.\\nFinally, Philip claimed that a potential sale of another entity, Gulfcoast Surgery Center, was\\nsupposed to provide the funds to bring Askins & Miller into compliance with all of its tax\\nobligations, but the sale “unexpectedly” fell through. The district court did not explicitly resolve\\nthese disputes in its order denying the government’s motion for a preliminary injunction, but it\\ndid find that “the record demonstrates that Defendants have diverted and misappropriated” the\\nemployment taxes withheld from their employees’ wages.\\n 7\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 8 of 24\\n\\n\\n The district courts of the United States at the instance of the United States\\n shall have such jurisdiction to make and issue in civil actions, writs and\\n orders of injunction, and of ne exeat republica, orders appointing receivers,\\n and such other orders and processes, and to render such judgments and\\n decrees as may be necessary or appropriate for the enforcement of the\\n internal revenue laws. The remedies hereby provided are in addition to and\\n not exclusive of any and all other remedies of the United States in such\\n courts or otherwise to enforce such laws.\\n\\n26 U.S.C. § 7402(a). In analyzing this grant of injunctive power, we have said that\\nthe “decision to issue an injunction under § 7402(a) is governed by the traditional\\nfactors shaping the district court’s use of the equitable remedy.” United States v.\\nErnst & Whinney, 735 F.2d 1296, 1301 (11th Cir. 1984).3 To obtain a preliminary\\n\\ninjunction under “the traditional factors,” the IRS must demonstrate 1) a\\nsubstantial likelihood of success on the merits, 2) that it will suffer irreparable\\ninjury unless the injunction is issued, 3) that the threatened injury to the IRS\\noutweighs whatever harm the proposed injunction might cause the defendants, and\\n\\n3\\n We note that there is some question over whether applying “the traditional factors” in § 7402(a)\\ncases is the right approach. The statute’s “in addition to and not exclusive of” language could be\\nread to suggest that the government need not show the lack of an adequate remedy at law, as\\nwould normally be required under the traditional factors. See, e.g., United States v. Benson, 561\\nF.3d 718, 727 n.4 (7th Cir. 2009); cf. United States v. First Nat’l City Bank, 379 U.S. 378, 383\\n(1965) (“[O]ur review of the injunction as an exercise of the equity power granted by 26 U.S.C.\\n§ 7402(a) must be in light of the public interest involved: ‘Courts of equity may, and frequently\\ndo, go much farther both to give and withhold relief in furtherance of the public interest than\\nthey are accustomed to go when only private interests are involved.’” (citation omitted)). But the\\nIRS does not ask us to hold categorically that the adequate-remedy-at-law requirement is\\ninapplicable in § 7402(a) cases, and at any rate we are bound by our precedent. See Ernst &\\nWhinney, 735 F.2d at 1301; see also United States v. Cruz, 611 F.3d 880, 887 (11th Cir. 2010)\\n(rejecting argument that courts should disregard equitable factors when issuing injunctions under\\n§ 7407 and citing Ernst & Whinney); Klay v. United Healthgroup, Inc., 376 F.3d 1092, 1098–99\\n(11th Cir. 2004) (recognizing some “statutory injunction” contexts where the traditional\\nrequirements are relaxed, but citing Ernst & Whinney for the proposition that “several of our\\ncases also suggest that, when Congress authorizes injunctive relief, it implicitly requires that the\\ntraditional requirements for an injunction be met in addition to any elements explicitly specified\\nin the statute”).\\n 8\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 9 of 24\\n\\n\\n\\n4) that the injunction would not be adverse to the public interest. See Keeton v.\\nAnderson-Wiley, 664 F.3d 865, 868 (11th Cir. 2011). We review for abuse of\\n\\ndiscretion a district court’s “ultimate decision of whether to grant a preliminary\\ninjunction,” but we review de novo “determinations of law made by the district\\ncourt en route” to that decision. Owner-Operator Indep. Drivers Ass’n, Inc. v.\\nLandstar Sys., Inc., 622 F.3d 1307, 1323 (11th Cir. 2010) (internal quotation marks\\nand citation omitted).\\n III.\\n\\n Before reaching the merits, we face a preliminary question: whether\\nsubsequent events have rendered this case (or at least portions of this case) moot.\\nDuring the briefing, counsel for defendants filed a motion to withdraw because he\\nwas not getting paid. In that motion, counsel asserted that Askins & Miller “is no\\nlonger in business, has no employees, and has insufficient assets to ever resume\\nbusiness in the future.” The first five of the seven items in the proposed\\npreliminary injunction are premised on Askins & Miller’s continued viability.\\nAlthough counsel withdrew the motion after the Askins brothers “made\\nsatisfactory financial arrangements,” we asked the parties to address whether\\nAskins & Miller is “still incurring tax liabilities that the proposed preliminary\\ninjunction would address” and how the answer to that question should affect our\\ndisposition of the case.\\n “Whether a case is moot is a question of law that we review de novo.”\\nSheely v. MRI Radiology Network, P.A., 505 F.3d 1173, 1182 (11th Cir. 2007). A\\n“case is moot when it no longer presents a live controversy with respect to which\\n\\n 9\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 10 of 24\\n\\n\\n\\nthe court can give meaningful relief.” Id. at 1183 (quoting Troiano v. Supervisor\\nof Elections, 382 F.3d 1276, 1282 (11th Cir. 2004)). But an “important exception”\\n\\nto this “general rule” exists in cases of “voluntary cessation”—that is, where a\\ndefendant voluntarily puts an end to his offensive conduct. Id. In such cases, it is\\n“well settled” that the defendant’s voluntary cessation does not automatically moot\\nthe case; rather, a case “might become moot if subsequent events made it\\nabsolutely clear that the allegedly wrongful behavior could not reasonably be\\nexpected to recur.” Friends of the Earth, Inc. v. Laidlaw Envtl. Servs. (TOC), Inc.,\\n\\n528 U.S. 167, 189 (2000) (internal quotation marks and citation omitted). This\\n“stringent” standard imposes a “heavy” and “formidable” burden on the party\\nasserting mootness—here, the Askins brothers. Id. at 189–90. To carry this\\n“heavy” burden, we require more than a private party’s assertion that its challenged\\nconduct will not recur. See Sheely, 505 F.3d at 1184.\\n Based on the undisputed factual record, Askins & Miller’s possible closure\\ndid not moot the IRS’s claim for injunctive relief. The Supreme Court has made\\nclear that the voluntary cessation standard applies where a business entity’s closure\\nis alleged to have mooted the case. See Laidlaw, 528 U.S. at 193. In conducting\\nthe voluntary cessation analysis, we have previously identified “at least” three\\nrelevant factors: “(1) whether the challenged conduct was isolated or unintentional,\\nas opposed to a continuing and deliberate practice; (2) whether the defendant’s\\ncessation of the offending conduct was motivated by a genuine change of heart or\\ntimed to anticipate suit; and (3) whether, in ceasing the conduct, the defendant has\\nacknowledged liability.” Sheely, 505 F.3d at 1184. Applying those factors here—\\n\\n 10\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 11 of 24\\n\\n\\n\\nin light of the history of the case and the undisputed conduct of the defendants—\\nwe find it far from “absolutely clear that the allegedly wrongful behavior could not\\n\\nreasonably be expected to recur.” Laidlaw, 528 U.S. at 189 (internal quotation\\nmarks and citation omitted).\\n First, we consider “whether the challenged conduct was isolated or\\nunintentional, as opposed to a continuing and deliberate practice.” Sheely, 505\\nF.3d at 1184. The defendants’ failure to pay their federal employment taxes has\\nbeen “a continuing and deliberate practice” for the better part of a decade. Far\\n\\nfrom “isolated or unintentional,” the defendants’ routine failure to pay their\\nemployment taxes since 2010—despite withholding the money from their\\nemployees, and despite repeated interventions from the IRS—appears to have been\\ntheir method of doing business. And although the defendants attribute that routine\\nfailure to bad business rather than bad faith, their professed intentions wane in the\\nshadow of their undisputed history. Similarly, considering the record, we put little\\nweight on Askins & Miller’s (unsupported) eleventh-hour assurances that the\\nbusiness is gone for good. Indeed, we have repeatedly said that a “defendant’s\\nassertion that it has no intention of reinstating the challenged practice ‘does not\\nsuffice to make a case moot’ and is but ‘one of the factors to be considered in\\ndetermining the appropriateness of granting an injunction against the now-\\ndiscontinued acts.’” Id. (quoting United States v. W.T. Grant Co., 345 U.S. 629,\\n\\n\\n\\n\\n 11\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 12 of 24\\n\\n\\n\\n633 (1953)). And, again, we require more than a private party’s unsupported\\nassertions—especially here, given the history of this case.\\n\\n Second, we ask “whether the defendant’s cessation of the offending conduct\\nwas motivated by a genuine change of heart or timed to anticipate suit.” Id. Here,\\nthe timing of Askins & Miller’s possible closure is more indicative of a changed\\ntax-avoidance strategy than a changed heart. We have previously expressed\\nskepticism where changed circumstances come on the eve of a significant decision\\npoint in litigation. See id. at 1187 n.13 (defendant applied “new policy” shortly\\n\\nbefore summary judgment motion); see also id. at 1186 (collecting cases). Here,\\nAskins & Miller claims to have closed down while this case was on appeal.\\nSignificantly, the undisputed facts in the record demonstrate that it would be\\nsimple to reopen at a moment’s notice: back in November 2015, while the IRS was\\nstill experimenting with different collection strategies, “the company submitted a\\nfinancial statement” reflecting “no investments, no accounts or notes receivable, no\\nreal estate, and no business equipment.” Despite that lack of assets, the company\\ncontinued in business until at least mid-2018. The record further demonstrates the\\ndefendants’ history of moving money around from entity to entity. Even taking the\\ndefendants at their word, one of the brothers “has continued his practice\\nincorporated as Roland V. Askins, III, M.D., P.A.,” and their attorney represented\\nat oral argument that although Askins & Miller is out of business “as a practical\\nmatter” (whatever that may mean), the corporation “continues to exist” and “hasn’t\\nbeen formally dissolved.” Those admissions only underscore the ease with which\\nthe brothers could revive Askins & Miller. In light of the record evidence, the\\n\\n 12\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 13 of 24\\n\\n\\n\\ndefendants’ claim that they have “insufficient assets to ever resume business in the\\nfuture” rings hollow.\\n\\n Third, we look to “whether, in ceasing the conduct, the defendant has\\nacknowledged liability.” Id. at 1184. Although the defendants here have not\\ndisputed their past tax debt—the district court entered a money damages judgment\\nfor past-due employment taxes, and Askins & Miller filed tax returns admitting its\\nliabilities—that is cold comfort given the history of this case, in which Askins &\\nMiller has demonstrated a pattern of admitting liability but refusing to pay. The\\n\\nIRS’s proposed relief is designed to prevent Askins & Miller from dodging its\\nadmitted tax liabilities going forward. Because the record amply demonstrates a\\npattern of Askins & Miller pairing its admitted liability with a refusal to pay, the\\nfact that it still admits its liability does not convince us that it is “absolutely clear\\nthat the allegedly wrongful behavior could not reasonably be expected to recur.”\\nLaidlaw, 528 U.S. at 189 (internal quotation marks and citation omitted).\\n Given the undisputed facts before us, we do not believe that the defendants\\ncan satisfy their “heavy” and “formidable” burden of making it “absolutely clear”\\nthat their behavior will not recur. And “we are unpersuaded that a remand would\\nfurther the expeditious resolution of the matter.” Sheely, 505 F.3d at 1188 n.15\\n(conducting mootness analysis without remanding for further fact finding). The\\ndistrict court already concluded that the defendants have “a proclivity for unlawful\\nconduct” and are “likely to continue ignoring” their tax obligations. The record\\ndemonstrates a near-decade-long saga in which the IRS has pursued Askins &\\nMiller time and again. Over that time span, the defendants have funneled money\\n\\n 13\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 14 of 24\\n\\n\\n\\nto new accounts and entities as the IRS closed in on the old ones. For at least the\\ntime between November 2015 and mid-2018, Askins & Miller continued as a\\n\\ngoing concern despite reporting “no investments, no accounts or notes receivable,\\nno real estate, and no business equipment.” Against that backdrop—and in light of\\nthe defendants’ admissions that Askins & Miller “continues to exist” and that one\\nof the brothers continues to practice medicine—“we can discern no reason for\\nsending the question of mootness back to the district court for further review or\\nfact finding.” Id.\\n\\n We emphasize that our decision that the case is not moot does not resolve\\nwhether Askins & Miller’s possible closure makes injunctive relief inappropriate\\non the merits. That is due to the differences between the standard for mootness\\ndue to voluntary cessation and the standard for granting injunctive relief. For a\\ncase to be moot under the voluntary cessation doctrine, the party asserting\\nmootness—here, the defendants—bears the burden to convince a court that\\n“subsequent events made it absolutely clear that the allegedly wrongful behavior\\ncould not reasonably be expected to recur.” Laidlaw, 528 U.S. at 189 (internal\\nquotation marks and citation omitted). By contrast, to obtain an injunction, the\\nplaintiff must “establish by a preponderance of the evidence that this form of\\nequitable relief is necessary.” Sheely, 505 F.3d at 1182 n.10. Because “the two\\ninquiries are strikingly different”—both as to who bears the burden and as to what\\nthat burden is—it follows that “[e]ven though a case is not moot, that does not\\nmean that injunctive relief follows automatically.” Id. The analyses may\\n“overlap[]” because “both are concerned with the likelihood of future unlawful\\n\\n 14\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 15 of 24\\n\\n\\n\\nconduct,” but as we have explained, the answers may well turn out to be different.\\nId. Our analysis here answers the mootness question, but we leave it to the district\\n\\ncourt on remand to answer the merits question.\\n IV.\\n Assured of our jurisdiction, we turn to the merits. We conclude that neither\\nthe adequate-remedy-at-law requirement nor Rule 65(d) should have precluded\\ninjunctive relief on the facts here.\\n A. Adequate Remedy at Law\\n\\n The district court determined that three out of the four “traditional factors”\\ngoverning the propriety of injunctive relief—likelihood of success on the merits,\\nthe balance of harms, and the public interest—were “not seriously disputed by\\nDefendants.” But it denied injunctive relief because it concluded that the IRS had\\nan adequate remedy at law: a suit for money damages after Askins & Miller failed\\nto pay its taxes. We disagree. On these facts, the IRS’s ability to sit on its hands\\nuntil the defendants fail to pay their taxes (again) and only then bring an action for\\nmoney damages does not qualify as an “adequate” legal remedy.\\n Our prior cases do not answer the question presented here. We have said\\nbefore that § 7402(a)’s language “encompasses a broad range of powers necessary\\nto compel compliance with the tax laws.” Ernst & Whinney, 735 F.2d at 1300.\\nAnd we have also emphasized that in any given case under § 7402(a) a court must\\nlook to “the traditional factors shaping the district court’s use of the equitable\\nremedy,” and that “[f]oremost among the principles governing the use of the\\ninjunctive remedy is the traditional requirement ‘that courts of equity should not\\n\\n 15\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 16 of 24\\n\\n\\n\\nact . . . when the moving party has an adequate remedy at law and will not suffer\\nirreparable injury if denied equitable relief.’” Id. at 1301 & n.11 (quoting Younger\\n\\nv. Harris, 401 U.S. 37, 43–44 (1971)). We left it to the district court in that case to\\n“examine the extent to which [the IRS’s] interests are protected by available legal\\nremedies.” Id. And our past precedents on adequate legal remedies do not\\nsquarely resolve the issue in this case: whether the collectability of a future money\\njudgment to cure an expected future injury matters. See, e.g., Ne. Fla. Chapter of\\nthe Ass’n of Gen. Contractors of Am. v. City of Jacksonville, 896 F.2d 1283, 1285\\n\\n(11th Cir. 1990) (stating broadly that an injury is irreparable “only if it cannot be\\nundone through monetary remedies”). But see, e.g., Scott v. Roberts, 612 F.3d\\n1279, 1294–95 (11th Cir. 2010) (discussing situations where an injury is\\nirreparable even though “a later money judgment might undo” it); Levi Strauss &\\nCo. v. Sunrise Int’l Trading Inc., 51 F.3d 982, 986 (11th Cir. 1995) (stating that\\ntrademark infringement causes irreparable harm, even though the trademark holder\\nwas also seeking monetary damages); Fla. Businessmen for Free Enter. v. City of\\nHollywood, 648 F.2d 956, 958 n.2 (5th Cir. Unit B June 1981) (stating that lost\\nprofits may amount to irreparable injury if they are “difficult or impossible to\\ncalculate”).\\n Addressing that issue now, we can see that the collectability of a future\\nmoney judgment to redress future harms is relevant in determining whether legal\\nremedies are “adequate” such that they preclude injunctive relief under § 7402(a).\\nThe very nature of equitable power—the thing that distinguishes it from law—is its\\nflexible and discretionary nature, its ability to respond to real-world practicalities,\\n\\n 16\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 17 of 24\\n\\n\\n\\nand its general aversion to rules that let bad actors capitalize on legal technicalities.\\nSee, e.g., Roscoe Pound, The Decadence of Equity, 5 Colum. L. Rev. 20 (1905).\\n\\n Equity courts have long recognized “extraordinary circumstances,”\\nincluding the likelihood that a defendant will never pay, as one way to “give rise to\\nthe irreparable harm necessary for a preliminary injunction.” 11A Charles Alan\\nWright & Arthur Miller, Federal Practice and Procedure § 2948.1 (3d ed. 2013);\\nsee also Ernst & Whinney, 735 F.2d at 1301 (citing Wright & Miller for its\\n“general discussion of equitable principles governing [the] injunctive remedy”).\\n\\nMore specifically, “most courts sensibly conclude that a damage judgment against\\nan insolvent defendant is an inadequate remedy.” Douglas Laycock, The Death of\\nthe Irreparable Injury Rule, 103 Harv. L. Rev. 687, 716 (1990); see also, e.g.,\\nLakeview Tech., Inc. v. Robinson, 446 F.3d 655, 657 (7th Cir. 2006) (noting that\\nthe “[a]bility to calculate damages” does not make a remedy adequate “if the\\nplaintiff cannot collect the award”).4\\n\\n Indeed, the Supreme Court long ago stressed the practical nature of the\\nequitable inquiry, stating that it “is not enough that there is a remedy at law; it must\\nbe plain and adequate, or in other words, as practical and as efficient to the ends of\\n\\njustice and its prompt administration, as the remedy in equity.” Boyce’s Ex’rs v.\\nGrundy, 28 U.S. (3 Pet.) 210, 215 (1830). The district court’s categorical rule that\\n\\n\\n4\\n The IRS also points to district court cases purportedly granting injunctions in circumstances\\nsimilar to this case, but we place little weight on them. First, the IRS concedes that many of\\nthese cases were the result of default or consent orders, so their propriety may not have been\\nsubject to the sort of vigorous litigation that would give them persuasive value. Second, the\\nrelevance of out-of-circuit cases is further watered down by the fact that some courts—unlike\\nthis Court—have not held injunctions under § 7402(a) to the traditional equitable requirements.\\n 17\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 18 of 24\\n\\n\\n\\na case involving calculable money damages can never warrant injunctive relief,\\nregardless of a plaintiff’s ability to collect on a future judgment, is discordant with\\n\\nthe history and purposes of equity jurisprudence.\\n The fact that the IRS is attempting to avoid future losses is key. As the IRS\\nnotes, it “is an involuntary creditor; it does not make a decision to extend credit.”\\nIn re Haas, 31 F.3d 1081, 1088 (11th Cir. 1994). As long as the brothers continue\\nto accrue employment taxes, the IRS continues to lose money. This sets the IRS\\napart from the position of other creditors (who can cut their losses by refusing to\\n\\nextend additional credit), and—crucially—means that the injunction sought is not\\nsimply an attempt to provide security for past debts. Rather, the proposed\\ninjunction here would staunch the flow of ongoing future losses as the brothers\\ncontinue to accumulate tax liabilities—unlike in cases where the loss has already\\nbeen inflicted or would be attributable to a single event, where we have stated that\\ninjuries are irreparable only when they “cannot be undone through monetary\\nremedies.” E.g., Scott, 612 F.3d at 1295 (quoting Cunningham v. Adams, 808 F.2d\\n815, 821 (11th Cir. 1987)).\\n Indeed, the record and the district court’s own findings demonstrate that the\\ngovernment’s proposed injunctive relief is “appropriate for the enforcement of the\\ninternal revenue laws,” 26 U.S.C. § 7402(a), and that the government will likely\\nsuffer irreparable injury absent an injunction. Among other things, the district\\ncourt noted that Askins & Miller had “a proclivity for unlawful conduct,” had\\n“diverted and misappropriated” the employment taxes it had withheld from its\\nemployees’ wages, and was “likely to continue ignoring” its employment tax\\n\\n 18\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 19 of 24\\n\\n\\n\\nobligations. The IRS’s declaration demonstrates that, over a period of several\\nyears, it expended considerable resources making numerous—and unsuccessful—\\n\\nattempts to collect Askins & Miller’s unpaid taxes. And in the face of all that, as\\nthe declaration explained, Askins & Miller is effectively judgment-proof. In short,\\nthe record amply demonstrates that, absent the requested injunction, the\\ngovernment will continue to suffer harm from Askins & Miller’s willful and\\ncontinuing failure to comply with its employment tax obligations—including lost\\ntax revenue and the expenditure of a disproportionate amount of its resources\\n\\nmonitoring Askins & Miller and attempting to bring it into compliance—and that,\\nin all likelihood, the government will never recoup these losses.\\n The district court relied primarily on our decision in Rosen v. Cascade\\nInternational, Inc., 21 F.3d 1520 (11th Cir. 1994), but Rosen is an uncomfortable\\nfit here. As background, shareholders in that case brought a suit for money\\ndamages against a company and its officers because of alleged securities fraud. Id.\\nat 1522. To ensure that the defendants would be able to satisfy any money\\njudgment ultimately obtained in the litigation, the district court entered a\\npreliminary injunction freezing the assets of one of the defendants. Id. On appeal,\\nwe held that the district court lacked authority to enter that injunction because\\n“cases in which the remedy sought is the recovery of money damages do not fall\\nwithin the jurisdiction of equity,” and as a general rule of federal equity, “a court\\nmay not reach a defendant’s assets unrelated to the underlying litigation and freeze\\nthem so that they may be preserved to satisfy a potential money judgment.” Id. at\\n1527 (internal quotation marks and citation omitted). We also noted that a request\\n\\n 19\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 20 of 24\\n\\n\\n\\nfor prejudgment attachment under Federal Rule of Civil Procedure 64, rather than a\\nmotion for a preliminary injunction under Rule 65, provided the appropriate means\\n\\nto seek an asset freeze. Id. at 1530–31. Looking to state law (as the Rule\\nrequires), we concluded that the plaintiffs had not shown that they were entitled to\\nRule 64 relief. Id.\\n The differences between that case and this one announce themselves rather\\nclearly. Rosen asked “whether a district court has the power to enter a preliminary\\ninjunction freezing the assets of a defendant before trial in a case where the\\n\\nplaintiffs ultimately seek only money damages.” Id. at 1526 (emphasis added).\\nThat damages-only fact was front and center: we explained that a preliminary\\ninjunction is appropriate only where it seeks relief of the “same character” as the\\nfinal relief sought, and that the asset freeze in that case was not of the same\\ncharacter as the ultimate relief because the plaintiffs there “sought only the award\\nof monetary damages—and not equitable relief.” Id. at 1527, 1529 (internal\\nquotation marks and citation omitted); accord Grupo Mexicano de Desarrollo, S.A.\\nv. Alliance Bond Fund, Inc., 527 U.S. 308 (1999); Mitsubishi Int’l Corp. v.\\nCardinal Textile Sales, Inc., 14 F.3d 1507 (11th Cir. 1994).\\n Here, in contrast, the IRS’s complaint asked for a permanent injunction\\nproviding prospective equitable relief for anticipated future violations—the same\\nrelief sought by the preliminary injunction at issue. Indeed, we have already held\\nthat Rosen does not apply where the complaint itself seeks a permanent injunction.\\nLevi Strauss & Co., 51 F.3d at 987; see also SEC v. ETS Payphones, Inc., 408 F.3d\\n727, 734 (11th Cir. 2005) (per curiam) (holding that Grupo Mexicano does not\\n\\n 20\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 21 of 24\\n\\n\\n\\napply where the complaint seeks equitable relief). As Rosen itself was careful to\\nnote, a preliminary injunction “is always appropriate to grant intermediate relief of\\n\\nthe same character as that which may be granted finally.” Rosen, 21 F.3d at 1527\\n(quoting De Beers Consol. Mines v. United States, 325 U.S. 212, 220 (1945)). 5\\n What’s more—and contrary to the district court’s reading—nothing in Rosen\\n\\nsuggests that the IRS has not shown an irreparable injury for purposes of a\\npreliminary injunction. The Rosen court’s statement that the “test of the\\ninadequacy of a remedy at law is whether a judgment could be obtained, not\\nwhether, once obtained it will be collectible,” 21 F.3d at 1531 (quoting St.\\nLawrence Co., N.V. v. Alkow Realty, Inc., 453 So. 2d 514, 514–15 (Fla. Dist. Ct.\\nApp. 1984)), was made in the context of a Rule 64 analysis relating to prejudgment\\n\\nattachment. As we have said, Rule 64 looks to the law of the state in which the\\ncourt sits. See Fed. R. Civ. P. 64(a). So this statement in Rosen merely described\\nFlorida law governing prejudgment attachment; it did not determine (or even\\ndescribe) federal equitable power.\\n\\n\\n\\n\\n5\\n We also note that, for at least a portion of the employment taxes at issue, the assets that the\\ninjunction would reach are not “unrelated”—indeed, they do not even wholly belong to the\\ndefendants—because when an employer withholds employees’ taxes, the withheld money is held\\nin trust for the United States. See Thibodeau v. United States, 828 F.2d 1499, 1506 (11th Cir.\\n1987) (per curiam). So at least for this portion of the taxes, the IRS has an equitable interest that\\nmight qualify it for relief analogous to the “creditor’s bill” recognized in English courts of\\nequity. See Grupo Mexicano, 527 U.S. at 319–20 & n.5 (“Some cases suggested that there was\\nan exception [to the requirement that a judgment be obtained before bringing a creditor’s bill]\\nwhere the debt was admitted or confessed, at least if the creditor possessed an interest in the\\ndebtor’s property.”).\\n 21\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 22 of 24\\n\\n\\n\\n In sum, the district court erred in applying a categorical rule that because tax\\nliability may be calculated and sought in an action for damages, it necessarily\\n\\nprecludes injunctive relief under § 7402(a).\\n B. Rule 65(d)\\n The district court also suggested that “the United States’ proposed injunction\\nwould be unenforceable” as an overbroad “obey-the-law” injunction. It is true that\\nwe have “questioned the enforceability of obey-the-law injunctions” because “they\\nlack specificity and deprive defendants of the procedural protections that would\\n\\nordinarily accompany a future charge of a violation.” SEC v. Goble, 682 F.3d 934,\\n949 (11th Cir. 2012). Such injunctions are disfavored because they often run afoul\\nof Rule 65(d)’s requirement that injunctions state their terms specifically and\\n“describe in reasonable detail” the “act or acts restrained or required.” Fed. R. Civ.\\nP. 65(d). But here, the “obey-the-law” problem does not doom the IRS’s proposed\\ninjunction—the injunction plainly requires more of the Askins brothers than the\\nlaw requires of others, and where it does direct action consistent with the law, it\\ndoes so for specific provisions that the Askins brothers claim they already\\nunderstand.\\n Backing up, the specificity requirements in Rule 65(d) are “designed to\\nprevent uncertainty and confusion on the part of those faced with injunctive orders,\\nand to avoid the possible founding of a contempt citation on a decree too vague to\\nbe understood.” Goble, 682 F.3d at 950 (quoting Schmidt v. Lessard, 414 U.S.\\n473, 476 (1974) (per curiam)). An injunction “should clearly let [the] defendant\\nknow what he is ordered to do or not to do” and “should be phrased in terms of\\n\\n 22\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 23 of 24\\n\\n\\n\\nobjective actions, not legal conclusions.” Id. (quoting Planetary Motion, Inc. v.\\nTechsplosion, Inc., 261 F.3d 1188, 1203 (11th Cir. 2001)). A defendant “should\\n\\nonly be required to look within the four corners of the injunction to determine what\\nhe must do or refrain from doing.” Id. at 952 (internal quotation marks and citation\\nomitted). But the “degree of particularity required depends on the nature of the\\nsubject matter,” and “at times an injunction that orders a defendant to comply with\\na statute may be appropriate.” Id. at 950 (internal quotation marks and citation\\nomitted). That is the case where the statutory terms are specific and the defendant\\n\\nclearly knows what conduct is prohibited or required. Id. at 950–51 (citing\\nMcComb v. Jacksonville Paper Co., 336 U.S. 187 (1949)).\\n The IRS’s proposed injunction passes muster here based on the district\\ncourt’s own findings. The district court found that the “statutes with which\\nDefendants must comply are specific, and the record demonstrates that they are\\nwell aware of the conduct the proposed injunction addresses, their failure to remit\\nto the IRS taxes withheld from their employees.” Askins & Miller does not contest\\nits tax liabilities and has engaged with the IRS for the better part of a decade in the\\nIRS’s repeated efforts to ensure compliance. The district court also found that the\\nIRS demonstrated the defendants’ “proclivity for unlawful conduct,” which cuts in\\nfavor of a broad injunction. Cf. McComb, 336 U.S. at 192 (noting that broad\\ninjunctions “are often necessary to prevent further violations where a proclivity for\\nunlawful conduct has been shown”). Finally, the proposed injunction goes well\\nbeyond merely requiring compliance with the employment tax laws. In fact, it lists\\nnumerous concrete actions for the defendants to take—to name only a few,\\n\\n 23\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 24 of 24\\n\\n\\n\\nsegregating their funds, informing the IRS of any new business ventures, and filing\\nvarious periodic affidavits—well beyond what a simple “obey-the-law” injunction\\n\\nwould look like. In short, this case does not raise the sort of fair notice concerns\\nthat Rule 65(d) is designed to address.\\n V.\\n Because the district court erroneously imposed a categorical rule that\\nprevented a proper exercise of its broad equitable discretion, we vacate its order\\ndenying the IRS’s request for a preliminary injunction against the Defendants-\\n\\nAppellees. On remand, the district court should consider the collectability of a\\nfuture money judgment in determining whether that remedy is “adequate.” It\\nshould also consider any relevant factual developments that may affect the\\npropriety of the injunctive relief sought, including the defendants’ assertion that\\nAskins & Miller is no longer in business and the IRS’s contention that it may need\\nto seek additional injunctive relief in light of those developments. As we have\\nalready explained, this analysis is distinct from the mootness issue that we have\\naddressed. Apart from what we have already said, we express no opinion on\\nwhether an injunction is ultimately appropriate. Rather, we leave it for the district\\ncourt on remand to exercise its equitable discretion consistent with the principles in\\nthis opinion.\\nVACATED AND REMANDED.\\n\\n\\n\\n\\n 24\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4399765/\", \"author_raw\": \"GRANT, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"MARCUS"},"judge2":{"kind":"string","value":"GRANT"},"judge3":{"kind":"string","value":"HULL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4622512/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff-Appellant, v. ASKINS & MILLER ORTHOPAEDICS, P.A., Roland v. Askins, III, Philip H. Askins, Defendants-Appellees.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-23\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 18-11434 Date Filed: 05/23/2019 Page: 1 of 24\n\n\n [PUBLISH]\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 18-11434\n ________________________\n\n D.C. Docket No. 8:17-cv-00092-JDW-MAP\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff-Appellant,\n\n versus\n\nASKINS & MILLER ORTHOPAEDICS, P.A.,\nROLAND V. ASKINS, III,\nPHILIP H. ASKINS,\n\n Defendants-Appellees.\n ________________________\n\n Appeal from the United States District Court\n for the Middle District of Florida\n ________________________\n\n (May 23, 2019)\nBefore MARCUS, GRANT, and HULL, Circuit Judges.\nGRANT, Circuit Judge:\n\n The IRS says it needs a preliminary injunction against Askins & Miller\nOrthopaedics—a serial employment-tax delinquent—to ensure that it gets its due\nas taxes continue to pile up. It could just wait for nonpayment and later seek a\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 2 of 24\n\n\n\nmoney judgment, but if past is prologue, the money will be long gone before the\nIRS can collect. Given the alternative of a valid but potentially useless action for\n\ndamages, does the IRS necessarily have an “adequate” remedy at law that puts an\ninjunction out of the question? We conclude that it does not, so we vacate the\ndistrict court’s order denying injunctive relief and remand for further proceedings.\n I.\n The facts in this case tell a cyclical and monotonous story about the IRS’s\nyears-long battle against two brothers, but the long and short of it is this: Askins &\n\nMiller Orthopaedics habitually fails to pay its federal employment taxes, and the\ngovernment seeks injunctive relief to make sure it gets paid going forward.\n Askins & Miller is a Sarasota medical practice run by brothers Philip H.\nAskins and Roland V. Askins III. As an employer, Askins & Miller is required\nunder the tax laws to 1) withhold from its employees’ wages and pay over to the\nIRS federal income and Federal Insurance Contributions Act (FICA) taxes, and 2)\npay its own FICA taxes. These payments must be deposited in an appropriate\nfederal depository bank. But since 2010, Askins & Miller has repeatedly failed to\npay these taxes—both its own share of FICA taxes and the income and FICA taxes\nit has withheld from its employees—to the IRS. Askins & Miller does not dispute\nits tax liability; indeed, it has filed returns documenting it. It just fails, over and\nover again, to pay.\n The IRS has tried several collection strategies over the years. It started with\nan effort to achieve voluntary compliance: IRS representatives have spoken with\nthe Askins brothers “at least 34 times” since December 2010, including 27 in-\n\n 2\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 3 of 24\n\n\n\nperson meetings. Twice they entered into installment agreements that set up\nmonthly payments to bring Askins & Miller back into compliance, but the\n\ncompany defaulted both times. Two other times, they warned Askins & Miller that\ncontinued noncompliance could prompt the government to seek an injunction.\n The IRS has employed more aggressive means as well. It served levies on\n“approximately two dozen entities,” but most “responded by indicating that there\nwere no funds available to satisfy the levies.” Three entities paid some money, but\nnot nearly enough to satisfy Askins & Miller’s debts or to keep pace with its\n\naccrual of new liabilities. Additionally, the IRS’s ability to collect payments\nthrough levies has been hampered by the defendants’ attempts to hide Askins &\nMiller’s funds and to keep the balances in Askins & Miller’s accounts low.\nBetween 2014 and 2016, the Askins brothers transferred money from Askins &\nMiller to “RVA Trust,” which operates a private hunting club for the brothers, and\n“RVA Investments,” an accounting business associated with their father. The IRS\nalso discovered additional accounts at BankUnited and Stonegate Bank. It did not\nseek to levy RVA Trust, RVA Investments, or the bank accounts because it\ndiscovered them after this case had been referred to the Department of Justice and\nbecause the IRS believed that “there is a substantial risk that any new levy would\nresult in [the defendants] opening new undisclosed accounts and moving the\nmoney there.”\n Next up were the brothers’ personal assets: because the brothers ran Askins\n& Miller and were responsible for its failure to pay the taxes, the IRS “assessed\ntrust fund recovery penalties against Roland V. Askins III for tax periods in 2014–\n\n 3\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 4 of 24\n\n\n\n2016 and against Philip Askins for tax periods in 2009–2012 and 2014–2016.”\nTrust fund recovery penalties allow the IRS to hold a company’s officers\n\npersonally liable for the taxes withheld from employees’ wages—which belong to\nthe government and are merely held in trust by the company—when those officers\nwillfully fail to remit the employees’ taxes to the IRS. The IRS issued levies to\n“approximately 15 entities” associated with Roland, but only one entity made any\npayments; that source was enough “to satisfy current trust fund recovery penalties\nassessments [sic] against Roland,” but not enough “to keep pace with the rate at\n\nwhich the company” continued to accrue liabilities. The IRS levied\n“approximately six entities” for Philip, but after one paid less than $2,000, Philip\nclosed the account. The IRS does not believe the brothers have enough assets in\ntheir own names to cover the debts, and even if they did, trust fund recovery\npenalties cannot be used to cover Askins & Miller’s share of its own employment\ntaxes (as distinct from employees’ taxes that were withheld from their paychecks).\n The IRS “consistently” filed notices of federal tax liens, but this approach\nwas a nonstarter: liens “are only valuable insofar as a taxpayer has property against\nwhich the liens can be enforced,” and Askins & Miller “does not own any\nsubstantial property.” For the same reason, the IRS considered but decided not to\npursue asset seizure: the most promising target, a 2004 Cadillac worth $10,000,\nwas apparently not worth the effort.\n Feeling as if it had reached the end of its rope, the IRS sued Askins & Miller\nand both brothers in 2017. It asserted two counts: one for permanent injunctive\nrelief requiring Askins & Miller and the brothers to take specific steps to ensure\n\n 4\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 5 of 24\n\n\n\nthat future payments would be made before the brothers could divert the money,\nand another for damages to account for outstanding liabilities between 2010 and\n\n2015. Relying on a declaration from one of its revenue officers, the IRS asked the\ndistrict court to issue a preliminary injunction—largely mirroring the permanent\ninjunction that it sought in its complaint—designed to prevent Askins & Miller\nfrom incurring further tax liabilities while the litigation was still ongoing. But the\ndistrict court denied the motion without prejudice because it found the declaration\nconclusory, and because it thought the proposed injunction was “effectively an\n\n‘obey-the-law’ injunction.”\n Trying again, the IRS submitted a more detailed declaration and additional\nargument as to why the court should issue a preliminary injunction. It contended\nthat the proposed injunction was not an “obey-the-law” one and that it lacked an\nadequate remedy at law because all of its previous collection efforts had proven\nunsuccessful. The IRS also argued that because the company appeared to be\njudgment-proof, the money judgment it sought for past liabilities was likely\nmeaningless. But again, the court declined: although the court found that three of\nthe four factors for granting injunctive relief were “not seriously disputed,” it\ndenied an injunction because it concluded that the availability of an action for\ndamages was an adequate remedy at law and that the IRS therefore could not show\nirreparable harm. The court also suggested that the injunction, at least as drafted\nand proposed by the IRS, 1 was still, effectively, a disfavored “obey-the-law”\n\n1\n The proposed injunction included seven terms:\n\n\n\n 5\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 6 of 24\n\n\n\ninjunction. The IRS appealed. See 28 U.S.C. § 1292(a)(1) (allowing for\ninterlocutory appeal of orders denying an injunction). Since then, the district court\n\nhas granted summary judgment to the IRS on count two (the damages claim for\ntaxes between 2010 and 2015), but it deferred ruling on count one (the request for\na permanent injunction) because it concluded that the IRS’s appeal divested it of\njurisdiction over that count. 2\n\n\n (1) Defendants shall, for liabilities due on each employment tax return required to be\n filed after the date of the preliminary injunction, pay over to the IRS all income and\n Federal Insurance Contributions Act (“FICA”) taxes withheld from employees and\n Askins & Miller’s own share of FICA taxes (collectively, “employment taxes”);\n (2) Defendants shall segregate (i.e., hold separate and apart from all other funds) all\n employment taxes of employees of Askins & Miller and shall, on a semiweekly\n schedule, deposit them in an appropriate federal depository bank;\n (3) Defendants shall not transfer any money or property to any other entity—except a\n payroll processing company that is shown a copy of the injunction and is approved in\n advance by Revenue Officer Richard Paulsen (or another employee designated by the\n IRS)—to have that entity pay the salaries or wages of Askins & Miller’s employees.\n If Defendants employ an approved payroll processing company, all transfers shall\n include sufficient funds for the payroll processing company to make Askins &\n Miller’s federal tax deposits, and Defendants shall provide the payroll processing\n company with the authority and information necessary to make such deposits;\n (4) Except for use of a payroll processing company in accordance with paragraph three\n above, Defendants shall not assign any of Askins & Miller’s property or rights to\n Askins & Miller’s property or make any disbursements from Askins & Miller’s\n accounts before making all required deposits and paying all required outstanding\n liabilities due on each employment tax return required to be filed after the date of the\n preliminary injunction;\n (5) Defendants shall sign and deliver affidavits to the IRS at 5971 Cattleridge Boulevard,\n Suite 102-Mail Stop 5410, Sarasota, FL 34232, or to such other specific location as\n directed by the IRS, within two banking days after each employment tax deposit is\n due, stating that the requisite deposit was timely made;\n (6) Defendant Roland V. Askins III shall notify the IRS of any new company or business\n he may come to own or manage; and\n (7) Defendant Philip H. Askins shall notify the IRS of any new company or business he\n may come to own or manage.\n2\n The brothers did not materially dispute the IRS’s account of the facts before the district court,\nnor do they do so on appeal. They did (and do), however, contest the IRS’s characterizations of\n\n\n 6\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 7 of 24\n\n\n\n Meanwhile, the defendants’ delinquency continued: Askins & Miller racked\nup more liabilities in 2017 even after the IRS sued, and the district court found that\n\nthe defendants have “a proclivity for unlawful conduct” and are “likely to continue\nignoring” their tax obligations. In fact, other businesses associated with the\nbrothers—RVA Trust and Gulfcoast Surgery Center—also fell behind on their\nemployment taxes. The IRS represented to the district court that Askins & Miller\nwas “accumulating new employment tax liabilities faster than the IRS’s ability to\ncollect the outstanding obligations” and that its time spent playing cat-and-mouse\n\nover the years “constituted a substantial drain” on resources. Deeming an action\nfor damages a Sisyphean task in these circumstances, the IRS contends on appeal\nthat the district court should have granted a preliminary injunction because the IRS\nhas no “adequate” remedy at law.\n II.\n Section 7402(a) of the Internal Revenue Code grants federal district courts\nan array of powers to aid in enforcing the tax laws:\n\n\n\ntheir motivations and intent: in the brothers’ telling, it was bad business, not bad faith, that\ncaused them to fall behind. Specifically, Philip Askins submitted a declaration to the district\ncourt stating that Askins & Miller did not make “any decision never to pay withholding taxes,”\nthat Askins & Miller has “consistently reported all of its tax liabilities,” and that “extreme\nfinancial reversals and financial hardships” caused the business to fall behind on all of its debts.\nPhilip also claimed that Askins & Miller never “sought to hide or avoid it’s [sic] liabilities either\nto the IRS or to any of its other creditors” and that he had been truthful and open with the IRS.\nFinally, Philip claimed that a potential sale of another entity, Gulfcoast Surgery Center, was\nsupposed to provide the funds to bring Askins & Miller into compliance with all of its tax\nobligations, but the sale “unexpectedly” fell through. The district court did not explicitly resolve\nthese disputes in its order denying the government’s motion for a preliminary injunction, but it\ndid find that “the record demonstrates that Defendants have diverted and misappropriated” the\nemployment taxes withheld from their employees’ wages.\n 7\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 8 of 24\n\n\n The district courts of the United States at the instance of the United States\n shall have such jurisdiction to make and issue in civil actions, writs and\n orders of injunction, and of ne exeat republica, orders appointing receivers,\n and such other orders and processes, and to render such judgments and\n decrees as may be necessary or appropriate for the enforcement of the\n internal revenue laws. The remedies hereby provided are in addition to and\n not exclusive of any and all other remedies of the United States in such\n courts or otherwise to enforce such laws.\n\n26 U.S.C. § 7402(a). In analyzing this grant of injunctive power, we have said that\nthe “decision to issue an injunction under § 7402(a) is governed by the traditional\nfactors shaping the district court’s use of the equitable remedy.” United States v.\nErnst & Whinney, 735 F.2d 1296, 1301 (11th Cir. 1984).3 To obtain a preliminary\n\ninjunction under “the traditional factors,” the IRS must demonstrate 1) a\nsubstantial likelihood of success on the merits, 2) that it will suffer irreparable\ninjury unless the injunction is issued, 3) that the threatened injury to the IRS\noutweighs whatever harm the proposed injunction might cause the defendants, and\n\n3\n We note that there is some question over whether applying “the traditional factors” in § 7402(a)\ncases is the right approach. The statute’s “in addition to and not exclusive of” language could be\nread to suggest that the government need not show the lack of an adequate remedy at law, as\nwould normally be required under the traditional factors. See, e.g., United States v. Benson, 561\nF.3d 718, 727 n.4 (7th Cir. 2009); cf. United States v. First Nat’l City Bank, 379 U.S. 378, 383\n(1965) (“[O]ur review of the injunction as an exercise of the equity power granted by 26 U.S.C.\n§ 7402(a) must be in light of the public interest involved: ‘Courts of equity may, and frequently\ndo, go much farther both to give and withhold relief in furtherance of the public interest than\nthey are accustomed to go when only private interests are involved.’” (citation omitted)). But the\nIRS does not ask us to hold categorically that the adequate-remedy-at-law requirement is\ninapplicable in § 7402(a) cases, and at any rate we are bound by our precedent. See Ernst &\nWhinney, 735 F.2d at 1301; see also United States v. Cruz, 611 F.3d 880, 887 (11th Cir. 2010)\n(rejecting argument that courts should disregard equitable factors when issuing injunctions under\n§ 7407 and citing Ernst & Whinney); Klay v. United Healthgroup, Inc., 376 F.3d 1092, 1098–99\n(11th Cir. 2004) (recognizing some “statutory injunction” contexts where the traditional\nrequirements are relaxed, but citing Ernst & Whinney for the proposition that “several of our\ncases also suggest that, when Congress authorizes injunctive relief, it implicitly requires that the\ntraditional requirements for an injunction be met in addition to any elements explicitly specified\nin the statute”).\n 8\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 9 of 24\n\n\n\n4) that the injunction would not be adverse to the public interest. See Keeton v.\nAnderson-Wiley, 664 F.3d 865, 868 (11th Cir. 2011). We review for abuse of\n\ndiscretion a district court’s “ultimate decision of whether to grant a preliminary\ninjunction,” but we review de novo “determinations of law made by the district\ncourt en route” to that decision. Owner-Operator Indep. Drivers Ass’n, Inc. v.\nLandstar Sys., Inc., 622 F.3d 1307, 1323 (11th Cir. 2010) (internal quotation marks\nand citation omitted).\n III.\n\n Before reaching the merits, we face a preliminary question: whether\nsubsequent events have rendered this case (or at least portions of this case) moot.\nDuring the briefing, counsel for defendants filed a motion to withdraw because he\nwas not getting paid. In that motion, counsel asserted that Askins & Miller “is no\nlonger in business, has no employees, and has insufficient assets to ever resume\nbusiness in the future.” The first five of the seven items in the proposed\npreliminary injunction are premised on Askins & Miller’s continued viability.\nAlthough counsel withdrew the motion after the Askins brothers “made\nsatisfactory financial arrangements,” we asked the parties to address whether\nAskins & Miller is “still incurring tax liabilities that the proposed preliminary\ninjunction would address” and how the answer to that question should affect our\ndisposition of the case.\n “Whether a case is moot is a question of law that we review de novo.”\nSheely v. MRI Radiology Network, P.A., 505 F.3d 1173, 1182 (11th Cir. 2007). A\n“case is moot when it no longer presents a live controversy with respect to which\n\n 9\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 10 of 24\n\n\n\nthe court can give meaningful relief.” Id. at 1183 (quoting Troiano v. Supervisor\nof Elections, 382 F.3d 1276, 1282 (11th Cir. 2004)). But an “important exception”\n\nto this “general rule” exists in cases of “voluntary cessation”—that is, where a\ndefendant voluntarily puts an end to his offensive conduct. Id. In such cases, it is\n“well settled” that the defendant’s voluntary cessation does not automatically moot\nthe case; rather, a case “might become moot if subsequent events made it\nabsolutely clear that the allegedly wrongful behavior could not reasonably be\nexpected to recur.” Friends of the Earth, Inc. v. Laidlaw Envtl. Servs. (TOC), Inc.,\n\n528 U.S. 167, 189 (2000) (internal quotation marks and citation omitted). This\n“stringent” standard imposes a “heavy” and “formidable” burden on the party\nasserting mootness—here, the Askins brothers. Id. at 189–90. To carry this\n“heavy” burden, we require more than a private party’s assertion that its challenged\nconduct will not recur. See Sheely, 505 F.3d at 1184.\n Based on the undisputed factual record, Askins & Miller’s possible closure\ndid not moot the IRS’s claim for injunctive relief. The Supreme Court has made\nclear that the voluntary cessation standard applies where a business entity’s closure\nis alleged to have mooted the case. See Laidlaw, 528 U.S. at 193. In conducting\nthe voluntary cessation analysis, we have previously identified “at least” three\nrelevant factors: “(1) whether the challenged conduct was isolated or unintentional,\nas opposed to a continuing and deliberate practice; (2) whether the defendant’s\ncessation of the offending conduct was motivated by a genuine change of heart or\ntimed to anticipate suit; and (3) whether, in ceasing the conduct, the defendant has\nacknowledged liability.” Sheely, 505 F.3d at 1184. Applying those factors here—\n\n 10\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 11 of 24\n\n\n\nin light of the history of the case and the undisputed conduct of the defendants—\nwe find it far from “absolutely clear that the allegedly wrongful behavior could not\n\nreasonably be expected to recur.” Laidlaw, 528 U.S. at 189 (internal quotation\nmarks and citation omitted).\n First, we consider “whether the challenged conduct was isolated or\nunintentional, as opposed to a continuing and deliberate practice.” Sheely, 505\nF.3d at 1184. The defendants’ failure to pay their federal employment taxes has\nbeen “a continuing and deliberate practice” for the better part of a decade. Far\n\nfrom “isolated or unintentional,” the defendants’ routine failure to pay their\nemployment taxes since 2010—despite withholding the money from their\nemployees, and despite repeated interventions from the IRS—appears to have been\ntheir method of doing business. And although the defendants attribute that routine\nfailure to bad business rather than bad faith, their professed intentions wane in the\nshadow of their undisputed history. Similarly, considering the record, we put little\nweight on Askins & Miller’s (unsupported) eleventh-hour assurances that the\nbusiness is gone for good. Indeed, we have repeatedly said that a “defendant’s\nassertion that it has no intention of reinstating the challenged practice ‘does not\nsuffice to make a case moot’ and is but ‘one of the factors to be considered in\ndetermining the appropriateness of granting an injunction against the now-\ndiscontinued acts.’” Id. (quoting United States v. W.T. Grant Co., 345 U.S. 629,\n\n\n\n\n 11\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 12 of 24\n\n\n\n633 (1953)). And, again, we require more than a private party’s unsupported\nassertions—especially here, given the history of this case.\n\n Second, we ask “whether the defendant’s cessation of the offending conduct\nwas motivated by a genuine change of heart or timed to anticipate suit.” Id. Here,\nthe timing of Askins & Miller’s possible closure is more indicative of a changed\ntax-avoidance strategy than a changed heart. We have previously expressed\nskepticism where changed circumstances come on the eve of a significant decision\npoint in litigation. See id. at 1187 n.13 (defendant applied “new policy” shortly\n\nbefore summary judgment motion); see also id. at 1186 (collecting cases). Here,\nAskins & Miller claims to have closed down while this case was on appeal.\nSignificantly, the undisputed facts in the record demonstrate that it would be\nsimple to reopen at a moment’s notice: back in November 2015, while the IRS was\nstill experimenting with different collection strategies, “the company submitted a\nfinancial statement” reflecting “no investments, no accounts or notes receivable, no\nreal estate, and no business equipment.” Despite that lack of assets, the company\ncontinued in business until at least mid-2018. The record further demonstrates the\ndefendants’ history of moving money around from entity to entity. Even taking the\ndefendants at their word, one of the brothers “has continued his practice\nincorporated as Roland V. Askins, III, M.D., P.A.,” and their attorney represented\nat oral argument that although Askins & Miller is out of business “as a practical\nmatter” (whatever that may mean), the corporation “continues to exist” and “hasn’t\nbeen formally dissolved.” Those admissions only underscore the ease with which\nthe brothers could revive Askins & Miller. In light of the record evidence, the\n\n 12\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 13 of 24\n\n\n\ndefendants’ claim that they have “insufficient assets to ever resume business in the\nfuture” rings hollow.\n\n Third, we look to “whether, in ceasing the conduct, the defendant has\nacknowledged liability.” Id. at 1184. Although the defendants here have not\ndisputed their past tax debt—the district court entered a money damages judgment\nfor past-due employment taxes, and Askins & Miller filed tax returns admitting its\nliabilities—that is cold comfort given the history of this case, in which Askins &\nMiller has demonstrated a pattern of admitting liability but refusing to pay. The\n\nIRS’s proposed relief is designed to prevent Askins & Miller from dodging its\nadmitted tax liabilities going forward. Because the record amply demonstrates a\npattern of Askins & Miller pairing its admitted liability with a refusal to pay, the\nfact that it still admits its liability does not convince us that it is “absolutely clear\nthat the allegedly wrongful behavior could not reasonably be expected to recur.”\nLaidlaw, 528 U.S. at 189 (internal quotation marks and citation omitted).\n Given the undisputed facts before us, we do not believe that the defendants\ncan satisfy their “heavy” and “formidable” burden of making it “absolutely clear”\nthat their behavior will not recur. And “we are unpersuaded that a remand would\nfurther the expeditious resolution of the matter.” Sheely, 505 F.3d at 1188 n.15\n(conducting mootness analysis without remanding for further fact finding). The\ndistrict court already concluded that the defendants have “a proclivity for unlawful\nconduct” and are “likely to continue ignoring” their tax obligations. The record\ndemonstrates a near-decade-long saga in which the IRS has pursued Askins &\nMiller time and again. Over that time span, the defendants have funneled money\n\n 13\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 14 of 24\n\n\n\nto new accounts and entities as the IRS closed in on the old ones. For at least the\ntime between November 2015 and mid-2018, Askins & Miller continued as a\n\ngoing concern despite reporting “no investments, no accounts or notes receivable,\nno real estate, and no business equipment.” Against that backdrop—and in light of\nthe defendants’ admissions that Askins & Miller “continues to exist” and that one\nof the brothers continues to practice medicine—“we can discern no reason for\nsending the question of mootness back to the district court for further review or\nfact finding.” Id.\n\n We emphasize that our decision that the case is not moot does not resolve\nwhether Askins & Miller’s possible closure makes injunctive relief inappropriate\non the merits. That is due to the differences between the standard for mootness\ndue to voluntary cessation and the standard for granting injunctive relief. For a\ncase to be moot under the voluntary cessation doctrine, the party asserting\nmootness—here, the defendants—bears the burden to convince a court that\n“subsequent events made it absolutely clear that the allegedly wrongful behavior\ncould not reasonably be expected to recur.” Laidlaw, 528 U.S. at 189 (internal\nquotation marks and citation omitted). By contrast, to obtain an injunction, the\nplaintiff must “establish by a preponderance of the evidence that this form of\nequitable relief is necessary.” Sheely, 505 F.3d at 1182 n.10. Because “the two\ninquiries are strikingly different”—both as to who bears the burden and as to what\nthat burden is—it follows that “[e]ven though a case is not moot, that does not\nmean that injunctive relief follows automatically.” Id. The analyses may\n“overlap[]” because “both are concerned with the likelihood of future unlawful\n\n 14\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 15 of 24\n\n\n\nconduct,” but as we have explained, the answers may well turn out to be different.\nId. Our analysis here answers the mootness question, but we leave it to the district\n\ncourt on remand to answer the merits question.\n IV.\n Assured of our jurisdiction, we turn to the merits. We conclude that neither\nthe adequate-remedy-at-law requirement nor Rule 65(d) should have precluded\ninjunctive relief on the facts here.\n A. Adequate Remedy at Law\n\n The district court determined that three out of the four “traditional factors”\ngoverning the propriety of injunctive relief—likelihood of success on the merits,\nthe balance of harms, and the public interest—were “not seriously disputed by\nDefendants.” But it denied injunctive relief because it concluded that the IRS had\nan adequate remedy at law: a suit for money damages after Askins & Miller failed\nto pay its taxes. We disagree. On these facts, the IRS’s ability to sit on its hands\nuntil the defendants fail to pay their taxes (again) and only then bring an action for\nmoney damages does not qualify as an “adequate” legal remedy.\n Our prior cases do not answer the question presented here. We have said\nbefore that § 7402(a)’s language “encompasses a broad range of powers necessary\nto compel compliance with the tax laws.” Ernst & Whinney, 735 F.2d at 1300.\nAnd we have also emphasized that in any given case under § 7402(a) a court must\nlook to “the traditional factors shaping the district court’s use of the equitable\nremedy,” and that “[f]oremost among the principles governing the use of the\ninjunctive remedy is the traditional requirement ‘that courts of equity should not\n\n 15\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 16 of 24\n\n\n\nact . . . when the moving party has an adequate remedy at law and will not suffer\nirreparable injury if denied equitable relief.’” Id. at 1301 & n.11 (quoting Younger\n\nv. Harris, 401 U.S. 37, 43–44 (1971)). We left it to the district court in that case to\n“examine the extent to which [the IRS’s] interests are protected by available legal\nremedies.” Id. And our past precedents on adequate legal remedies do not\nsquarely resolve the issue in this case: whether the collectability of a future money\njudgment to cure an expected future injury matters. See, e.g., Ne. Fla. Chapter of\nthe Ass’n of Gen. Contractors of Am. v. City of Jacksonville, 896 F.2d 1283, 1285\n\n(11th Cir. 1990) (stating broadly that an injury is irreparable “only if it cannot be\nundone through monetary remedies”). But see, e.g., Scott v. Roberts, 612 F.3d\n1279, 1294–95 (11th Cir. 2010) (discussing situations where an injury is\nirreparable even though “a later money judgment might undo” it); Levi Strauss &\nCo. v. Sunrise Int’l Trading Inc., 51 F.3d 982, 986 (11th Cir. 1995) (stating that\ntrademark infringement causes irreparable harm, even though the trademark holder\nwas also seeking monetary damages); Fla. Businessmen for Free Enter. v. City of\nHollywood, 648 F.2d 956, 958 n.2 (5th Cir. Unit B June 1981) (stating that lost\nprofits may amount to irreparable injury if they are “difficult or impossible to\ncalculate”).\n Addressing that issue now, we can see that the collectability of a future\nmoney judgment to redress future harms is relevant in determining whether legal\nremedies are “adequate” such that they preclude injunctive relief under § 7402(a).\nThe very nature of equitable power—the thing that distinguishes it from law—is its\nflexible and discretionary nature, its ability to respond to real-world practicalities,\n\n 16\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 17 of 24\n\n\n\nand its general aversion to rules that let bad actors capitalize on legal technicalities.\nSee, e.g., Roscoe Pound, The Decadence of Equity, 5 Colum. L. Rev. 20 (1905).\n\n Equity courts have long recognized “extraordinary circumstances,”\nincluding the likelihood that a defendant will never pay, as one way to “give rise to\nthe irreparable harm necessary for a preliminary injunction.” 11A Charles Alan\nWright & Arthur Miller, Federal Practice and Procedure § 2948.1 (3d ed. 2013);\nsee also Ernst & Whinney, 735 F.2d at 1301 (citing Wright & Miller for its\n“general discussion of equitable principles governing [the] injunctive remedy”).\n\nMore specifically, “most courts sensibly conclude that a damage judgment against\nan insolvent defendant is an inadequate remedy.” Douglas Laycock, The Death of\nthe Irreparable Injury Rule, 103 Harv. L. Rev. 687, 716 (1990); see also, e.g.,\nLakeview Tech., Inc. v. Robinson, 446 F.3d 655, 657 (7th Cir. 2006) (noting that\nthe “[a]bility to calculate damages” does not make a remedy adequate “if the\nplaintiff cannot collect the award”).4\n\n Indeed, the Supreme Court long ago stressed the practical nature of the\nequitable inquiry, stating that it “is not enough that there is a remedy at law; it must\nbe plain and adequate, or in other words, as practical and as efficient to the ends of\n\njustice and its prompt administration, as the remedy in equity.” Boyce’s Ex’rs v.\nGrundy, 28 U.S. (3 Pet.) 210, 215 (1830). The district court’s categorical rule that\n\n\n4\n The IRS also points to district court cases purportedly granting injunctions in circumstances\nsimilar to this case, but we place little weight on them. First, the IRS concedes that many of\nthese cases were the result of default or consent orders, so their propriety may not have been\nsubject to the sort of vigorous litigation that would give them persuasive value. Second, the\nrelevance of out-of-circuit cases is further watered down by the fact that some courts—unlike\nthis Court—have not held injunctions under § 7402(a) to the traditional equitable requirements.\n 17\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 18 of 24\n\n\n\na case involving calculable money damages can never warrant injunctive relief,\nregardless of a plaintiff’s ability to collect on a future judgment, is discordant with\n\nthe history and purposes of equity jurisprudence.\n The fact that the IRS is attempting to avoid future losses is key. As the IRS\nnotes, it “is an involuntary creditor; it does not make a decision to extend credit.”\nIn re Haas, 31 F.3d 1081, 1088 (11th Cir. 1994). As long as the brothers continue\nto accrue employment taxes, the IRS continues to lose money. This sets the IRS\napart from the position of other creditors (who can cut their losses by refusing to\n\nextend additional credit), and—crucially—means that the injunction sought is not\nsimply an attempt to provide security for past debts. Rather, the proposed\ninjunction here would staunch the flow of ongoing future losses as the brothers\ncontinue to accumulate tax liabilities—unlike in cases where the loss has already\nbeen inflicted or would be attributable to a single event, where we have stated that\ninjuries are irreparable only when they “cannot be undone through monetary\nremedies.” E.g., Scott, 612 F.3d at 1295 (quoting Cunningham v. Adams, 808 F.2d\n815, 821 (11th Cir. 1987)).\n Indeed, the record and the district court’s own findings demonstrate that the\ngovernment’s proposed injunctive relief is “appropriate for the enforcement of the\ninternal revenue laws,” 26 U.S.C. § 7402(a), and that the government will likely\nsuffer irreparable injury absent an injunction. Among other things, the district\ncourt noted that Askins & Miller had “a proclivity for unlawful conduct,” had\n“diverted and misappropriated” the employment taxes it had withheld from its\nemployees’ wages, and was “likely to continue ignoring” its employment tax\n\n 18\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 19 of 24\n\n\n\nobligations. The IRS’s declaration demonstrates that, over a period of several\nyears, it expended considerable resources making numerous—and unsuccessful—\n\nattempts to collect Askins & Miller’s unpaid taxes. And in the face of all that, as\nthe declaration explained, Askins & Miller is effectively judgment-proof. In short,\nthe record amply demonstrates that, absent the requested injunction, the\ngovernment will continue to suffer harm from Askins & Miller’s willful and\ncontinuing failure to comply with its employment tax obligations—including lost\ntax revenue and the expenditure of a disproportionate amount of its resources\n\nmonitoring Askins & Miller and attempting to bring it into compliance—and that,\nin all likelihood, the government will never recoup these losses.\n The district court relied primarily on our decision in Rosen v. Cascade\nInternational, Inc., 21 F.3d 1520 (11th Cir. 1994), but Rosen is an uncomfortable\nfit here. As background, shareholders in that case brought a suit for money\ndamages against a company and its officers because of alleged securities fraud. Id.\nat 1522. To ensure that the defendants would be able to satisfy any money\njudgment ultimately obtained in the litigation, the district court entered a\npreliminary injunction freezing the assets of one of the defendants. Id. On appeal,\nwe held that the district court lacked authority to enter that injunction because\n“cases in which the remedy sought is the recovery of money damages do not fall\nwithin the jurisdiction of equity,” and as a general rule of federal equity, “a court\nmay not reach a defendant’s assets unrelated to the underlying litigation and freeze\nthem so that they may be preserved to satisfy a potential money judgment.” Id. at\n1527 (internal quotation marks and citation omitted). We also noted that a request\n\n 19\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 20 of 24\n\n\n\nfor prejudgment attachment under Federal Rule of Civil Procedure 64, rather than a\nmotion for a preliminary injunction under Rule 65, provided the appropriate means\n\nto seek an asset freeze. Id. at 1530–31. Looking to state law (as the Rule\nrequires), we concluded that the plaintiffs had not shown that they were entitled to\nRule 64 relief. Id.\n The differences between that case and this one announce themselves rather\nclearly. Rosen asked “whether a district court has the power to enter a preliminary\ninjunction freezing the assets of a defendant before trial in a case where the\n\nplaintiffs ultimately seek only money damages.” Id. at 1526 (emphasis added).\nThat damages-only fact was front and center: we explained that a preliminary\ninjunction is appropriate only where it seeks relief of the “same character” as the\nfinal relief sought, and that the asset freeze in that case was not of the same\ncharacter as the ultimate relief because the plaintiffs there “sought only the award\nof monetary damages—and not equitable relief.” Id. at 1527, 1529 (internal\nquotation marks and citation omitted); accord Grupo Mexicano de Desarrollo, S.A.\nv. Alliance Bond Fund, Inc., 527 U.S. 308 (1999); Mitsubishi Int’l Corp. v.\nCardinal Textile Sales, Inc., 14 F.3d 1507 (11th Cir. 1994).\n Here, in contrast, the IRS’s complaint asked for a permanent injunction\nproviding prospective equitable relief for anticipated future violations—the same\nrelief sought by the preliminary injunction at issue. Indeed, we have already held\nthat Rosen does not apply where the complaint itself seeks a permanent injunction.\nLevi Strauss & Co., 51 F.3d at 987; see also SEC v. ETS Payphones, Inc., 408 F.3d\n727, 734 (11th Cir. 2005) (per curiam) (holding that Grupo Mexicano does not\n\n 20\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 21 of 24\n\n\n\napply where the complaint seeks equitable relief). As Rosen itself was careful to\nnote, a preliminary injunction “is always appropriate to grant intermediate relief of\n\nthe same character as that which may be granted finally.” Rosen, 21 F.3d at 1527\n(quoting De Beers Consol. Mines v. United States, 325 U.S. 212, 220 (1945)). 5\n What’s more—and contrary to the district court’s reading—nothing in Rosen\n\nsuggests that the IRS has not shown an irreparable injury for purposes of a\npreliminary injunction. The Rosen court’s statement that the “test of the\ninadequacy of a remedy at law is whether a judgment could be obtained, not\nwhether, once obtained it will be collectible,” 21 F.3d at 1531 (quoting St.\nLawrence Co., N.V. v. Alkow Realty, Inc., 453 So. 2d 514, 514–15 (Fla. Dist. Ct.\nApp. 1984)), was made in the context of a Rule 64 analysis relating to prejudgment\n\nattachment. As we have said, Rule 64 looks to the law of the state in which the\ncourt sits. See Fed. R. Civ. P. 64(a). So this statement in Rosen merely described\nFlorida law governing prejudgment attachment; it did not determine (or even\ndescribe) federal equitable power.\n\n\n\n\n5\n We also note that, for at least a portion of the employment taxes at issue, the assets that the\ninjunction would reach are not “unrelated”—indeed, they do not even wholly belong to the\ndefendants—because when an employer withholds employees’ taxes, the withheld money is held\nin trust for the United States. See Thibodeau v. United States, 828 F.2d 1499, 1506 (11th Cir.\n1987) (per curiam). So at least for this portion of the taxes, the IRS has an equitable interest that\nmight qualify it for relief analogous to the “creditor’s bill” recognized in English courts of\nequity. See Grupo Mexicano, 527 U.S. at 319–20 & n.5 (“Some cases suggested that there was\nan exception [to the requirement that a judgment be obtained before bringing a creditor’s bill]\nwhere the debt was admitted or confessed, at least if the creditor possessed an interest in the\ndebtor’s property.”).\n 21\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 22 of 24\n\n\n\n In sum, the district court erred in applying a categorical rule that because tax\nliability may be calculated and sought in an action for damages, it necessarily\n\nprecludes injunctive relief under § 7402(a).\n B. Rule 65(d)\n The district court also suggested that “the United States’ proposed injunction\nwould be unenforceable” as an overbroad “obey-the-law” injunction. It is true that\nwe have “questioned the enforceability of obey-the-law injunctions” because “they\nlack specificity and deprive defendants of the procedural protections that would\n\nordinarily accompany a future charge of a violation.” SEC v. Goble, 682 F.3d 934,\n949 (11th Cir. 2012). Such injunctions are disfavored because they often run afoul\nof Rule 65(d)’s requirement that injunctions state their terms specifically and\n“describe in reasonable detail” the “act or acts restrained or required.” Fed. R. Civ.\nP. 65(d). But here, the “obey-the-law” problem does not doom the IRS’s proposed\ninjunction—the injunction plainly requires more of the Askins brothers than the\nlaw requires of others, and where it does direct action consistent with the law, it\ndoes so for specific provisions that the Askins brothers claim they already\nunderstand.\n Backing up, the specificity requirements in Rule 65(d) are “designed to\nprevent uncertainty and confusion on the part of those faced with injunctive orders,\nand to avoid the possible founding of a contempt citation on a decree too vague to\nbe understood.” Goble, 682 F.3d at 950 (quoting Schmidt v. Lessard, 414 U.S.\n473, 476 (1974) (per curiam)). An injunction “should clearly let [the] defendant\nknow what he is ordered to do or not to do” and “should be phrased in terms of\n\n 22\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 23 of 24\n\n\n\nobjective actions, not legal conclusions.” Id. (quoting Planetary Motion, Inc. v.\nTechsplosion, Inc., 261 F.3d 1188, 1203 (11th Cir. 2001)). A defendant “should\n\nonly be required to look within the four corners of the injunction to determine what\nhe must do or refrain from doing.” Id. at 952 (internal quotation marks and citation\nomitted). But the “degree of particularity required depends on the nature of the\nsubject matter,” and “at times an injunction that orders a defendant to comply with\na statute may be appropriate.” Id. at 950 (internal quotation marks and citation\nomitted). That is the case where the statutory terms are specific and the defendant\n\nclearly knows what conduct is prohibited or required. Id. at 950–51 (citing\nMcComb v. Jacksonville Paper Co., 336 U.S. 187 (1949)).\n The IRS’s proposed injunction passes muster here based on the district\ncourt’s own findings. The district court found that the “statutes with which\nDefendants must comply are specific, and the record demonstrates that they are\nwell aware of the conduct the proposed injunction addresses, their failure to remit\nto the IRS taxes withheld from their employees.” Askins & Miller does not contest\nits tax liabilities and has engaged with the IRS for the better part of a decade in the\nIRS’s repeated efforts to ensure compliance. The district court also found that the\nIRS demonstrated the defendants’ “proclivity for unlawful conduct,” which cuts in\nfavor of a broad injunction. Cf. McComb, 336 U.S. at 192 (noting that broad\ninjunctions “are often necessary to prevent further violations where a proclivity for\nunlawful conduct has been shown”). Finally, the proposed injunction goes well\nbeyond merely requiring compliance with the employment tax laws. In fact, it lists\nnumerous concrete actions for the defendants to take—to name only a few,\n\n 23\n\f Case: 18-11434 Date Filed: 05/23/2019 Page: 24 of 24\n\n\n\nsegregating their funds, informing the IRS of any new business ventures, and filing\nvarious periodic affidavits—well beyond what a simple “obey-the-law” injunction\n\nwould look like. In short, this case does not raise the sort of fair notice concerns\nthat Rule 65(d) is designed to address.\n V.\n Because the district court erroneously imposed a categorical rule that\nprevented a proper exercise of its broad equitable discretion, we vacate its order\ndenying the IRS’s request for a preliminary injunction against the Defendants-\n\nAppellees. On remand, the district court should consider the collectability of a\nfuture money judgment in determining whether that remedy is “adequate.” It\nshould also consider any relevant factual developments that may affect the\npropriety of the injunctive relief sought, including the defendants’ assertion that\nAskins & Miller is no longer in business and the IRS’s contention that it may need\nto seek additional injunctive relief in light of those developments. As we have\nalready explained, this analysis is distinct from the mootness issue that we have\naddressed. Apart from what we have already said, we express no opinion on\nwhether an injunction is ultimately appropriate. Rather, we leave it for the district\ncourt on remand to exercise its equitable discretion consistent with the principles in\nthis opinion.\nVACATED AND REMANDED.\n\n\n\n\n 24\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff-Appellant, v. ASKINS & MILLER ORTHOPAEDICS, P.A., Roland v. Askins, III, Philip H. Askins, Defendants-Appellees.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-23\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 18-11434 Date Filed: 05/23/2019 Page: 1 of 24\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 18-11434\\n ________________________\\n\\n D.C. Docket No. 8:17-cv-00092-JDW-MAP\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff-Appellant,\\n\\n versus\\n\\nASKINS & MILLER ORTHOPAEDICS, P.A.,\\nROLAND V. ASKINS, III,\\nPHILIP H. ASKINS,\\n\\n Defendants-Appellees.\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Middle District of Florida\\n ________________________\\n\\n (May 23, 2019)\\nBefore MARCUS, GRANT, and HULL, Circuit Judges.\\nGRANT, Circuit Judge:\\n\\n The IRS says it needs a preliminary injunction against Askins & Miller\\nOrthopaedics—a serial employment-tax delinquent—to ensure that it gets its due\\nas taxes continue to pile up. It could just wait for nonpayment and later seek a\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 2 of 24\\n\\n\\n\\nmoney judgment, but if past is prologue, the money will be long gone before the\\nIRS can collect. Given the alternative of a valid but potentially useless action for\\n\\ndamages, does the IRS necessarily have an “adequate” remedy at law that puts an\\ninjunction out of the question? We conclude that it does not, so we vacate the\\ndistrict court’s order denying injunctive relief and remand for further proceedings.\\n I.\\n The facts in this case tell a cyclical and monotonous story about the IRS’s\\nyears-long battle against two brothers, but the long and short of it is this: Askins &\\n\\nMiller Orthopaedics habitually fails to pay its federal employment taxes, and the\\ngovernment seeks injunctive relief to make sure it gets paid going forward.\\n Askins & Miller is a Sarasota medical practice run by brothers Philip H.\\nAskins and Roland V. Askins III. As an employer, Askins & Miller is required\\nunder the tax laws to 1) withhold from its employees’ wages and pay over to the\\nIRS federal income and Federal Insurance Contributions Act (FICA) taxes, and 2)\\npay its own FICA taxes. These payments must be deposited in an appropriate\\nfederal depository bank. But since 2010, Askins & Miller has repeatedly failed to\\npay these taxes—both its own share of FICA taxes and the income and FICA taxes\\nit has withheld from its employees—to the IRS. Askins & Miller does not dispute\\nits tax liability; indeed, it has filed returns documenting it. It just fails, over and\\nover again, to pay.\\n The IRS has tried several collection strategies over the years. It started with\\nan effort to achieve voluntary compliance: IRS representatives have spoken with\\nthe Askins brothers “at least 34 times” since December 2010, including 27 in-\\n\\n 2\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 3 of 24\\n\\n\\n\\nperson meetings. Twice they entered into installment agreements that set up\\nmonthly payments to bring Askins & Miller back into compliance, but the\\n\\ncompany defaulted both times. Two other times, they warned Askins & Miller that\\ncontinued noncompliance could prompt the government to seek an injunction.\\n The IRS has employed more aggressive means as well. It served levies on\\n“approximately two dozen entities,” but most “responded by indicating that there\\nwere no funds available to satisfy the levies.” Three entities paid some money, but\\nnot nearly enough to satisfy Askins & Miller’s debts or to keep pace with its\\n\\naccrual of new liabilities. Additionally, the IRS’s ability to collect payments\\nthrough levies has been hampered by the defendants’ attempts to hide Askins &\\nMiller’s funds and to keep the balances in Askins & Miller’s accounts low.\\nBetween 2014 and 2016, the Askins brothers transferred money from Askins &\\nMiller to “RVA Trust,” which operates a private hunting club for the brothers, and\\n“RVA Investments,” an accounting business associated with their father. The IRS\\nalso discovered additional accounts at BankUnited and Stonegate Bank. It did not\\nseek to levy RVA Trust, RVA Investments, or the bank accounts because it\\ndiscovered them after this case had been referred to the Department of Justice and\\nbecause the IRS believed that “there is a substantial risk that any new levy would\\nresult in [the defendants] opening new undisclosed accounts and moving the\\nmoney there.”\\n Next up were the brothers’ personal assets: because the brothers ran Askins\\n& Miller and were responsible for its failure to pay the taxes, the IRS “assessed\\ntrust fund recovery penalties against Roland V. Askins III for tax periods in 2014–\\n\\n 3\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 4 of 24\\n\\n\\n\\n2016 and against Philip Askins for tax periods in 2009–2012 and 2014–2016.”\\nTrust fund recovery penalties allow the IRS to hold a company’s officers\\n\\npersonally liable for the taxes withheld from employees’ wages—which belong to\\nthe government and are merely held in trust by the company—when those officers\\nwillfully fail to remit the employees’ taxes to the IRS. The IRS issued levies to\\n“approximately 15 entities” associated with Roland, but only one entity made any\\npayments; that source was enough “to satisfy current trust fund recovery penalties\\nassessments [sic] against Roland,” but not enough “to keep pace with the rate at\\n\\nwhich the company” continued to accrue liabilities. The IRS levied\\n“approximately six entities” for Philip, but after one paid less than $2,000, Philip\\nclosed the account. The IRS does not believe the brothers have enough assets in\\ntheir own names to cover the debts, and even if they did, trust fund recovery\\npenalties cannot be used to cover Askins & Miller’s share of its own employment\\ntaxes (as distinct from employees’ taxes that were withheld from their paychecks).\\n The IRS “consistently” filed notices of federal tax liens, but this approach\\nwas a nonstarter: liens “are only valuable insofar as a taxpayer has property against\\nwhich the liens can be enforced,” and Askins & Miller “does not own any\\nsubstantial property.” For the same reason, the IRS considered but decided not to\\npursue asset seizure: the most promising target, a 2004 Cadillac worth $10,000,\\nwas apparently not worth the effort.\\n Feeling as if it had reached the end of its rope, the IRS sued Askins & Miller\\nand both brothers in 2017. It asserted two counts: one for permanent injunctive\\nrelief requiring Askins & Miller and the brothers to take specific steps to ensure\\n\\n 4\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 5 of 24\\n\\n\\n\\nthat future payments would be made before the brothers could divert the money,\\nand another for damages to account for outstanding liabilities between 2010 and\\n\\n2015. Relying on a declaration from one of its revenue officers, the IRS asked the\\ndistrict court to issue a preliminary injunction—largely mirroring the permanent\\ninjunction that it sought in its complaint—designed to prevent Askins & Miller\\nfrom incurring further tax liabilities while the litigation was still ongoing. But the\\ndistrict court denied the motion without prejudice because it found the declaration\\nconclusory, and because it thought the proposed injunction was “effectively an\\n\\n‘obey-the-law’ injunction.”\\n Trying again, the IRS submitted a more detailed declaration and additional\\nargument as to why the court should issue a preliminary injunction. It contended\\nthat the proposed injunction was not an “obey-the-law” one and that it lacked an\\nadequate remedy at law because all of its previous collection efforts had proven\\nunsuccessful. The IRS also argued that because the company appeared to be\\njudgment-proof, the money judgment it sought for past liabilities was likely\\nmeaningless. But again, the court declined: although the court found that three of\\nthe four factors for granting injunctive relief were “not seriously disputed,” it\\ndenied an injunction because it concluded that the availability of an action for\\ndamages was an adequate remedy at law and that the IRS therefore could not show\\nirreparable harm. The court also suggested that the injunction, at least as drafted\\nand proposed by the IRS, 1 was still, effectively, a disfavored “obey-the-law”\\n\\n1\\n The proposed injunction included seven terms:\\n\\n\\n\\n 5\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 6 of 24\\n\\n\\n\\ninjunction. The IRS appealed. See 28 U.S.C. § 1292(a)(1) (allowing for\\ninterlocutory appeal of orders denying an injunction). Since then, the district court\\n\\nhas granted summary judgment to the IRS on count two (the damages claim for\\ntaxes between 2010 and 2015), but it deferred ruling on count one (the request for\\na permanent injunction) because it concluded that the IRS’s appeal divested it of\\njurisdiction over that count. 2\\n\\n\\n (1) Defendants shall, for liabilities due on each employment tax return required to be\\n filed after the date of the preliminary injunction, pay over to the IRS all income and\\n Federal Insurance Contributions Act (“FICA”) taxes withheld from employees and\\n Askins & Miller’s own share of FICA taxes (collectively, “employment taxes”);\\n (2) Defendants shall segregate (i.e., hold separate and apart from all other funds) all\\n employment taxes of employees of Askins & Miller and shall, on a semiweekly\\n schedule, deposit them in an appropriate federal depository bank;\\n (3) Defendants shall not transfer any money or property to any other entity—except a\\n payroll processing company that is shown a copy of the injunction and is approved in\\n advance by Revenue Officer Richard Paulsen (or another employee designated by the\\n IRS)—to have that entity pay the salaries or wages of Askins & Miller’s employees.\\n If Defendants employ an approved payroll processing company, all transfers shall\\n include sufficient funds for the payroll processing company to make Askins &\\n Miller’s federal tax deposits, and Defendants shall provide the payroll processing\\n company with the authority and information necessary to make such deposits;\\n (4) Except for use of a payroll processing company in accordance with paragraph three\\n above, Defendants shall not assign any of Askins & Miller’s property or rights to\\n Askins & Miller’s property or make any disbursements from Askins & Miller’s\\n accounts before making all required deposits and paying all required outstanding\\n liabilities due on each employment tax return required to be filed after the date of the\\n preliminary injunction;\\n (5) Defendants shall sign and deliver affidavits to the IRS at 5971 Cattleridge Boulevard,\\n Suite 102-Mail Stop 5410, Sarasota, FL 34232, or to such other specific location as\\n directed by the IRS, within two banking days after each employment tax deposit is\\n due, stating that the requisite deposit was timely made;\\n (6) Defendant Roland V. Askins III shall notify the IRS of any new company or business\\n he may come to own or manage; and\\n (7) Defendant Philip H. Askins shall notify the IRS of any new company or business he\\n may come to own or manage.\\n2\\n The brothers did not materially dispute the IRS’s account of the facts before the district court,\\nnor do they do so on appeal. They did (and do), however, contest the IRS’s characterizations of\\n\\n\\n 6\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 7 of 24\\n\\n\\n\\n Meanwhile, the defendants’ delinquency continued: Askins & Miller racked\\nup more liabilities in 2017 even after the IRS sued, and the district court found that\\n\\nthe defendants have “a proclivity for unlawful conduct” and are “likely to continue\\nignoring” their tax obligations. In fact, other businesses associated with the\\nbrothers—RVA Trust and Gulfcoast Surgery Center—also fell behind on their\\nemployment taxes. The IRS represented to the district court that Askins & Miller\\nwas “accumulating new employment tax liabilities faster than the IRS’s ability to\\ncollect the outstanding obligations” and that its time spent playing cat-and-mouse\\n\\nover the years “constituted a substantial drain” on resources. Deeming an action\\nfor damages a Sisyphean task in these circumstances, the IRS contends on appeal\\nthat the district court should have granted a preliminary injunction because the IRS\\nhas no “adequate” remedy at law.\\n II.\\n Section 7402(a) of the Internal Revenue Code grants federal district courts\\nan array of powers to aid in enforcing the tax laws:\\n\\n\\n\\ntheir motivations and intent: in the brothers’ telling, it was bad business, not bad faith, that\\ncaused them to fall behind. Specifically, Philip Askins submitted a declaration to the district\\ncourt stating that Askins & Miller did not make “any decision never to pay withholding taxes,”\\nthat Askins & Miller has “consistently reported all of its tax liabilities,” and that “extreme\\nfinancial reversals and financial hardships” caused the business to fall behind on all of its debts.\\nPhilip also claimed that Askins & Miller never “sought to hide or avoid it’s [sic] liabilities either\\nto the IRS or to any of its other creditors” and that he had been truthful and open with the IRS.\\nFinally, Philip claimed that a potential sale of another entity, Gulfcoast Surgery Center, was\\nsupposed to provide the funds to bring Askins & Miller into compliance with all of its tax\\nobligations, but the sale “unexpectedly” fell through. The district court did not explicitly resolve\\nthese disputes in its order denying the government’s motion for a preliminary injunction, but it\\ndid find that “the record demonstrates that Defendants have diverted and misappropriated” the\\nemployment taxes withheld from their employees’ wages.\\n 7\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 8 of 24\\n\\n\\n The district courts of the United States at the instance of the United States\\n shall have such jurisdiction to make and issue in civil actions, writs and\\n orders of injunction, and of ne exeat republica, orders appointing receivers,\\n and such other orders and processes, and to render such judgments and\\n decrees as may be necessary or appropriate for the enforcement of the\\n internal revenue laws. The remedies hereby provided are in addition to and\\n not exclusive of any and all other remedies of the United States in such\\n courts or otherwise to enforce such laws.\\n\\n26 U.S.C. § 7402(a). In analyzing this grant of injunctive power, we have said that\\nthe “decision to issue an injunction under § 7402(a) is governed by the traditional\\nfactors shaping the district court’s use of the equitable remedy.” United States v.\\nErnst & Whinney, 735 F.2d 1296, 1301 (11th Cir. 1984).3 To obtain a preliminary\\n\\ninjunction under “the traditional factors,” the IRS must demonstrate 1) a\\nsubstantial likelihood of success on the merits, 2) that it will suffer irreparable\\ninjury unless the injunction is issued, 3) that the threatened injury to the IRS\\noutweighs whatever harm the proposed injunction might cause the defendants, and\\n\\n3\\n We note that there is some question over whether applying “the traditional factors” in § 7402(a)\\ncases is the right approach. The statute’s “in addition to and not exclusive of” language could be\\nread to suggest that the government need not show the lack of an adequate remedy at law, as\\nwould normally be required under the traditional factors. See, e.g., United States v. Benson, 561\\nF.3d 718, 727 n.4 (7th Cir. 2009); cf. United States v. First Nat’l City Bank, 379 U.S. 378, 383\\n(1965) (“[O]ur review of the injunction as an exercise of the equity power granted by 26 U.S.C.\\n§ 7402(a) must be in light of the public interest involved: ‘Courts of equity may, and frequently\\ndo, go much farther both to give and withhold relief in furtherance of the public interest than\\nthey are accustomed to go when only private interests are involved.’” (citation omitted)). But the\\nIRS does not ask us to hold categorically that the adequate-remedy-at-law requirement is\\ninapplicable in § 7402(a) cases, and at any rate we are bound by our precedent. See Ernst &\\nWhinney, 735 F.2d at 1301; see also United States v. Cruz, 611 F.3d 880, 887 (11th Cir. 2010)\\n(rejecting argument that courts should disregard equitable factors when issuing injunctions under\\n§ 7407 and citing Ernst & Whinney); Klay v. United Healthgroup, Inc., 376 F.3d 1092, 1098–99\\n(11th Cir. 2004) (recognizing some “statutory injunction” contexts where the traditional\\nrequirements are relaxed, but citing Ernst & Whinney for the proposition that “several of our\\ncases also suggest that, when Congress authorizes injunctive relief, it implicitly requires that the\\ntraditional requirements for an injunction be met in addition to any elements explicitly specified\\nin the statute”).\\n 8\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 9 of 24\\n\\n\\n\\n4) that the injunction would not be adverse to the public interest. See Keeton v.\\nAnderson-Wiley, 664 F.3d 865, 868 (11th Cir. 2011). We review for abuse of\\n\\ndiscretion a district court’s “ultimate decision of whether to grant a preliminary\\ninjunction,” but we review de novo “determinations of law made by the district\\ncourt en route” to that decision. Owner-Operator Indep. Drivers Ass’n, Inc. v.\\nLandstar Sys., Inc., 622 F.3d 1307, 1323 (11th Cir. 2010) (internal quotation marks\\nand citation omitted).\\n III.\\n\\n Before reaching the merits, we face a preliminary question: whether\\nsubsequent events have rendered this case (or at least portions of this case) moot.\\nDuring the briefing, counsel for defendants filed a motion to withdraw because he\\nwas not getting paid. In that motion, counsel asserted that Askins & Miller “is no\\nlonger in business, has no employees, and has insufficient assets to ever resume\\nbusiness in the future.” The first five of the seven items in the proposed\\npreliminary injunction are premised on Askins & Miller’s continued viability.\\nAlthough counsel withdrew the motion after the Askins brothers “made\\nsatisfactory financial arrangements,” we asked the parties to address whether\\nAskins & Miller is “still incurring tax liabilities that the proposed preliminary\\ninjunction would address” and how the answer to that question should affect our\\ndisposition of the case.\\n “Whether a case is moot is a question of law that we review de novo.”\\nSheely v. MRI Radiology Network, P.A., 505 F.3d 1173, 1182 (11th Cir. 2007). A\\n“case is moot when it no longer presents a live controversy with respect to which\\n\\n 9\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 10 of 24\\n\\n\\n\\nthe court can give meaningful relief.” Id. at 1183 (quoting Troiano v. Supervisor\\nof Elections, 382 F.3d 1276, 1282 (11th Cir. 2004)). But an “important exception”\\n\\nto this “general rule” exists in cases of “voluntary cessation”—that is, where a\\ndefendant voluntarily puts an end to his offensive conduct. Id. In such cases, it is\\n“well settled” that the defendant’s voluntary cessation does not automatically moot\\nthe case; rather, a case “might become moot if subsequent events made it\\nabsolutely clear that the allegedly wrongful behavior could not reasonably be\\nexpected to recur.” Friends of the Earth, Inc. v. Laidlaw Envtl. Servs. (TOC), Inc.,\\n\\n528 U.S. 167, 189 (2000) (internal quotation marks and citation omitted). This\\n“stringent” standard imposes a “heavy” and “formidable” burden on the party\\nasserting mootness—here, the Askins brothers. Id. at 189–90. To carry this\\n“heavy” burden, we require more than a private party’s assertion that its challenged\\nconduct will not recur. See Sheely, 505 F.3d at 1184.\\n Based on the undisputed factual record, Askins & Miller’s possible closure\\ndid not moot the IRS’s claim for injunctive relief. The Supreme Court has made\\nclear that the voluntary cessation standard applies where a business entity’s closure\\nis alleged to have mooted the case. See Laidlaw, 528 U.S. at 193. In conducting\\nthe voluntary cessation analysis, we have previously identified “at least” three\\nrelevant factors: “(1) whether the challenged conduct was isolated or unintentional,\\nas opposed to a continuing and deliberate practice; (2) whether the defendant’s\\ncessation of the offending conduct was motivated by a genuine change of heart or\\ntimed to anticipate suit; and (3) whether, in ceasing the conduct, the defendant has\\nacknowledged liability.” Sheely, 505 F.3d at 1184. Applying those factors here—\\n\\n 10\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 11 of 24\\n\\n\\n\\nin light of the history of the case and the undisputed conduct of the defendants—\\nwe find it far from “absolutely clear that the allegedly wrongful behavior could not\\n\\nreasonably be expected to recur.” Laidlaw, 528 U.S. at 189 (internal quotation\\nmarks and citation omitted).\\n First, we consider “whether the challenged conduct was isolated or\\nunintentional, as opposed to a continuing and deliberate practice.” Sheely, 505\\nF.3d at 1184. The defendants’ failure to pay their federal employment taxes has\\nbeen “a continuing and deliberate practice” for the better part of a decade. Far\\n\\nfrom “isolated or unintentional,” the defendants’ routine failure to pay their\\nemployment taxes since 2010—despite withholding the money from their\\nemployees, and despite repeated interventions from the IRS—appears to have been\\ntheir method of doing business. And although the defendants attribute that routine\\nfailure to bad business rather than bad faith, their professed intentions wane in the\\nshadow of their undisputed history. Similarly, considering the record, we put little\\nweight on Askins & Miller’s (unsupported) eleventh-hour assurances that the\\nbusiness is gone for good. Indeed, we have repeatedly said that a “defendant’s\\nassertion that it has no intention of reinstating the challenged practice ‘does not\\nsuffice to make a case moot’ and is but ‘one of the factors to be considered in\\ndetermining the appropriateness of granting an injunction against the now-\\ndiscontinued acts.’” Id. (quoting United States v. W.T. Grant Co., 345 U.S. 629,\\n\\n\\n\\n\\n 11\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 12 of 24\\n\\n\\n\\n633 (1953)). And, again, we require more than a private party’s unsupported\\nassertions—especially here, given the history of this case.\\n\\n Second, we ask “whether the defendant’s cessation of the offending conduct\\nwas motivated by a genuine change of heart or timed to anticipate suit.” Id. Here,\\nthe timing of Askins & Miller’s possible closure is more indicative of a changed\\ntax-avoidance strategy than a changed heart. We have previously expressed\\nskepticism where changed circumstances come on the eve of a significant decision\\npoint in litigation. See id. at 1187 n.13 (defendant applied “new policy” shortly\\n\\nbefore summary judgment motion); see also id. at 1186 (collecting cases). Here,\\nAskins & Miller claims to have closed down while this case was on appeal.\\nSignificantly, the undisputed facts in the record demonstrate that it would be\\nsimple to reopen at a moment’s notice: back in November 2015, while the IRS was\\nstill experimenting with different collection strategies, “the company submitted a\\nfinancial statement” reflecting “no investments, no accounts or notes receivable, no\\nreal estate, and no business equipment.” Despite that lack of assets, the company\\ncontinued in business until at least mid-2018. The record further demonstrates the\\ndefendants’ history of moving money around from entity to entity. Even taking the\\ndefendants at their word, one of the brothers “has continued his practice\\nincorporated as Roland V. Askins, III, M.D., P.A.,” and their attorney represented\\nat oral argument that although Askins & Miller is out of business “as a practical\\nmatter” (whatever that may mean), the corporation “continues to exist” and “hasn’t\\nbeen formally dissolved.” Those admissions only underscore the ease with which\\nthe brothers could revive Askins & Miller. In light of the record evidence, the\\n\\n 12\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 13 of 24\\n\\n\\n\\ndefendants’ claim that they have “insufficient assets to ever resume business in the\\nfuture” rings hollow.\\n\\n Third, we look to “whether, in ceasing the conduct, the defendant has\\nacknowledged liability.” Id. at 1184. Although the defendants here have not\\ndisputed their past tax debt—the district court entered a money damages judgment\\nfor past-due employment taxes, and Askins & Miller filed tax returns admitting its\\nliabilities—that is cold comfort given the history of this case, in which Askins &\\nMiller has demonstrated a pattern of admitting liability but refusing to pay. The\\n\\nIRS’s proposed relief is designed to prevent Askins & Miller from dodging its\\nadmitted tax liabilities going forward. Because the record amply demonstrates a\\npattern of Askins & Miller pairing its admitted liability with a refusal to pay, the\\nfact that it still admits its liability does not convince us that it is “absolutely clear\\nthat the allegedly wrongful behavior could not reasonably be expected to recur.”\\nLaidlaw, 528 U.S. at 189 (internal quotation marks and citation omitted).\\n Given the undisputed facts before us, we do not believe that the defendants\\ncan satisfy their “heavy” and “formidable” burden of making it “absolutely clear”\\nthat their behavior will not recur. And “we are unpersuaded that a remand would\\nfurther the expeditious resolution of the matter.” Sheely, 505 F.3d at 1188 n.15\\n(conducting mootness analysis without remanding for further fact finding). The\\ndistrict court already concluded that the defendants have “a proclivity for unlawful\\nconduct” and are “likely to continue ignoring” their tax obligations. The record\\ndemonstrates a near-decade-long saga in which the IRS has pursued Askins &\\nMiller time and again. Over that time span, the defendants have funneled money\\n\\n 13\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 14 of 24\\n\\n\\n\\nto new accounts and entities as the IRS closed in on the old ones. For at least the\\ntime between November 2015 and mid-2018, Askins & Miller continued as a\\n\\ngoing concern despite reporting “no investments, no accounts or notes receivable,\\nno real estate, and no business equipment.” Against that backdrop—and in light of\\nthe defendants’ admissions that Askins & Miller “continues to exist” and that one\\nof the brothers continues to practice medicine—“we can discern no reason for\\nsending the question of mootness back to the district court for further review or\\nfact finding.” Id.\\n\\n We emphasize that our decision that the case is not moot does not resolve\\nwhether Askins & Miller’s possible closure makes injunctive relief inappropriate\\non the merits. That is due to the differences between the standard for mootness\\ndue to voluntary cessation and the standard for granting injunctive relief. For a\\ncase to be moot under the voluntary cessation doctrine, the party asserting\\nmootness—here, the defendants—bears the burden to convince a court that\\n“subsequent events made it absolutely clear that the allegedly wrongful behavior\\ncould not reasonably be expected to recur.” Laidlaw, 528 U.S. at 189 (internal\\nquotation marks and citation omitted). By contrast, to obtain an injunction, the\\nplaintiff must “establish by a preponderance of the evidence that this form of\\nequitable relief is necessary.” Sheely, 505 F.3d at 1182 n.10. Because “the two\\ninquiries are strikingly different”—both as to who bears the burden and as to what\\nthat burden is—it follows that “[e]ven though a case is not moot, that does not\\nmean that injunctive relief follows automatically.” Id. The analyses may\\n“overlap[]” because “both are concerned with the likelihood of future unlawful\\n\\n 14\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 15 of 24\\n\\n\\n\\nconduct,” but as we have explained, the answers may well turn out to be different.\\nId. Our analysis here answers the mootness question, but we leave it to the district\\n\\ncourt on remand to answer the merits question.\\n IV.\\n Assured of our jurisdiction, we turn to the merits. We conclude that neither\\nthe adequate-remedy-at-law requirement nor Rule 65(d) should have precluded\\ninjunctive relief on the facts here.\\n A. Adequate Remedy at Law\\n\\n The district court determined that three out of the four “traditional factors”\\ngoverning the propriety of injunctive relief—likelihood of success on the merits,\\nthe balance of harms, and the public interest—were “not seriously disputed by\\nDefendants.” But it denied injunctive relief because it concluded that the IRS had\\nan adequate remedy at law: a suit for money damages after Askins & Miller failed\\nto pay its taxes. We disagree. On these facts, the IRS’s ability to sit on its hands\\nuntil the defendants fail to pay their taxes (again) and only then bring an action for\\nmoney damages does not qualify as an “adequate” legal remedy.\\n Our prior cases do not answer the question presented here. We have said\\nbefore that § 7402(a)’s language “encompasses a broad range of powers necessary\\nto compel compliance with the tax laws.” Ernst & Whinney, 735 F.2d at 1300.\\nAnd we have also emphasized that in any given case under § 7402(a) a court must\\nlook to “the traditional factors shaping the district court’s use of the equitable\\nremedy,” and that “[f]oremost among the principles governing the use of the\\ninjunctive remedy is the traditional requirement ‘that courts of equity should not\\n\\n 15\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 16 of 24\\n\\n\\n\\nact . . . when the moving party has an adequate remedy at law and will not suffer\\nirreparable injury if denied equitable relief.’” Id. at 1301 & n.11 (quoting Younger\\n\\nv. Harris, 401 U.S. 37, 43–44 (1971)). We left it to the district court in that case to\\n“examine the extent to which [the IRS’s] interests are protected by available legal\\nremedies.” Id. And our past precedents on adequate legal remedies do not\\nsquarely resolve the issue in this case: whether the collectability of a future money\\njudgment to cure an expected future injury matters. See, e.g., Ne. Fla. Chapter of\\nthe Ass’n of Gen. Contractors of Am. v. City of Jacksonville, 896 F.2d 1283, 1285\\n\\n(11th Cir. 1990) (stating broadly that an injury is irreparable “only if it cannot be\\nundone through monetary remedies”). But see, e.g., Scott v. Roberts, 612 F.3d\\n1279, 1294–95 (11th Cir. 2010) (discussing situations where an injury is\\nirreparable even though “a later money judgment might undo” it); Levi Strauss &\\nCo. v. Sunrise Int’l Trading Inc., 51 F.3d 982, 986 (11th Cir. 1995) (stating that\\ntrademark infringement causes irreparable harm, even though the trademark holder\\nwas also seeking monetary damages); Fla. Businessmen for Free Enter. v. City of\\nHollywood, 648 F.2d 956, 958 n.2 (5th Cir. Unit B June 1981) (stating that lost\\nprofits may amount to irreparable injury if they are “difficult or impossible to\\ncalculate”).\\n Addressing that issue now, we can see that the collectability of a future\\nmoney judgment to redress future harms is relevant in determining whether legal\\nremedies are “adequate” such that they preclude injunctive relief under § 7402(a).\\nThe very nature of equitable power—the thing that distinguishes it from law—is its\\nflexible and discretionary nature, its ability to respond to real-world practicalities,\\n\\n 16\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 17 of 24\\n\\n\\n\\nand its general aversion to rules that let bad actors capitalize on legal technicalities.\\nSee, e.g., Roscoe Pound, The Decadence of Equity, 5 Colum. L. Rev. 20 (1905).\\n\\n Equity courts have long recognized “extraordinary circumstances,”\\nincluding the likelihood that a defendant will never pay, as one way to “give rise to\\nthe irreparable harm necessary for a preliminary injunction.” 11A Charles Alan\\nWright & Arthur Miller, Federal Practice and Procedure § 2948.1 (3d ed. 2013);\\nsee also Ernst & Whinney, 735 F.2d at 1301 (citing Wright & Miller for its\\n“general discussion of equitable principles governing [the] injunctive remedy”).\\n\\nMore specifically, “most courts sensibly conclude that a damage judgment against\\nan insolvent defendant is an inadequate remedy.” Douglas Laycock, The Death of\\nthe Irreparable Injury Rule, 103 Harv. L. Rev. 687, 716 (1990); see also, e.g.,\\nLakeview Tech., Inc. v. Robinson, 446 F.3d 655, 657 (7th Cir. 2006) (noting that\\nthe “[a]bility to calculate damages” does not make a remedy adequate “if the\\nplaintiff cannot collect the award”).4\\n\\n Indeed, the Supreme Court long ago stressed the practical nature of the\\nequitable inquiry, stating that it “is not enough that there is a remedy at law; it must\\nbe plain and adequate, or in other words, as practical and as efficient to the ends of\\n\\njustice and its prompt administration, as the remedy in equity.” Boyce’s Ex’rs v.\\nGrundy, 28 U.S. (3 Pet.) 210, 215 (1830). The district court’s categorical rule that\\n\\n\\n4\\n The IRS also points to district court cases purportedly granting injunctions in circumstances\\nsimilar to this case, but we place little weight on them. First, the IRS concedes that many of\\nthese cases were the result of default or consent orders, so their propriety may not have been\\nsubject to the sort of vigorous litigation that would give them persuasive value. Second, the\\nrelevance of out-of-circuit cases is further watered down by the fact that some courts—unlike\\nthis Court—have not held injunctions under § 7402(a) to the traditional equitable requirements.\\n 17\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 18 of 24\\n\\n\\n\\na case involving calculable money damages can never warrant injunctive relief,\\nregardless of a plaintiff’s ability to collect on a future judgment, is discordant with\\n\\nthe history and purposes of equity jurisprudence.\\n The fact that the IRS is attempting to avoid future losses is key. As the IRS\\nnotes, it “is an involuntary creditor; it does not make a decision to extend credit.”\\nIn re Haas, 31 F.3d 1081, 1088 (11th Cir. 1994). As long as the brothers continue\\nto accrue employment taxes, the IRS continues to lose money. This sets the IRS\\napart from the position of other creditors (who can cut their losses by refusing to\\n\\nextend additional credit), and—crucially—means that the injunction sought is not\\nsimply an attempt to provide security for past debts. Rather, the proposed\\ninjunction here would staunch the flow of ongoing future losses as the brothers\\ncontinue to accumulate tax liabilities—unlike in cases where the loss has already\\nbeen inflicted or would be attributable to a single event, where we have stated that\\ninjuries are irreparable only when they “cannot be undone through monetary\\nremedies.” E.g., Scott, 612 F.3d at 1295 (quoting Cunningham v. Adams, 808 F.2d\\n815, 821 (11th Cir. 1987)).\\n Indeed, the record and the district court’s own findings demonstrate that the\\ngovernment’s proposed injunctive relief is “appropriate for the enforcement of the\\ninternal revenue laws,” 26 U.S.C. § 7402(a), and that the government will likely\\nsuffer irreparable injury absent an injunction. Among other things, the district\\ncourt noted that Askins & Miller had “a proclivity for unlawful conduct,” had\\n“diverted and misappropriated” the employment taxes it had withheld from its\\nemployees’ wages, and was “likely to continue ignoring” its employment tax\\n\\n 18\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 19 of 24\\n\\n\\n\\nobligations. The IRS’s declaration demonstrates that, over a period of several\\nyears, it expended considerable resources making numerous—and unsuccessful—\\n\\nattempts to collect Askins & Miller’s unpaid taxes. And in the face of all that, as\\nthe declaration explained, Askins & Miller is effectively judgment-proof. In short,\\nthe record amply demonstrates that, absent the requested injunction, the\\ngovernment will continue to suffer harm from Askins & Miller’s willful and\\ncontinuing failure to comply with its employment tax obligations—including lost\\ntax revenue and the expenditure of a disproportionate amount of its resources\\n\\nmonitoring Askins & Miller and attempting to bring it into compliance—and that,\\nin all likelihood, the government will never recoup these losses.\\n The district court relied primarily on our decision in Rosen v. Cascade\\nInternational, Inc., 21 F.3d 1520 (11th Cir. 1994), but Rosen is an uncomfortable\\nfit here. As background, shareholders in that case brought a suit for money\\ndamages against a company and its officers because of alleged securities fraud. Id.\\nat 1522. To ensure that the defendants would be able to satisfy any money\\njudgment ultimately obtained in the litigation, the district court entered a\\npreliminary injunction freezing the assets of one of the defendants. Id. On appeal,\\nwe held that the district court lacked authority to enter that injunction because\\n“cases in which the remedy sought is the recovery of money damages do not fall\\nwithin the jurisdiction of equity,” and as a general rule of federal equity, “a court\\nmay not reach a defendant’s assets unrelated to the underlying litigation and freeze\\nthem so that they may be preserved to satisfy a potential money judgment.” Id. at\\n1527 (internal quotation marks and citation omitted). We also noted that a request\\n\\n 19\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 20 of 24\\n\\n\\n\\nfor prejudgment attachment under Federal Rule of Civil Procedure 64, rather than a\\nmotion for a preliminary injunction under Rule 65, provided the appropriate means\\n\\nto seek an asset freeze. Id. at 1530–31. Looking to state law (as the Rule\\nrequires), we concluded that the plaintiffs had not shown that they were entitled to\\nRule 64 relief. Id.\\n The differences between that case and this one announce themselves rather\\nclearly. Rosen asked “whether a district court has the power to enter a preliminary\\ninjunction freezing the assets of a defendant before trial in a case where the\\n\\nplaintiffs ultimately seek only money damages.” Id. at 1526 (emphasis added).\\nThat damages-only fact was front and center: we explained that a preliminary\\ninjunction is appropriate only where it seeks relief of the “same character” as the\\nfinal relief sought, and that the asset freeze in that case was not of the same\\ncharacter as the ultimate relief because the plaintiffs there “sought only the award\\nof monetary damages—and not equitable relief.” Id. at 1527, 1529 (internal\\nquotation marks and citation omitted); accord Grupo Mexicano de Desarrollo, S.A.\\nv. Alliance Bond Fund, Inc., 527 U.S. 308 (1999); Mitsubishi Int’l Corp. v.\\nCardinal Textile Sales, Inc., 14 F.3d 1507 (11th Cir. 1994).\\n Here, in contrast, the IRS’s complaint asked for a permanent injunction\\nproviding prospective equitable relief for anticipated future violations—the same\\nrelief sought by the preliminary injunction at issue. Indeed, we have already held\\nthat Rosen does not apply where the complaint itself seeks a permanent injunction.\\nLevi Strauss & Co., 51 F.3d at 987; see also SEC v. ETS Payphones, Inc., 408 F.3d\\n727, 734 (11th Cir. 2005) (per curiam) (holding that Grupo Mexicano does not\\n\\n 20\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 21 of 24\\n\\n\\n\\napply where the complaint seeks equitable relief). As Rosen itself was careful to\\nnote, a preliminary injunction “is always appropriate to grant intermediate relief of\\n\\nthe same character as that which may be granted finally.” Rosen, 21 F.3d at 1527\\n(quoting De Beers Consol. Mines v. United States, 325 U.S. 212, 220 (1945)). 5\\n What’s more—and contrary to the district court’s reading—nothing in Rosen\\n\\nsuggests that the IRS has not shown an irreparable injury for purposes of a\\npreliminary injunction. The Rosen court’s statement that the “test of the\\ninadequacy of a remedy at law is whether a judgment could be obtained, not\\nwhether, once obtained it will be collectible,” 21 F.3d at 1531 (quoting St.\\nLawrence Co., N.V. v. Alkow Realty, Inc., 453 So. 2d 514, 514–15 (Fla. Dist. Ct.\\nApp. 1984)), was made in the context of a Rule 64 analysis relating to prejudgment\\n\\nattachment. As we have said, Rule 64 looks to the law of the state in which the\\ncourt sits. See Fed. R. Civ. P. 64(a). So this statement in Rosen merely described\\nFlorida law governing prejudgment attachment; it did not determine (or even\\ndescribe) federal equitable power.\\n\\n\\n\\n\\n5\\n We also note that, for at least a portion of the employment taxes at issue, the assets that the\\ninjunction would reach are not “unrelated”—indeed, they do not even wholly belong to the\\ndefendants—because when an employer withholds employees’ taxes, the withheld money is held\\nin trust for the United States. See Thibodeau v. United States, 828 F.2d 1499, 1506 (11th Cir.\\n1987) (per curiam). So at least for this portion of the taxes, the IRS has an equitable interest that\\nmight qualify it for relief analogous to the “creditor’s bill” recognized in English courts of\\nequity. See Grupo Mexicano, 527 U.S. at 319–20 & n.5 (“Some cases suggested that there was\\nan exception [to the requirement that a judgment be obtained before bringing a creditor’s bill]\\nwhere the debt was admitted or confessed, at least if the creditor possessed an interest in the\\ndebtor’s property.”).\\n 21\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 22 of 24\\n\\n\\n\\n In sum, the district court erred in applying a categorical rule that because tax\\nliability may be calculated and sought in an action for damages, it necessarily\\n\\nprecludes injunctive relief under § 7402(a).\\n B. Rule 65(d)\\n The district court also suggested that “the United States’ proposed injunction\\nwould be unenforceable” as an overbroad “obey-the-law” injunction. It is true that\\nwe have “questioned the enforceability of obey-the-law injunctions” because “they\\nlack specificity and deprive defendants of the procedural protections that would\\n\\nordinarily accompany a future charge of a violation.” SEC v. Goble, 682 F.3d 934,\\n949 (11th Cir. 2012). Such injunctions are disfavored because they often run afoul\\nof Rule 65(d)’s requirement that injunctions state their terms specifically and\\n“describe in reasonable detail” the “act or acts restrained or required.” Fed. R. Civ.\\nP. 65(d). But here, the “obey-the-law” problem does not doom the IRS’s proposed\\ninjunction—the injunction plainly requires more of the Askins brothers than the\\nlaw requires of others, and where it does direct action consistent with the law, it\\ndoes so for specific provisions that the Askins brothers claim they already\\nunderstand.\\n Backing up, the specificity requirements in Rule 65(d) are “designed to\\nprevent uncertainty and confusion on the part of those faced with injunctive orders,\\nand to avoid the possible founding of a contempt citation on a decree too vague to\\nbe understood.” Goble, 682 F.3d at 950 (quoting Schmidt v. Lessard, 414 U.S.\\n473, 476 (1974) (per curiam)). An injunction “should clearly let [the] defendant\\nknow what he is ordered to do or not to do” and “should be phrased in terms of\\n\\n 22\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 23 of 24\\n\\n\\n\\nobjective actions, not legal conclusions.” Id. (quoting Planetary Motion, Inc. v.\\nTechsplosion, Inc., 261 F.3d 1188, 1203 (11th Cir. 2001)). A defendant “should\\n\\nonly be required to look within the four corners of the injunction to determine what\\nhe must do or refrain from doing.” Id. at 952 (internal quotation marks and citation\\nomitted). But the “degree of particularity required depends on the nature of the\\nsubject matter,” and “at times an injunction that orders a defendant to comply with\\na statute may be appropriate.” Id. at 950 (internal quotation marks and citation\\nomitted). That is the case where the statutory terms are specific and the defendant\\n\\nclearly knows what conduct is prohibited or required. Id. at 950–51 (citing\\nMcComb v. Jacksonville Paper Co., 336 U.S. 187 (1949)).\\n The IRS’s proposed injunction passes muster here based on the district\\ncourt’s own findings. The district court found that the “statutes with which\\nDefendants must comply are specific, and the record demonstrates that they are\\nwell aware of the conduct the proposed injunction addresses, their failure to remit\\nto the IRS taxes withheld from their employees.” Askins & Miller does not contest\\nits tax liabilities and has engaged with the IRS for the better part of a decade in the\\nIRS’s repeated efforts to ensure compliance. The district court also found that the\\nIRS demonstrated the defendants’ “proclivity for unlawful conduct,” which cuts in\\nfavor of a broad injunction. Cf. McComb, 336 U.S. at 192 (noting that broad\\ninjunctions “are often necessary to prevent further violations where a proclivity for\\nunlawful conduct has been shown”). Finally, the proposed injunction goes well\\nbeyond merely requiring compliance with the employment tax laws. In fact, it lists\\nnumerous concrete actions for the defendants to take—to name only a few,\\n\\n 23\\n\\f Case: 18-11434 Date Filed: 05/23/2019 Page: 24 of 24\\n\\n\\n\\nsegregating their funds, informing the IRS of any new business ventures, and filing\\nvarious periodic affidavits—well beyond what a simple “obey-the-law” injunction\\n\\nwould look like. In short, this case does not raise the sort of fair notice concerns\\nthat Rule 65(d) is designed to address.\\n V.\\n Because the district court erroneously imposed a categorical rule that\\nprevented a proper exercise of its broad equitable discretion, we vacate its order\\ndenying the IRS’s request for a preliminary injunction against the Defendants-\\n\\nAppellees. On remand, the district court should consider the collectability of a\\nfuture money judgment in determining whether that remedy is “adequate.” It\\nshould also consider any relevant factual developments that may affect the\\npropriety of the injunctive relief sought, including the defendants’ assertion that\\nAskins & Miller is no longer in business and the IRS’s contention that it may need\\nto seek additional injunctive relief in light of those developments. As we have\\nalready explained, this analysis is distinct from the mootness issue that we have\\naddressed. Apart from what we have already said, we express no opinion on\\nwhether an injunction is ultimately appropriate. Rather, we leave it for the district\\ncourt on remand to exercise its equitable discretion consistent with the principles in\\nthis opinion.\\nVACATED AND REMANDED.\\n\\n\\n\\n\\n 24\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2290,"cells":{"id":{"kind":"number","value":4622769,"string":"4,622,769"},"name":{"kind":"string","value":"Calvin Lee WORD, Petitioner, v. U.S. COMMODITY FUTURES TRADING COMMISSION, Louie G. Stidham, June C. Stidham, Respondents."},"name_abbreviation":{"kind":"string","value":"Calvin Lee Word v. U.S. Commodity Futures Trading Commission"},"decision_date":{"kind":"string","value":"2019-05-23"},"docket_number":{"kind":"string","value":"16-15302"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wilson, Pryor, Tallman\", \"parties\": \"\", \"opinions\": [{\"author\": \"TALLMAN, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 16-15302 Date Filed: 05/23/2019 Page: 1 of 14\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 16-15302\\n ________________________\\n\\n CFTC No.: 89-R300\\n\\n\\n\\nCALVIN LEE WORD,\\n\\n Petitioner,\\n\\nversus\\n\\n\\nU.S. COMMODITY FUTURES TRADING COMMISSION,\\nLOUIE G. STIDHAM, JUNE C. STIDHAM,\\n\\n Respondents.\\n\\n ________________________\\n\\n Petition for Review from the United States Commodity Futures Trading\\n Commission\\n ________________________\\n\\n (May 23, 2019)\\n\\nBefore WILSON, JILL PRYOR and TALLMAN, * Circuit Judges.\\n\\n\\n\\n\\n*\\n Honorable Richard C. Tallman, United States Circuit Judge for the Ninth Circuit, sitting\\nby designation.\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 2 of 14\\n\\n\\nTALLMAN, Circuit Judge:\\n\\n Petitioner Calvin Word seeks review of a 2016 order (the “2016 Order”)\\n\\nentered by the United States Commodity Futures Trading Commission (the\\n\\n“CFTC” or the “Commission”) denying his motion to set aside a 1992 default\\n\\njudgment order (the “1992 Order”) requiring him to pay $17,511.91 in reparations\\n\\nplus interest to June and Louie Stidham (the “Stidhams”) for violations of the\\n\\nCommodity Exchange Act, 7 U.S.C. §§ 1, et seq. (the “Act”). On October 11,\\n\\n2016, after Word sought review of the 2016 Order, both Respondents filed a\\n\\nmotion to dismiss the petition for lack of jurisdiction [Dkt. No. 14] (the “Motion”)\\n\\nbecause Word failed to post the required appeal bond under 7 U.S.C. § 18(e). We\\n\\ngrant their Motion and dismiss Word’s petition for want of jurisdiction.\\n\\n I\\n\\n This case has a long history. The Stidhams were customers of a failed\\n\\ncommodity futures trading merchant. In 1989, the Stidhams filed a reparation\\n\\ncomplaint with the CFTC against traders Word, Madlyn L. Ferro, Andrew C.\\n\\nAnderson, and their employer, First Commodity Corporation of Boston (“FCCB”).\\n\\nThe Stidhams alleged that Word and the other respondents had intentionally and\\n\\nfraudulently misrepresented material facts in soliciting and maintaining an account\\n\\nto trade commodity futures contracts. Ferro answered the reparation complaint and\\n\\nmoved to dismiss the Stidhams’ claims against her, asserting that their claims were\\n\\n\\n 2\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 3 of 14\\n\\n\\nbarred by the two-year statute of limitations set forth in 7 U.S.C. § 18(a) (1988).\\n\\nAfter being served with legal process under the Commission’s regulations,1 Word,\\n\\nAnderson, and FCCB did not respond to the Stidhams’ complaint or otherwise\\n\\nparticipate in the proceedings. The Stidhams moved for default against those who\\n\\ndid not appear, including Word.\\n\\n A CFTC administrative law judge (an “ALJ”) then issued the 1992 Order\\n\\ndenying the motion for default against Ferro and granting Ferro’s motion to\\n\\ndismiss because the statute of limitations had run. But the 1992 Order entered\\n\\ndefault against Word and the others, stating that they also might have been able to\\n\\nassert a successful statute-of-limitations defense, but concluding that they had\\n\\nwaived the defense by not raising it in any answer. The 1992 Order required\\n\\nWord, FCCB, and Anderson to pay the Stidhams reparation in the amount of\\n\\n\\n1\\n By regulation, the CFTC was required to serve Word with the Stidhams’ complaint by\\nregistered or certified mail at the address Word, a registrant with the CFTC, had “previously\\ndesignated with the Commission . . . for receipt of reparation complaints.” 17 C.F.R. § 12.15(a)\\n(1989). Word was required to update the CFTC on his address for two years after his registration\\nwas terminated. Id. § 3.30 (1989). Even assuming Word’s registration ended as early as he\\nasserts that it did, he still would have been required to keep the CFTC apprised of his address\\nthrough at least February 15, 1990, well after the Stidhams filed their reparation complaint. A\\nregulation provided that “[a]n order of default . . . may be entered in any proceeding, including a\\nreparation proceeding commenced while the registrant is registered or within two years\\nthereafter, for failure to file a required response to any communication sent to the latest . . .\\naddress” the registrant had on file with the CFTC. Id. Word concedes that the address he had on\\nfile with the CFTC was the address to which the CFTC sent the Stidhams’ complaint by certified\\nmail in 1989, and he has not argued that a typo in the street name printed on the envelope caused\\nthe envelope to be sent to a different address. Therefore, even though it is undisputed that the\\ncomplaint the CFTC forwarded to Word was returned unclaimed and Word never received actual\\nnotice of the Stidhams’ complaint or the 1992 Order until after the 1992 Order was entered, the\\nCFTC fulfilled its obligations under its own regulations to serve him.\\n 3\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 4 of 14\\n\\n\\n$17,511.91, plus 4.58 percent interest compounded annually from April 7, 1986, 2\\n\\nuntil the date of payment. Significantly, Word—unaware that the default had been\\n\\nentered against him—did not appeal the default order to the Commission.\\n\\n The Stidhams then filed a complaint in the United States District Court for\\n\\nthe Northern District of Georgia to enforce the reparations award against Word\\n\\nunder 7 U.S.C. § 18(d) (1988). After significant delay caused by Word’s\\n\\nrecalcitrance, including avoiding service, filing a bankruptcy petition, and refusing\\n\\nto participate in discovery, the district court struck Word’s answer in the litigation\\n\\nand entered default judgment (the “1996 Order”) against him as a sanction. The\\n\\n1996 Order required Word to pay the Stidhams $37,402.35, which included the\\n\\noriginal reparation award, and accumulated interest plus costs and attorneys’ fees.\\n\\n In 2011, Word filed a motion to set aside the 1992 Order on grounds of\\n\\nexcusable neglect. An ALJ denied that motion under 17 C.F.R. § 12.23(b), which\\n\\nrequires motions to set aside default orders in CFTC reparation cases for excusable\\n\\nneglect to be filed within one year of the issuance of the order. On appeal, the\\n\\nCommission affirmed the ALJ’s decision (the “2012 Order”), declining to waive\\n\\nthe one-year filing deadline because doing so would prejudice the Stidhams, who\\n\\nhad already spent 23 years trying to collect the money they lost. See 17 C.F.R.\\n\\n§ 12.4(b). Word did not seek judicial review of that 2012 Order.\\n\\n\\n2\\n The Stidhams closed their account with FCCB on this date.\\n 4\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 5 of 14\\n\\n\\n In 2015, Word filed a second motion to set aside the 1992 Order and dismiss\\n\\nthe Stidhams’ reparation complaint. In his latest motion, Word contended that the\\n\\nStidhams’ failure to file their reparation complaint within the two-year statutory\\n\\ntime limit set forth in 7 U.S.C. § 18(a) deprived the CFTC of jurisdiction to\\n\\nconsider the complaint and rendered the reparation award against him void. In\\n\\nresponse to Word’s motion, the Stidhams challenged Word’s assertion that the\\n\\ntwo-year statute of limitations was jurisdictional.\\n\\n On July 29, 2016, the Commission issued the 2016 Order denying Word’s\\n\\nsecond motion to set aside the 1992 Order, holding that the two-year statute of\\n\\nlimitations in § 18(a)(1) was not jurisdictional, and, thus, the Commission had the\\n\\npower to enter the 1992 Order against Word. The Commission held that because\\n\\nWord had no jurisdictional challenge to the default order, he was once again barred\\n\\nfrom moving to vacate the order by the one-year time limit in 17 C.F.R. § 12.23(b).\\n\\nThe Commission further held that, even if Word’s motion to vacate was properly\\n\\nbefore the Commission, it would have denied the motion because he had waived\\n\\nthe statute of limitations defense by failing to raise it in any answer to the\\n\\nStidhams’ original complaint. The Commission noted that Word could petition for\\n\\nreview of its reparation order to a United States Court of Appeals, and that, under 7\\n\\nU.S.C. § 18(e), such a petition would not be effective unless, in conformance with\\n\\nthe statute, within 30 days of the date of the order he filed with the court “a bond\\n\\n\\n 5\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 6 of 14\\n\\n\\nequal to double the amount of any reparation award.”\\n\\n On August 4, 2016, Word filed here a petition for review of the 2016 Order.\\n\\nHe also filed a motion for leave to appeal in forma pauperis (IFP). However, he\\n\\nfailed to file an appeal bond with the Clerk of Court or elsewhere.\\n\\n On September 1, 2016, according to the Stidhams, Word owed them a total\\n\\nof approximately $128,900, including still accumulating interest, costs, and\\n\\nattorneys’ fees. The Stidhams collected a partial payment of $75,211.75 from a\\n\\n2016 disbursement of funds by the receiver of a limited liability company partly\\n\\nowned by Word, in accordance with a court order obtained in a state court\\n\\nproceeding initiated by the Stidhams. But even after the disbursement, the\\n\\nStidhams contend that Word still owed them over $50,000 on account of the ever-\\n\\nincreasing costs, fees, and interest arising from the 1992 Order. 3\\n\\n On October 11, 2016, both Respondents filed a motion to dismiss Word’s\\n\\ncurrent petition for review for lack of jurisdiction because Word has never posted\\n\\nany bond as required by 7 U.S.C. § 18(e), the congressional directive governing\\n\\njudicial review of CFTC reparation orders. Word responded to the motion pro se,\\n\\nand we appointed Word pro bono counsel to further elucidate the jurisdictional\\n\\nissues.\\n\\n\\n\\n3\\n Though the record is unclear as to exactly what is owed today, it is undisputed that Word\\nremains indebted to the Stidhams for some significant amount.\\n 6\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 7 of 14\\n\\n\\n II\\n\\n “Federal courts are courts of limited jurisdiction” and “possess only that\\n\\npower authorized by” Congress or the Constitution. Kokkonen v. Guardian Life\\n\\nIns. Co. of Am., 511 U.S. 375, 377 (1994); see also Save the Bay, Inc. v. U.S.\\n\\nArmy, 639 F.2d 1100, 1102 (5th Cir. Feb. 1981).4 “It is to be presumed that a\\n\\ncause lies outside this limited jurisdiction, and the burden of establishing the\\n\\ncontrary rests upon the party asserting jurisdiction.” Kokkonen, 511 U.S. at 377\\n\\n(citations omitted).\\n\\n Our jurisdiction over a direct petition for review of a CFTC order, as with\\n\\nany agency order, must be founded on some statutory grant of authority from\\n\\nCongress. See 5 U.S.C. § 703; Sch. Bd. of Broward Cty. v. Dep’t of Health, Educ.\\n\\n& Welfare, 475 F.2d 1117, 1119 (5th Cir. 1973).\\n\\n Under § 18(e), a party may obtain judicial review of any CFTC order by\\n\\nfiling a petition for review of the order in the appropriate court of appeals. See 7\\n\\nU.S.C. § 18(e) (“Any order of the Commission entered hereunder shall be\\n\\nreviewable on petition of any party aggrieved thereby, by the United States Court\\n\\nof Appeals for any circuit in which a hearing was held . . . .”); see also Clayton\\n\\nBrokerage Co. of St. Louis v. Commodity Futures Trading Comm’n, 794 F.2d 573,\\n\\n\\n4\\n Decisions of the former Fifth Circuit rendered prior to the close of business on September\\n30, 1981 are binding on this Court. See Bonner v. City of Prichard, 661 F.2d 1206, 1209 (11th\\nCir. 1981) (en banc).\\n 7\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 8 of 14\\n\\n\\n575 (11th Cir. 1986) (noting that we have jurisdiction to review the CFTC’s order\\n\\nawarding reparations under § 18(e)). Section 18(e) further provides, however, that\\n\\n [s]uch appeal shall not be effective unless within 30 days from and after\\n the date of the reparation order the appellant also files with the clerk of\\n the court a bond in double the amount of the reparation awarded against\\n the appellant conditioned upon the payment of the judgment entered by\\n the court, plus interest and costs, including a reasonable attorney’s fee\\n for the appellee, if the appellee shall prevail.\\n\\n(emphasis added).\\n\\n Respondents contend that this bond requirement is jurisdictional, and the\\n\\npetition for review must therefore be dismissed because Word failed to post the\\n\\nbond. This is an issue of first impression in this Circuit. We agree with\\n\\nRespondents that the bond requirement is jurisdictional.\\n\\n Whether a statutory requirement is jurisdictional or merely a claims-\\n\\nprocessing rule has been the source of much litigation before the Supreme Court in\\n\\nthe past several years. See, e.g., United States v. Kwai Fun Wong, 135 S. Ct. 1625,\\n\\n1632 (2015); Henderson ex rel. Henderson v. Shinseki, 562 U.S. 428, 434–36\\n\\n(2011). A requirement is jurisdictional if Congress “clearly states that a threshold\\n\\nlimitation on a statute’s scope shall count as jurisdictional.” Arbaugh v. Y & H\\n\\nCorp., 546 U.S. 500, 515 (2006); see also Kwai Fun Wong, 135 S. Ct. at 1632.\\n\\nWhen analyzing whether a statutory requirement is jurisdictional, we must focus\\n\\non the “text, context, and relevant historical treatment” of the statute. Reed\\n\\nElsevier, Inc. v. Muchnick, 559 U.S. 154, 166 (2010) (citing Zipes v. Trans World\\n 8\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 9 of 14\\n\\n\\nAirlines, Inc., 455 U.S. 385, 393–95 (1982)).\\n\\n We begin our analysis with the statutory language. See Mansell v. Mansell,\\n\\n490 U.S. 581, 588 (1989) (“Where, as here, the question is one of statutory\\n\\nconstruction, we begin with the language of the statute.”). And the “shall not be\\n\\neffective” language in § 18(e) is a strong indication that the bond was intended to\\n\\nbe jurisdictional. See Chicago Commodities, Inc. v. Commodities Futures Trading\\n\\nComm’n, 811 F.2d 1262, 1263 (9th Cir. 1987) (“The plain meaning of the language\\n\\nin [§ 18(e)] supports our conclusion that the bond requirement is jurisdictional.”).\\n\\nMoreover, as the Ninth Circuit and the D.C. Circuit have noted, § 18(e)’s bond\\n\\nrequirement text is identical to that of the Perishable Agricultural Commodities Act\\n\\n(“PACA”), 7 U.S.C. § 499g(c), Chicago Commodities, 811 F.2d at 1263;\\n\\nKessenich v. Commodity Futures Trading Comm’n, 684 F.2d 88, 91 (D.C. Cir.\\n\\n1982), and PACA’s “shall not be effective” language has been unanimously\\n\\ninterpreted as jurisdictional, see, e.g., Alphas Co. v. William H. Kopke, Jr., Inc.,\\n\\n708 F.3d 33, 38 (1st Cir. 2013); G. & T. Terminal Packaging Co. v. Hawman, 870\\n\\nF.2d 77, 79 (2d Cir. 1989).\\n\\n In the context of § 18, Congress employed the less strict word “may” when\\n\\ncreating a statute of limitations for reparations complaints. See 7 U.S.C. § 18(a)\\n\\n(providing that any person “may, at any time within two years after the cause of\\n\\naction accrues, apply to the Commission for an order . . .”) (emphasis added). That\\n\\n\\n 9\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 10 of 14\\n\\n\\nchoice indicates further that the bond requirement was intended to be mandatory\\n\\nand jurisdictional as opposed to a claims-processing rule.\\n\\n Additionally, the legislative history of PACA, on which § 18(e) is based,\\n\\nmakes even clearer that Congress intended the bond requirement in § 18(e) to be\\n\\njurisdictional in nature. See H.R. Rep. No. 87-1546, at 7 (1962), as reprinted in\\n\\n1962 U.S.C.C.A.N. 2749, 2754; see also Chicago Commodities, 811 F.2d at 1263\\n\\n(“[The Act] was modeled after PACA. The bond requirements in the two statutes\\n\\nare identical. The legislative history of PACA unequivocally indicates that the\\n\\nbond requirement is jurisdictional.”). The relevant House Report on PACA states\\n\\nthat § 499g(c) was amended to “make it clear that an appeal from a reparation\\n\\naward of the Secretary shall not be effective as an appeal, and therefore not a\\n\\nmatter within the jurisdiction of the” federal courts, “unless the required bond is\\n\\nfiled with the court within 30 days from and after” the appealed order. See H.R.\\n\\nRep. No. 87-1546, at 7 (1962) (emphasis added).\\n\\n Taken together, the statutory text, context, and legislative history are a “clear\\n\\nstatement” of congressional intent that the bond requirement in § 18(e) is\\n\\njurisdictional. See Arbaugh, 546 U.S. at 515; Kwai Fun Wong, 135 S. Ct. at 1632\\n\\n(absent a “clear statement” from Congress, statutory requirement is a claims-\\n\\nprocessing rule rather than jurisdictional).\\n\\n Indeed, both circuits addressing this question in published opinions over the\\n\\n\\n 10\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 11 of 14\\n\\n\\nyears have agreed that § 18(e)’s bond requirement is jurisdictional. See Chicago\\n\\nCommodities, 811 F.2d at 1263; Kessenich, 684 F.2d at 93; Saharoff v. Stone, 638\\n\\nF.2d 90, 91–92 (9th Cir. 1980). Therefore, the “historical treatment” of § 18(e)\\n\\nalso indicates that the bond requirement is jurisdictional. Here, then, we have both\\n\\na clear statement from Congress and historical precedent all pointing to the\\n\\njurisdictional nature of the bond requirement. See Muchnick, 559 U.S. at 166. We\\n\\nnow join our sister circuits and hold that § 18(e)’s bond requirement is\\n\\njurisdictional.\\n\\n Yet, Word persists. He reasons that, even assuming § 18(e)’s bond\\n\\nrequirement is normally jurisdictional, the 2016 Order does not itself contain a\\n\\nreparation award that can be doubled, so he does not need to post any bond. He\\n\\nargues that “the statute requires a party seeking to appeal ‘[a]ny order of the\\n\\nCommission’ to post, ‘within 30 days from and after the date of the reparation\\n\\norder . . . a bond in double the amount of the reparation awarded.’ 7 U.S.C.\\n\\n§ 18(e) (emphasis added). The italicized phrases must be referring to the same\\n\\norder.” We are not persuaded for at least three reasons.\\n\\n First, Word’s quote is incomplete. The statute says, “within 30 days from\\n\\nand after the date of the reparation order” the appellant must post “a bond in\\n\\ndouble the amount of the reparation awarded against the appellant.” 7 U.S.C.\\n\\n§ 18(e) (emphasis added). That phrase “awarded against the appellant,” instead of\\n\\n\\n 11\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 12 of 14\\n\\n\\n“awarded in the reparation order,” demonstrates a purposeful decision by Congress\\n\\nnot to limit the relevant award for bond purposes to that found in the order being\\n\\nappealed. “[A]gainst the appellant” is broader than that, and we think a common\\n\\nsense reading of the statute shows that the bond amount can come from any\\n\\nrelevant reparation award, including one granted earlier in petitioner’s case.\\n\\n Second, the bond requirement is jurisdictional. Congress would not create a\\n\\njurisdictional requirement that only applies some of the time but not in the situation\\n\\npresent here for motions to set aside or seeking reconsideration without expressly\\n\\nstating it. To the extent there is ambiguity in the statutory language, Congress\\n\\nexpressly declared with respect to PACA’s appeal bond that federal courts lack\\n\\njurisdiction to review without the posting of a bond. See H.R. Rep. No. 87-1546,\\n\\nat 7 (1962). The legislative history never suggests a scenario where an appellant\\n\\nneed not post a bond (i.e., saying, “if any”). See id. This lack of legislative\\n\\nexemption weighs against Word’s preferred reading.\\n\\n Third, Word’s interpretation would lead to absurd results thwarting\\n\\nCongress’ intent. Lewis v. Barnhart, 285 F.3d 1329, 1332 (11th Cir. 2002) (courts\\n\\nwill interpret statutes to avoid “absurdity of results” (internal quotation marks\\n\\nomitted)). All a petitioner would have to do is simply not appeal the original order\\n\\nrequiring him to pay, refuse to pay, move to set aside the original order later, and,\\n\\nif he loses that motion, appeal the denial, never having to post a bond while\\n\\n\\n 12\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 13 of 14\\n\\n\\ncontinuing to delay payment. That would encourage the very dilatory tactics and\\n\\nmounting of expenses in collection of the reparation awarded that Congress\\n\\nintended to discourage by imposing the statutory bond requirement. The more\\n\\nlogical reading is that the bond required must be twice the size of at least the\\n\\nreparation order originally entered “against the [petitioner]” before the CFTC.\\n\\n7 U.S.C. § 18(e).\\n\\n Word raises two additional, related arguments. First, the Stidhams have\\n\\nalready received approximately $75,000 from Word via a receivership, which is\\n\\nmore than “double the amount of the reparation awarded against” Word. Id.\\n\\nTherefore, under the Saharoff court’s reasoning, no bond is needed to secure\\n\\npayment of the reparation award, plus interest, costs and attorneys’ fees. See 638\\n\\nF.2d at 92–93. Second, Word argues that since the Stidhams have received some\\n\\npayment towards the reparation award, and Respondents have not identified what\\n\\namount of a bond Word should have posted with the Clerk here, that amount must\\n\\nbe zero.\\n\\n The first argument is not persuasive because it is undisputed that Word still\\n\\nowes the Stidhams tens of thousands of dollars arising from the reparation awarded\\n\\n(and compounded interest) in the original 1992 Order—for which Word needed to\\n\\npost a bond as a basis for our statutory jurisdiction. The second question of how\\n\\nmuch the bond should be here is an interesting and difficult one, but one we need\\n\\n\\n 13\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 14 of 14\\n\\n\\nnot reach. Had Word posted a bond here to satisfy § 18(e) in any amount, and he\\n\\nwas before us arguing the size should not be double the original amount of the\\n\\naward in the 1992 Order, we might have been persuaded, as our colleagues were in\\n\\nSaharoff, to require a smaller bond. 638 F.2d at 91, 93. Indeed, we granted Word\\n\\nIFP status in this case, and he might have had a good Equal Protection Clause\\n\\nargument that a bond exceeding $35,023.82 (double the 1992 award) was\\n\\nnonetheless prohibitive and improper. But his failure to post any appeal bond in\\n\\nthe face of § 18(e)’s mandatory and jurisdictional requirement drowns his\\n\\narguments before they can swim.\\n\\n We dismiss Word’s petition for review for want of jurisdiction. We need go\\n\\nno further to discuss the merits of this appeal.\\n\\n III\\n\\n The Motion is GRANTED and Word’s petition for review is DISMISSED\\n\\nfor want of jurisdiction.\\n\\n DISMISSED.\\n\\n\\n\\n\\n 14\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4400022/\", \"author_raw\": \"TALLMAN, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILSON"},"judge2":{"kind":"string","value":"PRYOR"},"judge3":{"kind":"string","value":"TALLMAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4622769/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Calvin Lee WORD, Petitioner, v. U.S. COMMODITY FUTURES TRADING COMMISSION, Louie G. Stidham, June C. Stidham, Respondents.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-23\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 16-15302 Date Filed: 05/23/2019 Page: 1 of 14\n\n\n [PUBLISH]\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 16-15302\n ________________________\n\n CFTC No.: 89-R300\n\n\n\nCALVIN LEE WORD,\n\n Petitioner,\n\nversus\n\n\nU.S. COMMODITY FUTURES TRADING COMMISSION,\nLOUIE G. STIDHAM, JUNE C. STIDHAM,\n\n Respondents.\n\n ________________________\n\n Petition for Review from the United States Commodity Futures Trading\n Commission\n ________________________\n\n (May 23, 2019)\n\nBefore WILSON, JILL PRYOR and TALLMAN, * Circuit Judges.\n\n\n\n\n*\n Honorable Richard C. Tallman, United States Circuit Judge for the Ninth Circuit, sitting\nby designation.\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 2 of 14\n\n\nTALLMAN, Circuit Judge:\n\n Petitioner Calvin Word seeks review of a 2016 order (the “2016 Order”)\n\nentered by the United States Commodity Futures Trading Commission (the\n\n“CFTC” or the “Commission”) denying his motion to set aside a 1992 default\n\njudgment order (the “1992 Order”) requiring him to pay $17,511.91 in reparations\n\nplus interest to June and Louie Stidham (the “Stidhams”) for violations of the\n\nCommodity Exchange Act, 7 U.S.C. §§ 1, et seq. (the “Act”). On October 11,\n\n2016, after Word sought review of the 2016 Order, both Respondents filed a\n\nmotion to dismiss the petition for lack of jurisdiction [Dkt. No. 14] (the “Motion”)\n\nbecause Word failed to post the required appeal bond under 7 U.S.C. § 18(e). We\n\ngrant their Motion and dismiss Word’s petition for want of jurisdiction.\n\n I\n\n This case has a long history. The Stidhams were customers of a failed\n\ncommodity futures trading merchant. In 1989, the Stidhams filed a reparation\n\ncomplaint with the CFTC against traders Word, Madlyn L. Ferro, Andrew C.\n\nAnderson, and their employer, First Commodity Corporation of Boston (“FCCB”).\n\nThe Stidhams alleged that Word and the other respondents had intentionally and\n\nfraudulently misrepresented material facts in soliciting and maintaining an account\n\nto trade commodity futures contracts. Ferro answered the reparation complaint and\n\nmoved to dismiss the Stidhams’ claims against her, asserting that their claims were\n\n\n 2\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 3 of 14\n\n\nbarred by the two-year statute of limitations set forth in 7 U.S.C. § 18(a) (1988).\n\nAfter being served with legal process under the Commission’s regulations,1 Word,\n\nAnderson, and FCCB did not respond to the Stidhams’ complaint or otherwise\n\nparticipate in the proceedings. The Stidhams moved for default against those who\n\ndid not appear, including Word.\n\n A CFTC administrative law judge (an “ALJ”) then issued the 1992 Order\n\ndenying the motion for default against Ferro and granting Ferro’s motion to\n\ndismiss because the statute of limitations had run. But the 1992 Order entered\n\ndefault against Word and the others, stating that they also might have been able to\n\nassert a successful statute-of-limitations defense, but concluding that they had\n\nwaived the defense by not raising it in any answer. The 1992 Order required\n\nWord, FCCB, and Anderson to pay the Stidhams reparation in the amount of\n\n\n1\n By regulation, the CFTC was required to serve Word with the Stidhams’ complaint by\nregistered or certified mail at the address Word, a registrant with the CFTC, had “previously\ndesignated with the Commission . . . for receipt of reparation complaints.” 17 C.F.R. § 12.15(a)\n(1989). Word was required to update the CFTC on his address for two years after his registration\nwas terminated. Id. § 3.30 (1989). Even assuming Word’s registration ended as early as he\nasserts that it did, he still would have been required to keep the CFTC apprised of his address\nthrough at least February 15, 1990, well after the Stidhams filed their reparation complaint. A\nregulation provided that “[a]n order of default . . . may be entered in any proceeding, including a\nreparation proceeding commenced while the registrant is registered or within two years\nthereafter, for failure to file a required response to any communication sent to the latest . . .\naddress” the registrant had on file with the CFTC. Id. Word concedes that the address he had on\nfile with the CFTC was the address to which the CFTC sent the Stidhams’ complaint by certified\nmail in 1989, and he has not argued that a typo in the street name printed on the envelope caused\nthe envelope to be sent to a different address. Therefore, even though it is undisputed that the\ncomplaint the CFTC forwarded to Word was returned unclaimed and Word never received actual\nnotice of the Stidhams’ complaint or the 1992 Order until after the 1992 Order was entered, the\nCFTC fulfilled its obligations under its own regulations to serve him.\n 3\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 4 of 14\n\n\n$17,511.91, plus 4.58 percent interest compounded annually from April 7, 1986, 2\n\nuntil the date of payment. Significantly, Word—unaware that the default had been\n\nentered against him—did not appeal the default order to the Commission.\n\n The Stidhams then filed a complaint in the United States District Court for\n\nthe Northern District of Georgia to enforce the reparations award against Word\n\nunder 7 U.S.C. § 18(d) (1988). After significant delay caused by Word’s\n\nrecalcitrance, including avoiding service, filing a bankruptcy petition, and refusing\n\nto participate in discovery, the district court struck Word’s answer in the litigation\n\nand entered default judgment (the “1996 Order”) against him as a sanction. The\n\n1996 Order required Word to pay the Stidhams $37,402.35, which included the\n\noriginal reparation award, and accumulated interest plus costs and attorneys’ fees.\n\n In 2011, Word filed a motion to set aside the 1992 Order on grounds of\n\nexcusable neglect. An ALJ denied that motion under 17 C.F.R. § 12.23(b), which\n\nrequires motions to set aside default orders in CFTC reparation cases for excusable\n\nneglect to be filed within one year of the issuance of the order. On appeal, the\n\nCommission affirmed the ALJ’s decision (the “2012 Order”), declining to waive\n\nthe one-year filing deadline because doing so would prejudice the Stidhams, who\n\nhad already spent 23 years trying to collect the money they lost. See 17 C.F.R.\n\n§ 12.4(b). Word did not seek judicial review of that 2012 Order.\n\n\n2\n The Stidhams closed their account with FCCB on this date.\n 4\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 5 of 14\n\n\n In 2015, Word filed a second motion to set aside the 1992 Order and dismiss\n\nthe Stidhams’ reparation complaint. In his latest motion, Word contended that the\n\nStidhams’ failure to file their reparation complaint within the two-year statutory\n\ntime limit set forth in 7 U.S.C. § 18(a) deprived the CFTC of jurisdiction to\n\nconsider the complaint and rendered the reparation award against him void. In\n\nresponse to Word’s motion, the Stidhams challenged Word’s assertion that the\n\ntwo-year statute of limitations was jurisdictional.\n\n On July 29, 2016, the Commission issued the 2016 Order denying Word’s\n\nsecond motion to set aside the 1992 Order, holding that the two-year statute of\n\nlimitations in § 18(a)(1) was not jurisdictional, and, thus, the Commission had the\n\npower to enter the 1992 Order against Word. The Commission held that because\n\nWord had no jurisdictional challenge to the default order, he was once again barred\n\nfrom moving to vacate the order by the one-year time limit in 17 C.F.R. § 12.23(b).\n\nThe Commission further held that, even if Word’s motion to vacate was properly\n\nbefore the Commission, it would have denied the motion because he had waived\n\nthe statute of limitations defense by failing to raise it in any answer to the\n\nStidhams’ original complaint. The Commission noted that Word could petition for\n\nreview of its reparation order to a United States Court of Appeals, and that, under 7\n\nU.S.C. § 18(e), such a petition would not be effective unless, in conformance with\n\nthe statute, within 30 days of the date of the order he filed with the court “a bond\n\n\n 5\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 6 of 14\n\n\nequal to double the amount of any reparation award.”\n\n On August 4, 2016, Word filed here a petition for review of the 2016 Order.\n\nHe also filed a motion for leave to appeal in forma pauperis (IFP). However, he\n\nfailed to file an appeal bond with the Clerk of Court or elsewhere.\n\n On September 1, 2016, according to the Stidhams, Word owed them a total\n\nof approximately $128,900, including still accumulating interest, costs, and\n\nattorneys’ fees. The Stidhams collected a partial payment of $75,211.75 from a\n\n2016 disbursement of funds by the receiver of a limited liability company partly\n\nowned by Word, in accordance with a court order obtained in a state court\n\nproceeding initiated by the Stidhams. But even after the disbursement, the\n\nStidhams contend that Word still owed them over $50,000 on account of the ever-\n\nincreasing costs, fees, and interest arising from the 1992 Order. 3\n\n On October 11, 2016, both Respondents filed a motion to dismiss Word’s\n\ncurrent petition for review for lack of jurisdiction because Word has never posted\n\nany bond as required by 7 U.S.C. § 18(e), the congressional directive governing\n\njudicial review of CFTC reparation orders. Word responded to the motion pro se,\n\nand we appointed Word pro bono counsel to further elucidate the jurisdictional\n\nissues.\n\n\n\n3\n Though the record is unclear as to exactly what is owed today, it is undisputed that Word\nremains indebted to the Stidhams for some significant amount.\n 6\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 7 of 14\n\n\n II\n\n “Federal courts are courts of limited jurisdiction” and “possess only that\n\npower authorized by” Congress or the Constitution. Kokkonen v. Guardian Life\n\nIns. Co. of Am., 511 U.S. 375, 377 (1994); see also Save the Bay, Inc. v. U.S.\n\nArmy, 639 F.2d 1100, 1102 (5th Cir. Feb. 1981).4 “It is to be presumed that a\n\ncause lies outside this limited jurisdiction, and the burden of establishing the\n\ncontrary rests upon the party asserting jurisdiction.” Kokkonen, 511 U.S. at 377\n\n(citations omitted).\n\n Our jurisdiction over a direct petition for review of a CFTC order, as with\n\nany agency order, must be founded on some statutory grant of authority from\n\nCongress. See 5 U.S.C. § 703; Sch. Bd. of Broward Cty. v. Dep’t of Health, Educ.\n\n& Welfare, 475 F.2d 1117, 1119 (5th Cir. 1973).\n\n Under § 18(e), a party may obtain judicial review of any CFTC order by\n\nfiling a petition for review of the order in the appropriate court of appeals. See 7\n\nU.S.C. § 18(e) (“Any order of the Commission entered hereunder shall be\n\nreviewable on petition of any party aggrieved thereby, by the United States Court\n\nof Appeals for any circuit in which a hearing was held . . . .”); see also Clayton\n\nBrokerage Co. of St. Louis v. Commodity Futures Trading Comm’n, 794 F.2d 573,\n\n\n4\n Decisions of the former Fifth Circuit rendered prior to the close of business on September\n30, 1981 are binding on this Court. See Bonner v. City of Prichard, 661 F.2d 1206, 1209 (11th\nCir. 1981) (en banc).\n 7\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 8 of 14\n\n\n575 (11th Cir. 1986) (noting that we have jurisdiction to review the CFTC’s order\n\nawarding reparations under § 18(e)). Section 18(e) further provides, however, that\n\n [s]uch appeal shall not be effective unless within 30 days from and after\n the date of the reparation order the appellant also files with the clerk of\n the court a bond in double the amount of the reparation awarded against\n the appellant conditioned upon the payment of the judgment entered by\n the court, plus interest and costs, including a reasonable attorney’s fee\n for the appellee, if the appellee shall prevail.\n\n(emphasis added).\n\n Respondents contend that this bond requirement is jurisdictional, and the\n\npetition for review must therefore be dismissed because Word failed to post the\n\nbond. This is an issue of first impression in this Circuit. We agree with\n\nRespondents that the bond requirement is jurisdictional.\n\n Whether a statutory requirement is jurisdictional or merely a claims-\n\nprocessing rule has been the source of much litigation before the Supreme Court in\n\nthe past several years. See, e.g., United States v. Kwai Fun Wong, 135 S. Ct. 1625,\n\n1632 (2015); Henderson ex rel. Henderson v. Shinseki, 562 U.S. 428, 434–36\n\n(2011). A requirement is jurisdictional if Congress “clearly states that a threshold\n\nlimitation on a statute’s scope shall count as jurisdictional.” Arbaugh v. Y & H\n\nCorp., 546 U.S. 500, 515 (2006); see also Kwai Fun Wong, 135 S. Ct. at 1632.\n\nWhen analyzing whether a statutory requirement is jurisdictional, we must focus\n\non the “text, context, and relevant historical treatment” of the statute. Reed\n\nElsevier, Inc. v. Muchnick, 559 U.S. 154, 166 (2010) (citing Zipes v. Trans World\n 8\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 9 of 14\n\n\nAirlines, Inc., 455 U.S. 385, 393–95 (1982)).\n\n We begin our analysis with the statutory language. See Mansell v. Mansell,\n\n490 U.S. 581, 588 (1989) (“Where, as here, the question is one of statutory\n\nconstruction, we begin with the language of the statute.”). And the “shall not be\n\neffective” language in § 18(e) is a strong indication that the bond was intended to\n\nbe jurisdictional. See Chicago Commodities, Inc. v. Commodities Futures Trading\n\nComm’n, 811 F.2d 1262, 1263 (9th Cir. 1987) (“The plain meaning of the language\n\nin [§ 18(e)] supports our conclusion that the bond requirement is jurisdictional.”).\n\nMoreover, as the Ninth Circuit and the D.C. Circuit have noted, § 18(e)’s bond\n\nrequirement text is identical to that of the Perishable Agricultural Commodities Act\n\n(“PACA”), 7 U.S.C. § 499g(c), Chicago Commodities, 811 F.2d at 1263;\n\nKessenich v. Commodity Futures Trading Comm’n, 684 F.2d 88, 91 (D.C. Cir.\n\n1982), and PACA’s “shall not be effective” language has been unanimously\n\ninterpreted as jurisdictional, see, e.g., Alphas Co. v. William H. Kopke, Jr., Inc.,\n\n708 F.3d 33, 38 (1st Cir. 2013); G. & T. Terminal Packaging Co. v. Hawman, 870\n\nF.2d 77, 79 (2d Cir. 1989).\n\n In the context of § 18, Congress employed the less strict word “may” when\n\ncreating a statute of limitations for reparations complaints. See 7 U.S.C. § 18(a)\n\n(providing that any person “may, at any time within two years after the cause of\n\naction accrues, apply to the Commission for an order . . .”) (emphasis added). That\n\n\n 9\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 10 of 14\n\n\nchoice indicates further that the bond requirement was intended to be mandatory\n\nand jurisdictional as opposed to a claims-processing rule.\n\n Additionally, the legislative history of PACA, on which § 18(e) is based,\n\nmakes even clearer that Congress intended the bond requirement in § 18(e) to be\n\njurisdictional in nature. See H.R. Rep. No. 87-1546, at 7 (1962), as reprinted in\n\n1962 U.S.C.C.A.N. 2749, 2754; see also Chicago Commodities, 811 F.2d at 1263\n\n(“[The Act] was modeled after PACA. The bond requirements in the two statutes\n\nare identical. The legislative history of PACA unequivocally indicates that the\n\nbond requirement is jurisdictional.”). The relevant House Report on PACA states\n\nthat § 499g(c) was amended to “make it clear that an appeal from a reparation\n\naward of the Secretary shall not be effective as an appeal, and therefore not a\n\nmatter within the jurisdiction of the” federal courts, “unless the required bond is\n\nfiled with the court within 30 days from and after” the appealed order. See H.R.\n\nRep. No. 87-1546, at 7 (1962) (emphasis added).\n\n Taken together, the statutory text, context, and legislative history are a “clear\n\nstatement” of congressional intent that the bond requirement in § 18(e) is\n\njurisdictional. See Arbaugh, 546 U.S. at 515; Kwai Fun Wong, 135 S. Ct. at 1632\n\n(absent a “clear statement” from Congress, statutory requirement is a claims-\n\nprocessing rule rather than jurisdictional).\n\n Indeed, both circuits addressing this question in published opinions over the\n\n\n 10\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 11 of 14\n\n\nyears have agreed that § 18(e)’s bond requirement is jurisdictional. See Chicago\n\nCommodities, 811 F.2d at 1263; Kessenich, 684 F.2d at 93; Saharoff v. Stone, 638\n\nF.2d 90, 91–92 (9th Cir. 1980). Therefore, the “historical treatment” of § 18(e)\n\nalso indicates that the bond requirement is jurisdictional. Here, then, we have both\n\na clear statement from Congress and historical precedent all pointing to the\n\njurisdictional nature of the bond requirement. See Muchnick, 559 U.S. at 166. We\n\nnow join our sister circuits and hold that § 18(e)’s bond requirement is\n\njurisdictional.\n\n Yet, Word persists. He reasons that, even assuming § 18(e)’s bond\n\nrequirement is normally jurisdictional, the 2016 Order does not itself contain a\n\nreparation award that can be doubled, so he does not need to post any bond. He\n\nargues that “the statute requires a party seeking to appeal ‘[a]ny order of the\n\nCommission’ to post, ‘within 30 days from and after the date of the reparation\n\norder . . . a bond in double the amount of the reparation awarded.’ 7 U.S.C.\n\n§ 18(e) (emphasis added). The italicized phrases must be referring to the same\n\norder.” We are not persuaded for at least three reasons.\n\n First, Word’s quote is incomplete. The statute says, “within 30 days from\n\nand after the date of the reparation order” the appellant must post “a bond in\n\ndouble the amount of the reparation awarded against the appellant.” 7 U.S.C.\n\n§ 18(e) (emphasis added). That phrase “awarded against the appellant,” instead of\n\n\n 11\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 12 of 14\n\n\n“awarded in the reparation order,” demonstrates a purposeful decision by Congress\n\nnot to limit the relevant award for bond purposes to that found in the order being\n\nappealed. “[A]gainst the appellant” is broader than that, and we think a common\n\nsense reading of the statute shows that the bond amount can come from any\n\nrelevant reparation award, including one granted earlier in petitioner’s case.\n\n Second, the bond requirement is jurisdictional. Congress would not create a\n\njurisdictional requirement that only applies some of the time but not in the situation\n\npresent here for motions to set aside or seeking reconsideration without expressly\n\nstating it. To the extent there is ambiguity in the statutory language, Congress\n\nexpressly declared with respect to PACA’s appeal bond that federal courts lack\n\njurisdiction to review without the posting of a bond. See H.R. Rep. No. 87-1546,\n\nat 7 (1962). The legislative history never suggests a scenario where an appellant\n\nneed not post a bond (i.e., saying, “if any”). See id. This lack of legislative\n\nexemption weighs against Word’s preferred reading.\n\n Third, Word’s interpretation would lead to absurd results thwarting\n\nCongress’ intent. Lewis v. Barnhart, 285 F.3d 1329, 1332 (11th Cir. 2002) (courts\n\nwill interpret statutes to avoid “absurdity of results” (internal quotation marks\n\nomitted)). All a petitioner would have to do is simply not appeal the original order\n\nrequiring him to pay, refuse to pay, move to set aside the original order later, and,\n\nif he loses that motion, appeal the denial, never having to post a bond while\n\n\n 12\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 13 of 14\n\n\ncontinuing to delay payment. That would encourage the very dilatory tactics and\n\nmounting of expenses in collection of the reparation awarded that Congress\n\nintended to discourage by imposing the statutory bond requirement. The more\n\nlogical reading is that the bond required must be twice the size of at least the\n\nreparation order originally entered “against the [petitioner]” before the CFTC.\n\n7 U.S.C. § 18(e).\n\n Word raises two additional, related arguments. First, the Stidhams have\n\nalready received approximately $75,000 from Word via a receivership, which is\n\nmore than “double the amount of the reparation awarded against” Word. Id.\n\nTherefore, under the Saharoff court’s reasoning, no bond is needed to secure\n\npayment of the reparation award, plus interest, costs and attorneys’ fees. See 638\n\nF.2d at 92–93. Second, Word argues that since the Stidhams have received some\n\npayment towards the reparation award, and Respondents have not identified what\n\namount of a bond Word should have posted with the Clerk here, that amount must\n\nbe zero.\n\n The first argument is not persuasive because it is undisputed that Word still\n\nowes the Stidhams tens of thousands of dollars arising from the reparation awarded\n\n(and compounded interest) in the original 1992 Order—for which Word needed to\n\npost a bond as a basis for our statutory jurisdiction. The second question of how\n\nmuch the bond should be here is an interesting and difficult one, but one we need\n\n\n 13\n\f Case: 16-15302 Date Filed: 05/23/2019 Page: 14 of 14\n\n\nnot reach. Had Word posted a bond here to satisfy § 18(e) in any amount, and he\n\nwas before us arguing the size should not be double the original amount of the\n\naward in the 1992 Order, we might have been persuaded, as our colleagues were in\n\nSaharoff, to require a smaller bond. 638 F.2d at 91, 93. Indeed, we granted Word\n\nIFP status in this case, and he might have had a good Equal Protection Clause\n\nargument that a bond exceeding $35,023.82 (double the 1992 award) was\n\nnonetheless prohibitive and improper. But his failure to post any appeal bond in\n\nthe face of § 18(e)’s mandatory and jurisdictional requirement drowns his\n\narguments before they can swim.\n\n We dismiss Word’s petition for review for want of jurisdiction. We need go\n\nno further to discuss the merits of this appeal.\n\n III\n\n The Motion is GRANTED and Word’s petition for review is DISMISSED\n\nfor want of jurisdiction.\n\n DISMISSED.\n\n\n\n\n 14\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Calvin Lee WORD, Petitioner, v. U.S. COMMODITY FUTURES TRADING COMMISSION, Louie G. Stidham, June C. Stidham, Respondents.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-23\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 16-15302 Date Filed: 05/23/2019 Page: 1 of 14\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 16-15302\\n ________________________\\n\\n CFTC No.: 89-R300\\n\\n\\n\\nCALVIN LEE WORD,\\n\\n Petitioner,\\n\\nversus\\n\\n\\nU.S. COMMODITY FUTURES TRADING COMMISSION,\\nLOUIE G. STIDHAM, JUNE C. STIDHAM,\\n\\n Respondents.\\n\\n ________________________\\n\\n Petition for Review from the United States Commodity Futures Trading\\n Commission\\n ________________________\\n\\n (May 23, 2019)\\n\\nBefore WILSON, JILL PRYOR and TALLMAN, * Circuit Judges.\\n\\n\\n\\n\\n*\\n Honorable Richard C. Tallman, United States Circuit Judge for the Ninth Circuit, sitting\\nby designation.\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 2 of 14\\n\\n\\nTALLMAN, Circuit Judge:\\n\\n Petitioner Calvin Word seeks review of a 2016 order (the “2016 Order”)\\n\\nentered by the United States Commodity Futures Trading Commission (the\\n\\n“CFTC” or the “Commission”) denying his motion to set aside a 1992 default\\n\\njudgment order (the “1992 Order”) requiring him to pay $17,511.91 in reparations\\n\\nplus interest to June and Louie Stidham (the “Stidhams”) for violations of the\\n\\nCommodity Exchange Act, 7 U.S.C. §§ 1, et seq. (the “Act”). On October 11,\\n\\n2016, after Word sought review of the 2016 Order, both Respondents filed a\\n\\nmotion to dismiss the petition for lack of jurisdiction [Dkt. No. 14] (the “Motion”)\\n\\nbecause Word failed to post the required appeal bond under 7 U.S.C. § 18(e). We\\n\\ngrant their Motion and dismiss Word’s petition for want of jurisdiction.\\n\\n I\\n\\n This case has a long history. The Stidhams were customers of a failed\\n\\ncommodity futures trading merchant. In 1989, the Stidhams filed a reparation\\n\\ncomplaint with the CFTC against traders Word, Madlyn L. Ferro, Andrew C.\\n\\nAnderson, and their employer, First Commodity Corporation of Boston (“FCCB”).\\n\\nThe Stidhams alleged that Word and the other respondents had intentionally and\\n\\nfraudulently misrepresented material facts in soliciting and maintaining an account\\n\\nto trade commodity futures contracts. Ferro answered the reparation complaint and\\n\\nmoved to dismiss the Stidhams’ claims against her, asserting that their claims were\\n\\n\\n 2\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 3 of 14\\n\\n\\nbarred by the two-year statute of limitations set forth in 7 U.S.C. § 18(a) (1988).\\n\\nAfter being served with legal process under the Commission’s regulations,1 Word,\\n\\nAnderson, and FCCB did not respond to the Stidhams’ complaint or otherwise\\n\\nparticipate in the proceedings. The Stidhams moved for default against those who\\n\\ndid not appear, including Word.\\n\\n A CFTC administrative law judge (an “ALJ”) then issued the 1992 Order\\n\\ndenying the motion for default against Ferro and granting Ferro’s motion to\\n\\ndismiss because the statute of limitations had run. But the 1992 Order entered\\n\\ndefault against Word and the others, stating that they also might have been able to\\n\\nassert a successful statute-of-limitations defense, but concluding that they had\\n\\nwaived the defense by not raising it in any answer. The 1992 Order required\\n\\nWord, FCCB, and Anderson to pay the Stidhams reparation in the amount of\\n\\n\\n1\\n By regulation, the CFTC was required to serve Word with the Stidhams’ complaint by\\nregistered or certified mail at the address Word, a registrant with the CFTC, had “previously\\ndesignated with the Commission . . . for receipt of reparation complaints.” 17 C.F.R. § 12.15(a)\\n(1989). Word was required to update the CFTC on his address for two years after his registration\\nwas terminated. Id. § 3.30 (1989). Even assuming Word’s registration ended as early as he\\nasserts that it did, he still would have been required to keep the CFTC apprised of his address\\nthrough at least February 15, 1990, well after the Stidhams filed their reparation complaint. A\\nregulation provided that “[a]n order of default . . . may be entered in any proceeding, including a\\nreparation proceeding commenced while the registrant is registered or within two years\\nthereafter, for failure to file a required response to any communication sent to the latest . . .\\naddress” the registrant had on file with the CFTC. Id. Word concedes that the address he had on\\nfile with the CFTC was the address to which the CFTC sent the Stidhams’ complaint by certified\\nmail in 1989, and he has not argued that a typo in the street name printed on the envelope caused\\nthe envelope to be sent to a different address. Therefore, even though it is undisputed that the\\ncomplaint the CFTC forwarded to Word was returned unclaimed and Word never received actual\\nnotice of the Stidhams’ complaint or the 1992 Order until after the 1992 Order was entered, the\\nCFTC fulfilled its obligations under its own regulations to serve him.\\n 3\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 4 of 14\\n\\n\\n$17,511.91, plus 4.58 percent interest compounded annually from April 7, 1986, 2\\n\\nuntil the date of payment. Significantly, Word—unaware that the default had been\\n\\nentered against him—did not appeal the default order to the Commission.\\n\\n The Stidhams then filed a complaint in the United States District Court for\\n\\nthe Northern District of Georgia to enforce the reparations award against Word\\n\\nunder 7 U.S.C. § 18(d) (1988). After significant delay caused by Word’s\\n\\nrecalcitrance, including avoiding service, filing a bankruptcy petition, and refusing\\n\\nto participate in discovery, the district court struck Word’s answer in the litigation\\n\\nand entered default judgment (the “1996 Order”) against him as a sanction. The\\n\\n1996 Order required Word to pay the Stidhams $37,402.35, which included the\\n\\noriginal reparation award, and accumulated interest plus costs and attorneys’ fees.\\n\\n In 2011, Word filed a motion to set aside the 1992 Order on grounds of\\n\\nexcusable neglect. An ALJ denied that motion under 17 C.F.R. § 12.23(b), which\\n\\nrequires motions to set aside default orders in CFTC reparation cases for excusable\\n\\nneglect to be filed within one year of the issuance of the order. On appeal, the\\n\\nCommission affirmed the ALJ’s decision (the “2012 Order”), declining to waive\\n\\nthe one-year filing deadline because doing so would prejudice the Stidhams, who\\n\\nhad already spent 23 years trying to collect the money they lost. See 17 C.F.R.\\n\\n§ 12.4(b). Word did not seek judicial review of that 2012 Order.\\n\\n\\n2\\n The Stidhams closed their account with FCCB on this date.\\n 4\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 5 of 14\\n\\n\\n In 2015, Word filed a second motion to set aside the 1992 Order and dismiss\\n\\nthe Stidhams’ reparation complaint. In his latest motion, Word contended that the\\n\\nStidhams’ failure to file their reparation complaint within the two-year statutory\\n\\ntime limit set forth in 7 U.S.C. § 18(a) deprived the CFTC of jurisdiction to\\n\\nconsider the complaint and rendered the reparation award against him void. In\\n\\nresponse to Word’s motion, the Stidhams challenged Word’s assertion that the\\n\\ntwo-year statute of limitations was jurisdictional.\\n\\n On July 29, 2016, the Commission issued the 2016 Order denying Word’s\\n\\nsecond motion to set aside the 1992 Order, holding that the two-year statute of\\n\\nlimitations in § 18(a)(1) was not jurisdictional, and, thus, the Commission had the\\n\\npower to enter the 1992 Order against Word. The Commission held that because\\n\\nWord had no jurisdictional challenge to the default order, he was once again barred\\n\\nfrom moving to vacate the order by the one-year time limit in 17 C.F.R. § 12.23(b).\\n\\nThe Commission further held that, even if Word’s motion to vacate was properly\\n\\nbefore the Commission, it would have denied the motion because he had waived\\n\\nthe statute of limitations defense by failing to raise it in any answer to the\\n\\nStidhams’ original complaint. The Commission noted that Word could petition for\\n\\nreview of its reparation order to a United States Court of Appeals, and that, under 7\\n\\nU.S.C. § 18(e), such a petition would not be effective unless, in conformance with\\n\\nthe statute, within 30 days of the date of the order he filed with the court “a bond\\n\\n\\n 5\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 6 of 14\\n\\n\\nequal to double the amount of any reparation award.”\\n\\n On August 4, 2016, Word filed here a petition for review of the 2016 Order.\\n\\nHe also filed a motion for leave to appeal in forma pauperis (IFP). However, he\\n\\nfailed to file an appeal bond with the Clerk of Court or elsewhere.\\n\\n On September 1, 2016, according to the Stidhams, Word owed them a total\\n\\nof approximately $128,900, including still accumulating interest, costs, and\\n\\nattorneys’ fees. The Stidhams collected a partial payment of $75,211.75 from a\\n\\n2016 disbursement of funds by the receiver of a limited liability company partly\\n\\nowned by Word, in accordance with a court order obtained in a state court\\n\\nproceeding initiated by the Stidhams. But even after the disbursement, the\\n\\nStidhams contend that Word still owed them over $50,000 on account of the ever-\\n\\nincreasing costs, fees, and interest arising from the 1992 Order. 3\\n\\n On October 11, 2016, both Respondents filed a motion to dismiss Word’s\\n\\ncurrent petition for review for lack of jurisdiction because Word has never posted\\n\\nany bond as required by 7 U.S.C. § 18(e), the congressional directive governing\\n\\njudicial review of CFTC reparation orders. Word responded to the motion pro se,\\n\\nand we appointed Word pro bono counsel to further elucidate the jurisdictional\\n\\nissues.\\n\\n\\n\\n3\\n Though the record is unclear as to exactly what is owed today, it is undisputed that Word\\nremains indebted to the Stidhams for some significant amount.\\n 6\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 7 of 14\\n\\n\\n II\\n\\n “Federal courts are courts of limited jurisdiction” and “possess only that\\n\\npower authorized by” Congress or the Constitution. Kokkonen v. Guardian Life\\n\\nIns. Co. of Am., 511 U.S. 375, 377 (1994); see also Save the Bay, Inc. v. U.S.\\n\\nArmy, 639 F.2d 1100, 1102 (5th Cir. Feb. 1981).4 “It is to be presumed that a\\n\\ncause lies outside this limited jurisdiction, and the burden of establishing the\\n\\ncontrary rests upon the party asserting jurisdiction.” Kokkonen, 511 U.S. at 377\\n\\n(citations omitted).\\n\\n Our jurisdiction over a direct petition for review of a CFTC order, as with\\n\\nany agency order, must be founded on some statutory grant of authority from\\n\\nCongress. See 5 U.S.C. § 703; Sch. Bd. of Broward Cty. v. Dep’t of Health, Educ.\\n\\n& Welfare, 475 F.2d 1117, 1119 (5th Cir. 1973).\\n\\n Under § 18(e), a party may obtain judicial review of any CFTC order by\\n\\nfiling a petition for review of the order in the appropriate court of appeals. See 7\\n\\nU.S.C. § 18(e) (“Any order of the Commission entered hereunder shall be\\n\\nreviewable on petition of any party aggrieved thereby, by the United States Court\\n\\nof Appeals for any circuit in which a hearing was held . . . .”); see also Clayton\\n\\nBrokerage Co. of St. Louis v. Commodity Futures Trading Comm’n, 794 F.2d 573,\\n\\n\\n4\\n Decisions of the former Fifth Circuit rendered prior to the close of business on September\\n30, 1981 are binding on this Court. See Bonner v. City of Prichard, 661 F.2d 1206, 1209 (11th\\nCir. 1981) (en banc).\\n 7\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 8 of 14\\n\\n\\n575 (11th Cir. 1986) (noting that we have jurisdiction to review the CFTC’s order\\n\\nawarding reparations under § 18(e)). Section 18(e) further provides, however, that\\n\\n [s]uch appeal shall not be effective unless within 30 days from and after\\n the date of the reparation order the appellant also files with the clerk of\\n the court a bond in double the amount of the reparation awarded against\\n the appellant conditioned upon the payment of the judgment entered by\\n the court, plus interest and costs, including a reasonable attorney’s fee\\n for the appellee, if the appellee shall prevail.\\n\\n(emphasis added).\\n\\n Respondents contend that this bond requirement is jurisdictional, and the\\n\\npetition for review must therefore be dismissed because Word failed to post the\\n\\nbond. This is an issue of first impression in this Circuit. We agree with\\n\\nRespondents that the bond requirement is jurisdictional.\\n\\n Whether a statutory requirement is jurisdictional or merely a claims-\\n\\nprocessing rule has been the source of much litigation before the Supreme Court in\\n\\nthe past several years. See, e.g., United States v. Kwai Fun Wong, 135 S. Ct. 1625,\\n\\n1632 (2015); Henderson ex rel. Henderson v. Shinseki, 562 U.S. 428, 434–36\\n\\n(2011). A requirement is jurisdictional if Congress “clearly states that a threshold\\n\\nlimitation on a statute’s scope shall count as jurisdictional.” Arbaugh v. Y & H\\n\\nCorp., 546 U.S. 500, 515 (2006); see also Kwai Fun Wong, 135 S. Ct. at 1632.\\n\\nWhen analyzing whether a statutory requirement is jurisdictional, we must focus\\n\\non the “text, context, and relevant historical treatment” of the statute. Reed\\n\\nElsevier, Inc. v. Muchnick, 559 U.S. 154, 166 (2010) (citing Zipes v. Trans World\\n 8\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 9 of 14\\n\\n\\nAirlines, Inc., 455 U.S. 385, 393–95 (1982)).\\n\\n We begin our analysis with the statutory language. See Mansell v. Mansell,\\n\\n490 U.S. 581, 588 (1989) (“Where, as here, the question is one of statutory\\n\\nconstruction, we begin with the language of the statute.”). And the “shall not be\\n\\neffective” language in § 18(e) is a strong indication that the bond was intended to\\n\\nbe jurisdictional. See Chicago Commodities, Inc. v. Commodities Futures Trading\\n\\nComm’n, 811 F.2d 1262, 1263 (9th Cir. 1987) (“The plain meaning of the language\\n\\nin [§ 18(e)] supports our conclusion that the bond requirement is jurisdictional.”).\\n\\nMoreover, as the Ninth Circuit and the D.C. Circuit have noted, § 18(e)’s bond\\n\\nrequirement text is identical to that of the Perishable Agricultural Commodities Act\\n\\n(“PACA”), 7 U.S.C. § 499g(c), Chicago Commodities, 811 F.2d at 1263;\\n\\nKessenich v. Commodity Futures Trading Comm’n, 684 F.2d 88, 91 (D.C. Cir.\\n\\n1982), and PACA’s “shall not be effective” language has been unanimously\\n\\ninterpreted as jurisdictional, see, e.g., Alphas Co. v. William H. Kopke, Jr., Inc.,\\n\\n708 F.3d 33, 38 (1st Cir. 2013); G. & T. Terminal Packaging Co. v. Hawman, 870\\n\\nF.2d 77, 79 (2d Cir. 1989).\\n\\n In the context of § 18, Congress employed the less strict word “may” when\\n\\ncreating a statute of limitations for reparations complaints. See 7 U.S.C. § 18(a)\\n\\n(providing that any person “may, at any time within two years after the cause of\\n\\naction accrues, apply to the Commission for an order . . .”) (emphasis added). That\\n\\n\\n 9\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 10 of 14\\n\\n\\nchoice indicates further that the bond requirement was intended to be mandatory\\n\\nand jurisdictional as opposed to a claims-processing rule.\\n\\n Additionally, the legislative history of PACA, on which § 18(e) is based,\\n\\nmakes even clearer that Congress intended the bond requirement in § 18(e) to be\\n\\njurisdictional in nature. See H.R. Rep. No. 87-1546, at 7 (1962), as reprinted in\\n\\n1962 U.S.C.C.A.N. 2749, 2754; see also Chicago Commodities, 811 F.2d at 1263\\n\\n(“[The Act] was modeled after PACA. The bond requirements in the two statutes\\n\\nare identical. The legislative history of PACA unequivocally indicates that the\\n\\nbond requirement is jurisdictional.”). The relevant House Report on PACA states\\n\\nthat § 499g(c) was amended to “make it clear that an appeal from a reparation\\n\\naward of the Secretary shall not be effective as an appeal, and therefore not a\\n\\nmatter within the jurisdiction of the” federal courts, “unless the required bond is\\n\\nfiled with the court within 30 days from and after” the appealed order. See H.R.\\n\\nRep. No. 87-1546, at 7 (1962) (emphasis added).\\n\\n Taken together, the statutory text, context, and legislative history are a “clear\\n\\nstatement” of congressional intent that the bond requirement in § 18(e) is\\n\\njurisdictional. See Arbaugh, 546 U.S. at 515; Kwai Fun Wong, 135 S. Ct. at 1632\\n\\n(absent a “clear statement” from Congress, statutory requirement is a claims-\\n\\nprocessing rule rather than jurisdictional).\\n\\n Indeed, both circuits addressing this question in published opinions over the\\n\\n\\n 10\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 11 of 14\\n\\n\\nyears have agreed that § 18(e)’s bond requirement is jurisdictional. See Chicago\\n\\nCommodities, 811 F.2d at 1263; Kessenich, 684 F.2d at 93; Saharoff v. Stone, 638\\n\\nF.2d 90, 91–92 (9th Cir. 1980). Therefore, the “historical treatment” of § 18(e)\\n\\nalso indicates that the bond requirement is jurisdictional. Here, then, we have both\\n\\na clear statement from Congress and historical precedent all pointing to the\\n\\njurisdictional nature of the bond requirement. See Muchnick, 559 U.S. at 166. We\\n\\nnow join our sister circuits and hold that § 18(e)’s bond requirement is\\n\\njurisdictional.\\n\\n Yet, Word persists. He reasons that, even assuming § 18(e)’s bond\\n\\nrequirement is normally jurisdictional, the 2016 Order does not itself contain a\\n\\nreparation award that can be doubled, so he does not need to post any bond. He\\n\\nargues that “the statute requires a party seeking to appeal ‘[a]ny order of the\\n\\nCommission’ to post, ‘within 30 days from and after the date of the reparation\\n\\norder . . . a bond in double the amount of the reparation awarded.’ 7 U.S.C.\\n\\n§ 18(e) (emphasis added). The italicized phrases must be referring to the same\\n\\norder.” We are not persuaded for at least three reasons.\\n\\n First, Word’s quote is incomplete. The statute says, “within 30 days from\\n\\nand after the date of the reparation order” the appellant must post “a bond in\\n\\ndouble the amount of the reparation awarded against the appellant.” 7 U.S.C.\\n\\n§ 18(e) (emphasis added). That phrase “awarded against the appellant,” instead of\\n\\n\\n 11\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 12 of 14\\n\\n\\n“awarded in the reparation order,” demonstrates a purposeful decision by Congress\\n\\nnot to limit the relevant award for bond purposes to that found in the order being\\n\\nappealed. “[A]gainst the appellant” is broader than that, and we think a common\\n\\nsense reading of the statute shows that the bond amount can come from any\\n\\nrelevant reparation award, including one granted earlier in petitioner’s case.\\n\\n Second, the bond requirement is jurisdictional. Congress would not create a\\n\\njurisdictional requirement that only applies some of the time but not in the situation\\n\\npresent here for motions to set aside or seeking reconsideration without expressly\\n\\nstating it. To the extent there is ambiguity in the statutory language, Congress\\n\\nexpressly declared with respect to PACA’s appeal bond that federal courts lack\\n\\njurisdiction to review without the posting of a bond. See H.R. Rep. No. 87-1546,\\n\\nat 7 (1962). The legislative history never suggests a scenario where an appellant\\n\\nneed not post a bond (i.e., saying, “if any”). See id. This lack of legislative\\n\\nexemption weighs against Word’s preferred reading.\\n\\n Third, Word’s interpretation would lead to absurd results thwarting\\n\\nCongress’ intent. Lewis v. Barnhart, 285 F.3d 1329, 1332 (11th Cir. 2002) (courts\\n\\nwill interpret statutes to avoid “absurdity of results” (internal quotation marks\\n\\nomitted)). All a petitioner would have to do is simply not appeal the original order\\n\\nrequiring him to pay, refuse to pay, move to set aside the original order later, and,\\n\\nif he loses that motion, appeal the denial, never having to post a bond while\\n\\n\\n 12\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 13 of 14\\n\\n\\ncontinuing to delay payment. That would encourage the very dilatory tactics and\\n\\nmounting of expenses in collection of the reparation awarded that Congress\\n\\nintended to discourage by imposing the statutory bond requirement. The more\\n\\nlogical reading is that the bond required must be twice the size of at least the\\n\\nreparation order originally entered “against the [petitioner]” before the CFTC.\\n\\n7 U.S.C. § 18(e).\\n\\n Word raises two additional, related arguments. First, the Stidhams have\\n\\nalready received approximately $75,000 from Word via a receivership, which is\\n\\nmore than “double the amount of the reparation awarded against” Word. Id.\\n\\nTherefore, under the Saharoff court’s reasoning, no bond is needed to secure\\n\\npayment of the reparation award, plus interest, costs and attorneys’ fees. See 638\\n\\nF.2d at 92–93. Second, Word argues that since the Stidhams have received some\\n\\npayment towards the reparation award, and Respondents have not identified what\\n\\namount of a bond Word should have posted with the Clerk here, that amount must\\n\\nbe zero.\\n\\n The first argument is not persuasive because it is undisputed that Word still\\n\\nowes the Stidhams tens of thousands of dollars arising from the reparation awarded\\n\\n(and compounded interest) in the original 1992 Order—for which Word needed to\\n\\npost a bond as a basis for our statutory jurisdiction. The second question of how\\n\\nmuch the bond should be here is an interesting and difficult one, but one we need\\n\\n\\n 13\\n\\f Case: 16-15302 Date Filed: 05/23/2019 Page: 14 of 14\\n\\n\\nnot reach. Had Word posted a bond here to satisfy § 18(e) in any amount, and he\\n\\nwas before us arguing the size should not be double the original amount of the\\n\\naward in the 1992 Order, we might have been persuaded, as our colleagues were in\\n\\nSaharoff, to require a smaller bond. 638 F.2d at 91, 93. Indeed, we granted Word\\n\\nIFP status in this case, and he might have had a good Equal Protection Clause\\n\\nargument that a bond exceeding $35,023.82 (double the 1992 award) was\\n\\nnonetheless prohibitive and improper. But his failure to post any appeal bond in\\n\\nthe face of § 18(e)’s mandatory and jurisdictional requirement drowns his\\n\\narguments before they can swim.\\n\\n We dismiss Word’s petition for review for want of jurisdiction. We need go\\n\\nno further to discuss the merits of this appeal.\\n\\n III\\n\\n The Motion is GRANTED and Word’s petition for review is DISMISSED\\n\\nfor want of jurisdiction.\\n\\n DISMISSED.\\n\\n\\n\\n\\n 14\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2291,"cells":{"id":{"kind":"number","value":4623035,"string":"4,623,035"},"name":{"kind":"string","value":"UNITED STATES of America, Plaintiff - Appellee, v. Darrell Mark BABCOCK, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"United States v. Darrell Mark Babcock"},"decision_date":{"kind":"string","value":"2019-05-24"},"docket_number":{"kind":"string","value":"17-13678"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Pryor, Newsom, Vratil\", \"parties\": \"\", \"opinions\": [{\"author\": \"NEWSOM, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-13678 Date Filed: 05/24/2019 Page: 1 of 32\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-13678\\n ________________________\\n\\n D.C. Docket No. 2:16-cr-14071-KAM-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nDARRELL MARK BABCOCK,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 23, 2019)\\n\\nBefore WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District\\nJudge.\\n\\n\\n\\n\\n*\\n The Honorable Kathryn H. Vratil, United States District Court Judge for the District of Kansas,\\nsitting by designation.\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 2 of 32\\n\\n\\nNEWSOM, Circuit Judge:\\n\\n In this case, police officers investigating a domestic disturbance confiscated\\n\\na suspect’s cell phone and held it for two days before eventually obtaining a\\n\\nwarrant to search it. The appeal before us presents two Fourth Amendment\\n\\nquestions. First, was the seizure justified on the ground that the officers had\\n\\nreasonable suspicion to believe that the phone’s owner was engaged in criminal\\n\\nwrongdoing—was it, in effect, a permissible “Terry stop” of the phone? We hold\\n\\nthat it was not. Second, in the particular circumstances of this case, did the officers\\n\\nhave probable cause to believe not only that the phone’s owner had committed a\\n\\ncrime and that the phone contained evidence of that crime, but also that the suspect\\n\\nwould likely destroy that evidence before they could procure a warrant? We hold\\n\\nthat they did. Accordingly, and on that ground, we affirm the district court’s order\\n\\ndenying the motion to suppress. We separately affirm the district court’s sentence.\\n\\n I\\n\\n A\\n\\n Early one Friday morning, Deputy Andrea Olson of the Stuart, Florida\\n\\nPolice Department responded to a domestic-disturbance call reporting a ruckus\\n\\ncoming from a camper parked at Darrell Babcock’s residence—specifically, a\\n\\nfemale had been heard yelling, “Stop, stop, stop!” When Deputy Olson knocked\\n\\non the door of Babcock’s camper, Babcock exited, closed the door behind him, and\\n\\n\\n 2\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 3 of 32\\n\\n\\nvolunteered that no one else was inside. Almost immediately, though, Deputy\\n\\nOlson heard a female announce that she was coming out. A teenage girl emerged\\n\\nfrom the trailer; she was wearing only yoga shorts and a camo jacket, and she had\\n\\nblood on her left thigh. Seemingly by way of explanation, Babcock handed\\n\\nDeputy Olson his cell phone to show her a video of the girl—we’ll call her C.A.—\\n\\nsitting on a bed, holding a knife to her own throat and saying that she wanted to\\n\\ndie. In the video Babcock could be heard berating the girl, telling her, “you’re\\n\\ndumb as f***” and complaining, “this is what I deal with right here . . . you gotta\\n\\ndo drama and fighting me all over the place.” After viewing the clip, Deputy\\n\\nOlson returned Babcock’s phone. When backup arrived on the scene, Deputy\\n\\nOlson asked for the phone again so that she could show the video to her colleague,\\n\\nOfficer Michael McMahan.\\n\\n The officers then interviewed Babcock and C.A. separately. Babcock denied\\n\\nknowing C.A.’s age and also disputed that the two were in a relationship, although\\n\\nhe admitted that he had known C.A. for three years and that she used to be his\\n\\nneighbor. He also said that C.A. had shown up at his camper unannounced,\\n\\nsometime during the middle of the night. C.A., by contrast—whose license\\n\\nshowed that she was only 16 years old—stated that she and Babcock had gone\\n\\ntogether the night before to a Halloween party, where she had consumed alcohol,\\n\\ncocaine, and other substances. After answering a few questions, C.A. began either\\n\\n\\n 3\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 4 of 32\\n\\n\\npanicking or experiencing the effects of an overdose, so the officers called an\\n\\nambulance. Deputy Olson rode with C.A. to the hospital.\\n\\n Meanwhile, another officer, Detective Brian Broughton, remained behind to\\n\\ncontinue questioning Babcock. Detective Broughton sought and received\\n\\npermission to search Babcock’s camper, where he discovered blood on the\\n\\nbedsheets and prescription pills scattered about. When Detective Broughton asked\\n\\nto further inspect Babcock’s phone, Babcock refused and asked to have it back.\\n\\nBabcock offered to e-mail the video clip of C.A. with the knife, but Detective\\n\\nBroughton decided to keep the phone instead. He told Officer McMahan to enter it\\n\\ninto evidence and then took it with him to the hospital to talk to C.A.\\n\\n At the hospital, C.A. again insisted that she and Babcock were just friends,\\n\\nthat they had gone to a Halloween party, and that the two had then argued. She\\n\\nfirmly denied any further relationship. But when Detective Broughton informed\\n\\nC.A. that he had Babcock’s phone, she abruptly reversed course and admitted that\\n\\nthe two had been in a relationship and, further, that the officers would find sexually\\n\\nexplicit images of her on the phone. Two days later, Detective Broughton applied\\n\\nfor and obtained a warrant to search the phone, where he found nude images of\\n\\nC.A. and explicit video recordings of Babcock and C.A. together.\\n\\n\\n\\n\\n 4\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 5 of 32\\n\\n\\n B\\n\\n Babcock was charged with two counts of producing a visual depiction of\\n\\nsexually explicit conduct with a minor in violation of 18 U.S.C. § 2251(a), (e). He\\n\\nfiled a motion to suppress, arguing that officers had seized his phone without a\\n\\nwarrant or probable cause. The government filed a response, arguing primarily\\n\\nthat the cell-phone seizure was reasonable because “under the totality of the\\n\\ncircumstances” the officers had “reasonable suspicion to investigate further,” and\\n\\nadding that, at any rate, the officers had probable cause to believe that the phone\\n\\ncontained evidence of a crime. The government further contended that “detention\\n\\nof the cell phone was necessary to preserve the evidence observed by the\\n\\ndeputies.” Finally, the government asserted that, even in the absence of a warrant,\\n\\neither Babcock’s consent or the inevitability that the images would have been\\n\\ndiscovered rendered the seizure constitutional.\\n\\n A magistrate judge recommended that Babcock’s motion be denied. He\\n\\nconcluded—referencing two distinct Fourth Amendment standards—that “the\\n\\ncollective knowledge and information received by the officers at the scene\\n\\nconstituted sufficient probable cause and reasonable suspicion that there may have\\n\\nbeen a crime committed which may have been preserved on the cell phone.” The\\n\\ndistrict court agreed, noting—also somewhat vaguely—that the surrounding\\n\\ncircumstances were “sufficient for law enforcement to suspect inappropriate\\n\\n\\n 5\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 6 of 32\\n\\n\\nconduct between [Babcock] and C.A.” Later, at sentencing, the district judge\\n\\nfurther remarked that although he “didn’t say [it] in the order,” he was “putting [it]\\n\\non the record for appellate purposes” that in the video C.A. “appear[ed] to be either\\n\\nwith no pants on or underwear” and that, based on “what she says and how she\\n\\nsays it about what she wants to do to herself,” it was “obvious . . . that there was an\\n\\ninappropriate relationship going on which would have given [the officers]\\n\\nreasonable probable cause to believe that there was inappropriate sexual activity\\n\\nbetween” Babcock and C.A. Babcock took a plea, reserving his right to appeal the\\n\\ndenial of his motion to suppress.\\n\\n At sentencing, Babcock asked for the mandatory minimum of 180 months,\\n\\narguing that his conduct, while inappropriate, was outside the core child-\\n\\npornography-distribution behavior that Congress sought to deter under § 2251(a)\\n\\nand (e). The government in turn asked for a sentence within the 360-to-720-month\\n\\nrecommended Guidelines range, stressing the harm to C.A. and her family. The\\n\\ncourt imposed a below-Guidelines sentence of 324 months. Babcock appealed\\n\\nboth the denial of his motion to suppress and his sentence.\\n\\n II\\n\\n We’ll tackle the Fourth Amendment issues first. A person suffers a\\n\\n“seizure” of his property within the meaning of the Fourth Amendment when there\\n\\nis a “meaningful interference” with his possessory interest in it. United States v.\\n\\n\\n 6\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 7 of 32\\n\\n\\nVirden, 488 F.3d 1317, 1321 (11th Cir. 2007).1 While the seizure of private\\n\\nproperty generally requires a warrant, the Supreme Court has interpreted the\\n\\nFourth Amendment to allow a warrantless seizure when police can show both (1)\\n\\nprobable cause to believe that property contains contraband or evidence of a crime\\n\\nand (2) an applicable warrant exception, such as exigent circumstances. See, e.g.,\\n\\nKentucky v. King, 563 U.S. 452, 459–60 (2011) (citations omitted). Accordingly,\\n\\nabsent either a warrant or probable cause plus an exception, police may not seize\\n\\nprivate property. There is, however, an asterisk. Under a line of luggage-related\\n\\ncases from the 1980s, police may “briefly detain” property—Terry-stop style—on\\n\\nthe strength of reasonable suspicion alone. See United States v. Place, 462 U.S.\\n\\n696, 697–98 (1983); United States v. Puglisi, 723 F.2d 779, 788–89 (11th Cir.\\n\\n1984).\\n\\n Here, the government principally argues that these cases permitted the\\n\\nofficers to detain Babcock’s phone based on their reasonable suspicion that he had\\n\\ncommitted a crime. Alternatively, the government contends that the officers had\\n\\nprobable cause to believe that the phone contained evidence of a crime and that\\n\\nexigent circumstances—namely, the need to prevent the destruction of that\\n\\nevidence—allowed them to seize the phone. We consider each argument in turn.\\n1\\n When reviewing the denial of a motion to suppress, we review factual findings for clear error\\nand legal determinations de novo. United States v. Gibson, 708 F.3d 1256, 1274 (11th Cir.\\n2013). We also review the evidence in the light most favorable to the government, as the\\nprevailing party. See United States v. Capers, 708 F.3d 1286, 1295–96 (11th Cir. 2013).\\n\\n 7\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 8 of 32\\n\\n\\n A\\n\\n 1\\n\\n Reasonable suspicion is “a particularized and objective basis” for suspecting\\n\\na person of criminal activity. Ornelas v. United States, 517 U.S. 690, 696 (1996)\\n\\n(quotation marks omitted). It requires “specific, articulable, and objective facts\\n\\nreasonably to suspect” that a crime is being or will soon be committed, Puglisi,\\n\\n723 F.2d at 789, but “is a less demanding standard than probable cause,” Illinois v.\\n\\nWardlow, 528 U.S. 119, 123 (2000). In Terry v. Ohio, the Supreme Court\\n\\nfamously held that, even absent probable cause, police officers may briefly detain\\n\\nan individual based on reasonable suspicion that he is (or is about to be) engaged in\\n\\ncriminal activity. See 392 U.S. 1, 30–31 (1968).\\n\\n The Supreme Court first extended Terry’s rationale from people to property\\n\\nin United States v. Place, 462 U.S. 696 (1983). There, the Court held that while a\\n\\nbrief investigatory detention of property could be justified on the basis of\\n\\nreasonable suspicion alone, an officer’s 90-minute seizure of an airline traveler’s\\n\\nsuitcase exceeded constitutional boundaries. Id. at 702. In so holding, the Court\\n\\nrecognized that “[t]he intrusion on possessory interests occasioned by a seizure of\\n\\none’s personal effects can vary both in its nature and extent.” Id. at 705. While\\n\\nsome “brief detentions of personal effects”—such as, the Court hypothesized, “on-\\n\\nthe-spot” dog sniffs—may be “so minimally intrusive” as to “justify a seizure\\n\\n\\n 8\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 9 of 32\\n\\n\\nbased only on specific articulable facts that the property contains contraband,” the\\n\\nluggage seizure didn’t fit the bill. Id. at 705–06. By way of explanation, the Court\\n\\nemphasized several factors: the duration of the detention, the degree of the\\n\\nintrusion on the owner’s possessory interests in his property, and the officer’s lack\\n\\nof diligence in timely pursuing their investigation. Id. at 709–10. The Court also\\n\\nhighlighted that a confiscation of luggage, in particular, interferes not only with\\n\\npossessory interests but also with liberty interests because, while a suspect whose\\n\\nluggage is stopped is “technically still free to continue” on his way, the detention\\n\\nmight “effectively restrain” him by disrupting his travel plans. Id. at 708–09.\\n\\n Shortly after the Supreme Court decided Place, this Court had occasion to\\n\\napply it on similar facts. In United States v. Puglisi, an officer made what began as\\n\\na brief stop by ordering a suspicious traveler’s bags removed from a luggage cart;\\n\\nhe then stowed the luggage in his office until a drug-sniffing dog became available.\\n\\n723 F.2d 779, 790 (11th Cir. 1984). Meanwhile, the traveler boarded his flight\\n\\nwithout his bags. Although we deemed the initial seizure permissible under Terry,\\n\\nwe found that the length and intrusiveness—140 minutes—caused the “brief stop”\\n\\nto “ripen” into a full-blown seizure that could be justified only by probable cause.\\n\\nId. at 784. We explained that “Place requires the same test as Terry: a court must\\n\\nweigh the intrusiveness of a limited seizure of the individual against society’s\\n\\ninterest in detection and prevention of crime.” Id. at 785. We cautioned, however,\\n\\n\\n 9\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 10 of 32\\n\\n\\nthat because the Fourth Amendment “protects people, not things,” the focus was\\n\\nthe effective “seizure of persons, through their luggage.” Id. at 787–88.\\n\\n Although Place and Puglisi concerned luggage, both this Court and others\\n\\nhave since indicated that any detention of property based on reasonable suspicion\\n\\nmust be fairly analogous to a Terry stop, regardless of the item at issue.\\n\\nAccordingly, we have said, “the factors used to determine whether a Terry stop has\\n\\nmatured into an arrest are also useful in evaluating whether a seizure of property\\n\\nrequired probable cause” rather than mere reasonable suspicion. Virden, 488 F.3d\\n\\nat 1321. Echoing Place, we have said that these factors include, but are not limited\\n\\nto, (1) the detention’s duration, (2) its intrusiveness, (3) the diligence with which\\n\\nofficers pursued their investigation, and (4) the law-enforcement purposes served\\n\\nby the detention. See id.; accord United States v. Gonzalez, 781 F.3d 422, 428–29\\n\\n(8th Cir. 2015); Farm Labor Org. Comm. v. Ohio State Highway Patrol, 308 F.3d\\n\\n523, 544–45 (6th Cir. 2002); United States v. $557,933.89, More or Less, in U.S.\\n\\nFunds, 287 F.3d 66, 86 (2d Cir. 2002). We’ll explain each in a bit more detail here\\n\\nbefore applying them to the facts of this case\\n\\n First, duration. Although the Supreme Court has “decline[d] to adopt any\\n\\noutside time limit for a permissible Terry stop,” the Court in Place observed that it\\n\\nhad “never approved a seizure of the person for the prolonged 90-minute period\\n\\ninvolved” in that case and that, on the facts presented there, it wouldn’t approve a\\n\\n\\n 10\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 11 of 32\\n\\n\\n90-minute detention of property, either. 462 U.S. at 709–10. In Virden, this Court\\n\\nsimilarly determined that an officer’s transfer of a defendant and his car to another\\n\\nlocation for a dog sniff, “[w]hile not unduly lengthy” at about 30 minutes, was\\n\\nnonetheless “unreasonable absent probable cause.” 488 F.3d at 1321. 2\\n\\n At the other end of the spectrum, the Fourth Circuit has approved a seconds-\\n\\nlong cell-phone stop on the basis of reasonable suspicion alone. In United States v.\\n\\nLawing, that court held that an officer’s brief detention of a suspect’s phone during\\n\\na traffic stop—for just long enough to see if it would ring when the officer dialed a\\n\\nknown drug-distributor’s number—was sufficiently minimal to qualify for\\n\\nTerry/Place treatment. 703 F.3d 229, 238 (4th Cir. 2012). Similarly, the Second\\n\\nCircuit held that reasonable suspicion justified a brief investigatory detention that\\n\\noccurred when a detective took between two and 20 minutes to respond to a\\n\\nrequest for a luggage investigation while a traveler waited at an airport security\\n\\ncheckpoint with his luggage. See $557,933.89, More or Less, 287 F.3d at 71, 86–\\n\\n87 & n.16.\\n\\n Second, intrusiveness. The “intrusiveness” factor concerns the degree to\\n\\nwhich a property detention interferes with a person’s possessory interest in his\\n\\nbelongings. In Place, for instance, the Court emphasized that although “the\\n\\n2\\n Even though the detention there more directly implicated the owner’s liberty interests than in\\nPlace because the owner remained in his car while it was transported to another location, we\\nanalyzed the stop primarily as one of property rather than of an individual. See Virden, 488 F.3d\\nat 1321.\\n 11\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 12 of 32\\n\\n\\nparticular course of investigation that the agents intended to pursue”—just a brief\\n\\n“exposure of respondent’s luggage, which was located in a public place, to a\\n\\ntrained canine”—would have been permissible based on mere reasonable\\n\\nsuspicion, the 90-minute seizure that they actually effected was not. 462 U.S. at\\n\\n707, 709–10 (emphasis added). The Court explained that the planned sniff would\\n\\nhave revealed “only the presence or absence of narcotics, a contraband item,” and\\n\\nwouldn’t have exposed the traveler’s personal “noncontraband items that otherwise\\n\\nwould remain hidden from public view, as [would], for example, an officer’s\\n\\nrummaging through the contents of the luggage.” Id. at 707.\\n\\n This Court has likewise recognized that individuals have strong interests in\\n\\ncontainers that hold personal effects or private information, such as luggage and\\n\\ncomputers. In Puglisi, we emphasized that “privacy and possessory interests in\\n\\nluggage are often high” because a traveler may have “his most important and\\n\\nprivate possessions in his suitcase” and likely wants “to shield them from the\\n\\nprying eyes of strangers, especially the government.” 723 F.2d at 786. And in\\n\\nUnited States v. Laist, we acknowledged that “computers are a unique possession,\\n\\none in which individuals may have a particularly powerful possessory interest,”\\n\\nbecause they store “personal letters, e-mails, financial information, passwords,\\n\\nfamily photos, and countless other items of a personal nature.” 702 F.3d 608, 614\\n\\n(11th Cir. 2012); see also United States v. Mitchell, 565 F.3d 1347, 1352 (11th Cir.\\n\\n\\n 12\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 13 of 32\\n\\n\\n2009) (calling a computer hard drive “the digital equivalent of its owner’s home,\\n\\ncapable of holding a universe of private information”) (internal quotation marks\\n\\nomitted).\\n\\n Third, diligence. When police diligently pursue their investigation, a\\n\\nreviewing court can have greater confidence that the governmental interest is\\n\\nlegitimate and that the intrusion occasioned by the challenged detention was no\\n\\ngreater than reasonably necessary. See United States v. Burgard, 675 F.3d 1029,\\n\\n1033 (7th Cir. 2012). “Diligence” in this context includes not only seeking a\\n\\nwarrant application promptly, but also communicating with the suspect concerning\\n\\nthe specifics of the detention. In Place, for instance, the Court faulted officers for\\n\\nfailing to inform the suspect where and for how long they were taking his bags,\\n\\nand when and how he could get them back. See 462 U.S. at 710. So too, in Farm\\n\\nLabor, the Sixth Circuit observed—in the course of holding that the seizure of two\\n\\nsuspects’ green cards couldn’t be justified based on reasonable suspicion alone—\\n\\nthat an officer had failed to act diligently when he “wait[ed] for four days to return\\n\\n[their] green cards” and that “[t]he unreasonable nature of the seizure was\\n\\nexacerbated by the undisputed fact that [the officer] did not make clear . . . how\\n\\n\\n\\n\\n 13\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 14 of 32\\n\\n\\nlong the documents would be held or when or how he would return them.” 308\\n\\nF.3d at 546–47 (internal quotation marks omitted).3\\n\\n Finally, governmental interest. The final factor looks at the other side of the\\n\\nledger. As the Court explained in Place, “[t]he exception to the probable-cause\\n\\nrequirement for limited seizures of the person recognized in Terry and its progeny\\n\\nrests on a balancing of the competing interests to determine the reasonableness of\\n\\nthe type of seizure.” 462 U.S. at 703. Thus, “[w]e must balance the nature and\\n\\nquality of the intrusion on the individual’s Fourth Amendment interests against the\\n\\nimportance of the governmental interests alleged to justify the intrusion.” Id.\\n\\nIn Place, that meant taking account of the public’s compelling interest in\\n\\n“detecting those who would traffic in deadly drugs for personal profit.” Id.\\n\\n(internal quotation marks omitted).\\n\\n 2\\n\\n How, then, do these considerations stack up in this case? In short, not well\\n\\nfor the government. To begin at the end, we don’t doubt for a moment the\\n\\ngovernment’s “compelling” interest in preventing the creation and distribution of\\n\\nchild pornography. E.g., New York v. Ferber, 458 U.S. 747, 761 (1982). Standing\\n\\nalone, though, that interest can’t counterbalance the duration, intrusion, and\\n3\\n The diligence component of the analysis necessarily intersects with the duration component\\nbecause, “[i]n the ordinary case, the sooner the warrant issues, the sooner the property\\nowner’s possessory rights can be restored if the search reveals nothing incriminating”—and, of\\ncourse, the sooner an officer seeks a warrant, the sooner a warrant can issue. See Mitchell, 565\\nF.3d at 1352 (citation omitted).\\n 14\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 15 of 32\\n\\n\\ndiligence factors, all of which—for reasons we will explain—weigh heavily here in\\n\\nfavor of a determination that the officers’ two-day seizure of Babcock’s phone was\\n\\nnot just a brief “investigatory stop” but rather a full-blown seizure that required a\\n\\nshowing of full-blown probable cause. See Place, 462 U.S. at 699–700.\\n\\n Looking first to duration, the government cites United States v. Brignoni-\\n\\nPonce, 422 U.S. 873, 881 (1975), for the proposition that law enforcement may\\n\\n“conduct a limited warrantless seizure of a person or item ‘on facts that do not\\n\\nconstitute probable cause.’” Br. of Appellee at 15. Brignoni-Ponce, however,\\n\\nconsidered only whether a momentary stop for “a brief question or two” was\\n\\npermissible on less than probable cause. 422 U.S. at 880; see also Place, 462 U.S.\\n\\nat 709 (describing Terry and Brignoni Ponce as involving “momentary” stops).\\n\\nBut that’s a far cry from the two-day pre-warrant seizure at issue here. The\\n\\ngovernment also points to what it calls the “similar” case of Laist, in which we\\n\\nheld that a 25-day delay between a seizure and a warrant was permissible. 702\\n\\nF.3d at 614–15. But Laist isn’t similar at all; the seizure in that case was based on\\n\\nprobable cause, not mere reasonable suspicion. Id.; see also Burgard, 675 F.3d at\\n\\n1033 (explaining, in justifying a six-day delay, that a seizure supported by\\n\\nprobable cause permits a much greater intrusion than a seizure supported by mere\\n\\nreasonable suspicion).\\n\\n\\n\\n\\n 15\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 16 of 32\\n\\n\\n What of the more analogous decisions in Place and Puglisi? The\\n\\ngovernment seeks to distinguish them on the ground that both cases analyzed the\\n\\nseizure of luggage “as essentially a detention of the person.” Br. of Appellant at 16\\n\\nn.4. The government asserts that Puglisi, in particular, is inapt because the Court\\n\\nthere held that “[f]or time even to be relevant, the seizure of luggage must have\\n\\nactually or constructively seized the person.” 723 F.2d at 788.\\n\\n Two responses. For starters, we don’t think that this one line, taken alone,\\n\\nrepresents the holding of Puglisi. See Dantzler v. I.R.S., 183 F.3d 1247, 1251\\n\\n(11th Cir. 1999) (“A judicial opinion is not a statute, and not every sentence in a\\n\\njudicial opinion is law.”). Constructive seizure of the person was not the only\\n\\nelement relevant to whether the luggage detention in Puglisi was permissible based\\n\\non reasonable suspicion alone. Instead, we analyzed the 140-minute seizure\\n\\nagainst Place’s considerations of duration, intrusiveness, and diligence before\\n\\ndeeming the detention unlawful. Puglisi, 723 F.2d at 788, 790–91.\\n\\n Furthermore—and more importantly—it’s not clear why, under the rationale\\n\\nof Place and Puglisi, an officer’s confiscation of a cell phone is any less a\\n\\nconstructive seizure of its owner than his detention of luggage (which, per Place,\\n\\nwould make even 90 minutes too long). In Place the Court reasoned that while a\\n\\nsuspect whose luggage is detained is “technically still free to continue his travels,”\\n\\nthe seizure might nonetheless “effectively restrain” him by disrupting his travel\\n\\n\\n 16\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 17 of 32\\n\\n\\nplans. 462 U.S. at 708. Given the ubiquity of cell phones—and our increasing\\n\\nreliance on them—it’s no stretch to hazard that a modern-day traveler would likely\\n\\nrather arrive in a strange place without her luggage than without her phone.\\n\\nWithout the former, she may be left with only the “clothes on [her] back,” Puglisi,\\n\\n723 F.2d at 786, but without the latter she may be left without directions, hotel\\n\\nreservations, and payment and ride-share apps, not to mention voice, text, and\\n\\nemail communications—in short, isolated and incapacitated. Whatever heft the\\n\\nconstructive-seizure argument has with respect to luggage applies equally (if not a\\n\\nfortiori) to cell phones. In any event, no matter what one thinks about the relative\\n\\nimport of luggage and phones, it’s clear that the duration of the seizure in this case\\n\\nputs it in a different bucket than the on-the-spot inquiry hypothesized in Place, see\\n\\n462 U.S. at 705–706, or carried out in Lawing, see 703 F.3d at 238.4\\n\\n Next, the intrusion into Babcock’s possessory interest in his private property\\n\\nwas serious. For many of the reasons just explained, a person’s possessory interest\\n\\nin his cell phone is at least as high as—if not higher than—his interest in his\\n\\n\\n4\\n The government suggested for the first time at oral argument that, rather than lasting two days,\\nthe reasonable-suspicion-based seizure lasted only until Detective Broughton used the phone to\\nprompt C.A.’s confession, at which time the reasonable suspicion became probable cause and,\\npresumably, washed away any budding issues with the seizure. We decline to wade into this\\nargument when the entire record below is predicated on the seizure lasting two days. Because\\nthe government made no argument—and the district court made no finding—concerning the\\nlength of time between the seizure and the confession, any determination of the same on our part\\nwould be mere speculation. See Byrd v. United States, 138 S. Ct. 1518, 1530 (2018) (declining\\nto consider the government’s argument raised for the first time on appeal when argument was\\npredicated on factual issue “not addressed” below and “unclear” from the record).\\n\\n 17\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 18 of 32\\n\\n\\nluggage. A smart phone, as the Supreme Court recently emphasized, is unique in\\n\\nboth the breadth and depth of personal information it stores, including\\n\\n“photographs, picture messages, text messages, Internet browsing history, a\\n\\ncalendar, a thousand-entry phone book”—information that, all told, “reveal[s]\\n\\nmuch more in combination than any isolated record.” Riley v. California, 573 U.S.\\n\\n373, 394 (2014). In other words, while a piece of luggage may hold certain\\n\\nphysical items that an individual needs for a trip, a cell phone holds “[t]he sum of\\n\\nan individual’s private life”—hence our attentiveness to (which is to say obsession\\n\\nwith) our cell phones. Id. Put simply, the government’s confiscation of Babcock’s\\n\\nphone for a period of two days—and with it his personal messages, contacts,\\n\\ncalendar, and more—worked a serious interference with his possessory interests,\\n\\nand undermines the government’s current contention that the seizure was but a\\n\\n“limited intrusion” allowable based on mere reasonable suspicion.\\n\\n Finally, diligence. Detective Broughton’s actions here—holding onto\\n\\nBabcock’s phone over the weekend rather than more promptly attempting to secure\\n\\na warrant, either telephonically or in person—further confirm that the seizure in\\n\\nthis case looks nothing like a Terry stop. The government has offered no\\n\\nexplanation as to why Detective Broughton waited more than two days to take any\\n\\naction regarding the phone, nor does the record evidence indicate that he explained\\n\\nto Babcock when or whether he could expect to get his phone back. And while a\\n\\n\\n 18\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 19 of 32\\n\\n\\ntwo-day delay certainly wouldn’t cross the line in the probable-cause context, see,\\n\\ne.g., Laist, 702 F.3d at 614–15 (approving a 25-day delay in obtaining a warrant\\n\\nfollowing a probable-cause seizure), we know from precedent that it’s well outside\\n\\nthe realm of a permissible Terry stop, and thus weighs heavily against a finding of\\n\\ndiligence here, see Place, 462 U.S. at 710; Virden, 488 F.3d at 1321; Farm Labor,\\n\\n308 F.3d at 546–47.\\n\\n * * *\\n\\n Accordingly, we reject the government’s contention that the officers’ two-\\n\\nday detention of Babcock’s cell phone was a mere investigatory “stop” allowable\\n\\nbased on reasonable suspicion alone. Rather, we hold that it “ripened” into a full-\\n\\nblown seizure that required probable cause. See Puglisi, 723 F.2d at 784.\\n\\n B\\n\\n The government contends, in the alternative, that it can meet the probable-\\n\\ncause standard and, further, that it can show that exigent circumstances justified a\\n\\nwarrantless seizure. We will consider the two components of the government’s\\n\\nargument in turn, looking first to whether the officers at Babcock’s residence had\\n\\nprobable cause to believe that his phone contained evidence of a crime, and then to\\n\\nwhether exigent circumstances excused them from the need to obtain a warrant\\n\\npre-seizure.\\n\\n\\n\\n\\n 19\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 20 of 32\\n\\n\\n 1\\n\\n Probable cause to seize property is what it sounds like—a belief that\\n\\nevidence will probably be found in a particular location. See United States v.\\n\\nNoriega, 676 F.3d 1252, 1261 (11th Cir. 2012). As the Supreme Court recently\\n\\nreiterated, probable cause “is not a high bar.” District of Columbia v. Wesby, 138\\n\\nS. Ct. 577, 586 (2018) (quoting Kaley v. United States, 571 U.S. 320, 338 (2014)).\\n\\nAlthough probable cause requires more than reasonable suspicion that criminal\\n\\nbehavior is afoot, it doesn’t entail the same “standard of conclusiveness and\\n\\nprobability as the facts necessary to support a conviction.” United States v.\\n\\nDunn, 345 F.3d 1285, 1290 (11th Cir. 2003) (internal quotations omitted). Rather,\\n\\nit requires only “a substantial chance” that evidence of criminal activity exists.\\n\\nIllinois v. Gates, 462 U.S. 213, 243 n.13 (1983). We recently explained that this\\n\\n“substantial chance” exists “where the facts within the collective knowledge of law\\n\\nenforcement officials” suffice “to cause a person of reasonable caution to believe\\n\\nthat a criminal offense has been or is being committed”—and here, that evidence\\n\\nof that offense will be found in a particular place. Gates v. Khokar, 884 F.3d 1290,\\n\\n1298 (11th Cir. 2018) (internal quotation marks omitted).\\n\\n Babcock contends that while the officers in this case might have suspected\\n\\nthat something was up, their collective knowledge at the time of the seizure didn’t\\n\\nrise to the level of probable cause that a crime had been committed. To evaluate\\n\\n\\n 20\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 21 of 32\\n\\n\\nthat contention, let’s recap: At the time Detective Broughton retained Babcock’s\\n\\nphone, the officers knew—\\n\\n • that a domestic-disturbance call had reported a female at Babcock’s\\n residence yelling “Stop, stop, stop!”;\\n\\n • that after Babcock had denied that anyone else was in his camper, a teenage\\n girl emerged with cuts on her legs;\\n\\n • that Babcock had accompanied the girl to a Halloween party the night\\n before, where she had consumed alcohol and drugs, and that she was in his\\n camper the next morning;\\n\\n • that the girl had been in or on Babcock’s bed and left traces of blood there;\\n\\n • that the girl had been distraught, holding a knife to her own throat and\\n saying, “I just want to die”; and\\n\\n • that shortly after they arrived at Babcock’s residence, the girl appeared to be\\n panicking or suffering an overdose.\\n\\nFinally—and perhaps most tellingly—the officers knew that, while the girl sat on\\n\\nBabcock’s bed with the knife to her neck, Babcock called her “dumb as f***” and\\n\\nthen complained—in the present tense—that “this is what I deal with right here . . .\\n\\nyou gotta do drama and fighting me all over the place.”\\n\\n Collectively, these circumstances gave the officers probable cause to believe\\n\\nthat Babcock had committed a crime against C.A. This common-sense conclusion\\n\\ndoesn’t depend on any particular fact taken in isolation; rather, as is “often” the\\n\\ncase, “the whole is . . . greater than the sum of its parts.” Wesby, 138 S. Ct. at 588;\\n\\nsee United States v. Arvizu, 534 U.S. 266, 274 (2002) (rejecting a “divide-and-\\n\\n 21\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 22 of 32\\n\\n\\nconquer” approach and instructing courts to evaluate probable cause in light of the\\n\\ntotality of the circumstances). Here, Babcock’s lies contributed to probable cause,\\n\\nsee Wesby, 138 S. Ct. at 587 (citing Devenpeck v. Alford, 543 U.S. 146, 149, 155–\\n\\n56 (2004)), as did his own present-tense statements clearly indicating an ongoing\\n\\nrelationship. When the officers considered Babcock’s own utterances in light of\\n\\nthe litany of other suspicious facts the learned, they certainly could have suspected\\n\\na “substantial chance of criminal activity.” Gates, 462 U.S. at 243 n.13.\\n\\n From there, it required no leap for the officers to deduce that evidence of a\\n\\ncrime would likely be found on Babcock’s phone. The officers already knew that\\n\\nthe phone contained one eyebrow-raising video suggesting an ongoing relationship\\n\\nbetween a grown man and a teenage girl. It was eminently reasonable for them to\\n\\nbelieve that additional evidence of that relationship—messages, texts, pictures,\\n\\nvideos, etc.—would be found in the same place.\\n\\n True, as Babcock points out, the government has been a little wishy-washy\\n\\nabout the exact crime that the officers suspected at the time of the seizure. The\\n\\ngovernment doesn’t contend that the officers had probable cause to believe that the\\n\\nphone contained evidence of child pornography; rather, it concedes that until\\n\\nDetective Broughton confronted C.A. with the phone at the hospital post-seizure,\\n\\nhe had “no reason to believe that there were videos of sexual activity between [the]\\n\\ntwo.” Importantly, though, our precedent doesn’t require officers to predict the\\n\\n\\n 22\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 23 of 32\\n\\n\\neventually-charged offense in order to demonstrate probable cause, only that the\\n\\ncollective facts would cause a “person of reasonable caution” to believe that “a\\n\\ncriminal offense has been or is being committed.” See Khokar, 884 F.3d at 1298\\n\\n(emphasis added) (internal quotation marks omitted).\\n\\n Here, the government’s arguments at the suppression hearing focused\\n\\nmainly on preserving both the video of C.A. on the bed and any evidence that\\n\\nmight have shed light on the events leading up to it. And indeed, that is exactly\\n\\nwhat the officers ended up finding: evidence of an illegal, coercive relationship,\\n\\nconfirming the suspicions sparked by the video’s portrayal of Babcock’s\\n\\ndisdainful, bullying tone and C.A.’s distraught appearance. The fact that the phone\\n\\nalso (and unexpectedly) contained pornographic images and videos doesn’t\\n\\ninvalidate probable cause for any number of Florida state crimes the officers\\n\\nreasonably could have believed occurred based on the scene greeting them at\\n\\nBabcock’s residence. See, e.g., Fla. Stat. § 794.05(1) (“Unlawful sexual activity\\n\\nwith certain minors”); id. § 794.011(4)(a) (“Sexual battery”). Accordingly, we\\n\\nhold that on these facts the officers had probable cause to believe that Babcock was\\n\\nguilty of a crime, and that evidence of the crime would be found on his phone.\\n\\n 2\\n\\n Of course, probable cause isn’t alone enough to seize an individual’s\\n\\npersonal property—officers typically need a warrant. “[A] warrantless search\\n\\n\\n 23\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 24 of 32\\n\\n\\nand seizure can be justified,” however, “when probable cause has been established\\n\\nto believe that evidence will be removed or destroyed before a warrant can be\\n\\nobtained.” United States v. Young, 909 F.2d 442, 446 (11th Cir. 1990). This\\n\\nexception—one branch of the “exigent-circumstances” doctrine—entails, like\\n\\nprobable cause itself, an objective inquiry. See United States v. Bradley, 644 F.3d\\n\\n1213, 1262 (11th Cir. 2011).\\n\\n Historically, we have found the exigent-circumstances exception\\n\\n“particularly compelling” in drug cases “because contraband and records can be\\n\\neasily and quickly destroyed while a search is progressing.” Young, 909 F.2d at\\n\\n446. The same is true of electronic files. In Bradley, for instance, we found that\\n\\nthe exigent-circumstances exception permitted officers to shut down a company’s\\n\\nservers—a seizure of the company’s property—when multiple employees “had the\\n\\nability and incentive to, after learning of the raid, destroy damning information\\n\\ncontained on the computer servers.” 644 F.3d at 1262–63.\\n\\n To be clear, it’s not that a cell phone itself creates an exigent circumstance.\\n\\n“Taken to its logical conclusion,” that “would permit police officers to seize now-\\n\\nubiquitous cell phones from any person, in any place, at any time, so long as the\\n\\nphone contains photographs or videos that could serve as evidence of a crime—\\n\\nsimply because the ‘nature’ of the device used to capture that evidence might result\\n\\nin it being lost.” Crocker v. Beatty, 886 F.3d 1132, 1137 (11th Cir. 2018)\\n\\n\\n 24\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 25 of 32\\n\\n\\n(emphasis in original). In Crocker, we held that the exigent-circumstances\\n\\nexception didn’t apply where an officer had seized a bystander’s phone to prevent\\n\\ndeletion of photographs that he observed the onlooker snapping following a huge\\n\\nhighway crash. Id. Absent any reason for the officer to think that the bystander\\n\\nwouldn’t preserve the pictures or would refuse to turn them over if asked, we\\n\\nfound the government’s exigent-circumstances argument unconvincing. Id.\\n\\n This case is different. Given the facts here, a reasonable, experienced agent\\n\\ncertainly could have believed that Babcock—the suspect, not a mere bystander—\\n\\nwould delete any incriminating evidence on his phone before a warrant could be\\n\\nobtained. For starters, Babcock had tried to deceive the responding officers from\\n\\nthe get-go, denying that anyone else was in his camper, reporting that C.A. had\\n\\nrandomly shown up at his house in the middle of the night, and claiming that he\\n\\ndidn’t know her age—all lies. Moreover Babcock surely knew that he was under\\n\\nsuspicion once Detective Broughton asked to search the camper and to further\\n\\ninspect his phone. Finally, of course, and on top of all that, the electronic files on\\n\\nBabcock’s phone could have been “quickly destroyed while [the] search [wa]s\\n\\nprogressing.” Young, 909 F.2d at 446. All told, as in Bradley, it was reasonable\\n\\nfor the officers here to conclude that Babcock had the “ability and incentive to,\\n\\nafter learning” of the investigation into his relationship with C.A., “destroy\\n\\n\\n\\n\\n 25\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 26 of 32\\n\\n\\ndamning information contained on” his phone. 644 F.3d at 1262–63. That’s all\\n\\nthe exigent-circumstances doctrine requires. 5\\n\\n Babcock contends that his offer to e-mail the video to the officers removed\\n\\nany urgency, thereby undermining any exigent-circumstances argument. He cites\\n\\nour decision in United States v. Hernandez-Cano, 808 F.2d 779 (11th Cir. 1987),\\n\\nfor the proposition that officers can’t claim exigent circumstances when the\\n\\nsupposed risk can be alleviated by alternative means. But Hernandez-Cano was\\n\\ndifferent—and in fact boomerangs back around on Babcock here. There, we\\n\\nconsidered a warrantless search of a suspect’s luggage and determined that,\\n\\nbecause officers had probable cause to arrest him at the time of the search, “any\\n\\nexigencies inherent in the situation could have been removed” by simply doing so.\\n\\n5\\n Babcock asserts that the government forfeited its exigency argument by failing to use the\\nphrase “exigent circumstances”—and failing to fully develop its position regarding the same—in\\nits response to the motion to suppress. We disagree. While it’s true that alternative theories of\\nadmissibility—including exigent circumstances—can be forfeited even when the government is\\nthe appellee or respondent, see Steagald v. United States, 451 U.S. 204, 208 (1981); Giordenello\\nv. United States, 357 U.S. 480, 487–88 (1958), we conclude that the government did enough here\\nto preserve its exigent-circumstances argument. To be sure, in responding to Babcock’s motion\\nto suppress, the government didn’t use the phrase “exigent circumstances” or cite case law\\nspecifically in support of the exception. It did argue, though, that “[t]he deputies had probable\\ncause to believe that the phone had evidentiary value” and that “detention of the cellular phone\\nwas necessary to preserve the evidence observed by the deputies.” Gov’t Resp. Mot. Suppress at\\n5 (emphasis added). That—whether accompanied by magic words or not—is the very definition\\nof the exigent-circumstances exception. See, e.g., Young, 909 F.2d at 446 (“[W]hen probable\\ncause has been established to believe that evidence will be removed or destroyed before a\\nwarrant can be obtained, a warrantless search and seizure can be justified.”). That the\\ngovernment presented a more robust version of its argument on appeal doesn’t render its initial\\nargument null. See, e.g., Sec’y, U.S. Dep’t of Labor v. Preston, 873 F.3d 877, 883 n.5 (11th Cir.\\n2017) (explaining that “[o]ffering a new argument or case citation in support of a position\\nadvanced in the district court is permissible—and often advisable” lest “the quality and depth of\\nargument [fail] to improve on appeal—an unfortunate result”), cert. denied sub nom. Preston v.\\nAcosta, 138 S. Ct. 2680 (2018).\\n 26\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 27 of 32\\n\\n\\nId. at 782. We explained that “[e]ven if exigent circumstances existed that justified\\n\\nthe seizure of the suitcase to prevent the loss or destruction of its contents, the\\n\\ngovernment still had to obtain a warrant to search the suitcase.” Id. (emphasis\\n\\nadded). Here, the officers didn’t conduct a warrantless search. Instead, faced with\\n\\nthe potential destruction of evidence, they did exactly what Hernandez-Cano\\n\\nsuggests they should have done—they seized the phone “to prevent the loss or\\n\\ndestruction of its contents,” and then obtained a warrant before searching through\\n\\nit. See id.\\n\\n Thus, because a reasonable officer could have believed that Babcock would\\n\\ndelete any incriminating evidence on his phone before a warrant could be\\n\\nobtained—and because none of Babcock’s arguments convinces us otherwise—we\\n\\nfind that the exigent-circumstances exception applies in this case. 6\\n\\n * * *\\n\\n\\n6\\n The government also argues in the alternative that Babcock consented to the seizure by\\nvoluntarily providing his phone to the officers to display the video of C.A. threatening self-harm.\\nIt is well-settled, however, that “the scope of a search based on consent may not exceed the\\nscope of the given consent.” United States v. Watkins, 760 F.3d 1271, 1279 (11th Cir. 2014)\\n(citing Florida v. Jimeno, 500 U.S. 248, 251 (1991)). The standard for measuring the scope of\\nconsent is “objective reasonableness”—what “would the typical reasonable person have\\nunderstood by the exchange between the officer and the [individual giving the consent]?” Id.\\n(internal quotation marks omitted). Here, Babcock clearly consented only to the officers’\\nviewing the video he showed them. After the initial viewing, Deputy Olson asked for the phone\\nagain, for the express purpose of showing Officer McMahan the video. Babcock consented to\\nthe officers viewing the clip again, but then asked for his phone back and refused consent when\\nDetective Broughton asked to poke around further. Contrary to the government’s contention, the\\ninitial limited-in-scope consent doesn’t justify an unlimited-in-scope full seizure over Babcock’s\\nobjection.\\n\\n 27\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 28 of 32\\n\\n\\n To sum up, we reject the government’s contention that a two-day\\n\\nwarrantless seizure of a suspect’s cell phone is permissible based on reasonable\\n\\nsuspicion alone. We conclude, however, that the warrantless seizure of Babcock’s\\n\\nphone was lawful because the officers on the scene had probable cause to believe\\n\\nboth that evidence of a crime would be found on it and that the evidence would be\\n\\ndestroyed before they could obtain a warrant.\\n\\n III\\n\\n Babcock separately challenges his sentence, arguing that it is both (1)\\n\\nprocedurally unreasonable because the district court erroneously imposed two\\n\\nenhancements for the same harm and (2) substantively unreasonable because it is\\n\\ntoo harsh in light of the facts.7 Neither argument is persuasive.\\n\\n Babcock raises his procedural-reasonableness argument for the first time on\\n\\nappeal, so we can correct any missteps only if he shows a “plain error” that affects\\n\\nhis substantial rights and that seriously undermines the fairness, integrity, or public\\n\\nreputation of judicial proceedings. See United States v. Shelton, 400 F.3d 1325,\\n\\n1328–29 (11th Cir. 2005). Babcock essentially argues that the district court’s\\n\\napplication of both § 2G2.1(b)(2) and § 4B1.5(b) of the Sentencing Guidelines\\n\\nconstitutes impermissible double-counting.\\n\\n7\\n Babcock also argues that his sentence is procedurally unreasonable because the government did\\nnot group two counts of conviction which were based on the same harm. As the government\\npoints out, though, the Guidelines specifically exclude convictions under § 2G2.1 from the\\ngrouping rules. See U.S.S.G. § 3D1.2(d).\\n\\n 28\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 29 of 32\\n\\n\\n Double-counting occurs when one part of the Sentencing Guidelines is\\n\\napplied to increase a defendant’s punishment on account of a harm that has already\\n\\nbeen fully accounted for by application of another part of the Guidelines. See\\n\\nUnited States v. Dudley, 463 F.3d 1221, 1226–27 (11th Cir. 2006). Absent\\n\\nevidence to the contrary, however, the presumption is that “the Sentencing\\n\\nCommission intended to apply separate sections cumulatively,” United States v.\\n\\nKapordelis, 569 F.3d 1291, 1315 (11th Cir. 2009) (citation omitted), such that\\n\\nwhat might appear to be impermissible double-counting is instead what we will\\n\\ncall permissible “cumulative-counting.”\\n\\n We conclude that applying both enhancements in this case constitutes\\n\\ncumulative- (rather than double-) counting. Chapter Two of the Guidelines,\\n\\nfocusing on the sexual exploitation of minors through pictures, provides that an\\n\\noffender’s base sentencing level should be enhanced by two when “the commission\\n\\nof a sexual act or sexual contact” occurs during a visual depiction. U.S.S.G.\\n\\n§ 2G2.1(b)(2)(A). Chapter Four then makes clear that when a “pattern of . . .\\n\\nprohibited sexual contact” occurs, a court should add five to “the offense level\\n\\ndetermined under Chapter[] Two.” U.S.S.G. § 4B1.5(b). The Guidelines say\\n\\nnothing about adding this enhancement to only a portion of the base level\\n\\ndetermined under Chapter Two, or otherwise adjusting the calculation in any\\n\\nway—instead, they simply presuppose that a certain offense level was determined\\n\\n\\n 29\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 30 of 32\\n\\n\\nunder Chapter Two, and then instruct the sentencing court to add five levels,\\n\\nperiod. Nothing in the Guidelines, then, indicates that these sections may not be\\n\\napplied cumulatively. See Kapordelis, 569 F.3d at 1315. Moreover, and in any\\n\\nevent, it isn’t clear that the harm in § 4B1.5(b)’s “pattern of activity involving\\n\\nprohibited sexual contact” is “fully accounted for” in § 2G2.1(b)(2)’s “sexual act\\n\\nor sexual contact” occurring in a visual depiction, such that application of the two\\n\\nsections could be considered double-counting at all. See Dudley, 463 F.3d at\\n\\n1226–27. There was no plain error here.\\n\\n Looking next to substantive reasonableness, Babcock argues that the nature\\n\\nand circumstances of this case do not compel the same severe sentence required to\\n\\ndeter creators of commercial child pornography. Basically, Babcock contends that\\n\\nhis crime—an inappropriate, long-term relationship with an older teenager—\\n\\ndoesn’t indicate that he is a threat to children generally or affect the child-\\n\\npornography market as would, for instance, the rape of a child for video\\n\\ndistribution or other predatory production of commercial child pornography.\\n\\nBabcock asserts that because there is no evidence that he intended ever to show\\n\\nanyone his videos or pictures of C.A., his 324-month sentence is substantively\\n\\nunreasonable.\\n\\n We review challenges to the substantive reasonableness of a sentence for\\n\\nabuse of discretion. Gall v. United States, 552 U.S. 38, 41 (2007). The party\\n\\n\\n 30\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 31 of 32\\n\\n\\nchallenging the sentence bears the burden of showing that the sentence is\\n\\nunreasonable in light of the record and the 18 U.S.C. § 3553(a) factors. United\\n\\nStates v. Tome, 611 F.3d 1371, 1378 (11th Cir. 2010). While we do not formally\\n\\npresume that a within-Guidelines sentence is reasonable, we ordinarily expect it to\\n\\nbe so. United States v. Hunt, 526 F.3d 739, 746 (11th Cir. 2008). That a sentence\\n\\nis imposed well below the statutory maximum penalty may also indicate its\\n\\nreasonableness. See United States v. Gonzalez, 550 F.3d 1319, 1324 (11th Cir.\\n\\n2008) (per curiam).\\n\\n There is a certain intuitive logic to Babcock’s argument here—it’s true that\\n\\nnothing in the record necessarily indicates a propensity to distribute child\\n\\npornography. That being said, Babcock’s conduct falls squarely within the\\n\\nconfines of § 2G2.1—“sexually exploiting a minor by production of sexually\\n\\nexplicit visual or printed material”—and, as the sentencing judge emphasized, the\\n\\neffect of his actions on C.A. and her family was far from insignificant. We are\\n\\ncomfortable that the sentencing judge took into consideration all of the relevant\\n\\ncircumstances when he sentenced Babcock to 324 months—a downward variance\\n\\nfrom the 360 to 720 months recommended by the Guidelines. See Gonzalez, 550\\n\\nF.3d at 1324. Accordingly, we find no abuse of discretion in the district court’s\\n\\nsentencing decision.\\n\\n\\n\\n\\n 31\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 32 of 32\\n\\n\\n IV\\n\\n For the foregoing reasons, we hold (1) that reasonable suspicion alone could\\n\\nnot have justified the officers’ warrantless two-day seizure of Babcock’s cell\\n\\nphone; (2) that the officers in this case had probable cause to believe that a crime\\n\\nhad been committed, that evidence of the crime would be found on Babcock’s\\n\\nphone, and that there was a risk that Babcock would destroy the evidence before\\n\\nthey could get a warrant, such that the seizure did not violate the Fourth\\n\\nAmendment; and (3) that Babcock’s sentence was both procedurally and\\n\\nsubstantively reasonable. Accordingly, we affirm the district court’s denial of\\n\\nBabcock’s motion to suppress as well as its 324-month sentence.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 32\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4400288/\", \"author_raw\": \"NEWSOM, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"PRYOR"},"judge2":{"kind":"string","value":"NEWSOM"},"judge3":{"kind":"string","value":"VRATIL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4623035/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Darrell Mark BABCOCK, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-24\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-13678 Date Filed: 05/24/2019 Page: 1 of 32\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-13678\n ________________________\n\n D.C. Docket No. 2:16-cr-14071-KAM-1\n\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\nversus\n\nDARRELL MARK BABCOCK,\n\n Defendant - Appellant.\n\n ________________________\n\n Appeal from the United States District Court\n for the Southern District of Florida\n ________________________\n\n (May 23, 2019)\n\nBefore WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District\nJudge.\n\n\n\n\n*\n The Honorable Kathryn H. Vratil, United States District Court Judge for the District of Kansas,\nsitting by designation.\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 2 of 32\n\n\nNEWSOM, Circuit Judge:\n\n In this case, police officers investigating a domestic disturbance confiscated\n\na suspect’s cell phone and held it for two days before eventually obtaining a\n\nwarrant to search it. The appeal before us presents two Fourth Amendment\n\nquestions. First, was the seizure justified on the ground that the officers had\n\nreasonable suspicion to believe that the phone’s owner was engaged in criminal\n\nwrongdoing—was it, in effect, a permissible “Terry stop” of the phone? We hold\n\nthat it was not. Second, in the particular circumstances of this case, did the officers\n\nhave probable cause to believe not only that the phone’s owner had committed a\n\ncrime and that the phone contained evidence of that crime, but also that the suspect\n\nwould likely destroy that evidence before they could procure a warrant? We hold\n\nthat they did. Accordingly, and on that ground, we affirm the district court’s order\n\ndenying the motion to suppress. We separately affirm the district court’s sentence.\n\n I\n\n A\n\n Early one Friday morning, Deputy Andrea Olson of the Stuart, Florida\n\nPolice Department responded to a domestic-disturbance call reporting a ruckus\n\ncoming from a camper parked at Darrell Babcock’s residence—specifically, a\n\nfemale had been heard yelling, “Stop, stop, stop!” When Deputy Olson knocked\n\non the door of Babcock’s camper, Babcock exited, closed the door behind him, and\n\n\n 2\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 3 of 32\n\n\nvolunteered that no one else was inside. Almost immediately, though, Deputy\n\nOlson heard a female announce that she was coming out. A teenage girl emerged\n\nfrom the trailer; she was wearing only yoga shorts and a camo jacket, and she had\n\nblood on her left thigh. Seemingly by way of explanation, Babcock handed\n\nDeputy Olson his cell phone to show her a video of the girl—we’ll call her C.A.—\n\nsitting on a bed, holding a knife to her own throat and saying that she wanted to\n\ndie. In the video Babcock could be heard berating the girl, telling her, “you’re\n\ndumb as f***” and complaining, “this is what I deal with right here . . . you gotta\n\ndo drama and fighting me all over the place.” After viewing the clip, Deputy\n\nOlson returned Babcock’s phone. When backup arrived on the scene, Deputy\n\nOlson asked for the phone again so that she could show the video to her colleague,\n\nOfficer Michael McMahan.\n\n The officers then interviewed Babcock and C.A. separately. Babcock denied\n\nknowing C.A.’s age and also disputed that the two were in a relationship, although\n\nhe admitted that he had known C.A. for three years and that she used to be his\n\nneighbor. He also said that C.A. had shown up at his camper unannounced,\n\nsometime during the middle of the night. C.A., by contrast—whose license\n\nshowed that she was only 16 years old—stated that she and Babcock had gone\n\ntogether the night before to a Halloween party, where she had consumed alcohol,\n\ncocaine, and other substances. After answering a few questions, C.A. began either\n\n\n 3\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 4 of 32\n\n\npanicking or experiencing the effects of an overdose, so the officers called an\n\nambulance. Deputy Olson rode with C.A. to the hospital.\n\n Meanwhile, another officer, Detective Brian Broughton, remained behind to\n\ncontinue questioning Babcock. Detective Broughton sought and received\n\npermission to search Babcock’s camper, where he discovered blood on the\n\nbedsheets and prescription pills scattered about. When Detective Broughton asked\n\nto further inspect Babcock’s phone, Babcock refused and asked to have it back.\n\nBabcock offered to e-mail the video clip of C.A. with the knife, but Detective\n\nBroughton decided to keep the phone instead. He told Officer McMahan to enter it\n\ninto evidence and then took it with him to the hospital to talk to C.A.\n\n At the hospital, C.A. again insisted that she and Babcock were just friends,\n\nthat they had gone to a Halloween party, and that the two had then argued. She\n\nfirmly denied any further relationship. But when Detective Broughton informed\n\nC.A. that he had Babcock’s phone, she abruptly reversed course and admitted that\n\nthe two had been in a relationship and, further, that the officers would find sexually\n\nexplicit images of her on the phone. Two days later, Detective Broughton applied\n\nfor and obtained a warrant to search the phone, where he found nude images of\n\nC.A. and explicit video recordings of Babcock and C.A. together.\n\n\n\n\n 4\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 5 of 32\n\n\n B\n\n Babcock was charged with two counts of producing a visual depiction of\n\nsexually explicit conduct with a minor in violation of 18 U.S.C. § 2251(a), (e). He\n\nfiled a motion to suppress, arguing that officers had seized his phone without a\n\nwarrant or probable cause. The government filed a response, arguing primarily\n\nthat the cell-phone seizure was reasonable because “under the totality of the\n\ncircumstances” the officers had “reasonable suspicion to investigate further,” and\n\nadding that, at any rate, the officers had probable cause to believe that the phone\n\ncontained evidence of a crime. The government further contended that “detention\n\nof the cell phone was necessary to preserve the evidence observed by the\n\ndeputies.” Finally, the government asserted that, even in the absence of a warrant,\n\neither Babcock’s consent or the inevitability that the images would have been\n\ndiscovered rendered the seizure constitutional.\n\n A magistrate judge recommended that Babcock’s motion be denied. He\n\nconcluded—referencing two distinct Fourth Amendment standards—that “the\n\ncollective knowledge and information received by the officers at the scene\n\nconstituted sufficient probable cause and reasonable suspicion that there may have\n\nbeen a crime committed which may have been preserved on the cell phone.” The\n\ndistrict court agreed, noting—also somewhat vaguely—that the surrounding\n\ncircumstances were “sufficient for law enforcement to suspect inappropriate\n\n\n 5\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 6 of 32\n\n\nconduct between [Babcock] and C.A.” Later, at sentencing, the district judge\n\nfurther remarked that although he “didn’t say [it] in the order,” he was “putting [it]\n\non the record for appellate purposes” that in the video C.A. “appear[ed] to be either\n\nwith no pants on or underwear” and that, based on “what she says and how she\n\nsays it about what she wants to do to herself,” it was “obvious . . . that there was an\n\ninappropriate relationship going on which would have given [the officers]\n\nreasonable probable cause to believe that there was inappropriate sexual activity\n\nbetween” Babcock and C.A. Babcock took a plea, reserving his right to appeal the\n\ndenial of his motion to suppress.\n\n At sentencing, Babcock asked for the mandatory minimum of 180 months,\n\narguing that his conduct, while inappropriate, was outside the core child-\n\npornography-distribution behavior that Congress sought to deter under § 2251(a)\n\nand (e). The government in turn asked for a sentence within the 360-to-720-month\n\nrecommended Guidelines range, stressing the harm to C.A. and her family. The\n\ncourt imposed a below-Guidelines sentence of 324 months. Babcock appealed\n\nboth the denial of his motion to suppress and his sentence.\n\n II\n\n We’ll tackle the Fourth Amendment issues first. A person suffers a\n\n“seizure” of his property within the meaning of the Fourth Amendment when there\n\nis a “meaningful interference” with his possessory interest in it. United States v.\n\n\n 6\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 7 of 32\n\n\nVirden, 488 F.3d 1317, 1321 (11th Cir. 2007).1 While the seizure of private\n\nproperty generally requires a warrant, the Supreme Court has interpreted the\n\nFourth Amendment to allow a warrantless seizure when police can show both (1)\n\nprobable cause to believe that property contains contraband or evidence of a crime\n\nand (2) an applicable warrant exception, such as exigent circumstances. See, e.g.,\n\nKentucky v. King, 563 U.S. 452, 459–60 (2011) (citations omitted). Accordingly,\n\nabsent either a warrant or probable cause plus an exception, police may not seize\n\nprivate property. There is, however, an asterisk. Under a line of luggage-related\n\ncases from the 1980s, police may “briefly detain” property—Terry-stop style—on\n\nthe strength of reasonable suspicion alone. See United States v. Place, 462 U.S.\n\n696, 697–98 (1983); United States v. Puglisi, 723 F.2d 779, 788–89 (11th Cir.\n\n1984).\n\n Here, the government principally argues that these cases permitted the\n\nofficers to detain Babcock’s phone based on their reasonable suspicion that he had\n\ncommitted a crime. Alternatively, the government contends that the officers had\n\nprobable cause to believe that the phone contained evidence of a crime and that\n\nexigent circumstances—namely, the need to prevent the destruction of that\n\nevidence—allowed them to seize the phone. We consider each argument in turn.\n1\n When reviewing the denial of a motion to suppress, we review factual findings for clear error\nand legal determinations de novo. United States v. Gibson, 708 F.3d 1256, 1274 (11th Cir.\n2013). We also review the evidence in the light most favorable to the government, as the\nprevailing party. See United States v. Capers, 708 F.3d 1286, 1295–96 (11th Cir. 2013).\n\n 7\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 8 of 32\n\n\n A\n\n 1\n\n Reasonable suspicion is “a particularized and objective basis” for suspecting\n\na person of criminal activity. Ornelas v. United States, 517 U.S. 690, 696 (1996)\n\n(quotation marks omitted). It requires “specific, articulable, and objective facts\n\nreasonably to suspect” that a crime is being or will soon be committed, Puglisi,\n\n723 F.2d at 789, but “is a less demanding standard than probable cause,” Illinois v.\n\nWardlow, 528 U.S. 119, 123 (2000). In Terry v. Ohio, the Supreme Court\n\nfamously held that, even absent probable cause, police officers may briefly detain\n\nan individual based on reasonable suspicion that he is (or is about to be) engaged in\n\ncriminal activity. See 392 U.S. 1, 30–31 (1968).\n\n The Supreme Court first extended Terry’s rationale from people to property\n\nin United States v. Place, 462 U.S. 696 (1983). There, the Court held that while a\n\nbrief investigatory detention of property could be justified on the basis of\n\nreasonable suspicion alone, an officer’s 90-minute seizure of an airline traveler’s\n\nsuitcase exceeded constitutional boundaries. Id. at 702. In so holding, the Court\n\nrecognized that “[t]he intrusion on possessory interests occasioned by a seizure of\n\none’s personal effects can vary both in its nature and extent.” Id. at 705. While\n\nsome “brief detentions of personal effects”—such as, the Court hypothesized, “on-\n\nthe-spot” dog sniffs—may be “so minimally intrusive” as to “justify a seizure\n\n\n 8\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 9 of 32\n\n\nbased only on specific articulable facts that the property contains contraband,” the\n\nluggage seizure didn’t fit the bill. Id. at 705–06. By way of explanation, the Court\n\nemphasized several factors: the duration of the detention, the degree of the\n\nintrusion on the owner’s possessory interests in his property, and the officer’s lack\n\nof diligence in timely pursuing their investigation. Id. at 709–10. The Court also\n\nhighlighted that a confiscation of luggage, in particular, interferes not only with\n\npossessory interests but also with liberty interests because, while a suspect whose\n\nluggage is stopped is “technically still free to continue” on his way, the detention\n\nmight “effectively restrain” him by disrupting his travel plans. Id. at 708–09.\n\n Shortly after the Supreme Court decided Place, this Court had occasion to\n\napply it on similar facts. In United States v. Puglisi, an officer made what began as\n\na brief stop by ordering a suspicious traveler’s bags removed from a luggage cart;\n\nhe then stowed the luggage in his office until a drug-sniffing dog became available.\n\n723 F.2d 779, 790 (11th Cir. 1984). Meanwhile, the traveler boarded his flight\n\nwithout his bags. Although we deemed the initial seizure permissible under Terry,\n\nwe found that the length and intrusiveness—140 minutes—caused the “brief stop”\n\nto “ripen” into a full-blown seizure that could be justified only by probable cause.\n\nId. at 784. We explained that “Place requires the same test as Terry: a court must\n\nweigh the intrusiveness of a limited seizure of the individual against society’s\n\ninterest in detection and prevention of crime.” Id. at 785. We cautioned, however,\n\n\n 9\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 10 of 32\n\n\nthat because the Fourth Amendment “protects people, not things,” the focus was\n\nthe effective “seizure of persons, through their luggage.” Id. at 787–88.\n\n Although Place and Puglisi concerned luggage, both this Court and others\n\nhave since indicated that any detention of property based on reasonable suspicion\n\nmust be fairly analogous to a Terry stop, regardless of the item at issue.\n\nAccordingly, we have said, “the factors used to determine whether a Terry stop has\n\nmatured into an arrest are also useful in evaluating whether a seizure of property\n\nrequired probable cause” rather than mere reasonable suspicion. Virden, 488 F.3d\n\nat 1321. Echoing Place, we have said that these factors include, but are not limited\n\nto, (1) the detention’s duration, (2) its intrusiveness, (3) the diligence with which\n\nofficers pursued their investigation, and (4) the law-enforcement purposes served\n\nby the detention. See id.; accord United States v. Gonzalez, 781 F.3d 422, 428–29\n\n(8th Cir. 2015); Farm Labor Org. Comm. v. Ohio State Highway Patrol, 308 F.3d\n\n523, 544–45 (6th Cir. 2002); United States v. $557,933.89, More or Less, in U.S.\n\nFunds, 287 F.3d 66, 86 (2d Cir. 2002). We’ll explain each in a bit more detail here\n\nbefore applying them to the facts of this case\n\n First, duration. Although the Supreme Court has “decline[d] to adopt any\n\noutside time limit for a permissible Terry stop,” the Court in Place observed that it\n\nhad “never approved a seizure of the person for the prolonged 90-minute period\n\ninvolved” in that case and that, on the facts presented there, it wouldn’t approve a\n\n\n 10\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 11 of 32\n\n\n90-minute detention of property, either. 462 U.S. at 709–10. In Virden, this Court\n\nsimilarly determined that an officer’s transfer of a defendant and his car to another\n\nlocation for a dog sniff, “[w]hile not unduly lengthy” at about 30 minutes, was\n\nnonetheless “unreasonable absent probable cause.” 488 F.3d at 1321. 2\n\n At the other end of the spectrum, the Fourth Circuit has approved a seconds-\n\nlong cell-phone stop on the basis of reasonable suspicion alone. In United States v.\n\nLawing, that court held that an officer’s brief detention of a suspect’s phone during\n\na traffic stop—for just long enough to see if it would ring when the officer dialed a\n\nknown drug-distributor’s number—was sufficiently minimal to qualify for\n\nTerry/Place treatment. 703 F.3d 229, 238 (4th Cir. 2012). Similarly, the Second\n\nCircuit held that reasonable suspicion justified a brief investigatory detention that\n\noccurred when a detective took between two and 20 minutes to respond to a\n\nrequest for a luggage investigation while a traveler waited at an airport security\n\ncheckpoint with his luggage. See $557,933.89, More or Less, 287 F.3d at 71, 86–\n\n87 & n.16.\n\n Second, intrusiveness. The “intrusiveness” factor concerns the degree to\n\nwhich a property detention interferes with a person’s possessory interest in his\n\nbelongings. In Place, for instance, the Court emphasized that although “the\n\n2\n Even though the detention there more directly implicated the owner’s liberty interests than in\nPlace because the owner remained in his car while it was transported to another location, we\nanalyzed the stop primarily as one of property rather than of an individual. See Virden, 488 F.3d\nat 1321.\n 11\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 12 of 32\n\n\nparticular course of investigation that the agents intended to pursue”—just a brief\n\n“exposure of respondent’s luggage, which was located in a public place, to a\n\ntrained canine”—would have been permissible based on mere reasonable\n\nsuspicion, the 90-minute seizure that they actually effected was not. 462 U.S. at\n\n707, 709–10 (emphasis added). The Court explained that the planned sniff would\n\nhave revealed “only the presence or absence of narcotics, a contraband item,” and\n\nwouldn’t have exposed the traveler’s personal “noncontraband items that otherwise\n\nwould remain hidden from public view, as [would], for example, an officer’s\n\nrummaging through the contents of the luggage.” Id. at 707.\n\n This Court has likewise recognized that individuals have strong interests in\n\ncontainers that hold personal effects or private information, such as luggage and\n\ncomputers. In Puglisi, we emphasized that “privacy and possessory interests in\n\nluggage are often high” because a traveler may have “his most important and\n\nprivate possessions in his suitcase” and likely wants “to shield them from the\n\nprying eyes of strangers, especially the government.” 723 F.2d at 786. And in\n\nUnited States v. Laist, we acknowledged that “computers are a unique possession,\n\none in which individuals may have a particularly powerful possessory interest,”\n\nbecause they store “personal letters, e-mails, financial information, passwords,\n\nfamily photos, and countless other items of a personal nature.” 702 F.3d 608, 614\n\n(11th Cir. 2012); see also United States v. Mitchell, 565 F.3d 1347, 1352 (11th Cir.\n\n\n 12\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 13 of 32\n\n\n2009) (calling a computer hard drive “the digital equivalent of its owner’s home,\n\ncapable of holding a universe of private information”) (internal quotation marks\n\nomitted).\n\n Third, diligence. When police diligently pursue their investigation, a\n\nreviewing court can have greater confidence that the governmental interest is\n\nlegitimate and that the intrusion occasioned by the challenged detention was no\n\ngreater than reasonably necessary. See United States v. Burgard, 675 F.3d 1029,\n\n1033 (7th Cir. 2012). “Diligence” in this context includes not only seeking a\n\nwarrant application promptly, but also communicating with the suspect concerning\n\nthe specifics of the detention. In Place, for instance, the Court faulted officers for\n\nfailing to inform the suspect where and for how long they were taking his bags,\n\nand when and how he could get them back. See 462 U.S. at 710. So too, in Farm\n\nLabor, the Sixth Circuit observed—in the course of holding that the seizure of two\n\nsuspects’ green cards couldn’t be justified based on reasonable suspicion alone—\n\nthat an officer had failed to act diligently when he “wait[ed] for four days to return\n\n[their] green cards” and that “[t]he unreasonable nature of the seizure was\n\nexacerbated by the undisputed fact that [the officer] did not make clear . . . how\n\n\n\n\n 13\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 14 of 32\n\n\nlong the documents would be held or when or how he would return them.” 308\n\nF.3d at 546–47 (internal quotation marks omitted).3\n\n Finally, governmental interest. The final factor looks at the other side of the\n\nledger. As the Court explained in Place, “[t]he exception to the probable-cause\n\nrequirement for limited seizures of the person recognized in Terry and its progeny\n\nrests on a balancing of the competing interests to determine the reasonableness of\n\nthe type of seizure.” 462 U.S. at 703. Thus, “[w]e must balance the nature and\n\nquality of the intrusion on the individual’s Fourth Amendment interests against the\n\nimportance of the governmental interests alleged to justify the intrusion.” Id.\n\nIn Place, that meant taking account of the public’s compelling interest in\n\n“detecting those who would traffic in deadly drugs for personal profit.” Id.\n\n(internal quotation marks omitted).\n\n 2\n\n How, then, do these considerations stack up in this case? In short, not well\n\nfor the government. To begin at the end, we don’t doubt for a moment the\n\ngovernment’s “compelling” interest in preventing the creation and distribution of\n\nchild pornography. E.g., New York v. Ferber, 458 U.S. 747, 761 (1982). Standing\n\nalone, though, that interest can’t counterbalance the duration, intrusion, and\n3\n The diligence component of the analysis necessarily intersects with the duration component\nbecause, “[i]n the ordinary case, the sooner the warrant issues, the sooner the property\nowner’s possessory rights can be restored if the search reveals nothing incriminating”—and, of\ncourse, the sooner an officer seeks a warrant, the sooner a warrant can issue. See Mitchell, 565\nF.3d at 1352 (citation omitted).\n 14\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 15 of 32\n\n\ndiligence factors, all of which—for reasons we will explain—weigh heavily here in\n\nfavor of a determination that the officers’ two-day seizure of Babcock’s phone was\n\nnot just a brief “investigatory stop” but rather a full-blown seizure that required a\n\nshowing of full-blown probable cause. See Place, 462 U.S. at 699–700.\n\n Looking first to duration, the government cites United States v. Brignoni-\n\nPonce, 422 U.S. 873, 881 (1975), for the proposition that law enforcement may\n\n“conduct a limited warrantless seizure of a person or item ‘on facts that do not\n\nconstitute probable cause.’” Br. of Appellee at 15. Brignoni-Ponce, however,\n\nconsidered only whether a momentary stop for “a brief question or two” was\n\npermissible on less than probable cause. 422 U.S. at 880; see also Place, 462 U.S.\n\nat 709 (describing Terry and Brignoni Ponce as involving “momentary” stops).\n\nBut that’s a far cry from the two-day pre-warrant seizure at issue here. The\n\ngovernment also points to what it calls the “similar” case of Laist, in which we\n\nheld that a 25-day delay between a seizure and a warrant was permissible. 702\n\nF.3d at 614–15. But Laist isn’t similar at all; the seizure in that case was based on\n\nprobable cause, not mere reasonable suspicion. Id.; see also Burgard, 675 F.3d at\n\n1033 (explaining, in justifying a six-day delay, that a seizure supported by\n\nprobable cause permits a much greater intrusion than a seizure supported by mere\n\nreasonable suspicion).\n\n\n\n\n 15\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 16 of 32\n\n\n What of the more analogous decisions in Place and Puglisi? The\n\ngovernment seeks to distinguish them on the ground that both cases analyzed the\n\nseizure of luggage “as essentially a detention of the person.” Br. of Appellant at 16\n\nn.4. The government asserts that Puglisi, in particular, is inapt because the Court\n\nthere held that “[f]or time even to be relevant, the seizure of luggage must have\n\nactually or constructively seized the person.” 723 F.2d at 788.\n\n Two responses. For starters, we don’t think that this one line, taken alone,\n\nrepresents the holding of Puglisi. See Dantzler v. I.R.S., 183 F.3d 1247, 1251\n\n(11th Cir. 1999) (“A judicial opinion is not a statute, and not every sentence in a\n\njudicial opinion is law.”). Constructive seizure of the person was not the only\n\nelement relevant to whether the luggage detention in Puglisi was permissible based\n\non reasonable suspicion alone. Instead, we analyzed the 140-minute seizure\n\nagainst Place’s considerations of duration, intrusiveness, and diligence before\n\ndeeming the detention unlawful. Puglisi, 723 F.2d at 788, 790–91.\n\n Furthermore—and more importantly—it’s not clear why, under the rationale\n\nof Place and Puglisi, an officer’s confiscation of a cell phone is any less a\n\nconstructive seizure of its owner than his detention of luggage (which, per Place,\n\nwould make even 90 minutes too long). In Place the Court reasoned that while a\n\nsuspect whose luggage is detained is “technically still free to continue his travels,”\n\nthe seizure might nonetheless “effectively restrain” him by disrupting his travel\n\n\n 16\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 17 of 32\n\n\nplans. 462 U.S. at 708. Given the ubiquity of cell phones—and our increasing\n\nreliance on them—it’s no stretch to hazard that a modern-day traveler would likely\n\nrather arrive in a strange place without her luggage than without her phone.\n\nWithout the former, she may be left with only the “clothes on [her] back,” Puglisi,\n\n723 F.2d at 786, but without the latter she may be left without directions, hotel\n\nreservations, and payment and ride-share apps, not to mention voice, text, and\n\nemail communications—in short, isolated and incapacitated. Whatever heft the\n\nconstructive-seizure argument has with respect to luggage applies equally (if not a\n\nfortiori) to cell phones. In any event, no matter what one thinks about the relative\n\nimport of luggage and phones, it’s clear that the duration of the seizure in this case\n\nputs it in a different bucket than the on-the-spot inquiry hypothesized in Place, see\n\n462 U.S. at 705–706, or carried out in Lawing, see 703 F.3d at 238.4\n\n Next, the intrusion into Babcock’s possessory interest in his private property\n\nwas serious. For many of the reasons just explained, a person’s possessory interest\n\nin his cell phone is at least as high as—if not higher than—his interest in his\n\n\n4\n The government suggested for the first time at oral argument that, rather than lasting two days,\nthe reasonable-suspicion-based seizure lasted only until Detective Broughton used the phone to\nprompt C.A.’s confession, at which time the reasonable suspicion became probable cause and,\npresumably, washed away any budding issues with the seizure. We decline to wade into this\nargument when the entire record below is predicated on the seizure lasting two days. Because\nthe government made no argument—and the district court made no finding—concerning the\nlength of time between the seizure and the confession, any determination of the same on our part\nwould be mere speculation. See Byrd v. United States, 138 S. Ct. 1518, 1530 (2018) (declining\nto consider the government’s argument raised for the first time on appeal when argument was\npredicated on factual issue “not addressed” below and “unclear” from the record).\n\n 17\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 18 of 32\n\n\nluggage. A smart phone, as the Supreme Court recently emphasized, is unique in\n\nboth the breadth and depth of personal information it stores, including\n\n“photographs, picture messages, text messages, Internet browsing history, a\n\ncalendar, a thousand-entry phone book”—information that, all told, “reveal[s]\n\nmuch more in combination than any isolated record.” Riley v. California, 573 U.S.\n\n373, 394 (2014). In other words, while a piece of luggage may hold certain\n\nphysical items that an individual needs for a trip, a cell phone holds “[t]he sum of\n\nan individual’s private life”—hence our attentiveness to (which is to say obsession\n\nwith) our cell phones. Id. Put simply, the government’s confiscation of Babcock’s\n\nphone for a period of two days—and with it his personal messages, contacts,\n\ncalendar, and more—worked a serious interference with his possessory interests,\n\nand undermines the government’s current contention that the seizure was but a\n\n“limited intrusion” allowable based on mere reasonable suspicion.\n\n Finally, diligence. Detective Broughton’s actions here—holding onto\n\nBabcock’s phone over the weekend rather than more promptly attempting to secure\n\na warrant, either telephonically or in person—further confirm that the seizure in\n\nthis case looks nothing like a Terry stop. The government has offered no\n\nexplanation as to why Detective Broughton waited more than two days to take any\n\naction regarding the phone, nor does the record evidence indicate that he explained\n\nto Babcock when or whether he could expect to get his phone back. And while a\n\n\n 18\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 19 of 32\n\n\ntwo-day delay certainly wouldn’t cross the line in the probable-cause context, see,\n\ne.g., Laist, 702 F.3d at 614–15 (approving a 25-day delay in obtaining a warrant\n\nfollowing a probable-cause seizure), we know from precedent that it’s well outside\n\nthe realm of a permissible Terry stop, and thus weighs heavily against a finding of\n\ndiligence here, see Place, 462 U.S. at 710; Virden, 488 F.3d at 1321; Farm Labor,\n\n308 F.3d at 546–47.\n\n * * *\n\n Accordingly, we reject the government’s contention that the officers’ two-\n\nday detention of Babcock’s cell phone was a mere investigatory “stop” allowable\n\nbased on reasonable suspicion alone. Rather, we hold that it “ripened” into a full-\n\nblown seizure that required probable cause. See Puglisi, 723 F.2d at 784.\n\n B\n\n The government contends, in the alternative, that it can meet the probable-\n\ncause standard and, further, that it can show that exigent circumstances justified a\n\nwarrantless seizure. We will consider the two components of the government’s\n\nargument in turn, looking first to whether the officers at Babcock’s residence had\n\nprobable cause to believe that his phone contained evidence of a crime, and then to\n\nwhether exigent circumstances excused them from the need to obtain a warrant\n\npre-seizure.\n\n\n\n\n 19\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 20 of 32\n\n\n 1\n\n Probable cause to seize property is what it sounds like—a belief that\n\nevidence will probably be found in a particular location. See United States v.\n\nNoriega, 676 F.3d 1252, 1261 (11th Cir. 2012). As the Supreme Court recently\n\nreiterated, probable cause “is not a high bar.” District of Columbia v. Wesby, 138\n\nS. Ct. 577, 586 (2018) (quoting Kaley v. United States, 571 U.S. 320, 338 (2014)).\n\nAlthough probable cause requires more than reasonable suspicion that criminal\n\nbehavior is afoot, it doesn’t entail the same “standard of conclusiveness and\n\nprobability as the facts necessary to support a conviction.” United States v.\n\nDunn, 345 F.3d 1285, 1290 (11th Cir. 2003) (internal quotations omitted). Rather,\n\nit requires only “a substantial chance” that evidence of criminal activity exists.\n\nIllinois v. Gates, 462 U.S. 213, 243 n.13 (1983). We recently explained that this\n\n“substantial chance” exists “where the facts within the collective knowledge of law\n\nenforcement officials” suffice “to cause a person of reasonable caution to believe\n\nthat a criminal offense has been or is being committed”—and here, that evidence\n\nof that offense will be found in a particular place. Gates v. Khokar, 884 F.3d 1290,\n\n1298 (11th Cir. 2018) (internal quotation marks omitted).\n\n Babcock contends that while the officers in this case might have suspected\n\nthat something was up, their collective knowledge at the time of the seizure didn’t\n\nrise to the level of probable cause that a crime had been committed. To evaluate\n\n\n 20\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 21 of 32\n\n\nthat contention, let’s recap: At the time Detective Broughton retained Babcock’s\n\nphone, the officers knew—\n\n • that a domestic-disturbance call had reported a female at Babcock’s\n residence yelling “Stop, stop, stop!”;\n\n • that after Babcock had denied that anyone else was in his camper, a teenage\n girl emerged with cuts on her legs;\n\n • that Babcock had accompanied the girl to a Halloween party the night\n before, where she had consumed alcohol and drugs, and that she was in his\n camper the next morning;\n\n • that the girl had been in or on Babcock’s bed and left traces of blood there;\n\n • that the girl had been distraught, holding a knife to her own throat and\n saying, “I just want to die”; and\n\n • that shortly after they arrived at Babcock’s residence, the girl appeared to be\n panicking or suffering an overdose.\n\nFinally—and perhaps most tellingly—the officers knew that, while the girl sat on\n\nBabcock’s bed with the knife to her neck, Babcock called her “dumb as f***” and\n\nthen complained—in the present tense—that “this is what I deal with right here . . .\n\nyou gotta do drama and fighting me all over the place.”\n\n Collectively, these circumstances gave the officers probable cause to believe\n\nthat Babcock had committed a crime against C.A. This common-sense conclusion\n\ndoesn’t depend on any particular fact taken in isolation; rather, as is “often” the\n\ncase, “the whole is . . . greater than the sum of its parts.” Wesby, 138 S. Ct. at 588;\n\nsee United States v. Arvizu, 534 U.S. 266, 274 (2002) (rejecting a “divide-and-\n\n 21\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 22 of 32\n\n\nconquer” approach and instructing courts to evaluate probable cause in light of the\n\ntotality of the circumstances). Here, Babcock’s lies contributed to probable cause,\n\nsee Wesby, 138 S. Ct. at 587 (citing Devenpeck v. Alford, 543 U.S. 146, 149, 155–\n\n56 (2004)), as did his own present-tense statements clearly indicating an ongoing\n\nrelationship. When the officers considered Babcock’s own utterances in light of\n\nthe litany of other suspicious facts the learned, they certainly could have suspected\n\na “substantial chance of criminal activity.” Gates, 462 U.S. at 243 n.13.\n\n From there, it required no leap for the officers to deduce that evidence of a\n\ncrime would likely be found on Babcock’s phone. The officers already knew that\n\nthe phone contained one eyebrow-raising video suggesting an ongoing relationship\n\nbetween a grown man and a teenage girl. It was eminently reasonable for them to\n\nbelieve that additional evidence of that relationship—messages, texts, pictures,\n\nvideos, etc.—would be found in the same place.\n\n True, as Babcock points out, the government has been a little wishy-washy\n\nabout the exact crime that the officers suspected at the time of the seizure. The\n\ngovernment doesn’t contend that the officers had probable cause to believe that the\n\nphone contained evidence of child pornography; rather, it concedes that until\n\nDetective Broughton confronted C.A. with the phone at the hospital post-seizure,\n\nhe had “no reason to believe that there were videos of sexual activity between [the]\n\ntwo.” Importantly, though, our precedent doesn’t require officers to predict the\n\n\n 22\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 23 of 32\n\n\neventually-charged offense in order to demonstrate probable cause, only that the\n\ncollective facts would cause a “person of reasonable caution” to believe that “a\n\ncriminal offense has been or is being committed.” See Khokar, 884 F.3d at 1298\n\n(emphasis added) (internal quotation marks omitted).\n\n Here, the government’s arguments at the suppression hearing focused\n\nmainly on preserving both the video of C.A. on the bed and any evidence that\n\nmight have shed light on the events leading up to it. And indeed, that is exactly\n\nwhat the officers ended up finding: evidence of an illegal, coercive relationship,\n\nconfirming the suspicions sparked by the video’s portrayal of Babcock’s\n\ndisdainful, bullying tone and C.A.’s distraught appearance. The fact that the phone\n\nalso (and unexpectedly) contained pornographic images and videos doesn’t\n\ninvalidate probable cause for any number of Florida state crimes the officers\n\nreasonably could have believed occurred based on the scene greeting them at\n\nBabcock’s residence. See, e.g., Fla. Stat. § 794.05(1) (“Unlawful sexual activity\n\nwith certain minors”); id. § 794.011(4)(a) (“Sexual battery”). Accordingly, we\n\nhold that on these facts the officers had probable cause to believe that Babcock was\n\nguilty of a crime, and that evidence of the crime would be found on his phone.\n\n 2\n\n Of course, probable cause isn’t alone enough to seize an individual’s\n\npersonal property—officers typically need a warrant. “[A] warrantless search\n\n\n 23\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 24 of 32\n\n\nand seizure can be justified,” however, “when probable cause has been established\n\nto believe that evidence will be removed or destroyed before a warrant can be\n\nobtained.” United States v. Young, 909 F.2d 442, 446 (11th Cir. 1990). This\n\nexception—one branch of the “exigent-circumstances” doctrine—entails, like\n\nprobable cause itself, an objective inquiry. See United States v. Bradley, 644 F.3d\n\n1213, 1262 (11th Cir. 2011).\n\n Historically, we have found the exigent-circumstances exception\n\n“particularly compelling” in drug cases “because contraband and records can be\n\neasily and quickly destroyed while a search is progressing.” Young, 909 F.2d at\n\n446. The same is true of electronic files. In Bradley, for instance, we found that\n\nthe exigent-circumstances exception permitted officers to shut down a company’s\n\nservers—a seizure of the company’s property—when multiple employees “had the\n\nability and incentive to, after learning of the raid, destroy damning information\n\ncontained on the computer servers.” 644 F.3d at 1262–63.\n\n To be clear, it’s not that a cell phone itself creates an exigent circumstance.\n\n“Taken to its logical conclusion,” that “would permit police officers to seize now-\n\nubiquitous cell phones from any person, in any place, at any time, so long as the\n\nphone contains photographs or videos that could serve as evidence of a crime—\n\nsimply because the ‘nature’ of the device used to capture that evidence might result\n\nin it being lost.” Crocker v. Beatty, 886 F.3d 1132, 1137 (11th Cir. 2018)\n\n\n 24\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 25 of 32\n\n\n(emphasis in original). In Crocker, we held that the exigent-circumstances\n\nexception didn’t apply where an officer had seized a bystander’s phone to prevent\n\ndeletion of photographs that he observed the onlooker snapping following a huge\n\nhighway crash. Id. Absent any reason for the officer to think that the bystander\n\nwouldn’t preserve the pictures or would refuse to turn them over if asked, we\n\nfound the government’s exigent-circumstances argument unconvincing. Id.\n\n This case is different. Given the facts here, a reasonable, experienced agent\n\ncertainly could have believed that Babcock—the suspect, not a mere bystander—\n\nwould delete any incriminating evidence on his phone before a warrant could be\n\nobtained. For starters, Babcock had tried to deceive the responding officers from\n\nthe get-go, denying that anyone else was in his camper, reporting that C.A. had\n\nrandomly shown up at his house in the middle of the night, and claiming that he\n\ndidn’t know her age—all lies. Moreover Babcock surely knew that he was under\n\nsuspicion once Detective Broughton asked to search the camper and to further\n\ninspect his phone. Finally, of course, and on top of all that, the electronic files on\n\nBabcock’s phone could have been “quickly destroyed while [the] search [wa]s\n\nprogressing.” Young, 909 F.2d at 446. All told, as in Bradley, it was reasonable\n\nfor the officers here to conclude that Babcock had the “ability and incentive to,\n\nafter learning” of the investigation into his relationship with C.A., “destroy\n\n\n\n\n 25\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 26 of 32\n\n\ndamning information contained on” his phone. 644 F.3d at 1262–63. That’s all\n\nthe exigent-circumstances doctrine requires. 5\n\n Babcock contends that his offer to e-mail the video to the officers removed\n\nany urgency, thereby undermining any exigent-circumstances argument. He cites\n\nour decision in United States v. Hernandez-Cano, 808 F.2d 779 (11th Cir. 1987),\n\nfor the proposition that officers can’t claim exigent circumstances when the\n\nsupposed risk can be alleviated by alternative means. But Hernandez-Cano was\n\ndifferent—and in fact boomerangs back around on Babcock here. There, we\n\nconsidered a warrantless search of a suspect’s luggage and determined that,\n\nbecause officers had probable cause to arrest him at the time of the search, “any\n\nexigencies inherent in the situation could have been removed” by simply doing so.\n\n5\n Babcock asserts that the government forfeited its exigency argument by failing to use the\nphrase “exigent circumstances”—and failing to fully develop its position regarding the same—in\nits response to the motion to suppress. We disagree. While it’s true that alternative theories of\nadmissibility—including exigent circumstances—can be forfeited even when the government is\nthe appellee or respondent, see Steagald v. United States, 451 U.S. 204, 208 (1981); Giordenello\nv. United States, 357 U.S. 480, 487–88 (1958), we conclude that the government did enough here\nto preserve its exigent-circumstances argument. To be sure, in responding to Babcock’s motion\nto suppress, the government didn’t use the phrase “exigent circumstances” or cite case law\nspecifically in support of the exception. It did argue, though, that “[t]he deputies had probable\ncause to believe that the phone had evidentiary value” and that “detention of the cellular phone\nwas necessary to preserve the evidence observed by the deputies.” Gov’t Resp. Mot. Suppress at\n5 (emphasis added). That—whether accompanied by magic words or not—is the very definition\nof the exigent-circumstances exception. See, e.g., Young, 909 F.2d at 446 (“[W]hen probable\ncause has been established to believe that evidence will be removed or destroyed before a\nwarrant can be obtained, a warrantless search and seizure can be justified.”). That the\ngovernment presented a more robust version of its argument on appeal doesn’t render its initial\nargument null. See, e.g., Sec’y, U.S. Dep’t of Labor v. Preston, 873 F.3d 877, 883 n.5 (11th Cir.\n2017) (explaining that “[o]ffering a new argument or case citation in support of a position\nadvanced in the district court is permissible—and often advisable” lest “the quality and depth of\nargument [fail] to improve on appeal—an unfortunate result”), cert. denied sub nom. Preston v.\nAcosta, 138 S. Ct. 2680 (2018).\n 26\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 27 of 32\n\n\nId. at 782. We explained that “[e]ven if exigent circumstances existed that justified\n\nthe seizure of the suitcase to prevent the loss or destruction of its contents, the\n\ngovernment still had to obtain a warrant to search the suitcase.” Id. (emphasis\n\nadded). Here, the officers didn’t conduct a warrantless search. Instead, faced with\n\nthe potential destruction of evidence, they did exactly what Hernandez-Cano\n\nsuggests they should have done—they seized the phone “to prevent the loss or\n\ndestruction of its contents,” and then obtained a warrant before searching through\n\nit. See id.\n\n Thus, because a reasonable officer could have believed that Babcock would\n\ndelete any incriminating evidence on his phone before a warrant could be\n\nobtained—and because none of Babcock’s arguments convinces us otherwise—we\n\nfind that the exigent-circumstances exception applies in this case. 6\n\n * * *\n\n\n6\n The government also argues in the alternative that Babcock consented to the seizure by\nvoluntarily providing his phone to the officers to display the video of C.A. threatening self-harm.\nIt is well-settled, however, that “the scope of a search based on consent may not exceed the\nscope of the given consent.” United States v. Watkins, 760 F.3d 1271, 1279 (11th Cir. 2014)\n(citing Florida v. Jimeno, 500 U.S. 248, 251 (1991)). The standard for measuring the scope of\nconsent is “objective reasonableness”—what “would the typical reasonable person have\nunderstood by the exchange between the officer and the [individual giving the consent]?” Id.\n(internal quotation marks omitted). Here, Babcock clearly consented only to the officers’\nviewing the video he showed them. After the initial viewing, Deputy Olson asked for the phone\nagain, for the express purpose of showing Officer McMahan the video. Babcock consented to\nthe officers viewing the clip again, but then asked for his phone back and refused consent when\nDetective Broughton asked to poke around further. Contrary to the government’s contention, the\ninitial limited-in-scope consent doesn’t justify an unlimited-in-scope full seizure over Babcock’s\nobjection.\n\n 27\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 28 of 32\n\n\n To sum up, we reject the government’s contention that a two-day\n\nwarrantless seizure of a suspect’s cell phone is permissible based on reasonable\n\nsuspicion alone. We conclude, however, that the warrantless seizure of Babcock’s\n\nphone was lawful because the officers on the scene had probable cause to believe\n\nboth that evidence of a crime would be found on it and that the evidence would be\n\ndestroyed before they could obtain a warrant.\n\n III\n\n Babcock separately challenges his sentence, arguing that it is both (1)\n\nprocedurally unreasonable because the district court erroneously imposed two\n\nenhancements for the same harm and (2) substantively unreasonable because it is\n\ntoo harsh in light of the facts.7 Neither argument is persuasive.\n\n Babcock raises his procedural-reasonableness argument for the first time on\n\nappeal, so we can correct any missteps only if he shows a “plain error” that affects\n\nhis substantial rights and that seriously undermines the fairness, integrity, or public\n\nreputation of judicial proceedings. See United States v. Shelton, 400 F.3d 1325,\n\n1328–29 (11th Cir. 2005). Babcock essentially argues that the district court’s\n\napplication of both § 2G2.1(b)(2) and § 4B1.5(b) of the Sentencing Guidelines\n\nconstitutes impermissible double-counting.\n\n7\n Babcock also argues that his sentence is procedurally unreasonable because the government did\nnot group two counts of conviction which were based on the same harm. As the government\npoints out, though, the Guidelines specifically exclude convictions under § 2G2.1 from the\ngrouping rules. See U.S.S.G. § 3D1.2(d).\n\n 28\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 29 of 32\n\n\n Double-counting occurs when one part of the Sentencing Guidelines is\n\napplied to increase a defendant’s punishment on account of a harm that has already\n\nbeen fully accounted for by application of another part of the Guidelines. See\n\nUnited States v. Dudley, 463 F.3d 1221, 1226–27 (11th Cir. 2006). Absent\n\nevidence to the contrary, however, the presumption is that “the Sentencing\n\nCommission intended to apply separate sections cumulatively,” United States v.\n\nKapordelis, 569 F.3d 1291, 1315 (11th Cir. 2009) (citation omitted), such that\n\nwhat might appear to be impermissible double-counting is instead what we will\n\ncall permissible “cumulative-counting.”\n\n We conclude that applying both enhancements in this case constitutes\n\ncumulative- (rather than double-) counting. Chapter Two of the Guidelines,\n\nfocusing on the sexual exploitation of minors through pictures, provides that an\n\noffender’s base sentencing level should be enhanced by two when “the commission\n\nof a sexual act or sexual contact” occurs during a visual depiction. U.S.S.G.\n\n§ 2G2.1(b)(2)(A). Chapter Four then makes clear that when a “pattern of . . .\n\nprohibited sexual contact” occurs, a court should add five to “the offense level\n\ndetermined under Chapter[] Two.” U.S.S.G. § 4B1.5(b). The Guidelines say\n\nnothing about adding this enhancement to only a portion of the base level\n\ndetermined under Chapter Two, or otherwise adjusting the calculation in any\n\nway—instead, they simply presuppose that a certain offense level was determined\n\n\n 29\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 30 of 32\n\n\nunder Chapter Two, and then instruct the sentencing court to add five levels,\n\nperiod. Nothing in the Guidelines, then, indicates that these sections may not be\n\napplied cumulatively. See Kapordelis, 569 F.3d at 1315. Moreover, and in any\n\nevent, it isn’t clear that the harm in § 4B1.5(b)’s “pattern of activity involving\n\nprohibited sexual contact” is “fully accounted for” in § 2G2.1(b)(2)’s “sexual act\n\nor sexual contact” occurring in a visual depiction, such that application of the two\n\nsections could be considered double-counting at all. See Dudley, 463 F.3d at\n\n1226–27. There was no plain error here.\n\n Looking next to substantive reasonableness, Babcock argues that the nature\n\nand circumstances of this case do not compel the same severe sentence required to\n\ndeter creators of commercial child pornography. Basically, Babcock contends that\n\nhis crime—an inappropriate, long-term relationship with an older teenager—\n\ndoesn’t indicate that he is a threat to children generally or affect the child-\n\npornography market as would, for instance, the rape of a child for video\n\ndistribution or other predatory production of commercial child pornography.\n\nBabcock asserts that because there is no evidence that he intended ever to show\n\nanyone his videos or pictures of C.A., his 324-month sentence is substantively\n\nunreasonable.\n\n We review challenges to the substantive reasonableness of a sentence for\n\nabuse of discretion. Gall v. United States, 552 U.S. 38, 41 (2007). The party\n\n\n 30\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 31 of 32\n\n\nchallenging the sentence bears the burden of showing that the sentence is\n\nunreasonable in light of the record and the 18 U.S.C. § 3553(a) factors. United\n\nStates v. Tome, 611 F.3d 1371, 1378 (11th Cir. 2010). While we do not formally\n\npresume that a within-Guidelines sentence is reasonable, we ordinarily expect it to\n\nbe so. United States v. Hunt, 526 F.3d 739, 746 (11th Cir. 2008). That a sentence\n\nis imposed well below the statutory maximum penalty may also indicate its\n\nreasonableness. See United States v. Gonzalez, 550 F.3d 1319, 1324 (11th Cir.\n\n2008) (per curiam).\n\n There is a certain intuitive logic to Babcock’s argument here—it’s true that\n\nnothing in the record necessarily indicates a propensity to distribute child\n\npornography. That being said, Babcock’s conduct falls squarely within the\n\nconfines of § 2G2.1—“sexually exploiting a minor by production of sexually\n\nexplicit visual or printed material”—and, as the sentencing judge emphasized, the\n\neffect of his actions on C.A. and her family was far from insignificant. We are\n\ncomfortable that the sentencing judge took into consideration all of the relevant\n\ncircumstances when he sentenced Babcock to 324 months—a downward variance\n\nfrom the 360 to 720 months recommended by the Guidelines. See Gonzalez, 550\n\nF.3d at 1324. Accordingly, we find no abuse of discretion in the district court’s\n\nsentencing decision.\n\n\n\n\n 31\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 32 of 32\n\n\n IV\n\n For the foregoing reasons, we hold (1) that reasonable suspicion alone could\n\nnot have justified the officers’ warrantless two-day seizure of Babcock’s cell\n\nphone; (2) that the officers in this case had probable cause to believe that a crime\n\nhad been committed, that evidence of the crime would be found on Babcock’s\n\nphone, and that there was a risk that Babcock would destroy the evidence before\n\nthey could get a warrant, such that the seizure did not violate the Fourth\n\nAmendment; and (3) that Babcock’s sentence was both procedurally and\n\nsubstantively reasonable. Accordingly, we affirm the district court’s denial of\n\nBabcock’s motion to suppress as well as its 324-month sentence.\n\n AFFIRMED.\n\n\n\n\n 32\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: UNITED STATES of America, Plaintiff - Appellee, v. Darrell Mark BABCOCK, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-24\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-13678 Date Filed: 05/24/2019 Page: 1 of 32\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-13678\\n ________________________\\n\\n D.C. Docket No. 2:16-cr-14071-KAM-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nDARRELL MARK BABCOCK,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 23, 2019)\\n\\nBefore WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District\\nJudge.\\n\\n\\n\\n\\n*\\n The Honorable Kathryn H. Vratil, United States District Court Judge for the District of Kansas,\\nsitting by designation.\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 2 of 32\\n\\n\\nNEWSOM, Circuit Judge:\\n\\n In this case, police officers investigating a domestic disturbance confiscated\\n\\na suspect’s cell phone and held it for two days before eventually obtaining a\\n\\nwarrant to search it. The appeal before us presents two Fourth Amendment\\n\\nquestions. First, was the seizure justified on the ground that the officers had\\n\\nreasonable suspicion to believe that the phone’s owner was engaged in criminal\\n\\nwrongdoing—was it, in effect, a permissible “Terry stop” of the phone? We hold\\n\\nthat it was not. Second, in the particular circumstances of this case, did the officers\\n\\nhave probable cause to believe not only that the phone’s owner had committed a\\n\\ncrime and that the phone contained evidence of that crime, but also that the suspect\\n\\nwould likely destroy that evidence before they could procure a warrant? We hold\\n\\nthat they did. Accordingly, and on that ground, we affirm the district court’s order\\n\\ndenying the motion to suppress. We separately affirm the district court’s sentence.\\n\\n I\\n\\n A\\n\\n Early one Friday morning, Deputy Andrea Olson of the Stuart, Florida\\n\\nPolice Department responded to a domestic-disturbance call reporting a ruckus\\n\\ncoming from a camper parked at Darrell Babcock’s residence—specifically, a\\n\\nfemale had been heard yelling, “Stop, stop, stop!” When Deputy Olson knocked\\n\\non the door of Babcock’s camper, Babcock exited, closed the door behind him, and\\n\\n\\n 2\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 3 of 32\\n\\n\\nvolunteered that no one else was inside. Almost immediately, though, Deputy\\n\\nOlson heard a female announce that she was coming out. A teenage girl emerged\\n\\nfrom the trailer; she was wearing only yoga shorts and a camo jacket, and she had\\n\\nblood on her left thigh. Seemingly by way of explanation, Babcock handed\\n\\nDeputy Olson his cell phone to show her a video of the girl—we’ll call her C.A.—\\n\\nsitting on a bed, holding a knife to her own throat and saying that she wanted to\\n\\ndie. In the video Babcock could be heard berating the girl, telling her, “you’re\\n\\ndumb as f***” and complaining, “this is what I deal with right here . . . you gotta\\n\\ndo drama and fighting me all over the place.” After viewing the clip, Deputy\\n\\nOlson returned Babcock’s phone. When backup arrived on the scene, Deputy\\n\\nOlson asked for the phone again so that she could show the video to her colleague,\\n\\nOfficer Michael McMahan.\\n\\n The officers then interviewed Babcock and C.A. separately. Babcock denied\\n\\nknowing C.A.’s age and also disputed that the two were in a relationship, although\\n\\nhe admitted that he had known C.A. for three years and that she used to be his\\n\\nneighbor. He also said that C.A. had shown up at his camper unannounced,\\n\\nsometime during the middle of the night. C.A., by contrast—whose license\\n\\nshowed that she was only 16 years old—stated that she and Babcock had gone\\n\\ntogether the night before to a Halloween party, where she had consumed alcohol,\\n\\ncocaine, and other substances. After answering a few questions, C.A. began either\\n\\n\\n 3\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 4 of 32\\n\\n\\npanicking or experiencing the effects of an overdose, so the officers called an\\n\\nambulance. Deputy Olson rode with C.A. to the hospital.\\n\\n Meanwhile, another officer, Detective Brian Broughton, remained behind to\\n\\ncontinue questioning Babcock. Detective Broughton sought and received\\n\\npermission to search Babcock’s camper, where he discovered blood on the\\n\\nbedsheets and prescription pills scattered about. When Detective Broughton asked\\n\\nto further inspect Babcock’s phone, Babcock refused and asked to have it back.\\n\\nBabcock offered to e-mail the video clip of C.A. with the knife, but Detective\\n\\nBroughton decided to keep the phone instead. He told Officer McMahan to enter it\\n\\ninto evidence and then took it with him to the hospital to talk to C.A.\\n\\n At the hospital, C.A. again insisted that she and Babcock were just friends,\\n\\nthat they had gone to a Halloween party, and that the two had then argued. She\\n\\nfirmly denied any further relationship. But when Detective Broughton informed\\n\\nC.A. that he had Babcock’s phone, she abruptly reversed course and admitted that\\n\\nthe two had been in a relationship and, further, that the officers would find sexually\\n\\nexplicit images of her on the phone. Two days later, Detective Broughton applied\\n\\nfor and obtained a warrant to search the phone, where he found nude images of\\n\\nC.A. and explicit video recordings of Babcock and C.A. together.\\n\\n\\n\\n\\n 4\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 5 of 32\\n\\n\\n B\\n\\n Babcock was charged with two counts of producing a visual depiction of\\n\\nsexually explicit conduct with a minor in violation of 18 U.S.C. § 2251(a), (e). He\\n\\nfiled a motion to suppress, arguing that officers had seized his phone without a\\n\\nwarrant or probable cause. The government filed a response, arguing primarily\\n\\nthat the cell-phone seizure was reasonable because “under the totality of the\\n\\ncircumstances” the officers had “reasonable suspicion to investigate further,” and\\n\\nadding that, at any rate, the officers had probable cause to believe that the phone\\n\\ncontained evidence of a crime. The government further contended that “detention\\n\\nof the cell phone was necessary to preserve the evidence observed by the\\n\\ndeputies.” Finally, the government asserted that, even in the absence of a warrant,\\n\\neither Babcock’s consent or the inevitability that the images would have been\\n\\ndiscovered rendered the seizure constitutional.\\n\\n A magistrate judge recommended that Babcock’s motion be denied. He\\n\\nconcluded—referencing two distinct Fourth Amendment standards—that “the\\n\\ncollective knowledge and information received by the officers at the scene\\n\\nconstituted sufficient probable cause and reasonable suspicion that there may have\\n\\nbeen a crime committed which may have been preserved on the cell phone.” The\\n\\ndistrict court agreed, noting—also somewhat vaguely—that the surrounding\\n\\ncircumstances were “sufficient for law enforcement to suspect inappropriate\\n\\n\\n 5\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 6 of 32\\n\\n\\nconduct between [Babcock] and C.A.” Later, at sentencing, the district judge\\n\\nfurther remarked that although he “didn’t say [it] in the order,” he was “putting [it]\\n\\non the record for appellate purposes” that in the video C.A. “appear[ed] to be either\\n\\nwith no pants on or underwear” and that, based on “what she says and how she\\n\\nsays it about what she wants to do to herself,” it was “obvious . . . that there was an\\n\\ninappropriate relationship going on which would have given [the officers]\\n\\nreasonable probable cause to believe that there was inappropriate sexual activity\\n\\nbetween” Babcock and C.A. Babcock took a plea, reserving his right to appeal the\\n\\ndenial of his motion to suppress.\\n\\n At sentencing, Babcock asked for the mandatory minimum of 180 months,\\n\\narguing that his conduct, while inappropriate, was outside the core child-\\n\\npornography-distribution behavior that Congress sought to deter under § 2251(a)\\n\\nand (e). The government in turn asked for a sentence within the 360-to-720-month\\n\\nrecommended Guidelines range, stressing the harm to C.A. and her family. The\\n\\ncourt imposed a below-Guidelines sentence of 324 months. Babcock appealed\\n\\nboth the denial of his motion to suppress and his sentence.\\n\\n II\\n\\n We’ll tackle the Fourth Amendment issues first. A person suffers a\\n\\n“seizure” of his property within the meaning of the Fourth Amendment when there\\n\\nis a “meaningful interference” with his possessory interest in it. United States v.\\n\\n\\n 6\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 7 of 32\\n\\n\\nVirden, 488 F.3d 1317, 1321 (11th Cir. 2007).1 While the seizure of private\\n\\nproperty generally requires a warrant, the Supreme Court has interpreted the\\n\\nFourth Amendment to allow a warrantless seizure when police can show both (1)\\n\\nprobable cause to believe that property contains contraband or evidence of a crime\\n\\nand (2) an applicable warrant exception, such as exigent circumstances. See, e.g.,\\n\\nKentucky v. King, 563 U.S. 452, 459–60 (2011) (citations omitted). Accordingly,\\n\\nabsent either a warrant or probable cause plus an exception, police may not seize\\n\\nprivate property. There is, however, an asterisk. Under a line of luggage-related\\n\\ncases from the 1980s, police may “briefly detain” property—Terry-stop style—on\\n\\nthe strength of reasonable suspicion alone. See United States v. Place, 462 U.S.\\n\\n696, 697–98 (1983); United States v. Puglisi, 723 F.2d 779, 788–89 (11th Cir.\\n\\n1984).\\n\\n Here, the government principally argues that these cases permitted the\\n\\nofficers to detain Babcock’s phone based on their reasonable suspicion that he had\\n\\ncommitted a crime. Alternatively, the government contends that the officers had\\n\\nprobable cause to believe that the phone contained evidence of a crime and that\\n\\nexigent circumstances—namely, the need to prevent the destruction of that\\n\\nevidence—allowed them to seize the phone. We consider each argument in turn.\\n1\\n When reviewing the denial of a motion to suppress, we review factual findings for clear error\\nand legal determinations de novo. United States v. Gibson, 708 F.3d 1256, 1274 (11th Cir.\\n2013). We also review the evidence in the light most favorable to the government, as the\\nprevailing party. See United States v. Capers, 708 F.3d 1286, 1295–96 (11th Cir. 2013).\\n\\n 7\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 8 of 32\\n\\n\\n A\\n\\n 1\\n\\n Reasonable suspicion is “a particularized and objective basis” for suspecting\\n\\na person of criminal activity. Ornelas v. United States, 517 U.S. 690, 696 (1996)\\n\\n(quotation marks omitted). It requires “specific, articulable, and objective facts\\n\\nreasonably to suspect” that a crime is being or will soon be committed, Puglisi,\\n\\n723 F.2d at 789, but “is a less demanding standard than probable cause,” Illinois v.\\n\\nWardlow, 528 U.S. 119, 123 (2000). In Terry v. Ohio, the Supreme Court\\n\\nfamously held that, even absent probable cause, police officers may briefly detain\\n\\nan individual based on reasonable suspicion that he is (or is about to be) engaged in\\n\\ncriminal activity. See 392 U.S. 1, 30–31 (1968).\\n\\n The Supreme Court first extended Terry’s rationale from people to property\\n\\nin United States v. Place, 462 U.S. 696 (1983). There, the Court held that while a\\n\\nbrief investigatory detention of property could be justified on the basis of\\n\\nreasonable suspicion alone, an officer’s 90-minute seizure of an airline traveler’s\\n\\nsuitcase exceeded constitutional boundaries. Id. at 702. In so holding, the Court\\n\\nrecognized that “[t]he intrusion on possessory interests occasioned by a seizure of\\n\\none’s personal effects can vary both in its nature and extent.” Id. at 705. While\\n\\nsome “brief detentions of personal effects”—such as, the Court hypothesized, “on-\\n\\nthe-spot” dog sniffs—may be “so minimally intrusive” as to “justify a seizure\\n\\n\\n 8\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 9 of 32\\n\\n\\nbased only on specific articulable facts that the property contains contraband,” the\\n\\nluggage seizure didn’t fit the bill. Id. at 705–06. By way of explanation, the Court\\n\\nemphasized several factors: the duration of the detention, the degree of the\\n\\nintrusion on the owner’s possessory interests in his property, and the officer’s lack\\n\\nof diligence in timely pursuing their investigation. Id. at 709–10. The Court also\\n\\nhighlighted that a confiscation of luggage, in particular, interferes not only with\\n\\npossessory interests but also with liberty interests because, while a suspect whose\\n\\nluggage is stopped is “technically still free to continue” on his way, the detention\\n\\nmight “effectively restrain” him by disrupting his travel plans. Id. at 708–09.\\n\\n Shortly after the Supreme Court decided Place, this Court had occasion to\\n\\napply it on similar facts. In United States v. Puglisi, an officer made what began as\\n\\na brief stop by ordering a suspicious traveler’s bags removed from a luggage cart;\\n\\nhe then stowed the luggage in his office until a drug-sniffing dog became available.\\n\\n723 F.2d 779, 790 (11th Cir. 1984). Meanwhile, the traveler boarded his flight\\n\\nwithout his bags. Although we deemed the initial seizure permissible under Terry,\\n\\nwe found that the length and intrusiveness—140 minutes—caused the “brief stop”\\n\\nto “ripen” into a full-blown seizure that could be justified only by probable cause.\\n\\nId. at 784. We explained that “Place requires the same test as Terry: a court must\\n\\nweigh the intrusiveness of a limited seizure of the individual against society’s\\n\\ninterest in detection and prevention of crime.” Id. at 785. We cautioned, however,\\n\\n\\n 9\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 10 of 32\\n\\n\\nthat because the Fourth Amendment “protects people, not things,” the focus was\\n\\nthe effective “seizure of persons, through their luggage.” Id. at 787–88.\\n\\n Although Place and Puglisi concerned luggage, both this Court and others\\n\\nhave since indicated that any detention of property based on reasonable suspicion\\n\\nmust be fairly analogous to a Terry stop, regardless of the item at issue.\\n\\nAccordingly, we have said, “the factors used to determine whether a Terry stop has\\n\\nmatured into an arrest are also useful in evaluating whether a seizure of property\\n\\nrequired probable cause” rather than mere reasonable suspicion. Virden, 488 F.3d\\n\\nat 1321. Echoing Place, we have said that these factors include, but are not limited\\n\\nto, (1) the detention’s duration, (2) its intrusiveness, (3) the diligence with which\\n\\nofficers pursued their investigation, and (4) the law-enforcement purposes served\\n\\nby the detention. See id.; accord United States v. Gonzalez, 781 F.3d 422, 428–29\\n\\n(8th Cir. 2015); Farm Labor Org. Comm. v. Ohio State Highway Patrol, 308 F.3d\\n\\n523, 544–45 (6th Cir. 2002); United States v. $557,933.89, More or Less, in U.S.\\n\\nFunds, 287 F.3d 66, 86 (2d Cir. 2002). We’ll explain each in a bit more detail here\\n\\nbefore applying them to the facts of this case\\n\\n First, duration. Although the Supreme Court has “decline[d] to adopt any\\n\\noutside time limit for a permissible Terry stop,” the Court in Place observed that it\\n\\nhad “never approved a seizure of the person for the prolonged 90-minute period\\n\\ninvolved” in that case and that, on the facts presented there, it wouldn’t approve a\\n\\n\\n 10\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 11 of 32\\n\\n\\n90-minute detention of property, either. 462 U.S. at 709–10. In Virden, this Court\\n\\nsimilarly determined that an officer’s transfer of a defendant and his car to another\\n\\nlocation for a dog sniff, “[w]hile not unduly lengthy” at about 30 minutes, was\\n\\nnonetheless “unreasonable absent probable cause.” 488 F.3d at 1321. 2\\n\\n At the other end of the spectrum, the Fourth Circuit has approved a seconds-\\n\\nlong cell-phone stop on the basis of reasonable suspicion alone. In United States v.\\n\\nLawing, that court held that an officer’s brief detention of a suspect’s phone during\\n\\na traffic stop—for just long enough to see if it would ring when the officer dialed a\\n\\nknown drug-distributor’s number—was sufficiently minimal to qualify for\\n\\nTerry/Place treatment. 703 F.3d 229, 238 (4th Cir. 2012). Similarly, the Second\\n\\nCircuit held that reasonable suspicion justified a brief investigatory detention that\\n\\noccurred when a detective took between two and 20 minutes to respond to a\\n\\nrequest for a luggage investigation while a traveler waited at an airport security\\n\\ncheckpoint with his luggage. See $557,933.89, More or Less, 287 F.3d at 71, 86–\\n\\n87 & n.16.\\n\\n Second, intrusiveness. The “intrusiveness” factor concerns the degree to\\n\\nwhich a property detention interferes with a person’s possessory interest in his\\n\\nbelongings. In Place, for instance, the Court emphasized that although “the\\n\\n2\\n Even though the detention there more directly implicated the owner’s liberty interests than in\\nPlace because the owner remained in his car while it was transported to another location, we\\nanalyzed the stop primarily as one of property rather than of an individual. See Virden, 488 F.3d\\nat 1321.\\n 11\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 12 of 32\\n\\n\\nparticular course of investigation that the agents intended to pursue”—just a brief\\n\\n“exposure of respondent’s luggage, which was located in a public place, to a\\n\\ntrained canine”—would have been permissible based on mere reasonable\\n\\nsuspicion, the 90-minute seizure that they actually effected was not. 462 U.S. at\\n\\n707, 709–10 (emphasis added). The Court explained that the planned sniff would\\n\\nhave revealed “only the presence or absence of narcotics, a contraband item,” and\\n\\nwouldn’t have exposed the traveler’s personal “noncontraband items that otherwise\\n\\nwould remain hidden from public view, as [would], for example, an officer’s\\n\\nrummaging through the contents of the luggage.” Id. at 707.\\n\\n This Court has likewise recognized that individuals have strong interests in\\n\\ncontainers that hold personal effects or private information, such as luggage and\\n\\ncomputers. In Puglisi, we emphasized that “privacy and possessory interests in\\n\\nluggage are often high” because a traveler may have “his most important and\\n\\nprivate possessions in his suitcase” and likely wants “to shield them from the\\n\\nprying eyes of strangers, especially the government.” 723 F.2d at 786. And in\\n\\nUnited States v. Laist, we acknowledged that “computers are a unique possession,\\n\\none in which individuals may have a particularly powerful possessory interest,”\\n\\nbecause they store “personal letters, e-mails, financial information, passwords,\\n\\nfamily photos, and countless other items of a personal nature.” 702 F.3d 608, 614\\n\\n(11th Cir. 2012); see also United States v. Mitchell, 565 F.3d 1347, 1352 (11th Cir.\\n\\n\\n 12\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 13 of 32\\n\\n\\n2009) (calling a computer hard drive “the digital equivalent of its owner’s home,\\n\\ncapable of holding a universe of private information”) (internal quotation marks\\n\\nomitted).\\n\\n Third, diligence. When police diligently pursue their investigation, a\\n\\nreviewing court can have greater confidence that the governmental interest is\\n\\nlegitimate and that the intrusion occasioned by the challenged detention was no\\n\\ngreater than reasonably necessary. See United States v. Burgard, 675 F.3d 1029,\\n\\n1033 (7th Cir. 2012). “Diligence” in this context includes not only seeking a\\n\\nwarrant application promptly, but also communicating with the suspect concerning\\n\\nthe specifics of the detention. In Place, for instance, the Court faulted officers for\\n\\nfailing to inform the suspect where and for how long they were taking his bags,\\n\\nand when and how he could get them back. See 462 U.S. at 710. So too, in Farm\\n\\nLabor, the Sixth Circuit observed—in the course of holding that the seizure of two\\n\\nsuspects’ green cards couldn’t be justified based on reasonable suspicion alone—\\n\\nthat an officer had failed to act diligently when he “wait[ed] for four days to return\\n\\n[their] green cards” and that “[t]he unreasonable nature of the seizure was\\n\\nexacerbated by the undisputed fact that [the officer] did not make clear . . . how\\n\\n\\n\\n\\n 13\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 14 of 32\\n\\n\\nlong the documents would be held or when or how he would return them.” 308\\n\\nF.3d at 546–47 (internal quotation marks omitted).3\\n\\n Finally, governmental interest. The final factor looks at the other side of the\\n\\nledger. As the Court explained in Place, “[t]he exception to the probable-cause\\n\\nrequirement for limited seizures of the person recognized in Terry and its progeny\\n\\nrests on a balancing of the competing interests to determine the reasonableness of\\n\\nthe type of seizure.” 462 U.S. at 703. Thus, “[w]e must balance the nature and\\n\\nquality of the intrusion on the individual’s Fourth Amendment interests against the\\n\\nimportance of the governmental interests alleged to justify the intrusion.” Id.\\n\\nIn Place, that meant taking account of the public’s compelling interest in\\n\\n“detecting those who would traffic in deadly drugs for personal profit.” Id.\\n\\n(internal quotation marks omitted).\\n\\n 2\\n\\n How, then, do these considerations stack up in this case? In short, not well\\n\\nfor the government. To begin at the end, we don’t doubt for a moment the\\n\\ngovernment’s “compelling” interest in preventing the creation and distribution of\\n\\nchild pornography. E.g., New York v. Ferber, 458 U.S. 747, 761 (1982). Standing\\n\\nalone, though, that interest can’t counterbalance the duration, intrusion, and\\n3\\n The diligence component of the analysis necessarily intersects with the duration component\\nbecause, “[i]n the ordinary case, the sooner the warrant issues, the sooner the property\\nowner’s possessory rights can be restored if the search reveals nothing incriminating”—and, of\\ncourse, the sooner an officer seeks a warrant, the sooner a warrant can issue. See Mitchell, 565\\nF.3d at 1352 (citation omitted).\\n 14\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 15 of 32\\n\\n\\ndiligence factors, all of which—for reasons we will explain—weigh heavily here in\\n\\nfavor of a determination that the officers’ two-day seizure of Babcock’s phone was\\n\\nnot just a brief “investigatory stop” but rather a full-blown seizure that required a\\n\\nshowing of full-blown probable cause. See Place, 462 U.S. at 699–700.\\n\\n Looking first to duration, the government cites United States v. Brignoni-\\n\\nPonce, 422 U.S. 873, 881 (1975), for the proposition that law enforcement may\\n\\n“conduct a limited warrantless seizure of a person or item ‘on facts that do not\\n\\nconstitute probable cause.’” Br. of Appellee at 15. Brignoni-Ponce, however,\\n\\nconsidered only whether a momentary stop for “a brief question or two” was\\n\\npermissible on less than probable cause. 422 U.S. at 880; see also Place, 462 U.S.\\n\\nat 709 (describing Terry and Brignoni Ponce as involving “momentary” stops).\\n\\nBut that’s a far cry from the two-day pre-warrant seizure at issue here. The\\n\\ngovernment also points to what it calls the “similar” case of Laist, in which we\\n\\nheld that a 25-day delay between a seizure and a warrant was permissible. 702\\n\\nF.3d at 614–15. But Laist isn’t similar at all; the seizure in that case was based on\\n\\nprobable cause, not mere reasonable suspicion. Id.; see also Burgard, 675 F.3d at\\n\\n1033 (explaining, in justifying a six-day delay, that a seizure supported by\\n\\nprobable cause permits a much greater intrusion than a seizure supported by mere\\n\\nreasonable suspicion).\\n\\n\\n\\n\\n 15\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 16 of 32\\n\\n\\n What of the more analogous decisions in Place and Puglisi? The\\n\\ngovernment seeks to distinguish them on the ground that both cases analyzed the\\n\\nseizure of luggage “as essentially a detention of the person.” Br. of Appellant at 16\\n\\nn.4. The government asserts that Puglisi, in particular, is inapt because the Court\\n\\nthere held that “[f]or time even to be relevant, the seizure of luggage must have\\n\\nactually or constructively seized the person.” 723 F.2d at 788.\\n\\n Two responses. For starters, we don’t think that this one line, taken alone,\\n\\nrepresents the holding of Puglisi. See Dantzler v. I.R.S., 183 F.3d 1247, 1251\\n\\n(11th Cir. 1999) (“A judicial opinion is not a statute, and not every sentence in a\\n\\njudicial opinion is law.”). Constructive seizure of the person was not the only\\n\\nelement relevant to whether the luggage detention in Puglisi was permissible based\\n\\non reasonable suspicion alone. Instead, we analyzed the 140-minute seizure\\n\\nagainst Place’s considerations of duration, intrusiveness, and diligence before\\n\\ndeeming the detention unlawful. Puglisi, 723 F.2d at 788, 790–91.\\n\\n Furthermore—and more importantly—it’s not clear why, under the rationale\\n\\nof Place and Puglisi, an officer’s confiscation of a cell phone is any less a\\n\\nconstructive seizure of its owner than his detention of luggage (which, per Place,\\n\\nwould make even 90 minutes too long). In Place the Court reasoned that while a\\n\\nsuspect whose luggage is detained is “technically still free to continue his travels,”\\n\\nthe seizure might nonetheless “effectively restrain” him by disrupting his travel\\n\\n\\n 16\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 17 of 32\\n\\n\\nplans. 462 U.S. at 708. Given the ubiquity of cell phones—and our increasing\\n\\nreliance on them—it’s no stretch to hazard that a modern-day traveler would likely\\n\\nrather arrive in a strange place without her luggage than without her phone.\\n\\nWithout the former, she may be left with only the “clothes on [her] back,” Puglisi,\\n\\n723 F.2d at 786, but without the latter she may be left without directions, hotel\\n\\nreservations, and payment and ride-share apps, not to mention voice, text, and\\n\\nemail communications—in short, isolated and incapacitated. Whatever heft the\\n\\nconstructive-seizure argument has with respect to luggage applies equally (if not a\\n\\nfortiori) to cell phones. In any event, no matter what one thinks about the relative\\n\\nimport of luggage and phones, it’s clear that the duration of the seizure in this case\\n\\nputs it in a different bucket than the on-the-spot inquiry hypothesized in Place, see\\n\\n462 U.S. at 705–706, or carried out in Lawing, see 703 F.3d at 238.4\\n\\n Next, the intrusion into Babcock’s possessory interest in his private property\\n\\nwas serious. For many of the reasons just explained, a person’s possessory interest\\n\\nin his cell phone is at least as high as—if not higher than—his interest in his\\n\\n\\n4\\n The government suggested for the first time at oral argument that, rather than lasting two days,\\nthe reasonable-suspicion-based seizure lasted only until Detective Broughton used the phone to\\nprompt C.A.’s confession, at which time the reasonable suspicion became probable cause and,\\npresumably, washed away any budding issues with the seizure. We decline to wade into this\\nargument when the entire record below is predicated on the seizure lasting two days. Because\\nthe government made no argument—and the district court made no finding—concerning the\\nlength of time between the seizure and the confession, any determination of the same on our part\\nwould be mere speculation. See Byrd v. United States, 138 S. Ct. 1518, 1530 (2018) (declining\\nto consider the government’s argument raised for the first time on appeal when argument was\\npredicated on factual issue “not addressed” below and “unclear” from the record).\\n\\n 17\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 18 of 32\\n\\n\\nluggage. A smart phone, as the Supreme Court recently emphasized, is unique in\\n\\nboth the breadth and depth of personal information it stores, including\\n\\n“photographs, picture messages, text messages, Internet browsing history, a\\n\\ncalendar, a thousand-entry phone book”—information that, all told, “reveal[s]\\n\\nmuch more in combination than any isolated record.” Riley v. California, 573 U.S.\\n\\n373, 394 (2014). In other words, while a piece of luggage may hold certain\\n\\nphysical items that an individual needs for a trip, a cell phone holds “[t]he sum of\\n\\nan individual’s private life”—hence our attentiveness to (which is to say obsession\\n\\nwith) our cell phones. Id. Put simply, the government’s confiscation of Babcock’s\\n\\nphone for a period of two days—and with it his personal messages, contacts,\\n\\ncalendar, and more—worked a serious interference with his possessory interests,\\n\\nand undermines the government’s current contention that the seizure was but a\\n\\n“limited intrusion” allowable based on mere reasonable suspicion.\\n\\n Finally, diligence. Detective Broughton’s actions here—holding onto\\n\\nBabcock’s phone over the weekend rather than more promptly attempting to secure\\n\\na warrant, either telephonically or in person—further confirm that the seizure in\\n\\nthis case looks nothing like a Terry stop. The government has offered no\\n\\nexplanation as to why Detective Broughton waited more than two days to take any\\n\\naction regarding the phone, nor does the record evidence indicate that he explained\\n\\nto Babcock when or whether he could expect to get his phone back. And while a\\n\\n\\n 18\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 19 of 32\\n\\n\\ntwo-day delay certainly wouldn’t cross the line in the probable-cause context, see,\\n\\ne.g., Laist, 702 F.3d at 614–15 (approving a 25-day delay in obtaining a warrant\\n\\nfollowing a probable-cause seizure), we know from precedent that it’s well outside\\n\\nthe realm of a permissible Terry stop, and thus weighs heavily against a finding of\\n\\ndiligence here, see Place, 462 U.S. at 710; Virden, 488 F.3d at 1321; Farm Labor,\\n\\n308 F.3d at 546–47.\\n\\n * * *\\n\\n Accordingly, we reject the government’s contention that the officers’ two-\\n\\nday detention of Babcock’s cell phone was a mere investigatory “stop” allowable\\n\\nbased on reasonable suspicion alone. Rather, we hold that it “ripened” into a full-\\n\\nblown seizure that required probable cause. See Puglisi, 723 F.2d at 784.\\n\\n B\\n\\n The government contends, in the alternative, that it can meet the probable-\\n\\ncause standard and, further, that it can show that exigent circumstances justified a\\n\\nwarrantless seizure. We will consider the two components of the government’s\\n\\nargument in turn, looking first to whether the officers at Babcock’s residence had\\n\\nprobable cause to believe that his phone contained evidence of a crime, and then to\\n\\nwhether exigent circumstances excused them from the need to obtain a warrant\\n\\npre-seizure.\\n\\n\\n\\n\\n 19\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 20 of 32\\n\\n\\n 1\\n\\n Probable cause to seize property is what it sounds like—a belief that\\n\\nevidence will probably be found in a particular location. See United States v.\\n\\nNoriega, 676 F.3d 1252, 1261 (11th Cir. 2012). As the Supreme Court recently\\n\\nreiterated, probable cause “is not a high bar.” District of Columbia v. Wesby, 138\\n\\nS. Ct. 577, 586 (2018) (quoting Kaley v. United States, 571 U.S. 320, 338 (2014)).\\n\\nAlthough probable cause requires more than reasonable suspicion that criminal\\n\\nbehavior is afoot, it doesn’t entail the same “standard of conclusiveness and\\n\\nprobability as the facts necessary to support a conviction.” United States v.\\n\\nDunn, 345 F.3d 1285, 1290 (11th Cir. 2003) (internal quotations omitted). Rather,\\n\\nit requires only “a substantial chance” that evidence of criminal activity exists.\\n\\nIllinois v. Gates, 462 U.S. 213, 243 n.13 (1983). We recently explained that this\\n\\n“substantial chance” exists “where the facts within the collective knowledge of law\\n\\nenforcement officials” suffice “to cause a person of reasonable caution to believe\\n\\nthat a criminal offense has been or is being committed”—and here, that evidence\\n\\nof that offense will be found in a particular place. Gates v. Khokar, 884 F.3d 1290,\\n\\n1298 (11th Cir. 2018) (internal quotation marks omitted).\\n\\n Babcock contends that while the officers in this case might have suspected\\n\\nthat something was up, their collective knowledge at the time of the seizure didn’t\\n\\nrise to the level of probable cause that a crime had been committed. To evaluate\\n\\n\\n 20\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 21 of 32\\n\\n\\nthat contention, let’s recap: At the time Detective Broughton retained Babcock’s\\n\\nphone, the officers knew—\\n\\n • that a domestic-disturbance call had reported a female at Babcock’s\\n residence yelling “Stop, stop, stop!”;\\n\\n • that after Babcock had denied that anyone else was in his camper, a teenage\\n girl emerged with cuts on her legs;\\n\\n • that Babcock had accompanied the girl to a Halloween party the night\\n before, where she had consumed alcohol and drugs, and that she was in his\\n camper the next morning;\\n\\n • that the girl had been in or on Babcock’s bed and left traces of blood there;\\n\\n • that the girl had been distraught, holding a knife to her own throat and\\n saying, “I just want to die”; and\\n\\n • that shortly after they arrived at Babcock’s residence, the girl appeared to be\\n panicking or suffering an overdose.\\n\\nFinally—and perhaps most tellingly—the officers knew that, while the girl sat on\\n\\nBabcock’s bed with the knife to her neck, Babcock called her “dumb as f***” and\\n\\nthen complained—in the present tense—that “this is what I deal with right here . . .\\n\\nyou gotta do drama and fighting me all over the place.”\\n\\n Collectively, these circumstances gave the officers probable cause to believe\\n\\nthat Babcock had committed a crime against C.A. This common-sense conclusion\\n\\ndoesn’t depend on any particular fact taken in isolation; rather, as is “often” the\\n\\ncase, “the whole is . . . greater than the sum of its parts.” Wesby, 138 S. Ct. at 588;\\n\\nsee United States v. Arvizu, 534 U.S. 266, 274 (2002) (rejecting a “divide-and-\\n\\n 21\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 22 of 32\\n\\n\\nconquer” approach and instructing courts to evaluate probable cause in light of the\\n\\ntotality of the circumstances). Here, Babcock’s lies contributed to probable cause,\\n\\nsee Wesby, 138 S. Ct. at 587 (citing Devenpeck v. Alford, 543 U.S. 146, 149, 155–\\n\\n56 (2004)), as did his own present-tense statements clearly indicating an ongoing\\n\\nrelationship. When the officers considered Babcock’s own utterances in light of\\n\\nthe litany of other suspicious facts the learned, they certainly could have suspected\\n\\na “substantial chance of criminal activity.” Gates, 462 U.S. at 243 n.13.\\n\\n From there, it required no leap for the officers to deduce that evidence of a\\n\\ncrime would likely be found on Babcock’s phone. The officers already knew that\\n\\nthe phone contained one eyebrow-raising video suggesting an ongoing relationship\\n\\nbetween a grown man and a teenage girl. It was eminently reasonable for them to\\n\\nbelieve that additional evidence of that relationship—messages, texts, pictures,\\n\\nvideos, etc.—would be found in the same place.\\n\\n True, as Babcock points out, the government has been a little wishy-washy\\n\\nabout the exact crime that the officers suspected at the time of the seizure. The\\n\\ngovernment doesn’t contend that the officers had probable cause to believe that the\\n\\nphone contained evidence of child pornography; rather, it concedes that until\\n\\nDetective Broughton confronted C.A. with the phone at the hospital post-seizure,\\n\\nhe had “no reason to believe that there were videos of sexual activity between [the]\\n\\ntwo.” Importantly, though, our precedent doesn’t require officers to predict the\\n\\n\\n 22\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 23 of 32\\n\\n\\neventually-charged offense in order to demonstrate probable cause, only that the\\n\\ncollective facts would cause a “person of reasonable caution” to believe that “a\\n\\ncriminal offense has been or is being committed.” See Khokar, 884 F.3d at 1298\\n\\n(emphasis added) (internal quotation marks omitted).\\n\\n Here, the government’s arguments at the suppression hearing focused\\n\\nmainly on preserving both the video of C.A. on the bed and any evidence that\\n\\nmight have shed light on the events leading up to it. And indeed, that is exactly\\n\\nwhat the officers ended up finding: evidence of an illegal, coercive relationship,\\n\\nconfirming the suspicions sparked by the video’s portrayal of Babcock’s\\n\\ndisdainful, bullying tone and C.A.’s distraught appearance. The fact that the phone\\n\\nalso (and unexpectedly) contained pornographic images and videos doesn’t\\n\\ninvalidate probable cause for any number of Florida state crimes the officers\\n\\nreasonably could have believed occurred based on the scene greeting them at\\n\\nBabcock’s residence. See, e.g., Fla. Stat. § 794.05(1) (“Unlawful sexual activity\\n\\nwith certain minors”); id. § 794.011(4)(a) (“Sexual battery”). Accordingly, we\\n\\nhold that on these facts the officers had probable cause to believe that Babcock was\\n\\nguilty of a crime, and that evidence of the crime would be found on his phone.\\n\\n 2\\n\\n Of course, probable cause isn’t alone enough to seize an individual’s\\n\\npersonal property—officers typically need a warrant. “[A] warrantless search\\n\\n\\n 23\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 24 of 32\\n\\n\\nand seizure can be justified,” however, “when probable cause has been established\\n\\nto believe that evidence will be removed or destroyed before a warrant can be\\n\\nobtained.” United States v. Young, 909 F.2d 442, 446 (11th Cir. 1990). This\\n\\nexception—one branch of the “exigent-circumstances” doctrine—entails, like\\n\\nprobable cause itself, an objective inquiry. See United States v. Bradley, 644 F.3d\\n\\n1213, 1262 (11th Cir. 2011).\\n\\n Historically, we have found the exigent-circumstances exception\\n\\n“particularly compelling” in drug cases “because contraband and records can be\\n\\neasily and quickly destroyed while a search is progressing.” Young, 909 F.2d at\\n\\n446. The same is true of electronic files. In Bradley, for instance, we found that\\n\\nthe exigent-circumstances exception permitted officers to shut down a company’s\\n\\nservers—a seizure of the company’s property—when multiple employees “had the\\n\\nability and incentive to, after learning of the raid, destroy damning information\\n\\ncontained on the computer servers.” 644 F.3d at 1262–63.\\n\\n To be clear, it’s not that a cell phone itself creates an exigent circumstance.\\n\\n“Taken to its logical conclusion,” that “would permit police officers to seize now-\\n\\nubiquitous cell phones from any person, in any place, at any time, so long as the\\n\\nphone contains photographs or videos that could serve as evidence of a crime—\\n\\nsimply because the ‘nature’ of the device used to capture that evidence might result\\n\\nin it being lost.” Crocker v. Beatty, 886 F.3d 1132, 1137 (11th Cir. 2018)\\n\\n\\n 24\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 25 of 32\\n\\n\\n(emphasis in original). In Crocker, we held that the exigent-circumstances\\n\\nexception didn’t apply where an officer had seized a bystander’s phone to prevent\\n\\ndeletion of photographs that he observed the onlooker snapping following a huge\\n\\nhighway crash. Id. Absent any reason for the officer to think that the bystander\\n\\nwouldn’t preserve the pictures or would refuse to turn them over if asked, we\\n\\nfound the government’s exigent-circumstances argument unconvincing. Id.\\n\\n This case is different. Given the facts here, a reasonable, experienced agent\\n\\ncertainly could have believed that Babcock—the suspect, not a mere bystander—\\n\\nwould delete any incriminating evidence on his phone before a warrant could be\\n\\nobtained. For starters, Babcock had tried to deceive the responding officers from\\n\\nthe get-go, denying that anyone else was in his camper, reporting that C.A. had\\n\\nrandomly shown up at his house in the middle of the night, and claiming that he\\n\\ndidn’t know her age—all lies. Moreover Babcock surely knew that he was under\\n\\nsuspicion once Detective Broughton asked to search the camper and to further\\n\\ninspect his phone. Finally, of course, and on top of all that, the electronic files on\\n\\nBabcock’s phone could have been “quickly destroyed while [the] search [wa]s\\n\\nprogressing.” Young, 909 F.2d at 446. All told, as in Bradley, it was reasonable\\n\\nfor the officers here to conclude that Babcock had the “ability and incentive to,\\n\\nafter learning” of the investigation into his relationship with C.A., “destroy\\n\\n\\n\\n\\n 25\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 26 of 32\\n\\n\\ndamning information contained on” his phone. 644 F.3d at 1262–63. That’s all\\n\\nthe exigent-circumstances doctrine requires. 5\\n\\n Babcock contends that his offer to e-mail the video to the officers removed\\n\\nany urgency, thereby undermining any exigent-circumstances argument. He cites\\n\\nour decision in United States v. Hernandez-Cano, 808 F.2d 779 (11th Cir. 1987),\\n\\nfor the proposition that officers can’t claim exigent circumstances when the\\n\\nsupposed risk can be alleviated by alternative means. But Hernandez-Cano was\\n\\ndifferent—and in fact boomerangs back around on Babcock here. There, we\\n\\nconsidered a warrantless search of a suspect’s luggage and determined that,\\n\\nbecause officers had probable cause to arrest him at the time of the search, “any\\n\\nexigencies inherent in the situation could have been removed” by simply doing so.\\n\\n5\\n Babcock asserts that the government forfeited its exigency argument by failing to use the\\nphrase “exigent circumstances”—and failing to fully develop its position regarding the same—in\\nits response to the motion to suppress. We disagree. While it’s true that alternative theories of\\nadmissibility—including exigent circumstances—can be forfeited even when the government is\\nthe appellee or respondent, see Steagald v. United States, 451 U.S. 204, 208 (1981); Giordenello\\nv. United States, 357 U.S. 480, 487–88 (1958), we conclude that the government did enough here\\nto preserve its exigent-circumstances argument. To be sure, in responding to Babcock’s motion\\nto suppress, the government didn’t use the phrase “exigent circumstances” or cite case law\\nspecifically in support of the exception. It did argue, though, that “[t]he deputies had probable\\ncause to believe that the phone had evidentiary value” and that “detention of the cellular phone\\nwas necessary to preserve the evidence observed by the deputies.” Gov’t Resp. Mot. Suppress at\\n5 (emphasis added). That—whether accompanied by magic words or not—is the very definition\\nof the exigent-circumstances exception. See, e.g., Young, 909 F.2d at 446 (“[W]hen probable\\ncause has been established to believe that evidence will be removed or destroyed before a\\nwarrant can be obtained, a warrantless search and seizure can be justified.”). That the\\ngovernment presented a more robust version of its argument on appeal doesn’t render its initial\\nargument null. See, e.g., Sec’y, U.S. Dep’t of Labor v. Preston, 873 F.3d 877, 883 n.5 (11th Cir.\\n2017) (explaining that “[o]ffering a new argument or case citation in support of a position\\nadvanced in the district court is permissible—and often advisable” lest “the quality and depth of\\nargument [fail] to improve on appeal—an unfortunate result”), cert. denied sub nom. Preston v.\\nAcosta, 138 S. Ct. 2680 (2018).\\n 26\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 27 of 32\\n\\n\\nId. at 782. We explained that “[e]ven if exigent circumstances existed that justified\\n\\nthe seizure of the suitcase to prevent the loss or destruction of its contents, the\\n\\ngovernment still had to obtain a warrant to search the suitcase.” Id. (emphasis\\n\\nadded). Here, the officers didn’t conduct a warrantless search. Instead, faced with\\n\\nthe potential destruction of evidence, they did exactly what Hernandez-Cano\\n\\nsuggests they should have done—they seized the phone “to prevent the loss or\\n\\ndestruction of its contents,” and then obtained a warrant before searching through\\n\\nit. See id.\\n\\n Thus, because a reasonable officer could have believed that Babcock would\\n\\ndelete any incriminating evidence on his phone before a warrant could be\\n\\nobtained—and because none of Babcock’s arguments convinces us otherwise—we\\n\\nfind that the exigent-circumstances exception applies in this case. 6\\n\\n * * *\\n\\n\\n6\\n The government also argues in the alternative that Babcock consented to the seizure by\\nvoluntarily providing his phone to the officers to display the video of C.A. threatening self-harm.\\nIt is well-settled, however, that “the scope of a search based on consent may not exceed the\\nscope of the given consent.” United States v. Watkins, 760 F.3d 1271, 1279 (11th Cir. 2014)\\n(citing Florida v. Jimeno, 500 U.S. 248, 251 (1991)). The standard for measuring the scope of\\nconsent is “objective reasonableness”—what “would the typical reasonable person have\\nunderstood by the exchange between the officer and the [individual giving the consent]?” Id.\\n(internal quotation marks omitted). Here, Babcock clearly consented only to the officers’\\nviewing the video he showed them. After the initial viewing, Deputy Olson asked for the phone\\nagain, for the express purpose of showing Officer McMahan the video. Babcock consented to\\nthe officers viewing the clip again, but then asked for his phone back and refused consent when\\nDetective Broughton asked to poke around further. Contrary to the government’s contention, the\\ninitial limited-in-scope consent doesn’t justify an unlimited-in-scope full seizure over Babcock’s\\nobjection.\\n\\n 27\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 28 of 32\\n\\n\\n To sum up, we reject the government’s contention that a two-day\\n\\nwarrantless seizure of a suspect’s cell phone is permissible based on reasonable\\n\\nsuspicion alone. We conclude, however, that the warrantless seizure of Babcock’s\\n\\nphone was lawful because the officers on the scene had probable cause to believe\\n\\nboth that evidence of a crime would be found on it and that the evidence would be\\n\\ndestroyed before they could obtain a warrant.\\n\\n III\\n\\n Babcock separately challenges his sentence, arguing that it is both (1)\\n\\nprocedurally unreasonable because the district court erroneously imposed two\\n\\nenhancements for the same harm and (2) substantively unreasonable because it is\\n\\ntoo harsh in light of the facts.7 Neither argument is persuasive.\\n\\n Babcock raises his procedural-reasonableness argument for the first time on\\n\\nappeal, so we can correct any missteps only if he shows a “plain error” that affects\\n\\nhis substantial rights and that seriously undermines the fairness, integrity, or public\\n\\nreputation of judicial proceedings. See United States v. Shelton, 400 F.3d 1325,\\n\\n1328–29 (11th Cir. 2005). Babcock essentially argues that the district court’s\\n\\napplication of both § 2G2.1(b)(2) and § 4B1.5(b) of the Sentencing Guidelines\\n\\nconstitutes impermissible double-counting.\\n\\n7\\n Babcock also argues that his sentence is procedurally unreasonable because the government did\\nnot group two counts of conviction which were based on the same harm. As the government\\npoints out, though, the Guidelines specifically exclude convictions under § 2G2.1 from the\\ngrouping rules. See U.S.S.G. § 3D1.2(d).\\n\\n 28\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 29 of 32\\n\\n\\n Double-counting occurs when one part of the Sentencing Guidelines is\\n\\napplied to increase a defendant’s punishment on account of a harm that has already\\n\\nbeen fully accounted for by application of another part of the Guidelines. See\\n\\nUnited States v. Dudley, 463 F.3d 1221, 1226–27 (11th Cir. 2006). Absent\\n\\nevidence to the contrary, however, the presumption is that “the Sentencing\\n\\nCommission intended to apply separate sections cumulatively,” United States v.\\n\\nKapordelis, 569 F.3d 1291, 1315 (11th Cir. 2009) (citation omitted), such that\\n\\nwhat might appear to be impermissible double-counting is instead what we will\\n\\ncall permissible “cumulative-counting.”\\n\\n We conclude that applying both enhancements in this case constitutes\\n\\ncumulative- (rather than double-) counting. Chapter Two of the Guidelines,\\n\\nfocusing on the sexual exploitation of minors through pictures, provides that an\\n\\noffender’s base sentencing level should be enhanced by two when “the commission\\n\\nof a sexual act or sexual contact” occurs during a visual depiction. U.S.S.G.\\n\\n§ 2G2.1(b)(2)(A). Chapter Four then makes clear that when a “pattern of . . .\\n\\nprohibited sexual contact” occurs, a court should add five to “the offense level\\n\\ndetermined under Chapter[] Two.” U.S.S.G. § 4B1.5(b). The Guidelines say\\n\\nnothing about adding this enhancement to only a portion of the base level\\n\\ndetermined under Chapter Two, or otherwise adjusting the calculation in any\\n\\nway—instead, they simply presuppose that a certain offense level was determined\\n\\n\\n 29\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 30 of 32\\n\\n\\nunder Chapter Two, and then instruct the sentencing court to add five levels,\\n\\nperiod. Nothing in the Guidelines, then, indicates that these sections may not be\\n\\napplied cumulatively. See Kapordelis, 569 F.3d at 1315. Moreover, and in any\\n\\nevent, it isn’t clear that the harm in § 4B1.5(b)’s “pattern of activity involving\\n\\nprohibited sexual contact” is “fully accounted for” in § 2G2.1(b)(2)’s “sexual act\\n\\nor sexual contact” occurring in a visual depiction, such that application of the two\\n\\nsections could be considered double-counting at all. See Dudley, 463 F.3d at\\n\\n1226–27. There was no plain error here.\\n\\n Looking next to substantive reasonableness, Babcock argues that the nature\\n\\nand circumstances of this case do not compel the same severe sentence required to\\n\\ndeter creators of commercial child pornography. Basically, Babcock contends that\\n\\nhis crime—an inappropriate, long-term relationship with an older teenager—\\n\\ndoesn’t indicate that he is a threat to children generally or affect the child-\\n\\npornography market as would, for instance, the rape of a child for video\\n\\ndistribution or other predatory production of commercial child pornography.\\n\\nBabcock asserts that because there is no evidence that he intended ever to show\\n\\nanyone his videos or pictures of C.A., his 324-month sentence is substantively\\n\\nunreasonable.\\n\\n We review challenges to the substantive reasonableness of a sentence for\\n\\nabuse of discretion. Gall v. United States, 552 U.S. 38, 41 (2007). The party\\n\\n\\n 30\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 31 of 32\\n\\n\\nchallenging the sentence bears the burden of showing that the sentence is\\n\\nunreasonable in light of the record and the 18 U.S.C. § 3553(a) factors. United\\n\\nStates v. Tome, 611 F.3d 1371, 1378 (11th Cir. 2010). While we do not formally\\n\\npresume that a within-Guidelines sentence is reasonable, we ordinarily expect it to\\n\\nbe so. United States v. Hunt, 526 F.3d 739, 746 (11th Cir. 2008). That a sentence\\n\\nis imposed well below the statutory maximum penalty may also indicate its\\n\\nreasonableness. See United States v. Gonzalez, 550 F.3d 1319, 1324 (11th Cir.\\n\\n2008) (per curiam).\\n\\n There is a certain intuitive logic to Babcock’s argument here—it’s true that\\n\\nnothing in the record necessarily indicates a propensity to distribute child\\n\\npornography. That being said, Babcock’s conduct falls squarely within the\\n\\nconfines of § 2G2.1—“sexually exploiting a minor by production of sexually\\n\\nexplicit visual or printed material”—and, as the sentencing judge emphasized, the\\n\\neffect of his actions on C.A. and her family was far from insignificant. We are\\n\\ncomfortable that the sentencing judge took into consideration all of the relevant\\n\\ncircumstances when he sentenced Babcock to 324 months—a downward variance\\n\\nfrom the 360 to 720 months recommended by the Guidelines. See Gonzalez, 550\\n\\nF.3d at 1324. Accordingly, we find no abuse of discretion in the district court’s\\n\\nsentencing decision.\\n\\n\\n\\n\\n 31\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 32 of 32\\n\\n\\n IV\\n\\n For the foregoing reasons, we hold (1) that reasonable suspicion alone could\\n\\nnot have justified the officers’ warrantless two-day seizure of Babcock’s cell\\n\\nphone; (2) that the officers in this case had probable cause to believe that a crime\\n\\nhad been committed, that evidence of the crime would be found on Babcock’s\\n\\nphone, and that there was a risk that Babcock would destroy the evidence before\\n\\nthey could get a warrant, such that the seizure did not violate the Fourth\\n\\nAmendment; and (3) that Babcock’s sentence was both procedurally and\\n\\nsubstantively reasonable. Accordingly, we affirm the district court’s denial of\\n\\nBabcock’s motion to suppress as well as its 324-month sentence.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 32\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2292,"cells":{"id":{"kind":"number","value":4623249,"string":"4,623,249"},"name":{"kind":"string","value":""},"name_abbreviation":{"kind":"string","value":"United States v. Darrell Mark Babcock"},"decision_date":{"kind":"string","value":"2019-05-24"},"docket_number":{"kind":"string","value":"17-13678"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Before WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District Judge.\", \"parties\": \"\", \"opinions\": [{\"author\": \"NEWSOM, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-13678 Date Filed: 05/24/2019 Page: 1 of 32\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-13678\\n ________________________\\n\\n D.C. Docket No. 2:16-cr-14071-KAM-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nDARRELL MARK BABCOCK,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 24, 2019)\\n\\nBefore WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District\\nJudge.\\n\\n\\n\\n\\n*\\n The Honorable Kathryn H. Vratil, United States District Court Judge for the District of Kansas,\\nsitting by designation.\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 2 of 32\\n\\n\\nNEWSOM, Circuit Judge:\\n\\n In this case, police officers investigating a domestic disturbance confiscated\\n\\na suspect’s cell phone and held it for two days before eventually obtaining a\\n\\nwarrant to search it. The appeal before us presents two Fourth Amendment\\n\\nquestions. First, was the seizure justified on the ground that the officers had\\n\\nreasonable suspicion to believe that the phone’s owner was engaged in criminal\\n\\nwrongdoing—was it, in effect, a permissible “Terry stop” of the phone? We hold\\n\\nthat it was not. Second, in the particular circumstances of this case, did the officers\\n\\nhave probable cause to believe not only that the phone’s owner had committed a\\n\\ncrime and that the phone contained evidence of that crime, but also that the suspect\\n\\nwould likely destroy that evidence before they could procure a warrant? We hold\\n\\nthat they did. Accordingly, and on that ground, we affirm the district court’s order\\n\\ndenying the motion to suppress. We separately affirm the district court’s sentence.\\n\\n I\\n\\n A\\n\\n Early one Friday morning, Deputy Andrea Olson of the Stuart, Florida\\n\\nPolice Department responded to a domestic-disturbance call reporting a ruckus\\n\\ncoming from a camper parked at Darrell Babcock’s residence—specifically, a\\n\\nfemale had been heard yelling, “Stop, stop, stop!” When Deputy Olson knocked\\n\\non the door of Babcock’s camper, Babcock exited, closed the door behind him, and\\n\\n\\n 2\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 3 of 32\\n\\n\\nvolunteered that no one else was inside. Almost immediately, though, Deputy\\n\\nOlson heard a female announce that she was coming out. A teenage girl emerged\\n\\nfrom the trailer; she was wearing only yoga shorts and a camo jacket, and she had\\n\\nblood on her left thigh. Seemingly by way of explanation, Babcock handed\\n\\nDeputy Olson his cell phone to show her a video of the girl—we’ll call her C.A.—\\n\\nsitting on a bed, holding a knife to her own throat and saying that she wanted to\\n\\ndie. In the video Babcock could be heard berating the girl, telling her, “you’re\\n\\ndumb as f***” and complaining, “this is what I deal with right here . . . you gotta\\n\\ndo drama and fighting me all over the place.” After viewing the clip, Deputy\\n\\nOlson returned Babcock’s phone. When backup arrived on the scene, Deputy\\n\\nOlson asked for the phone again so that she could show the video to her colleague,\\n\\nOfficer Michael McMahan.\\n\\n The officers then interviewed Babcock and C.A. separately. Babcock denied\\n\\nknowing C.A.’s age and also disputed that the two were in a relationship, although\\n\\nhe admitted that he had known C.A. for three years and that she used to be his\\n\\nneighbor. He also said that C.A. had shown up at his camper unannounced,\\n\\nsometime during the middle of the night. C.A., by contrast—whose license\\n\\nshowed that she was only 16 years old—stated that she and Babcock had gone\\n\\ntogether the night before to a Halloween party, where she had consumed alcohol,\\n\\ncocaine, and other substances. After answering a few questions, C.A. began either\\n\\n\\n 3\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 4 of 32\\n\\n\\npanicking or experiencing the effects of an overdose, so the officers called an\\n\\nambulance. Deputy Olson rode with C.A. to the hospital.\\n\\n Meanwhile, another officer, Detective Brian Broughton, remained behind to\\n\\ncontinue questioning Babcock. Detective Broughton sought and received\\n\\npermission to search Babcock’s camper, where he discovered blood on the\\n\\nbedsheets and prescription pills scattered about. When Detective Broughton asked\\n\\nto further inspect Babcock’s phone, Babcock refused and asked to have it back.\\n\\nBabcock offered to e-mail the video clip of C.A. with the knife, but Detective\\n\\nBroughton decided to keep the phone instead. He told Officer McMahan to enter it\\n\\ninto evidence and then took it with him to the hospital to talk to C.A.\\n\\n At the hospital, C.A. again insisted that she and Babcock were just friends,\\n\\nthat they had gone to a Halloween party, and that the two had then argued. She\\n\\nfirmly denied any further relationship. But when Detective Broughton informed\\n\\nC.A. that he had Babcock’s phone, she abruptly reversed course and admitted that\\n\\nthe two had been in a relationship and, further, that the officers would find sexually\\n\\nexplicit images of her on the phone. Two days later, Detective Broughton applied\\n\\nfor and obtained a warrant to search the phone, where he found nude images of\\n\\nC.A. and explicit video recordings of Babcock and C.A. together.\\n\\n\\n\\n\\n 4\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 5 of 32\\n\\n\\n B\\n\\n Babcock was charged with two counts of producing a visual depiction of\\n\\nsexually explicit conduct with a minor in violation of 18 U.S.C. § 2251(a), (e). He\\n\\nfiled a motion to suppress, arguing that officers had seized his phone without a\\n\\nwarrant or probable cause. The government filed a response, arguing primarily\\n\\nthat the cell-phone seizure was reasonable because “under the totality of the\\n\\ncircumstances” the officers had “reasonable suspicion to investigate further,” and\\n\\nadding that, at any rate, the officers had probable cause to believe that the phone\\n\\ncontained evidence of a crime. The government further contended that “detention\\n\\nof the cell phone was necessary to preserve the evidence observed by the\\n\\ndeputies.” Finally, the government asserted that, even in the absence of a warrant,\\n\\neither Babcock’s consent or the inevitability that the images would have been\\n\\ndiscovered rendered the seizure constitutional.\\n\\n A magistrate judge recommended that Babcock’s motion be denied. He\\n\\nconcluded—referencing two distinct Fourth Amendment standards—that “the\\n\\ncollective knowledge and information received by the officers at the scene\\n\\nconstituted sufficient probable cause and reasonable suspicion that there may have\\n\\nbeen a crime committed which may have been preserved on the cell phone.” The\\n\\ndistrict court agreed, noting—also somewhat vaguely—that the surrounding\\n\\ncircumstances were “sufficient for law enforcement to suspect inappropriate\\n\\n\\n 5\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 6 of 32\\n\\n\\nconduct between [Babcock] and C.A.” Later, at sentencing, the district judge\\n\\nfurther remarked that although he “didn’t say [it] in the order,” he was “putting [it]\\n\\non the record for appellate purposes” that in the video C.A. “appear[ed] to be either\\n\\nwith no pants on or underwear” and that, based on “what she says and how she\\n\\nsays it about what she wants to do to herself,” it was “obvious . . . that there was an\\n\\ninappropriate relationship going on which would have given [the officers]\\n\\nreasonable probable cause to believe that there was inappropriate sexual activity\\n\\nbetween” Babcock and C.A. Babcock took a plea, reserving his right to appeal the\\n\\ndenial of his motion to suppress.\\n\\n At sentencing, Babcock asked for the mandatory minimum of 180 months,\\n\\narguing that his conduct, while inappropriate, was outside the core child-\\n\\npornography-distribution behavior that Congress sought to deter under § 2251(a)\\n\\nand (e). The government in turn asked for a sentence within the 360-to-720-month\\n\\nrecommended Guidelines range, stressing the harm to C.A. and her family. The\\n\\ncourt imposed a below-Guidelines sentence of 324 months. Babcock appealed\\n\\nboth the denial of his motion to suppress and his sentence.\\n\\n II\\n\\n We’ll tackle the Fourth Amendment issues first. A person suffers a\\n\\n“seizure” of his property within the meaning of the Fourth Amendment when there\\n\\nis a “meaningful interference” with his possessory interest in it. United States v.\\n\\n\\n 6\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 7 of 32\\n\\n\\nVirden, 488 F.3d 1317, 1321 (11th Cir. 2007).1 While the seizure of private\\n\\nproperty generally requires a warrant, the Supreme Court has interpreted the\\n\\nFourth Amendment to allow a warrantless seizure when police can show both (1)\\n\\nprobable cause to believe that property contains contraband or evidence of a crime\\n\\nand (2) an applicable warrant exception, such as exigent circumstances. See, e.g.,\\n\\nKentucky v. King, 563 U.S. 452, 459–60 (2011) (citations omitted). Accordingly,\\n\\nabsent either a warrant or probable cause plus an exception, police may not seize\\n\\nprivate property. There is, however, an asterisk. Under a line of luggage-related\\n\\ncases from the 1980s, police may “briefly detain” property—Terry-stop style—on\\n\\nthe strength of reasonable suspicion alone. See United States v. Place, 462 U.S.\\n\\n696, 697–98 (1983); United States v. Puglisi, 723 F.2d 779, 788–89 (11th Cir.\\n\\n1984).\\n\\n Here, the government principally argues that these cases permitted the\\n\\nofficers to detain Babcock’s phone based on their reasonable suspicion that he had\\n\\ncommitted a crime. Alternatively, the government contends that the officers had\\n\\nprobable cause to believe that the phone contained evidence of a crime and that\\n\\nexigent circumstances—namely, the need to prevent the destruction of that\\n\\nevidence—allowed them to seize the phone. We consider each argument in turn.\\n1\\n When reviewing the denial of a motion to suppress, we review factual findings for clear error\\nand legal determinations de novo. United States v. Gibson, 708 F.3d 1256, 1274 (11th Cir.\\n2013). We also review the evidence in the light most favorable to the government, as the\\nprevailing party. See United States v. Capers, 708 F.3d 1286, 1295–96 (11th Cir. 2013).\\n\\n 7\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 8 of 32\\n\\n\\n A\\n\\n 1\\n\\n Reasonable suspicion is “a particularized and objective basis” for suspecting\\n\\na person of criminal activity. Ornelas v. United States, 517 U.S. 690, 696 (1996)\\n\\n(quotation marks omitted). It requires “specific, articulable, and objective facts\\n\\nreasonably to suspect” that a crime is being or will soon be committed, Puglisi,\\n\\n723 F.2d at 789, but “is a less demanding standard than probable cause,” Illinois v.\\n\\nWardlow, 528 U.S. 119, 123 (2000). In Terry v. Ohio, the Supreme Court\\n\\nfamously held that, even absent probable cause, police officers may briefly detain\\n\\nan individual based on reasonable suspicion that he is (or is about to be) engaged in\\n\\ncriminal activity. See 392 U.S. 1, 30–31 (1968).\\n\\n The Supreme Court first extended Terry’s rationale from people to property\\n\\nin United States v. Place, 462 U.S. 696 (1983). There, the Court held that while a\\n\\nbrief investigatory detention of property could be justified on the basis of\\n\\nreasonable suspicion alone, an officer’s 90-minute seizure of an airline traveler’s\\n\\nsuitcase exceeded constitutional boundaries. Id. at 702. In so holding, the Court\\n\\nrecognized that “[t]he intrusion on possessory interests occasioned by a seizure of\\n\\none’s personal effects can vary both in its nature and extent.” Id. at 705. While\\n\\nsome “brief detentions of personal effects”—such as, the Court hypothesized, “on-\\n\\nthe-spot” dog sniffs—may be “so minimally intrusive” as to “justify a seizure\\n\\n\\n 8\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 9 of 32\\n\\n\\nbased only on specific articulable facts that the property contains contraband,” the\\n\\nluggage seizure didn’t fit the bill. Id. at 705–06. By way of explanation, the Court\\n\\nemphasized several factors: the duration of the detention, the degree of the\\n\\nintrusion on the owner’s possessory interests in his property, and the officer’s lack\\n\\nof diligence in timely pursuing their investigation. Id. at 709–10. The Court also\\n\\nhighlighted that a confiscation of luggage, in particular, interferes not only with\\n\\npossessory interests but also with liberty interests because, while a suspect whose\\n\\nluggage is stopped is “technically still free to continue” on his way, the detention\\n\\nmight “effectively restrain” him by disrupting his travel plans. Id. at 708–09.\\n\\n Shortly after the Supreme Court decided Place, this Court had occasion to\\n\\napply it on similar facts. In United States v. Puglisi, an officer made what began as\\n\\na brief stop by ordering a suspicious traveler’s bags removed from a luggage cart;\\n\\nhe then stowed the luggage in his office until a drug-sniffing dog became available.\\n\\n723 F.2d 779, 790 (11th Cir. 1984). Meanwhile, the traveler boarded his flight\\n\\nwithout his bags. Although we deemed the initial seizure permissible under Terry,\\n\\nwe found that the length and intrusiveness—140 minutes—caused the “brief stop”\\n\\nto “ripen” into a full-blown seizure that could be justified only by probable cause.\\n\\nId. at 784. We explained that “Place requires the same test as Terry: a court must\\n\\nweigh the intrusiveness of a limited seizure of the individual against society’s\\n\\ninterest in detection and prevention of crime.” Id. at 785. We cautioned, however,\\n\\n\\n 9\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 10 of 32\\n\\n\\nthat because the Fourth Amendment “protects people, not things,” the focus was\\n\\nthe effective “seizure of persons, through their luggage.” Id. at 787–88.\\n\\n Although Place and Puglisi concerned luggage, both this Court and others\\n\\nhave since indicated that any detention of property based on reasonable suspicion\\n\\nmust be fairly analogous to a Terry stop, regardless of the item at issue.\\n\\nAccordingly, we have said, “the factors used to determine whether a Terry stop has\\n\\nmatured into an arrest are also useful in evaluating whether a seizure of property\\n\\nrequired probable cause” rather than mere reasonable suspicion. Virden, 488 F.3d\\n\\nat 1321. Echoing Place, we have said that these factors include, but are not limited\\n\\nto, (1) the detention’s duration, (2) its intrusiveness, (3) the diligence with which\\n\\nofficers pursued their investigation, and (4) the law-enforcement purposes served\\n\\nby the detention. See id.; accord United States v. Gonzalez, 781 F.3d 422, 428–29\\n\\n(8th Cir. 2015); Farm Labor Org. Comm. v. Ohio State Highway Patrol, 308 F.3d\\n\\n523, 544–45 (6th Cir. 2002); United States v. $557,933.89, More or Less, in U.S.\\n\\nFunds, 287 F.3d 66, 86 (2d Cir. 2002). We’ll explain each in a bit more detail here\\n\\nbefore applying them to the facts of this case\\n\\n First, duration. Although the Supreme Court has “decline[d] to adopt any\\n\\noutside time limit for a permissible Terry stop,” the Court in Place observed that it\\n\\nhad “never approved a seizure of the person for the prolonged 90-minute period\\n\\ninvolved” in that case and that, on the facts presented there, it wouldn’t approve a\\n\\n\\n 10\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 11 of 32\\n\\n\\n90-minute detention of property, either. 462 U.S. at 709–10. In Virden, this Court\\n\\nsimilarly determined that an officer’s transfer of a defendant and his car to another\\n\\nlocation for a dog sniff, “[w]hile not unduly lengthy” at about 30 minutes, was\\n\\nnonetheless “unreasonable absent probable cause.” 488 F.3d at 1321. 2\\n\\n At the other end of the spectrum, the Fourth Circuit has approved a seconds-\\n\\nlong cell-phone stop on the basis of reasonable suspicion alone. In United States v.\\n\\nLawing, that court held that an officer’s brief detention of a suspect’s phone during\\n\\na traffic stop—for just long enough to see if it would ring when the officer dialed a\\n\\nknown drug-distributor’s number—was sufficiently minimal to qualify for\\n\\nTerry/Place treatment. 703 F.3d 229, 238 (4th Cir. 2012). Similarly, the Second\\n\\nCircuit held that reasonable suspicion justified a brief investigatory detention that\\n\\noccurred when a detective took between two and 20 minutes to respond to a\\n\\nrequest for a luggage investigation while a traveler waited at an airport security\\n\\ncheckpoint with his luggage. See $557,933.89, More or Less, 287 F.3d at 71, 86–\\n\\n87 & n.16.\\n\\n Second, intrusiveness. The “intrusiveness” factor concerns the degree to\\n\\nwhich a property detention interferes with a person’s possessory interest in his\\n\\nbelongings. In Place, for instance, the Court emphasized that although “the\\n\\n2\\n Even though the detention there more directly implicated the owner’s liberty interests than in\\nPlace because the owner remained in his car while it was transported to another location, we\\nanalyzed the stop primarily as one of property rather than of an individual. See Virden, 488 F.3d\\nat 1321.\\n 11\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 12 of 32\\n\\n\\nparticular course of investigation that the agents intended to pursue”—just a brief\\n\\n“exposure of respondent’s luggage, which was located in a public place, to a\\n\\ntrained canine”—would have been permissible based on mere reasonable\\n\\nsuspicion, the 90-minute seizure that they actually effected was not. 462 U.S. at\\n\\n707, 709–10 (emphasis added). The Court explained that the planned sniff would\\n\\nhave revealed “only the presence or absence of narcotics, a contraband item,” and\\n\\nwouldn’t have exposed the traveler’s personal “noncontraband items that otherwise\\n\\nwould remain hidden from public view, as [would], for example, an officer’s\\n\\nrummaging through the contents of the luggage.” Id. at 707.\\n\\n This Court has likewise recognized that individuals have strong interests in\\n\\ncontainers that hold personal effects or private information, such as luggage and\\n\\ncomputers. In Puglisi, we emphasized that “privacy and possessory interests in\\n\\nluggage are often high” because a traveler may have “his most important and\\n\\nprivate possessions in his suitcase” and likely wants “to shield them from the\\n\\nprying eyes of strangers, especially the government.” 723 F.2d at 786. And in\\n\\nUnited States v. Laist, we acknowledged that “computers are a unique possession,\\n\\none in which individuals may have a particularly powerful possessory interest,”\\n\\nbecause they store “personal letters, e-mails, financial information, passwords,\\n\\nfamily photos, and countless other items of a personal nature.” 702 F.3d 608, 614\\n\\n(11th Cir. 2012); see also United States v. Mitchell, 565 F.3d 1347, 1352 (11th Cir.\\n\\n\\n 12\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 13 of 32\\n\\n\\n2009) (calling a computer hard drive “the digital equivalent of its owner’s home,\\n\\ncapable of holding a universe of private information”) (internal quotation marks\\n\\nomitted).\\n\\n Third, diligence. When police diligently pursue their investigation, a\\n\\nreviewing court can have greater confidence that the governmental interest is\\n\\nlegitimate and that the intrusion occasioned by the challenged detention was no\\n\\ngreater than reasonably necessary. See United States v. Burgard, 675 F.3d 1029,\\n\\n1033 (7th Cir. 2012). “Diligence” in this context includes not only seeking a\\n\\nwarrant application promptly, but also communicating with the suspect concerning\\n\\nthe specifics of the detention. In Place, for instance, the Court faulted officers for\\n\\nfailing to inform the suspect where and for how long they were taking his bags,\\n\\nand when and how he could get them back. See 462 U.S. at 710. So too, in Farm\\n\\nLabor, the Sixth Circuit observed—in the course of holding that the seizure of two\\n\\nsuspects’ green cards couldn’t be justified based on reasonable suspicion alone—\\n\\nthat an officer had failed to act diligently when he “wait[ed] for four days to return\\n\\n[their] green cards” and that “[t]he unreasonable nature of the seizure was\\n\\nexacerbated by the undisputed fact that [the officer] did not make clear . . . how\\n\\n\\n\\n\\n 13\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 14 of 32\\n\\n\\nlong the documents would be held or when or how he would return them.” 308\\n\\nF.3d at 546–47 (internal quotation marks omitted).3\\n\\n Finally, governmental interest. The final factor looks at the other side of the\\n\\nledger. As the Court explained in Place, “[t]he exception to the probable-cause\\n\\nrequirement for limited seizures of the person recognized in Terry and its progeny\\n\\nrests on a balancing of the competing interests to determine the reasonableness of\\n\\nthe type of seizure.” 462 U.S. at 703. Thus, “[w]e must balance the nature and\\n\\nquality of the intrusion on the individual’s Fourth Amendment interests against the\\n\\nimportance of the governmental interests alleged to justify the intrusion.” Id.\\n\\nIn Place, that meant taking account of the public’s compelling interest in\\n\\n“detecting those who would traffic in deadly drugs for personal profit.” Id.\\n\\n(internal quotation marks omitted).\\n\\n 2\\n\\n How, then, do these considerations stack up in this case? In short, not well\\n\\nfor the government. To begin at the end, we don’t doubt for a moment the\\n\\ngovernment’s “compelling” interest in preventing the creation and distribution of\\n\\nchild pornography. E.g., New York v. Ferber, 458 U.S. 747, 761 (1982). Standing\\n\\nalone, though, that interest can’t counterbalance the duration, intrusion, and\\n3\\n The diligence component of the analysis necessarily intersects with the duration component\\nbecause, “[i]n the ordinary case, the sooner the warrant issues, the sooner the property\\nowner’s possessory rights can be restored if the search reveals nothing incriminating”—and, of\\ncourse, the sooner an officer seeks a warrant, the sooner a warrant can issue. See Mitchell, 565\\nF.3d at 1352 (citation omitted).\\n 14\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 15 of 32\\n\\n\\ndiligence factors, all of which—for reasons we will explain—weigh heavily here in\\n\\nfavor of a determination that the officers’ two-day seizure of Babcock’s phone was\\n\\nnot just a brief “investigatory stop” but rather a full-blown seizure that required a\\n\\nshowing of full-blown probable cause. See Place, 462 U.S. at 699–700.\\n\\n Looking first to duration, the government cites United States v. Brignoni-\\n\\nPonce, 422 U.S. 873, 881 (1975), for the proposition that law enforcement may\\n\\n“conduct a limited warrantless seizure of a person or item ‘on facts that do not\\n\\nconstitute probable cause.’” Br. of Appellee at 15. Brignoni-Ponce, however,\\n\\nconsidered only whether a momentary stop for “a brief question or two” was\\n\\npermissible on less than probable cause. 422 U.S. at 880; see also Place, 462 U.S.\\n\\nat 709 (describing Terry and Brignoni Ponce as involving “momentary” stops).\\n\\nBut that’s a far cry from the two-day pre-warrant seizure at issue here. The\\n\\ngovernment also points to what it calls the “similar” case of Laist, in which we\\n\\nheld that a 25-day delay between a seizure and a warrant was permissible. 702\\n\\nF.3d at 614–15. But Laist isn’t similar at all; the seizure in that case was based on\\n\\nprobable cause, not mere reasonable suspicion. Id.; see also Burgard, 675 F.3d at\\n\\n1033 (explaining, in justifying a six-day delay, that a seizure supported by\\n\\nprobable cause permits a much greater intrusion than a seizure supported by mere\\n\\nreasonable suspicion).\\n\\n\\n\\n\\n 15\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 16 of 32\\n\\n\\n What of the more analogous decisions in Place and Puglisi? The\\n\\ngovernment seeks to distinguish them on the ground that both cases analyzed the\\n\\nseizure of luggage “as essentially a detention of the person.” Br. of Appellant at 16\\n\\nn.4. The government asserts that Puglisi, in particular, is inapt because the Court\\n\\nthere held that “[f]or time even to be relevant, the seizure of luggage must have\\n\\nactually or constructively seized the person.” 723 F.2d at 788.\\n\\n Two responses. For starters, we don’t think that this one line, taken alone,\\n\\nrepresents the holding of Puglisi. See Dantzler v. I.R.S., 183 F.3d 1247, 1251\\n\\n(11th Cir. 1999) (“A judicial opinion is not a statute, and not every sentence in a\\n\\njudicial opinion is law.”). Constructive seizure of the person was not the only\\n\\nelement relevant to whether the luggage detention in Puglisi was permissible based\\n\\non reasonable suspicion alone. Instead, we analyzed the 140-minute seizure\\n\\nagainst Place’s considerations of duration, intrusiveness, and diligence before\\n\\ndeeming the detention unlawful. Puglisi, 723 F.2d at 788, 790–91.\\n\\n Furthermore—and more importantly—it’s not clear why, under the rationale\\n\\nof Place and Puglisi, an officer’s confiscation of a cell phone is any less a\\n\\nconstructive seizure of its owner than his detention of luggage (which, per Place,\\n\\nwould make even 90 minutes too long). In Place the Court reasoned that while a\\n\\nsuspect whose luggage is detained is “technically still free to continue his travels,”\\n\\nthe seizure might nonetheless “effectively restrain” him by disrupting his travel\\n\\n\\n 16\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 17 of 32\\n\\n\\nplans. 462 U.S. at 708. Given the ubiquity of cell phones—and our increasing\\n\\nreliance on them—it’s no stretch to hazard that a modern-day traveler would likely\\n\\nrather arrive in a strange place without her luggage than without her phone.\\n\\nWithout the former, she may be left with only the “clothes on [her] back,” Puglisi,\\n\\n723 F.2d at 786, but without the latter she may be left without directions, hotel\\n\\nreservations, and payment and ride-share apps, not to mention voice, text, and\\n\\nemail communications—in short, isolated and incapacitated. Whatever heft the\\n\\nconstructive-seizure argument has with respect to luggage applies equally (if not a\\n\\nfortiori) to cell phones. In any event, no matter what one thinks about the relative\\n\\nimport of luggage and phones, it’s clear that the duration of the seizure in this case\\n\\nputs it in a different bucket than the on-the-spot inquiry hypothesized in Place, see\\n\\n462 U.S. at 705–706, or carried out in Lawing, see 703 F.3d at 238.4\\n\\n Next, the intrusion into Babcock’s possessory interest in his private property\\n\\nwas serious. For many of the reasons just explained, a person’s possessory interest\\n\\nin his cell phone is at least as high as—if not higher than—his interest in his\\n\\n\\n4\\n The government suggested for the first time at oral argument that, rather than lasting two days,\\nthe reasonable-suspicion-based seizure lasted only until Detective Broughton used the phone to\\nprompt C.A.’s confession, at which time the reasonable suspicion became probable cause and,\\npresumably, washed away any budding issues with the seizure. We decline to wade into this\\nargument when the entire record below is predicated on the seizure lasting two days. Because\\nthe government made no argument—and the district court made no finding—concerning the\\nlength of time between the seizure and the confession, any determination of the same on our part\\nwould be mere speculation. See Byrd v. United States, 138 S. Ct. 1518, 1530 (2018) (declining\\nto consider the government’s argument raised for the first time on appeal when argument was\\npredicated on factual issue “not addressed” below and “unclear” from the record).\\n\\n 17\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 18 of 32\\n\\n\\nluggage. A smart phone, as the Supreme Court recently emphasized, is unique in\\n\\nboth the breadth and depth of personal information it stores, including\\n\\n“photographs, picture messages, text messages, Internet browsing history, a\\n\\ncalendar, a thousand-entry phone book”—information that, all told, “reveal[s]\\n\\nmuch more in combination than any isolated record.” Riley v. California, 573 U.S.\\n\\n373, 394 (2014). In other words, while a piece of luggage may hold certain\\n\\nphysical items that an individual needs for a trip, a cell phone holds “[t]he sum of\\n\\nan individual’s private life”—hence our attentiveness to (which is to say obsession\\n\\nwith) our cell phones. Id. Put simply, the government’s confiscation of Babcock’s\\n\\nphone for a period of two days—and with it his personal messages, contacts,\\n\\ncalendar, and more—worked a serious interference with his possessory interests,\\n\\nand undermines the government’s current contention that the seizure was but a\\n\\n“limited intrusion” allowable based on mere reasonable suspicion.\\n\\n Finally, diligence. Detective Broughton’s actions here—holding onto\\n\\nBabcock’s phone over the weekend rather than more promptly attempting to secure\\n\\na warrant, either telephonically or in person—further confirm that the seizure in\\n\\nthis case looks nothing like a Terry stop. The government has offered no\\n\\nexplanation as to why Detective Broughton waited more than two days to take any\\n\\naction regarding the phone, nor does the record evidence indicate that he explained\\n\\nto Babcock when or whether he could expect to get his phone back. And while a\\n\\n\\n 18\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 19 of 32\\n\\n\\ntwo-day delay certainly wouldn’t cross the line in the probable-cause context, see,\\n\\ne.g., Laist, 702 F.3d at 614–15 (approving a 25-day delay in obtaining a warrant\\n\\nfollowing a probable-cause seizure), we know from precedent that it’s well outside\\n\\nthe realm of a permissible Terry stop, and thus weighs heavily against a finding of\\n\\ndiligence here, see Place, 462 U.S. at 710; Virden, 488 F.3d at 1321; Farm Labor,\\n\\n308 F.3d at 546–47.\\n\\n * * *\\n\\n Accordingly, we reject the government’s contention that the officers’ two-\\n\\nday detention of Babcock’s cell phone was a mere investigatory “stop” allowable\\n\\nbased on reasonable suspicion alone. Rather, we hold that it “ripened” into a full-\\n\\nblown seizure that required probable cause. See Puglisi, 723 F.2d at 784.\\n\\n B\\n\\n The government contends, in the alternative, that it can meet the probable-\\n\\ncause standard and, further, that it can show that exigent circumstances justified a\\n\\nwarrantless seizure. We will consider the two components of the government’s\\n\\nargument in turn, looking first to whether the officers at Babcock’s residence had\\n\\nprobable cause to believe that his phone contained evidence of a crime, and then to\\n\\nwhether exigent circumstances excused them from the need to obtain a warrant\\n\\npre-seizure.\\n\\n\\n\\n\\n 19\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 20 of 32\\n\\n\\n 1\\n\\n Probable cause to seize property is what it sounds like—a belief that\\n\\nevidence will probably be found in a particular location. See United States v.\\n\\nNoriega, 676 F.3d 1252, 1261 (11th Cir. 2012). As the Supreme Court recently\\n\\nreiterated, probable cause “is not a high bar.” District of Columbia v. Wesby, 138\\n\\nS. Ct. 577, 586 (2018) (quoting Kaley v. United States, 571 U.S. 320, 338 (2014)).\\n\\nAlthough probable cause requires more than reasonable suspicion that criminal\\n\\nbehavior is afoot, it doesn’t entail the same “standard of conclusiveness and\\n\\nprobability as the facts necessary to support a conviction.” United States v.\\n\\nDunn, 345 F.3d 1285, 1290 (11th Cir. 2003) (internal quotations omitted). Rather,\\n\\nit requires only “a substantial chance” that evidence of criminal activity exists.\\n\\nIllinois v. Gates, 462 U.S. 213, 243 n.13 (1983). We recently explained that this\\n\\n“substantial chance” exists “where the facts within the collective knowledge of law\\n\\nenforcement officials” suffice “to cause a person of reasonable caution to believe\\n\\nthat a criminal offense has been or is being committed”—and here, that evidence\\n\\nof that offense will be found in a particular place. Gates v. Khokar, 884 F.3d 1290,\\n\\n1298 (11th Cir. 2018) (internal quotation marks omitted).\\n\\n Babcock contends that while the officers in this case might have suspected\\n\\nthat something was up, their collective knowledge at the time of the seizure didn’t\\n\\nrise to the level of probable cause that a crime had been committed. To evaluate\\n\\n\\n 20\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 21 of 32\\n\\n\\nthat contention, let’s recap: At the time Detective Broughton retained Babcock’s\\n\\nphone, the officers knew—\\n\\n • that a domestic-disturbance call had reported a female at Babcock’s\\n residence yelling “Stop, stop, stop!”;\\n\\n • that after Babcock had denied that anyone else was in his camper, a teenage\\n girl emerged with cuts on her legs;\\n\\n • that Babcock had accompanied the girl to a Halloween party the night\\n before, where she had consumed alcohol and drugs, and that she was in his\\n camper the next morning;\\n\\n • that the girl had been in or on Babcock’s bed and left traces of blood there;\\n\\n • that the girl had been distraught, holding a knife to her own throat and\\n saying, “I just want to die”; and\\n\\n • that shortly after they arrived at Babcock’s residence, the girl appeared to be\\n panicking or suffering an overdose.\\n\\nFinally—and perhaps most tellingly—the officers knew that, while the girl sat on\\n\\nBabcock’s bed with the knife to her neck, Babcock called her “dumb as f***” and\\n\\nthen complained—in the present tense—that “this is what I deal with right here . . .\\n\\nyou gotta do drama and fighting me all over the place.”\\n\\n Collectively, these circumstances gave the officers probable cause to believe\\n\\nthat Babcock had committed a crime against C.A. This common-sense conclusion\\n\\ndoesn’t depend on any particular fact taken in isolation; rather, as is “often” the\\n\\ncase, “the whole is . . . greater than the sum of its parts.” Wesby, 138 S. Ct. at 588;\\n\\nsee United States v. Arvizu, 534 U.S. 266, 274 (2002) (rejecting a “divide-and-\\n\\n 21\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 22 of 32\\n\\n\\nconquer” approach and instructing courts to evaluate probable cause in light of the\\n\\ntotality of the circumstances). Here, Babcock’s lies contributed to probable cause,\\n\\nsee Wesby, 138 S. Ct. at 587 (citing Devenpeck v. Alford, 543 U.S. 146, 149, 155–\\n\\n56 (2004)), as did his own present-tense statements clearly indicating an ongoing\\n\\nrelationship. When the officers considered Babcock’s own utterances in light of\\n\\nthe litany of other suspicious facts the learned, they certainly could have suspected\\n\\na “substantial chance of criminal activity.” Gates, 462 U.S. at 243 n.13.\\n\\n From there, it required no leap for the officers to deduce that evidence of a\\n\\ncrime would likely be found on Babcock’s phone. The officers already knew that\\n\\nthe phone contained one eyebrow-raising video suggesting an ongoing relationship\\n\\nbetween a grown man and a teenage girl. It was eminently reasonable for them to\\n\\nbelieve that additional evidence of that relationship—messages, texts, pictures,\\n\\nvideos, etc.—would be found in the same place.\\n\\n True, as Babcock points out, the government has been a little wishy-washy\\n\\nabout the exact crime that the officers suspected at the time of the seizure. The\\n\\ngovernment doesn’t contend that the officers had probable cause to believe that the\\n\\nphone contained evidence of child pornography; rather, it concedes that until\\n\\nDetective Broughton confronted C.A. with the phone at the hospital post-seizure,\\n\\nhe had “no reason to believe that there were videos of sexual activity between [the]\\n\\ntwo.” Importantly, though, our precedent doesn’t require officers to predict the\\n\\n\\n 22\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 23 of 32\\n\\n\\neventually-charged offense in order to demonstrate probable cause, only that the\\n\\ncollective facts would cause a “person of reasonable caution” to believe that “a\\n\\ncriminal offense has been or is being committed.” See Khokar, 884 F.3d at 1298\\n\\n(emphasis added) (internal quotation marks omitted).\\n\\n Here, the government’s arguments at the suppression hearing focused\\n\\nmainly on preserving both the video of C.A. on the bed and any evidence that\\n\\nmight have shed light on the events leading up to it. And indeed, that is exactly\\n\\nwhat the officers ended up finding: evidence of an illegal, coercive relationship,\\n\\nconfirming the suspicions sparked by the video’s portrayal of Babcock’s\\n\\ndisdainful, bullying tone and C.A.’s distraught appearance. The fact that the phone\\n\\nalso (and unexpectedly) contained pornographic images and videos doesn’t\\n\\ninvalidate probable cause for any number of Florida state crimes the officers\\n\\nreasonably could have believed occurred based on the scene greeting them at\\n\\nBabcock’s residence. See, e.g., Fla. Stat. § 794.05(1) (“Unlawful sexual activity\\n\\nwith certain minors”); id. § 794.011(4)(a) (“Sexual battery”). Accordingly, we\\n\\nhold that on these facts the officers had probable cause to believe that Babcock was\\n\\nguilty of a crime, and that evidence of the crime would be found on his phone.\\n\\n 2\\n\\n Of course, probable cause isn’t alone enough to seize an individual’s\\n\\npersonal property—officers typically need a warrant. “[A] warrantless search\\n\\n\\n 23\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 24 of 32\\n\\n\\nand seizure can be justified,” however, “when probable cause has been established\\n\\nto believe that evidence will be removed or destroyed before a warrant can be\\n\\nobtained.” United States v. Young, 909 F.2d 442, 446 (11th Cir. 1990). This\\n\\nexception—one branch of the “exigent-circumstances” doctrine—entails, like\\n\\nprobable cause itself, an objective inquiry. See United States v. Bradley, 644 F.3d\\n\\n1213, 1262 (11th Cir. 2011).\\n\\n Historically, we have found the exigent-circumstances exception\\n\\n“particularly compelling” in drug cases “because contraband and records can be\\n\\neasily and quickly destroyed while a search is progressing.” Young, 909 F.2d at\\n\\n446. The same is true of electronic files. In Bradley, for instance, we found that\\n\\nthe exigent-circumstances exception permitted officers to shut down a company’s\\n\\nservers—a seizure of the company’s property—when multiple employees “had the\\n\\nability and incentive to, after learning of the raid, destroy damning information\\n\\ncontained on the computer servers.” 644 F.3d at 1262–63.\\n\\n To be clear, it’s not that a cell phone itself creates an exigent circumstance.\\n\\n“Taken to its logical conclusion,” that “would permit police officers to seize now-\\n\\nubiquitous cell phones from any person, in any place, at any time, so long as the\\n\\nphone contains photographs or videos that could serve as evidence of a crime—\\n\\nsimply because the ‘nature’ of the device used to capture that evidence might result\\n\\nin it being lost.” Crocker v. Beatty, 886 F.3d 1132, 1137 (11th Cir. 2018)\\n\\n\\n 24\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 25 of 32\\n\\n\\n(emphasis in original). In Crocker, we held that the exigent-circumstances\\n\\nexception didn’t apply where an officer had seized a bystander’s phone to prevent\\n\\ndeletion of photographs that he observed the onlooker snapping following a huge\\n\\nhighway crash. Id. Absent any reason for the officer to think that the bystander\\n\\nwouldn’t preserve the pictures or would refuse to turn them over if asked, we\\n\\nfound the government’s exigent-circumstances argument unconvincing. Id.\\n\\n This case is different. Given the facts here, a reasonable, experienced agent\\n\\ncertainly could have believed that Babcock—the suspect, not a mere bystander—\\n\\nwould delete any incriminating evidence on his phone before a warrant could be\\n\\nobtained. For starters, Babcock had tried to deceive the responding officers from\\n\\nthe get-go, denying that anyone else was in his camper, reporting that C.A. had\\n\\nrandomly shown up at his house in the middle of the night, and claiming that he\\n\\ndidn’t know her age—all lies. Moreover Babcock surely knew that he was under\\n\\nsuspicion once Detective Broughton asked to search the camper and to further\\n\\ninspect his phone. Finally, of course, and on top of all that, the electronic files on\\n\\nBabcock’s phone could have been “quickly destroyed while [the] search [wa]s\\n\\nprogressing.” Young, 909 F.2d at 446. All told, as in Bradley, it was reasonable\\n\\nfor the officers here to conclude that Babcock had the “ability and incentive to,\\n\\nafter learning” of the investigation into his relationship with C.A., “destroy\\n\\n\\n\\n\\n 25\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 26 of 32\\n\\n\\ndamning information contained on” his phone. 644 F.3d at 1262–63. That’s all\\n\\nthe exigent-circumstances doctrine requires. 5\\n\\n Babcock contends that his offer to e-mail the video to the officers removed\\n\\nany urgency, thereby undermining any exigent-circumstances argument. He cites\\n\\nour decision in United States v. Hernandez-Cano, 808 F.2d 779 (11th Cir. 1987),\\n\\nfor the proposition that officers can’t claim exigent circumstances when the\\n\\nsupposed risk can be alleviated by alternative means. But Hernandez-Cano was\\n\\ndifferent—and in fact boomerangs back around on Babcock here. There, we\\n\\nconsidered a warrantless search of a suspect’s luggage and determined that,\\n\\nbecause officers had probable cause to arrest him at the time of the search, “any\\n\\nexigencies inherent in the situation could have been removed” by simply doing so.\\n\\n5\\n Babcock asserts that the government forfeited its exigency argument by failing to use the\\nphrase “exigent circumstances”—and failing to fully develop its position regarding the same—in\\nits response to the motion to suppress. We disagree. While it’s true that alternative theories of\\nadmissibility—including exigent circumstances—can be forfeited even when the government is\\nthe appellee or respondent, see Steagald v. United States, 451 U.S. 204, 208 (1981); Giordenello\\nv. United States, 357 U.S. 480, 487–88 (1958), we conclude that the government did enough here\\nto preserve its exigent-circumstances argument. To be sure, in responding to Babcock’s motion\\nto suppress, the government didn’t use the phrase “exigent circumstances” or cite case law\\nspecifically in support of the exception. It did argue, though, that “[t]he deputies had probable\\ncause to believe that the phone had evidentiary value” and that “detention of the cellular phone\\nwas necessary to preserve the evidence observed by the deputies.” Gov’t Resp. Mot. Suppress at\\n5 (emphasis added). That—whether accompanied by magic words or not—is the very definition\\nof the exigent-circumstances exception. See, e.g., Young, 909 F.2d at 446 (“[W]hen probable\\ncause has been established to believe that evidence will be removed or destroyed before a\\nwarrant can be obtained, a warrantless search and seizure can be justified.”). That the\\ngovernment presented a more robust version of its argument on appeal doesn’t render its initial\\nargument null. See, e.g., Sec’y, U.S. Dep’t of Labor v. Preston, 873 F.3d 877, 883 n.5 (11th Cir.\\n2017) (explaining that “[o]ffering a new argument or case citation in support of a position\\nadvanced in the district court is permissible—and often advisable” lest “the quality and depth of\\nargument [fail] to improve on appeal—an unfortunate result”), cert. denied sub nom. Preston v.\\nAcosta, 138 S. Ct. 2680 (2018).\\n 26\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 27 of 32\\n\\n\\nId. at 782. We explained that “[e]ven if exigent circumstances existed that justified\\n\\nthe seizure of the suitcase to prevent the loss or destruction of its contents, the\\n\\ngovernment still had to obtain a warrant to search the suitcase.” Id. (emphasis\\n\\nadded). Here, the officers didn’t conduct a warrantless search. Instead, faced with\\n\\nthe potential destruction of evidence, they did exactly what Hernandez-Cano\\n\\nsuggests they should have done—they seized the phone “to prevent the loss or\\n\\ndestruction of its contents,” and then obtained a warrant before searching through\\n\\nit. See id.\\n\\n Thus, because a reasonable officer could have believed that Babcock would\\n\\ndelete any incriminating evidence on his phone before a warrant could be\\n\\nobtained—and because none of Babcock’s arguments convinces us otherwise—we\\n\\nfind that the exigent-circumstances exception applies in this case.6\\n\\n * * *\\n\\n\\n6\\n The government also argues in the alternative that Babcock consented to the seizure by\\nvoluntarily providing his phone to the officers to display the video of C.A. threatening self-harm.\\nIt is well-settled, however, that “the scope of a search based on consent may not exceed the\\nscope of the given consent.” United States v. Watkins, 760 F.3d 1271, 1279 (11th Cir. 2014)\\n(citing Florida v. Jimeno, 500 U.S. 248, 251 (1991)). The standard for measuring the scope of\\nconsent is “objective reasonableness”—what “would the typical reasonable person have\\nunderstood by the exchange between the officer and the [individual giving the consent]?” Id.\\n(internal quotation marks omitted). Here, Babcock clearly consented only to the officers’\\nviewing the video he showed them. After the initial viewing, Deputy Olson asked for the phone\\nagain, for the express purpose of showing Officer McMahan the video. Babcock consented to\\nthe officers viewing the clip again, but then asked for his phone back and refused consent when\\nDetective Broughton asked to poke around further. Contrary to the government’s contention, the\\ninitial limited-in-scope consent doesn’t justify an unlimited-in-scope full seizure over Babcock’s\\nobjection.\\n\\n 27\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 28 of 32\\n\\n\\n To sum up, we reject the government’s contention that a two-day\\n\\nwarrantless seizure of a suspect’s cell phone is permissible based on reasonable\\n\\nsuspicion alone. We conclude, however, that the warrantless seizure of Babcock’s\\n\\nphone was lawful because the officers on the scene had probable cause to believe\\n\\nboth that evidence of a crime would be found on it and that the evidence would be\\n\\ndestroyed before they could obtain a warrant.\\n\\n III\\n\\n Babcock separately challenges his sentence, arguing that it is both (1)\\n\\nprocedurally unreasonable because the district court erroneously imposed two\\n\\nenhancements for the same harm and (2) substantively unreasonable because it is\\n\\ntoo harsh in light of the facts.7 Neither argument is persuasive.\\n\\n Babcock raises his procedural-reasonableness argument for the first time on\\n\\nappeal, so we can correct any missteps only if he shows a “plain error” that affects\\n\\nhis substantial rights and that seriously undermines the fairness, integrity, or public\\n\\nreputation of judicial proceedings. See United States v. Shelton, 400 F.3d 1325,\\n\\n1328–29 (11th Cir. 2005). Babcock essentially argues that the district court’s\\n\\napplication of both § 2G2.1(b)(2) and § 4B1.5(b) of the Sentencing Guidelines\\n\\nconstitutes impermissible double-counting.\\n\\n7\\n Babcock also argues that his sentence is procedurally unreasonable because the government did\\nnot group two counts of conviction which were based on the same harm. As the government\\npoints out, though, the Guidelines specifically exclude convictions under § 2G2.1 from the\\ngrouping rules. See U.S.S.G. § 3D1.2(d).\\n\\n 28\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 29 of 32\\n\\n\\n Double-counting occurs when one part of the Sentencing Guidelines is\\n\\napplied to increase a defendant’s punishment on account of a harm that has already\\n\\nbeen fully accounted for by application of another part of the Guidelines. See\\n\\nUnited States v. Dudley, 463 F.3d 1221, 1226–27 (11th Cir. 2006). Absent\\n\\nevidence to the contrary, however, the presumption is that “the Sentencing\\n\\nCommission intended to apply separate sections cumulatively,” United States v.\\n\\nKapordelis, 569 F.3d 1291, 1315 (11th Cir. 2009) (citation omitted), such that\\n\\nwhat might appear to be impermissible double-counting is instead what we will\\n\\ncall permissible “cumulative-counting.”\\n\\n We conclude that applying both enhancements in this case constitutes\\n\\ncumulative- (rather than double-) counting. Chapter Two of the Guidelines,\\n\\nfocusing on the sexual exploitation of minors through pictures, provides that an\\n\\noffender’s base sentencing level should be enhanced by two when “the commission\\n\\nof a sexual act or sexual contact” occurs during a visual depiction. U.S.S.G.\\n\\n§ 2G2.1(b)(2)(A). Chapter Four then makes clear that when a “pattern of . . .\\n\\nprohibited sexual contact” occurs, a court should add five to “the offense level\\n\\ndetermined under Chapter[] Two.” U.S.S.G. § 4B1.5(b). The Guidelines say\\n\\nnothing about adding this enhancement to only a portion of the base level\\n\\ndetermined under Chapter Two, or otherwise adjusting the calculation in any\\n\\nway—instead, they simply presuppose that a certain offense level was determined\\n\\n\\n 29\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 30 of 32\\n\\n\\nunder Chapter Two, and then instruct the sentencing court to add five levels,\\n\\nperiod. Nothing in the Guidelines, then, indicates that these sections may not be\\n\\napplied cumulatively. See Kapordelis, 569 F.3d at 1315. Moreover, and in any\\n\\nevent, it isn’t clear that the harm in § 4B1.5(b)’s “pattern of activity involving\\n\\nprohibited sexual contact” is “fully accounted for” in § 2G2.1(b)(2)’s “sexual act\\n\\nor sexual contact” occurring in a visual depiction, such that application of the two\\n\\nsections could be considered double-counting at all. See Dudley, 463 F.3d at\\n\\n1226–27. There was no plain error here.\\n\\n Looking next to substantive reasonableness, Babcock argues that the nature\\n\\nand circumstances of this case do not compel the same severe sentence required to\\n\\ndeter creators of commercial child pornography. Basically, Babcock contends that\\n\\nhis crime—an inappropriate, long-term relationship with an older teenager—\\n\\ndoesn’t indicate that he is a threat to children generally or affect the child-\\n\\npornography market as would, for instance, the rape of a child for video\\n\\ndistribution or other predatory production of commercial child pornography.\\n\\nBabcock asserts that because there is no evidence that he intended ever to show\\n\\nanyone his videos or pictures of C.A., his 324-month sentence is substantively\\n\\nunreasonable.\\n\\n We review challenges to the substantive reasonableness of a sentence for\\n\\nabuse of discretion. Gall v. United States, 552 U.S. 38, 41 (2007). The party\\n\\n\\n 30\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 31 of 32\\n\\n\\nchallenging the sentence bears the burden of showing that the sentence is\\n\\nunreasonable in light of the record and the 18 U.S.C. § 3553(a) factors. United\\n\\nStates v. Tome, 611 F.3d 1371, 1378 (11th Cir. 2010). While we do not formally\\n\\npresume that a within-Guidelines sentence is reasonable, we ordinarily expect it to\\n\\nbe so. United States v. Hunt, 526 F.3d 739, 746 (11th Cir. 2008). That a sentence\\n\\nis imposed well below the statutory maximum penalty may also indicate its\\n\\nreasonableness. See United States v. Gonzalez, 550 F.3d 1319, 1324 (11th Cir.\\n\\n2008) (per curiam).\\n\\n There is a certain intuitive logic to Babcock’s argument here—it’s true that\\n\\nnothing in the record necessarily indicates a propensity to distribute child\\n\\npornography. That being said, Babcock’s conduct falls squarely within the\\n\\nconfines of § 2G2.1—“sexually exploiting a minor by production of sexually\\n\\nexplicit visual or printed material”—and, as the sentencing judge emphasized, the\\n\\neffect of his actions on C.A. and her family was far from insignificant. We are\\n\\ncomfortable that the sentencing judge took into consideration all of the relevant\\n\\ncircumstances when he sentenced Babcock to 324 months—a downward variance\\n\\nfrom the 360 to 720 months recommended by the Guidelines. See Gonzalez, 550\\n\\nF.3d at 1324. Accordingly, we find no abuse of discretion in the district court’s\\n\\nsentencing decision.\\n\\n\\n\\n\\n 31\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 32 of 32\\n\\n\\n IV\\n\\n For the foregoing reasons, we hold (1) that reasonable suspicion alone could\\n\\nnot have justified the officers’ warrantless two-day seizure of Babcock’s cell\\n\\nphone; (2) that the officers in this case had probable cause to believe that a crime\\n\\nhad been committed, that evidence of the crime would be found on Babcock’s\\n\\nphone, and that there was a risk that Babcock would destroy the evidence before\\n\\nthey could get a warrant, such that the seizure did not violate the Fourth\\n\\nAmendment; and (3) that Babcock’s sentence was both procedurally and\\n\\nsubstantively reasonable. Accordingly, we affirm the district court’s denial of\\n\\nBabcock’s motion to suppress as well as its 324-month sentence.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 32\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4400502/\", \"author_raw\": \"NEWSOM, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"WILLIAM PRYOR"},"judge2":{"kind":"string","value":"NEWSOM"},"judge3":{"kind":"string","value":"VRATIL"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{\"WILLIAM PRYOR\": \", Circuit\", \"NEWSOM\": \", Circuit\", \"VRATIL\": \", District\"}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4623249/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: United States v. Darrell Mark Babcock\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-24\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-13678 Date Filed: 05/24/2019 Page: 1 of 32\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-13678\n ________________________\n\n D.C. Docket No. 2:16-cr-14071-KAM-1\n\n\n\nUNITED STATES OF AMERICA,\n\n Plaintiff - Appellee,\n\nversus\n\nDARRELL MARK BABCOCK,\n\n Defendant - Appellant.\n\n ________________________\n\n Appeal from the United States District Court\n for the Southern District of Florida\n ________________________\n\n (May 24, 2019)\n\nBefore WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District\nJudge.\n\n\n\n\n*\n The Honorable Kathryn H. Vratil, United States District Court Judge for the District of Kansas,\nsitting by designation.\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 2 of 32\n\n\nNEWSOM, Circuit Judge:\n\n In this case, police officers investigating a domestic disturbance confiscated\n\na suspect’s cell phone and held it for two days before eventually obtaining a\n\nwarrant to search it. The appeal before us presents two Fourth Amendment\n\nquestions. First, was the seizure justified on the ground that the officers had\n\nreasonable suspicion to believe that the phone’s owner was engaged in criminal\n\nwrongdoing—was it, in effect, a permissible “Terry stop” of the phone? We hold\n\nthat it was not. Second, in the particular circumstances of this case, did the officers\n\nhave probable cause to believe not only that the phone’s owner had committed a\n\ncrime and that the phone contained evidence of that crime, but also that the suspect\n\nwould likely destroy that evidence before they could procure a warrant? We hold\n\nthat they did. Accordingly, and on that ground, we affirm the district court’s order\n\ndenying the motion to suppress. We separately affirm the district court’s sentence.\n\n I\n\n A\n\n Early one Friday morning, Deputy Andrea Olson of the Stuart, Florida\n\nPolice Department responded to a domestic-disturbance call reporting a ruckus\n\ncoming from a camper parked at Darrell Babcock’s residence—specifically, a\n\nfemale had been heard yelling, “Stop, stop, stop!” When Deputy Olson knocked\n\non the door of Babcock’s camper, Babcock exited, closed the door behind him, and\n\n\n 2\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 3 of 32\n\n\nvolunteered that no one else was inside. Almost immediately, though, Deputy\n\nOlson heard a female announce that she was coming out. A teenage girl emerged\n\nfrom the trailer; she was wearing only yoga shorts and a camo jacket, and she had\n\nblood on her left thigh. Seemingly by way of explanation, Babcock handed\n\nDeputy Olson his cell phone to show her a video of the girl—we’ll call her C.A.—\n\nsitting on a bed, holding a knife to her own throat and saying that she wanted to\n\ndie. In the video Babcock could be heard berating the girl, telling her, “you’re\n\ndumb as f***” and complaining, “this is what I deal with right here . . . you gotta\n\ndo drama and fighting me all over the place.” After viewing the clip, Deputy\n\nOlson returned Babcock’s phone. When backup arrived on the scene, Deputy\n\nOlson asked for the phone again so that she could show the video to her colleague,\n\nOfficer Michael McMahan.\n\n The officers then interviewed Babcock and C.A. separately. Babcock denied\n\nknowing C.A.’s age and also disputed that the two were in a relationship, although\n\nhe admitted that he had known C.A. for three years and that she used to be his\n\nneighbor. He also said that C.A. had shown up at his camper unannounced,\n\nsometime during the middle of the night. C.A., by contrast—whose license\n\nshowed that she was only 16 years old—stated that she and Babcock had gone\n\ntogether the night before to a Halloween party, where she had consumed alcohol,\n\ncocaine, and other substances. After answering a few questions, C.A. began either\n\n\n 3\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 4 of 32\n\n\npanicking or experiencing the effects of an overdose, so the officers called an\n\nambulance. Deputy Olson rode with C.A. to the hospital.\n\n Meanwhile, another officer, Detective Brian Broughton, remained behind to\n\ncontinue questioning Babcock. Detective Broughton sought and received\n\npermission to search Babcock’s camper, where he discovered blood on the\n\nbedsheets and prescription pills scattered about. When Detective Broughton asked\n\nto further inspect Babcock’s phone, Babcock refused and asked to have it back.\n\nBabcock offered to e-mail the video clip of C.A. with the knife, but Detective\n\nBroughton decided to keep the phone instead. He told Officer McMahan to enter it\n\ninto evidence and then took it with him to the hospital to talk to C.A.\n\n At the hospital, C.A. again insisted that she and Babcock were just friends,\n\nthat they had gone to a Halloween party, and that the two had then argued. She\n\nfirmly denied any further relationship. But when Detective Broughton informed\n\nC.A. that he had Babcock’s phone, she abruptly reversed course and admitted that\n\nthe two had been in a relationship and, further, that the officers would find sexually\n\nexplicit images of her on the phone. Two days later, Detective Broughton applied\n\nfor and obtained a warrant to search the phone, where he found nude images of\n\nC.A. and explicit video recordings of Babcock and C.A. together.\n\n\n\n\n 4\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 5 of 32\n\n\n B\n\n Babcock was charged with two counts of producing a visual depiction of\n\nsexually explicit conduct with a minor in violation of 18 U.S.C. § 2251(a), (e). He\n\nfiled a motion to suppress, arguing that officers had seized his phone without a\n\nwarrant or probable cause. The government filed a response, arguing primarily\n\nthat the cell-phone seizure was reasonable because “under the totality of the\n\ncircumstances” the officers had “reasonable suspicion to investigate further,” and\n\nadding that, at any rate, the officers had probable cause to believe that the phone\n\ncontained evidence of a crime. The government further contended that “detention\n\nof the cell phone was necessary to preserve the evidence observed by the\n\ndeputies.” Finally, the government asserted that, even in the absence of a warrant,\n\neither Babcock’s consent or the inevitability that the images would have been\n\ndiscovered rendered the seizure constitutional.\n\n A magistrate judge recommended that Babcock’s motion be denied. He\n\nconcluded—referencing two distinct Fourth Amendment standards—that “the\n\ncollective knowledge and information received by the officers at the scene\n\nconstituted sufficient probable cause and reasonable suspicion that there may have\n\nbeen a crime committed which may have been preserved on the cell phone.” The\n\ndistrict court agreed, noting—also somewhat vaguely—that the surrounding\n\ncircumstances were “sufficient for law enforcement to suspect inappropriate\n\n\n 5\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 6 of 32\n\n\nconduct between [Babcock] and C.A.” Later, at sentencing, the district judge\n\nfurther remarked that although he “didn’t say [it] in the order,” he was “putting [it]\n\non the record for appellate purposes” that in the video C.A. “appear[ed] to be either\n\nwith no pants on or underwear” and that, based on “what she says and how she\n\nsays it about what she wants to do to herself,” it was “obvious . . . that there was an\n\ninappropriate relationship going on which would have given [the officers]\n\nreasonable probable cause to believe that there was inappropriate sexual activity\n\nbetween” Babcock and C.A. Babcock took a plea, reserving his right to appeal the\n\ndenial of his motion to suppress.\n\n At sentencing, Babcock asked for the mandatory minimum of 180 months,\n\narguing that his conduct, while inappropriate, was outside the core child-\n\npornography-distribution behavior that Congress sought to deter under § 2251(a)\n\nand (e). The government in turn asked for a sentence within the 360-to-720-month\n\nrecommended Guidelines range, stressing the harm to C.A. and her family. The\n\ncourt imposed a below-Guidelines sentence of 324 months. Babcock appealed\n\nboth the denial of his motion to suppress and his sentence.\n\n II\n\n We’ll tackle the Fourth Amendment issues first. A person suffers a\n\n“seizure” of his property within the meaning of the Fourth Amendment when there\n\nis a “meaningful interference” with his possessory interest in it. United States v.\n\n\n 6\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 7 of 32\n\n\nVirden, 488 F.3d 1317, 1321 (11th Cir. 2007).1 While the seizure of private\n\nproperty generally requires a warrant, the Supreme Court has interpreted the\n\nFourth Amendment to allow a warrantless seizure when police can show both (1)\n\nprobable cause to believe that property contains contraband or evidence of a crime\n\nand (2) an applicable warrant exception, such as exigent circumstances. See, e.g.,\n\nKentucky v. King, 563 U.S. 452, 459–60 (2011) (citations omitted). Accordingly,\n\nabsent either a warrant or probable cause plus an exception, police may not seize\n\nprivate property. There is, however, an asterisk. Under a line of luggage-related\n\ncases from the 1980s, police may “briefly detain” property—Terry-stop style—on\n\nthe strength of reasonable suspicion alone. See United States v. Place, 462 U.S.\n\n696, 697–98 (1983); United States v. Puglisi, 723 F.2d 779, 788–89 (11th Cir.\n\n1984).\n\n Here, the government principally argues that these cases permitted the\n\nofficers to detain Babcock’s phone based on their reasonable suspicion that he had\n\ncommitted a crime. Alternatively, the government contends that the officers had\n\nprobable cause to believe that the phone contained evidence of a crime and that\n\nexigent circumstances—namely, the need to prevent the destruction of that\n\nevidence—allowed them to seize the phone. We consider each argument in turn.\n1\n When reviewing the denial of a motion to suppress, we review factual findings for clear error\nand legal determinations de novo. United States v. Gibson, 708 F.3d 1256, 1274 (11th Cir.\n2013). We also review the evidence in the light most favorable to the government, as the\nprevailing party. See United States v. Capers, 708 F.3d 1286, 1295–96 (11th Cir. 2013).\n\n 7\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 8 of 32\n\n\n A\n\n 1\n\n Reasonable suspicion is “a particularized and objective basis” for suspecting\n\na person of criminal activity. Ornelas v. United States, 517 U.S. 690, 696 (1996)\n\n(quotation marks omitted). It requires “specific, articulable, and objective facts\n\nreasonably to suspect” that a crime is being or will soon be committed, Puglisi,\n\n723 F.2d at 789, but “is a less demanding standard than probable cause,” Illinois v.\n\nWardlow, 528 U.S. 119, 123 (2000). In Terry v. Ohio, the Supreme Court\n\nfamously held that, even absent probable cause, police officers may briefly detain\n\nan individual based on reasonable suspicion that he is (or is about to be) engaged in\n\ncriminal activity. See 392 U.S. 1, 30–31 (1968).\n\n The Supreme Court first extended Terry’s rationale from people to property\n\nin United States v. Place, 462 U.S. 696 (1983). There, the Court held that while a\n\nbrief investigatory detention of property could be justified on the basis of\n\nreasonable suspicion alone, an officer’s 90-minute seizure of an airline traveler’s\n\nsuitcase exceeded constitutional boundaries. Id. at 702. In so holding, the Court\n\nrecognized that “[t]he intrusion on possessory interests occasioned by a seizure of\n\none’s personal effects can vary both in its nature and extent.” Id. at 705. While\n\nsome “brief detentions of personal effects”—such as, the Court hypothesized, “on-\n\nthe-spot” dog sniffs—may be “so minimally intrusive” as to “justify a seizure\n\n\n 8\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 9 of 32\n\n\nbased only on specific articulable facts that the property contains contraband,” the\n\nluggage seizure didn’t fit the bill. Id. at 705–06. By way of explanation, the Court\n\nemphasized several factors: the duration of the detention, the degree of the\n\nintrusion on the owner’s possessory interests in his property, and the officer’s lack\n\nof diligence in timely pursuing their investigation. Id. at 709–10. The Court also\n\nhighlighted that a confiscation of luggage, in particular, interferes not only with\n\npossessory interests but also with liberty interests because, while a suspect whose\n\nluggage is stopped is “technically still free to continue” on his way, the detention\n\nmight “effectively restrain” him by disrupting his travel plans. Id. at 708–09.\n\n Shortly after the Supreme Court decided Place, this Court had occasion to\n\napply it on similar facts. In United States v. Puglisi, an officer made what began as\n\na brief stop by ordering a suspicious traveler’s bags removed from a luggage cart;\n\nhe then stowed the luggage in his office until a drug-sniffing dog became available.\n\n723 F.2d 779, 790 (11th Cir. 1984). Meanwhile, the traveler boarded his flight\n\nwithout his bags. Although we deemed the initial seizure permissible under Terry,\n\nwe found that the length and intrusiveness—140 minutes—caused the “brief stop”\n\nto “ripen” into a full-blown seizure that could be justified only by probable cause.\n\nId. at 784. We explained that “Place requires the same test as Terry: a court must\n\nweigh the intrusiveness of a limited seizure of the individual against society’s\n\ninterest in detection and prevention of crime.” Id. at 785. We cautioned, however,\n\n\n 9\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 10 of 32\n\n\nthat because the Fourth Amendment “protects people, not things,” the focus was\n\nthe effective “seizure of persons, through their luggage.” Id. at 787–88.\n\n Although Place and Puglisi concerned luggage, both this Court and others\n\nhave since indicated that any detention of property based on reasonable suspicion\n\nmust be fairly analogous to a Terry stop, regardless of the item at issue.\n\nAccordingly, we have said, “the factors used to determine whether a Terry stop has\n\nmatured into an arrest are also useful in evaluating whether a seizure of property\n\nrequired probable cause” rather than mere reasonable suspicion. Virden, 488 F.3d\n\nat 1321. Echoing Place, we have said that these factors include, but are not limited\n\nto, (1) the detention’s duration, (2) its intrusiveness, (3) the diligence with which\n\nofficers pursued their investigation, and (4) the law-enforcement purposes served\n\nby the detention. See id.; accord United States v. Gonzalez, 781 F.3d 422, 428–29\n\n(8th Cir. 2015); Farm Labor Org. Comm. v. Ohio State Highway Patrol, 308 F.3d\n\n523, 544–45 (6th Cir. 2002); United States v. $557,933.89, More or Less, in U.S.\n\nFunds, 287 F.3d 66, 86 (2d Cir. 2002). We’ll explain each in a bit more detail here\n\nbefore applying them to the facts of this case\n\n First, duration. Although the Supreme Court has “decline[d] to adopt any\n\noutside time limit for a permissible Terry stop,” the Court in Place observed that it\n\nhad “never approved a seizure of the person for the prolonged 90-minute period\n\ninvolved” in that case and that, on the facts presented there, it wouldn’t approve a\n\n\n 10\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 11 of 32\n\n\n90-minute detention of property, either. 462 U.S. at 709–10. In Virden, this Court\n\nsimilarly determined that an officer’s transfer of a defendant and his car to another\n\nlocation for a dog sniff, “[w]hile not unduly lengthy” at about 30 minutes, was\n\nnonetheless “unreasonable absent probable cause.” 488 F.3d at 1321. 2\n\n At the other end of the spectrum, the Fourth Circuit has approved a seconds-\n\nlong cell-phone stop on the basis of reasonable suspicion alone. In United States v.\n\nLawing, that court held that an officer’s brief detention of a suspect’s phone during\n\na traffic stop—for just long enough to see if it would ring when the officer dialed a\n\nknown drug-distributor’s number—was sufficiently minimal to qualify for\n\nTerry/Place treatment. 703 F.3d 229, 238 (4th Cir. 2012). Similarly, the Second\n\nCircuit held that reasonable suspicion justified a brief investigatory detention that\n\noccurred when a detective took between two and 20 minutes to respond to a\n\nrequest for a luggage investigation while a traveler waited at an airport security\n\ncheckpoint with his luggage. See $557,933.89, More or Less, 287 F.3d at 71, 86–\n\n87 & n.16.\n\n Second, intrusiveness. The “intrusiveness” factor concerns the degree to\n\nwhich a property detention interferes with a person’s possessory interest in his\n\nbelongings. In Place, for instance, the Court emphasized that although “the\n\n2\n Even though the detention there more directly implicated the owner’s liberty interests than in\nPlace because the owner remained in his car while it was transported to another location, we\nanalyzed the stop primarily as one of property rather than of an individual. See Virden, 488 F.3d\nat 1321.\n 11\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 12 of 32\n\n\nparticular course of investigation that the agents intended to pursue”—just a brief\n\n“exposure of respondent’s luggage, which was located in a public place, to a\n\ntrained canine”—would have been permissible based on mere reasonable\n\nsuspicion, the 90-minute seizure that they actually effected was not. 462 U.S. at\n\n707, 709–10 (emphasis added). The Court explained that the planned sniff would\n\nhave revealed “only the presence or absence of narcotics, a contraband item,” and\n\nwouldn’t have exposed the traveler’s personal “noncontraband items that otherwise\n\nwould remain hidden from public view, as [would], for example, an officer’s\n\nrummaging through the contents of the luggage.” Id. at 707.\n\n This Court has likewise recognized that individuals have strong interests in\n\ncontainers that hold personal effects or private information, such as luggage and\n\ncomputers. In Puglisi, we emphasized that “privacy and possessory interests in\n\nluggage are often high” because a traveler may have “his most important and\n\nprivate possessions in his suitcase” and likely wants “to shield them from the\n\nprying eyes of strangers, especially the government.” 723 F.2d at 786. And in\n\nUnited States v. Laist, we acknowledged that “computers are a unique possession,\n\none in which individuals may have a particularly powerful possessory interest,”\n\nbecause they store “personal letters, e-mails, financial information, passwords,\n\nfamily photos, and countless other items of a personal nature.” 702 F.3d 608, 614\n\n(11th Cir. 2012); see also United States v. Mitchell, 565 F.3d 1347, 1352 (11th Cir.\n\n\n 12\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 13 of 32\n\n\n2009) (calling a computer hard drive “the digital equivalent of its owner’s home,\n\ncapable of holding a universe of private information”) (internal quotation marks\n\nomitted).\n\n Third, diligence. When police diligently pursue their investigation, a\n\nreviewing court can have greater confidence that the governmental interest is\n\nlegitimate and that the intrusion occasioned by the challenged detention was no\n\ngreater than reasonably necessary. See United States v. Burgard, 675 F.3d 1029,\n\n1033 (7th Cir. 2012). “Diligence” in this context includes not only seeking a\n\nwarrant application promptly, but also communicating with the suspect concerning\n\nthe specifics of the detention. In Place, for instance, the Court faulted officers for\n\nfailing to inform the suspect where and for how long they were taking his bags,\n\nand when and how he could get them back. See 462 U.S. at 710. So too, in Farm\n\nLabor, the Sixth Circuit observed—in the course of holding that the seizure of two\n\nsuspects’ green cards couldn’t be justified based on reasonable suspicion alone—\n\nthat an officer had failed to act diligently when he “wait[ed] for four days to return\n\n[their] green cards” and that “[t]he unreasonable nature of the seizure was\n\nexacerbated by the undisputed fact that [the officer] did not make clear . . . how\n\n\n\n\n 13\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 14 of 32\n\n\nlong the documents would be held or when or how he would return them.” 308\n\nF.3d at 546–47 (internal quotation marks omitted).3\n\n Finally, governmental interest. The final factor looks at the other side of the\n\nledger. As the Court explained in Place, “[t]he exception to the probable-cause\n\nrequirement for limited seizures of the person recognized in Terry and its progeny\n\nrests on a balancing of the competing interests to determine the reasonableness of\n\nthe type of seizure.” 462 U.S. at 703. Thus, “[w]e must balance the nature and\n\nquality of the intrusion on the individual’s Fourth Amendment interests against the\n\nimportance of the governmental interests alleged to justify the intrusion.” Id.\n\nIn Place, that meant taking account of the public’s compelling interest in\n\n“detecting those who would traffic in deadly drugs for personal profit.” Id.\n\n(internal quotation marks omitted).\n\n 2\n\n How, then, do these considerations stack up in this case? In short, not well\n\nfor the government. To begin at the end, we don’t doubt for a moment the\n\ngovernment’s “compelling” interest in preventing the creation and distribution of\n\nchild pornography. E.g., New York v. Ferber, 458 U.S. 747, 761 (1982). Standing\n\nalone, though, that interest can’t counterbalance the duration, intrusion, and\n3\n The diligence component of the analysis necessarily intersects with the duration component\nbecause, “[i]n the ordinary case, the sooner the warrant issues, the sooner the property\nowner’s possessory rights can be restored if the search reveals nothing incriminating”—and, of\ncourse, the sooner an officer seeks a warrant, the sooner a warrant can issue. See Mitchell, 565\nF.3d at 1352 (citation omitted).\n 14\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 15 of 32\n\n\ndiligence factors, all of which—for reasons we will explain—weigh heavily here in\n\nfavor of a determination that the officers’ two-day seizure of Babcock’s phone was\n\nnot just a brief “investigatory stop” but rather a full-blown seizure that required a\n\nshowing of full-blown probable cause. See Place, 462 U.S. at 699–700.\n\n Looking first to duration, the government cites United States v. Brignoni-\n\nPonce, 422 U.S. 873, 881 (1975), for the proposition that law enforcement may\n\n“conduct a limited warrantless seizure of a person or item ‘on facts that do not\n\nconstitute probable cause.’” Br. of Appellee at 15. Brignoni-Ponce, however,\n\nconsidered only whether a momentary stop for “a brief question or two” was\n\npermissible on less than probable cause. 422 U.S. at 880; see also Place, 462 U.S.\n\nat 709 (describing Terry and Brignoni Ponce as involving “momentary” stops).\n\nBut that’s a far cry from the two-day pre-warrant seizure at issue here. The\n\ngovernment also points to what it calls the “similar” case of Laist, in which we\n\nheld that a 25-day delay between a seizure and a warrant was permissible. 702\n\nF.3d at 614–15. But Laist isn’t similar at all; the seizure in that case was based on\n\nprobable cause, not mere reasonable suspicion. Id.; see also Burgard, 675 F.3d at\n\n1033 (explaining, in justifying a six-day delay, that a seizure supported by\n\nprobable cause permits a much greater intrusion than a seizure supported by mere\n\nreasonable suspicion).\n\n\n\n\n 15\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 16 of 32\n\n\n What of the more analogous decisions in Place and Puglisi? The\n\ngovernment seeks to distinguish them on the ground that both cases analyzed the\n\nseizure of luggage “as essentially a detention of the person.” Br. of Appellant at 16\n\nn.4. The government asserts that Puglisi, in particular, is inapt because the Court\n\nthere held that “[f]or time even to be relevant, the seizure of luggage must have\n\nactually or constructively seized the person.” 723 F.2d at 788.\n\n Two responses. For starters, we don’t think that this one line, taken alone,\n\nrepresents the holding of Puglisi. See Dantzler v. I.R.S., 183 F.3d 1247, 1251\n\n(11th Cir. 1999) (“A judicial opinion is not a statute, and not every sentence in a\n\njudicial opinion is law.”). Constructive seizure of the person was not the only\n\nelement relevant to whether the luggage detention in Puglisi was permissible based\n\non reasonable suspicion alone. Instead, we analyzed the 140-minute seizure\n\nagainst Place’s considerations of duration, intrusiveness, and diligence before\n\ndeeming the detention unlawful. Puglisi, 723 F.2d at 788, 790–91.\n\n Furthermore—and more importantly—it’s not clear why, under the rationale\n\nof Place and Puglisi, an officer’s confiscation of a cell phone is any less a\n\nconstructive seizure of its owner than his detention of luggage (which, per Place,\n\nwould make even 90 minutes too long). In Place the Court reasoned that while a\n\nsuspect whose luggage is detained is “technically still free to continue his travels,”\n\nthe seizure might nonetheless “effectively restrain” him by disrupting his travel\n\n\n 16\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 17 of 32\n\n\nplans. 462 U.S. at 708. Given the ubiquity of cell phones—and our increasing\n\nreliance on them—it’s no stretch to hazard that a modern-day traveler would likely\n\nrather arrive in a strange place without her luggage than without her phone.\n\nWithout the former, she may be left with only the “clothes on [her] back,” Puglisi,\n\n723 F.2d at 786, but without the latter she may be left without directions, hotel\n\nreservations, and payment and ride-share apps, not to mention voice, text, and\n\nemail communications—in short, isolated and incapacitated. Whatever heft the\n\nconstructive-seizure argument has with respect to luggage applies equally (if not a\n\nfortiori) to cell phones. In any event, no matter what one thinks about the relative\n\nimport of luggage and phones, it’s clear that the duration of the seizure in this case\n\nputs it in a different bucket than the on-the-spot inquiry hypothesized in Place, see\n\n462 U.S. at 705–706, or carried out in Lawing, see 703 F.3d at 238.4\n\n Next, the intrusion into Babcock’s possessory interest in his private property\n\nwas serious. For many of the reasons just explained, a person’s possessory interest\n\nin his cell phone is at least as high as—if not higher than—his interest in his\n\n\n4\n The government suggested for the first time at oral argument that, rather than lasting two days,\nthe reasonable-suspicion-based seizure lasted only until Detective Broughton used the phone to\nprompt C.A.’s confession, at which time the reasonable suspicion became probable cause and,\npresumably, washed away any budding issues with the seizure. We decline to wade into this\nargument when the entire record below is predicated on the seizure lasting two days. Because\nthe government made no argument—and the district court made no finding—concerning the\nlength of time between the seizure and the confession, any determination of the same on our part\nwould be mere speculation. See Byrd v. United States, 138 S. Ct. 1518, 1530 (2018) (declining\nto consider the government’s argument raised for the first time on appeal when argument was\npredicated on factual issue “not addressed” below and “unclear” from the record).\n\n 17\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 18 of 32\n\n\nluggage. A smart phone, as the Supreme Court recently emphasized, is unique in\n\nboth the breadth and depth of personal information it stores, including\n\n“photographs, picture messages, text messages, Internet browsing history, a\n\ncalendar, a thousand-entry phone book”—information that, all told, “reveal[s]\n\nmuch more in combination than any isolated record.” Riley v. California, 573 U.S.\n\n373, 394 (2014). In other words, while a piece of luggage may hold certain\n\nphysical items that an individual needs for a trip, a cell phone holds “[t]he sum of\n\nan individual’s private life”—hence our attentiveness to (which is to say obsession\n\nwith) our cell phones. Id. Put simply, the government’s confiscation of Babcock’s\n\nphone for a period of two days—and with it his personal messages, contacts,\n\ncalendar, and more—worked a serious interference with his possessory interests,\n\nand undermines the government’s current contention that the seizure was but a\n\n“limited intrusion” allowable based on mere reasonable suspicion.\n\n Finally, diligence. Detective Broughton’s actions here—holding onto\n\nBabcock’s phone over the weekend rather than more promptly attempting to secure\n\na warrant, either telephonically or in person—further confirm that the seizure in\n\nthis case looks nothing like a Terry stop. The government has offered no\n\nexplanation as to why Detective Broughton waited more than two days to take any\n\naction regarding the phone, nor does the record evidence indicate that he explained\n\nto Babcock when or whether he could expect to get his phone back. And while a\n\n\n 18\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 19 of 32\n\n\ntwo-day delay certainly wouldn’t cross the line in the probable-cause context, see,\n\ne.g., Laist, 702 F.3d at 614–15 (approving a 25-day delay in obtaining a warrant\n\nfollowing a probable-cause seizure), we know from precedent that it’s well outside\n\nthe realm of a permissible Terry stop, and thus weighs heavily against a finding of\n\ndiligence here, see Place, 462 U.S. at 710; Virden, 488 F.3d at 1321; Farm Labor,\n\n308 F.3d at 546–47.\n\n * * *\n\n Accordingly, we reject the government’s contention that the officers’ two-\n\nday detention of Babcock’s cell phone was a mere investigatory “stop” allowable\n\nbased on reasonable suspicion alone. Rather, we hold that it “ripened” into a full-\n\nblown seizure that required probable cause. See Puglisi, 723 F.2d at 784.\n\n B\n\n The government contends, in the alternative, that it can meet the probable-\n\ncause standard and, further, that it can show that exigent circumstances justified a\n\nwarrantless seizure. We will consider the two components of the government’s\n\nargument in turn, looking first to whether the officers at Babcock’s residence had\n\nprobable cause to believe that his phone contained evidence of a crime, and then to\n\nwhether exigent circumstances excused them from the need to obtain a warrant\n\npre-seizure.\n\n\n\n\n 19\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 20 of 32\n\n\n 1\n\n Probable cause to seize property is what it sounds like—a belief that\n\nevidence will probably be found in a particular location. See United States v.\n\nNoriega, 676 F.3d 1252, 1261 (11th Cir. 2012). As the Supreme Court recently\n\nreiterated, probable cause “is not a high bar.” District of Columbia v. Wesby, 138\n\nS. Ct. 577, 586 (2018) (quoting Kaley v. United States, 571 U.S. 320, 338 (2014)).\n\nAlthough probable cause requires more than reasonable suspicion that criminal\n\nbehavior is afoot, it doesn’t entail the same “standard of conclusiveness and\n\nprobability as the facts necessary to support a conviction.” United States v.\n\nDunn, 345 F.3d 1285, 1290 (11th Cir. 2003) (internal quotations omitted). Rather,\n\nit requires only “a substantial chance” that evidence of criminal activity exists.\n\nIllinois v. Gates, 462 U.S. 213, 243 n.13 (1983). We recently explained that this\n\n“substantial chance” exists “where the facts within the collective knowledge of law\n\nenforcement officials” suffice “to cause a person of reasonable caution to believe\n\nthat a criminal offense has been or is being committed”—and here, that evidence\n\nof that offense will be found in a particular place. Gates v. Khokar, 884 F.3d 1290,\n\n1298 (11th Cir. 2018) (internal quotation marks omitted).\n\n Babcock contends that while the officers in this case might have suspected\n\nthat something was up, their collective knowledge at the time of the seizure didn’t\n\nrise to the level of probable cause that a crime had been committed. To evaluate\n\n\n 20\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 21 of 32\n\n\nthat contention, let’s recap: At the time Detective Broughton retained Babcock’s\n\nphone, the officers knew—\n\n • that a domestic-disturbance call had reported a female at Babcock’s\n residence yelling “Stop, stop, stop!”;\n\n • that after Babcock had denied that anyone else was in his camper, a teenage\n girl emerged with cuts on her legs;\n\n • that Babcock had accompanied the girl to a Halloween party the night\n before, where she had consumed alcohol and drugs, and that she was in his\n camper the next morning;\n\n • that the girl had been in or on Babcock’s bed and left traces of blood there;\n\n • that the girl had been distraught, holding a knife to her own throat and\n saying, “I just want to die”; and\n\n • that shortly after they arrived at Babcock’s residence, the girl appeared to be\n panicking or suffering an overdose.\n\nFinally—and perhaps most tellingly—the officers knew that, while the girl sat on\n\nBabcock’s bed with the knife to her neck, Babcock called her “dumb as f***” and\n\nthen complained—in the present tense—that “this is what I deal with right here . . .\n\nyou gotta do drama and fighting me all over the place.”\n\n Collectively, these circumstances gave the officers probable cause to believe\n\nthat Babcock had committed a crime against C.A. This common-sense conclusion\n\ndoesn’t depend on any particular fact taken in isolation; rather, as is “often” the\n\ncase, “the whole is . . . greater than the sum of its parts.” Wesby, 138 S. Ct. at 588;\n\nsee United States v. Arvizu, 534 U.S. 266, 274 (2002) (rejecting a “divide-and-\n\n 21\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 22 of 32\n\n\nconquer” approach and instructing courts to evaluate probable cause in light of the\n\ntotality of the circumstances). Here, Babcock’s lies contributed to probable cause,\n\nsee Wesby, 138 S. Ct. at 587 (citing Devenpeck v. Alford, 543 U.S. 146, 149, 155–\n\n56 (2004)), as did his own present-tense statements clearly indicating an ongoing\n\nrelationship. When the officers considered Babcock’s own utterances in light of\n\nthe litany of other suspicious facts the learned, they certainly could have suspected\n\na “substantial chance of criminal activity.” Gates, 462 U.S. at 243 n.13.\n\n From there, it required no leap for the officers to deduce that evidence of a\n\ncrime would likely be found on Babcock’s phone. The officers already knew that\n\nthe phone contained one eyebrow-raising video suggesting an ongoing relationship\n\nbetween a grown man and a teenage girl. It was eminently reasonable for them to\n\nbelieve that additional evidence of that relationship—messages, texts, pictures,\n\nvideos, etc.—would be found in the same place.\n\n True, as Babcock points out, the government has been a little wishy-washy\n\nabout the exact crime that the officers suspected at the time of the seizure. The\n\ngovernment doesn’t contend that the officers had probable cause to believe that the\n\nphone contained evidence of child pornography; rather, it concedes that until\n\nDetective Broughton confronted C.A. with the phone at the hospital post-seizure,\n\nhe had “no reason to believe that there were videos of sexual activity between [the]\n\ntwo.” Importantly, though, our precedent doesn’t require officers to predict the\n\n\n 22\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 23 of 32\n\n\neventually-charged offense in order to demonstrate probable cause, only that the\n\ncollective facts would cause a “person of reasonable caution” to believe that “a\n\ncriminal offense has been or is being committed.” See Khokar, 884 F.3d at 1298\n\n(emphasis added) (internal quotation marks omitted).\n\n Here, the government’s arguments at the suppression hearing focused\n\nmainly on preserving both the video of C.A. on the bed and any evidence that\n\nmight have shed light on the events leading up to it. And indeed, that is exactly\n\nwhat the officers ended up finding: evidence of an illegal, coercive relationship,\n\nconfirming the suspicions sparked by the video’s portrayal of Babcock’s\n\ndisdainful, bullying tone and C.A.’s distraught appearance. The fact that the phone\n\nalso (and unexpectedly) contained pornographic images and videos doesn’t\n\ninvalidate probable cause for any number of Florida state crimes the officers\n\nreasonably could have believed occurred based on the scene greeting them at\n\nBabcock’s residence. See, e.g., Fla. Stat. § 794.05(1) (“Unlawful sexual activity\n\nwith certain minors”); id. § 794.011(4)(a) (“Sexual battery”). Accordingly, we\n\nhold that on these facts the officers had probable cause to believe that Babcock was\n\nguilty of a crime, and that evidence of the crime would be found on his phone.\n\n 2\n\n Of course, probable cause isn’t alone enough to seize an individual’s\n\npersonal property—officers typically need a warrant. “[A] warrantless search\n\n\n 23\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 24 of 32\n\n\nand seizure can be justified,” however, “when probable cause has been established\n\nto believe that evidence will be removed or destroyed before a warrant can be\n\nobtained.” United States v. Young, 909 F.2d 442, 446 (11th Cir. 1990). This\n\nexception—one branch of the “exigent-circumstances” doctrine—entails, like\n\nprobable cause itself, an objective inquiry. See United States v. Bradley, 644 F.3d\n\n1213, 1262 (11th Cir. 2011).\n\n Historically, we have found the exigent-circumstances exception\n\n“particularly compelling” in drug cases “because contraband and records can be\n\neasily and quickly destroyed while a search is progressing.” Young, 909 F.2d at\n\n446. The same is true of electronic files. In Bradley, for instance, we found that\n\nthe exigent-circumstances exception permitted officers to shut down a company’s\n\nservers—a seizure of the company’s property—when multiple employees “had the\n\nability and incentive to, after learning of the raid, destroy damning information\n\ncontained on the computer servers.” 644 F.3d at 1262–63.\n\n To be clear, it’s not that a cell phone itself creates an exigent circumstance.\n\n“Taken to its logical conclusion,” that “would permit police officers to seize now-\n\nubiquitous cell phones from any person, in any place, at any time, so long as the\n\nphone contains photographs or videos that could serve as evidence of a crime—\n\nsimply because the ‘nature’ of the device used to capture that evidence might result\n\nin it being lost.” Crocker v. Beatty, 886 F.3d 1132, 1137 (11th Cir. 2018)\n\n\n 24\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 25 of 32\n\n\n(emphasis in original). In Crocker, we held that the exigent-circumstances\n\nexception didn’t apply where an officer had seized a bystander’s phone to prevent\n\ndeletion of photographs that he observed the onlooker snapping following a huge\n\nhighway crash. Id. Absent any reason for the officer to think that the bystander\n\nwouldn’t preserve the pictures or would refuse to turn them over if asked, we\n\nfound the government’s exigent-circumstances argument unconvincing. Id.\n\n This case is different. Given the facts here, a reasonable, experienced agent\n\ncertainly could have believed that Babcock—the suspect, not a mere bystander—\n\nwould delete any incriminating evidence on his phone before a warrant could be\n\nobtained. For starters, Babcock had tried to deceive the responding officers from\n\nthe get-go, denying that anyone else was in his camper, reporting that C.A. had\n\nrandomly shown up at his house in the middle of the night, and claiming that he\n\ndidn’t know her age—all lies. Moreover Babcock surely knew that he was under\n\nsuspicion once Detective Broughton asked to search the camper and to further\n\ninspect his phone. Finally, of course, and on top of all that, the electronic files on\n\nBabcock’s phone could have been “quickly destroyed while [the] search [wa]s\n\nprogressing.” Young, 909 F.2d at 446. All told, as in Bradley, it was reasonable\n\nfor the officers here to conclude that Babcock had the “ability and incentive to,\n\nafter learning” of the investigation into his relationship with C.A., “destroy\n\n\n\n\n 25\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 26 of 32\n\n\ndamning information contained on” his phone. 644 F.3d at 1262–63. That’s all\n\nthe exigent-circumstances doctrine requires. 5\n\n Babcock contends that his offer to e-mail the video to the officers removed\n\nany urgency, thereby undermining any exigent-circumstances argument. He cites\n\nour decision in United States v. Hernandez-Cano, 808 F.2d 779 (11th Cir. 1987),\n\nfor the proposition that officers can’t claim exigent circumstances when the\n\nsupposed risk can be alleviated by alternative means. But Hernandez-Cano was\n\ndifferent—and in fact boomerangs back around on Babcock here. There, we\n\nconsidered a warrantless search of a suspect’s luggage and determined that,\n\nbecause officers had probable cause to arrest him at the time of the search, “any\n\nexigencies inherent in the situation could have been removed” by simply doing so.\n\n5\n Babcock asserts that the government forfeited its exigency argument by failing to use the\nphrase “exigent circumstances”—and failing to fully develop its position regarding the same—in\nits response to the motion to suppress. We disagree. While it’s true that alternative theories of\nadmissibility—including exigent circumstances—can be forfeited even when the government is\nthe appellee or respondent, see Steagald v. United States, 451 U.S. 204, 208 (1981); Giordenello\nv. United States, 357 U.S. 480, 487–88 (1958), we conclude that the government did enough here\nto preserve its exigent-circumstances argument. To be sure, in responding to Babcock’s motion\nto suppress, the government didn’t use the phrase “exigent circumstances” or cite case law\nspecifically in support of the exception. It did argue, though, that “[t]he deputies had probable\ncause to believe that the phone had evidentiary value” and that “detention of the cellular phone\nwas necessary to preserve the evidence observed by the deputies.” Gov’t Resp. Mot. Suppress at\n5 (emphasis added). That—whether accompanied by magic words or not—is the very definition\nof the exigent-circumstances exception. See, e.g., Young, 909 F.2d at 446 (“[W]hen probable\ncause has been established to believe that evidence will be removed or destroyed before a\nwarrant can be obtained, a warrantless search and seizure can be justified.”). That the\ngovernment presented a more robust version of its argument on appeal doesn’t render its initial\nargument null. See, e.g., Sec’y, U.S. Dep’t of Labor v. Preston, 873 F.3d 877, 883 n.5 (11th Cir.\n2017) (explaining that “[o]ffering a new argument or case citation in support of a position\nadvanced in the district court is permissible—and often advisable” lest “the quality and depth of\nargument [fail] to improve on appeal—an unfortunate result”), cert. denied sub nom. Preston v.\nAcosta, 138 S. Ct. 2680 (2018).\n 26\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 27 of 32\n\n\nId. at 782. We explained that “[e]ven if exigent circumstances existed that justified\n\nthe seizure of the suitcase to prevent the loss or destruction of its contents, the\n\ngovernment still had to obtain a warrant to search the suitcase.” Id. (emphasis\n\nadded). Here, the officers didn’t conduct a warrantless search. Instead, faced with\n\nthe potential destruction of evidence, they did exactly what Hernandez-Cano\n\nsuggests they should have done—they seized the phone “to prevent the loss or\n\ndestruction of its contents,” and then obtained a warrant before searching through\n\nit. See id.\n\n Thus, because a reasonable officer could have believed that Babcock would\n\ndelete any incriminating evidence on his phone before a warrant could be\n\nobtained—and because none of Babcock’s arguments convinces us otherwise—we\n\nfind that the exigent-circumstances exception applies in this case.6\n\n * * *\n\n\n6\n The government also argues in the alternative that Babcock consented to the seizure by\nvoluntarily providing his phone to the officers to display the video of C.A. threatening self-harm.\nIt is well-settled, however, that “the scope of a search based on consent may not exceed the\nscope of the given consent.” United States v. Watkins, 760 F.3d 1271, 1279 (11th Cir. 2014)\n(citing Florida v. Jimeno, 500 U.S. 248, 251 (1991)). The standard for measuring the scope of\nconsent is “objective reasonableness”—what “would the typical reasonable person have\nunderstood by the exchange between the officer and the [individual giving the consent]?” Id.\n(internal quotation marks omitted). Here, Babcock clearly consented only to the officers’\nviewing the video he showed them. After the initial viewing, Deputy Olson asked for the phone\nagain, for the express purpose of showing Officer McMahan the video. Babcock consented to\nthe officers viewing the clip again, but then asked for his phone back and refused consent when\nDetective Broughton asked to poke around further. Contrary to the government’s contention, the\ninitial limited-in-scope consent doesn’t justify an unlimited-in-scope full seizure over Babcock’s\nobjection.\n\n 27\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 28 of 32\n\n\n To sum up, we reject the government’s contention that a two-day\n\nwarrantless seizure of a suspect’s cell phone is permissible based on reasonable\n\nsuspicion alone. We conclude, however, that the warrantless seizure of Babcock’s\n\nphone was lawful because the officers on the scene had probable cause to believe\n\nboth that evidence of a crime would be found on it and that the evidence would be\n\ndestroyed before they could obtain a warrant.\n\n III\n\n Babcock separately challenges his sentence, arguing that it is both (1)\n\nprocedurally unreasonable because the district court erroneously imposed two\n\nenhancements for the same harm and (2) substantively unreasonable because it is\n\ntoo harsh in light of the facts.7 Neither argument is persuasive.\n\n Babcock raises his procedural-reasonableness argument for the first time on\n\nappeal, so we can correct any missteps only if he shows a “plain error” that affects\n\nhis substantial rights and that seriously undermines the fairness, integrity, or public\n\nreputation of judicial proceedings. See United States v. Shelton, 400 F.3d 1325,\n\n1328–29 (11th Cir. 2005). Babcock essentially argues that the district court’s\n\napplication of both § 2G2.1(b)(2) and § 4B1.5(b) of the Sentencing Guidelines\n\nconstitutes impermissible double-counting.\n\n7\n Babcock also argues that his sentence is procedurally unreasonable because the government did\nnot group two counts of conviction which were based on the same harm. As the government\npoints out, though, the Guidelines specifically exclude convictions under § 2G2.1 from the\ngrouping rules. See U.S.S.G. § 3D1.2(d).\n\n 28\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 29 of 32\n\n\n Double-counting occurs when one part of the Sentencing Guidelines is\n\napplied to increase a defendant’s punishment on account of a harm that has already\n\nbeen fully accounted for by application of another part of the Guidelines. See\n\nUnited States v. Dudley, 463 F.3d 1221, 1226–27 (11th Cir. 2006). Absent\n\nevidence to the contrary, however, the presumption is that “the Sentencing\n\nCommission intended to apply separate sections cumulatively,” United States v.\n\nKapordelis, 569 F.3d 1291, 1315 (11th Cir. 2009) (citation omitted), such that\n\nwhat might appear to be impermissible double-counting is instead what we will\n\ncall permissible “cumulative-counting.”\n\n We conclude that applying both enhancements in this case constitutes\n\ncumulative- (rather than double-) counting. Chapter Two of the Guidelines,\n\nfocusing on the sexual exploitation of minors through pictures, provides that an\n\noffender’s base sentencing level should be enhanced by two when “the commission\n\nof a sexual act or sexual contact” occurs during a visual depiction. U.S.S.G.\n\n§ 2G2.1(b)(2)(A). Chapter Four then makes clear that when a “pattern of . . .\n\nprohibited sexual contact” occurs, a court should add five to “the offense level\n\ndetermined under Chapter[] Two.” U.S.S.G. § 4B1.5(b). The Guidelines say\n\nnothing about adding this enhancement to only a portion of the base level\n\ndetermined under Chapter Two, or otherwise adjusting the calculation in any\n\nway—instead, they simply presuppose that a certain offense level was determined\n\n\n 29\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 30 of 32\n\n\nunder Chapter Two, and then instruct the sentencing court to add five levels,\n\nperiod. Nothing in the Guidelines, then, indicates that these sections may not be\n\napplied cumulatively. See Kapordelis, 569 F.3d at 1315. Moreover, and in any\n\nevent, it isn’t clear that the harm in § 4B1.5(b)’s “pattern of activity involving\n\nprohibited sexual contact” is “fully accounted for” in § 2G2.1(b)(2)’s “sexual act\n\nor sexual contact” occurring in a visual depiction, such that application of the two\n\nsections could be considered double-counting at all. See Dudley, 463 F.3d at\n\n1226–27. There was no plain error here.\n\n Looking next to substantive reasonableness, Babcock argues that the nature\n\nand circumstances of this case do not compel the same severe sentence required to\n\ndeter creators of commercial child pornography. Basically, Babcock contends that\n\nhis crime—an inappropriate, long-term relationship with an older teenager—\n\ndoesn’t indicate that he is a threat to children generally or affect the child-\n\npornography market as would, for instance, the rape of a child for video\n\ndistribution or other predatory production of commercial child pornography.\n\nBabcock asserts that because there is no evidence that he intended ever to show\n\nanyone his videos or pictures of C.A., his 324-month sentence is substantively\n\nunreasonable.\n\n We review challenges to the substantive reasonableness of a sentence for\n\nabuse of discretion. Gall v. United States, 552 U.S. 38, 41 (2007). The party\n\n\n 30\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 31 of 32\n\n\nchallenging the sentence bears the burden of showing that the sentence is\n\nunreasonable in light of the record and the 18 U.S.C. § 3553(a) factors. United\n\nStates v. Tome, 611 F.3d 1371, 1378 (11th Cir. 2010). While we do not formally\n\npresume that a within-Guidelines sentence is reasonable, we ordinarily expect it to\n\nbe so. United States v. Hunt, 526 F.3d 739, 746 (11th Cir. 2008). That a sentence\n\nis imposed well below the statutory maximum penalty may also indicate its\n\nreasonableness. See United States v. Gonzalez, 550 F.3d 1319, 1324 (11th Cir.\n\n2008) (per curiam).\n\n There is a certain intuitive logic to Babcock’s argument here—it’s true that\n\nnothing in the record necessarily indicates a propensity to distribute child\n\npornography. That being said, Babcock’s conduct falls squarely within the\n\nconfines of § 2G2.1—“sexually exploiting a minor by production of sexually\n\nexplicit visual or printed material”—and, as the sentencing judge emphasized, the\n\neffect of his actions on C.A. and her family was far from insignificant. We are\n\ncomfortable that the sentencing judge took into consideration all of the relevant\n\ncircumstances when he sentenced Babcock to 324 months—a downward variance\n\nfrom the 360 to 720 months recommended by the Guidelines. See Gonzalez, 550\n\nF.3d at 1324. Accordingly, we find no abuse of discretion in the district court’s\n\nsentencing decision.\n\n\n\n\n 31\n\f Case: 17-13678 Date Filed: 05/24/2019 Page: 32 of 32\n\n\n IV\n\n For the foregoing reasons, we hold (1) that reasonable suspicion alone could\n\nnot have justified the officers’ warrantless two-day seizure of Babcock’s cell\n\nphone; (2) that the officers in this case had probable cause to believe that a crime\n\nhad been committed, that evidence of the crime would be found on Babcock’s\n\nphone, and that there was a risk that Babcock would destroy the evidence before\n\nthey could get a warrant, such that the seizure did not violate the Fourth\n\nAmendment; and (3) that Babcock’s sentence was both procedurally and\n\nsubstantively reasonable. Accordingly, we affirm the district court’s denial of\n\nBabcock’s motion to suppress as well as its 324-month sentence.\n\n AFFIRMED.\n\n\n\n\n 32\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: United States v. Darrell Mark Babcock\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-24\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-13678 Date Filed: 05/24/2019 Page: 1 of 32\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-13678\\n ________________________\\n\\n D.C. Docket No. 2:16-cr-14071-KAM-1\\n\\n\\n\\nUNITED STATES OF AMERICA,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nDARRELL MARK BABCOCK,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 24, 2019)\\n\\nBefore WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District\\nJudge.\\n\\n\\n\\n\\n*\\n The Honorable Kathryn H. Vratil, United States District Court Judge for the District of Kansas,\\nsitting by designation.\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 2 of 32\\n\\n\\nNEWSOM, Circuit Judge:\\n\\n In this case, police officers investigating a domestic disturbance confiscated\\n\\na suspect’s cell phone and held it for two days before eventually obtaining a\\n\\nwarrant to search it. The appeal before us presents two Fourth Amendment\\n\\nquestions. First, was the seizure justified on the ground that the officers had\\n\\nreasonable suspicion to believe that the phone’s owner was engaged in criminal\\n\\nwrongdoing—was it, in effect, a permissible “Terry stop” of the phone? We hold\\n\\nthat it was not. Second, in the particular circumstances of this case, did the officers\\n\\nhave probable cause to believe not only that the phone’s owner had committed a\\n\\ncrime and that the phone contained evidence of that crime, but also that the suspect\\n\\nwould likely destroy that evidence before they could procure a warrant? We hold\\n\\nthat they did. Accordingly, and on that ground, we affirm the district court’s order\\n\\ndenying the motion to suppress. We separately affirm the district court’s sentence.\\n\\n I\\n\\n A\\n\\n Early one Friday morning, Deputy Andrea Olson of the Stuart, Florida\\n\\nPolice Department responded to a domestic-disturbance call reporting a ruckus\\n\\ncoming from a camper parked at Darrell Babcock’s residence—specifically, a\\n\\nfemale had been heard yelling, “Stop, stop, stop!” When Deputy Olson knocked\\n\\non the door of Babcock’s camper, Babcock exited, closed the door behind him, and\\n\\n\\n 2\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 3 of 32\\n\\n\\nvolunteered that no one else was inside. Almost immediately, though, Deputy\\n\\nOlson heard a female announce that she was coming out. A teenage girl emerged\\n\\nfrom the trailer; she was wearing only yoga shorts and a camo jacket, and she had\\n\\nblood on her left thigh. Seemingly by way of explanation, Babcock handed\\n\\nDeputy Olson his cell phone to show her a video of the girl—we’ll call her C.A.—\\n\\nsitting on a bed, holding a knife to her own throat and saying that she wanted to\\n\\ndie. In the video Babcock could be heard berating the girl, telling her, “you’re\\n\\ndumb as f***” and complaining, “this is what I deal with right here . . . you gotta\\n\\ndo drama and fighting me all over the place.” After viewing the clip, Deputy\\n\\nOlson returned Babcock’s phone. When backup arrived on the scene, Deputy\\n\\nOlson asked for the phone again so that she could show the video to her colleague,\\n\\nOfficer Michael McMahan.\\n\\n The officers then interviewed Babcock and C.A. separately. Babcock denied\\n\\nknowing C.A.’s age and also disputed that the two were in a relationship, although\\n\\nhe admitted that he had known C.A. for three years and that she used to be his\\n\\nneighbor. He also said that C.A. had shown up at his camper unannounced,\\n\\nsometime during the middle of the night. C.A., by contrast—whose license\\n\\nshowed that she was only 16 years old—stated that she and Babcock had gone\\n\\ntogether the night before to a Halloween party, where she had consumed alcohol,\\n\\ncocaine, and other substances. After answering a few questions, C.A. began either\\n\\n\\n 3\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 4 of 32\\n\\n\\npanicking or experiencing the effects of an overdose, so the officers called an\\n\\nambulance. Deputy Olson rode with C.A. to the hospital.\\n\\n Meanwhile, another officer, Detective Brian Broughton, remained behind to\\n\\ncontinue questioning Babcock. Detective Broughton sought and received\\n\\npermission to search Babcock’s camper, where he discovered blood on the\\n\\nbedsheets and prescription pills scattered about. When Detective Broughton asked\\n\\nto further inspect Babcock’s phone, Babcock refused and asked to have it back.\\n\\nBabcock offered to e-mail the video clip of C.A. with the knife, but Detective\\n\\nBroughton decided to keep the phone instead. He told Officer McMahan to enter it\\n\\ninto evidence and then took it with him to the hospital to talk to C.A.\\n\\n At the hospital, C.A. again insisted that she and Babcock were just friends,\\n\\nthat they had gone to a Halloween party, and that the two had then argued. She\\n\\nfirmly denied any further relationship. But when Detective Broughton informed\\n\\nC.A. that he had Babcock’s phone, she abruptly reversed course and admitted that\\n\\nthe two had been in a relationship and, further, that the officers would find sexually\\n\\nexplicit images of her on the phone. Two days later, Detective Broughton applied\\n\\nfor and obtained a warrant to search the phone, where he found nude images of\\n\\nC.A. and explicit video recordings of Babcock and C.A. together.\\n\\n\\n\\n\\n 4\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 5 of 32\\n\\n\\n B\\n\\n Babcock was charged with two counts of producing a visual depiction of\\n\\nsexually explicit conduct with a minor in violation of 18 U.S.C. § 2251(a), (e). He\\n\\nfiled a motion to suppress, arguing that officers had seized his phone without a\\n\\nwarrant or probable cause. The government filed a response, arguing primarily\\n\\nthat the cell-phone seizure was reasonable because “under the totality of the\\n\\ncircumstances” the officers had “reasonable suspicion to investigate further,” and\\n\\nadding that, at any rate, the officers had probable cause to believe that the phone\\n\\ncontained evidence of a crime. The government further contended that “detention\\n\\nof the cell phone was necessary to preserve the evidence observed by the\\n\\ndeputies.” Finally, the government asserted that, even in the absence of a warrant,\\n\\neither Babcock’s consent or the inevitability that the images would have been\\n\\ndiscovered rendered the seizure constitutional.\\n\\n A magistrate judge recommended that Babcock’s motion be denied. He\\n\\nconcluded—referencing two distinct Fourth Amendment standards—that “the\\n\\ncollective knowledge and information received by the officers at the scene\\n\\nconstituted sufficient probable cause and reasonable suspicion that there may have\\n\\nbeen a crime committed which may have been preserved on the cell phone.” The\\n\\ndistrict court agreed, noting—also somewhat vaguely—that the surrounding\\n\\ncircumstances were “sufficient for law enforcement to suspect inappropriate\\n\\n\\n 5\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 6 of 32\\n\\n\\nconduct between [Babcock] and C.A.” Later, at sentencing, the district judge\\n\\nfurther remarked that although he “didn’t say [it] in the order,” he was “putting [it]\\n\\non the record for appellate purposes” that in the video C.A. “appear[ed] to be either\\n\\nwith no pants on or underwear” and that, based on “what she says and how she\\n\\nsays it about what she wants to do to herself,” it was “obvious . . . that there was an\\n\\ninappropriate relationship going on which would have given [the officers]\\n\\nreasonable probable cause to believe that there was inappropriate sexual activity\\n\\nbetween” Babcock and C.A. Babcock took a plea, reserving his right to appeal the\\n\\ndenial of his motion to suppress.\\n\\n At sentencing, Babcock asked for the mandatory minimum of 180 months,\\n\\narguing that his conduct, while inappropriate, was outside the core child-\\n\\npornography-distribution behavior that Congress sought to deter under § 2251(a)\\n\\nand (e). The government in turn asked for a sentence within the 360-to-720-month\\n\\nrecommended Guidelines range, stressing the harm to C.A. and her family. The\\n\\ncourt imposed a below-Guidelines sentence of 324 months. Babcock appealed\\n\\nboth the denial of his motion to suppress and his sentence.\\n\\n II\\n\\n We’ll tackle the Fourth Amendment issues first. A person suffers a\\n\\n“seizure” of his property within the meaning of the Fourth Amendment when there\\n\\nis a “meaningful interference” with his possessory interest in it. United States v.\\n\\n\\n 6\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 7 of 32\\n\\n\\nVirden, 488 F.3d 1317, 1321 (11th Cir. 2007).1 While the seizure of private\\n\\nproperty generally requires a warrant, the Supreme Court has interpreted the\\n\\nFourth Amendment to allow a warrantless seizure when police can show both (1)\\n\\nprobable cause to believe that property contains contraband or evidence of a crime\\n\\nand (2) an applicable warrant exception, such as exigent circumstances. See, e.g.,\\n\\nKentucky v. King, 563 U.S. 452, 459–60 (2011) (citations omitted). Accordingly,\\n\\nabsent either a warrant or probable cause plus an exception, police may not seize\\n\\nprivate property. There is, however, an asterisk. Under a line of luggage-related\\n\\ncases from the 1980s, police may “briefly detain” property—Terry-stop style—on\\n\\nthe strength of reasonable suspicion alone. See United States v. Place, 462 U.S.\\n\\n696, 697–98 (1983); United States v. Puglisi, 723 F.2d 779, 788–89 (11th Cir.\\n\\n1984).\\n\\n Here, the government principally argues that these cases permitted the\\n\\nofficers to detain Babcock’s phone based on their reasonable suspicion that he had\\n\\ncommitted a crime. Alternatively, the government contends that the officers had\\n\\nprobable cause to believe that the phone contained evidence of a crime and that\\n\\nexigent circumstances—namely, the need to prevent the destruction of that\\n\\nevidence—allowed them to seize the phone. We consider each argument in turn.\\n1\\n When reviewing the denial of a motion to suppress, we review factual findings for clear error\\nand legal determinations de novo. United States v. Gibson, 708 F.3d 1256, 1274 (11th Cir.\\n2013). We also review the evidence in the light most favorable to the government, as the\\nprevailing party. See United States v. Capers, 708 F.3d 1286, 1295–96 (11th Cir. 2013).\\n\\n 7\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 8 of 32\\n\\n\\n A\\n\\n 1\\n\\n Reasonable suspicion is “a particularized and objective basis” for suspecting\\n\\na person of criminal activity. Ornelas v. United States, 517 U.S. 690, 696 (1996)\\n\\n(quotation marks omitted). It requires “specific, articulable, and objective facts\\n\\nreasonably to suspect” that a crime is being or will soon be committed, Puglisi,\\n\\n723 F.2d at 789, but “is a less demanding standard than probable cause,” Illinois v.\\n\\nWardlow, 528 U.S. 119, 123 (2000). In Terry v. Ohio, the Supreme Court\\n\\nfamously held that, even absent probable cause, police officers may briefly detain\\n\\nan individual based on reasonable suspicion that he is (or is about to be) engaged in\\n\\ncriminal activity. See 392 U.S. 1, 30–31 (1968).\\n\\n The Supreme Court first extended Terry’s rationale from people to property\\n\\nin United States v. Place, 462 U.S. 696 (1983). There, the Court held that while a\\n\\nbrief investigatory detention of property could be justified on the basis of\\n\\nreasonable suspicion alone, an officer’s 90-minute seizure of an airline traveler’s\\n\\nsuitcase exceeded constitutional boundaries. Id. at 702. In so holding, the Court\\n\\nrecognized that “[t]he intrusion on possessory interests occasioned by a seizure of\\n\\none’s personal effects can vary both in its nature and extent.” Id. at 705. While\\n\\nsome “brief detentions of personal effects”—such as, the Court hypothesized, “on-\\n\\nthe-spot” dog sniffs—may be “so minimally intrusive” as to “justify a seizure\\n\\n\\n 8\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 9 of 32\\n\\n\\nbased only on specific articulable facts that the property contains contraband,” the\\n\\nluggage seizure didn’t fit the bill. Id. at 705–06. By way of explanation, the Court\\n\\nemphasized several factors: the duration of the detention, the degree of the\\n\\nintrusion on the owner’s possessory interests in his property, and the officer’s lack\\n\\nof diligence in timely pursuing their investigation. Id. at 709–10. The Court also\\n\\nhighlighted that a confiscation of luggage, in particular, interferes not only with\\n\\npossessory interests but also with liberty interests because, while a suspect whose\\n\\nluggage is stopped is “technically still free to continue” on his way, the detention\\n\\nmight “effectively restrain” him by disrupting his travel plans. Id. at 708–09.\\n\\n Shortly after the Supreme Court decided Place, this Court had occasion to\\n\\napply it on similar facts. In United States v. Puglisi, an officer made what began as\\n\\na brief stop by ordering a suspicious traveler’s bags removed from a luggage cart;\\n\\nhe then stowed the luggage in his office until a drug-sniffing dog became available.\\n\\n723 F.2d 779, 790 (11th Cir. 1984). Meanwhile, the traveler boarded his flight\\n\\nwithout his bags. Although we deemed the initial seizure permissible under Terry,\\n\\nwe found that the length and intrusiveness—140 minutes—caused the “brief stop”\\n\\nto “ripen” into a full-blown seizure that could be justified only by probable cause.\\n\\nId. at 784. We explained that “Place requires the same test as Terry: a court must\\n\\nweigh the intrusiveness of a limited seizure of the individual against society’s\\n\\ninterest in detection and prevention of crime.” Id. at 785. We cautioned, however,\\n\\n\\n 9\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 10 of 32\\n\\n\\nthat because the Fourth Amendment “protects people, not things,” the focus was\\n\\nthe effective “seizure of persons, through their luggage.” Id. at 787–88.\\n\\n Although Place and Puglisi concerned luggage, both this Court and others\\n\\nhave since indicated that any detention of property based on reasonable suspicion\\n\\nmust be fairly analogous to a Terry stop, regardless of the item at issue.\\n\\nAccordingly, we have said, “the factors used to determine whether a Terry stop has\\n\\nmatured into an arrest are also useful in evaluating whether a seizure of property\\n\\nrequired probable cause” rather than mere reasonable suspicion. Virden, 488 F.3d\\n\\nat 1321. Echoing Place, we have said that these factors include, but are not limited\\n\\nto, (1) the detention’s duration, (2) its intrusiveness, (3) the diligence with which\\n\\nofficers pursued their investigation, and (4) the law-enforcement purposes served\\n\\nby the detention. See id.; accord United States v. Gonzalez, 781 F.3d 422, 428–29\\n\\n(8th Cir. 2015); Farm Labor Org. Comm. v. Ohio State Highway Patrol, 308 F.3d\\n\\n523, 544–45 (6th Cir. 2002); United States v. $557,933.89, More or Less, in U.S.\\n\\nFunds, 287 F.3d 66, 86 (2d Cir. 2002). We’ll explain each in a bit more detail here\\n\\nbefore applying them to the facts of this case\\n\\n First, duration. Although the Supreme Court has “decline[d] to adopt any\\n\\noutside time limit for a permissible Terry stop,” the Court in Place observed that it\\n\\nhad “never approved a seizure of the person for the prolonged 90-minute period\\n\\ninvolved” in that case and that, on the facts presented there, it wouldn’t approve a\\n\\n\\n 10\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 11 of 32\\n\\n\\n90-minute detention of property, either. 462 U.S. at 709–10. In Virden, this Court\\n\\nsimilarly determined that an officer’s transfer of a defendant and his car to another\\n\\nlocation for a dog sniff, “[w]hile not unduly lengthy” at about 30 minutes, was\\n\\nnonetheless “unreasonable absent probable cause.” 488 F.3d at 1321. 2\\n\\n At the other end of the spectrum, the Fourth Circuit has approved a seconds-\\n\\nlong cell-phone stop on the basis of reasonable suspicion alone. In United States v.\\n\\nLawing, that court held that an officer’s brief detention of a suspect’s phone during\\n\\na traffic stop—for just long enough to see if it would ring when the officer dialed a\\n\\nknown drug-distributor’s number—was sufficiently minimal to qualify for\\n\\nTerry/Place treatment. 703 F.3d 229, 238 (4th Cir. 2012). Similarly, the Second\\n\\nCircuit held that reasonable suspicion justified a brief investigatory detention that\\n\\noccurred when a detective took between two and 20 minutes to respond to a\\n\\nrequest for a luggage investigation while a traveler waited at an airport security\\n\\ncheckpoint with his luggage. See $557,933.89, More or Less, 287 F.3d at 71, 86–\\n\\n87 & n.16.\\n\\n Second, intrusiveness. The “intrusiveness” factor concerns the degree to\\n\\nwhich a property detention interferes with a person’s possessory interest in his\\n\\nbelongings. In Place, for instance, the Court emphasized that although “the\\n\\n2\\n Even though the detention there more directly implicated the owner’s liberty interests than in\\nPlace because the owner remained in his car while it was transported to another location, we\\nanalyzed the stop primarily as one of property rather than of an individual. See Virden, 488 F.3d\\nat 1321.\\n 11\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 12 of 32\\n\\n\\nparticular course of investigation that the agents intended to pursue”—just a brief\\n\\n“exposure of respondent’s luggage, which was located in a public place, to a\\n\\ntrained canine”—would have been permissible based on mere reasonable\\n\\nsuspicion, the 90-minute seizure that they actually effected was not. 462 U.S. at\\n\\n707, 709–10 (emphasis added). The Court explained that the planned sniff would\\n\\nhave revealed “only the presence or absence of narcotics, a contraband item,” and\\n\\nwouldn’t have exposed the traveler’s personal “noncontraband items that otherwise\\n\\nwould remain hidden from public view, as [would], for example, an officer’s\\n\\nrummaging through the contents of the luggage.” Id. at 707.\\n\\n This Court has likewise recognized that individuals have strong interests in\\n\\ncontainers that hold personal effects or private information, such as luggage and\\n\\ncomputers. In Puglisi, we emphasized that “privacy and possessory interests in\\n\\nluggage are often high” because a traveler may have “his most important and\\n\\nprivate possessions in his suitcase” and likely wants “to shield them from the\\n\\nprying eyes of strangers, especially the government.” 723 F.2d at 786. And in\\n\\nUnited States v. Laist, we acknowledged that “computers are a unique possession,\\n\\none in which individuals may have a particularly powerful possessory interest,”\\n\\nbecause they store “personal letters, e-mails, financial information, passwords,\\n\\nfamily photos, and countless other items of a personal nature.” 702 F.3d 608, 614\\n\\n(11th Cir. 2012); see also United States v. Mitchell, 565 F.3d 1347, 1352 (11th Cir.\\n\\n\\n 12\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 13 of 32\\n\\n\\n2009) (calling a computer hard drive “the digital equivalent of its owner’s home,\\n\\ncapable of holding a universe of private information”) (internal quotation marks\\n\\nomitted).\\n\\n Third, diligence. When police diligently pursue their investigation, a\\n\\nreviewing court can have greater confidence that the governmental interest is\\n\\nlegitimate and that the intrusion occasioned by the challenged detention was no\\n\\ngreater than reasonably necessary. See United States v. Burgard, 675 F.3d 1029,\\n\\n1033 (7th Cir. 2012). “Diligence” in this context includes not only seeking a\\n\\nwarrant application promptly, but also communicating with the suspect concerning\\n\\nthe specifics of the detention. In Place, for instance, the Court faulted officers for\\n\\nfailing to inform the suspect where and for how long they were taking his bags,\\n\\nand when and how he could get them back. See 462 U.S. at 710. So too, in Farm\\n\\nLabor, the Sixth Circuit observed—in the course of holding that the seizure of two\\n\\nsuspects’ green cards couldn’t be justified based on reasonable suspicion alone—\\n\\nthat an officer had failed to act diligently when he “wait[ed] for four days to return\\n\\n[their] green cards” and that “[t]he unreasonable nature of the seizure was\\n\\nexacerbated by the undisputed fact that [the officer] did not make clear . . . how\\n\\n\\n\\n\\n 13\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 14 of 32\\n\\n\\nlong the documents would be held or when or how he would return them.” 308\\n\\nF.3d at 546–47 (internal quotation marks omitted).3\\n\\n Finally, governmental interest. The final factor looks at the other side of the\\n\\nledger. As the Court explained in Place, “[t]he exception to the probable-cause\\n\\nrequirement for limited seizures of the person recognized in Terry and its progeny\\n\\nrests on a balancing of the competing interests to determine the reasonableness of\\n\\nthe type of seizure.” 462 U.S. at 703. Thus, “[w]e must balance the nature and\\n\\nquality of the intrusion on the individual’s Fourth Amendment interests against the\\n\\nimportance of the governmental interests alleged to justify the intrusion.” Id.\\n\\nIn Place, that meant taking account of the public’s compelling interest in\\n\\n“detecting those who would traffic in deadly drugs for personal profit.” Id.\\n\\n(internal quotation marks omitted).\\n\\n 2\\n\\n How, then, do these considerations stack up in this case? In short, not well\\n\\nfor the government. To begin at the end, we don’t doubt for a moment the\\n\\ngovernment’s “compelling” interest in preventing the creation and distribution of\\n\\nchild pornography. E.g., New York v. Ferber, 458 U.S. 747, 761 (1982). Standing\\n\\nalone, though, that interest can’t counterbalance the duration, intrusion, and\\n3\\n The diligence component of the analysis necessarily intersects with the duration component\\nbecause, “[i]n the ordinary case, the sooner the warrant issues, the sooner the property\\nowner’s possessory rights can be restored if the search reveals nothing incriminating”—and, of\\ncourse, the sooner an officer seeks a warrant, the sooner a warrant can issue. See Mitchell, 565\\nF.3d at 1352 (citation omitted).\\n 14\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 15 of 32\\n\\n\\ndiligence factors, all of which—for reasons we will explain—weigh heavily here in\\n\\nfavor of a determination that the officers’ two-day seizure of Babcock’s phone was\\n\\nnot just a brief “investigatory stop” but rather a full-blown seizure that required a\\n\\nshowing of full-blown probable cause. See Place, 462 U.S. at 699–700.\\n\\n Looking first to duration, the government cites United States v. Brignoni-\\n\\nPonce, 422 U.S. 873, 881 (1975), for the proposition that law enforcement may\\n\\n“conduct a limited warrantless seizure of a person or item ‘on facts that do not\\n\\nconstitute probable cause.’” Br. of Appellee at 15. Brignoni-Ponce, however,\\n\\nconsidered only whether a momentary stop for “a brief question or two” was\\n\\npermissible on less than probable cause. 422 U.S. at 880; see also Place, 462 U.S.\\n\\nat 709 (describing Terry and Brignoni Ponce as involving “momentary” stops).\\n\\nBut that’s a far cry from the two-day pre-warrant seizure at issue here. The\\n\\ngovernment also points to what it calls the “similar” case of Laist, in which we\\n\\nheld that a 25-day delay between a seizure and a warrant was permissible. 702\\n\\nF.3d at 614–15. But Laist isn’t similar at all; the seizure in that case was based on\\n\\nprobable cause, not mere reasonable suspicion. Id.; see also Burgard, 675 F.3d at\\n\\n1033 (explaining, in justifying a six-day delay, that a seizure supported by\\n\\nprobable cause permits a much greater intrusion than a seizure supported by mere\\n\\nreasonable suspicion).\\n\\n\\n\\n\\n 15\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 16 of 32\\n\\n\\n What of the more analogous decisions in Place and Puglisi? The\\n\\ngovernment seeks to distinguish them on the ground that both cases analyzed the\\n\\nseizure of luggage “as essentially a detention of the person.” Br. of Appellant at 16\\n\\nn.4. The government asserts that Puglisi, in particular, is inapt because the Court\\n\\nthere held that “[f]or time even to be relevant, the seizure of luggage must have\\n\\nactually or constructively seized the person.” 723 F.2d at 788.\\n\\n Two responses. For starters, we don’t think that this one line, taken alone,\\n\\nrepresents the holding of Puglisi. See Dantzler v. I.R.S., 183 F.3d 1247, 1251\\n\\n(11th Cir. 1999) (“A judicial opinion is not a statute, and not every sentence in a\\n\\njudicial opinion is law.”). Constructive seizure of the person was not the only\\n\\nelement relevant to whether the luggage detention in Puglisi was permissible based\\n\\non reasonable suspicion alone. Instead, we analyzed the 140-minute seizure\\n\\nagainst Place’s considerations of duration, intrusiveness, and diligence before\\n\\ndeeming the detention unlawful. Puglisi, 723 F.2d at 788, 790–91.\\n\\n Furthermore—and more importantly—it’s not clear why, under the rationale\\n\\nof Place and Puglisi, an officer’s confiscation of a cell phone is any less a\\n\\nconstructive seizure of its owner than his detention of luggage (which, per Place,\\n\\nwould make even 90 minutes too long). In Place the Court reasoned that while a\\n\\nsuspect whose luggage is detained is “technically still free to continue his travels,”\\n\\nthe seizure might nonetheless “effectively restrain” him by disrupting his travel\\n\\n\\n 16\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 17 of 32\\n\\n\\nplans. 462 U.S. at 708. Given the ubiquity of cell phones—and our increasing\\n\\nreliance on them—it’s no stretch to hazard that a modern-day traveler would likely\\n\\nrather arrive in a strange place without her luggage than without her phone.\\n\\nWithout the former, she may be left with only the “clothes on [her] back,” Puglisi,\\n\\n723 F.2d at 786, but without the latter she may be left without directions, hotel\\n\\nreservations, and payment and ride-share apps, not to mention voice, text, and\\n\\nemail communications—in short, isolated and incapacitated. Whatever heft the\\n\\nconstructive-seizure argument has with respect to luggage applies equally (if not a\\n\\nfortiori) to cell phones. In any event, no matter what one thinks about the relative\\n\\nimport of luggage and phones, it’s clear that the duration of the seizure in this case\\n\\nputs it in a different bucket than the on-the-spot inquiry hypothesized in Place, see\\n\\n462 U.S. at 705–706, or carried out in Lawing, see 703 F.3d at 238.4\\n\\n Next, the intrusion into Babcock’s possessory interest in his private property\\n\\nwas serious. For many of the reasons just explained, a person’s possessory interest\\n\\nin his cell phone is at least as high as—if not higher than—his interest in his\\n\\n\\n4\\n The government suggested for the first time at oral argument that, rather than lasting two days,\\nthe reasonable-suspicion-based seizure lasted only until Detective Broughton used the phone to\\nprompt C.A.’s confession, at which time the reasonable suspicion became probable cause and,\\npresumably, washed away any budding issues with the seizure. We decline to wade into this\\nargument when the entire record below is predicated on the seizure lasting two days. Because\\nthe government made no argument—and the district court made no finding—concerning the\\nlength of time between the seizure and the confession, any determination of the same on our part\\nwould be mere speculation. See Byrd v. United States, 138 S. Ct. 1518, 1530 (2018) (declining\\nto consider the government’s argument raised for the first time on appeal when argument was\\npredicated on factual issue “not addressed” below and “unclear” from the record).\\n\\n 17\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 18 of 32\\n\\n\\nluggage. A smart phone, as the Supreme Court recently emphasized, is unique in\\n\\nboth the breadth and depth of personal information it stores, including\\n\\n“photographs, picture messages, text messages, Internet browsing history, a\\n\\ncalendar, a thousand-entry phone book”—information that, all told, “reveal[s]\\n\\nmuch more in combination than any isolated record.” Riley v. California, 573 U.S.\\n\\n373, 394 (2014). In other words, while a piece of luggage may hold certain\\n\\nphysical items that an individual needs for a trip, a cell phone holds “[t]he sum of\\n\\nan individual’s private life”—hence our attentiveness to (which is to say obsession\\n\\nwith) our cell phones. Id. Put simply, the government’s confiscation of Babcock’s\\n\\nphone for a period of two days—and with it his personal messages, contacts,\\n\\ncalendar, and more—worked a serious interference with his possessory interests,\\n\\nand undermines the government’s current contention that the seizure was but a\\n\\n“limited intrusion” allowable based on mere reasonable suspicion.\\n\\n Finally, diligence. Detective Broughton’s actions here—holding onto\\n\\nBabcock’s phone over the weekend rather than more promptly attempting to secure\\n\\na warrant, either telephonically or in person—further confirm that the seizure in\\n\\nthis case looks nothing like a Terry stop. The government has offered no\\n\\nexplanation as to why Detective Broughton waited more than two days to take any\\n\\naction regarding the phone, nor does the record evidence indicate that he explained\\n\\nto Babcock when or whether he could expect to get his phone back. And while a\\n\\n\\n 18\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 19 of 32\\n\\n\\ntwo-day delay certainly wouldn’t cross the line in the probable-cause context, see,\\n\\ne.g., Laist, 702 F.3d at 614–15 (approving a 25-day delay in obtaining a warrant\\n\\nfollowing a probable-cause seizure), we know from precedent that it’s well outside\\n\\nthe realm of a permissible Terry stop, and thus weighs heavily against a finding of\\n\\ndiligence here, see Place, 462 U.S. at 710; Virden, 488 F.3d at 1321; Farm Labor,\\n\\n308 F.3d at 546–47.\\n\\n * * *\\n\\n Accordingly, we reject the government’s contention that the officers’ two-\\n\\nday detention of Babcock’s cell phone was a mere investigatory “stop” allowable\\n\\nbased on reasonable suspicion alone. Rather, we hold that it “ripened” into a full-\\n\\nblown seizure that required probable cause. See Puglisi, 723 F.2d at 784.\\n\\n B\\n\\n The government contends, in the alternative, that it can meet the probable-\\n\\ncause standard and, further, that it can show that exigent circumstances justified a\\n\\nwarrantless seizure. We will consider the two components of the government’s\\n\\nargument in turn, looking first to whether the officers at Babcock’s residence had\\n\\nprobable cause to believe that his phone contained evidence of a crime, and then to\\n\\nwhether exigent circumstances excused them from the need to obtain a warrant\\n\\npre-seizure.\\n\\n\\n\\n\\n 19\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 20 of 32\\n\\n\\n 1\\n\\n Probable cause to seize property is what it sounds like—a belief that\\n\\nevidence will probably be found in a particular location. See United States v.\\n\\nNoriega, 676 F.3d 1252, 1261 (11th Cir. 2012). As the Supreme Court recently\\n\\nreiterated, probable cause “is not a high bar.” District of Columbia v. Wesby, 138\\n\\nS. Ct. 577, 586 (2018) (quoting Kaley v. United States, 571 U.S. 320, 338 (2014)).\\n\\nAlthough probable cause requires more than reasonable suspicion that criminal\\n\\nbehavior is afoot, it doesn’t entail the same “standard of conclusiveness and\\n\\nprobability as the facts necessary to support a conviction.” United States v.\\n\\nDunn, 345 F.3d 1285, 1290 (11th Cir. 2003) (internal quotations omitted). Rather,\\n\\nit requires only “a substantial chance” that evidence of criminal activity exists.\\n\\nIllinois v. Gates, 462 U.S. 213, 243 n.13 (1983). We recently explained that this\\n\\n“substantial chance” exists “where the facts within the collective knowledge of law\\n\\nenforcement officials” suffice “to cause a person of reasonable caution to believe\\n\\nthat a criminal offense has been or is being committed”—and here, that evidence\\n\\nof that offense will be found in a particular place. Gates v. Khokar, 884 F.3d 1290,\\n\\n1298 (11th Cir. 2018) (internal quotation marks omitted).\\n\\n Babcock contends that while the officers in this case might have suspected\\n\\nthat something was up, their collective knowledge at the time of the seizure didn’t\\n\\nrise to the level of probable cause that a crime had been committed. To evaluate\\n\\n\\n 20\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 21 of 32\\n\\n\\nthat contention, let’s recap: At the time Detective Broughton retained Babcock’s\\n\\nphone, the officers knew—\\n\\n • that a domestic-disturbance call had reported a female at Babcock’s\\n residence yelling “Stop, stop, stop!”;\\n\\n • that after Babcock had denied that anyone else was in his camper, a teenage\\n girl emerged with cuts on her legs;\\n\\n • that Babcock had accompanied the girl to a Halloween party the night\\n before, where she had consumed alcohol and drugs, and that she was in his\\n camper the next morning;\\n\\n • that the girl had been in or on Babcock’s bed and left traces of blood there;\\n\\n • that the girl had been distraught, holding a knife to her own throat and\\n saying, “I just want to die”; and\\n\\n • that shortly after they arrived at Babcock’s residence, the girl appeared to be\\n panicking or suffering an overdose.\\n\\nFinally—and perhaps most tellingly—the officers knew that, while the girl sat on\\n\\nBabcock’s bed with the knife to her neck, Babcock called her “dumb as f***” and\\n\\nthen complained—in the present tense—that “this is what I deal with right here . . .\\n\\nyou gotta do drama and fighting me all over the place.”\\n\\n Collectively, these circumstances gave the officers probable cause to believe\\n\\nthat Babcock had committed a crime against C.A. This common-sense conclusion\\n\\ndoesn’t depend on any particular fact taken in isolation; rather, as is “often” the\\n\\ncase, “the whole is . . . greater than the sum of its parts.” Wesby, 138 S. Ct. at 588;\\n\\nsee United States v. Arvizu, 534 U.S. 266, 274 (2002) (rejecting a “divide-and-\\n\\n 21\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 22 of 32\\n\\n\\nconquer” approach and instructing courts to evaluate probable cause in light of the\\n\\ntotality of the circumstances). Here, Babcock’s lies contributed to probable cause,\\n\\nsee Wesby, 138 S. Ct. at 587 (citing Devenpeck v. Alford, 543 U.S. 146, 149, 155–\\n\\n56 (2004)), as did his own present-tense statements clearly indicating an ongoing\\n\\nrelationship. When the officers considered Babcock’s own utterances in light of\\n\\nthe litany of other suspicious facts the learned, they certainly could have suspected\\n\\na “substantial chance of criminal activity.” Gates, 462 U.S. at 243 n.13.\\n\\n From there, it required no leap for the officers to deduce that evidence of a\\n\\ncrime would likely be found on Babcock’s phone. The officers already knew that\\n\\nthe phone contained one eyebrow-raising video suggesting an ongoing relationship\\n\\nbetween a grown man and a teenage girl. It was eminently reasonable for them to\\n\\nbelieve that additional evidence of that relationship—messages, texts, pictures,\\n\\nvideos, etc.—would be found in the same place.\\n\\n True, as Babcock points out, the government has been a little wishy-washy\\n\\nabout the exact crime that the officers suspected at the time of the seizure. The\\n\\ngovernment doesn’t contend that the officers had probable cause to believe that the\\n\\nphone contained evidence of child pornography; rather, it concedes that until\\n\\nDetective Broughton confronted C.A. with the phone at the hospital post-seizure,\\n\\nhe had “no reason to believe that there were videos of sexual activity between [the]\\n\\ntwo.” Importantly, though, our precedent doesn’t require officers to predict the\\n\\n\\n 22\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 23 of 32\\n\\n\\neventually-charged offense in order to demonstrate probable cause, only that the\\n\\ncollective facts would cause a “person of reasonable caution” to believe that “a\\n\\ncriminal offense has been or is being committed.” See Khokar, 884 F.3d at 1298\\n\\n(emphasis added) (internal quotation marks omitted).\\n\\n Here, the government’s arguments at the suppression hearing focused\\n\\nmainly on preserving both the video of C.A. on the bed and any evidence that\\n\\nmight have shed light on the events leading up to it. And indeed, that is exactly\\n\\nwhat the officers ended up finding: evidence of an illegal, coercive relationship,\\n\\nconfirming the suspicions sparked by the video’s portrayal of Babcock’s\\n\\ndisdainful, bullying tone and C.A.’s distraught appearance. The fact that the phone\\n\\nalso (and unexpectedly) contained pornographic images and videos doesn’t\\n\\ninvalidate probable cause for any number of Florida state crimes the officers\\n\\nreasonably could have believed occurred based on the scene greeting them at\\n\\nBabcock’s residence. See, e.g., Fla. Stat. § 794.05(1) (“Unlawful sexual activity\\n\\nwith certain minors”); id. § 794.011(4)(a) (“Sexual battery”). Accordingly, we\\n\\nhold that on these facts the officers had probable cause to believe that Babcock was\\n\\nguilty of a crime, and that evidence of the crime would be found on his phone.\\n\\n 2\\n\\n Of course, probable cause isn’t alone enough to seize an individual’s\\n\\npersonal property—officers typically need a warrant. “[A] warrantless search\\n\\n\\n 23\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 24 of 32\\n\\n\\nand seizure can be justified,” however, “when probable cause has been established\\n\\nto believe that evidence will be removed or destroyed before a warrant can be\\n\\nobtained.” United States v. Young, 909 F.2d 442, 446 (11th Cir. 1990). This\\n\\nexception—one branch of the “exigent-circumstances” doctrine—entails, like\\n\\nprobable cause itself, an objective inquiry. See United States v. Bradley, 644 F.3d\\n\\n1213, 1262 (11th Cir. 2011).\\n\\n Historically, we have found the exigent-circumstances exception\\n\\n“particularly compelling” in drug cases “because contraband and records can be\\n\\neasily and quickly destroyed while a search is progressing.” Young, 909 F.2d at\\n\\n446. The same is true of electronic files. In Bradley, for instance, we found that\\n\\nthe exigent-circumstances exception permitted officers to shut down a company’s\\n\\nservers—a seizure of the company’s property—when multiple employees “had the\\n\\nability and incentive to, after learning of the raid, destroy damning information\\n\\ncontained on the computer servers.” 644 F.3d at 1262–63.\\n\\n To be clear, it’s not that a cell phone itself creates an exigent circumstance.\\n\\n“Taken to its logical conclusion,” that “would permit police officers to seize now-\\n\\nubiquitous cell phones from any person, in any place, at any time, so long as the\\n\\nphone contains photographs or videos that could serve as evidence of a crime—\\n\\nsimply because the ‘nature’ of the device used to capture that evidence might result\\n\\nin it being lost.” Crocker v. Beatty, 886 F.3d 1132, 1137 (11th Cir. 2018)\\n\\n\\n 24\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 25 of 32\\n\\n\\n(emphasis in original). In Crocker, we held that the exigent-circumstances\\n\\nexception didn’t apply where an officer had seized a bystander’s phone to prevent\\n\\ndeletion of photographs that he observed the onlooker snapping following a huge\\n\\nhighway crash. Id. Absent any reason for the officer to think that the bystander\\n\\nwouldn’t preserve the pictures or would refuse to turn them over if asked, we\\n\\nfound the government’s exigent-circumstances argument unconvincing. Id.\\n\\n This case is different. Given the facts here, a reasonable, experienced agent\\n\\ncertainly could have believed that Babcock—the suspect, not a mere bystander—\\n\\nwould delete any incriminating evidence on his phone before a warrant could be\\n\\nobtained. For starters, Babcock had tried to deceive the responding officers from\\n\\nthe get-go, denying that anyone else was in his camper, reporting that C.A. had\\n\\nrandomly shown up at his house in the middle of the night, and claiming that he\\n\\ndidn’t know her age—all lies. Moreover Babcock surely knew that he was under\\n\\nsuspicion once Detective Broughton asked to search the camper and to further\\n\\ninspect his phone. Finally, of course, and on top of all that, the electronic files on\\n\\nBabcock’s phone could have been “quickly destroyed while [the] search [wa]s\\n\\nprogressing.” Young, 909 F.2d at 446. All told, as in Bradley, it was reasonable\\n\\nfor the officers here to conclude that Babcock had the “ability and incentive to,\\n\\nafter learning” of the investigation into his relationship with C.A., “destroy\\n\\n\\n\\n\\n 25\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 26 of 32\\n\\n\\ndamning information contained on” his phone. 644 F.3d at 1262–63. That’s all\\n\\nthe exigent-circumstances doctrine requires. 5\\n\\n Babcock contends that his offer to e-mail the video to the officers removed\\n\\nany urgency, thereby undermining any exigent-circumstances argument. He cites\\n\\nour decision in United States v. Hernandez-Cano, 808 F.2d 779 (11th Cir. 1987),\\n\\nfor the proposition that officers can’t claim exigent circumstances when the\\n\\nsupposed risk can be alleviated by alternative means. But Hernandez-Cano was\\n\\ndifferent—and in fact boomerangs back around on Babcock here. There, we\\n\\nconsidered a warrantless search of a suspect’s luggage and determined that,\\n\\nbecause officers had probable cause to arrest him at the time of the search, “any\\n\\nexigencies inherent in the situation could have been removed” by simply doing so.\\n\\n5\\n Babcock asserts that the government forfeited its exigency argument by failing to use the\\nphrase “exigent circumstances”—and failing to fully develop its position regarding the same—in\\nits response to the motion to suppress. We disagree. While it’s true that alternative theories of\\nadmissibility—including exigent circumstances—can be forfeited even when the government is\\nthe appellee or respondent, see Steagald v. United States, 451 U.S. 204, 208 (1981); Giordenello\\nv. United States, 357 U.S. 480, 487–88 (1958), we conclude that the government did enough here\\nto preserve its exigent-circumstances argument. To be sure, in responding to Babcock’s motion\\nto suppress, the government didn’t use the phrase “exigent circumstances” or cite case law\\nspecifically in support of the exception. It did argue, though, that “[t]he deputies had probable\\ncause to believe that the phone had evidentiary value” and that “detention of the cellular phone\\nwas necessary to preserve the evidence observed by the deputies.” Gov’t Resp. Mot. Suppress at\\n5 (emphasis added). That—whether accompanied by magic words or not—is the very definition\\nof the exigent-circumstances exception. See, e.g., Young, 909 F.2d at 446 (“[W]hen probable\\ncause has been established to believe that evidence will be removed or destroyed before a\\nwarrant can be obtained, a warrantless search and seizure can be justified.”). That the\\ngovernment presented a more robust version of its argument on appeal doesn’t render its initial\\nargument null. See, e.g., Sec’y, U.S. Dep’t of Labor v. Preston, 873 F.3d 877, 883 n.5 (11th Cir.\\n2017) (explaining that “[o]ffering a new argument or case citation in support of a position\\nadvanced in the district court is permissible—and often advisable” lest “the quality and depth of\\nargument [fail] to improve on appeal—an unfortunate result”), cert. denied sub nom. Preston v.\\nAcosta, 138 S. Ct. 2680 (2018).\\n 26\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 27 of 32\\n\\n\\nId. at 782. We explained that “[e]ven if exigent circumstances existed that justified\\n\\nthe seizure of the suitcase to prevent the loss or destruction of its contents, the\\n\\ngovernment still had to obtain a warrant to search the suitcase.” Id. (emphasis\\n\\nadded). Here, the officers didn’t conduct a warrantless search. Instead, faced with\\n\\nthe potential destruction of evidence, they did exactly what Hernandez-Cano\\n\\nsuggests they should have done—they seized the phone “to prevent the loss or\\n\\ndestruction of its contents,” and then obtained a warrant before searching through\\n\\nit. See id.\\n\\n Thus, because a reasonable officer could have believed that Babcock would\\n\\ndelete any incriminating evidence on his phone before a warrant could be\\n\\nobtained—and because none of Babcock’s arguments convinces us otherwise—we\\n\\nfind that the exigent-circumstances exception applies in this case.6\\n\\n * * *\\n\\n\\n6\\n The government also argues in the alternative that Babcock consented to the seizure by\\nvoluntarily providing his phone to the officers to display the video of C.A. threatening self-harm.\\nIt is well-settled, however, that “the scope of a search based on consent may not exceed the\\nscope of the given consent.” United States v. Watkins, 760 F.3d 1271, 1279 (11th Cir. 2014)\\n(citing Florida v. Jimeno, 500 U.S. 248, 251 (1991)). The standard for measuring the scope of\\nconsent is “objective reasonableness”—what “would the typical reasonable person have\\nunderstood by the exchange between the officer and the [individual giving the consent]?” Id.\\n(internal quotation marks omitted). Here, Babcock clearly consented only to the officers’\\nviewing the video he showed them. After the initial viewing, Deputy Olson asked for the phone\\nagain, for the express purpose of showing Officer McMahan the video. Babcock consented to\\nthe officers viewing the clip again, but then asked for his phone back and refused consent when\\nDetective Broughton asked to poke around further. Contrary to the government’s contention, the\\ninitial limited-in-scope consent doesn’t justify an unlimited-in-scope full seizure over Babcock’s\\nobjection.\\n\\n 27\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 28 of 32\\n\\n\\n To sum up, we reject the government’s contention that a two-day\\n\\nwarrantless seizure of a suspect’s cell phone is permissible based on reasonable\\n\\nsuspicion alone. We conclude, however, that the warrantless seizure of Babcock’s\\n\\nphone was lawful because the officers on the scene had probable cause to believe\\n\\nboth that evidence of a crime would be found on it and that the evidence would be\\n\\ndestroyed before they could obtain a warrant.\\n\\n III\\n\\n Babcock separately challenges his sentence, arguing that it is both (1)\\n\\nprocedurally unreasonable because the district court erroneously imposed two\\n\\nenhancements for the same harm and (2) substantively unreasonable because it is\\n\\ntoo harsh in light of the facts.7 Neither argument is persuasive.\\n\\n Babcock raises his procedural-reasonableness argument for the first time on\\n\\nappeal, so we can correct any missteps only if he shows a “plain error” that affects\\n\\nhis substantial rights and that seriously undermines the fairness, integrity, or public\\n\\nreputation of judicial proceedings. See United States v. Shelton, 400 F.3d 1325,\\n\\n1328–29 (11th Cir. 2005). Babcock essentially argues that the district court’s\\n\\napplication of both § 2G2.1(b)(2) and § 4B1.5(b) of the Sentencing Guidelines\\n\\nconstitutes impermissible double-counting.\\n\\n7\\n Babcock also argues that his sentence is procedurally unreasonable because the government did\\nnot group two counts of conviction which were based on the same harm. As the government\\npoints out, though, the Guidelines specifically exclude convictions under § 2G2.1 from the\\ngrouping rules. See U.S.S.G. § 3D1.2(d).\\n\\n 28\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 29 of 32\\n\\n\\n Double-counting occurs when one part of the Sentencing Guidelines is\\n\\napplied to increase a defendant’s punishment on account of a harm that has already\\n\\nbeen fully accounted for by application of another part of the Guidelines. See\\n\\nUnited States v. Dudley, 463 F.3d 1221, 1226–27 (11th Cir. 2006). Absent\\n\\nevidence to the contrary, however, the presumption is that “the Sentencing\\n\\nCommission intended to apply separate sections cumulatively,” United States v.\\n\\nKapordelis, 569 F.3d 1291, 1315 (11th Cir. 2009) (citation omitted), such that\\n\\nwhat might appear to be impermissible double-counting is instead what we will\\n\\ncall permissible “cumulative-counting.”\\n\\n We conclude that applying both enhancements in this case constitutes\\n\\ncumulative- (rather than double-) counting. Chapter Two of the Guidelines,\\n\\nfocusing on the sexual exploitation of minors through pictures, provides that an\\n\\noffender’s base sentencing level should be enhanced by two when “the commission\\n\\nof a sexual act or sexual contact” occurs during a visual depiction. U.S.S.G.\\n\\n§ 2G2.1(b)(2)(A). Chapter Four then makes clear that when a “pattern of . . .\\n\\nprohibited sexual contact” occurs, a court should add five to “the offense level\\n\\ndetermined under Chapter[] Two.” U.S.S.G. § 4B1.5(b). The Guidelines say\\n\\nnothing about adding this enhancement to only a portion of the base level\\n\\ndetermined under Chapter Two, or otherwise adjusting the calculation in any\\n\\nway—instead, they simply presuppose that a certain offense level was determined\\n\\n\\n 29\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 30 of 32\\n\\n\\nunder Chapter Two, and then instruct the sentencing court to add five levels,\\n\\nperiod. Nothing in the Guidelines, then, indicates that these sections may not be\\n\\napplied cumulatively. See Kapordelis, 569 F.3d at 1315. Moreover, and in any\\n\\nevent, it isn’t clear that the harm in § 4B1.5(b)’s “pattern of activity involving\\n\\nprohibited sexual contact” is “fully accounted for” in § 2G2.1(b)(2)’s “sexual act\\n\\nor sexual contact” occurring in a visual depiction, such that application of the two\\n\\nsections could be considered double-counting at all. See Dudley, 463 F.3d at\\n\\n1226–27. There was no plain error here.\\n\\n Looking next to substantive reasonableness, Babcock argues that the nature\\n\\nand circumstances of this case do not compel the same severe sentence required to\\n\\ndeter creators of commercial child pornography. Basically, Babcock contends that\\n\\nhis crime—an inappropriate, long-term relationship with an older teenager—\\n\\ndoesn’t indicate that he is a threat to children generally or affect the child-\\n\\npornography market as would, for instance, the rape of a child for video\\n\\ndistribution or other predatory production of commercial child pornography.\\n\\nBabcock asserts that because there is no evidence that he intended ever to show\\n\\nanyone his videos or pictures of C.A., his 324-month sentence is substantively\\n\\nunreasonable.\\n\\n We review challenges to the substantive reasonableness of a sentence for\\n\\nabuse of discretion. Gall v. United States, 552 U.S. 38, 41 (2007). The party\\n\\n\\n 30\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 31 of 32\\n\\n\\nchallenging the sentence bears the burden of showing that the sentence is\\n\\nunreasonable in light of the record and the 18 U.S.C. § 3553(a) factors. United\\n\\nStates v. Tome, 611 F.3d 1371, 1378 (11th Cir. 2010). While we do not formally\\n\\npresume that a within-Guidelines sentence is reasonable, we ordinarily expect it to\\n\\nbe so. United States v. Hunt, 526 F.3d 739, 746 (11th Cir. 2008). That a sentence\\n\\nis imposed well below the statutory maximum penalty may also indicate its\\n\\nreasonableness. See United States v. Gonzalez, 550 F.3d 1319, 1324 (11th Cir.\\n\\n2008) (per curiam).\\n\\n There is a certain intuitive logic to Babcock’s argument here—it’s true that\\n\\nnothing in the record necessarily indicates a propensity to distribute child\\n\\npornography. That being said, Babcock’s conduct falls squarely within the\\n\\nconfines of § 2G2.1—“sexually exploiting a minor by production of sexually\\n\\nexplicit visual or printed material”—and, as the sentencing judge emphasized, the\\n\\neffect of his actions on C.A. and her family was far from insignificant. We are\\n\\ncomfortable that the sentencing judge took into consideration all of the relevant\\n\\ncircumstances when he sentenced Babcock to 324 months—a downward variance\\n\\nfrom the 360 to 720 months recommended by the Guidelines. See Gonzalez, 550\\n\\nF.3d at 1324. Accordingly, we find no abuse of discretion in the district court’s\\n\\nsentencing decision.\\n\\n\\n\\n\\n 31\\n\\f Case: 17-13678 Date Filed: 05/24/2019 Page: 32 of 32\\n\\n\\n IV\\n\\n For the foregoing reasons, we hold (1) that reasonable suspicion alone could\\n\\nnot have justified the officers’ warrantless two-day seizure of Babcock’s cell\\n\\nphone; (2) that the officers in this case had probable cause to believe that a crime\\n\\nhad been committed, that evidence of the crime would be found on Babcock’s\\n\\nphone, and that there was a risk that Babcock would destroy the evidence before\\n\\nthey could get a warrant, such that the seizure did not violate the Fourth\\n\\nAmendment; and (3) that Babcock’s sentence was both procedurally and\\n\\nsubstantively reasonable. Accordingly, we affirm the district court’s denial of\\n\\nBabcock’s motion to suppress as well as its 324-month sentence.\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 32\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2293,"cells":{"id":{"kind":"number","value":4623250,"string":"4,623,250"},"name":{"kind":"string","value":"CLUB MADONNA, INC., a Florida Corporation D.B.A. Club Madonna, Plaintiff - Appellant, v. CITY OF MIAMI BEACH, a Florida Municipal Corporation, Defendant - Appellee."},"name_abbreviation":{"kind":"string","value":"Club Madonna, Inc. v. City of Miami Beach"},"decision_date":{"kind":"string","value":"2019-05-24"},"docket_number":{"kind":"string","value":"17-13934"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Carnes, Rosenbaum, Dubina\", \"parties\": \"\", \"opinions\": [{\"author\": \"ROSENBAUM, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-13934 Date Filed: 05/24/2019 Page: 1 of 23\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-13934\\n ________________________\\n\\n D.C. Docket No. 1:16-cv-25378-FAM\\n\\n\\n\\nCLUB MADONNA, INC.,\\na Florida corporation d.b.a. Club Madonna,\\n\\n Plaintiff - Appellant,\\n\\nversus\\n\\nCITY OF MIAMI BEACH,\\na Florida municipal corporation,\\n\\n Defendant - Appellee.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 24, 2019)\\n\\nBefore ED CARNES, Chief Judge, and ROSENBAUM and DUBINA, Circuit\\nJudges.\\n\\nROSENBAUM, Circuit Judge:\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 2 of 23\\n\\n\\n People often say that timing is everything. Hitting a home run? Timing.1\\n\\nComedy? Timing. 2 Winemaking? Timing. 3 Relationships? Timing. 4 Politics?\\n\\nTiming. 5\\n\\n And of course, timing is also important when it comes to Article III\\n\\njusticiability. File before the facts underpinning the claim have been sufficiently\\n\\ndeveloped, and a court must dismiss the claim because it is not ripe for the court’s\\n\\nreview. But wait until the claim has been resolved and the court can offer no further\\n\\nrelief, and a court must dismiss the claim because it is moot. Yet if a well-pleaded\\n\\nclaim falls in the sweet spot between ripeness and mootness and is otherwise\\n\\njusticiable, it states a “case or controversy” that the court must entertain.\\n\\n\\n\\n\\n 1\\n Babe Ruth said that a great hitter didn’t “swing any harder” or “with any longer arc than\\nthe poorer hitters” but had “perfect timing sense.” George Herman Ruth, Babe Ruth’s Own Book\\nof Baseball 178 (University of Nebraska Press, 1992) (1928); see also Nate Scott, “The 50 Greatest\\nYogi Berra Quotes,” USA Today Sept. 23, 2015, available at\\nhttps://ftw.usatoday.com/2015/09/the-50-greatest-yogi-berra-quotes (last visited May 24, 2019).\\n 2\\n According to Bob Hope, timing is “the essence of life and definitely of comedy.” William\\nRobert Faith, Bob Hope: A Life in Comedy (Da Capo Press, Inc. 2009). Asked to comment further,\\nhe reportedly paused and said, “We don’t have time for that.” Dena Kleiman, “Bob Hope Gives a\\nLesson in Comedy,” New York Times, April 30, 1986, available at https://nyti.ms/2HLa4Mi.\\n 3\\n Timing’s importance in winemaking was central to the Paul Masson advertising campaign\\nfrom the late 1970s, which featured Orson Welles informing the viewer that the company would\\n“sell no wine before its time.” See Orson Welles for Paul Masson Wine (April 2, 1979), YouTube\\n(May 14, 2009), https://youtu.be/oSs6DcA6dFI, (last visited May 24, 2019).\\n 4\\n Just ask Mila Kunis and Ashton Kutcher. They married in 2015, over a decade and a half\\nafter their first kiss—as actors in the pilot episode of That ‘70s Show. Stephanie Petit, “#TBT:\\nMila Kunis and Ashton Kutcher First Kissed on That 70’s Show,” People (July 21, 2016),\\nhttps://people.com/tv/mila-kunis-and-ashton-kutcher-recall-first-kiss-on-that-70s-show/ (last\\nvisited May 24, 2019).\\n 5\\n Pierre Trudeau is credited as saying that timing was the “essential ingredient” of politics.\\nSee The Wordsworth Dictionary of Quotations 439 (Connie Robertson, ed.,Wordsworth 1997).\\n 2\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 3 of 23\\n\\n\\n Here, Appellant Club Madonna, Inc. (the “Club”), a fully-nude strip club in\\n\\nthe City of Miami Beach (the “City”), filed several claims against the City,\\n\\nchallenging administrative action it had taken against the Club, the laws authorizing\\n\\nthat action, and ordinances the City later enacted that regulate the fully nude strip-\\n\\nclub business. The district court dismissed all sixteen of the Club’s claims, six\\n\\nbecause they did not state a claim and ten because they were not yet ripe for the\\n\\ncourt’s review.\\n\\n The Club appealed the district court’s dismissal as it pertains to all but Counts\\n\\nI, II, and part of Count VI. We agree that Counts III through VI failed to state claims.\\n\\nWe also agree that one of the remaining claims was not ripe. And we affirm the\\n\\ndistrict court’s dismissal of one more of those claims because the Club lacks standing\\n\\nto pursue it. But we conclude that the eight remaining appealed claims were ripe for\\n\\nthe district court’s review and therefore reverse and remand to the district court for\\n\\nfurther proceedings.\\n\\n I.\\n\\n The catalyst for this case arose out of events occurring on January 6, 2014.\\n\\nOn that date, police executed a search warrant at the Club. The affidavit supporting\\n\\nthe warrant application described a police investigation into the disappearance of a\\n\\n13-year-old girl. Among other information, it asserted that the girl had been\\n\\ntrafficked by various people, including a woman who herself danced at the Club and\\n\\n\\n 3\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 4 of 23\\n\\n\\nwho forced the girl to dance, fully nude, at the Club on several occasions. According\\n\\nto the affidavit, the Club did not require the girl to provide it with identification to\\n\\nverify her age, and the girl did not offer the Club any identification before\\n\\nperforming. The affidavit further attested that the woman and her cohorts coerced\\n\\nthe girl to turn over to them any money she earned working at the Club, under threat\\n\\nand actions of physical abuse.\\n\\n On January 10, 2014, the City’s city manager found, based on the search\\n\\nwarrant, that the conditions at the Club constituted an emergency and immediately\\n\\nsuspended the Club’s business license. 6 The City scheduled a hearing on that\\n\\nsuspension, to be held before a special master on February 5, 2014. Before the\\n\\nhearing, though, the Club and the City reached a compromise under which the Club\\n\\nagreed to institute measures to ensure that similar events would not happen again,\\n\\nand the City agreed to return the Club’s business license.\\n\\n Following these events, the City passed two ordinances regulating nude dance\\n\\nestablishments, City of Miami Beach Ordinance Nos. 2015-3917 and 2015-3926\\n\\n(collectively, the “Ordinance”). The Ordinance remains in effect and contains three\\n\\nsections.\\n\\n\\n\\n\\n 6\\n Strictly speaking, the City suspended the Club’s Business Tax Receipt and its Certificate\\nof Use for the building. The parties and district court variously used the terms “occupational\\nlicenses” and “business license” to describe these items. For simplicity, we refer to them\\ncollectively simply as the Club’s “business license.”\\n 4\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 5 of 23\\n\\n\\n First, Section 18-913 requires nude dance establishments such as the Club to\\n\\ncheck the age and work eligibility of “any worker or performer” by requiring that\\n\\nthey “provide proof of an original, lawfully issued state or federal photo\\n\\nidentification, and one additional form of identification.” The owner or manager of\\n\\nthe establishment must also “[v]erify the accuracy” of the documents by making a\\n\\n“sworn statement . . . confirming that the individual performer is at least 18 years of\\n\\nage.” In the same sworn statement, the owner or manager must “[c]onfirm” that the\\n\\nworker is “performing of her or his own accord, and is not being forced or\\n\\nintimidated into performing or working.” Code of the City of Miami Beach § 18-\\n\\n913. Section 18-913 also requires the business to keep a log of workers as they enter\\n\\nand exit the premises and to make all of the required documentation available “for\\n\\ninspection by the city upon demand.” Id.\\n\\n Next, under Section 18-914, nude dance establishments must “[p]rovide direct\\n\\nmonetary or non-monetary compensation to any worker or performer” and “maintain\\n\\ndocumentary proof” that the compensation “was directly received by the worker or\\n\\nperformer.” Code of the City of Miami Beach § 18-914. As with Section 18-913,\\n\\nSection 18-914 requires the business to maintain records of its compliance, and the\\n\\nCity enjoys “a right to request and inspect the records for any and all workers or\\n\\nperformers.” Id.\\n\\n\\n\\n\\n 5\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 6 of 23\\n\\n\\n Finally, Section 18-915 describes the penalties for failure to comply with the\\n\\nrequirements of Sections 18-913 and 18-914. For a first, second, and third offense\\n\\nwithin specified time periods, a business shall be fined $5,000, $10,000, and\\n\\n$20,000, respectively. For a second offense within three years, the City will shut\\n\\ndown the business for three months. And a third offense allows the City to exercise\\n\\nits discretion to close the business for up to a year. Code of the City of Miami Beach\\n\\n§ 18-915. An establishment charged with violating the ordinance has a right to an\\n\\nadministrative hearing and may appeal the decision to “a court of competent\\n\\njurisdiction.” Id.\\n\\n So far, the City has not alleged that the Club has fallen short of compliance\\n\\nwith the Ordinance.\\n\\n II.\\n\\n Displeased with the City’s activities after the execution of the search warrant,\\n\\nthe Club filed a complaint against the City. The complaint contains multiple and\\n\\nvaried constitutional-law claims that might inspire a law-school professor writing a\\n\\nfinal exam. We catalogue them below.\\n\\n Counts I through VI all concern the City’s actions in response to the execution\\n\\nof the search warrant and challenge laws existing at that time, before the enactment\\n\\nof the new Ordinance. More specifically, Count I presented a facial challenge to the\\n\\nordinances that authorized the City to close the Club on an emergency basis and\\n\\n\\n 6\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 7 of 23\\n\\n\\nasserts that they impose an unlawful prior restraint under the First Amendment;\\n\\nCount II lodges the same argument, only as applied to the Club. And Count III\\n\\nalleges that these ordinances are facially unconstitutional under the Due Process\\n\\nClause. Count IV contests the facial constitutionality of the City’s post-deprivation\\n\\nprocedures in particular under the Due Process Clause; Count V makes the same\\n\\nargument as applied to the Club. Count VI asserts that the City’s use of the local\\n\\nlaws to suspend its business license violated the First Amendment and the Due\\n\\nProcess Clause because, according to the complaint, the City acted in bad faith and\\n\\nfor retaliatory reasons.\\n\\n Counts VII through XVI concern the legality of the Ordinance enacted in the\\n\\nwake of the police investigation. Count VII contends that the Ordinance imposes an\\n\\nunconstitutional burden on the Club’s First Amendment rights. Count VIII alleges\\n\\nthat the Ordinance is an unconstitutional tax on speech. Count IX challenges the\\n\\nOrdinance as a violation of the Equal Protection Clause. Count X argues that the\\n\\nOrdinance is unconstitutionally vague. Count XI posits that the Ordinance violates\\n\\nthe Contract Clause. Count XII takes issue with the penalty provision, claiming it\\n\\nviolates the Eighth Amendment. Counts XIII, XIV, and XV allege that the\\n\\nOrdinance is preempted by state and federal laws. And finally, Count XVI contends\\n\\nthat the inspection provision of the Ordinance violates the Fourth Amendment.\\n\\n\\n\\n\\n 7\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 8 of 23\\n\\n\\n In response to the Club’s complaint, the City moved to dismiss the case. To\\n\\nsupport its motion, the City attached the search warrant (complete with the\\n\\nsupporting search-warrant affidavit) that prompted its actions, the order suspending\\n\\nthe Club’s business license, and the order offering to reinstate the Club’s business\\n\\nlicense under a negotiated compromise.\\n\\n As for its legal argument, the City asserted that the complaint should be\\n\\ndismissed because the Club lacked standing to bring any of its claims. Besides that,\\n\\nthe City continued, Counts I through VI were moot, and Counts VII through XVI\\n\\nwere not ripe for the court’s review. In the alternative, the City argued that the Club\\n\\nfailed to state any claim.\\n\\n In response, the Club contended that its claims were justiciable and viable.\\n\\n The district court granted the City’s motion to dismiss. It reasoned that Counts\\n\\nI through VI were justiciable but did not state claims. Specifically, as to Counts I,\\n\\nII, and VI of the complaint, the court said that the Ordinance satisfied United States\\n\\nv. O’Brien’s, 391 U.S. 367 (1968), test for content-neutral laws that incidentally\\n\\nregulate expressive conduct and thus did not violate the Club’s First Amendment\\n\\nrights.7 As for Counts III-VI of the complaint, the court noted that the Club had not\\n\\ncontested the City’s suspension of its business license at the scheduled\\n\\n\\n 7\\n The Club does not appeal the district court’s dismissal of Counts I and II, nor the dismissal\\nof Count VI to the extent it asserts a violation of the First Amendment. As a result, we do not\\naddress those claims.\\n 8\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 9 of 23\\n\\n\\nadministrative hearing and had not availed itself of the other process available to it\\n\\nunder state and local law. Therefore, the court concluded, those due-process counts\\n\\nwere “incognizable” under McKinney v. Pate, 20 F.3d 1550 (11th Cir. 1994) (en\\n\\nbanc).\\n\\n Next, the Court reasoned that Counts VII through XVI were not ripe for the\\n\\ncourt’s review. Specifically, the court observed that “the Club ha[d] not been\\n\\ncharged with violating” the Ordinance. “Without the facts of a particular violation,”\\n\\nthe court explained, it could “only speculate as to whether the Club will be charged\\n\\nunder the ordinances and if so, whether it will be subject to specific penalties.” On\\n\\nthat basis, the district court concluded that “the Club ha[d] not satisfied the ‘fitness’\\n\\nprong of the ripeness inquiry.” In addition, the district court determined that the\\n\\nClub would not suffer a substantial hardship as a result of postponing adjudication\\n\\nbecause the law did not “prohibit the Club from providing fully nude dance\\n\\nentertainment to its adult patrons.”\\n\\n This appeal followed.\\n\\n III.\\n\\n We review de novo the grant of a motion to dismiss for failure to state a claim,\\n\\naccepting the allegations in the complaint as true and construing them in the light\\n\\nmost favorable to the plaintiff. Fourth Estate Pub. Benefit Corp. v. Wall-Street.com,\\n\\nLLC, 856 F.3d 1338, 1339 (11th Cir. 2017). We likewise review de novo questions\\n\\n\\n 9\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 10 of 23\\n\\n\\nconcerning our subject matter jurisdiction, including standing and ripeness. Elend\\n\\nv. Basham, 471 F.3d 1199, 1204 (11th Cir. 2006). And we can affirm on any basis\\n\\nsupported by the record, regardless of whether the district court decided the case on\\n\\nthat basis. Jarvela v. Crete Carrier Corp., 776 F.3d 822, 828 (11th Cir. 2015).\\n\\n IV.\\n\\n After careful consideration of the record and oral argument, we affirm in part\\n\\nand reverse and remand in part. We agree with the district court that Counts III\\n\\nthrough VI (the due-process part of that claim) 8 of the Club’s complaint failed to\\n\\nstate claims. We also agree that Count XII was not ripe for the court’s review. And\\n\\nwe affirm the dismissal of Count X because the Club lacked standing. We conclude,\\n\\nhowever, that the remaining counts are ripe for the court’s review, so we reverse the\\n\\ncourt’s order on those counts and remand the case for further proceedings.\\n\\n A.\\n\\n We begin with Counts III-VI of the Club’s complaint. As we have noted, the\\n\\ndistrict court dismissed these counts for failure to state a claim, citing McKinney.\\n\\nWe agree.\\n\\n To state a claim under 42 U.S.C § 1983, a plaintiff must allege facts showing\\n\\nthat the defendant, acting under color of state law, deprived it of a right protected by\\n\\nthe Constitution or by a federal statute. Where, as here, the plaintiff alleges a\\n\\n\\n 8\\n See supra at n.7.\\n 10\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 11 of 23\\n\\n\\nviolation of procedural due process, the plaintiff must show the deprivation of that\\n\\nprotected interest “without due process of law.” Zinermon v. Burch, 494 U.S. 113,\\n\\n123 (1990) (emphasis in original). And a violation of procedural due process does\\n\\nnot “become complete ‘unless and until the state refuses to provide due process.’”\\n\\nMcKinney, 20 F.3d at 1562 (quoting Zinermon, 494 U.S. at 123). Here, all of the\\n\\nClub’s due-process claims in Counts III-VI fail for the same reason: they all lack\\n\\nthe essential element that the state refused to provide the Club with due process.\\n\\n First, the Club was not entitled to a pre-suspension hearing. Though Mathews\\n\\nv. Eldridge, 424 U.S. 319 (1976), can require pre-deprivation process, that is not\\n\\nalways the case. Among other such circumstances, the Supreme Court has\\n\\ndetermined that pre-deprivation process is not required when a need for “quick\\n\\naction” exists. Zinermon v. Burch, 494 U.S. 113, 128 (1990) (citation and quotation\\n\\nmarks omitted). As we have noted, here, law enforcement had probable cause to\\n\\nbelieve that the Club had allowed a 13-year-old trafficked girl to perform under\\n\\nthreat and act of physical abuse. These circumstances raised immediate and pressing\\n\\nconcerns for the physical and mental health and welfare of minors. So the City\\n\\nreasonably concluded that there was a need for “quick action,” and no pre-\\n\\ndeprivation process was required.\\n\\n We therefore turn to the post-deprivation process the Club received. Upon\\n\\nthe City’s decision to suspend its business license, the Club was entitled to a hearing\\n\\n\\n 11\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 12 of 23\\n\\n\\non an emergency basis before a special master to challenge that decision. Code of\\n\\nthe City of Miami Beach §§ 14-406(b); 102-383. At the conclusion of that hearing,\\n\\nthe special master would have issued a final administrative order. Code of the City\\n\\nof Miami Beach §§ 14-408(c); 102-385(c). Then, the Club would have been entitled\\n\\nto appeal that order to the Florida State Circuit Court. Fla. Stat. Ann. § 162.11; see\\n\\nalso Fla Stat. Ann. § 162.03 (providing that special masters with enforcement\\n\\nauthority have the “same status” as enforcement boards for purposes of Fla. Stat.\\n\\nAnn. § 162); Code of the City of Miami Beach §§ 30-2, 30-77 (stating that the City\\n\\nhas given special masters enforcement authority and that the special masters’\\n\\ndecisions are appealable to the circuit court under Fla. Stat. Ann. § 162.11).\\n\\n As we have previously held, that procedure satisfies due process because the\\n\\nFlorida Circuit Court has the power to remedy any procedural deficiencies and cure\\n\\nviolations of due process. McKinney, 20 F.3d at 1564.\\n\\n Here, the Club did not avail itself of the processes provided by local and state\\n\\nlaw. Instead of presenting its arguments to the special master and Florida Circuit\\n\\nCourt, the Club brought its arguments to federal court. For that reason, we cannot\\n\\nsay that the City or state refused to provide the Club with due process. The district\\n\\n\\n\\n\\n 12\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 13 of 23\\n\\n\\ncourt was therefore correct to dismiss Counts III-VI of the Club’s complaint for\\n\\nfailure to state a claim. 9\\n\\n B.\\n\\n The district court dismissed Counts VII-XVI on the basis that they were not\\n\\nripe for review. Specifically, the court reasoned that the Club “ha[d] not been\\n\\ncharged with violating” the Ordinance and that the Club would not suffer a\\n\\nsubstantial hardship as a result of postponing adjudication of its claims, so the Club’s\\n\\nclaims were not ripe for review. We respectfully disagree.\\n\\n Article III limits the power of the federal courts to “cases” and\\n\\n“controversies.” U.S. Const. art III, § 2; see Lujan v. Defenders of Wildlife, 504 U.S.\\n\\n555, 559-60 (1992). One of the “landmarks” of that requirement is the doctrine of\\n\\nstanding, which requires that a party have suffered an “injury in fact,” that the party’s\\n\\ninjury is fairly traceable to the challenged action of the defendant, and that the injury\\n\\nwould “likely” be “redressed by a favorable decision.” Lujan, 504 U.S. at 560-61.\\n\\n But even when a claim meets the case-or-controversy requirement’s\\n\\nconstitutional demands, such as standing, we also recognize important prudential\\n\\n\\n 9\\n Because we hold that the district court’s dismissal of Counts III-VI of the complaint was\\nproper under McKinney, we need not determine whether the district court appropriately relied on\\nthe documents attached to the City’s motion to dismiss. Those documents are not relevant to the\\nMcKinney issue. The search-warrant affidavit is the only one of the attached documents that we\\nhave considered in this appeal, and we considered it only for purposes of recounting the\\nbackground facts of the case. We may take notice of that document because its authenticity is not\\nin question and it is central to the claims at issue. See Maxcess, Inc. v. Lucent Techs., Inc., 433\\nF.3d 1337, 1340 n.3 (11th Cir. 2005); Horsley v. Feldt, 304 F.3d 1125, 1134 (11th Cir. 2002).\\n 13\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 14 of 23\\n\\n\\nlimitations on the kinds of cases that a court has power to decide. Nat’l Advert. Co.\\n\\nv. City of Miami, 402 F.3d 1335, 1338-39 (11th Cir. 2005). Those prudential\\n\\nconcerns “counsel judicial restraint” and prevent courts from “rendering\\n\\nimpermissible advisory opinions and wasting resources through review of potential\\n\\nor abstract disputes.” Id. at 1339. Based on these interests, courts decide only cases\\n\\nthat are ripe for their review. We determine ripeness, which addresses both\\n\\nconstitutional and prudential concerns, by evaluating “(1) the fitness of the issues\\n\\nfor judicial decision and (2) the hardship to the parties of withholding court\\n\\nconsideration.” Nat’l Advert. Co., 402 F.3d at 1339 (citing Abbott Lab. v. Gardner,\\n\\n387 U.S. 136, 148-49 (1967)).\\n\\n Concerning fitness for judicial decision, we ask whether the parties raise an\\n\\nissue that we can decide without further factual development and whether the\\n\\ninstitutional interests of the court and agency favor immediate review. Harrell v.\\n\\nThe Fla. Bar, 608 F.3d 1241, 1258 (11th Cir. 2010); Cheffer v. Reno, 55 F.3d 1517,\\n\\n1524 (11th Cir. 1995). As for “hardship,” litigants must show that they are “forced\\n\\nto choose between foregoing lawful activity and risking substantial legal sanctions.”\\n\\nCheffer, 55 F.3d at 1524 (citing Steffel v. Thompson, 415 U.S. 452, 462 (1974)); see\\n\\nalso Elend, 471 F.3d at 1211. If a claim is fit for judicial decision, that is end of the\\n\\ninquiry, and the matter is ripe, given that the absence of a “hardship” “cannot tip the\\n\\n\\n\\n\\n 14\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 15 of 23\\n\\n\\nbalance against judicial review” under those circumstances. See Harrell, 608 F.3d\\n\\nat 1259 (citation and internal quotation marks omitted).\\n\\n We assess ripeness on a claim-by-claim basis. A facial challenge presenting\\n\\na purely legal argument, for example, “is presumptively ripe for judicial review”\\n\\nbecause that type of argument does not rely on a developed factual record. Harris\\n\\nv. Mexican Specialty Foods, Inc., 564 F.3d 1301, 1308 (11th Cir. 2009). In contrast,\\n\\nan as-applied challenge “necessarily requires the development of a factual record for\\n\\nthe court to consider.” Id.\\n\\n Applying these principles here, we conclude that Counts VII, VIII, IX, XI,\\n\\nXIII, XIV, XV, and XVI of the Club’s complaint are ripe for review. To begin with,\\n\\nCounts XIII, XIV, and XV assert that the Ordinance was preempted by state and\\n\\nfederal law. Further factual development cannot assist in resolution of these facial\\n\\nchallenges, which raise purely legal issues. Nor do any institutional concerns of the\\n\\ncourt or the City render the issues unfit for review. Consequently, these claims are\\n\\nripe. Id. at 1308.\\n\\n Next, the Club’s as-applied challenges—asserting an unconstitutional burden\\n\\nand tax on speech (Counts VII and VIII), an Equal Protection violation (Count IX),\\n\\nand a Contract Clause violation (Count XI)—require no more factual development\\n\\nto be ripe for review. It is undisputed that the Club is subject to the Ordinance and\\n\\n\\n\\n\\n 15\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 16 of 23\\n\\n\\nis complying with its regulations. And that compliance is what forms the factual\\n\\nbasis of the Club’s as-applied arguments.\\n\\n To be sure, the Club does not contend that it was charged with violating the\\n\\nOrdinance or that it has suffered the Ordinance’s penalties. But that does not render\\n\\nthe claims in Counts VII, VIII, IX and XI unripe for the district court’s review. If\\n\\nthe Club were to fall short of any of the Ordinance’s requirements and the City were\\n\\nto charge it with a violation of the law, the resulting additional facts would shed no\\n\\nfurther light on whether compliance with the Ordinance is an unconstitutional\\n\\nburden on speech, a tax on speech, an equal-protection violation, or a Contract\\n\\nClause violation in the first place. For these same reasons, institutional concerns\\n\\nlikewise present no impediment to fitness for review. So Counts VII, VIII, IX, and\\n\\nXI are ripe for review. See Harrell, 608 F.3d at 1258; Cheffer, 55 F.3d at 1524.\\n\\n Count XVI is also fit for review. The Club claims that the Ordinance\\n\\nauthorizes the City to engage in warrantless searches in violation of the Fourth\\n\\nAmendment. That claim presents purely legal questions, such as (1) whether the\\n\\nOrdinance falls within the administrative-search exception, and if so, whether it\\n\\naffords the Club an opportunity to obtain pre-compliance review before a neutral\\n\\ndecisionmaker, and (2) whether the Club is part of a “closely regulated” industry,\\n\\nand if so, whether warrantless inspections are necessary to further a substantial\\n\\ngovernment interest and whether the Ordinance adequately constrains police\\n\\n\\n 16\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 17 of 23\\n\\n\\ndiscretion. See City of Los Angeles v. Patel, 135 S. Ct. 2243, 2452–56 (2015). As a\\n\\nresult, we need not wait for further facts, such as a warrantless search under the\\n\\nOrdinance, to occur to resolve this claim.\\n\\n As for Count XII, we agree with the district court that it is not ripe for review.\\n\\nCount XII alleges that that the Ordinance’s penalty provision violates the Eighth\\n\\nAmendment. But we have held that “Eighth Amendment challenges are generally\\n\\nnot ripe until the imposition, or immediately impending imposition, of a challenged\\n\\npunishment or fine.” Cheffer, 55 F.3d at 1523-24. The Club does not allege that the\\n\\nCity imposed a fine under that provision or that the imposition of a fine is\\n\\nimmediately forthcoming, so the district court correctly determined that the Club’s\\n\\nEighth Amendment argument is not ripe for review.\\n\\n C.\\n\\n Finally, we turn to Count X, which alleges that the Ordinance is\\n\\nunconstitutionally vague. The district court dismissed that claim as unripe, but we\\n\\naffirm for a different reason: the Club lacked standing to bring it. 10\\n\\n As we have noted, to have standing, a party must demonstrate that (1) it has\\n\\nsuffered, or imminently will suffer, an injury-in-fact; (2) the injury is fairly traceable\\n\\nto the operation of the challenged law; and (3) a favorable judgment is likely to\\n\\n\\n 10\\n Standing is a jurisdictional requirement that we are obligated to address sua sponte. See\\nMurphy v. Dulay, 768 F.3d 1360, 1366 n.4 (11th Cir. 2014); Region 8 Forest Serv. Timber\\nPurchasers Council v. Alcock, 993 F.2d 800, 806-807 (11th Cir. 1993).\\n 17\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 18 of 23\\n\\n\\nredress the injury. Wollschlaeger v. Governor, 848 F.3d 1293, 1303-1304 (11th Cir.\\n\\n2017) (en banc); Harrell, 608 F.3d at 1254. Though we “most loosely” apply the\\n\\ninjury-in-fact requirement when a claim involves First Amendment rights, we\\n\\nnevertheless conclude that the Club lacked standing to argue that the Ordinance is\\n\\nunconstitutionally vague. Even if the Club could show that it had suffered, or will\\n\\nimminently suffer, an injury in fact, it cannot demonstrate that the injury is fairly\\n\\ntraceable to the Ordinance’s purported imprecision.\\n\\n In the first step of our standing analysis, we ask whether the Club has suffered,\\n\\nor imminently will suffer, an injury in fact. We have previously held that a party\\n\\nmight satisfy this prong by showing self-censorship. See Wollschlaeger, 848 F.3d\\n\\nat 1304-1305; Harrell, 608 F.3d at 1253. Here, though, it is undisputed that the Club\\n\\nis not self-censoring, but rather, is continuing to carry on its business, apparently in\\n\\ncompliance with the Ordinance.\\n\\n The Club might also suggest that the Ordinance contains vague language that\\n\\ncauses it to fear that the City will enforce it arbitrarily, and is thereby injured. But\\n\\nmere fear of unconstitutional action alone on the part of the City is too speculative\\n\\nan injury to confer standing to the Club. See JW v. Birmingham Bd. Of Educ., 904\\n\\nF.3d 1248, 1264 (11th Cir. 2018); 31 Foster Children v. Bush, 329 F.3d 1255, 1263\\n\\n(11th Cir. 2003). That is especially true here, since the Club has apparently been\\n\\n\\n\\n\\n 18\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 19 of 23\\n\\n\\nsuccessfully complying with the Ordinance without incident since it was\\n\\npromulgated roughly three years ago.\\n\\n The Club’s most promising standing argument would be that it unnecessarily\\n\\nincurred additional expenses in an effort to comply with what it says is an\\n\\nunconstitutionally vague law, above and beyond the expense that would have been\\n\\nnecessary to comply with a law that was not vague. The Club suggested that\\n\\nargument in its pleadings and briefs to this Court. Assuming that the Club is making\\n\\nthat argument, and assuming that such an injury could help confer standing in a pre-\\n\\nenforcement vagueness challenge, the Club would also need to demonstrate that the\\n\\nadditional expense incurred was fairly traceable to the alleged deficiencies in the\\n\\nchallenged provisions. Just as in Harrell, where the injury was self-censorship, the\\n\\nClub would have to establish that its injury was fairly traceable to the purportedly\\n\\nvague provisions by showing that those provisions were “at least arguably vague”\\n\\nas applied to it. 608 F.3d at 1254.\\n\\n In other words, our standing analysis requires us to take a “peek” at the merits\\n\\nof the Club’s vagueness claim. See Transp. Workers Union of Am., AFL-CIO v.\\n\\nTransp. Sec. Admin., 492 F.3d 471, 475 (D.C. Cir. 2007). Of course, while “standing\\n\\nin no way depends on the merits” of a plaintiff’s claim, “it often turns on the nature\\n\\nand source of the claim asserted.” Warth v. Seldin, 422 U.S. 490, 500 (1975). As\\n\\nwe recently observed, we “‘must not confuse weakness on the merits with absence\\n\\n\\n 19\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 20 of 23\\n\\n\\nof Article III standing.’” Moody v. Holman, 887 F.3d 1281, 1285 (11th Cir. 2018)\\n\\n(quoting Ariz. St. Leg. v. Ariz. Indep. Redistricting Comm’n, 135 S. Ct. 2652, 2663\\n\\n(2015)). In some circumstances, however, those “‘distinct concepts can be difficult\\n\\nto keep separate.’” Id. (quoting Bond v. United States, 564 U.S. 211, 218 (2011)).\\n\\n Here, the “nature and source” of the Club’s claim requires us to ask whether\\n\\nthe Ordinance’s challenged provisions are “at least arguably vague” as applied to it.\\n\\nHarrell, 608 F.3d at 1254. The answer to that question will allow us to assess\\n\\nwhether the Club’s apparent injury—the expense above and beyond that necessary\\n\\nto comply with a clear law—is “fairly traceable” to the Ordinance’s vagueness and,\\n\\naccordingly, whether the Club has standing to bring Count X of its complaint.\\n\\n But here, none of the challenged provisions are “at least arguably vague” as\\n\\napplied to the Club. As a result, the Club cannot show that a financial injury was\\n\\nfairly traceable to language it characterizes as “vague.”\\n\\n First, the Club contends that the provision requiring employees to present a\\n\\n“lawfully issued state or federal photo identification” and “one additional form of\\n\\nidentification” is vague. We disagree; it is not arguable that “people of ordinary\\n\\nintelligence” would fail to understand what the Ordinance requires. See Hill v.\\n\\nColorado, 530 U.S. 703, 732 (2000). The plain language of that provision\\n\\nunambiguously requires employees to provide two legal forms of identification\\n\\n\\n\\n\\n 20\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 21 of 23\\n\\n\\nissued by a state or federal government, that show the employee’s age and work\\n\\neligibility.\\n\\n The Ordinance’s requirements that the Club “verify the accuracy” of those\\n\\ndocuments and “confirm that the person is working or performing of his or her own\\n\\naccord and not being forced or intimidated into working or performing” are not\\n\\narguably vague, either. In fact, the Ordinance specifically instructs the Club as to\\n\\nhow it must execute these requirements: “by preparing and retaining a sworn\\n\\nstatement from the owner or manager” confirming that the employee is of age and\\n\\nis not being forced or intimidated into working. By its language, the Ordinance\\n\\nsimply requires the Club manager or owner to verify the accuracy of the documents\\n\\nand the employee’s willingness to work to the verifying official’s good-faith\\n\\nsatisfaction, so the verifying official is comfortable swearing to those circumstances.\\n\\nWe find nothing arguably vague about this aspect of the Ordinance as applied to the\\n\\nClub.\\n\\n Next, the Club suggests that the provision of the Ordinance that requires that\\n\\n“no person shall be allowed to enter” the establishment if the manager has not\\n\\n“verified” the person to be of age, work-eligible, and not working because of force\\n\\nor intimidation is vague because it could apply to patrons as well as employees. We\\n\\nare not persuaded. This provision clearly refers to employees and not to patrons.\\n\\nAfter all, even to the extent that the Ordinance’s language is unclear in the least, the\\n\\n\\n 21\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 22 of 23\\n\\n\\ntitle of the section makes it obvious that the requirement applies to “workers and\\n\\nperformers.” Essex Ins. Co. v. Zota, 466 F.3d 981, 989-90 (11th Cir. 2006).\\n\\n Finally, the Ordinance’s penalty provision stating that the city manager “may”\\n\\nrevoke the Club’s business license for up to one year is not arguably vague. The\\n\\nprovision specifies with “sufficient clarity” what the enhanced penalty is. See\\n\\nBeckles v. United States, 137 S. Ct. 886, 892 (2017). And although the provision\\n\\ngives the city manager considerable discretion to determine when, and to what\\n\\nextent, to impose that penalty, the sort of discretion conferred here does not render\\n\\nthe provision unconstitutionally vague. See id. at 893 (“[O]ur cases have never\\n\\nsuggested that a defendant can successfully challenge as vague a sentencing statute\\n\\nconferring discretion to select an appropriate sentence from within a statutory range,\\n\\neven when that discretion is unfettered.”).\\n\\n In short, the Club cannot clear the low bar of demonstrating that the\\n\\nchallenged provisions are at least arguably vague as applied to it. So even if it\\n\\nshowed that it had incurred some additional expense in an attempt to comply with\\n\\nthose provisions, and assuming that the additional expense constituted an injury for\\n\\npurposes of standing, that injury would not be fairly traceable to the purportedly\\n\\nvague language. And without an injury that is fairly traceable to the challenged\\n\\nprovisions, the Club lacks standing to argue that they are unconstitutionally vague.\\n\\nWe therefore affirm the district court’s dismissal of Count X.\\n\\n\\n 22\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 23 of 23\\n\\n\\n D.\\n\\n In sum, Counts VII-IX, XI, and XIII-XVI of the Club’s complaint are ripe for\\n\\nreview, so we reverse the district court’s order and remand the case for further\\n\\nproceedings on those counts. Count XII of the complaint is not ripe, and the Club\\n\\nlacks standing to argue in Count X that the Ordinance is unconstitutionally vague,\\n\\nso we affirm the district court’s order dismissing those counts.\\n\\n V.\\n\\n For these reasons, we affirm the dismissal of Counts III-VI, X, and XII of the\\n\\nClub’s complaint. But we reverse the dismissal of Counts VII-IX, XI, and XIII-XVI\\n\\nof that complaint and remand the case to the district court for further proceedings.\\n\\n AFFIRMED IN PART and REVERSED AND REMANDED IN PART.\\n\\n\\n\\n\\n 23\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4400503/\", \"author_raw\": \"ROSENBAUM, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"CARNES"},"judge2":{"kind":"string","value":"ROSENBAUM"},"judge3":{"kind":"string","value":"DUBINA"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4623250/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: CLUB MADONNA, INC., a Florida Corporation D.B.A. Club Madonna, Plaintiff - Appellant, v. CITY OF MIAMI BEACH, a Florida Municipal Corporation, Defendant - Appellee.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-24\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-13934 Date Filed: 05/24/2019 Page: 1 of 23\n\n\n [PUBLISH]\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-13934\n ________________________\n\n D.C. Docket No. 1:16-cv-25378-FAM\n\n\n\nCLUB MADONNA, INC.,\na Florida corporation d.b.a. Club Madonna,\n\n Plaintiff - Appellant,\n\nversus\n\nCITY OF MIAMI BEACH,\na Florida municipal corporation,\n\n Defendant - Appellee.\n\n ________________________\n\n Appeal from the United States District Court\n for the Southern District of Florida\n ________________________\n\n (May 24, 2019)\n\nBefore ED CARNES, Chief Judge, and ROSENBAUM and DUBINA, Circuit\nJudges.\n\nROSENBAUM, Circuit Judge:\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 2 of 23\n\n\n People often say that timing is everything. Hitting a home run? Timing.1\n\nComedy? Timing. 2 Winemaking? Timing. 3 Relationships? Timing. 4 Politics?\n\nTiming. 5\n\n And of course, timing is also important when it comes to Article III\n\njusticiability. File before the facts underpinning the claim have been sufficiently\n\ndeveloped, and a court must dismiss the claim because it is not ripe for the court’s\n\nreview. But wait until the claim has been resolved and the court can offer no further\n\nrelief, and a court must dismiss the claim because it is moot. Yet if a well-pleaded\n\nclaim falls in the sweet spot between ripeness and mootness and is otherwise\n\njusticiable, it states a “case or controversy” that the court must entertain.\n\n\n\n\n 1\n Babe Ruth said that a great hitter didn’t “swing any harder” or “with any longer arc than\nthe poorer hitters” but had “perfect timing sense.” George Herman Ruth, Babe Ruth’s Own Book\nof Baseball 178 (University of Nebraska Press, 1992) (1928); see also Nate Scott, “The 50 Greatest\nYogi Berra Quotes,” USA Today Sept. 23, 2015, available at\nhttps://ftw.usatoday.com/2015/09/the-50-greatest-yogi-berra-quotes (last visited May 24, 2019).\n 2\n According to Bob Hope, timing is “the essence of life and definitely of comedy.” William\nRobert Faith, Bob Hope: A Life in Comedy (Da Capo Press, Inc. 2009). Asked to comment further,\nhe reportedly paused and said, “We don’t have time for that.” Dena Kleiman, “Bob Hope Gives a\nLesson in Comedy,” New York Times, April 30, 1986, available at https://nyti.ms/2HLa4Mi.\n 3\n Timing’s importance in winemaking was central to the Paul Masson advertising campaign\nfrom the late 1970s, which featured Orson Welles informing the viewer that the company would\n“sell no wine before its time.” See Orson Welles for Paul Masson Wine (April 2, 1979), YouTube\n(May 14, 2009), https://youtu.be/oSs6DcA6dFI, (last visited May 24, 2019).\n 4\n Just ask Mila Kunis and Ashton Kutcher. They married in 2015, over a decade and a half\nafter their first kiss—as actors in the pilot episode of That ‘70s Show. Stephanie Petit, “#TBT:\nMila Kunis and Ashton Kutcher First Kissed on That 70’s Show,” People (July 21, 2016),\nhttps://people.com/tv/mila-kunis-and-ashton-kutcher-recall-first-kiss-on-that-70s-show/ (last\nvisited May 24, 2019).\n 5\n Pierre Trudeau is credited as saying that timing was the “essential ingredient” of politics.\nSee The Wordsworth Dictionary of Quotations 439 (Connie Robertson, ed.,Wordsworth 1997).\n 2\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 3 of 23\n\n\n Here, Appellant Club Madonna, Inc. (the “Club”), a fully-nude strip club in\n\nthe City of Miami Beach (the “City”), filed several claims against the City,\n\nchallenging administrative action it had taken against the Club, the laws authorizing\n\nthat action, and ordinances the City later enacted that regulate the fully nude strip-\n\nclub business. The district court dismissed all sixteen of the Club’s claims, six\n\nbecause they did not state a claim and ten because they were not yet ripe for the\n\ncourt’s review.\n\n The Club appealed the district court’s dismissal as it pertains to all but Counts\n\nI, II, and part of Count VI. We agree that Counts III through VI failed to state claims.\n\nWe also agree that one of the remaining claims was not ripe. And we affirm the\n\ndistrict court’s dismissal of one more of those claims because the Club lacks standing\n\nto pursue it. But we conclude that the eight remaining appealed claims were ripe for\n\nthe district court’s review and therefore reverse and remand to the district court for\n\nfurther proceedings.\n\n I.\n\n The catalyst for this case arose out of events occurring on January 6, 2014.\n\nOn that date, police executed a search warrant at the Club. The affidavit supporting\n\nthe warrant application described a police investigation into the disappearance of a\n\n13-year-old girl. Among other information, it asserted that the girl had been\n\ntrafficked by various people, including a woman who herself danced at the Club and\n\n\n 3\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 4 of 23\n\n\nwho forced the girl to dance, fully nude, at the Club on several occasions. According\n\nto the affidavit, the Club did not require the girl to provide it with identification to\n\nverify her age, and the girl did not offer the Club any identification before\n\nperforming. The affidavit further attested that the woman and her cohorts coerced\n\nthe girl to turn over to them any money she earned working at the Club, under threat\n\nand actions of physical abuse.\n\n On January 10, 2014, the City’s city manager found, based on the search\n\nwarrant, that the conditions at the Club constituted an emergency and immediately\n\nsuspended the Club’s business license. 6 The City scheduled a hearing on that\n\nsuspension, to be held before a special master on February 5, 2014. Before the\n\nhearing, though, the Club and the City reached a compromise under which the Club\n\nagreed to institute measures to ensure that similar events would not happen again,\n\nand the City agreed to return the Club’s business license.\n\n Following these events, the City passed two ordinances regulating nude dance\n\nestablishments, City of Miami Beach Ordinance Nos. 2015-3917 and 2015-3926\n\n(collectively, the “Ordinance”). The Ordinance remains in effect and contains three\n\nsections.\n\n\n\n\n 6\n Strictly speaking, the City suspended the Club’s Business Tax Receipt and its Certificate\nof Use for the building. The parties and district court variously used the terms “occupational\nlicenses” and “business license” to describe these items. For simplicity, we refer to them\ncollectively simply as the Club’s “business license.”\n 4\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 5 of 23\n\n\n First, Section 18-913 requires nude dance establishments such as the Club to\n\ncheck the age and work eligibility of “any worker or performer” by requiring that\n\nthey “provide proof of an original, lawfully issued state or federal photo\n\nidentification, and one additional form of identification.” The owner or manager of\n\nthe establishment must also “[v]erify the accuracy” of the documents by making a\n\n“sworn statement . . . confirming that the individual performer is at least 18 years of\n\nage.” In the same sworn statement, the owner or manager must “[c]onfirm” that the\n\nworker is “performing of her or his own accord, and is not being forced or\n\nintimidated into performing or working.” Code of the City of Miami Beach § 18-\n\n913. Section 18-913 also requires the business to keep a log of workers as they enter\n\nand exit the premises and to make all of the required documentation available “for\n\ninspection by the city upon demand.” Id.\n\n Next, under Section 18-914, nude dance establishments must “[p]rovide direct\n\nmonetary or non-monetary compensation to any worker or performer” and “maintain\n\ndocumentary proof” that the compensation “was directly received by the worker or\n\nperformer.” Code of the City of Miami Beach § 18-914. As with Section 18-913,\n\nSection 18-914 requires the business to maintain records of its compliance, and the\n\nCity enjoys “a right to request and inspect the records for any and all workers or\n\nperformers.” Id.\n\n\n\n\n 5\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 6 of 23\n\n\n Finally, Section 18-915 describes the penalties for failure to comply with the\n\nrequirements of Sections 18-913 and 18-914. For a first, second, and third offense\n\nwithin specified time periods, a business shall be fined $5,000, $10,000, and\n\n$20,000, respectively. For a second offense within three years, the City will shut\n\ndown the business for three months. And a third offense allows the City to exercise\n\nits discretion to close the business for up to a year. Code of the City of Miami Beach\n\n§ 18-915. An establishment charged with violating the ordinance has a right to an\n\nadministrative hearing and may appeal the decision to “a court of competent\n\njurisdiction.” Id.\n\n So far, the City has not alleged that the Club has fallen short of compliance\n\nwith the Ordinance.\n\n II.\n\n Displeased with the City’s activities after the execution of the search warrant,\n\nthe Club filed a complaint against the City. The complaint contains multiple and\n\nvaried constitutional-law claims that might inspire a law-school professor writing a\n\nfinal exam. We catalogue them below.\n\n Counts I through VI all concern the City’s actions in response to the execution\n\nof the search warrant and challenge laws existing at that time, before the enactment\n\nof the new Ordinance. More specifically, Count I presented a facial challenge to the\n\nordinances that authorized the City to close the Club on an emergency basis and\n\n\n 6\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 7 of 23\n\n\nasserts that they impose an unlawful prior restraint under the First Amendment;\n\nCount II lodges the same argument, only as applied to the Club. And Count III\n\nalleges that these ordinances are facially unconstitutional under the Due Process\n\nClause. Count IV contests the facial constitutionality of the City’s post-deprivation\n\nprocedures in particular under the Due Process Clause; Count V makes the same\n\nargument as applied to the Club. Count VI asserts that the City’s use of the local\n\nlaws to suspend its business license violated the First Amendment and the Due\n\nProcess Clause because, according to the complaint, the City acted in bad faith and\n\nfor retaliatory reasons.\n\n Counts VII through XVI concern the legality of the Ordinance enacted in the\n\nwake of the police investigation. Count VII contends that the Ordinance imposes an\n\nunconstitutional burden on the Club’s First Amendment rights. Count VIII alleges\n\nthat the Ordinance is an unconstitutional tax on speech. Count IX challenges the\n\nOrdinance as a violation of the Equal Protection Clause. Count X argues that the\n\nOrdinance is unconstitutionally vague. Count XI posits that the Ordinance violates\n\nthe Contract Clause. Count XII takes issue with the penalty provision, claiming it\n\nviolates the Eighth Amendment. Counts XIII, XIV, and XV allege that the\n\nOrdinance is preempted by state and federal laws. And finally, Count XVI contends\n\nthat the inspection provision of the Ordinance violates the Fourth Amendment.\n\n\n\n\n 7\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 8 of 23\n\n\n In response to the Club’s complaint, the City moved to dismiss the case. To\n\nsupport its motion, the City attached the search warrant (complete with the\n\nsupporting search-warrant affidavit) that prompted its actions, the order suspending\n\nthe Club’s business license, and the order offering to reinstate the Club’s business\n\nlicense under a negotiated compromise.\n\n As for its legal argument, the City asserted that the complaint should be\n\ndismissed because the Club lacked standing to bring any of its claims. Besides that,\n\nthe City continued, Counts I through VI were moot, and Counts VII through XVI\n\nwere not ripe for the court’s review. In the alternative, the City argued that the Club\n\nfailed to state any claim.\n\n In response, the Club contended that its claims were justiciable and viable.\n\n The district court granted the City’s motion to dismiss. It reasoned that Counts\n\nI through VI were justiciable but did not state claims. Specifically, as to Counts I,\n\nII, and VI of the complaint, the court said that the Ordinance satisfied United States\n\nv. O’Brien’s, 391 U.S. 367 (1968), test for content-neutral laws that incidentally\n\nregulate expressive conduct and thus did not violate the Club’s First Amendment\n\nrights.7 As for Counts III-VI of the complaint, the court noted that the Club had not\n\ncontested the City’s suspension of its business license at the scheduled\n\n\n 7\n The Club does not appeal the district court’s dismissal of Counts I and II, nor the dismissal\nof Count VI to the extent it asserts a violation of the First Amendment. As a result, we do not\naddress those claims.\n 8\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 9 of 23\n\n\nadministrative hearing and had not availed itself of the other process available to it\n\nunder state and local law. Therefore, the court concluded, those due-process counts\n\nwere “incognizable” under McKinney v. Pate, 20 F.3d 1550 (11th Cir. 1994) (en\n\nbanc).\n\n Next, the Court reasoned that Counts VII through XVI were not ripe for the\n\ncourt’s review. Specifically, the court observed that “the Club ha[d] not been\n\ncharged with violating” the Ordinance. “Without the facts of a particular violation,”\n\nthe court explained, it could “only speculate as to whether the Club will be charged\n\nunder the ordinances and if so, whether it will be subject to specific penalties.” On\n\nthat basis, the district court concluded that “the Club ha[d] not satisfied the ‘fitness’\n\nprong of the ripeness inquiry.” In addition, the district court determined that the\n\nClub would not suffer a substantial hardship as a result of postponing adjudication\n\nbecause the law did not “prohibit the Club from providing fully nude dance\n\nentertainment to its adult patrons.”\n\n This appeal followed.\n\n III.\n\n We review de novo the grant of a motion to dismiss for failure to state a claim,\n\naccepting the allegations in the complaint as true and construing them in the light\n\nmost favorable to the plaintiff. Fourth Estate Pub. Benefit Corp. v. Wall-Street.com,\n\nLLC, 856 F.3d 1338, 1339 (11th Cir. 2017). We likewise review de novo questions\n\n\n 9\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 10 of 23\n\n\nconcerning our subject matter jurisdiction, including standing and ripeness. Elend\n\nv. Basham, 471 F.3d 1199, 1204 (11th Cir. 2006). And we can affirm on any basis\n\nsupported by the record, regardless of whether the district court decided the case on\n\nthat basis. Jarvela v. Crete Carrier Corp., 776 F.3d 822, 828 (11th Cir. 2015).\n\n IV.\n\n After careful consideration of the record and oral argument, we affirm in part\n\nand reverse and remand in part. We agree with the district court that Counts III\n\nthrough VI (the due-process part of that claim) 8 of the Club’s complaint failed to\n\nstate claims. We also agree that Count XII was not ripe for the court’s review. And\n\nwe affirm the dismissal of Count X because the Club lacked standing. We conclude,\n\nhowever, that the remaining counts are ripe for the court’s review, so we reverse the\n\ncourt’s order on those counts and remand the case for further proceedings.\n\n A.\n\n We begin with Counts III-VI of the Club’s complaint. As we have noted, the\n\ndistrict court dismissed these counts for failure to state a claim, citing McKinney.\n\nWe agree.\n\n To state a claim under 42 U.S.C § 1983, a plaintiff must allege facts showing\n\nthat the defendant, acting under color of state law, deprived it of a right protected by\n\nthe Constitution or by a federal statute. Where, as here, the plaintiff alleges a\n\n\n 8\n See supra at n.7.\n 10\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 11 of 23\n\n\nviolation of procedural due process, the plaintiff must show the deprivation of that\n\nprotected interest “without due process of law.” Zinermon v. Burch, 494 U.S. 113,\n\n123 (1990) (emphasis in original). And a violation of procedural due process does\n\nnot “become complete ‘unless and until the state refuses to provide due process.’”\n\nMcKinney, 20 F.3d at 1562 (quoting Zinermon, 494 U.S. at 123). Here, all of the\n\nClub’s due-process claims in Counts III-VI fail for the same reason: they all lack\n\nthe essential element that the state refused to provide the Club with due process.\n\n First, the Club was not entitled to a pre-suspension hearing. Though Mathews\n\nv. Eldridge, 424 U.S. 319 (1976), can require pre-deprivation process, that is not\n\nalways the case. Among other such circumstances, the Supreme Court has\n\ndetermined that pre-deprivation process is not required when a need for “quick\n\naction” exists. Zinermon v. Burch, 494 U.S. 113, 128 (1990) (citation and quotation\n\nmarks omitted). As we have noted, here, law enforcement had probable cause to\n\nbelieve that the Club had allowed a 13-year-old trafficked girl to perform under\n\nthreat and act of physical abuse. These circumstances raised immediate and pressing\n\nconcerns for the physical and mental health and welfare of minors. So the City\n\nreasonably concluded that there was a need for “quick action,” and no pre-\n\ndeprivation process was required.\n\n We therefore turn to the post-deprivation process the Club received. Upon\n\nthe City’s decision to suspend its business license, the Club was entitled to a hearing\n\n\n 11\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 12 of 23\n\n\non an emergency basis before a special master to challenge that decision. Code of\n\nthe City of Miami Beach §§ 14-406(b); 102-383. At the conclusion of that hearing,\n\nthe special master would have issued a final administrative order. Code of the City\n\nof Miami Beach §§ 14-408(c); 102-385(c). Then, the Club would have been entitled\n\nto appeal that order to the Florida State Circuit Court. Fla. Stat. Ann. § 162.11; see\n\nalso Fla Stat. Ann. § 162.03 (providing that special masters with enforcement\n\nauthority have the “same status” as enforcement boards for purposes of Fla. Stat.\n\nAnn. § 162); Code of the City of Miami Beach §§ 30-2, 30-77 (stating that the City\n\nhas given special masters enforcement authority and that the special masters’\n\ndecisions are appealable to the circuit court under Fla. Stat. Ann. § 162.11).\n\n As we have previously held, that procedure satisfies due process because the\n\nFlorida Circuit Court has the power to remedy any procedural deficiencies and cure\n\nviolations of due process. McKinney, 20 F.3d at 1564.\n\n Here, the Club did not avail itself of the processes provided by local and state\n\nlaw. Instead of presenting its arguments to the special master and Florida Circuit\n\nCourt, the Club brought its arguments to federal court. For that reason, we cannot\n\nsay that the City or state refused to provide the Club with due process. The district\n\n\n\n\n 12\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 13 of 23\n\n\ncourt was therefore correct to dismiss Counts III-VI of the Club’s complaint for\n\nfailure to state a claim. 9\n\n B.\n\n The district court dismissed Counts VII-XVI on the basis that they were not\n\nripe for review. Specifically, the court reasoned that the Club “ha[d] not been\n\ncharged with violating” the Ordinance and that the Club would not suffer a\n\nsubstantial hardship as a result of postponing adjudication of its claims, so the Club’s\n\nclaims were not ripe for review. We respectfully disagree.\n\n Article III limits the power of the federal courts to “cases” and\n\n“controversies.” U.S. Const. art III, § 2; see Lujan v. Defenders of Wildlife, 504 U.S.\n\n555, 559-60 (1992). One of the “landmarks” of that requirement is the doctrine of\n\nstanding, which requires that a party have suffered an “injury in fact,” that the party’s\n\ninjury is fairly traceable to the challenged action of the defendant, and that the injury\n\nwould “likely” be “redressed by a favorable decision.” Lujan, 504 U.S. at 560-61.\n\n But even when a claim meets the case-or-controversy requirement’s\n\nconstitutional demands, such as standing, we also recognize important prudential\n\n\n 9\n Because we hold that the district court’s dismissal of Counts III-VI of the complaint was\nproper under McKinney, we need not determine whether the district court appropriately relied on\nthe documents attached to the City’s motion to dismiss. Those documents are not relevant to the\nMcKinney issue. The search-warrant affidavit is the only one of the attached documents that we\nhave considered in this appeal, and we considered it only for purposes of recounting the\nbackground facts of the case. We may take notice of that document because its authenticity is not\nin question and it is central to the claims at issue. See Maxcess, Inc. v. Lucent Techs., Inc., 433\nF.3d 1337, 1340 n.3 (11th Cir. 2005); Horsley v. Feldt, 304 F.3d 1125, 1134 (11th Cir. 2002).\n 13\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 14 of 23\n\n\nlimitations on the kinds of cases that a court has power to decide. Nat’l Advert. Co.\n\nv. City of Miami, 402 F.3d 1335, 1338-39 (11th Cir. 2005). Those prudential\n\nconcerns “counsel judicial restraint” and prevent courts from “rendering\n\nimpermissible advisory opinions and wasting resources through review of potential\n\nor abstract disputes.” Id. at 1339. Based on these interests, courts decide only cases\n\nthat are ripe for their review. We determine ripeness, which addresses both\n\nconstitutional and prudential concerns, by evaluating “(1) the fitness of the issues\n\nfor judicial decision and (2) the hardship to the parties of withholding court\n\nconsideration.” Nat’l Advert. Co., 402 F.3d at 1339 (citing Abbott Lab. v. Gardner,\n\n387 U.S. 136, 148-49 (1967)).\n\n Concerning fitness for judicial decision, we ask whether the parties raise an\n\nissue that we can decide without further factual development and whether the\n\ninstitutional interests of the court and agency favor immediate review. Harrell v.\n\nThe Fla. Bar, 608 F.3d 1241, 1258 (11th Cir. 2010); Cheffer v. Reno, 55 F.3d 1517,\n\n1524 (11th Cir. 1995). As for “hardship,” litigants must show that they are “forced\n\nto choose between foregoing lawful activity and risking substantial legal sanctions.”\n\nCheffer, 55 F.3d at 1524 (citing Steffel v. Thompson, 415 U.S. 452, 462 (1974)); see\n\nalso Elend, 471 F.3d at 1211. If a claim is fit for judicial decision, that is end of the\n\ninquiry, and the matter is ripe, given that the absence of a “hardship” “cannot tip the\n\n\n\n\n 14\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 15 of 23\n\n\nbalance against judicial review” under those circumstances. See Harrell, 608 F.3d\n\nat 1259 (citation and internal quotation marks omitted).\n\n We assess ripeness on a claim-by-claim basis. A facial challenge presenting\n\na purely legal argument, for example, “is presumptively ripe for judicial review”\n\nbecause that type of argument does not rely on a developed factual record. Harris\n\nv. Mexican Specialty Foods, Inc., 564 F.3d 1301, 1308 (11th Cir. 2009). In contrast,\n\nan as-applied challenge “necessarily requires the development of a factual record for\n\nthe court to consider.” Id.\n\n Applying these principles here, we conclude that Counts VII, VIII, IX, XI,\n\nXIII, XIV, XV, and XVI of the Club’s complaint are ripe for review. To begin with,\n\nCounts XIII, XIV, and XV assert that the Ordinance was preempted by state and\n\nfederal law. Further factual development cannot assist in resolution of these facial\n\nchallenges, which raise purely legal issues. Nor do any institutional concerns of the\n\ncourt or the City render the issues unfit for review. Consequently, these claims are\n\nripe. Id. at 1308.\n\n Next, the Club’s as-applied challenges—asserting an unconstitutional burden\n\nand tax on speech (Counts VII and VIII), an Equal Protection violation (Count IX),\n\nand a Contract Clause violation (Count XI)—require no more factual development\n\nto be ripe for review. It is undisputed that the Club is subject to the Ordinance and\n\n\n\n\n 15\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 16 of 23\n\n\nis complying with its regulations. And that compliance is what forms the factual\n\nbasis of the Club’s as-applied arguments.\n\n To be sure, the Club does not contend that it was charged with violating the\n\nOrdinance or that it has suffered the Ordinance’s penalties. But that does not render\n\nthe claims in Counts VII, VIII, IX and XI unripe for the district court’s review. If\n\nthe Club were to fall short of any of the Ordinance’s requirements and the City were\n\nto charge it with a violation of the law, the resulting additional facts would shed no\n\nfurther light on whether compliance with the Ordinance is an unconstitutional\n\nburden on speech, a tax on speech, an equal-protection violation, or a Contract\n\nClause violation in the first place. For these same reasons, institutional concerns\n\nlikewise present no impediment to fitness for review. So Counts VII, VIII, IX, and\n\nXI are ripe for review. See Harrell, 608 F.3d at 1258; Cheffer, 55 F.3d at 1524.\n\n Count XVI is also fit for review. The Club claims that the Ordinance\n\nauthorizes the City to engage in warrantless searches in violation of the Fourth\n\nAmendment. That claim presents purely legal questions, such as (1) whether the\n\nOrdinance falls within the administrative-search exception, and if so, whether it\n\naffords the Club an opportunity to obtain pre-compliance review before a neutral\n\ndecisionmaker, and (2) whether the Club is part of a “closely regulated” industry,\n\nand if so, whether warrantless inspections are necessary to further a substantial\n\ngovernment interest and whether the Ordinance adequately constrains police\n\n\n 16\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 17 of 23\n\n\ndiscretion. See City of Los Angeles v. Patel, 135 S. Ct. 2243, 2452–56 (2015). As a\n\nresult, we need not wait for further facts, such as a warrantless search under the\n\nOrdinance, to occur to resolve this claim.\n\n As for Count XII, we agree with the district court that it is not ripe for review.\n\nCount XII alleges that that the Ordinance’s penalty provision violates the Eighth\n\nAmendment. But we have held that “Eighth Amendment challenges are generally\n\nnot ripe until the imposition, or immediately impending imposition, of a challenged\n\npunishment or fine.” Cheffer, 55 F.3d at 1523-24. The Club does not allege that the\n\nCity imposed a fine under that provision or that the imposition of a fine is\n\nimmediately forthcoming, so the district court correctly determined that the Club’s\n\nEighth Amendment argument is not ripe for review.\n\n C.\n\n Finally, we turn to Count X, which alleges that the Ordinance is\n\nunconstitutionally vague. The district court dismissed that claim as unripe, but we\n\naffirm for a different reason: the Club lacked standing to bring it. 10\n\n As we have noted, to have standing, a party must demonstrate that (1) it has\n\nsuffered, or imminently will suffer, an injury-in-fact; (2) the injury is fairly traceable\n\nto the operation of the challenged law; and (3) a favorable judgment is likely to\n\n\n 10\n Standing is a jurisdictional requirement that we are obligated to address sua sponte. See\nMurphy v. Dulay, 768 F.3d 1360, 1366 n.4 (11th Cir. 2014); Region 8 Forest Serv. Timber\nPurchasers Council v. Alcock, 993 F.2d 800, 806-807 (11th Cir. 1993).\n 17\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 18 of 23\n\n\nredress the injury. Wollschlaeger v. Governor, 848 F.3d 1293, 1303-1304 (11th Cir.\n\n2017) (en banc); Harrell, 608 F.3d at 1254. Though we “most loosely” apply the\n\ninjury-in-fact requirement when a claim involves First Amendment rights, we\n\nnevertheless conclude that the Club lacked standing to argue that the Ordinance is\n\nunconstitutionally vague. Even if the Club could show that it had suffered, or will\n\nimminently suffer, an injury in fact, it cannot demonstrate that the injury is fairly\n\ntraceable to the Ordinance’s purported imprecision.\n\n In the first step of our standing analysis, we ask whether the Club has suffered,\n\nor imminently will suffer, an injury in fact. We have previously held that a party\n\nmight satisfy this prong by showing self-censorship. See Wollschlaeger, 848 F.3d\n\nat 1304-1305; Harrell, 608 F.3d at 1253. Here, though, it is undisputed that the Club\n\nis not self-censoring, but rather, is continuing to carry on its business, apparently in\n\ncompliance with the Ordinance.\n\n The Club might also suggest that the Ordinance contains vague language that\n\ncauses it to fear that the City will enforce it arbitrarily, and is thereby injured. But\n\nmere fear of unconstitutional action alone on the part of the City is too speculative\n\nan injury to confer standing to the Club. See JW v. Birmingham Bd. Of Educ., 904\n\nF.3d 1248, 1264 (11th Cir. 2018); 31 Foster Children v. Bush, 329 F.3d 1255, 1263\n\n(11th Cir. 2003). That is especially true here, since the Club has apparently been\n\n\n\n\n 18\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 19 of 23\n\n\nsuccessfully complying with the Ordinance without incident since it was\n\npromulgated roughly three years ago.\n\n The Club’s most promising standing argument would be that it unnecessarily\n\nincurred additional expenses in an effort to comply with what it says is an\n\nunconstitutionally vague law, above and beyond the expense that would have been\n\nnecessary to comply with a law that was not vague. The Club suggested that\n\nargument in its pleadings and briefs to this Court. Assuming that the Club is making\n\nthat argument, and assuming that such an injury could help confer standing in a pre-\n\nenforcement vagueness challenge, the Club would also need to demonstrate that the\n\nadditional expense incurred was fairly traceable to the alleged deficiencies in the\n\nchallenged provisions. Just as in Harrell, where the injury was self-censorship, the\n\nClub would have to establish that its injury was fairly traceable to the purportedly\n\nvague provisions by showing that those provisions were “at least arguably vague”\n\nas applied to it. 608 F.3d at 1254.\n\n In other words, our standing analysis requires us to take a “peek” at the merits\n\nof the Club’s vagueness claim. See Transp. Workers Union of Am., AFL-CIO v.\n\nTransp. Sec. Admin., 492 F.3d 471, 475 (D.C. Cir. 2007). Of course, while “standing\n\nin no way depends on the merits” of a plaintiff’s claim, “it often turns on the nature\n\nand source of the claim asserted.” Warth v. Seldin, 422 U.S. 490, 500 (1975). As\n\nwe recently observed, we “‘must not confuse weakness on the merits with absence\n\n\n 19\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 20 of 23\n\n\nof Article III standing.’” Moody v. Holman, 887 F.3d 1281, 1285 (11th Cir. 2018)\n\n(quoting Ariz. St. Leg. v. Ariz. Indep. Redistricting Comm’n, 135 S. Ct. 2652, 2663\n\n(2015)). In some circumstances, however, those “‘distinct concepts can be difficult\n\nto keep separate.’” Id. (quoting Bond v. United States, 564 U.S. 211, 218 (2011)).\n\n Here, the “nature and source” of the Club’s claim requires us to ask whether\n\nthe Ordinance’s challenged provisions are “at least arguably vague” as applied to it.\n\nHarrell, 608 F.3d at 1254. The answer to that question will allow us to assess\n\nwhether the Club’s apparent injury—the expense above and beyond that necessary\n\nto comply with a clear law—is “fairly traceable” to the Ordinance’s vagueness and,\n\naccordingly, whether the Club has standing to bring Count X of its complaint.\n\n But here, none of the challenged provisions are “at least arguably vague” as\n\napplied to the Club. As a result, the Club cannot show that a financial injury was\n\nfairly traceable to language it characterizes as “vague.”\n\n First, the Club contends that the provision requiring employees to present a\n\n“lawfully issued state or federal photo identification” and “one additional form of\n\nidentification” is vague. We disagree; it is not arguable that “people of ordinary\n\nintelligence” would fail to understand what the Ordinance requires. See Hill v.\n\nColorado, 530 U.S. 703, 732 (2000). The plain language of that provision\n\nunambiguously requires employees to provide two legal forms of identification\n\n\n\n\n 20\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 21 of 23\n\n\nissued by a state or federal government, that show the employee’s age and work\n\neligibility.\n\n The Ordinance’s requirements that the Club “verify the accuracy” of those\n\ndocuments and “confirm that the person is working or performing of his or her own\n\naccord and not being forced or intimidated into working or performing” are not\n\narguably vague, either. In fact, the Ordinance specifically instructs the Club as to\n\nhow it must execute these requirements: “by preparing and retaining a sworn\n\nstatement from the owner or manager” confirming that the employee is of age and\n\nis not being forced or intimidated into working. By its language, the Ordinance\n\nsimply requires the Club manager or owner to verify the accuracy of the documents\n\nand the employee’s willingness to work to the verifying official’s good-faith\n\nsatisfaction, so the verifying official is comfortable swearing to those circumstances.\n\nWe find nothing arguably vague about this aspect of the Ordinance as applied to the\n\nClub.\n\n Next, the Club suggests that the provision of the Ordinance that requires that\n\n“no person shall be allowed to enter” the establishment if the manager has not\n\n“verified” the person to be of age, work-eligible, and not working because of force\n\nor intimidation is vague because it could apply to patrons as well as employees. We\n\nare not persuaded. This provision clearly refers to employees and not to patrons.\n\nAfter all, even to the extent that the Ordinance’s language is unclear in the least, the\n\n\n 21\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 22 of 23\n\n\ntitle of the section makes it obvious that the requirement applies to “workers and\n\nperformers.” Essex Ins. Co. v. Zota, 466 F.3d 981, 989-90 (11th Cir. 2006).\n\n Finally, the Ordinance’s penalty provision stating that the city manager “may”\n\nrevoke the Club’s business license for up to one year is not arguably vague. The\n\nprovision specifies with “sufficient clarity” what the enhanced penalty is. See\n\nBeckles v. United States, 137 S. Ct. 886, 892 (2017). And although the provision\n\ngives the city manager considerable discretion to determine when, and to what\n\nextent, to impose that penalty, the sort of discretion conferred here does not render\n\nthe provision unconstitutionally vague. See id. at 893 (“[O]ur cases have never\n\nsuggested that a defendant can successfully challenge as vague a sentencing statute\n\nconferring discretion to select an appropriate sentence from within a statutory range,\n\neven when that discretion is unfettered.”).\n\n In short, the Club cannot clear the low bar of demonstrating that the\n\nchallenged provisions are at least arguably vague as applied to it. So even if it\n\nshowed that it had incurred some additional expense in an attempt to comply with\n\nthose provisions, and assuming that the additional expense constituted an injury for\n\npurposes of standing, that injury would not be fairly traceable to the purportedly\n\nvague language. And without an injury that is fairly traceable to the challenged\n\nprovisions, the Club lacks standing to argue that they are unconstitutionally vague.\n\nWe therefore affirm the district court’s dismissal of Count X.\n\n\n 22\n\f Case: 17-13934 Date Filed: 05/24/2019 Page: 23 of 23\n\n\n D.\n\n In sum, Counts VII-IX, XI, and XIII-XVI of the Club’s complaint are ripe for\n\nreview, so we reverse the district court’s order and remand the case for further\n\nproceedings on those counts. Count XII of the complaint is not ripe, and the Club\n\nlacks standing to argue in Count X that the Ordinance is unconstitutionally vague,\n\nso we affirm the district court’s order dismissing those counts.\n\n V.\n\n For these reasons, we affirm the dismissal of Counts III-VI, X, and XII of the\n\nClub’s complaint. But we reverse the dismissal of Counts VII-IX, XI, and XIII-XVI\n\nof that complaint and remand the case to the district court for further proceedings.\n\n AFFIRMED IN PART and REVERSED AND REMANDED IN PART.\n\n\n\n\n 23\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: CLUB MADONNA, INC., a Florida Corporation D.B.A. Club Madonna, Plaintiff - Appellant, v. CITY OF MIAMI BEACH, a Florida Municipal Corporation, Defendant - Appellee.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-24\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-13934 Date Filed: 05/24/2019 Page: 1 of 23\\n\\n\\n [PUBLISH]\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-13934\\n ________________________\\n\\n D.C. Docket No. 1:16-cv-25378-FAM\\n\\n\\n\\nCLUB MADONNA, INC.,\\na Florida corporation d.b.a. Club Madonna,\\n\\n Plaintiff - Appellant,\\n\\nversus\\n\\nCITY OF MIAMI BEACH,\\na Florida municipal corporation,\\n\\n Defendant - Appellee.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 24, 2019)\\n\\nBefore ED CARNES, Chief Judge, and ROSENBAUM and DUBINA, Circuit\\nJudges.\\n\\nROSENBAUM, Circuit Judge:\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 2 of 23\\n\\n\\n People often say that timing is everything. Hitting a home run? Timing.1\\n\\nComedy? Timing. 2 Winemaking? Timing. 3 Relationships? Timing. 4 Politics?\\n\\nTiming. 5\\n\\n And of course, timing is also important when it comes to Article III\\n\\njusticiability. File before the facts underpinning the claim have been sufficiently\\n\\ndeveloped, and a court must dismiss the claim because it is not ripe for the court’s\\n\\nreview. But wait until the claim has been resolved and the court can offer no further\\n\\nrelief, and a court must dismiss the claim because it is moot. Yet if a well-pleaded\\n\\nclaim falls in the sweet spot between ripeness and mootness and is otherwise\\n\\njusticiable, it states a “case or controversy” that the court must entertain.\\n\\n\\n\\n\\n 1\\n Babe Ruth said that a great hitter didn’t “swing any harder” or “with any longer arc than\\nthe poorer hitters” but had “perfect timing sense.” George Herman Ruth, Babe Ruth’s Own Book\\nof Baseball 178 (University of Nebraska Press, 1992) (1928); see also Nate Scott, “The 50 Greatest\\nYogi Berra Quotes,” USA Today Sept. 23, 2015, available at\\nhttps://ftw.usatoday.com/2015/09/the-50-greatest-yogi-berra-quotes (last visited May 24, 2019).\\n 2\\n According to Bob Hope, timing is “the essence of life and definitely of comedy.” William\\nRobert Faith, Bob Hope: A Life in Comedy (Da Capo Press, Inc. 2009). Asked to comment further,\\nhe reportedly paused and said, “We don’t have time for that.” Dena Kleiman, “Bob Hope Gives a\\nLesson in Comedy,” New York Times, April 30, 1986, available at https://nyti.ms/2HLa4Mi.\\n 3\\n Timing’s importance in winemaking was central to the Paul Masson advertising campaign\\nfrom the late 1970s, which featured Orson Welles informing the viewer that the company would\\n“sell no wine before its time.” See Orson Welles for Paul Masson Wine (April 2, 1979), YouTube\\n(May 14, 2009), https://youtu.be/oSs6DcA6dFI, (last visited May 24, 2019).\\n 4\\n Just ask Mila Kunis and Ashton Kutcher. They married in 2015, over a decade and a half\\nafter their first kiss—as actors in the pilot episode of That ‘70s Show. Stephanie Petit, “#TBT:\\nMila Kunis and Ashton Kutcher First Kissed on That 70’s Show,” People (July 21, 2016),\\nhttps://people.com/tv/mila-kunis-and-ashton-kutcher-recall-first-kiss-on-that-70s-show/ (last\\nvisited May 24, 2019).\\n 5\\n Pierre Trudeau is credited as saying that timing was the “essential ingredient” of politics.\\nSee The Wordsworth Dictionary of Quotations 439 (Connie Robertson, ed.,Wordsworth 1997).\\n 2\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 3 of 23\\n\\n\\n Here, Appellant Club Madonna, Inc. (the “Club”), a fully-nude strip club in\\n\\nthe City of Miami Beach (the “City”), filed several claims against the City,\\n\\nchallenging administrative action it had taken against the Club, the laws authorizing\\n\\nthat action, and ordinances the City later enacted that regulate the fully nude strip-\\n\\nclub business. The district court dismissed all sixteen of the Club’s claims, six\\n\\nbecause they did not state a claim and ten because they were not yet ripe for the\\n\\ncourt’s review.\\n\\n The Club appealed the district court’s dismissal as it pertains to all but Counts\\n\\nI, II, and part of Count VI. We agree that Counts III through VI failed to state claims.\\n\\nWe also agree that one of the remaining claims was not ripe. And we affirm the\\n\\ndistrict court’s dismissal of one more of those claims because the Club lacks standing\\n\\nto pursue it. But we conclude that the eight remaining appealed claims were ripe for\\n\\nthe district court’s review and therefore reverse and remand to the district court for\\n\\nfurther proceedings.\\n\\n I.\\n\\n The catalyst for this case arose out of events occurring on January 6, 2014.\\n\\nOn that date, police executed a search warrant at the Club. The affidavit supporting\\n\\nthe warrant application described a police investigation into the disappearance of a\\n\\n13-year-old girl. Among other information, it asserted that the girl had been\\n\\ntrafficked by various people, including a woman who herself danced at the Club and\\n\\n\\n 3\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 4 of 23\\n\\n\\nwho forced the girl to dance, fully nude, at the Club on several occasions. According\\n\\nto the affidavit, the Club did not require the girl to provide it with identification to\\n\\nverify her age, and the girl did not offer the Club any identification before\\n\\nperforming. The affidavit further attested that the woman and her cohorts coerced\\n\\nthe girl to turn over to them any money she earned working at the Club, under threat\\n\\nand actions of physical abuse.\\n\\n On January 10, 2014, the City’s city manager found, based on the search\\n\\nwarrant, that the conditions at the Club constituted an emergency and immediately\\n\\nsuspended the Club’s business license. 6 The City scheduled a hearing on that\\n\\nsuspension, to be held before a special master on February 5, 2014. Before the\\n\\nhearing, though, the Club and the City reached a compromise under which the Club\\n\\nagreed to institute measures to ensure that similar events would not happen again,\\n\\nand the City agreed to return the Club’s business license.\\n\\n Following these events, the City passed two ordinances regulating nude dance\\n\\nestablishments, City of Miami Beach Ordinance Nos. 2015-3917 and 2015-3926\\n\\n(collectively, the “Ordinance”). The Ordinance remains in effect and contains three\\n\\nsections.\\n\\n\\n\\n\\n 6\\n Strictly speaking, the City suspended the Club’s Business Tax Receipt and its Certificate\\nof Use for the building. The parties and district court variously used the terms “occupational\\nlicenses” and “business license” to describe these items. For simplicity, we refer to them\\ncollectively simply as the Club’s “business license.”\\n 4\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 5 of 23\\n\\n\\n First, Section 18-913 requires nude dance establishments such as the Club to\\n\\ncheck the age and work eligibility of “any worker or performer” by requiring that\\n\\nthey “provide proof of an original, lawfully issued state or federal photo\\n\\nidentification, and one additional form of identification.” The owner or manager of\\n\\nthe establishment must also “[v]erify the accuracy” of the documents by making a\\n\\n“sworn statement . . . confirming that the individual performer is at least 18 years of\\n\\nage.” In the same sworn statement, the owner or manager must “[c]onfirm” that the\\n\\nworker is “performing of her or his own accord, and is not being forced or\\n\\nintimidated into performing or working.” Code of the City of Miami Beach § 18-\\n\\n913. Section 18-913 also requires the business to keep a log of workers as they enter\\n\\nand exit the premises and to make all of the required documentation available “for\\n\\ninspection by the city upon demand.” Id.\\n\\n Next, under Section 18-914, nude dance establishments must “[p]rovide direct\\n\\nmonetary or non-monetary compensation to any worker or performer” and “maintain\\n\\ndocumentary proof” that the compensation “was directly received by the worker or\\n\\nperformer.” Code of the City of Miami Beach § 18-914. As with Section 18-913,\\n\\nSection 18-914 requires the business to maintain records of its compliance, and the\\n\\nCity enjoys “a right to request and inspect the records for any and all workers or\\n\\nperformers.” Id.\\n\\n\\n\\n\\n 5\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 6 of 23\\n\\n\\n Finally, Section 18-915 describes the penalties for failure to comply with the\\n\\nrequirements of Sections 18-913 and 18-914. For a first, second, and third offense\\n\\nwithin specified time periods, a business shall be fined $5,000, $10,000, and\\n\\n$20,000, respectively. For a second offense within three years, the City will shut\\n\\ndown the business for three months. And a third offense allows the City to exercise\\n\\nits discretion to close the business for up to a year. Code of the City of Miami Beach\\n\\n§ 18-915. An establishment charged with violating the ordinance has a right to an\\n\\nadministrative hearing and may appeal the decision to “a court of competent\\n\\njurisdiction.” Id.\\n\\n So far, the City has not alleged that the Club has fallen short of compliance\\n\\nwith the Ordinance.\\n\\n II.\\n\\n Displeased with the City’s activities after the execution of the search warrant,\\n\\nthe Club filed a complaint against the City. The complaint contains multiple and\\n\\nvaried constitutional-law claims that might inspire a law-school professor writing a\\n\\nfinal exam. We catalogue them below.\\n\\n Counts I through VI all concern the City’s actions in response to the execution\\n\\nof the search warrant and challenge laws existing at that time, before the enactment\\n\\nof the new Ordinance. More specifically, Count I presented a facial challenge to the\\n\\nordinances that authorized the City to close the Club on an emergency basis and\\n\\n\\n 6\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 7 of 23\\n\\n\\nasserts that they impose an unlawful prior restraint under the First Amendment;\\n\\nCount II lodges the same argument, only as applied to the Club. And Count III\\n\\nalleges that these ordinances are facially unconstitutional under the Due Process\\n\\nClause. Count IV contests the facial constitutionality of the City’s post-deprivation\\n\\nprocedures in particular under the Due Process Clause; Count V makes the same\\n\\nargument as applied to the Club. Count VI asserts that the City’s use of the local\\n\\nlaws to suspend its business license violated the First Amendment and the Due\\n\\nProcess Clause because, according to the complaint, the City acted in bad faith and\\n\\nfor retaliatory reasons.\\n\\n Counts VII through XVI concern the legality of the Ordinance enacted in the\\n\\nwake of the police investigation. Count VII contends that the Ordinance imposes an\\n\\nunconstitutional burden on the Club’s First Amendment rights. Count VIII alleges\\n\\nthat the Ordinance is an unconstitutional tax on speech. Count IX challenges the\\n\\nOrdinance as a violation of the Equal Protection Clause. Count X argues that the\\n\\nOrdinance is unconstitutionally vague. Count XI posits that the Ordinance violates\\n\\nthe Contract Clause. Count XII takes issue with the penalty provision, claiming it\\n\\nviolates the Eighth Amendment. Counts XIII, XIV, and XV allege that the\\n\\nOrdinance is preempted by state and federal laws. And finally, Count XVI contends\\n\\nthat the inspection provision of the Ordinance violates the Fourth Amendment.\\n\\n\\n\\n\\n 7\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 8 of 23\\n\\n\\n In response to the Club’s complaint, the City moved to dismiss the case. To\\n\\nsupport its motion, the City attached the search warrant (complete with the\\n\\nsupporting search-warrant affidavit) that prompted its actions, the order suspending\\n\\nthe Club’s business license, and the order offering to reinstate the Club’s business\\n\\nlicense under a negotiated compromise.\\n\\n As for its legal argument, the City asserted that the complaint should be\\n\\ndismissed because the Club lacked standing to bring any of its claims. Besides that,\\n\\nthe City continued, Counts I through VI were moot, and Counts VII through XVI\\n\\nwere not ripe for the court’s review. In the alternative, the City argued that the Club\\n\\nfailed to state any claim.\\n\\n In response, the Club contended that its claims were justiciable and viable.\\n\\n The district court granted the City’s motion to dismiss. It reasoned that Counts\\n\\nI through VI were justiciable but did not state claims. Specifically, as to Counts I,\\n\\nII, and VI of the complaint, the court said that the Ordinance satisfied United States\\n\\nv. O’Brien’s, 391 U.S. 367 (1968), test for content-neutral laws that incidentally\\n\\nregulate expressive conduct and thus did not violate the Club’s First Amendment\\n\\nrights.7 As for Counts III-VI of the complaint, the court noted that the Club had not\\n\\ncontested the City’s suspension of its business license at the scheduled\\n\\n\\n 7\\n The Club does not appeal the district court’s dismissal of Counts I and II, nor the dismissal\\nof Count VI to the extent it asserts a violation of the First Amendment. As a result, we do not\\naddress those claims.\\n 8\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 9 of 23\\n\\n\\nadministrative hearing and had not availed itself of the other process available to it\\n\\nunder state and local law. Therefore, the court concluded, those due-process counts\\n\\nwere “incognizable” under McKinney v. Pate, 20 F.3d 1550 (11th Cir. 1994) (en\\n\\nbanc).\\n\\n Next, the Court reasoned that Counts VII through XVI were not ripe for the\\n\\ncourt’s review. Specifically, the court observed that “the Club ha[d] not been\\n\\ncharged with violating” the Ordinance. “Without the facts of a particular violation,”\\n\\nthe court explained, it could “only speculate as to whether the Club will be charged\\n\\nunder the ordinances and if so, whether it will be subject to specific penalties.” On\\n\\nthat basis, the district court concluded that “the Club ha[d] not satisfied the ‘fitness’\\n\\nprong of the ripeness inquiry.” In addition, the district court determined that the\\n\\nClub would not suffer a substantial hardship as a result of postponing adjudication\\n\\nbecause the law did not “prohibit the Club from providing fully nude dance\\n\\nentertainment to its adult patrons.”\\n\\n This appeal followed.\\n\\n III.\\n\\n We review de novo the grant of a motion to dismiss for failure to state a claim,\\n\\naccepting the allegations in the complaint as true and construing them in the light\\n\\nmost favorable to the plaintiff. Fourth Estate Pub. Benefit Corp. v. Wall-Street.com,\\n\\nLLC, 856 F.3d 1338, 1339 (11th Cir. 2017). We likewise review de novo questions\\n\\n\\n 9\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 10 of 23\\n\\n\\nconcerning our subject matter jurisdiction, including standing and ripeness. Elend\\n\\nv. Basham, 471 F.3d 1199, 1204 (11th Cir. 2006). And we can affirm on any basis\\n\\nsupported by the record, regardless of whether the district court decided the case on\\n\\nthat basis. Jarvela v. Crete Carrier Corp., 776 F.3d 822, 828 (11th Cir. 2015).\\n\\n IV.\\n\\n After careful consideration of the record and oral argument, we affirm in part\\n\\nand reverse and remand in part. We agree with the district court that Counts III\\n\\nthrough VI (the due-process part of that claim) 8 of the Club’s complaint failed to\\n\\nstate claims. We also agree that Count XII was not ripe for the court’s review. And\\n\\nwe affirm the dismissal of Count X because the Club lacked standing. We conclude,\\n\\nhowever, that the remaining counts are ripe for the court’s review, so we reverse the\\n\\ncourt’s order on those counts and remand the case for further proceedings.\\n\\n A.\\n\\n We begin with Counts III-VI of the Club’s complaint. As we have noted, the\\n\\ndistrict court dismissed these counts for failure to state a claim, citing McKinney.\\n\\nWe agree.\\n\\n To state a claim under 42 U.S.C § 1983, a plaintiff must allege facts showing\\n\\nthat the defendant, acting under color of state law, deprived it of a right protected by\\n\\nthe Constitution or by a federal statute. Where, as here, the plaintiff alleges a\\n\\n\\n 8\\n See supra at n.7.\\n 10\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 11 of 23\\n\\n\\nviolation of procedural due process, the plaintiff must show the deprivation of that\\n\\nprotected interest “without due process of law.” Zinermon v. Burch, 494 U.S. 113,\\n\\n123 (1990) (emphasis in original). And a violation of procedural due process does\\n\\nnot “become complete ‘unless and until the state refuses to provide due process.’”\\n\\nMcKinney, 20 F.3d at 1562 (quoting Zinermon, 494 U.S. at 123). Here, all of the\\n\\nClub’s due-process claims in Counts III-VI fail for the same reason: they all lack\\n\\nthe essential element that the state refused to provide the Club with due process.\\n\\n First, the Club was not entitled to a pre-suspension hearing. Though Mathews\\n\\nv. Eldridge, 424 U.S. 319 (1976), can require pre-deprivation process, that is not\\n\\nalways the case. Among other such circumstances, the Supreme Court has\\n\\ndetermined that pre-deprivation process is not required when a need for “quick\\n\\naction” exists. Zinermon v. Burch, 494 U.S. 113, 128 (1990) (citation and quotation\\n\\nmarks omitted). As we have noted, here, law enforcement had probable cause to\\n\\nbelieve that the Club had allowed a 13-year-old trafficked girl to perform under\\n\\nthreat and act of physical abuse. These circumstances raised immediate and pressing\\n\\nconcerns for the physical and mental health and welfare of minors. So the City\\n\\nreasonably concluded that there was a need for “quick action,” and no pre-\\n\\ndeprivation process was required.\\n\\n We therefore turn to the post-deprivation process the Club received. Upon\\n\\nthe City’s decision to suspend its business license, the Club was entitled to a hearing\\n\\n\\n 11\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 12 of 23\\n\\n\\non an emergency basis before a special master to challenge that decision. Code of\\n\\nthe City of Miami Beach §§ 14-406(b); 102-383. At the conclusion of that hearing,\\n\\nthe special master would have issued a final administrative order. Code of the City\\n\\nof Miami Beach §§ 14-408(c); 102-385(c). Then, the Club would have been entitled\\n\\nto appeal that order to the Florida State Circuit Court. Fla. Stat. Ann. § 162.11; see\\n\\nalso Fla Stat. Ann. § 162.03 (providing that special masters with enforcement\\n\\nauthority have the “same status” as enforcement boards for purposes of Fla. Stat.\\n\\nAnn. § 162); Code of the City of Miami Beach §§ 30-2, 30-77 (stating that the City\\n\\nhas given special masters enforcement authority and that the special masters’\\n\\ndecisions are appealable to the circuit court under Fla. Stat. Ann. § 162.11).\\n\\n As we have previously held, that procedure satisfies due process because the\\n\\nFlorida Circuit Court has the power to remedy any procedural deficiencies and cure\\n\\nviolations of due process. McKinney, 20 F.3d at 1564.\\n\\n Here, the Club did not avail itself of the processes provided by local and state\\n\\nlaw. Instead of presenting its arguments to the special master and Florida Circuit\\n\\nCourt, the Club brought its arguments to federal court. For that reason, we cannot\\n\\nsay that the City or state refused to provide the Club with due process. The district\\n\\n\\n\\n\\n 12\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 13 of 23\\n\\n\\ncourt was therefore correct to dismiss Counts III-VI of the Club’s complaint for\\n\\nfailure to state a claim. 9\\n\\n B.\\n\\n The district court dismissed Counts VII-XVI on the basis that they were not\\n\\nripe for review. Specifically, the court reasoned that the Club “ha[d] not been\\n\\ncharged with violating” the Ordinance and that the Club would not suffer a\\n\\nsubstantial hardship as a result of postponing adjudication of its claims, so the Club’s\\n\\nclaims were not ripe for review. We respectfully disagree.\\n\\n Article III limits the power of the federal courts to “cases” and\\n\\n“controversies.” U.S. Const. art III, § 2; see Lujan v. Defenders of Wildlife, 504 U.S.\\n\\n555, 559-60 (1992). One of the “landmarks” of that requirement is the doctrine of\\n\\nstanding, which requires that a party have suffered an “injury in fact,” that the party’s\\n\\ninjury is fairly traceable to the challenged action of the defendant, and that the injury\\n\\nwould “likely” be “redressed by a favorable decision.” Lujan, 504 U.S. at 560-61.\\n\\n But even when a claim meets the case-or-controversy requirement’s\\n\\nconstitutional demands, such as standing, we also recognize important prudential\\n\\n\\n 9\\n Because we hold that the district court’s dismissal of Counts III-VI of the complaint was\\nproper under McKinney, we need not determine whether the district court appropriately relied on\\nthe documents attached to the City’s motion to dismiss. Those documents are not relevant to the\\nMcKinney issue. The search-warrant affidavit is the only one of the attached documents that we\\nhave considered in this appeal, and we considered it only for purposes of recounting the\\nbackground facts of the case. We may take notice of that document because its authenticity is not\\nin question and it is central to the claims at issue. See Maxcess, Inc. v. Lucent Techs., Inc., 433\\nF.3d 1337, 1340 n.3 (11th Cir. 2005); Horsley v. Feldt, 304 F.3d 1125, 1134 (11th Cir. 2002).\\n 13\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 14 of 23\\n\\n\\nlimitations on the kinds of cases that a court has power to decide. Nat’l Advert. Co.\\n\\nv. City of Miami, 402 F.3d 1335, 1338-39 (11th Cir. 2005). Those prudential\\n\\nconcerns “counsel judicial restraint” and prevent courts from “rendering\\n\\nimpermissible advisory opinions and wasting resources through review of potential\\n\\nor abstract disputes.” Id. at 1339. Based on these interests, courts decide only cases\\n\\nthat are ripe for their review. We determine ripeness, which addresses both\\n\\nconstitutional and prudential concerns, by evaluating “(1) the fitness of the issues\\n\\nfor judicial decision and (2) the hardship to the parties of withholding court\\n\\nconsideration.” Nat’l Advert. Co., 402 F.3d at 1339 (citing Abbott Lab. v. Gardner,\\n\\n387 U.S. 136, 148-49 (1967)).\\n\\n Concerning fitness for judicial decision, we ask whether the parties raise an\\n\\nissue that we can decide without further factual development and whether the\\n\\ninstitutional interests of the court and agency favor immediate review. Harrell v.\\n\\nThe Fla. Bar, 608 F.3d 1241, 1258 (11th Cir. 2010); Cheffer v. Reno, 55 F.3d 1517,\\n\\n1524 (11th Cir. 1995). As for “hardship,” litigants must show that they are “forced\\n\\nto choose between foregoing lawful activity and risking substantial legal sanctions.”\\n\\nCheffer, 55 F.3d at 1524 (citing Steffel v. Thompson, 415 U.S. 452, 462 (1974)); see\\n\\nalso Elend, 471 F.3d at 1211. If a claim is fit for judicial decision, that is end of the\\n\\ninquiry, and the matter is ripe, given that the absence of a “hardship” “cannot tip the\\n\\n\\n\\n\\n 14\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 15 of 23\\n\\n\\nbalance against judicial review” under those circumstances. See Harrell, 608 F.3d\\n\\nat 1259 (citation and internal quotation marks omitted).\\n\\n We assess ripeness on a claim-by-claim basis. A facial challenge presenting\\n\\na purely legal argument, for example, “is presumptively ripe for judicial review”\\n\\nbecause that type of argument does not rely on a developed factual record. Harris\\n\\nv. Mexican Specialty Foods, Inc., 564 F.3d 1301, 1308 (11th Cir. 2009). In contrast,\\n\\nan as-applied challenge “necessarily requires the development of a factual record for\\n\\nthe court to consider.” Id.\\n\\n Applying these principles here, we conclude that Counts VII, VIII, IX, XI,\\n\\nXIII, XIV, XV, and XVI of the Club’s complaint are ripe for review. To begin with,\\n\\nCounts XIII, XIV, and XV assert that the Ordinance was preempted by state and\\n\\nfederal law. Further factual development cannot assist in resolution of these facial\\n\\nchallenges, which raise purely legal issues. Nor do any institutional concerns of the\\n\\ncourt or the City render the issues unfit for review. Consequently, these claims are\\n\\nripe. Id. at 1308.\\n\\n Next, the Club’s as-applied challenges—asserting an unconstitutional burden\\n\\nand tax on speech (Counts VII and VIII), an Equal Protection violation (Count IX),\\n\\nand a Contract Clause violation (Count XI)—require no more factual development\\n\\nto be ripe for review. It is undisputed that the Club is subject to the Ordinance and\\n\\n\\n\\n\\n 15\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 16 of 23\\n\\n\\nis complying with its regulations. And that compliance is what forms the factual\\n\\nbasis of the Club’s as-applied arguments.\\n\\n To be sure, the Club does not contend that it was charged with violating the\\n\\nOrdinance or that it has suffered the Ordinance’s penalties. But that does not render\\n\\nthe claims in Counts VII, VIII, IX and XI unripe for the district court’s review. If\\n\\nthe Club were to fall short of any of the Ordinance’s requirements and the City were\\n\\nto charge it with a violation of the law, the resulting additional facts would shed no\\n\\nfurther light on whether compliance with the Ordinance is an unconstitutional\\n\\nburden on speech, a tax on speech, an equal-protection violation, or a Contract\\n\\nClause violation in the first place. For these same reasons, institutional concerns\\n\\nlikewise present no impediment to fitness for review. So Counts VII, VIII, IX, and\\n\\nXI are ripe for review. See Harrell, 608 F.3d at 1258; Cheffer, 55 F.3d at 1524.\\n\\n Count XVI is also fit for review. The Club claims that the Ordinance\\n\\nauthorizes the City to engage in warrantless searches in violation of the Fourth\\n\\nAmendment. That claim presents purely legal questions, such as (1) whether the\\n\\nOrdinance falls within the administrative-search exception, and if so, whether it\\n\\naffords the Club an opportunity to obtain pre-compliance review before a neutral\\n\\ndecisionmaker, and (2) whether the Club is part of a “closely regulated” industry,\\n\\nand if so, whether warrantless inspections are necessary to further a substantial\\n\\ngovernment interest and whether the Ordinance adequately constrains police\\n\\n\\n 16\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 17 of 23\\n\\n\\ndiscretion. See City of Los Angeles v. Patel, 135 S. Ct. 2243, 2452–56 (2015). As a\\n\\nresult, we need not wait for further facts, such as a warrantless search under the\\n\\nOrdinance, to occur to resolve this claim.\\n\\n As for Count XII, we agree with the district court that it is not ripe for review.\\n\\nCount XII alleges that that the Ordinance’s penalty provision violates the Eighth\\n\\nAmendment. But we have held that “Eighth Amendment challenges are generally\\n\\nnot ripe until the imposition, or immediately impending imposition, of a challenged\\n\\npunishment or fine.” Cheffer, 55 F.3d at 1523-24. The Club does not allege that the\\n\\nCity imposed a fine under that provision or that the imposition of a fine is\\n\\nimmediately forthcoming, so the district court correctly determined that the Club’s\\n\\nEighth Amendment argument is not ripe for review.\\n\\n C.\\n\\n Finally, we turn to Count X, which alleges that the Ordinance is\\n\\nunconstitutionally vague. The district court dismissed that claim as unripe, but we\\n\\naffirm for a different reason: the Club lacked standing to bring it. 10\\n\\n As we have noted, to have standing, a party must demonstrate that (1) it has\\n\\nsuffered, or imminently will suffer, an injury-in-fact; (2) the injury is fairly traceable\\n\\nto the operation of the challenged law; and (3) a favorable judgment is likely to\\n\\n\\n 10\\n Standing is a jurisdictional requirement that we are obligated to address sua sponte. See\\nMurphy v. Dulay, 768 F.3d 1360, 1366 n.4 (11th Cir. 2014); Region 8 Forest Serv. Timber\\nPurchasers Council v. Alcock, 993 F.2d 800, 806-807 (11th Cir. 1993).\\n 17\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 18 of 23\\n\\n\\nredress the injury. Wollschlaeger v. Governor, 848 F.3d 1293, 1303-1304 (11th Cir.\\n\\n2017) (en banc); Harrell, 608 F.3d at 1254. Though we “most loosely” apply the\\n\\ninjury-in-fact requirement when a claim involves First Amendment rights, we\\n\\nnevertheless conclude that the Club lacked standing to argue that the Ordinance is\\n\\nunconstitutionally vague. Even if the Club could show that it had suffered, or will\\n\\nimminently suffer, an injury in fact, it cannot demonstrate that the injury is fairly\\n\\ntraceable to the Ordinance’s purported imprecision.\\n\\n In the first step of our standing analysis, we ask whether the Club has suffered,\\n\\nor imminently will suffer, an injury in fact. We have previously held that a party\\n\\nmight satisfy this prong by showing self-censorship. See Wollschlaeger, 848 F.3d\\n\\nat 1304-1305; Harrell, 608 F.3d at 1253. Here, though, it is undisputed that the Club\\n\\nis not self-censoring, but rather, is continuing to carry on its business, apparently in\\n\\ncompliance with the Ordinance.\\n\\n The Club might also suggest that the Ordinance contains vague language that\\n\\ncauses it to fear that the City will enforce it arbitrarily, and is thereby injured. But\\n\\nmere fear of unconstitutional action alone on the part of the City is too speculative\\n\\nan injury to confer standing to the Club. See JW v. Birmingham Bd. Of Educ., 904\\n\\nF.3d 1248, 1264 (11th Cir. 2018); 31 Foster Children v. Bush, 329 F.3d 1255, 1263\\n\\n(11th Cir. 2003). That is especially true here, since the Club has apparently been\\n\\n\\n\\n\\n 18\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 19 of 23\\n\\n\\nsuccessfully complying with the Ordinance without incident since it was\\n\\npromulgated roughly three years ago.\\n\\n The Club’s most promising standing argument would be that it unnecessarily\\n\\nincurred additional expenses in an effort to comply with what it says is an\\n\\nunconstitutionally vague law, above and beyond the expense that would have been\\n\\nnecessary to comply with a law that was not vague. The Club suggested that\\n\\nargument in its pleadings and briefs to this Court. Assuming that the Club is making\\n\\nthat argument, and assuming that such an injury could help confer standing in a pre-\\n\\nenforcement vagueness challenge, the Club would also need to demonstrate that the\\n\\nadditional expense incurred was fairly traceable to the alleged deficiencies in the\\n\\nchallenged provisions. Just as in Harrell, where the injury was self-censorship, the\\n\\nClub would have to establish that its injury was fairly traceable to the purportedly\\n\\nvague provisions by showing that those provisions were “at least arguably vague”\\n\\nas applied to it. 608 F.3d at 1254.\\n\\n In other words, our standing analysis requires us to take a “peek” at the merits\\n\\nof the Club’s vagueness claim. See Transp. Workers Union of Am., AFL-CIO v.\\n\\nTransp. Sec. Admin., 492 F.3d 471, 475 (D.C. Cir. 2007). Of course, while “standing\\n\\nin no way depends on the merits” of a plaintiff’s claim, “it often turns on the nature\\n\\nand source of the claim asserted.” Warth v. Seldin, 422 U.S. 490, 500 (1975). As\\n\\nwe recently observed, we “‘must not confuse weakness on the merits with absence\\n\\n\\n 19\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 20 of 23\\n\\n\\nof Article III standing.’” Moody v. Holman, 887 F.3d 1281, 1285 (11th Cir. 2018)\\n\\n(quoting Ariz. St. Leg. v. Ariz. Indep. Redistricting Comm’n, 135 S. Ct. 2652, 2663\\n\\n(2015)). In some circumstances, however, those “‘distinct concepts can be difficult\\n\\nto keep separate.’” Id. (quoting Bond v. United States, 564 U.S. 211, 218 (2011)).\\n\\n Here, the “nature and source” of the Club’s claim requires us to ask whether\\n\\nthe Ordinance’s challenged provisions are “at least arguably vague” as applied to it.\\n\\nHarrell, 608 F.3d at 1254. The answer to that question will allow us to assess\\n\\nwhether the Club’s apparent injury—the expense above and beyond that necessary\\n\\nto comply with a clear law—is “fairly traceable” to the Ordinance’s vagueness and,\\n\\naccordingly, whether the Club has standing to bring Count X of its complaint.\\n\\n But here, none of the challenged provisions are “at least arguably vague” as\\n\\napplied to the Club. As a result, the Club cannot show that a financial injury was\\n\\nfairly traceable to language it characterizes as “vague.”\\n\\n First, the Club contends that the provision requiring employees to present a\\n\\n“lawfully issued state or federal photo identification” and “one additional form of\\n\\nidentification” is vague. We disagree; it is not arguable that “people of ordinary\\n\\nintelligence” would fail to understand what the Ordinance requires. See Hill v.\\n\\nColorado, 530 U.S. 703, 732 (2000). The plain language of that provision\\n\\nunambiguously requires employees to provide two legal forms of identification\\n\\n\\n\\n\\n 20\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 21 of 23\\n\\n\\nissued by a state or federal government, that show the employee’s age and work\\n\\neligibility.\\n\\n The Ordinance’s requirements that the Club “verify the accuracy” of those\\n\\ndocuments and “confirm that the person is working or performing of his or her own\\n\\naccord and not being forced or intimidated into working or performing” are not\\n\\narguably vague, either. In fact, the Ordinance specifically instructs the Club as to\\n\\nhow it must execute these requirements: “by preparing and retaining a sworn\\n\\nstatement from the owner or manager” confirming that the employee is of age and\\n\\nis not being forced or intimidated into working. By its language, the Ordinance\\n\\nsimply requires the Club manager or owner to verify the accuracy of the documents\\n\\nand the employee’s willingness to work to the verifying official’s good-faith\\n\\nsatisfaction, so the verifying official is comfortable swearing to those circumstances.\\n\\nWe find nothing arguably vague about this aspect of the Ordinance as applied to the\\n\\nClub.\\n\\n Next, the Club suggests that the provision of the Ordinance that requires that\\n\\n“no person shall be allowed to enter” the establishment if the manager has not\\n\\n“verified” the person to be of age, work-eligible, and not working because of force\\n\\nor intimidation is vague because it could apply to patrons as well as employees. We\\n\\nare not persuaded. This provision clearly refers to employees and not to patrons.\\n\\nAfter all, even to the extent that the Ordinance’s language is unclear in the least, the\\n\\n\\n 21\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 22 of 23\\n\\n\\ntitle of the section makes it obvious that the requirement applies to “workers and\\n\\nperformers.” Essex Ins. Co. v. Zota, 466 F.3d 981, 989-90 (11th Cir. 2006).\\n\\n Finally, the Ordinance’s penalty provision stating that the city manager “may”\\n\\nrevoke the Club’s business license for up to one year is not arguably vague. The\\n\\nprovision specifies with “sufficient clarity” what the enhanced penalty is. See\\n\\nBeckles v. United States, 137 S. Ct. 886, 892 (2017). And although the provision\\n\\ngives the city manager considerable discretion to determine when, and to what\\n\\nextent, to impose that penalty, the sort of discretion conferred here does not render\\n\\nthe provision unconstitutionally vague. See id. at 893 (“[O]ur cases have never\\n\\nsuggested that a defendant can successfully challenge as vague a sentencing statute\\n\\nconferring discretion to select an appropriate sentence from within a statutory range,\\n\\neven when that discretion is unfettered.”).\\n\\n In short, the Club cannot clear the low bar of demonstrating that the\\n\\nchallenged provisions are at least arguably vague as applied to it. So even if it\\n\\nshowed that it had incurred some additional expense in an attempt to comply with\\n\\nthose provisions, and assuming that the additional expense constituted an injury for\\n\\npurposes of standing, that injury would not be fairly traceable to the purportedly\\n\\nvague language. And without an injury that is fairly traceable to the challenged\\n\\nprovisions, the Club lacks standing to argue that they are unconstitutionally vague.\\n\\nWe therefore affirm the district court’s dismissal of Count X.\\n\\n\\n 22\\n\\f Case: 17-13934 Date Filed: 05/24/2019 Page: 23 of 23\\n\\n\\n D.\\n\\n In sum, Counts VII-IX, XI, and XIII-XVI of the Club’s complaint are ripe for\\n\\nreview, so we reverse the district court’s order and remand the case for further\\n\\nproceedings on those counts. Count XII of the complaint is not ripe, and the Club\\n\\nlacks standing to argue in Count X that the Ordinance is unconstitutionally vague,\\n\\nso we affirm the district court’s order dismissing those counts.\\n\\n V.\\n\\n For these reasons, we affirm the dismissal of Counts III-VI, X, and XII of the\\n\\nClub’s complaint. But we reverse the dismissal of Counts VII-IX, XI, and XIII-XVI\\n\\nof that complaint and remand the case to the district court for further proceedings.\\n\\n AFFIRMED IN PART and REVERSED AND REMANDED IN PART.\\n\\n\\n\\n\\n 23\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2294,"cells":{"id":{"kind":"number","value":4624027,"string":"4,624,027"},"name":{"kind":"string","value":"S&M BRANDS, INC., Plaintiff - Appellant, v. State of GEORGIA EX REL., Christopher M. CARR, Attorney General, Defendant - Appellee."},"name_abbreviation":{"kind":"string","value":"S&M Brands, Inc. v. State of Georgia Ex Rel."},"decision_date":{"kind":"string","value":"2019-05-29"},"docket_number":{"kind":"string","value":"17-13261"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Tjoflat, Rosenbaum, Ungaro\", \"parties\": \"\", \"opinions\": [{\"author\": \"TJOFLAT, Circuit Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-13261 Date Filed: 05/29/2019 Page: 1 of 11\\n\\n\\n [PUBLISH]\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-13261\\n ________________________\\n\\n D.C. Docket No. 1:16-cv-04469-SCJ\\n\\n\\nS&M BRANDS, INC.,\\n\\n Plaintiff – Appellant,\\n\\n versus\\n\\nSTATE OF GEORGIA EX REL.,\\nChristopher M. Carr, Attorney General,\\n\\n Defendant – Appellee.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 29, 2019)\\n\\nBefore TJOFLAT and ROSENBAUM, Circuit Judges, and UNGARO, * District\\nJudge.\\n\\n\\n\\n *\\n Honorable Ursula Ungaro, United States District Judge for the Southern District of\\n Florida, sitting by designation.\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 2 of 11\\n\\n\\nTJOFLAT, Circuit Judge:\\n\\n S&M Brands, Inc., a tobacco producer, appeals the dismissal of its suit\\n\\nagainst the State of Georgia. In its complaint for declaratory and injunctive relief,\\n\\nS&M pleaded several constitutional and state-law violations based on Georgia’s\\n\\nscheme of tobacco regulation. Georgia moved to dismiss, and the District Court\\n\\ngranted the motion, dismissing the complaint on the grounds that its allegations\\n\\ndid not amount to constitutional violations and its state-law claims were barred by\\n\\nsovereign immunity. After thorough consideration, and with the benefit of oral\\n\\nargument, we affirm the dismissal of S&M’s complaint.\\n\\n I.\\n\\n Every tobacco producer that operates in Georgia is licensed to do business\\n\\nvia one of two routes. Many of the producers are parties to the Master Settlement\\n\\nAgreement (“MSA”), a 20-year-old omnibus settlement between the tobacco\\n\\nindustry and most U.S. states, including Georgia. KT & G Corp. v. Att’y Gen. of\\n\\nState of Okla., 535 F.3d 1114, 1118–19 (10th Cir. 2008); see generally Nat’l Ass’n\\n\\nof Att’ys Gen., Master Settlement Agreement (1999) (hereinafter “MSA”). These\\n\\nproducers—the “participating manufacturers,” or PMs—are saddled with ongoing\\n\\nobligations under the MSA, including a collective payment obligation of billions\\n\\nof dollars per year, in exchange for the states’ releasing them from liability for\\n\\nstate public-health expenditures caused by cigarette smoking. MSA §§ I, II(jj).\\n\\n 2\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 3 of 11\\n\\n\\nOther producers—the “non-participating manufacturers,” or NPMs—did not sign\\n\\nthe MSA, do not make payments to the states, and could potentially be sued in the\\n\\nfuture if they incur liability for the states’ public-health costs. Since NPMs may\\n\\nbecome liable, Georgia requires them to self-insure by contracting with an escrow\\n\\nagent to establish an escrow fund into which they pay a set amount per cigarette\\n\\nsold. O.G.C.A. § 10-13-3(2)(A). Otherwise, an NPM could make short-term\\n\\nprofits, rack up liability to the state, and then become judgment-proof before the\\n\\nstate could recover its public-health expenditures. Id. § 10-13-1(f). PMs are not\\n\\nrequired to self-insure; their liability is already settled, and they are contractually\\n\\nrequired to make payments. Id. § 10-13-3.\\n\\n NPM escrow funds are governed by the requirements of Georgia’s escrow\\n\\nstatute, which is implemented and enforced by the Attorney General. Id. § 10-13-\\n\\n3(2)(C). The principal funds deposited are available to pay judgments on or\\n\\nsettlements of claims like those settled in the MSA. Id. § 10-13-3(2)(B)(i). If not\\n\\npaid to the state, the funds are returned to the NPM after 25 years. Id. § 10-13-\\n\\n3(2)(B)(iii). The interest and other returns on the invested deposits are paid to the\\n\\nNPM as earned. Id. § 10-13-3(2)(B). NPMs must make several quarterly and\\n\\nannual certifications, including that they have complied with the escrow statute\\n\\nand that their funds are governed by a compliant escrow agreement that has been\\n\\nreviewed and approved by the Attorney General. Id. §§ 10-13-3(2)(C), 10-13A-\\n\\n 3\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 4 of 11\\n\\n\\n3(d)(2). The Attorney General has exercised his review and approval authority by\\n\\nrequiring that each NPM use a model escrow agreement drafted by his office. 1 The\\n\\nAttorney General’s model escrow agreement includes investment class restrictions\\n\\nfor escrow funds: only cash, a money-market fund, and U.S. Treasury securities\\n\\nare permitted investments. Noncompliance with the escrow statute or the Attorney\\n\\nGeneral’s requirements can lead to a statewide ban on sales of the NPM’s\\n\\nproducts. O.G.C.A. §§ 10-13A-4(b), 10-13A-5.\\n\\n S&M Brands is an NPM and has operated in Georgia for decades. From the\\n\\nsigning of the MSA and imposition of the two-route scheme until 2016, S&M\\n\\nperformed its obligations under the escrow statute. Back then, the escrow statute\\n\\ndid not impose any restrictions on escrow fund investments; the restrictions came\\n\\nsolely from the Attorney General’s prerogative to deny approval to NPM escrow\\n\\nagreements, informed by the State’s general policy of seeking to ensure a source\\n\\nof recovery from potential-defendant NPMs. In 2016, the General Assembly\\n\\namended the escrow statute, adding a provision that requires the value of the\\n\\n\\n\\n\\n 1\\n This requirement raises a thorny question of Georgia administrative law: does the\\nAttorney General have discretion to refuse to approve an escrow agreement that meets all the\\nsubstantive requirements of the escrow statute? Answering that question would require a\\nthorough inquiry into Georgia’s Administrative Procedure Act and the caselaw interpreting it.\\nBut this issue is not before us—the District Court dismissed S&M’s claim raising this point, and\\nS&M has not appealed that ruling—so we will operate under the assumption that the Attorney\\nGeneral’s review-and-approval authority allows him to require a specific form agreement.\\n 4\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 5 of 11\\n\\n\\nescrow fund not to diminish below the amount paid into it. 2 2016 Ga. Laws 529–\\n\\n30. To implement this amendment, the Attorney General’s office modified its\\n\\nform escrow agreement, changing the list of permitted investments for escrow\\n\\nfunds. Formerly, escrow monies could be invested in any U.S. Treasury\\n\\nsecurities; under the new model agreement, any U.S. Treasury securities bought\\n\\nwith escrow funds must mature in no more than 20 years, although already-\\n\\npurchased securities may be kept until they mature or are sold.\\n\\n S&M sued to enjoin the Attorney General from requiring it to use the\\n\\nrevised escrow agreement. The District Court dismissed the case, and this appeal\\n\\nfollowed. We affirm.\\n\\n II.\\n\\n A.\\n\\n S&M alleges that the investment restrictions in the revised escrow\\n\\nagreement reduce the returns it can expect to earn on its escrow money, and the\\n\\nAttorney General’s imposition of the new restrictions (pursuant to the statutory\\n\\namendment) is a “Law impairing the Obligation of Contracts” within the meaning\\n\\n\\n\\n 2\\n The statute is ambiguous as to what would be required if the value of the escrow\\ninvestments were to dip below the amount of principal deposited. If this were to happen, then\\npresumably the NPM could not certify that its escrow fund was compliant; it would have to\\nmake up the difference by depositing additional funds in order to so certify. But the statute\\nmakes no express provision for supplemental deposits, and whether such deposits could be\\nrequired (and how they would be administered) is an open question. The Attorney General’s\\npolicy seems to be to try to avoid the question by requiring minimally risky investments.\\n 5\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 6 of 11\\n\\n\\nof the Contract Clause. It also alleges that several differences between how the\\n\\nescrow statute is administered for NPMs and how MSA payments are\\n\\nadministered for PMs violate the Fourteenth Amendment’s Equal Protection\\n\\nClause. Finally, it alleges that it is owed a release of some excess escrow funds\\n\\ndue to having paid more than is required by state law.\\n\\n We start with S&M’s Contract Clause claim. The Contract Clause protects\\n\\ncontracting parties’ reasonable contractual expectations against unreasonable\\n\\nabrogation by the states. The threshold inquiry is whether the law “operate[s] as a\\n\\nsubstantial impairment of a contractual relationship” involving the plaintiff. Allied\\n\\nStructural Steel Co. v. Spannaus, 438 U.S. 234, 244, 98 S. Ct. 2716, 2722 (1978).\\n\\nIf an industry is already heavily regulated, regulatory changes that abrogate\\n\\nindustry players’ contract rights are less likely to be considered substantial\\n\\nimpairments. Energy Reserves Grp., Inc. v. Kan. Power & Light Co., 459 U.S.\\n\\n400, 413, 103 S. Ct. 697, 705 (1983). And when the subject matter of the contract\\n\\nitself is already subject to state regulation, the substantial-impairment case is even\\n\\nweaker. Veix v. Sixth Ward Bldg. & Loan Ass’n, 310 U.S. 32, 38, 60 S. Ct. 792,\\n\\n795 (1940).\\n\\n Here, S&M’s escrow agreement does not give rise to any reasonable\\n\\ncontractual expectations that implicate the Contract Clause. Every term of the old\\n\\nmodel escrow agreement was specifically dictated by the Attorney General as a\\n\\n 6\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 7 of 11\\n\\n\\ncondition of approval under O.G.C.A. § 10-13A-3(d)(2). It is hard to say that such\\n\\na contract could give rise to any reasonable contractual expectations that would\\n\\nimplicate the Clause, at least vis-à-vis the state that dictated the terms. 3 Georgia\\n\\ndoes not strip itself of police power when it regulates by requiring private parties\\n\\nto contract. Nor does the Contract Clause ossify the state’s regulatory scheme in\\n\\nthese circumstances; the general rule, that states can exercise the police power to\\n\\nsupersede old regulations, prevails. 4 So S&M has not plausibly alleged a Contract\\n\\nClause violation.\\n\\n B.\\n\\n On to S&M’s Equal Protection claim. S&M alleges that it is similarly\\n\\nsituated to the PMs, who are also required to pay money into escrow, and that\\n\\nGeorgia is discriminating against them in favor of the PMs with no rational basis\\n\\nand in a way that burdens their fundamental right of free speech. Our threshold\\n\\ninquiry in an Equal Protection case is whether the plaintiff and the proposed\\n\\ncomparator are similarly situated, since the Equal Protection Clause requires that\\n\\n\\n\\n\\n 3\\n The analysis could, of course, be different if the State were a party to the contract,\\nrather than a mere beneficiary. We do not mean to suggest that the State cannot bind itself by\\ncontract to limit some of its own powers. See U.S. Tr. Co. v. New Jersey, 431 U.S. 1, 23–24, 97\\nS. Ct. 1505, 1518 (1977).\\n 4\\n “One whose rights, such as they are, are subject to state restriction, cannot remove\\nthem from the power of the state by making a contract about them. The contract will carry with\\nit the infirmity of the subject-matter.” Hudson Cty. Water Co. v. McCarter, 209 U.S. 349, 357,\\n28 S. Ct. 529, 531–32 (1908).\\n 7\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 8 of 11\\n\\n\\n“persons similarly situated . . . be treated alike.” City of Cleburne v. Cleburne\\n\\nLiving Ctr., 473 U.S. 432, 439, 105 S. Ct. 3249, 3254 (1985); see also Dawson v.\\n\\nScott, 50 F.3d 884, 892 (11th Cir. 1995). If the plaintiff has not been treated\\n\\ndifferently than a similarly situated comparator, no Equal Protection violation\\n\\nexists. Dawson, 50 F.3d at 892.\\n\\n Here, S&M Brands and the other NPMs are not similarly situated to the\\n\\nPMs with respect to the challenged provisions of law. The PMs have settled their\\n\\nliability to the state; S&M and the NPMs have not. The PMs need not establish an\\n\\ninsurance fund, since Georgia has contract remedies available if a PM fails to\\n\\nmake an MSA payment. S&M makes much of the fact that MSA payments are\\n\\nadministered via an escrow system with different investment restrictions than\\n\\nthose applicable to NPMs. But the NPM and PM escrow systems are not\\n\\ncomparable: NPM escrow money stays in escrow for 25 years and then returns to\\n\\nthe NPM unless taken to pay a claim, while PM payments stay in escrow for only\\n\\na few days or weeks while the monies owed to each state are apportioned. The\\n\\nrole of escrow is different in PM and NPM regulation, so Georgia may impose\\n\\ndifferent requirements on PM and NPM escrow accounts without violating equal\\n\\nprotection.\\n\\n All the provisions S&M challenges under the Equal Protection clause—the\\n\\ninvestment restrictions, the quarterly rather than annual deposit schedule, the\\n\\n 8\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 9 of 11\\n\\n\\nregistered-agent and surety-bond requirements, and the delisting sanction for\\n\\nnoncompliance with the escrow statute—are provisions with respect to which PMs\\n\\nand NPMs are not similarly situated. So S&M has not plausibly alleged an Equal\\n\\nProtection violation.5\\n\\n C.\\n\\n S&M’s final claim is for a violation of state law; specifically, S&M claims\\n\\nthat the Attorney General was required to release escrow funds to it because it paid\\n\\nmore into escrow than it was required to under O.C.G.A. § 10-13-3(2)(B)(ii). The\\n\\nDistrict Court dismissed this claim under Rule 12(b)(1) for lack of jurisdiction.\\n\\nBecause the claim is barred by state sovereign immunity, we affirm.\\n\\n State sovereign immunity limits federal court jurisdiction. Seminole Tribe\\n\\nof Fla. v. Florida, 517 U.S. 44, 54, 116 S. Ct. 1114, 1122 (1996). Some suits\\n\\nrequesting injunctive or declaratory relief against state officials are not considered\\n\\nsuits against the state and thus are not barred by sovereign immunity. Ex parte\\n\\n\\n\\n\\n 5\\n S&M contends on appeal that its Complaint also states a standalone First Amendment\\nclaim. We disagree. S&M makes one conclusory allegation of a First Amendment violation in\\n¶ 114 of its Complaint; this is insufficient on its own to survive a motion to dismiss. See\\nAshcroft v. Iqbal, 556 U.S. 662, 678, 129 S.Ct. 1937, 1949 (2009). S&M argues on appeal that\\nthe facts it pleaded show that Georgia is either 1) coercing it to sign the MSA and thus waive its\\nFirst Amendment rights or 2) neutralizing the effect of its commercial speech by imposing\\neconomic disadvantages on it that are not imposed on the PMs. But neither of these theories are\\nplausibly supported by factual allegations in S&M’s Complaint. S&M has not alleged that it\\nwould be better off economically if it joined the MSA, a necessary component of its coercion\\ntheory. Nor has S&M alleged that the restrictions are sufficiently tied to its speech to support a\\nclaim on its neutralization theory. So S&M has not stated a First Amendment claim.\\n 9\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 10 of 11\\n\\n\\nYoung, 209 U.S. 123, 159–60, 28 S.Ct. 441, 454 (1908) (injunctive relief); Verizon\\n\\nMd., Inc. v. Pub. Serv. Comm'n of Md., 535 U.S. 635, 646, 122 S. Ct. 1753, 1760\\n\\n(2002) (declaratory relief). But when the claim of entitlement to relief is based on\\n\\na violation of state law, sovereign immunity applies. Pennhurst State Sch. &\\n\\nHosp. v. Halderman, 465 U.S. 89, 121, 104 S. Ct. 900, 919 (1984). And\\n\\nconclusory allegations that the same conduct that violates state law also violates\\n\\nthe U.S. Constitution will not boost the claim over the sovereign-immunity bar.\\n\\nDeKalb Cty. Sch. Dist. v. Schrenko, 109 F.3d 680, 688 (11th Cir. 1997).\\n\\n Schrenko’s facts are on point. There, a school district sought\\n\\nreimbursement from the state of Georgia for transportation costs. Id. at 684–85.\\n\\nThe entitlement to and amount of reimbursement were determined by a state\\n\\nstatute. Id. at 688. Although the school district referenced the Fourteenth\\n\\nAmendment and federal statutory law in its complaint, its claim necessarily relied\\n\\non a determination that state officials had not complied with state law. We thus\\n\\nheld the claim barred by sovereign immunity. Id. at 690.\\n\\n Here, S&M’s claim is that Georgia is required to release escrow funds back\\n\\nto it. Georgia’s obligation to do this comes from state law; specifically, O.C.G.A.\\n\\n§ 10-13-3(2)(B)(ii), which provides for release of excess escrow funds in the event\\n\\nan NPM deposits more than it would have paid in MSA payments were it a PM.\\n\\nS&M claims that this is really a constitutional claim, since the refusal to release\\n\\n 10\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 11 of 11\\n\\n\\nfunds serves to coerce it to give up its First Amendment rights and constitutes a\\n\\nFifth Amendment taking.\\n\\n We don’t buy it. Here, as in Schrenko, the obligation to release (or\\n\\nreimburse) funds comes from state law. The proper release amount is determined\\n\\nby state law. Accordingly, the “gravamen of [the] complaint appears to be that the\\n\\nState has improperly interpreted and failed to adhere to a state statute,” and\\n\\nPennhurst bars such claims. Id. at 688. We affirm the dismissal of S&M’s state-\\n\\nlaw claim.\\n\\n For the foregoing reasons, the dismissal of S&M Brands’ Complaint is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 11\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4401280/\", \"author_raw\": \"TJOFLAT, Circuit Judge:\"}]}"},"judge1":{"kind":"string","value":"TJOFLAT"},"judge2":{"kind":"string","value":"ROSENBAUM"},"judge3":{"kind":"string","value":"UNGARO"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4624027/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: S&M BRANDS, INC., Plaintiff - Appellant, v. State of GEORGIA EX REL., Christopher M. CARR, Attorney General, Defendant - Appellee.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-29\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-13261 Date Filed: 05/29/2019 Page: 1 of 11\n\n\n [PUBLISH]\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-13261\n ________________________\n\n D.C. Docket No. 1:16-cv-04469-SCJ\n\n\nS&M BRANDS, INC.,\n\n Plaintiff – Appellant,\n\n versus\n\nSTATE OF GEORGIA EX REL.,\nChristopher M. Carr, Attorney General,\n\n Defendant – Appellee.\n\n ________________________\n\n Appeal from the United States District Court\n for the Northern District of Georgia\n ________________________\n\n (May 29, 2019)\n\nBefore TJOFLAT and ROSENBAUM, Circuit Judges, and UNGARO, * District\nJudge.\n\n\n\n *\n Honorable Ursula Ungaro, United States District Judge for the Southern District of\n Florida, sitting by designation.\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 2 of 11\n\n\nTJOFLAT, Circuit Judge:\n\n S&M Brands, Inc., a tobacco producer, appeals the dismissal of its suit\n\nagainst the State of Georgia. In its complaint for declaratory and injunctive relief,\n\nS&M pleaded several constitutional and state-law violations based on Georgia’s\n\nscheme of tobacco regulation. Georgia moved to dismiss, and the District Court\n\ngranted the motion, dismissing the complaint on the grounds that its allegations\n\ndid not amount to constitutional violations and its state-law claims were barred by\n\nsovereign immunity. After thorough consideration, and with the benefit of oral\n\nargument, we affirm the dismissal of S&M’s complaint.\n\n I.\n\n Every tobacco producer that operates in Georgia is licensed to do business\n\nvia one of two routes. Many of the producers are parties to the Master Settlement\n\nAgreement (“MSA”), a 20-year-old omnibus settlement between the tobacco\n\nindustry and most U.S. states, including Georgia. KT & G Corp. v. Att’y Gen. of\n\nState of Okla., 535 F.3d 1114, 1118–19 (10th Cir. 2008); see generally Nat’l Ass’n\n\nof Att’ys Gen., Master Settlement Agreement (1999) (hereinafter “MSA”). These\n\nproducers—the “participating manufacturers,” or PMs—are saddled with ongoing\n\nobligations under the MSA, including a collective payment obligation of billions\n\nof dollars per year, in exchange for the states’ releasing them from liability for\n\nstate public-health expenditures caused by cigarette smoking. MSA §§ I, II(jj).\n\n 2\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 3 of 11\n\n\nOther producers—the “non-participating manufacturers,” or NPMs—did not sign\n\nthe MSA, do not make payments to the states, and could potentially be sued in the\n\nfuture if they incur liability for the states’ public-health costs. Since NPMs may\n\nbecome liable, Georgia requires them to self-insure by contracting with an escrow\n\nagent to establish an escrow fund into which they pay a set amount per cigarette\n\nsold. O.G.C.A. § 10-13-3(2)(A). Otherwise, an NPM could make short-term\n\nprofits, rack up liability to the state, and then become judgment-proof before the\n\nstate could recover its public-health expenditures. Id. § 10-13-1(f). PMs are not\n\nrequired to self-insure; their liability is already settled, and they are contractually\n\nrequired to make payments. Id. § 10-13-3.\n\n NPM escrow funds are governed by the requirements of Georgia’s escrow\n\nstatute, which is implemented and enforced by the Attorney General. Id. § 10-13-\n\n3(2)(C). The principal funds deposited are available to pay judgments on or\n\nsettlements of claims like those settled in the MSA. Id. § 10-13-3(2)(B)(i). If not\n\npaid to the state, the funds are returned to the NPM after 25 years. Id. § 10-13-\n\n3(2)(B)(iii). The interest and other returns on the invested deposits are paid to the\n\nNPM as earned. Id. § 10-13-3(2)(B). NPMs must make several quarterly and\n\nannual certifications, including that they have complied with the escrow statute\n\nand that their funds are governed by a compliant escrow agreement that has been\n\nreviewed and approved by the Attorney General. Id. §§ 10-13-3(2)(C), 10-13A-\n\n 3\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 4 of 11\n\n\n3(d)(2). The Attorney General has exercised his review and approval authority by\n\nrequiring that each NPM use a model escrow agreement drafted by his office. 1 The\n\nAttorney General’s model escrow agreement includes investment class restrictions\n\nfor escrow funds: only cash, a money-market fund, and U.S. Treasury securities\n\nare permitted investments. Noncompliance with the escrow statute or the Attorney\n\nGeneral’s requirements can lead to a statewide ban on sales of the NPM’s\n\nproducts. O.G.C.A. §§ 10-13A-4(b), 10-13A-5.\n\n S&M Brands is an NPM and has operated in Georgia for decades. From the\n\nsigning of the MSA and imposition of the two-route scheme until 2016, S&M\n\nperformed its obligations under the escrow statute. Back then, the escrow statute\n\ndid not impose any restrictions on escrow fund investments; the restrictions came\n\nsolely from the Attorney General’s prerogative to deny approval to NPM escrow\n\nagreements, informed by the State’s general policy of seeking to ensure a source\n\nof recovery from potential-defendant NPMs. In 2016, the General Assembly\n\namended the escrow statute, adding a provision that requires the value of the\n\n\n\n\n 1\n This requirement raises a thorny question of Georgia administrative law: does the\nAttorney General have discretion to refuse to approve an escrow agreement that meets all the\nsubstantive requirements of the escrow statute? Answering that question would require a\nthorough inquiry into Georgia’s Administrative Procedure Act and the caselaw interpreting it.\nBut this issue is not before us—the District Court dismissed S&M’s claim raising this point, and\nS&M has not appealed that ruling—so we will operate under the assumption that the Attorney\nGeneral’s review-and-approval authority allows him to require a specific form agreement.\n 4\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 5 of 11\n\n\nescrow fund not to diminish below the amount paid into it. 2 2016 Ga. Laws 529–\n\n30. To implement this amendment, the Attorney General’s office modified its\n\nform escrow agreement, changing the list of permitted investments for escrow\n\nfunds. Formerly, escrow monies could be invested in any U.S. Treasury\n\nsecurities; under the new model agreement, any U.S. Treasury securities bought\n\nwith escrow funds must mature in no more than 20 years, although already-\n\npurchased securities may be kept until they mature or are sold.\n\n S&M sued to enjoin the Attorney General from requiring it to use the\n\nrevised escrow agreement. The District Court dismissed the case, and this appeal\n\nfollowed. We affirm.\n\n II.\n\n A.\n\n S&M alleges that the investment restrictions in the revised escrow\n\nagreement reduce the returns it can expect to earn on its escrow money, and the\n\nAttorney General’s imposition of the new restrictions (pursuant to the statutory\n\namendment) is a “Law impairing the Obligation of Contracts” within the meaning\n\n\n\n 2\n The statute is ambiguous as to what would be required if the value of the escrow\ninvestments were to dip below the amount of principal deposited. If this were to happen, then\npresumably the NPM could not certify that its escrow fund was compliant; it would have to\nmake up the difference by depositing additional funds in order to so certify. But the statute\nmakes no express provision for supplemental deposits, and whether such deposits could be\nrequired (and how they would be administered) is an open question. The Attorney General’s\npolicy seems to be to try to avoid the question by requiring minimally risky investments.\n 5\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 6 of 11\n\n\nof the Contract Clause. It also alleges that several differences between how the\n\nescrow statute is administered for NPMs and how MSA payments are\n\nadministered for PMs violate the Fourteenth Amendment’s Equal Protection\n\nClause. Finally, it alleges that it is owed a release of some excess escrow funds\n\ndue to having paid more than is required by state law.\n\n We start with S&M’s Contract Clause claim. The Contract Clause protects\n\ncontracting parties’ reasonable contractual expectations against unreasonable\n\nabrogation by the states. The threshold inquiry is whether the law “operate[s] as a\n\nsubstantial impairment of a contractual relationship” involving the plaintiff. Allied\n\nStructural Steel Co. v. Spannaus, 438 U.S. 234, 244, 98 S. Ct. 2716, 2722 (1978).\n\nIf an industry is already heavily regulated, regulatory changes that abrogate\n\nindustry players’ contract rights are less likely to be considered substantial\n\nimpairments. Energy Reserves Grp., Inc. v. Kan. Power & Light Co., 459 U.S.\n\n400, 413, 103 S. Ct. 697, 705 (1983). And when the subject matter of the contract\n\nitself is already subject to state regulation, the substantial-impairment case is even\n\nweaker. Veix v. Sixth Ward Bldg. & Loan Ass’n, 310 U.S. 32, 38, 60 S. Ct. 792,\n\n795 (1940).\n\n Here, S&M’s escrow agreement does not give rise to any reasonable\n\ncontractual expectations that implicate the Contract Clause. Every term of the old\n\nmodel escrow agreement was specifically dictated by the Attorney General as a\n\n 6\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 7 of 11\n\n\ncondition of approval under O.G.C.A. § 10-13A-3(d)(2). It is hard to say that such\n\na contract could give rise to any reasonable contractual expectations that would\n\nimplicate the Clause, at least vis-à-vis the state that dictated the terms. 3 Georgia\n\ndoes not strip itself of police power when it regulates by requiring private parties\n\nto contract. Nor does the Contract Clause ossify the state’s regulatory scheme in\n\nthese circumstances; the general rule, that states can exercise the police power to\n\nsupersede old regulations, prevails. 4 So S&M has not plausibly alleged a Contract\n\nClause violation.\n\n B.\n\n On to S&M’s Equal Protection claim. S&M alleges that it is similarly\n\nsituated to the PMs, who are also required to pay money into escrow, and that\n\nGeorgia is discriminating against them in favor of the PMs with no rational basis\n\nand in a way that burdens their fundamental right of free speech. Our threshold\n\ninquiry in an Equal Protection case is whether the plaintiff and the proposed\n\ncomparator are similarly situated, since the Equal Protection Clause requires that\n\n\n\n\n 3\n The analysis could, of course, be different if the State were a party to the contract,\nrather than a mere beneficiary. We do not mean to suggest that the State cannot bind itself by\ncontract to limit some of its own powers. See U.S. Tr. Co. v. New Jersey, 431 U.S. 1, 23–24, 97\nS. Ct. 1505, 1518 (1977).\n 4\n “One whose rights, such as they are, are subject to state restriction, cannot remove\nthem from the power of the state by making a contract about them. The contract will carry with\nit the infirmity of the subject-matter.” Hudson Cty. Water Co. v. McCarter, 209 U.S. 349, 357,\n28 S. Ct. 529, 531–32 (1908).\n 7\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 8 of 11\n\n\n“persons similarly situated . . . be treated alike.” City of Cleburne v. Cleburne\n\nLiving Ctr., 473 U.S. 432, 439, 105 S. Ct. 3249, 3254 (1985); see also Dawson v.\n\nScott, 50 F.3d 884, 892 (11th Cir. 1995). If the plaintiff has not been treated\n\ndifferently than a similarly situated comparator, no Equal Protection violation\n\nexists. Dawson, 50 F.3d at 892.\n\n Here, S&M Brands and the other NPMs are not similarly situated to the\n\nPMs with respect to the challenged provisions of law. The PMs have settled their\n\nliability to the state; S&M and the NPMs have not. The PMs need not establish an\n\ninsurance fund, since Georgia has contract remedies available if a PM fails to\n\nmake an MSA payment. S&M makes much of the fact that MSA payments are\n\nadministered via an escrow system with different investment restrictions than\n\nthose applicable to NPMs. But the NPM and PM escrow systems are not\n\ncomparable: NPM escrow money stays in escrow for 25 years and then returns to\n\nthe NPM unless taken to pay a claim, while PM payments stay in escrow for only\n\na few days or weeks while the monies owed to each state are apportioned. The\n\nrole of escrow is different in PM and NPM regulation, so Georgia may impose\n\ndifferent requirements on PM and NPM escrow accounts without violating equal\n\nprotection.\n\n All the provisions S&M challenges under the Equal Protection clause—the\n\ninvestment restrictions, the quarterly rather than annual deposit schedule, the\n\n 8\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 9 of 11\n\n\nregistered-agent and surety-bond requirements, and the delisting sanction for\n\nnoncompliance with the escrow statute—are provisions with respect to which PMs\n\nand NPMs are not similarly situated. So S&M has not plausibly alleged an Equal\n\nProtection violation.5\n\n C.\n\n S&M’s final claim is for a violation of state law; specifically, S&M claims\n\nthat the Attorney General was required to release escrow funds to it because it paid\n\nmore into escrow than it was required to under O.C.G.A. § 10-13-3(2)(B)(ii). The\n\nDistrict Court dismissed this claim under Rule 12(b)(1) for lack of jurisdiction.\n\nBecause the claim is barred by state sovereign immunity, we affirm.\n\n State sovereign immunity limits federal court jurisdiction. Seminole Tribe\n\nof Fla. v. Florida, 517 U.S. 44, 54, 116 S. Ct. 1114, 1122 (1996). Some suits\n\nrequesting injunctive or declaratory relief against state officials are not considered\n\nsuits against the state and thus are not barred by sovereign immunity. Ex parte\n\n\n\n\n 5\n S&M contends on appeal that its Complaint also states a standalone First Amendment\nclaim. We disagree. S&M makes one conclusory allegation of a First Amendment violation in\n¶ 114 of its Complaint; this is insufficient on its own to survive a motion to dismiss. See\nAshcroft v. Iqbal, 556 U.S. 662, 678, 129 S.Ct. 1937, 1949 (2009). S&M argues on appeal that\nthe facts it pleaded show that Georgia is either 1) coercing it to sign the MSA and thus waive its\nFirst Amendment rights or 2) neutralizing the effect of its commercial speech by imposing\neconomic disadvantages on it that are not imposed on the PMs. But neither of these theories are\nplausibly supported by factual allegations in S&M’s Complaint. S&M has not alleged that it\nwould be better off economically if it joined the MSA, a necessary component of its coercion\ntheory. Nor has S&M alleged that the restrictions are sufficiently tied to its speech to support a\nclaim on its neutralization theory. So S&M has not stated a First Amendment claim.\n 9\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 10 of 11\n\n\nYoung, 209 U.S. 123, 159–60, 28 S.Ct. 441, 454 (1908) (injunctive relief); Verizon\n\nMd., Inc. v. Pub. Serv. Comm'n of Md., 535 U.S. 635, 646, 122 S. Ct. 1753, 1760\n\n(2002) (declaratory relief). But when the claim of entitlement to relief is based on\n\na violation of state law, sovereign immunity applies. Pennhurst State Sch. &\n\nHosp. v. Halderman, 465 U.S. 89, 121, 104 S. Ct. 900, 919 (1984). And\n\nconclusory allegations that the same conduct that violates state law also violates\n\nthe U.S. Constitution will not boost the claim over the sovereign-immunity bar.\n\nDeKalb Cty. Sch. Dist. v. Schrenko, 109 F.3d 680, 688 (11th Cir. 1997).\n\n Schrenko’s facts are on point. There, a school district sought\n\nreimbursement from the state of Georgia for transportation costs. Id. at 684–85.\n\nThe entitlement to and amount of reimbursement were determined by a state\n\nstatute. Id. at 688. Although the school district referenced the Fourteenth\n\nAmendment and federal statutory law in its complaint, its claim necessarily relied\n\non a determination that state officials had not complied with state law. We thus\n\nheld the claim barred by sovereign immunity. Id. at 690.\n\n Here, S&M’s claim is that Georgia is required to release escrow funds back\n\nto it. Georgia’s obligation to do this comes from state law; specifically, O.C.G.A.\n\n§ 10-13-3(2)(B)(ii), which provides for release of excess escrow funds in the event\n\nan NPM deposits more than it would have paid in MSA payments were it a PM.\n\nS&M claims that this is really a constitutional claim, since the refusal to release\n\n 10\n\f Case: 17-13261 Date Filed: 05/29/2019 Page: 11 of 11\n\n\nfunds serves to coerce it to give up its First Amendment rights and constitutes a\n\nFifth Amendment taking.\n\n We don’t buy it. Here, as in Schrenko, the obligation to release (or\n\nreimburse) funds comes from state law. The proper release amount is determined\n\nby state law. Accordingly, the “gravamen of [the] complaint appears to be that the\n\nState has improperly interpreted and failed to adhere to a state statute,” and\n\nPennhurst bars such claims. Id. at 688. We affirm the dismissal of S&M’s state-\n\nlaw claim.\n\n For the foregoing reasons, the dismissal of S&M Brands’ Complaint is\n\n AFFIRMED.\n\n\n\n\n 11\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: S&M BRANDS, INC., Plaintiff - Appellant, v. State of GEORGIA EX REL., Christopher M. CARR, Attorney General, Defendant - Appellee.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-29\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-13261 Date Filed: 05/29/2019 Page: 1 of 11\\n\\n\\n [PUBLISH]\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-13261\\n ________________________\\n\\n D.C. Docket No. 1:16-cv-04469-SCJ\\n\\n\\nS&M BRANDS, INC.,\\n\\n Plaintiff – Appellant,\\n\\n versus\\n\\nSTATE OF GEORGIA EX REL.,\\nChristopher M. Carr, Attorney General,\\n\\n Defendant – Appellee.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Northern District of Georgia\\n ________________________\\n\\n (May 29, 2019)\\n\\nBefore TJOFLAT and ROSENBAUM, Circuit Judges, and UNGARO, * District\\nJudge.\\n\\n\\n\\n *\\n Honorable Ursula Ungaro, United States District Judge for the Southern District of\\n Florida, sitting by designation.\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 2 of 11\\n\\n\\nTJOFLAT, Circuit Judge:\\n\\n S&M Brands, Inc., a tobacco producer, appeals the dismissal of its suit\\n\\nagainst the State of Georgia. In its complaint for declaratory and injunctive relief,\\n\\nS&M pleaded several constitutional and state-law violations based on Georgia’s\\n\\nscheme of tobacco regulation. Georgia moved to dismiss, and the District Court\\n\\ngranted the motion, dismissing the complaint on the grounds that its allegations\\n\\ndid not amount to constitutional violations and its state-law claims were barred by\\n\\nsovereign immunity. After thorough consideration, and with the benefit of oral\\n\\nargument, we affirm the dismissal of S&M’s complaint.\\n\\n I.\\n\\n Every tobacco producer that operates in Georgia is licensed to do business\\n\\nvia one of two routes. Many of the producers are parties to the Master Settlement\\n\\nAgreement (“MSA”), a 20-year-old omnibus settlement between the tobacco\\n\\nindustry and most U.S. states, including Georgia. KT & G Corp. v. Att’y Gen. of\\n\\nState of Okla., 535 F.3d 1114, 1118–19 (10th Cir. 2008); see generally Nat’l Ass’n\\n\\nof Att’ys Gen., Master Settlement Agreement (1999) (hereinafter “MSA”). These\\n\\nproducers—the “participating manufacturers,” or PMs—are saddled with ongoing\\n\\nobligations under the MSA, including a collective payment obligation of billions\\n\\nof dollars per year, in exchange for the states’ releasing them from liability for\\n\\nstate public-health expenditures caused by cigarette smoking. MSA §§ I, II(jj).\\n\\n 2\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 3 of 11\\n\\n\\nOther producers—the “non-participating manufacturers,” or NPMs—did not sign\\n\\nthe MSA, do not make payments to the states, and could potentially be sued in the\\n\\nfuture if they incur liability for the states’ public-health costs. Since NPMs may\\n\\nbecome liable, Georgia requires them to self-insure by contracting with an escrow\\n\\nagent to establish an escrow fund into which they pay a set amount per cigarette\\n\\nsold. O.G.C.A. § 10-13-3(2)(A). Otherwise, an NPM could make short-term\\n\\nprofits, rack up liability to the state, and then become judgment-proof before the\\n\\nstate could recover its public-health expenditures. Id. § 10-13-1(f). PMs are not\\n\\nrequired to self-insure; their liability is already settled, and they are contractually\\n\\nrequired to make payments. Id. § 10-13-3.\\n\\n NPM escrow funds are governed by the requirements of Georgia’s escrow\\n\\nstatute, which is implemented and enforced by the Attorney General. Id. § 10-13-\\n\\n3(2)(C). The principal funds deposited are available to pay judgments on or\\n\\nsettlements of claims like those settled in the MSA. Id. § 10-13-3(2)(B)(i). If not\\n\\npaid to the state, the funds are returned to the NPM after 25 years. Id. § 10-13-\\n\\n3(2)(B)(iii). The interest and other returns on the invested deposits are paid to the\\n\\nNPM as earned. Id. § 10-13-3(2)(B). NPMs must make several quarterly and\\n\\nannual certifications, including that they have complied with the escrow statute\\n\\nand that their funds are governed by a compliant escrow agreement that has been\\n\\nreviewed and approved by the Attorney General. Id. §§ 10-13-3(2)(C), 10-13A-\\n\\n 3\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 4 of 11\\n\\n\\n3(d)(2). The Attorney General has exercised his review and approval authority by\\n\\nrequiring that each NPM use a model escrow agreement drafted by his office. 1 The\\n\\nAttorney General’s model escrow agreement includes investment class restrictions\\n\\nfor escrow funds: only cash, a money-market fund, and U.S. Treasury securities\\n\\nare permitted investments. Noncompliance with the escrow statute or the Attorney\\n\\nGeneral’s requirements can lead to a statewide ban on sales of the NPM’s\\n\\nproducts. O.G.C.A. §§ 10-13A-4(b), 10-13A-5.\\n\\n S&M Brands is an NPM and has operated in Georgia for decades. From the\\n\\nsigning of the MSA and imposition of the two-route scheme until 2016, S&M\\n\\nperformed its obligations under the escrow statute. Back then, the escrow statute\\n\\ndid not impose any restrictions on escrow fund investments; the restrictions came\\n\\nsolely from the Attorney General’s prerogative to deny approval to NPM escrow\\n\\nagreements, informed by the State’s general policy of seeking to ensure a source\\n\\nof recovery from potential-defendant NPMs. In 2016, the General Assembly\\n\\namended the escrow statute, adding a provision that requires the value of the\\n\\n\\n\\n\\n 1\\n This requirement raises a thorny question of Georgia administrative law: does the\\nAttorney General have discretion to refuse to approve an escrow agreement that meets all the\\nsubstantive requirements of the escrow statute? Answering that question would require a\\nthorough inquiry into Georgia’s Administrative Procedure Act and the caselaw interpreting it.\\nBut this issue is not before us—the District Court dismissed S&M’s claim raising this point, and\\nS&M has not appealed that ruling—so we will operate under the assumption that the Attorney\\nGeneral’s review-and-approval authority allows him to require a specific form agreement.\\n 4\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 5 of 11\\n\\n\\nescrow fund not to diminish below the amount paid into it. 2 2016 Ga. Laws 529–\\n\\n30. To implement this amendment, the Attorney General’s office modified its\\n\\nform escrow agreement, changing the list of permitted investments for escrow\\n\\nfunds. Formerly, escrow monies could be invested in any U.S. Treasury\\n\\nsecurities; under the new model agreement, any U.S. Treasury securities bought\\n\\nwith escrow funds must mature in no more than 20 years, although already-\\n\\npurchased securities may be kept until they mature or are sold.\\n\\n S&M sued to enjoin the Attorney General from requiring it to use the\\n\\nrevised escrow agreement. The District Court dismissed the case, and this appeal\\n\\nfollowed. We affirm.\\n\\n II.\\n\\n A.\\n\\n S&M alleges that the investment restrictions in the revised escrow\\n\\nagreement reduce the returns it can expect to earn on its escrow money, and the\\n\\nAttorney General’s imposition of the new restrictions (pursuant to the statutory\\n\\namendment) is a “Law impairing the Obligation of Contracts” within the meaning\\n\\n\\n\\n 2\\n The statute is ambiguous as to what would be required if the value of the escrow\\ninvestments were to dip below the amount of principal deposited. If this were to happen, then\\npresumably the NPM could not certify that its escrow fund was compliant; it would have to\\nmake up the difference by depositing additional funds in order to so certify. But the statute\\nmakes no express provision for supplemental deposits, and whether such deposits could be\\nrequired (and how they would be administered) is an open question. The Attorney General’s\\npolicy seems to be to try to avoid the question by requiring minimally risky investments.\\n 5\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 6 of 11\\n\\n\\nof the Contract Clause. It also alleges that several differences between how the\\n\\nescrow statute is administered for NPMs and how MSA payments are\\n\\nadministered for PMs violate the Fourteenth Amendment’s Equal Protection\\n\\nClause. Finally, it alleges that it is owed a release of some excess escrow funds\\n\\ndue to having paid more than is required by state law.\\n\\n We start with S&M’s Contract Clause claim. The Contract Clause protects\\n\\ncontracting parties’ reasonable contractual expectations against unreasonable\\n\\nabrogation by the states. The threshold inquiry is whether the law “operate[s] as a\\n\\nsubstantial impairment of a contractual relationship” involving the plaintiff. Allied\\n\\nStructural Steel Co. v. Spannaus, 438 U.S. 234, 244, 98 S. Ct. 2716, 2722 (1978).\\n\\nIf an industry is already heavily regulated, regulatory changes that abrogate\\n\\nindustry players’ contract rights are less likely to be considered substantial\\n\\nimpairments. Energy Reserves Grp., Inc. v. Kan. Power & Light Co., 459 U.S.\\n\\n400, 413, 103 S. Ct. 697, 705 (1983). And when the subject matter of the contract\\n\\nitself is already subject to state regulation, the substantial-impairment case is even\\n\\nweaker. Veix v. Sixth Ward Bldg. & Loan Ass’n, 310 U.S. 32, 38, 60 S. Ct. 792,\\n\\n795 (1940).\\n\\n Here, S&M’s escrow agreement does not give rise to any reasonable\\n\\ncontractual expectations that implicate the Contract Clause. Every term of the old\\n\\nmodel escrow agreement was specifically dictated by the Attorney General as a\\n\\n 6\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 7 of 11\\n\\n\\ncondition of approval under O.G.C.A. § 10-13A-3(d)(2). It is hard to say that such\\n\\na contract could give rise to any reasonable contractual expectations that would\\n\\nimplicate the Clause, at least vis-à-vis the state that dictated the terms. 3 Georgia\\n\\ndoes not strip itself of police power when it regulates by requiring private parties\\n\\nto contract. Nor does the Contract Clause ossify the state’s regulatory scheme in\\n\\nthese circumstances; the general rule, that states can exercise the police power to\\n\\nsupersede old regulations, prevails. 4 So S&M has not plausibly alleged a Contract\\n\\nClause violation.\\n\\n B.\\n\\n On to S&M’s Equal Protection claim. S&M alleges that it is similarly\\n\\nsituated to the PMs, who are also required to pay money into escrow, and that\\n\\nGeorgia is discriminating against them in favor of the PMs with no rational basis\\n\\nand in a way that burdens their fundamental right of free speech. Our threshold\\n\\ninquiry in an Equal Protection case is whether the plaintiff and the proposed\\n\\ncomparator are similarly situated, since the Equal Protection Clause requires that\\n\\n\\n\\n\\n 3\\n The analysis could, of course, be different if the State were a party to the contract,\\nrather than a mere beneficiary. We do not mean to suggest that the State cannot bind itself by\\ncontract to limit some of its own powers. See U.S. Tr. Co. v. New Jersey, 431 U.S. 1, 23–24, 97\\nS. Ct. 1505, 1518 (1977).\\n 4\\n “One whose rights, such as they are, are subject to state restriction, cannot remove\\nthem from the power of the state by making a contract about them. The contract will carry with\\nit the infirmity of the subject-matter.” Hudson Cty. Water Co. v. McCarter, 209 U.S. 349, 357,\\n28 S. Ct. 529, 531–32 (1908).\\n 7\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 8 of 11\\n\\n\\n“persons similarly situated . . . be treated alike.” City of Cleburne v. Cleburne\\n\\nLiving Ctr., 473 U.S. 432, 439, 105 S. Ct. 3249, 3254 (1985); see also Dawson v.\\n\\nScott, 50 F.3d 884, 892 (11th Cir. 1995). If the plaintiff has not been treated\\n\\ndifferently than a similarly situated comparator, no Equal Protection violation\\n\\nexists. Dawson, 50 F.3d at 892.\\n\\n Here, S&M Brands and the other NPMs are not similarly situated to the\\n\\nPMs with respect to the challenged provisions of law. The PMs have settled their\\n\\nliability to the state; S&M and the NPMs have not. The PMs need not establish an\\n\\ninsurance fund, since Georgia has contract remedies available if a PM fails to\\n\\nmake an MSA payment. S&M makes much of the fact that MSA payments are\\n\\nadministered via an escrow system with different investment restrictions than\\n\\nthose applicable to NPMs. But the NPM and PM escrow systems are not\\n\\ncomparable: NPM escrow money stays in escrow for 25 years and then returns to\\n\\nthe NPM unless taken to pay a claim, while PM payments stay in escrow for only\\n\\na few days or weeks while the monies owed to each state are apportioned. The\\n\\nrole of escrow is different in PM and NPM regulation, so Georgia may impose\\n\\ndifferent requirements on PM and NPM escrow accounts without violating equal\\n\\nprotection.\\n\\n All the provisions S&M challenges under the Equal Protection clause—the\\n\\ninvestment restrictions, the quarterly rather than annual deposit schedule, the\\n\\n 8\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 9 of 11\\n\\n\\nregistered-agent and surety-bond requirements, and the delisting sanction for\\n\\nnoncompliance with the escrow statute—are provisions with respect to which PMs\\n\\nand NPMs are not similarly situated. So S&M has not plausibly alleged an Equal\\n\\nProtection violation.5\\n\\n C.\\n\\n S&M’s final claim is for a violation of state law; specifically, S&M claims\\n\\nthat the Attorney General was required to release escrow funds to it because it paid\\n\\nmore into escrow than it was required to under O.C.G.A. § 10-13-3(2)(B)(ii). The\\n\\nDistrict Court dismissed this claim under Rule 12(b)(1) for lack of jurisdiction.\\n\\nBecause the claim is barred by state sovereign immunity, we affirm.\\n\\n State sovereign immunity limits federal court jurisdiction. Seminole Tribe\\n\\nof Fla. v. Florida, 517 U.S. 44, 54, 116 S. Ct. 1114, 1122 (1996). Some suits\\n\\nrequesting injunctive or declaratory relief against state officials are not considered\\n\\nsuits against the state and thus are not barred by sovereign immunity. Ex parte\\n\\n\\n\\n\\n 5\\n S&M contends on appeal that its Complaint also states a standalone First Amendment\\nclaim. We disagree. S&M makes one conclusory allegation of a First Amendment violation in\\n¶ 114 of its Complaint; this is insufficient on its own to survive a motion to dismiss. See\\nAshcroft v. Iqbal, 556 U.S. 662, 678, 129 S.Ct. 1937, 1949 (2009). S&M argues on appeal that\\nthe facts it pleaded show that Georgia is either 1) coercing it to sign the MSA and thus waive its\\nFirst Amendment rights or 2) neutralizing the effect of its commercial speech by imposing\\neconomic disadvantages on it that are not imposed on the PMs. But neither of these theories are\\nplausibly supported by factual allegations in S&M’s Complaint. S&M has not alleged that it\\nwould be better off economically if it joined the MSA, a necessary component of its coercion\\ntheory. Nor has S&M alleged that the restrictions are sufficiently tied to its speech to support a\\nclaim on its neutralization theory. So S&M has not stated a First Amendment claim.\\n 9\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 10 of 11\\n\\n\\nYoung, 209 U.S. 123, 159–60, 28 S.Ct. 441, 454 (1908) (injunctive relief); Verizon\\n\\nMd., Inc. v. Pub. Serv. Comm'n of Md., 535 U.S. 635, 646, 122 S. Ct. 1753, 1760\\n\\n(2002) (declaratory relief). But when the claim of entitlement to relief is based on\\n\\na violation of state law, sovereign immunity applies. Pennhurst State Sch. &\\n\\nHosp. v. Halderman, 465 U.S. 89, 121, 104 S. Ct. 900, 919 (1984). And\\n\\nconclusory allegations that the same conduct that violates state law also violates\\n\\nthe U.S. Constitution will not boost the claim over the sovereign-immunity bar.\\n\\nDeKalb Cty. Sch. Dist. v. Schrenko, 109 F.3d 680, 688 (11th Cir. 1997).\\n\\n Schrenko’s facts are on point. There, a school district sought\\n\\nreimbursement from the state of Georgia for transportation costs. Id. at 684–85.\\n\\nThe entitlement to and amount of reimbursement were determined by a state\\n\\nstatute. Id. at 688. Although the school district referenced the Fourteenth\\n\\nAmendment and federal statutory law in its complaint, its claim necessarily relied\\n\\non a determination that state officials had not complied with state law. We thus\\n\\nheld the claim barred by sovereign immunity. Id. at 690.\\n\\n Here, S&M’s claim is that Georgia is required to release escrow funds back\\n\\nto it. Georgia’s obligation to do this comes from state law; specifically, O.C.G.A.\\n\\n§ 10-13-3(2)(B)(ii), which provides for release of excess escrow funds in the event\\n\\nan NPM deposits more than it would have paid in MSA payments were it a PM.\\n\\nS&M claims that this is really a constitutional claim, since the refusal to release\\n\\n 10\\n\\f Case: 17-13261 Date Filed: 05/29/2019 Page: 11 of 11\\n\\n\\nfunds serves to coerce it to give up its First Amendment rights and constitutes a\\n\\nFifth Amendment taking.\\n\\n We don’t buy it. Here, as in Schrenko, the obligation to release (or\\n\\nreimburse) funds comes from state law. The proper release amount is determined\\n\\nby state law. Accordingly, the “gravamen of [the] complaint appears to be that the\\n\\nState has improperly interpreted and failed to adhere to a state statute,” and\\n\\nPennhurst bars such claims. Id. at 688. We affirm the dismissal of S&M’s state-\\n\\nlaw claim.\\n\\n For the foregoing reasons, the dismissal of S&M Brands’ Complaint is\\n\\n AFFIRMED.\\n\\n\\n\\n\\n 11\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2295,"cells":{"id":{"kind":"number","value":4624568,"string":"4,624,568"},"name":{"kind":"string","value":"A&M GERBER CHIROPRACTIC LLC, as Assignee of Conor Carruthers, on Behalf of Itself and All Others Similarly Situated, Plaintiff - Appellee, v. GEICO GENERAL INSURANCE COMPANY, Defendant - Appellant."},"name_abbreviation":{"kind":"string","value":"A&M Gerber Chiropractic LLC v. GEICO General Insurance Company"},"decision_date":{"kind":"string","value":"2019-05-30"},"docket_number":{"kind":"string","value":"17-15606"},"court":{"kind":"string","value":"U.S. Court of Appeals for the Eleventh Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Wilson, Branch, Vinson\", \"parties\": \"\", \"opinions\": [{\"author\": \"VINSON, District Judge:\", \"type\": \"010combined\", \"text\": \"Case: 17-15606 Date Filed: 05/30/2019 Page: 1 of 23\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15606\\n ________________________\\n\\n D.C. Docket No. 0:16-cv-62610-BB\\n\\n\\nA&M GERBER CHIROPRACTIC LLC,\\nas assignee of Conor Carruthers, on behalf\\nof itself and all others similarly situated,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nGEICO GENERAL INSURANCE COMPANY,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 30, 2019)\\n\\n ON PETITION FOR REHEARING\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 2 of 23\\n\\n\\nBefore WILSON and BRANCH, Circuit Judges, and VINSON,∗ District Judge.\\n\\nVINSON, District Judge:\\n\\n Upon consideration, we grant the Appellee’s petition for panel rehearing.\\n\\nWe vacate our prior opinion in this case, issued on April 19, 2019, and published at\\n\\n921 F.3d 1273 (11th Cir. 2019), and hereby substitute the following opinion in its\\n\\nplace.\\n\\n Conor Carruthers was involved in a car accident on March 18, 2015, after\\n\\nwhich he sought medical services from A&M Gerber Chiropractic LLC. At the\\n\\ntime, Carruthers was covered under an automobile insurance policy issued by\\n\\nGEICO General Insurance Company. Pursuant to Florida’s Motor Vehicle No-\\n\\nFault Law, the policy provided him with $10,000 in personal injury protection\\n\\n(PIP) benefits. See Fla. Stat. § 627.736(1) (mandating that automobile insurers\\n\\nprovide PIP benefits “to a limit of $10,000”). To be entitled to the full $10,000,\\n\\nhowever, the statute required that Carruthers—like all PIP beneficiaries—be\\n\\ndiagnosed by an authorized health care provider with an “emergency medical\\n\\ncondition” (EMC); without such a diagnosis, he was limited to $2,500 in benefits.\\n\\nSee id. at § 627.736(1)(a)(3)-(4); Robbins v. Garrison Prop. & Cas. Ins. Co., 809\\n\\nF.3d 583, 587-88 (11th Cir. 2015) (holding in consolidated appeal that “[b]ecause\\n\\n\\n\\n ∗Honorable C. Roger Vinson, United States District Judge for the Northern District of\\nFlorida, sitting by designation.\\n 2\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 3 of 23\\n\\n\\nneither Robbins’ nor Enivert’s claim was supported by [an EMC determination],\\n\\nneither Garrison nor Progressive violated Fla. Stat. § 627.736 by limiting benefits\\n\\nto $2,500”); accord, e.g., Progressive Am. Ins. Co. v. Eduardo J. Garrido D.C.,\\n\\nP.A., 211 So.3d 1086, 1093 (Fla. 3d DCA 2017); Medical Ctr. of Palm Beaches v.\\n\\nUSAA Cas. Ins. Co., 202 So.3d 88, 92-93 (Fla. 4th DCA 2016); McCarty v. Myers,\\n\\n125 So.3d 333, 335 (Fla. 1st DCA 2013).\\n\\n It is undisputed that Carruthers was not diagnosed with an EMC at the time\\n\\nthis case was filed. It is also undisputed that, despite the lack of an EMC finding,\\n\\nGEICO paid Carruthers/Gerber $7,311 in PIP benefits pre-suit, well in excess of\\n\\nthe $2,500 cap. Even though Carruthers received almost triple the amount in PIP\\n\\nbenefits that he was entitled to, Gerber believed that GEICO had misinterpreted\\n\\ncertain language in its automobile policies and that this misinterpretation resulted\\n\\nin GEICO consistently underpaying PIP benefits as a “general business practice.”\\n\\n Specifically, the policy contains an endorsement identified as FLPIP (01-\\n\\n13), and that endorsement (under the heading “PAYMENTS WE WILL MAKE”)\\n\\nreferences fee schedules pursuant to which GEICO will pay 80% of benefits that\\n\\nare medically necessary. The endorsement goes on to state: “For all other medical\\n\\nservices, supplies, and care [GEICO will pay] 200 percent of the allowable amount\\n\\nunder [a Medicare Part B fee schedule],” subject to a limitation of 80% of the\\n\\n“maximum reimbursable allowance under workers’ compensation . . . .” Below\\n\\n\\n 3\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 4 of 23\\n\\n\\nthat statement, GEICO added the following: “A charge submitted by a provider,\\n\\nfor an amount less than the amount allowed above, shall be paid in the amount of\\n\\nthe charge submitted.” The underlying dispute in this case hinges on whether this\\n\\nsingle sentence is the operative language of the policy for health care provider bills\\n\\nof less than 200% of the fee schedule.\\n\\n GEICO has taken the position that the policy is an “80/20 policy” pursuant\\n\\nto which it was required to pay the lower of 80% of the fee schedule amount or\\n\\n80% of the charged amount, while insureds are required to pay the remaining 20%\\n\\nas co-insurance. To supports its position, GEICO relied, inter alia, on a document\\n\\nmailed or provided to its PIP policyholders effective on or after January 1, 2013,\\n\\nand identified as M608 (01-13). This document was titled\\n\\n IMPORTANT NOTICE\\n\\n FEE SCHEDULE ENDORSEMENT\\n\\nand it provides in relevant part that “in no event will the Company pay more than\\n\\n80 percent” of properly billed medical expenses. GEICO asserts that M608 (01-\\n\\n13) is an endorsement and, thus, part of the policy. Gerber has argued that M608\\n\\n(01-13) is not an endorsement/part of the policy, and it further argues that FLPIP\\n\\n(01-13) provides that when a health care provider bills for services at an amount\\n\\nless than 200% of the fee schedule, GEICO must pay the charge as billed (that is,\\n\\n“in the amount of the charge submitted”) without the 20% reduction.\\n\\n\\n 4\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 5 of 23\\n\\n\\n Carruthers assigned his rights to his treating chiropractic clinic, Gerber,\\n\\nwhich later filed a declaratory judgment class action suit in Florida state court in\\n\\nSeptember 2016. The complaint sought certification of a class (with Gerber as the\\n\\nclass representative) along with a declaration (a) that GEICO’s interpretation of its\\n\\npolicy language was wrong, and (b) that the misinterpretation “constitutes a breach\\n\\nof the insurance Policy.” Although the complaint sought a declaration that GEICO\\n\\nhad breached the policy, the complaint stated that “there is no claim for monetary\\n\\nrelief” in the case.\\n\\n GEICO removed the case to the United States District Court for the\\n\\nSouthern District of Florida in November 2016, pursuant to the Class Action\\n\\nFairness Act, and Gerber filed an unsuccessful motion to remand the case for lack\\n\\nof Article III standing. The District Court appointed Gerber as class\\n\\nrepresentative, and it certified the class to include:\\n\\n All health care providers that received an assignment of\\n benefits from a claimant and thereafter, pursuant to that\\n assignment, submitted claims for no-fault benefits under\\n GEICO PIP policies to which Endorsement FLPIP (01–\\n 13) applies, and any subsequent policies with\\n substantially similar language that were in effect since\\n January 1, 2013, where GEICO utilized the Code BA\\n [billed amount] with respect to the payment of any\\n claims.\\n\\n Shortly after the action was removed to federal court, and while its motion to\\n\\nremand was pending, Gerber filed an amended complaint. The amended complaint\\n\\n\\n 5\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 6 of 23\\n\\n\\nwas largely the same as the original complaint, but it added another sentence to re-\\n\\nemphasize that “this action does not assert a claim for any monetary relief,” and it\\n\\ndeleted the request for a declaration that GEICO’s misinterpretation of the disputed\\n\\npolicy language “constitutes a breach of the insurance Policy.” Thus, as amended,\\n\\nthe complaint clarified that it only sought declaratory relief and that there was no\\n\\nclaim for breach of contract or request for money damages related thereto. In July\\n\\n2017—more than two years after the underlying car accident, and ten months after\\n\\nthe litigation was filed—Carruthers obtained an EMC medical diagnosis.\\n\\n On cross motions for summary judgment, GEICO argued, inter alia, that\\n\\nGerber lacked standing at the outset of the lawsuit because it was undisputed that\\n\\nGEICO had paid Gerber more than $2,500 before the case was filed, even though\\n\\nhe had not been diagnosed with an EMC at that time. By order dated November\\n\\n17, 2017, the District Court disagreed with GEICO and found there was standing.\\n\\nIt also ruled that M608 (01-13) was not an endorsement (but rather was merely a\\n\\nnotice) and, thus, it was not part of the policy. Applying a textual interpretation of\\n\\nthe FLPIP (01-13) endorsement, the District Court granted summary judgment for\\n\\nGerber and held that, “under the disputed provision, when a health care provider\\n\\nbills for covered services in an amount less than 200% of the fee schedule, GEICO\\n\\nis required to pay the charge as billed without any reduction.”\\n\\n\\n\\n\\n 6\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 7 of 23\\n\\n\\n GEICO now appeals, arguing that Gerber lacked standing to bring this case.\\n\\nIt further argues that the District Court erred in certifying the class; in limiting the\\n\\ndocuments that comprise the policy (that is, in failing to treat M608 (01-13) as an\\n\\nendorsement); and in ruling for Gerber on the merits as to the policy interpretation\\n\\nquestion.\\n\\n I.\\n\\n We must begin with the question of standing. See Kondrat’yev v. City of\\n\\nPensacola, Fla., 903 F.3d 1169, 1172 (11th Cir. 2018). If there is no standing, we\\n\\nmust end there, too. University of S. Ala. v. American Tobacco Co., 168 F.3d 405,\\n\\n410 (11th Cir. 1999) (“Simply put, once a federal court determines that [the\\n\\nplaintiff has no standing], the court is powerless to continue.”).\\n\\n We review standing determinations de novo. See, e.g., SEC v. Quest Energy\\n\\nMgmt. Group, Inc., 768 F.3d 1106, 1108 (11th Cir. 2014) (citing CAMP Legal Def.\\n\\nFund, Inc. v. City of Atlanta, 451 F.3d 1257, 1268 (11th Cir. 2006)). After de novo\\n\\nreview—and with the benefit of oral argument—we conclude that Gerber lacks\\n\\nstanding.\\n\\n II.\\n\\n Article III of the Constitution limits federal courts to adjudicating actual\\n\\n“cases” and “controversies.” See, e.g., Allen v. Wright, 468 U.S. 737, 750 (1984),\\n\\nabrogated on other grounds by Lexmark Int’l, Inc. v. Static Control Components,\\n\\n\\n 7\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 8 of 23\\n\\n\\nInc., 572 U.S. 118 (2014). The case-or-controversy requirement sets fundamental\\n\\nlimits on federal judicial power. Id. “Perhaps the most important of the Article III\\n\\ndoctrines grounded in the case-or-controversy requirement is that of standing.”\\n\\nWooden v. Bd. of Regents of the Univ. Sys. of Ga., 247 F.3d 1262, 1273 (11th Cir.\\n\\n2001). Standing cannot be waived or conceded by the parties, and it may be raised\\n\\n(even by the court sua sponte) at any stage of the case. See Bender v. Williamsport\\n\\nArea Sch. Dist., 475 U.S. 534, 541 (1986); Harris v. Evans, 20 F.3d 1118, 1121 n.4\\n\\n(11th Cir. 1994).\\n\\n “In essence the question of standing is whether the litigant is entitled to\\n\\nhave the court decide the merits of the dispute or of particular issues.” Warth v.\\n\\nSeldin, 422 U.S. 490, 498 (1975); see also Yellow Pages Photos, Inc. v. Ziplocal,\\n\\nLP, 795 F.3d 1255, 1264 (11th Cir. 2015) (same). “The party who invokes a\\n\\nfederal court’s authority must show, at an ‘irreducible minimum,’ that at the time\\n\\nthe complaint was filed, he has suffered some actual or threatened injury resulting\\n\\nfrom the defendant’s conduct, that the injury fairly can be traced to the challenged\\n\\naction, and that the injury is likely to be redressed by favorable court disposition.”\\n\\nAtlanta Gas Light Co. v. Aetna Cas. & Sur. Co., 68 F.3d 409, 414 (11th Cir. 1995).\\n\\n Echoing the “case or controversy” requirement of Article III, the Declaratory\\n\\nJudgment Act “provides that a declaratory judgment may only be issued in the case\\n\\nof an actual controversy.” See Emory v. Peeler, 756 F.2d 1547, 1551-52 (11th Cir.\\n\\n\\n 8\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 9 of 23\\n\\n\\n1985) (citing 28 U.S.C. § 2201); see also Atlanta Gas Light, 68 F.3d at 414 (“In all\\n\\ncases arising under the Declaratory Judgment Act, . . . the threshold question is\\n\\nwhether a justiciable controversy exists.”). “That is, under the facts alleged, there\\n\\nmust be a substantial continuing controversy between parties having adverse legal\\n\\ninterests.” Emory, 756 F.2d at 1552. The controversy between the parties cannot\\n\\nbe “conjectural, hypothetical, or contingent; it must be real and immediate, and\\n\\ncreate a definite, rather than speculative threat of future injury.” Id. In order to\\n\\ndemonstrate that there is a case or controversy that satisfies Article III’s standing\\n\\nrequirement when a plaintiff is seeking declaratory relief—as opposed to seeking\\n\\ndamages for past harm—the plaintiff must allege facts from which it appears that\\n\\nthere is a “substantial likelihood that he will suffer injury in the future.” Malowney\\n\\nv. Federal Collection Deposit Grp., 193 F.3d 1342, 1346 (11th Cir. 1999); accord\\n\\nStrickland v. Alexander, 772 F.3d 876, 883 (11th Cir. 2014) (“Where the plaintiff\\n\\nseeks declaratory or injunctive relief, as opposed to damages for injuries already\\n\\nsuffered, . . . the injury-in-fact requirement insists that a plaintiff ‘allege facts from\\n\\nwhich it appears there is a substantial likelihood that he will suffer injury in the\\n\\nfuture.’”) (quoting Malowney, 193 F.3d at 1346). “Thus, in order for this Court to\\n\\nhave jurisdiction to issue a declaratory judgment, . . . [the plaintiffs] must assert a\\n\\nreasonable expectation that the injury they have suffered will continue or will be\\n\\nrepeated in the future.” Malowney, 193 F.3d at 1347; see also id. at 1348 (“Injury\\n\\n\\n 9\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 10 of 23\\n\\n\\nin the past . . . does not support a finding of an Article III case or controversy when\\n\\nthe only relief sought is a declaratory judgment.”). Accordingly, if a plaintiff does\\n\\nnot assert a reasonable expectation of future injury, he “lack[s] standing to bring an\\n\\naction for declaratory relief[.]” See id. at 1348.\\n\\n In this case, Gerber, as assignee, stands in Carruthers’ shoes. Houk v. C.I.R.,\\n\\n173 F.2d 821, 825 (5th Cir. 1949) (“[A]n assignee . . . stands in the same position\\n\\nas its assignor had stood.”).1 It necessarily follows, then, that if Carruthers had no\\n\\nstanding to file this case against GEICO, Gerber has no standing either. Crossman\\n\\nv. Fontainebleau Hotel Corp., 273 F.2d 720, 725 (5th Cir. 1959) (“An assignee has\\n\\nno greater rights than his assignor[.]”).\\n\\n It is well-settled that “if none of the named plaintiffs purporting to represent\\n\\na class establishes the requisite of a case or controversy with the defendants, none\\n\\nmay seek relief on behalf of himself or any other member of the class.” O’Shea v.\\n\\nLittleton, 414 U.S. 488, 494 (1974); see also Prado-Steiman ex rel. Prado v. Bush,\\n\\n221 F.3d 1266, 1279-80 (11th Cir. 2000) (class representative must have individual\\n\\nstanding to raise class claims); Wooden, 247 F.3d at 1288 (claim cannot be asserted\\n\\nfor a class “‘unless at least one named plaintiff has suffered the injury that gives\\n\\nrise to that claim’”) (quoting Prado-Steiman, 221 F.3d at 1280). As we have said:\\n\\n\\n 1\\n In Bonner v. City of Prichard, 661 F.2d 1206, 1209 (11th Cir. 1981) (en banc), we adopted\\nas binding precedent all Fifth Circuit decisions rendered prior to the close of business on September\\n30, 1981.\\n 10\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 11 of 23\\n\\n\\n Under elementary principles of standing, a plaintiff must\\n allege and show that he personally suffered injury. If he\\n cannot show personal injury, then no article III case or\\n controversy exists, and a federal court is powerless to\\n hear his grievance. This individual injury requirement is\\n not met by alleging that injury has been suffered by\\n other, unidentified members of the class to which the\\n plaintiff belongs and which he purports to represent.\\n Thus, a plaintiff cannot include class action allegations in\\n a complaint and expect to be relieved of personally\\n meeting the requirements of constitutional standing, even\\n if the persons described in the class definition would\\n have standing themselves to sue. A named plaintiff in a\\n class action who cannot establish the requisite case or\\n controversy between himself and the defendants simply\\n cannot seek relief for anyone—not for himself, and not\\n for any other member of the class.\\n\\nGriffin v. Dugger, 823 F.2d 1476, 1482-83 (11th Cir. 1987) (multiple citations,\\n\\nquotation marks, and brackets omitted).\\n\\n Importantly, Article III standing must be determined as of the time that the\\n\\nplaintiff’s complaint is filed. See, e.g., Arcia v. Florida Sec’y of State, 772 F.3d\\n\\n1335, 1340 (11th Cir. 2014); Focus on the Family v. Pinellas Suncoast Transit\\n\\nAuth., 344 F.3d 1263, 1275 (11th Cir. 2003) (collecting multiple cases); Atlanta\\n\\nGas Light, 68 F.3d at 414 (in determining whether there is an Article III case or\\n\\ncontroversy, “we ‘look to the state of affairs as of the filing of the complaint; a\\n\\njusticiable controversy must have existed at that time’”) (citation omitted); accord\\n\\nMorrison v. Bd. of Educ. of Boyd Cty., 521 F.3d 602, 616 (6th Cir. 2008) (stating\\n\\nthat standing must be evaluated “at the time the plaintiff filed his or her complaint\\n\\n\\n 11\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 12 of 23\\n\\n\\nand not at anytime thereafter”) (citation omitted). Florida’s standing requirement\\n\\nis the same in this respect. See Progressive Exp. Ins. Co. v. McGrath Community\\n\\nChiropractic, 913 So.2d 1281, 1284-85 (Fla. 2d DCA 2005) (citing and discussing\\n\\ncases and noting that “[a]s these cases demonstrate, the plaintiff’s lack of standing\\n\\nat the inception of the case is not a defect that may be cured by the acquisition of\\n\\nstanding after the case is filed”).\\n\\n III.\\n\\n GEICO argues on appeal, as it did below, that Carruthers was only entitled\\n\\nto $2,500 in PIP benefits under the policy because there was no EMC diagnosis at\\n\\nthe time the complaint was filed. Consequently, Gerber (as Carruthers’ assignee)\\n\\nwas not entitled to benefits beyond $2,500. Because GEICO paid much more than\\n\\nthat amount, Carruthers/Gerber didn’t suffer harm as a result of GEICO’s alleged\\n\\nmisapplication of its policy. According to GEICO, no matter how we interpret the\\n\\ndisputed policy language, Gerber will not be able to recover anything from GEICO\\n\\n(i.e., there was no injury to Carruthers resulting from GEICO’s conduct that can be\\n\\nfairly traced to the challenged action and redressed by a favorable court ruling),\\n\\nthereby eliminating the existence of a case or controversy. GEICO is correct.\\n\\n When an insurance company has “paid all benefits in full . . . [t]here is no\\n\\ncase or controversy[.]” Harrison v. United Mine Workers of Am. 1974 Ben. Plan\\n\\n\\n\\n\\n 12\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 13 of 23\\n\\n\\n& Trust, 941 F.2d 1190, 1193 (11th Cir. 1991); 2 accord Progressive Am. Ins. Co.\\n\\nv. Stand-Up MRI of Orlando, 990 So.2d 3, 4 (Fla. 5th DCA 2008) (“a PIP insurer is\\n\\nnot liable for benefits once benefits have been exhausted”); Neighborhood Health\\n\\nP’ship Inc. v. Fischer, 913 So.2d 703, 705 (Fla. 3d DCA 2005) (trial court abused\\n\\nits discretion in certifying a class action “where the uncontroverted evidence is\\n\\nclear that Dr. Fischer lacks standing to serve as a class representative because he\\n\\nhas no claim for damages against NHP, and, indeed, may in fact owe a refund to\\n\\nNHP for claims overpaid to him”); Graham v. State Farm Fire & Cas. Co., 813\\n\\nSo.2d 273, 274 (Fla. 5th DCA 2002) (“The conceded facts show that the Grahams\\n\\nwere paid in full two years prior to the filing of the class claims. . . . Based on the\\n\\nconceded facts, there is no existing dispute between the Grahams and State Farm\\n\\nthat would give the Grahams standing to proceed on behalf of other potential\\n\\nplaintiffs with similar disputes.”); Ramon v. Aries Ins. Co., 769 So.2d 1053 (Fla.\\n\\n\\n 2\\n We recognize that there was “no case or controversy” in Harrison because the case was\\nrendered moot after the insurer paid benefits in full while the case was pending, unlike this case\\nwhere the benefits were paid in full pre-suit. But that is a distinction without a difference. As\\nProfessor Monaghan has observed, the justiciability doctrines of standing and mootness “share\\nthe same root.” Henry P. Monaghan, Constitutional Adjudication: The Who and When, 82 Yale\\nL.J. 1363, 1384 (1973). The Supreme Court has described mootness as merely “‘the doctrine of\\nstanding set in a time frame: The requisite personal interest that must exist at the commencement\\nof the litigation (standing) must continue throughout its existence (mootness).’” United States\\nParole Comm’n v. Geraghty, 445 U.S. 388, 397 (1980) (quoting Monaghan, supra). If a case\\nbecomes non-justiciable because an insurer has paid full benefits while the case is pending (as in\\nHarrison), the case should be non-justiciable if it is undisputed that the benefits were paid before\\nthe case was even filed (as here). To hold otherwise would mean that if GEICO had denied PIP\\nbenefits pre-suit but then paid Gerber $7,311 shortly after the case was filed, the case would have\\nbecome moot and thus non-justiciable, but undisputed evidence showing that those same benefits\\nwere paid before the case was filed wouldn’t raise any justiciability concerns.\\n 13\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 14 of 23\\n\\n\\n3d DCA 2000) (policyholder who received full payment of PIP benefits lacked\\n\\nstanding to pursue class action claim).\\n\\n In finding that Gerber had standing in the order under review, the District\\n\\nCourt relied on a single case: Mills v. Foremost Ins. Co., 511 F.3d 1300 (11th Cir.\\n\\n2008). Based on that case, the District Court held that GEICO’s pre-suit (and pre-\\n\\nEMC) payment in excess of the statutory cap didn’t implicate standing, but, rather,\\n\\nit was an exhaustion of benefits affirmative defense. The District Court’s reliance\\n\\non Mills was misplaced.\\n\\n The plaintiffs in that case, Dale and Diane Mills, owned a mobile home that\\n\\nwas insured under a policy issued by the defendant, Foremost Insurance Company.\\n\\nThey filed a class action alleging that Foremost had failed to pay them (and other\\n\\ninsureds) for overhead, profit, and taxes after they sustained hurricane-damaged\\n\\nlosses, and they sought compensation for those “Withheld Payments.” Notably—\\n\\nand in contrast to this action—the plaintiffs in Mills were seeking both declaratory\\n\\nrelief and damages for breach of contract. The defendant argued that the plaintiffs\\n\\nhad failed to satisfy certain preconditions in the policy that allegedly required them\\n\\nto complete repair or replacement of their damaged property first and then submit a\\n\\nrepair or replacement cost claim to the insurance company before entitling them to\\n\\nthe Withheld Payments. Foremost argued that the Millses’ failure to do so\\n\\ndeprived them of standing, and the District Court agreed.\\n\\n\\n 14\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 15 of 23\\n\\n\\n In reversing, we began by holding the District Court erred in interpreting the\\n\\npolicy to require that the Millses jump through the aforementioned hoops. See 511\\n\\nF.3d at 1304-06 (rejecting the district court’s conclusion that preconditions in the\\n\\npolicy required the Millses to complete repair or replacement of their damaged\\n\\nproperty and to submit such a replacement cost claim to be entitled to the Withheld\\n\\nPayments). We then continued:\\n\\n The district court also erred in treating these particular\\n insurance coverage issues under the Policy as standing\\n issues. The complaint alleges that the Millses had a\\n mobile home, that Foremost issued an insurance policy\\n covering hurricane damage to the mobile home, that a\\n hurricane damaged the Millses’ mobile home, that the\\n Millses made a claim under the Policy for those damages,\\n and that Foremost paid less on the claim than the Millses\\n contend they are owed. Thus, the Millses clearly had\\n standing to sue for damages under the Policy. See\\n Wooden v. Bd. of Regents, 247 F.3d 1262, 1273-74 (11th\\n Cir. 2001) (stating that standing is essentially a\\n determination of “whether the litigant is entitled to have\\n the court decide the merits of the dispute or of particular\\n issues,” and requires that a plaintiff have suffered a\\n concrete, particularized injury that is caused by the\\n challenged action of the defendant and can be redressed\\n by a favorable court decision).\\n\\n Whether the Withheld Payments were covered by the\\n Policy is an issue of whether the Millses’ complaint fails\\n to state a claim for relief under the Policy—not a\\n standing issue. Whether the Millses’ complaint pled\\n sufficient facts is likewise a failure-to-state-a-claim issue.\\n We thus reject Foremost’s standing arguments as to the\\n Millses’ individual claims against Foremost on this basis\\n as well.\\n\\n\\n 15\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 16 of 23\\n\\n\\nId. at 1306-07 (emphasis added).\\n\\n Therefore, Mills was not (as here) an exhaustion of benefits case. Rather, it\\n\\nwas a coverage dispute that included a breach of contract claim seeking damages\\n\\narising out of that dispute. This distinction is critical because if the plaintiffs had\\n\\nprevailed in Mills, they would have been entitled to the Withheld Payments. Thus,\\n\\nwe found there that “the Millses clearly had standing to sue for damages under the\\n\\nPolicy” because the plaintiffs alleged that the insurer “paid [them] less on the claim\\n\\nthan [they] contend they are owed,” and a ruling in their favor on that point would\\n\\nentitle them to the money owed. 511 F.3d at 1307 (emphasis added). By contrast,\\n\\nwhen insurance benefits are fully exhausted (as here, and as in certain of the cases\\n\\ncited supra), there is no case or controversy because no money is owed regardless\\n\\nof how the case is ultimately decided. See, e.g., Harrison, 941 F.2d at 1193. Mills\\n\\nwould apply if Gerber alleged breach of contract and sought damages. But, it\\n\\nspecifically tailored its complaint to avoid such allegations. 3\\n\\n\\n\\n 3\\n In her concurring opinion, Judge Branch believes it is irrelevant that GEICO paid in\\nexcess of the PIP limit because Gerber is not seeking money damages. While it is true—as we\\nhave noted several times—that Gerber is not seeking money damages for unpaid benefits in this\\ncase, Gerber has made clear in its brief, in its notice of supplemental authority, and during oral\\nargument that the declaratory relief it seeks is merely a precursor to a claim for money damages\\nin subsequent cases. See Appellee Brief at 45 (“declaratory relief may serve ‘as a predicate for\\nlater monetary relief’”) (quoting Gooch v. Life Investors Ins. Co. of Am., 672 F.3d 402, 429 (6th\\nCir. 2012)); Notice of Supplemental Authority, dated December 5, 2018 (noting “‘a declaratory\\njudgment is normally a prelude to a request for other relief’”) (quoting Berger v. Xerox Corp.\\nRetirement Income Guarantee Plan, 338 F.3d 755, 763-64 (7th Cir. 2003)); Oral Argument\\n18:40-18:56 (“The declaratory relief, as we say in the cases cited in the supplemental authority\\n[Berger] and in the Gooch case from the Sixth Circuit that I want to focus on, all make it clear\\n 16\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 17 of 23\\n\\n\\n This is not to say, of course, that to have standing to pursue a declaratory\\n\\njudgment action the complaint must seek monetary relief. It doesn’t have to seek\\n\\nsuch relief. As earlier noted, however, when a plaintiff is seeking declaratory\\n\\nrelief without a claim for money damages for injuries already suffered, the plaintiff\\n\\nmust allege facts from which it appears that there is a substantial likelihood that he\\n\\nwill suffer injury in the future. E.g., Strickland, 772 F.3d at 883. Gerber has not\\n\\nalleged such facts here. Quite to the contrary, a review of Gerber’s motion to\\n\\nremand indicates that it specifically tailored its complaint to avoid alleging future\\n\\ninjury (as it did with the money damages). Indeed, Gerber unequivocally stated in\\n\\nits motion that “Plaintiff does not make any claim in the complaint that there is a\\n\\nrisk of future injury.” See Remand Mot. at 9 (emphasis added). 4\\n\\n\\nthat there’s nothing unusual about having declaratory relief as a precursor to monetary relief”).\\nConsistent with the foregoing, counsel for Gerber expressly said at oral argument that if their\\ninterpretation of GEICO’s policy is correct and Gerber prevails in this lawsuit, the “monetary\\nclaims . . . will come” later. Oral Argument 20:30-20:35. We understand this argument (that\\nthere are viable claims for damages that will be raised in the future) to potentially implicate the\\nstanding issue. If Gerber were to win on the merits, monetary claims may indeed come later\\n(and there may be standing) for class members who were underpaid as the result of GEICO’s\\nmisinterpretation of its policy language. However, it is undisputed that when the complaint was\\nfiled (the only time that matters) Carruthers (the only person who matters) was paid more in PIP\\nbenefits than he was entitled to. See, e.g., Appellee Brief at 29 (acknowledging that GEICO\\n“voluntarily pa[id] Gerber $7,311 with no EMC determination when Gerber made its insurance\\nclaims”). Thus, there is no monetary claim for Gerber as Carruthers’ assignee, and there will be\\nno such claim in the future for Carruthers—even though he was diagnosed with an EMC after\\nthis case was filed—because standing must be determined as of the time of filing. That is why\\nthe exhaustion of benefits issue is relevant and why we have discussed it, even though money\\ndamages are not being sought in this litigation.\\n 4\\n Ironically, it appears that Gerber didn’t allege future injury because it knew that doing\\nso would implicate federal jurisdiction, and it wanted to avoid federal court and stay in Florida\\nstate court. See Remand Mot. at 7-9 (arguing that federal courts lack Article III jurisdiction over\\n 17\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 18 of 23\\n\\n\\n Gerber now argues—directly contrary to what it previously argued—that\\n\\nthere is a risk of future injury here. Specifically, Gerber argues that the dispute\\n\\nabout the policy language will continue or be repeated in the future, and it will\\n\\ninjure Gerber and other chiropractors insofar as they don’t know whether to tell\\n\\ntheir patients that GEICO is responsible for the full 100% of the relevant charges,\\n\\nor whether the patients are responsible for 20%. See Oral Argument 19:16-20:23.\\n\\nThis is significant, Gerber’s counsel noted during oral argument, as evidenced by\\n\\nthe fact that GEICO had indirectly accused Gerber of insurance fraud in this case\\n\\nfor not attempting to collect the 20% from Carruthers, and such accusations could\\n\\nadversely impact its license in the future. See id. at 19:10-20:13.5\\n\\n Whether and to what extent Gerber might be injured is beside the point\\n\\nbecause the proper inquiry in this case must focus on the potential future injury to\\n\\nCarruthers, not to Gerber or other members of the class. Cf. Kostelac v. Allianz\\n\\nGlobal Corp. & Specialty AG, 517 F. App’x 670, 675-76 (11th Cir. 2013) (stating\\n\\nthat because an assignee must stand in the shoes of the assignor, and he has no\\n\\nrights greater than the assignor, “the relevant inquiry” must focus on the assignor,\\n\\n\\n\\ndeclaratory judgment actions if there is no claim for money damages or future injury—neither of\\nwhich, Gerber argued, was present in this case—but “the Florida Declaratory Judgment Act is\\nmuch more expansive and permits a claim similar to this action”).\\n 5\\n Gerber also points out in its brief that GEICO argued early on in this lawsuit (when it\\nremoved the action to federal court) that Gerber did have standing. As we have already noted,\\nhowever, standing cannot be waived or conceded, and we must independently decide whether it\\nexists.\\n 18\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 19 of 23\\n\\n\\nand it is “misguided” to “shift the . . . inquiry” to the assignee) (citing Crossman,\\n\\n273 F.2d at 725; Houk, 173 F.2d at 825). 6 And we can see no potential future\\n\\nthreat to Carruthers, other than the possibility that he may someday be in another\\n\\ncar accident; sustain an injury entitling him to PIP benefits; and still be insured by\\n\\nGEICO under the same or a similar policy being interpreted the same way, thereby\\n\\nhaving this issue present itself again. But, that is too contingent to constitute a\\n\\n“substantial likelihood” of future injury. See, e.g., Emory, 756 F.2d at 1552 (to\\n\\nsatisfy Article III, the case or controversy cannot be “conjectural, hypothetical, or\\n\\ncontingent; it must be real and immediate, and create a definite, rather than\\n\\nspeculative threat of future injury”).\\n\\n In the absence of a claim for money damages or substantial likelihood that\\n\\nCarruthers will suffer a future injury—both of which Gerber was careful to avoid\\n\\nalleging here—Gerber has no standing to pursue this case.\\n\\n IV.\\n\\n We recognize that this appeal raises an important issue for GEICO’s Florida\\n\\nPIP policyholders and for medical providers treating them. And we recognize, too,\\n\\nthat the lawsuit has been pending for several years and has consumed a lot of both\\n\\njudicial and attorney resources. If we could, we would reach the merits and give\\n\\n\\n 6\\n Although an unpublished opinion is not binding, it may be cited as persuasive authority.\\nSee, e.g., Searcy v. R.J. Reynolds Tobacco Co., 902 F.3d 1342, 1355 n.5 (11th Cir. 2018) (citing\\nUnited States v. Futrell, 209 F.3d 1286, 1289 (11th Cir. 2000), in turn citing 11th Cir. R. 36-2).\\n 19\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 20 of 23\\n\\n\\nfinality to the questions presented. But we cannot. “‘In the absence of standing, a\\n\\ncourt is not free to opine in an advisory capacity about the merits of a plaintiff’s\\n\\nclaims.’” CAMP Legal Def. Fund, 451 F.3d at 1269 (quoting Bochese v. Town of\\n\\nPonce Inlet, 405 F.3d 964, 974 (11th Cir. 2005)). Again, “standing is ‘perhaps the\\n\\nmost important’ jurisdictional doctrine, and, as with any jurisdictional requisite, we\\n\\nare powerless to hear a case when it is lacking.” Bochese, 405 F.3d at 974 (citation\\n\\nomitted).\\n\\n Because the District Court had no jurisdiction to entertain this suit, we\\n\\nVACATE its judgment. The District Court is instructed to enter an order\\n\\nremanding the case to the Circuit Court of the Seventeenth Judicial Circuit in and\\n\\nfor Broward County, Florida.7\\n\\n SO ORDERED.\\n\\n\\n\\n\\n 7\\n We acknowledge “the fundamental principle that state courts are the final arbiters of\\nstate law.” See Agan v. Vaughn, 119 F.3d 1538, 1549 (11th Cir. 1997). For that reason, on\\nremand, the state court should engage anew in any contract interpretation necessary to its\\nstanding or merits determinations.\\n 20\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 21 of 23\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4401821/\", \"author_raw\": \"VINSON, District Judge:\"}, {\"author\": \"BRANCH, Circuit Judge, concurring\", \"type\": \"concurrence\", \"text\": \"BRANCH, Circuit Judge, concurring in part and concurring in the judgment:\\n\\n I concur with the judgment in full and with the panel opinion except for the\\n\\nportion that analyzes exhaustion of benefits. I find that analysis irrelevant given\\n\\nthat Gerber seeks only declaratory relief.\\n\\n The oddness of this case calls for special emphasis. Gerber has deployed a\\n\\nvariety of tactics that make it hard to believe a case like this one will ever arise\\n\\nagain. In particular, Gerber vigorously argued in the district court that it lacked\\n\\nArticle III standing, and in doing so it expressly disclaimed any interest in future\\n\\nrelief. Nevertheless, Gerber decided to avoid the rigors of Rule 23(b)(3) of the\\n\\nFederal Rules of Civil Procedure and to move to certify a class only under Rule\\n\\n23(b)(2)—a rule intended, in part, to confer the prospective relief Gerber had\\n\\ndisclaimed. 1\\n\\n\\n\\n\\n 1\\n If a class action meets certain prerequisites laid out in Rule 23(a), a class action may be\\nmaintained under one of Rule 23(b)’s three provisions. Rule 23(b)(1) is not relevant here. Rule\\n23(b)(2) provides for a class action if “the party opposing the class has acted or refused to act on\\ngrounds that apply generally to the class, so that final injunctive relief or corresponding\\ndeclaratory relief is appropriate respecting the class as a whole.” Rule 23(b)(3) provides for a\\nclass action if “the court finds that the questions of law or fact common to class members\\npredominate over any questions affecting only individual members, and that a class action is\\nsuperior to other available methods for fairly and efficiently adjudicating the controversy.” As\\nthe Supreme Court has explained, the “procedural protections attending the (b)(3) class—\\npredominance, superiority, mandatory notice, and the right to opt out—are missing from (b)(2)\\n. . . .” Wal-Mart Stores v. Dukes, 564 U.S. 338, 362 (2011).\\n 21\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 22 of 23\\n\\n\\n With these things in mind, I agree with the panel that Gerber—and by\\n\\nextension Carruthers 2—lacks standing. But I agree only with the panel’s analysis\\n\\nthat concludes that Gerber and Carruthers lack an interest in future relief. I believe\\n\\nthat analysis is dispositive on its own.\\n\\n Gerber and Carruthers seek only a declaration that the PIP requires GEICO\\n\\nto pay 100% of certain charges rather than 80%. The only thing that matters, then,\\n\\nis whether Gerber and Carruthers have an interest in any future relief conferred by\\n\\nthe declaration they seek. See Malowney v. Fed. Collection Deposit Grp., 193 F.3d\\n\\n1342, 1346 (11th Cir. 1999) (“In order to demonstrate that a case or controversy\\n\\nexists to meet the Article III standing requirement when a plaintiff is seeking\\n\\ninjunctive or declaratory relief, a plaintiff must allege facts from which it appears\\n\\nthere is a substantial likelihood that he will suffer injury in the future.”); id. at 1348\\n\\n(“Injury in the past . . . does not support a finding of an Article III case or\\n\\ncontroversy when the only relief sought is a declaratory judgment.”).\\n\\n The panel correctly explains that a plaintiff need not seek monetary relief in\\n\\na declaratory judgment action. Yet the panel believes that it matters whether\\n\\n\\n 2\\n I agree with the panel that Gerber stands in Carruthers’s shoes as assignee. But that is\\nnot how the issue is framed, as Gerber purports to represent a class of healthcare providers that\\nreceived an assignment of benefits. The district court’s declaration also focuses on those\\nproviders. See A & M Gerber Chiropractic LLC v. GEICO Gen. Ins. Co., 291 F. Supp. 3d 1318,\\n1344 (S.D. Fla. 2017) (“[I]f a provider submits a bill to GEICO that is less than 200 percent of\\nthe applicable fee schedule, GEICO shall pay the provider 100 percent of the amount billed.”).\\nUltimately, we need not resolve the confusion. Neither Gerber nor Carruthers has standing to\\nseek declaratory relief in this case—on behalf of themselves or anyone else.\\n 22\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 23 of 23\\n\\n\\nGerber and Carruthers were paid beyond the PIP limit. The panel reasons that if\\n\\nGerber and Carruthers have exhausted their benefits, they have not suffered an\\n\\ninjury and will not benefit from a favorable declaration.\\n\\n The problem is that, contrary to GEICO’s and the panel’s assertion, this case\\n\\nis not about exhaustion of benefits. Again, Gerber’s operative complaint seeks\\n\\nonly a declaratory judgment regarding how GEICO should pay certain charges.\\n\\nYet Gerber has disclaimed the notion that GEICO will underpay it in the future.\\n\\nSee Doc. 7 at 7–9; Doc. 40 at 4. That disclaimer, not any money GEICO has paid\\n\\nGerber in the past, is why Gerber lacks standing.\\n\\n In short, it does not matter how much money Gerber and Carruthers have\\n\\nbeen paid. For that reason, the panel’s discussion of mootness is also irrelevant.\\n\\nGEICO could not buy its way out of this declaratory judgment action—before or\\n\\nafter the action began. A declaratory judgment lawsuit requires the plaintiff to\\n\\nprove a substantial likelihood of future harm. Gerber has disclaimed any such\\n\\nharm. The panel and I agree on this point. But I believe it should be the beginning\\n\\nand end of our standing inquiry.\\n\\n\\n\\n\\n 23\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4401821/\", \"author_raw\": \"BRANCH, Circuit Judge, concurring\"}]}"},"judge1":{"kind":"string","value":"WILSON"},"judge2":{"kind":"string","value":"BRANCH"},"judge3":{"kind":"string","value":"VINSON"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":2,"string":"2"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":1,"string":"1"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4624568/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: A&M GERBER CHIROPRACTIC LLC, as Assignee of Conor Carruthers, on Behalf of Itself and All Others Similarly Situated, Plaintiff - Appellee, v. GEICO GENERAL INSURANCE COMPANY, Defendant - Appellant.\nCourt: U.S. Court of Appeals for the Eleventh Circuit\nDate decided: 2019-05-30\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: Yes\nAdditional notes: \n\n[CASE_TEXT]\nCase: 17-15606 Date Filed: 05/30/2019 Page: 1 of 23\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT OF APPEALS\n\n FOR THE ELEVENTH CIRCUIT\n ________________________\n\n No. 17-15606\n ________________________\n\n D.C. Docket No. 0:16-cv-62610-BB\n\n\nA&M GERBER CHIROPRACTIC LLC,\nas assignee of Conor Carruthers, on behalf\nof itself and all others similarly situated,\n\n Plaintiff - Appellee,\n\nversus\n\nGEICO GENERAL INSURANCE COMPANY,\n\n Defendant - Appellant.\n\n ________________________\n\n Appeal from the United States District Court\n for the Southern District of Florida\n ________________________\n\n (May 30, 2019)\n\n ON PETITION FOR REHEARING\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 2 of 23\n\n\nBefore WILSON and BRANCH, Circuit Judges, and VINSON,∗ District Judge.\n\nVINSON, District Judge:\n\n Upon consideration, we grant the Appellee’s petition for panel rehearing.\n\nWe vacate our prior opinion in this case, issued on April 19, 2019, and published at\n\n921 F.3d 1273 (11th Cir. 2019), and hereby substitute the following opinion in its\n\nplace.\n\n Conor Carruthers was involved in a car accident on March 18, 2015, after\n\nwhich he sought medical services from A&M Gerber Chiropractic LLC. At the\n\ntime, Carruthers was covered under an automobile insurance policy issued by\n\nGEICO General Insurance Company. Pursuant to Florida’s Motor Vehicle No-\n\nFault Law, the policy provided him with $10,000 in personal injury protection\n\n(PIP) benefits. See Fla. Stat. § 627.736(1) (mandating that automobile insurers\n\nprovide PIP benefits “to a limit of $10,000”). To be entitled to the full $10,000,\n\nhowever, the statute required that Carruthers—like all PIP beneficiaries—be\n\ndiagnosed by an authorized health care provider with an “emergency medical\n\ncondition” (EMC); without such a diagnosis, he was limited to $2,500 in benefits.\n\nSee id. at § 627.736(1)(a)(3)-(4); Robbins v. Garrison Prop. & Cas. Ins. Co., 809\n\nF.3d 583, 587-88 (11th Cir. 2015) (holding in consolidated appeal that “[b]ecause\n\n\n\n ∗Honorable C. Roger Vinson, United States District Judge for the Northern District of\nFlorida, sitting by designation.\n 2\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 3 of 23\n\n\nneither Robbins’ nor Enivert’s claim was supported by [an EMC determination],\n\nneither Garrison nor Progressive violated Fla. Stat. § 627.736 by limiting benefits\n\nto $2,500”); accord, e.g., Progressive Am. Ins. Co. v. Eduardo J. Garrido D.C.,\n\nP.A., 211 So.3d 1086, 1093 (Fla. 3d DCA 2017); Medical Ctr. of Palm Beaches v.\n\nUSAA Cas. Ins. Co., 202 So.3d 88, 92-93 (Fla. 4th DCA 2016); McCarty v. Myers,\n\n125 So.3d 333, 335 (Fla. 1st DCA 2013).\n\n It is undisputed that Carruthers was not diagnosed with an EMC at the time\n\nthis case was filed. It is also undisputed that, despite the lack of an EMC finding,\n\nGEICO paid Carruthers/Gerber $7,311 in PIP benefits pre-suit, well in excess of\n\nthe $2,500 cap. Even though Carruthers received almost triple the amount in PIP\n\nbenefits that he was entitled to, Gerber believed that GEICO had misinterpreted\n\ncertain language in its automobile policies and that this misinterpretation resulted\n\nin GEICO consistently underpaying PIP benefits as a “general business practice.”\n\n Specifically, the policy contains an endorsement identified as FLPIP (01-\n\n13), and that endorsement (under the heading “PAYMENTS WE WILL MAKE”)\n\nreferences fee schedules pursuant to which GEICO will pay 80% of benefits that\n\nare medically necessary. The endorsement goes on to state: “For all other medical\n\nservices, supplies, and care [GEICO will pay] 200 percent of the allowable amount\n\nunder [a Medicare Part B fee schedule],” subject to a limitation of 80% of the\n\n“maximum reimbursable allowance under workers’ compensation . . . .” Below\n\n\n 3\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 4 of 23\n\n\nthat statement, GEICO added the following: “A charge submitted by a provider,\n\nfor an amount less than the amount allowed above, shall be paid in the amount of\n\nthe charge submitted.” The underlying dispute in this case hinges on whether this\n\nsingle sentence is the operative language of the policy for health care provider bills\n\nof less than 200% of the fee schedule.\n\n GEICO has taken the position that the policy is an “80/20 policy” pursuant\n\nto which it was required to pay the lower of 80% of the fee schedule amount or\n\n80% of the charged amount, while insureds are required to pay the remaining 20%\n\nas co-insurance. To supports its position, GEICO relied, inter alia, on a document\n\nmailed or provided to its PIP policyholders effective on or after January 1, 2013,\n\nand identified as M608 (01-13). This document was titled\n\n IMPORTANT NOTICE\n\n FEE SCHEDULE ENDORSEMENT\n\nand it provides in relevant part that “in no event will the Company pay more than\n\n80 percent” of properly billed medical expenses. GEICO asserts that M608 (01-\n\n13) is an endorsement and, thus, part of the policy. Gerber has argued that M608\n\n(01-13) is not an endorsement/part of the policy, and it further argues that FLPIP\n\n(01-13) provides that when a health care provider bills for services at an amount\n\nless than 200% of the fee schedule, GEICO must pay the charge as billed (that is,\n\n“in the amount of the charge submitted”) without the 20% reduction.\n\n\n 4\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 5 of 23\n\n\n Carruthers assigned his rights to his treating chiropractic clinic, Gerber,\n\nwhich later filed a declaratory judgment class action suit in Florida state court in\n\nSeptember 2016. The complaint sought certification of a class (with Gerber as the\n\nclass representative) along with a declaration (a) that GEICO’s interpretation of its\n\npolicy language was wrong, and (b) that the misinterpretation “constitutes a breach\n\nof the insurance Policy.” Although the complaint sought a declaration that GEICO\n\nhad breached the policy, the complaint stated that “there is no claim for monetary\n\nrelief” in the case.\n\n GEICO removed the case to the United States District Court for the\n\nSouthern District of Florida in November 2016, pursuant to the Class Action\n\nFairness Act, and Gerber filed an unsuccessful motion to remand the case for lack\n\nof Article III standing. The District Court appointed Gerber as class\n\nrepresentative, and it certified the class to include:\n\n All health care providers that received an assignment of\n benefits from a claimant and thereafter, pursuant to that\n assignment, submitted claims for no-fault benefits under\n GEICO PIP policies to which Endorsement FLPIP (01–\n 13) applies, and any subsequent policies with\n substantially similar language that were in effect since\n January 1, 2013, where GEICO utilized the Code BA\n [billed amount] with respect to the payment of any\n claims.\n\n Shortly after the action was removed to federal court, and while its motion to\n\nremand was pending, Gerber filed an amended complaint. The amended complaint\n\n\n 5\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 6 of 23\n\n\nwas largely the same as the original complaint, but it added another sentence to re-\n\nemphasize that “this action does not assert a claim for any monetary relief,” and it\n\ndeleted the request for a declaration that GEICO’s misinterpretation of the disputed\n\npolicy language “constitutes a breach of the insurance Policy.” Thus, as amended,\n\nthe complaint clarified that it only sought declaratory relief and that there was no\n\nclaim for breach of contract or request for money damages related thereto. In July\n\n2017—more than two years after the underlying car accident, and ten months after\n\nthe litigation was filed—Carruthers obtained an EMC medical diagnosis.\n\n On cross motions for summary judgment, GEICO argued, inter alia, that\n\nGerber lacked standing at the outset of the lawsuit because it was undisputed that\n\nGEICO had paid Gerber more than $2,500 before the case was filed, even though\n\nhe had not been diagnosed with an EMC at that time. By order dated November\n\n17, 2017, the District Court disagreed with GEICO and found there was standing.\n\nIt also ruled that M608 (01-13) was not an endorsement (but rather was merely a\n\nnotice) and, thus, it was not part of the policy. Applying a textual interpretation of\n\nthe FLPIP (01-13) endorsement, the District Court granted summary judgment for\n\nGerber and held that, “under the disputed provision, when a health care provider\n\nbills for covered services in an amount less than 200% of the fee schedule, GEICO\n\nis required to pay the charge as billed without any reduction.”\n\n\n\n\n 6\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 7 of 23\n\n\n GEICO now appeals, arguing that Gerber lacked standing to bring this case.\n\nIt further argues that the District Court erred in certifying the class; in limiting the\n\ndocuments that comprise the policy (that is, in failing to treat M608 (01-13) as an\n\nendorsement); and in ruling for Gerber on the merits as to the policy interpretation\n\nquestion.\n\n I.\n\n We must begin with the question of standing. See Kondrat’yev v. City of\n\nPensacola, Fla., 903 F.3d 1169, 1172 (11th Cir. 2018). If there is no standing, we\n\nmust end there, too. University of S. Ala. v. American Tobacco Co., 168 F.3d 405,\n\n410 (11th Cir. 1999) (“Simply put, once a federal court determines that [the\n\nplaintiff has no standing], the court is powerless to continue.”).\n\n We review standing determinations de novo. See, e.g., SEC v. Quest Energy\n\nMgmt. Group, Inc., 768 F.3d 1106, 1108 (11th Cir. 2014) (citing CAMP Legal Def.\n\nFund, Inc. v. City of Atlanta, 451 F.3d 1257, 1268 (11th Cir. 2006)). After de novo\n\nreview—and with the benefit of oral argument—we conclude that Gerber lacks\n\nstanding.\n\n II.\n\n Article III of the Constitution limits federal courts to adjudicating actual\n\n“cases” and “controversies.” See, e.g., Allen v. Wright, 468 U.S. 737, 750 (1984),\n\nabrogated on other grounds by Lexmark Int’l, Inc. v. Static Control Components,\n\n\n 7\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 8 of 23\n\n\nInc., 572 U.S. 118 (2014). The case-or-controversy requirement sets fundamental\n\nlimits on federal judicial power. Id. “Perhaps the most important of the Article III\n\ndoctrines grounded in the case-or-controversy requirement is that of standing.”\n\nWooden v. Bd. of Regents of the Univ. Sys. of Ga., 247 F.3d 1262, 1273 (11th Cir.\n\n2001). Standing cannot be waived or conceded by the parties, and it may be raised\n\n(even by the court sua sponte) at any stage of the case. See Bender v. Williamsport\n\nArea Sch. Dist., 475 U.S. 534, 541 (1986); Harris v. Evans, 20 F.3d 1118, 1121 n.4\n\n(11th Cir. 1994).\n\n “In essence the question of standing is whether the litigant is entitled to\n\nhave the court decide the merits of the dispute or of particular issues.” Warth v.\n\nSeldin, 422 U.S. 490, 498 (1975); see also Yellow Pages Photos, Inc. v. Ziplocal,\n\nLP, 795 F.3d 1255, 1264 (11th Cir. 2015) (same). “The party who invokes a\n\nfederal court’s authority must show, at an ‘irreducible minimum,’ that at the time\n\nthe complaint was filed, he has suffered some actual or threatened injury resulting\n\nfrom the defendant’s conduct, that the injury fairly can be traced to the challenged\n\naction, and that the injury is likely to be redressed by favorable court disposition.”\n\nAtlanta Gas Light Co. v. Aetna Cas. & Sur. Co., 68 F.3d 409, 414 (11th Cir. 1995).\n\n Echoing the “case or controversy” requirement of Article III, the Declaratory\n\nJudgment Act “provides that a declaratory judgment may only be issued in the case\n\nof an actual controversy.” See Emory v. Peeler, 756 F.2d 1547, 1551-52 (11th Cir.\n\n\n 8\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 9 of 23\n\n\n1985) (citing 28 U.S.C. § 2201); see also Atlanta Gas Light, 68 F.3d at 414 (“In all\n\ncases arising under the Declaratory Judgment Act, . . . the threshold question is\n\nwhether a justiciable controversy exists.”). “That is, under the facts alleged, there\n\nmust be a substantial continuing controversy between parties having adverse legal\n\ninterests.” Emory, 756 F.2d at 1552. The controversy between the parties cannot\n\nbe “conjectural, hypothetical, or contingent; it must be real and immediate, and\n\ncreate a definite, rather than speculative threat of future injury.” Id. In order to\n\ndemonstrate that there is a case or controversy that satisfies Article III’s standing\n\nrequirement when a plaintiff is seeking declaratory relief—as opposed to seeking\n\ndamages for past harm—the plaintiff must allege facts from which it appears that\n\nthere is a “substantial likelihood that he will suffer injury in the future.” Malowney\n\nv. Federal Collection Deposit Grp., 193 F.3d 1342, 1346 (11th Cir. 1999); accord\n\nStrickland v. Alexander, 772 F.3d 876, 883 (11th Cir. 2014) (“Where the plaintiff\n\nseeks declaratory or injunctive relief, as opposed to damages for injuries already\n\nsuffered, . . . the injury-in-fact requirement insists that a plaintiff ‘allege facts from\n\nwhich it appears there is a substantial likelihood that he will suffer injury in the\n\nfuture.’”) (quoting Malowney, 193 F.3d at 1346). “Thus, in order for this Court to\n\nhave jurisdiction to issue a declaratory judgment, . . . [the plaintiffs] must assert a\n\nreasonable expectation that the injury they have suffered will continue or will be\n\nrepeated in the future.” Malowney, 193 F.3d at 1347; see also id. at 1348 (“Injury\n\n\n 9\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 10 of 23\n\n\nin the past . . . does not support a finding of an Article III case or controversy when\n\nthe only relief sought is a declaratory judgment.”). Accordingly, if a plaintiff does\n\nnot assert a reasonable expectation of future injury, he “lack[s] standing to bring an\n\naction for declaratory relief[.]” See id. at 1348.\n\n In this case, Gerber, as assignee, stands in Carruthers’ shoes. Houk v. C.I.R.,\n\n173 F.2d 821, 825 (5th Cir. 1949) (“[A]n assignee . . . stands in the same position\n\nas its assignor had stood.”).1 It necessarily follows, then, that if Carruthers had no\n\nstanding to file this case against GEICO, Gerber has no standing either. Crossman\n\nv. Fontainebleau Hotel Corp., 273 F.2d 720, 725 (5th Cir. 1959) (“An assignee has\n\nno greater rights than his assignor[.]”).\n\n It is well-settled that “if none of the named plaintiffs purporting to represent\n\na class establishes the requisite of a case or controversy with the defendants, none\n\nmay seek relief on behalf of himself or any other member of the class.” O’Shea v.\n\nLittleton, 414 U.S. 488, 494 (1974); see also Prado-Steiman ex rel. Prado v. Bush,\n\n221 F.3d 1266, 1279-80 (11th Cir. 2000) (class representative must have individual\n\nstanding to raise class claims); Wooden, 247 F.3d at 1288 (claim cannot be asserted\n\nfor a class “‘unless at least one named plaintiff has suffered the injury that gives\n\nrise to that claim’”) (quoting Prado-Steiman, 221 F.3d at 1280). As we have said:\n\n\n 1\n In Bonner v. City of Prichard, 661 F.2d 1206, 1209 (11th Cir. 1981) (en banc), we adopted\nas binding precedent all Fifth Circuit decisions rendered prior to the close of business on September\n30, 1981.\n 10\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 11 of 23\n\n\n Under elementary principles of standing, a plaintiff must\n allege and show that he personally suffered injury. If he\n cannot show personal injury, then no article III case or\n controversy exists, and a federal court is powerless to\n hear his grievance. This individual injury requirement is\n not met by alleging that injury has been suffered by\n other, unidentified members of the class to which the\n plaintiff belongs and which he purports to represent.\n Thus, a plaintiff cannot include class action allegations in\n a complaint and expect to be relieved of personally\n meeting the requirements of constitutional standing, even\n if the persons described in the class definition would\n have standing themselves to sue. A named plaintiff in a\n class action who cannot establish the requisite case or\n controversy between himself and the defendants simply\n cannot seek relief for anyone—not for himself, and not\n for any other member of the class.\n\nGriffin v. Dugger, 823 F.2d 1476, 1482-83 (11th Cir. 1987) (multiple citations,\n\nquotation marks, and brackets omitted).\n\n Importantly, Article III standing must be determined as of the time that the\n\nplaintiff’s complaint is filed. See, e.g., Arcia v. Florida Sec’y of State, 772 F.3d\n\n1335, 1340 (11th Cir. 2014); Focus on the Family v. Pinellas Suncoast Transit\n\nAuth., 344 F.3d 1263, 1275 (11th Cir. 2003) (collecting multiple cases); Atlanta\n\nGas Light, 68 F.3d at 414 (in determining whether there is an Article III case or\n\ncontroversy, “we ‘look to the state of affairs as of the filing of the complaint; a\n\njusticiable controversy must have existed at that time’”) (citation omitted); accord\n\nMorrison v. Bd. of Educ. of Boyd Cty., 521 F.3d 602, 616 (6th Cir. 2008) (stating\n\nthat standing must be evaluated “at the time the plaintiff filed his or her complaint\n\n\n 11\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 12 of 23\n\n\nand not at anytime thereafter”) (citation omitted). Florida’s standing requirement\n\nis the same in this respect. See Progressive Exp. Ins. Co. v. McGrath Community\n\nChiropractic, 913 So.2d 1281, 1284-85 (Fla. 2d DCA 2005) (citing and discussing\n\ncases and noting that “[a]s these cases demonstrate, the plaintiff’s lack of standing\n\nat the inception of the case is not a defect that may be cured by the acquisition of\n\nstanding after the case is filed”).\n\n III.\n\n GEICO argues on appeal, as it did below, that Carruthers was only entitled\n\nto $2,500 in PIP benefits under the policy because there was no EMC diagnosis at\n\nthe time the complaint was filed. Consequently, Gerber (as Carruthers’ assignee)\n\nwas not entitled to benefits beyond $2,500. Because GEICO paid much more than\n\nthat amount, Carruthers/Gerber didn’t suffer harm as a result of GEICO’s alleged\n\nmisapplication of its policy. According to GEICO, no matter how we interpret the\n\ndisputed policy language, Gerber will not be able to recover anything from GEICO\n\n(i.e., there was no injury to Carruthers resulting from GEICO’s conduct that can be\n\nfairly traced to the challenged action and redressed by a favorable court ruling),\n\nthereby eliminating the existence of a case or controversy. GEICO is correct.\n\n When an insurance company has “paid all benefits in full . . . [t]here is no\n\ncase or controversy[.]” Harrison v. United Mine Workers of Am. 1974 Ben. Plan\n\n\n\n\n 12\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 13 of 23\n\n\n& Trust, 941 F.2d 1190, 1193 (11th Cir. 1991); 2 accord Progressive Am. Ins. Co.\n\nv. Stand-Up MRI of Orlando, 990 So.2d 3, 4 (Fla. 5th DCA 2008) (“a PIP insurer is\n\nnot liable for benefits once benefits have been exhausted”); Neighborhood Health\n\nP’ship Inc. v. Fischer, 913 So.2d 703, 705 (Fla. 3d DCA 2005) (trial court abused\n\nits discretion in certifying a class action “where the uncontroverted evidence is\n\nclear that Dr. Fischer lacks standing to serve as a class representative because he\n\nhas no claim for damages against NHP, and, indeed, may in fact owe a refund to\n\nNHP for claims overpaid to him”); Graham v. State Farm Fire & Cas. Co., 813\n\nSo.2d 273, 274 (Fla. 5th DCA 2002) (“The conceded facts show that the Grahams\n\nwere paid in full two years prior to the filing of the class claims. . . . Based on the\n\nconceded facts, there is no existing dispute between the Grahams and State Farm\n\nthat would give the Grahams standing to proceed on behalf of other potential\n\nplaintiffs with similar disputes.”); Ramon v. Aries Ins. Co., 769 So.2d 1053 (Fla.\n\n\n 2\n We recognize that there was “no case or controversy” in Harrison because the case was\nrendered moot after the insurer paid benefits in full while the case was pending, unlike this case\nwhere the benefits were paid in full pre-suit. But that is a distinction without a difference. As\nProfessor Monaghan has observed, the justiciability doctrines of standing and mootness “share\nthe same root.” Henry P. Monaghan, Constitutional Adjudication: The Who and When, 82 Yale\nL.J. 1363, 1384 (1973). The Supreme Court has described mootness as merely “‘the doctrine of\nstanding set in a time frame: The requisite personal interest that must exist at the commencement\nof the litigation (standing) must continue throughout its existence (mootness).’” United States\nParole Comm’n v. Geraghty, 445 U.S. 388, 397 (1980) (quoting Monaghan, supra). If a case\nbecomes non-justiciable because an insurer has paid full benefits while the case is pending (as in\nHarrison), the case should be non-justiciable if it is undisputed that the benefits were paid before\nthe case was even filed (as here). To hold otherwise would mean that if GEICO had denied PIP\nbenefits pre-suit but then paid Gerber $7,311 shortly after the case was filed, the case would have\nbecome moot and thus non-justiciable, but undisputed evidence showing that those same benefits\nwere paid before the case was filed wouldn’t raise any justiciability concerns.\n 13\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 14 of 23\n\n\n3d DCA 2000) (policyholder who received full payment of PIP benefits lacked\n\nstanding to pursue class action claim).\n\n In finding that Gerber had standing in the order under review, the District\n\nCourt relied on a single case: Mills v. Foremost Ins. Co., 511 F.3d 1300 (11th Cir.\n\n2008). Based on that case, the District Court held that GEICO’s pre-suit (and pre-\n\nEMC) payment in excess of the statutory cap didn’t implicate standing, but, rather,\n\nit was an exhaustion of benefits affirmative defense. The District Court’s reliance\n\non Mills was misplaced.\n\n The plaintiffs in that case, Dale and Diane Mills, owned a mobile home that\n\nwas insured under a policy issued by the defendant, Foremost Insurance Company.\n\nThey filed a class action alleging that Foremost had failed to pay them (and other\n\ninsureds) for overhead, profit, and taxes after they sustained hurricane-damaged\n\nlosses, and they sought compensation for those “Withheld Payments.” Notably—\n\nand in contrast to this action—the plaintiffs in Mills were seeking both declaratory\n\nrelief and damages for breach of contract. The defendant argued that the plaintiffs\n\nhad failed to satisfy certain preconditions in the policy that allegedly required them\n\nto complete repair or replacement of their damaged property first and then submit a\n\nrepair or replacement cost claim to the insurance company before entitling them to\n\nthe Withheld Payments. Foremost argued that the Millses’ failure to do so\n\ndeprived them of standing, and the District Court agreed.\n\n\n 14\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 15 of 23\n\n\n In reversing, we began by holding the District Court erred in interpreting the\n\npolicy to require that the Millses jump through the aforementioned hoops. See 511\n\nF.3d at 1304-06 (rejecting the district court’s conclusion that preconditions in the\n\npolicy required the Millses to complete repair or replacement of their damaged\n\nproperty and to submit such a replacement cost claim to be entitled to the Withheld\n\nPayments). We then continued:\n\n The district court also erred in treating these particular\n insurance coverage issues under the Policy as standing\n issues. The complaint alleges that the Millses had a\n mobile home, that Foremost issued an insurance policy\n covering hurricane damage to the mobile home, that a\n hurricane damaged the Millses’ mobile home, that the\n Millses made a claim under the Policy for those damages,\n and that Foremost paid less on the claim than the Millses\n contend they are owed. Thus, the Millses clearly had\n standing to sue for damages under the Policy. See\n Wooden v. Bd. of Regents, 247 F.3d 1262, 1273-74 (11th\n Cir. 2001) (stating that standing is essentially a\n determination of “whether the litigant is entitled to have\n the court decide the merits of the dispute or of particular\n issues,” and requires that a plaintiff have suffered a\n concrete, particularized injury that is caused by the\n challenged action of the defendant and can be redressed\n by a favorable court decision).\n\n Whether the Withheld Payments were covered by the\n Policy is an issue of whether the Millses’ complaint fails\n to state a claim for relief under the Policy—not a\n standing issue. Whether the Millses’ complaint pled\n sufficient facts is likewise a failure-to-state-a-claim issue.\n We thus reject Foremost’s standing arguments as to the\n Millses’ individual claims against Foremost on this basis\n as well.\n\n\n 15\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 16 of 23\n\n\nId. at 1306-07 (emphasis added).\n\n Therefore, Mills was not (as here) an exhaustion of benefits case. Rather, it\n\nwas a coverage dispute that included a breach of contract claim seeking damages\n\narising out of that dispute. This distinction is critical because if the plaintiffs had\n\nprevailed in Mills, they would have been entitled to the Withheld Payments. Thus,\n\nwe found there that “the Millses clearly had standing to sue for damages under the\n\nPolicy” because the plaintiffs alleged that the insurer “paid [them] less on the claim\n\nthan [they] contend they are owed,” and a ruling in their favor on that point would\n\nentitle them to the money owed. 511 F.3d at 1307 (emphasis added). By contrast,\n\nwhen insurance benefits are fully exhausted (as here, and as in certain of the cases\n\ncited supra), there is no case or controversy because no money is owed regardless\n\nof how the case is ultimately decided. See, e.g., Harrison, 941 F.2d at 1193. Mills\n\nwould apply if Gerber alleged breach of contract and sought damages. But, it\n\nspecifically tailored its complaint to avoid such allegations. 3\n\n\n\n 3\n In her concurring opinion, Judge Branch believes it is irrelevant that GEICO paid in\nexcess of the PIP limit because Gerber is not seeking money damages. While it is true—as we\nhave noted several times—that Gerber is not seeking money damages for unpaid benefits in this\ncase, Gerber has made clear in its brief, in its notice of supplemental authority, and during oral\nargument that the declaratory relief it seeks is merely a precursor to a claim for money damages\nin subsequent cases. See Appellee Brief at 45 (“declaratory relief may serve ‘as a predicate for\nlater monetary relief’”) (quoting Gooch v. Life Investors Ins. Co. of Am., 672 F.3d 402, 429 (6th\nCir. 2012)); Notice of Supplemental Authority, dated December 5, 2018 (noting “‘a declaratory\njudgment is normally a prelude to a request for other relief’”) (quoting Berger v. Xerox Corp.\nRetirement Income Guarantee Plan, 338 F.3d 755, 763-64 (7th Cir. 2003)); Oral Argument\n18:40-18:56 (“The declaratory relief, as we say in the cases cited in the supplemental authority\n[Berger] and in the Gooch case from the Sixth Circuit that I want to focus on, all make it clear\n 16\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 17 of 23\n\n\n This is not to say, of course, that to have standing to pursue a declaratory\n\njudgment action the complaint must seek monetary relief. It doesn’t have to seek\n\nsuch relief. As earlier noted, however, when a plaintiff is seeking declaratory\n\nrelief without a claim for money damages for injuries already suffered, the plaintiff\n\nmust allege facts from which it appears that there is a substantial likelihood that he\n\nwill suffer injury in the future. E.g., Strickland, 772 F.3d at 883. Gerber has not\n\nalleged such facts here. Quite to the contrary, a review of Gerber’s motion to\n\nremand indicates that it specifically tailored its complaint to avoid alleging future\n\ninjury (as it did with the money damages). Indeed, Gerber unequivocally stated in\n\nits motion that “Plaintiff does not make any claim in the complaint that there is a\n\nrisk of future injury.” See Remand Mot. at 9 (emphasis added). 4\n\n\nthat there’s nothing unusual about having declaratory relief as a precursor to monetary relief”).\nConsistent with the foregoing, counsel for Gerber expressly said at oral argument that if their\ninterpretation of GEICO’s policy is correct and Gerber prevails in this lawsuit, the “monetary\nclaims . . . will come” later. Oral Argument 20:30-20:35. We understand this argument (that\nthere are viable claims for damages that will be raised in the future) to potentially implicate the\nstanding issue. If Gerber were to win on the merits, monetary claims may indeed come later\n(and there may be standing) for class members who were underpaid as the result of GEICO’s\nmisinterpretation of its policy language. However, it is undisputed that when the complaint was\nfiled (the only time that matters) Carruthers (the only person who matters) was paid more in PIP\nbenefits than he was entitled to. See, e.g., Appellee Brief at 29 (acknowledging that GEICO\n“voluntarily pa[id] Gerber $7,311 with no EMC determination when Gerber made its insurance\nclaims”). Thus, there is no monetary claim for Gerber as Carruthers’ assignee, and there will be\nno such claim in the future for Carruthers—even though he was diagnosed with an EMC after\nthis case was filed—because standing must be determined as of the time of filing. That is why\nthe exhaustion of benefits issue is relevant and why we have discussed it, even though money\ndamages are not being sought in this litigation.\n 4\n Ironically, it appears that Gerber didn’t allege future injury because it knew that doing\nso would implicate federal jurisdiction, and it wanted to avoid federal court and stay in Florida\nstate court. See Remand Mot. at 7-9 (arguing that federal courts lack Article III jurisdiction over\n 17\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 18 of 23\n\n\n Gerber now argues—directly contrary to what it previously argued—that\n\nthere is a risk of future injury here. Specifically, Gerber argues that the dispute\n\nabout the policy language will continue or be repeated in the future, and it will\n\ninjure Gerber and other chiropractors insofar as they don’t know whether to tell\n\ntheir patients that GEICO is responsible for the full 100% of the relevant charges,\n\nor whether the patients are responsible for 20%. See Oral Argument 19:16-20:23.\n\nThis is significant, Gerber’s counsel noted during oral argument, as evidenced by\n\nthe fact that GEICO had indirectly accused Gerber of insurance fraud in this case\n\nfor not attempting to collect the 20% from Carruthers, and such accusations could\n\nadversely impact its license in the future. See id. at 19:10-20:13.5\n\n Whether and to what extent Gerber might be injured is beside the point\n\nbecause the proper inquiry in this case must focus on the potential future injury to\n\nCarruthers, not to Gerber or other members of the class. Cf. Kostelac v. Allianz\n\nGlobal Corp. & Specialty AG, 517 F. App’x 670, 675-76 (11th Cir. 2013) (stating\n\nthat because an assignee must stand in the shoes of the assignor, and he has no\n\nrights greater than the assignor, “the relevant inquiry” must focus on the assignor,\n\n\n\ndeclaratory judgment actions if there is no claim for money damages or future injury—neither of\nwhich, Gerber argued, was present in this case—but “the Florida Declaratory Judgment Act is\nmuch more expansive and permits a claim similar to this action”).\n 5\n Gerber also points out in its brief that GEICO argued early on in this lawsuit (when it\nremoved the action to federal court) that Gerber did have standing. As we have already noted,\nhowever, standing cannot be waived or conceded, and we must independently decide whether it\nexists.\n 18\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 19 of 23\n\n\nand it is “misguided” to “shift the . . . inquiry” to the assignee) (citing Crossman,\n\n273 F.2d at 725; Houk, 173 F.2d at 825). 6 And we can see no potential future\n\nthreat to Carruthers, other than the possibility that he may someday be in another\n\ncar accident; sustain an injury entitling him to PIP benefits; and still be insured by\n\nGEICO under the same or a similar policy being interpreted the same way, thereby\n\nhaving this issue present itself again. But, that is too contingent to constitute a\n\n“substantial likelihood” of future injury. See, e.g., Emory, 756 F.2d at 1552 (to\n\nsatisfy Article III, the case or controversy cannot be “conjectural, hypothetical, or\n\ncontingent; it must be real and immediate, and create a definite, rather than\n\nspeculative threat of future injury”).\n\n In the absence of a claim for money damages or substantial likelihood that\n\nCarruthers will suffer a future injury—both of which Gerber was careful to avoid\n\nalleging here—Gerber has no standing to pursue this case.\n\n IV.\n\n We recognize that this appeal raises an important issue for GEICO’s Florida\n\nPIP policyholders and for medical providers treating them. And we recognize, too,\n\nthat the lawsuit has been pending for several years and has consumed a lot of both\n\njudicial and attorney resources. If we could, we would reach the merits and give\n\n\n 6\n Although an unpublished opinion is not binding, it may be cited as persuasive authority.\nSee, e.g., Searcy v. R.J. Reynolds Tobacco Co., 902 F.3d 1342, 1355 n.5 (11th Cir. 2018) (citing\nUnited States v. Futrell, 209 F.3d 1286, 1289 (11th Cir. 2000), in turn citing 11th Cir. R. 36-2).\n 19\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 20 of 23\n\n\nfinality to the questions presented. But we cannot. “‘In the absence of standing, a\n\ncourt is not free to opine in an advisory capacity about the merits of a plaintiff’s\n\nclaims.’” CAMP Legal Def. Fund, 451 F.3d at 1269 (quoting Bochese v. Town of\n\nPonce Inlet, 405 F.3d 964, 974 (11th Cir. 2005)). Again, “standing is ‘perhaps the\n\nmost important’ jurisdictional doctrine, and, as with any jurisdictional requisite, we\n\nare powerless to hear a case when it is lacking.” Bochese, 405 F.3d at 974 (citation\n\nomitted).\n\n Because the District Court had no jurisdiction to entertain this suit, we\n\nVACATE its judgment. The District Court is instructed to enter an order\n\nremanding the case to the Circuit Court of the Seventeenth Judicial Circuit in and\n\nfor Broward County, Florida.7\n\n SO ORDERED.\n\n\n\n\n 7\n We acknowledge “the fundamental principle that state courts are the final arbiters of\nstate law.” See Agan v. Vaughn, 119 F.3d 1538, 1549 (11th Cir. 1997). For that reason, on\nremand, the state court should engage anew in any contract interpretation necessary to its\nstanding or merits determinations.\n 20\n\n Case: 17-15606 Date Filed: 05/30/2019 Page: 21 of 23\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: A&M GERBER CHIROPRACTIC LLC, as Assignee of Conor Carruthers, on Behalf of Itself and All Others Similarly Situated, Plaintiff - Appellee, v. GEICO GENERAL INSURANCE COMPANY, Defendant - Appellant.\\nCourt: U.S. Court of Appeals for the Eleventh Circuit\\nDate decided: 2019-05-30\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: Yes\\nAdditional notes: \\n\\n[CASE_TEXT]\\nCase: 17-15606 Date Filed: 05/30/2019 Page: 1 of 23\\n\\n\\n [PUBLISH]\\n\\n\\n\\n IN THE UNITED STATES COURT OF APPEALS\\n\\n FOR THE ELEVENTH CIRCUIT\\n ________________________\\n\\n No. 17-15606\\n ________________________\\n\\n D.C. Docket No. 0:16-cv-62610-BB\\n\\n\\nA&M GERBER CHIROPRACTIC LLC,\\nas assignee of Conor Carruthers, on behalf\\nof itself and all others similarly situated,\\n\\n Plaintiff - Appellee,\\n\\nversus\\n\\nGEICO GENERAL INSURANCE COMPANY,\\n\\n Defendant - Appellant.\\n\\n ________________________\\n\\n Appeal from the United States District Court\\n for the Southern District of Florida\\n ________________________\\n\\n (May 30, 2019)\\n\\n ON PETITION FOR REHEARING\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 2 of 23\\n\\n\\nBefore WILSON and BRANCH, Circuit Judges, and VINSON,∗ District Judge.\\n\\nVINSON, District Judge:\\n\\n Upon consideration, we grant the Appellee’s petition for panel rehearing.\\n\\nWe vacate our prior opinion in this case, issued on April 19, 2019, and published at\\n\\n921 F.3d 1273 (11th Cir. 2019), and hereby substitute the following opinion in its\\n\\nplace.\\n\\n Conor Carruthers was involved in a car accident on March 18, 2015, after\\n\\nwhich he sought medical services from A&M Gerber Chiropractic LLC. At the\\n\\ntime, Carruthers was covered under an automobile insurance policy issued by\\n\\nGEICO General Insurance Company. Pursuant to Florida’s Motor Vehicle No-\\n\\nFault Law, the policy provided him with $10,000 in personal injury protection\\n\\n(PIP) benefits. See Fla. Stat. § 627.736(1) (mandating that automobile insurers\\n\\nprovide PIP benefits “to a limit of $10,000”). To be entitled to the full $10,000,\\n\\nhowever, the statute required that Carruthers—like all PIP beneficiaries—be\\n\\ndiagnosed by an authorized health care provider with an “emergency medical\\n\\ncondition” (EMC); without such a diagnosis, he was limited to $2,500 in benefits.\\n\\nSee id. at § 627.736(1)(a)(3)-(4); Robbins v. Garrison Prop. & Cas. Ins. Co., 809\\n\\nF.3d 583, 587-88 (11th Cir. 2015) (holding in consolidated appeal that “[b]ecause\\n\\n\\n\\n ∗Honorable C. Roger Vinson, United States District Judge for the Northern District of\\nFlorida, sitting by designation.\\n 2\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 3 of 23\\n\\n\\nneither Robbins’ nor Enivert’s claim was supported by [an EMC determination],\\n\\nneither Garrison nor Progressive violated Fla. Stat. § 627.736 by limiting benefits\\n\\nto $2,500”); accord, e.g., Progressive Am. Ins. Co. v. Eduardo J. Garrido D.C.,\\n\\nP.A., 211 So.3d 1086, 1093 (Fla. 3d DCA 2017); Medical Ctr. of Palm Beaches v.\\n\\nUSAA Cas. Ins. Co., 202 So.3d 88, 92-93 (Fla. 4th DCA 2016); McCarty v. Myers,\\n\\n125 So.3d 333, 335 (Fla. 1st DCA 2013).\\n\\n It is undisputed that Carruthers was not diagnosed with an EMC at the time\\n\\nthis case was filed. It is also undisputed that, despite the lack of an EMC finding,\\n\\nGEICO paid Carruthers/Gerber $7,311 in PIP benefits pre-suit, well in excess of\\n\\nthe $2,500 cap. Even though Carruthers received almost triple the amount in PIP\\n\\nbenefits that he was entitled to, Gerber believed that GEICO had misinterpreted\\n\\ncertain language in its automobile policies and that this misinterpretation resulted\\n\\nin GEICO consistently underpaying PIP benefits as a “general business practice.”\\n\\n Specifically, the policy contains an endorsement identified as FLPIP (01-\\n\\n13), and that endorsement (under the heading “PAYMENTS WE WILL MAKE”)\\n\\nreferences fee schedules pursuant to which GEICO will pay 80% of benefits that\\n\\nare medically necessary. The endorsement goes on to state: “For all other medical\\n\\nservices, supplies, and care [GEICO will pay] 200 percent of the allowable amount\\n\\nunder [a Medicare Part B fee schedule],” subject to a limitation of 80% of the\\n\\n“maximum reimbursable allowance under workers’ compensation . . . .” Below\\n\\n\\n 3\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 4 of 23\\n\\n\\nthat statement, GEICO added the following: “A charge submitted by a provider,\\n\\nfor an amount less than the amount allowed above, shall be paid in the amount of\\n\\nthe charge submitted.” The underlying dispute in this case hinges on whether this\\n\\nsingle sentence is the operative language of the policy for health care provider bills\\n\\nof less than 200% of the fee schedule.\\n\\n GEICO has taken the position that the policy is an “80/20 policy” pursuant\\n\\nto which it was required to pay the lower of 80% of the fee schedule amount or\\n\\n80% of the charged amount, while insureds are required to pay the remaining 20%\\n\\nas co-insurance. To supports its position, GEICO relied, inter alia, on a document\\n\\nmailed or provided to its PIP policyholders effective on or after January 1, 2013,\\n\\nand identified as M608 (01-13). This document was titled\\n\\n IMPORTANT NOTICE\\n\\n FEE SCHEDULE ENDORSEMENT\\n\\nand it provides in relevant part that “in no event will the Company pay more than\\n\\n80 percent” of properly billed medical expenses. GEICO asserts that M608 (01-\\n\\n13) is an endorsement and, thus, part of the policy. Gerber has argued that M608\\n\\n(01-13) is not an endorsement/part of the policy, and it further argues that FLPIP\\n\\n(01-13) provides that when a health care provider bills for services at an amount\\n\\nless than 200% of the fee schedule, GEICO must pay the charge as billed (that is,\\n\\n“in the amount of the charge submitted”) without the 20% reduction.\\n\\n\\n 4\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 5 of 23\\n\\n\\n Carruthers assigned his rights to his treating chiropractic clinic, Gerber,\\n\\nwhich later filed a declaratory judgment class action suit in Florida state court in\\n\\nSeptember 2016. The complaint sought certification of a class (with Gerber as the\\n\\nclass representative) along with a declaration (a) that GEICO’s interpretation of its\\n\\npolicy language was wrong, and (b) that the misinterpretation “constitutes a breach\\n\\nof the insurance Policy.” Although the complaint sought a declaration that GEICO\\n\\nhad breached the policy, the complaint stated that “there is no claim for monetary\\n\\nrelief” in the case.\\n\\n GEICO removed the case to the United States District Court for the\\n\\nSouthern District of Florida in November 2016, pursuant to the Class Action\\n\\nFairness Act, and Gerber filed an unsuccessful motion to remand the case for lack\\n\\nof Article III standing. The District Court appointed Gerber as class\\n\\nrepresentative, and it certified the class to include:\\n\\n All health care providers that received an assignment of\\n benefits from a claimant and thereafter, pursuant to that\\n assignment, submitted claims for no-fault benefits under\\n GEICO PIP policies to which Endorsement FLPIP (01–\\n 13) applies, and any subsequent policies with\\n substantially similar language that were in effect since\\n January 1, 2013, where GEICO utilized the Code BA\\n [billed amount] with respect to the payment of any\\n claims.\\n\\n Shortly after the action was removed to federal court, and while its motion to\\n\\nremand was pending, Gerber filed an amended complaint. The amended complaint\\n\\n\\n 5\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 6 of 23\\n\\n\\nwas largely the same as the original complaint, but it added another sentence to re-\\n\\nemphasize that “this action does not assert a claim for any monetary relief,” and it\\n\\ndeleted the request for a declaration that GEICO’s misinterpretation of the disputed\\n\\npolicy language “constitutes a breach of the insurance Policy.” Thus, as amended,\\n\\nthe complaint clarified that it only sought declaratory relief and that there was no\\n\\nclaim for breach of contract or request for money damages related thereto. In July\\n\\n2017—more than two years after the underlying car accident, and ten months after\\n\\nthe litigation was filed—Carruthers obtained an EMC medical diagnosis.\\n\\n On cross motions for summary judgment, GEICO argued, inter alia, that\\n\\nGerber lacked standing at the outset of the lawsuit because it was undisputed that\\n\\nGEICO had paid Gerber more than $2,500 before the case was filed, even though\\n\\nhe had not been diagnosed with an EMC at that time. By order dated November\\n\\n17, 2017, the District Court disagreed with GEICO and found there was standing.\\n\\nIt also ruled that M608 (01-13) was not an endorsement (but rather was merely a\\n\\nnotice) and, thus, it was not part of the policy. Applying a textual interpretation of\\n\\nthe FLPIP (01-13) endorsement, the District Court granted summary judgment for\\n\\nGerber and held that, “under the disputed provision, when a health care provider\\n\\nbills for covered services in an amount less than 200% of the fee schedule, GEICO\\n\\nis required to pay the charge as billed without any reduction.”\\n\\n\\n\\n\\n 6\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 7 of 23\\n\\n\\n GEICO now appeals, arguing that Gerber lacked standing to bring this case.\\n\\nIt further argues that the District Court erred in certifying the class; in limiting the\\n\\ndocuments that comprise the policy (that is, in failing to treat M608 (01-13) as an\\n\\nendorsement); and in ruling for Gerber on the merits as to the policy interpretation\\n\\nquestion.\\n\\n I.\\n\\n We must begin with the question of standing. See Kondrat’yev v. City of\\n\\nPensacola, Fla., 903 F.3d 1169, 1172 (11th Cir. 2018). If there is no standing, we\\n\\nmust end there, too. University of S. Ala. v. American Tobacco Co., 168 F.3d 405,\\n\\n410 (11th Cir. 1999) (“Simply put, once a federal court determines that [the\\n\\nplaintiff has no standing], the court is powerless to continue.”).\\n\\n We review standing determinations de novo. See, e.g., SEC v. Quest Energy\\n\\nMgmt. Group, Inc., 768 F.3d 1106, 1108 (11th Cir. 2014) (citing CAMP Legal Def.\\n\\nFund, Inc. v. City of Atlanta, 451 F.3d 1257, 1268 (11th Cir. 2006)). After de novo\\n\\nreview—and with the benefit of oral argument—we conclude that Gerber lacks\\n\\nstanding.\\n\\n II.\\n\\n Article III of the Constitution limits federal courts to adjudicating actual\\n\\n“cases” and “controversies.” See, e.g., Allen v. Wright, 468 U.S. 737, 750 (1984),\\n\\nabrogated on other grounds by Lexmark Int’l, Inc. v. Static Control Components,\\n\\n\\n 7\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 8 of 23\\n\\n\\nInc., 572 U.S. 118 (2014). The case-or-controversy requirement sets fundamental\\n\\nlimits on federal judicial power. Id. “Perhaps the most important of the Article III\\n\\ndoctrines grounded in the case-or-controversy requirement is that of standing.”\\n\\nWooden v. Bd. of Regents of the Univ. Sys. of Ga., 247 F.3d 1262, 1273 (11th Cir.\\n\\n2001). Standing cannot be waived or conceded by the parties, and it may be raised\\n\\n(even by the court sua sponte) at any stage of the case. See Bender v. Williamsport\\n\\nArea Sch. Dist., 475 U.S. 534, 541 (1986); Harris v. Evans, 20 F.3d 1118, 1121 n.4\\n\\n(11th Cir. 1994).\\n\\n “In essence the question of standing is whether the litigant is entitled to\\n\\nhave the court decide the merits of the dispute or of particular issues.” Warth v.\\n\\nSeldin, 422 U.S. 490, 498 (1975); see also Yellow Pages Photos, Inc. v. Ziplocal,\\n\\nLP, 795 F.3d 1255, 1264 (11th Cir. 2015) (same). “The party who invokes a\\n\\nfederal court’s authority must show, at an ‘irreducible minimum,’ that at the time\\n\\nthe complaint was filed, he has suffered some actual or threatened injury resulting\\n\\nfrom the defendant’s conduct, that the injury fairly can be traced to the challenged\\n\\naction, and that the injury is likely to be redressed by favorable court disposition.”\\n\\nAtlanta Gas Light Co. v. Aetna Cas. & Sur. Co., 68 F.3d 409, 414 (11th Cir. 1995).\\n\\n Echoing the “case or controversy” requirement of Article III, the Declaratory\\n\\nJudgment Act “provides that a declaratory judgment may only be issued in the case\\n\\nof an actual controversy.” See Emory v. Peeler, 756 F.2d 1547, 1551-52 (11th Cir.\\n\\n\\n 8\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 9 of 23\\n\\n\\n1985) (citing 28 U.S.C. § 2201); see also Atlanta Gas Light, 68 F.3d at 414 (“In all\\n\\ncases arising under the Declaratory Judgment Act, . . . the threshold question is\\n\\nwhether a justiciable controversy exists.”). “That is, under the facts alleged, there\\n\\nmust be a substantial continuing controversy between parties having adverse legal\\n\\ninterests.” Emory, 756 F.2d at 1552. The controversy between the parties cannot\\n\\nbe “conjectural, hypothetical, or contingent; it must be real and immediate, and\\n\\ncreate a definite, rather than speculative threat of future injury.” Id. In order to\\n\\ndemonstrate that there is a case or controversy that satisfies Article III’s standing\\n\\nrequirement when a plaintiff is seeking declaratory relief—as opposed to seeking\\n\\ndamages for past harm—the plaintiff must allege facts from which it appears that\\n\\nthere is a “substantial likelihood that he will suffer injury in the future.” Malowney\\n\\nv. Federal Collection Deposit Grp., 193 F.3d 1342, 1346 (11th Cir. 1999); accord\\n\\nStrickland v. Alexander, 772 F.3d 876, 883 (11th Cir. 2014) (“Where the plaintiff\\n\\nseeks declaratory or injunctive relief, as opposed to damages for injuries already\\n\\nsuffered, . . . the injury-in-fact requirement insists that a plaintiff ‘allege facts from\\n\\nwhich it appears there is a substantial likelihood that he will suffer injury in the\\n\\nfuture.’”) (quoting Malowney, 193 F.3d at 1346). “Thus, in order for this Court to\\n\\nhave jurisdiction to issue a declaratory judgment, . . . [the plaintiffs] must assert a\\n\\nreasonable expectation that the injury they have suffered will continue or will be\\n\\nrepeated in the future.” Malowney, 193 F.3d at 1347; see also id. at 1348 (“Injury\\n\\n\\n 9\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 10 of 23\\n\\n\\nin the past . . . does not support a finding of an Article III case or controversy when\\n\\nthe only relief sought is a declaratory judgment.”). Accordingly, if a plaintiff does\\n\\nnot assert a reasonable expectation of future injury, he “lack[s] standing to bring an\\n\\naction for declaratory relief[.]” See id. at 1348.\\n\\n In this case, Gerber, as assignee, stands in Carruthers’ shoes. Houk v. C.I.R.,\\n\\n173 F.2d 821, 825 (5th Cir. 1949) (“[A]n assignee . . . stands in the same position\\n\\nas its assignor had stood.”).1 It necessarily follows, then, that if Carruthers had no\\n\\nstanding to file this case against GEICO, Gerber has no standing either. Crossman\\n\\nv. Fontainebleau Hotel Corp., 273 F.2d 720, 725 (5th Cir. 1959) (“An assignee has\\n\\nno greater rights than his assignor[.]”).\\n\\n It is well-settled that “if none of the named plaintiffs purporting to represent\\n\\na class establishes the requisite of a case or controversy with the defendants, none\\n\\nmay seek relief on behalf of himself or any other member of the class.” O’Shea v.\\n\\nLittleton, 414 U.S. 488, 494 (1974); see also Prado-Steiman ex rel. Prado v. Bush,\\n\\n221 F.3d 1266, 1279-80 (11th Cir. 2000) (class representative must have individual\\n\\nstanding to raise class claims); Wooden, 247 F.3d at 1288 (claim cannot be asserted\\n\\nfor a class “‘unless at least one named plaintiff has suffered the injury that gives\\n\\nrise to that claim’”) (quoting Prado-Steiman, 221 F.3d at 1280). As we have said:\\n\\n\\n 1\\n In Bonner v. City of Prichard, 661 F.2d 1206, 1209 (11th Cir. 1981) (en banc), we adopted\\nas binding precedent all Fifth Circuit decisions rendered prior to the close of business on September\\n30, 1981.\\n 10\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 11 of 23\\n\\n\\n Under elementary principles of standing, a plaintiff must\\n allege and show that he personally suffered injury. If he\\n cannot show personal injury, then no article III case or\\n controversy exists, and a federal court is powerless to\\n hear his grievance. This individual injury requirement is\\n not met by alleging that injury has been suffered by\\n other, unidentified members of the class to which the\\n plaintiff belongs and which he purports to represent.\\n Thus, a plaintiff cannot include class action allegations in\\n a complaint and expect to be relieved of personally\\n meeting the requirements of constitutional standing, even\\n if the persons described in the class definition would\\n have standing themselves to sue. A named plaintiff in a\\n class action who cannot establish the requisite case or\\n controversy between himself and the defendants simply\\n cannot seek relief for anyone—not for himself, and not\\n for any other member of the class.\\n\\nGriffin v. Dugger, 823 F.2d 1476, 1482-83 (11th Cir. 1987) (multiple citations,\\n\\nquotation marks, and brackets omitted).\\n\\n Importantly, Article III standing must be determined as of the time that the\\n\\nplaintiff’s complaint is filed. See, e.g., Arcia v. Florida Sec’y of State, 772 F.3d\\n\\n1335, 1340 (11th Cir. 2014); Focus on the Family v. Pinellas Suncoast Transit\\n\\nAuth., 344 F.3d 1263, 1275 (11th Cir. 2003) (collecting multiple cases); Atlanta\\n\\nGas Light, 68 F.3d at 414 (in determining whether there is an Article III case or\\n\\ncontroversy, “we ‘look to the state of affairs as of the filing of the complaint; a\\n\\njusticiable controversy must have existed at that time’”) (citation omitted); accord\\n\\nMorrison v. Bd. of Educ. of Boyd Cty., 521 F.3d 602, 616 (6th Cir. 2008) (stating\\n\\nthat standing must be evaluated “at the time the plaintiff filed his or her complaint\\n\\n\\n 11\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 12 of 23\\n\\n\\nand not at anytime thereafter”) (citation omitted). Florida’s standing requirement\\n\\nis the same in this respect. See Progressive Exp. Ins. Co. v. McGrath Community\\n\\nChiropractic, 913 So.2d 1281, 1284-85 (Fla. 2d DCA 2005) (citing and discussing\\n\\ncases and noting that “[a]s these cases demonstrate, the plaintiff’s lack of standing\\n\\nat the inception of the case is not a defect that may be cured by the acquisition of\\n\\nstanding after the case is filed”).\\n\\n III.\\n\\n GEICO argues on appeal, as it did below, that Carruthers was only entitled\\n\\nto $2,500 in PIP benefits under the policy because there was no EMC diagnosis at\\n\\nthe time the complaint was filed. Consequently, Gerber (as Carruthers’ assignee)\\n\\nwas not entitled to benefits beyond $2,500. Because GEICO paid much more than\\n\\nthat amount, Carruthers/Gerber didn’t suffer harm as a result of GEICO’s alleged\\n\\nmisapplication of its policy. According to GEICO, no matter how we interpret the\\n\\ndisputed policy language, Gerber will not be able to recover anything from GEICO\\n\\n(i.e., there was no injury to Carruthers resulting from GEICO’s conduct that can be\\n\\nfairly traced to the challenged action and redressed by a favorable court ruling),\\n\\nthereby eliminating the existence of a case or controversy. GEICO is correct.\\n\\n When an insurance company has “paid all benefits in full . . . [t]here is no\\n\\ncase or controversy[.]” Harrison v. United Mine Workers of Am. 1974 Ben. Plan\\n\\n\\n\\n\\n 12\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 13 of 23\\n\\n\\n& Trust, 941 F.2d 1190, 1193 (11th Cir. 1991); 2 accord Progressive Am. Ins. Co.\\n\\nv. Stand-Up MRI of Orlando, 990 So.2d 3, 4 (Fla. 5th DCA 2008) (“a PIP insurer is\\n\\nnot liable for benefits once benefits have been exhausted”); Neighborhood Health\\n\\nP’ship Inc. v. Fischer, 913 So.2d 703, 705 (Fla. 3d DCA 2005) (trial court abused\\n\\nits discretion in certifying a class action “where the uncontroverted evidence is\\n\\nclear that Dr. Fischer lacks standing to serve as a class representative because he\\n\\nhas no claim for damages against NHP, and, indeed, may in fact owe a refund to\\n\\nNHP for claims overpaid to him”); Graham v. State Farm Fire & Cas. Co., 813\\n\\nSo.2d 273, 274 (Fla. 5th DCA 2002) (“The conceded facts show that the Grahams\\n\\nwere paid in full two years prior to the filing of the class claims. . . . Based on the\\n\\nconceded facts, there is no existing dispute between the Grahams and State Farm\\n\\nthat would give the Grahams standing to proceed on behalf of other potential\\n\\nplaintiffs with similar disputes.”); Ramon v. Aries Ins. Co., 769 So.2d 1053 (Fla.\\n\\n\\n 2\\n We recognize that there was “no case or controversy” in Harrison because the case was\\nrendered moot after the insurer paid benefits in full while the case was pending, unlike this case\\nwhere the benefits were paid in full pre-suit. But that is a distinction without a difference. As\\nProfessor Monaghan has observed, the justiciability doctrines of standing and mootness “share\\nthe same root.” Henry P. Monaghan, Constitutional Adjudication: The Who and When, 82 Yale\\nL.J. 1363, 1384 (1973). The Supreme Court has described mootness as merely “‘the doctrine of\\nstanding set in a time frame: The requisite personal interest that must exist at the commencement\\nof the litigation (standing) must continue throughout its existence (mootness).’” United States\\nParole Comm’n v. Geraghty, 445 U.S. 388, 397 (1980) (quoting Monaghan, supra). If a case\\nbecomes non-justiciable because an insurer has paid full benefits while the case is pending (as in\\nHarrison), the case should be non-justiciable if it is undisputed that the benefits were paid before\\nthe case was even filed (as here). To hold otherwise would mean that if GEICO had denied PIP\\nbenefits pre-suit but then paid Gerber $7,311 shortly after the case was filed, the case would have\\nbecome moot and thus non-justiciable, but undisputed evidence showing that those same benefits\\nwere paid before the case was filed wouldn’t raise any justiciability concerns.\\n 13\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 14 of 23\\n\\n\\n3d DCA 2000) (policyholder who received full payment of PIP benefits lacked\\n\\nstanding to pursue class action claim).\\n\\n In finding that Gerber had standing in the order under review, the District\\n\\nCourt relied on a single case: Mills v. Foremost Ins. Co., 511 F.3d 1300 (11th Cir.\\n\\n2008). Based on that case, the District Court held that GEICO’s pre-suit (and pre-\\n\\nEMC) payment in excess of the statutory cap didn’t implicate standing, but, rather,\\n\\nit was an exhaustion of benefits affirmative defense. The District Court’s reliance\\n\\non Mills was misplaced.\\n\\n The plaintiffs in that case, Dale and Diane Mills, owned a mobile home that\\n\\nwas insured under a policy issued by the defendant, Foremost Insurance Company.\\n\\nThey filed a class action alleging that Foremost had failed to pay them (and other\\n\\ninsureds) for overhead, profit, and taxes after they sustained hurricane-damaged\\n\\nlosses, and they sought compensation for those “Withheld Payments.” Notably—\\n\\nand in contrast to this action—the plaintiffs in Mills were seeking both declaratory\\n\\nrelief and damages for breach of contract. The defendant argued that the plaintiffs\\n\\nhad failed to satisfy certain preconditions in the policy that allegedly required them\\n\\nto complete repair or replacement of their damaged property first and then submit a\\n\\nrepair or replacement cost claim to the insurance company before entitling them to\\n\\nthe Withheld Payments. Foremost argued that the Millses’ failure to do so\\n\\ndeprived them of standing, and the District Court agreed.\\n\\n\\n 14\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 15 of 23\\n\\n\\n In reversing, we began by holding the District Court erred in interpreting the\\n\\npolicy to require that the Millses jump through the aforementioned hoops. See 511\\n\\nF.3d at 1304-06 (rejecting the district court’s conclusion that preconditions in the\\n\\npolicy required the Millses to complete repair or replacement of their damaged\\n\\nproperty and to submit such a replacement cost claim to be entitled to the Withheld\\n\\nPayments). We then continued:\\n\\n The district court also erred in treating these particular\\n insurance coverage issues under the Policy as standing\\n issues. The complaint alleges that the Millses had a\\n mobile home, that Foremost issued an insurance policy\\n covering hurricane damage to the mobile home, that a\\n hurricane damaged the Millses’ mobile home, that the\\n Millses made a claim under the Policy for those damages,\\n and that Foremost paid less on the claim than the Millses\\n contend they are owed. Thus, the Millses clearly had\\n standing to sue for damages under the Policy. See\\n Wooden v. Bd. of Regents, 247 F.3d 1262, 1273-74 (11th\\n Cir. 2001) (stating that standing is essentially a\\n determination of “whether the litigant is entitled to have\\n the court decide the merits of the dispute or of particular\\n issues,” and requires that a plaintiff have suffered a\\n concrete, particularized injury that is caused by the\\n challenged action of the defendant and can be redressed\\n by a favorable court decision).\\n\\n Whether the Withheld Payments were covered by the\\n Policy is an issue of whether the Millses’ complaint fails\\n to state a claim for relief under the Policy—not a\\n standing issue. Whether the Millses’ complaint pled\\n sufficient facts is likewise a failure-to-state-a-claim issue.\\n We thus reject Foremost’s standing arguments as to the\\n Millses’ individual claims against Foremost on this basis\\n as well.\\n\\n\\n 15\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 16 of 23\\n\\n\\nId. at 1306-07 (emphasis added).\\n\\n Therefore, Mills was not (as here) an exhaustion of benefits case. Rather, it\\n\\nwas a coverage dispute that included a breach of contract claim seeking damages\\n\\narising out of that dispute. This distinction is critical because if the plaintiffs had\\n\\nprevailed in Mills, they would have been entitled to the Withheld Payments. Thus,\\n\\nwe found there that “the Millses clearly had standing to sue for damages under the\\n\\nPolicy” because the plaintiffs alleged that the insurer “paid [them] less on the claim\\n\\nthan [they] contend they are owed,” and a ruling in their favor on that point would\\n\\nentitle them to the money owed. 511 F.3d at 1307 (emphasis added). By contrast,\\n\\nwhen insurance benefits are fully exhausted (as here, and as in certain of the cases\\n\\ncited supra), there is no case or controversy because no money is owed regardless\\n\\nof how the case is ultimately decided. See, e.g., Harrison, 941 F.2d at 1193. Mills\\n\\nwould apply if Gerber alleged breach of contract and sought damages. But, it\\n\\nspecifically tailored its complaint to avoid such allegations. 3\\n\\n\\n\\n 3\\n In her concurring opinion, Judge Branch believes it is irrelevant that GEICO paid in\\nexcess of the PIP limit because Gerber is not seeking money damages. While it is true—as we\\nhave noted several times—that Gerber is not seeking money damages for unpaid benefits in this\\ncase, Gerber has made clear in its brief, in its notice of supplemental authority, and during oral\\nargument that the declaratory relief it seeks is merely a precursor to a claim for money damages\\nin subsequent cases. See Appellee Brief at 45 (“declaratory relief may serve ‘as a predicate for\\nlater monetary relief’”) (quoting Gooch v. Life Investors Ins. Co. of Am., 672 F.3d 402, 429 (6th\\nCir. 2012)); Notice of Supplemental Authority, dated December 5, 2018 (noting “‘a declaratory\\njudgment is normally a prelude to a request for other relief’”) (quoting Berger v. Xerox Corp.\\nRetirement Income Guarantee Plan, 338 F.3d 755, 763-64 (7th Cir. 2003)); Oral Argument\\n18:40-18:56 (“The declaratory relief, as we say in the cases cited in the supplemental authority\\n[Berger] and in the Gooch case from the Sixth Circuit that I want to focus on, all make it clear\\n 16\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 17 of 23\\n\\n\\n This is not to say, of course, that to have standing to pursue a declaratory\\n\\njudgment action the complaint must seek monetary relief. It doesn’t have to seek\\n\\nsuch relief. As earlier noted, however, when a plaintiff is seeking declaratory\\n\\nrelief without a claim for money damages for injuries already suffered, the plaintiff\\n\\nmust allege facts from which it appears that there is a substantial likelihood that he\\n\\nwill suffer injury in the future. E.g., Strickland, 772 F.3d at 883. Gerber has not\\n\\nalleged such facts here. Quite to the contrary, a review of Gerber’s motion to\\n\\nremand indicates that it specifically tailored its complaint to avoid alleging future\\n\\ninjury (as it did with the money damages). Indeed, Gerber unequivocally stated in\\n\\nits motion that “Plaintiff does not make any claim in the complaint that there is a\\n\\nrisk of future injury.” See Remand Mot. at 9 (emphasis added). 4\\n\\n\\nthat there’s nothing unusual about having declaratory relief as a precursor to monetary relief”).\\nConsistent with the foregoing, counsel for Gerber expressly said at oral argument that if their\\ninterpretation of GEICO’s policy is correct and Gerber prevails in this lawsuit, the “monetary\\nclaims . . . will come” later. Oral Argument 20:30-20:35. We understand this argument (that\\nthere are viable claims for damages that will be raised in the future) to potentially implicate the\\nstanding issue. If Gerber were to win on the merits, monetary claims may indeed come later\\n(and there may be standing) for class members who were underpaid as the result of GEICO’s\\nmisinterpretation of its policy language. However, it is undisputed that when the complaint was\\nfiled (the only time that matters) Carruthers (the only person who matters) was paid more in PIP\\nbenefits than he was entitled to. See, e.g., Appellee Brief at 29 (acknowledging that GEICO\\n“voluntarily pa[id] Gerber $7,311 with no EMC determination when Gerber made its insurance\\nclaims”). Thus, there is no monetary claim for Gerber as Carruthers’ assignee, and there will be\\nno such claim in the future for Carruthers—even though he was diagnosed with an EMC after\\nthis case was filed—because standing must be determined as of the time of filing. That is why\\nthe exhaustion of benefits issue is relevant and why we have discussed it, even though money\\ndamages are not being sought in this litigation.\\n 4\\n Ironically, it appears that Gerber didn’t allege future injury because it knew that doing\\nso would implicate federal jurisdiction, and it wanted to avoid federal court and stay in Florida\\nstate court. See Remand Mot. at 7-9 (arguing that federal courts lack Article III jurisdiction over\\n 17\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 18 of 23\\n\\n\\n Gerber now argues—directly contrary to what it previously argued—that\\n\\nthere is a risk of future injury here. Specifically, Gerber argues that the dispute\\n\\nabout the policy language will continue or be repeated in the future, and it will\\n\\ninjure Gerber and other chiropractors insofar as they don’t know whether to tell\\n\\ntheir patients that GEICO is responsible for the full 100% of the relevant charges,\\n\\nor whether the patients are responsible for 20%. See Oral Argument 19:16-20:23.\\n\\nThis is significant, Gerber’s counsel noted during oral argument, as evidenced by\\n\\nthe fact that GEICO had indirectly accused Gerber of insurance fraud in this case\\n\\nfor not attempting to collect the 20% from Carruthers, and such accusations could\\n\\nadversely impact its license in the future. See id. at 19:10-20:13.5\\n\\n Whether and to what extent Gerber might be injured is beside the point\\n\\nbecause the proper inquiry in this case must focus on the potential future injury to\\n\\nCarruthers, not to Gerber or other members of the class. Cf. Kostelac v. Allianz\\n\\nGlobal Corp. & Specialty AG, 517 F. App’x 670, 675-76 (11th Cir. 2013) (stating\\n\\nthat because an assignee must stand in the shoes of the assignor, and he has no\\n\\nrights greater than the assignor, “the relevant inquiry” must focus on the assignor,\\n\\n\\n\\ndeclaratory judgment actions if there is no claim for money damages or future injury—neither of\\nwhich, Gerber argued, was present in this case—but “the Florida Declaratory Judgment Act is\\nmuch more expansive and permits a claim similar to this action”).\\n 5\\n Gerber also points out in its brief that GEICO argued early on in this lawsuit (when it\\nremoved the action to federal court) that Gerber did have standing. As we have already noted,\\nhowever, standing cannot be waived or conceded, and we must independently decide whether it\\nexists.\\n 18\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 19 of 23\\n\\n\\nand it is “misguided” to “shift the . . . inquiry” to the assignee) (citing Crossman,\\n\\n273 F.2d at 725; Houk, 173 F.2d at 825). 6 And we can see no potential future\\n\\nthreat to Carruthers, other than the possibility that he may someday be in another\\n\\ncar accident; sustain an injury entitling him to PIP benefits; and still be insured by\\n\\nGEICO under the same or a similar policy being interpreted the same way, thereby\\n\\nhaving this issue present itself again. But, that is too contingent to constitute a\\n\\n“substantial likelihood” of future injury. See, e.g., Emory, 756 F.2d at 1552 (to\\n\\nsatisfy Article III, the case or controversy cannot be “conjectural, hypothetical, or\\n\\ncontingent; it must be real and immediate, and create a definite, rather than\\n\\nspeculative threat of future injury”).\\n\\n In the absence of a claim for money damages or substantial likelihood that\\n\\nCarruthers will suffer a future injury—both of which Gerber was careful to avoid\\n\\nalleging here—Gerber has no standing to pursue this case.\\n\\n IV.\\n\\n We recognize that this appeal raises an important issue for GEICO’s Florida\\n\\nPIP policyholders and for medical providers treating them. And we recognize, too,\\n\\nthat the lawsuit has been pending for several years and has consumed a lot of both\\n\\njudicial and attorney resources. If we could, we would reach the merits and give\\n\\n\\n 6\\n Although an unpublished opinion is not binding, it may be cited as persuasive authority.\\nSee, e.g., Searcy v. R.J. Reynolds Tobacco Co., 902 F.3d 1342, 1355 n.5 (11th Cir. 2018) (citing\\nUnited States v. Futrell, 209 F.3d 1286, 1289 (11th Cir. 2000), in turn citing 11th Cir. R. 36-2).\\n 19\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 20 of 23\\n\\n\\nfinality to the questions presented. But we cannot. “‘In the absence of standing, a\\n\\ncourt is not free to opine in an advisory capacity about the merits of a plaintiff’s\\n\\nclaims.’” CAMP Legal Def. Fund, 451 F.3d at 1269 (quoting Bochese v. Town of\\n\\nPonce Inlet, 405 F.3d 964, 974 (11th Cir. 2005)). Again, “standing is ‘perhaps the\\n\\nmost important’ jurisdictional doctrine, and, as with any jurisdictional requisite, we\\n\\nare powerless to hear a case when it is lacking.” Bochese, 405 F.3d at 974 (citation\\n\\nomitted).\\n\\n Because the District Court had no jurisdiction to entertain this suit, we\\n\\nVACATE its judgment. The District Court is instructed to enter an order\\n\\nremanding the case to the Circuit Court of the Seventeenth Judicial Circuit in and\\n\\nfor Broward County, Florida.7\\n\\n SO ORDERED.\\n\\n\\n\\n\\n 7\\n We acknowledge “the fundamental principle that state courts are the final arbiters of\\nstate law.” See Agan v. Vaughn, 119 F.3d 1538, 1549 (11th Cir. 1997). For that reason, on\\nremand, the state court should engage anew in any contract interpretation necessary to its\\nstanding or merits determinations.\\n 20\\n\\n Case: 17-15606 Date Filed: 05/30/2019 Page: 21 of 23\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2296,"cells":{"id":{"kind":"number","value":4616544,"string":"4,616,544"},"name":{"kind":"string","value":"GOVERNMENT OF the Province of MANITOBA, Appellee State of Missouri, Ex Rel. Eric Schmitt, Missouri Attorney General's Office, Appellant v. David BERNHARDT, Secretary, U.S. Department of the Interior, Et Al., Appellees"},"name_abbreviation":{"kind":"string","value":"Gvt. Province of Manitoba v. David Bernhardt"},"decision_date":{"kind":"string","value":"2019-05-03"},"docket_number":{"kind":"string","value":"17-5242"},"court":{"kind":"string","value":"U.S. Court of Appeals for the District of Columbia Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Henderson, Rogers, Srinivasan\", \"parties\": \"\", \"opinions\": [{\"author\": \"Opinion for the Court filed by Circuit Judge HENDERSON\", \"type\": \"010combined\", \"text\": \"United States Court of Appeals\\n FOR THE DISTRICT OF COLUMBIA CIRCUIT\\n\\n\\n\\nArgued November 8, 2018 Decided May 3, 2019\\n\\n No. 17-5242\\n\\n GOVERNMENT OF THE PROVINCE OF MANITOBA,\\n APPELLEE\\n\\n STATE OF MISSOURI, EX REL. ERIC SCHMITT,\\n MISSOURI ATTORNEY GENERAL’S OFFICE,\\n APPELLANT\\n\\n v.\\n\\n DAVID BERNHARDT, SECRETARY,\\n U.S. DEPARTMENT OF THE INTERIOR, ET AL.,\\n APPELLEES\\n\\n\\n Appeal from the United States District Court\\n for the District of Columbia\\n (No. 1:02-cv-02057)\\n\\n\\n Joshua M. Divine, Deputy Solicitor, Office of the Attorney\\nGeneral for the State of Missouri, argued the cause for the\\nappellant. Joshua D. Hawley, Attorney General, D. John\\nSauer, First Assistant and Solicitor and Julie Marie Blake,\\nDeputy Solicitor, were with him on brief. Laura E. Elsbury,\\nTrial Counsel, and Eldon V. Greenberg entered appearances.\\n\\n Anna T. Katselas, Attorney, United States Department of\\nJustice, argued the cause for the federal appellees. Jeffrey H.\\n\\f 2\\nWood, Acting Assistant Attorney General, Eric Grant, Deputy\\nAssistant Attorney General, and Robert J. Lundman, Attorney,\\nwere with her on brief. Andrew C. Mergen, Attorney, entered\\nan appearance.\\n\\n Nessa Horewitch Coppinger and Ryan J. Carra, Special\\nAssistant Attorneys General, Office of the Attorney General\\nfor the State of North Dakota, and Jennifer L. Verleger,\\nAssistant Attorney General, were on brief for the appellee State\\nof North Dakota. Scott M. DuBoff and Benjamin L. Lambiotte\\nentered appearances.\\n\\n Before: HENDERSON, ROGERS and SRINIVASAN, Circuit\\nJudges.\\n\\n Opinion for the Court filed by Circuit Judge HENDERSON.\\n\\n KAREN LECRAFT HENDERSON, Circuit Judge: The\\nNorthwest Area Water Supply Project (Project) will someday\\nsend clean water from the Missouri River Basin to parched\\ncommunities in northern North Dakota. That day has not yet\\ncome. For now, the Project’s construction remains bogged\\ndown in long-running environmental litigation. This case, the\\nmost recent leg of the litigation marathon, involves the State of\\nMissouri’s complaint that the Bureau of Reclamation\\n(Reclamation)—the federal agency responsible for carrying\\nout the Project—violated the National Environmental Policy\\nAct of 1969, Pub. L. No. 91-190, 83 Stat. 852 (1970) (codified\\nas amended at 42 U.S.C. §§ 4321 et seq.) (NEPA), by failing\\nto consider adequately how diverting billions of gallons of\\nMissouri River water will affect downstream States.\\n\\n Missouri brought this lawsuit on behalf of its citizens to\\nprevent the Project from causing them harm. In legal\\nlanguage, Missouri sued in its parens patriae capacity. The\\n\\f 3\\nproblem for Missouri is that, as a general matter, a “State does\\nnot have standing as parens patriae to bring an action against\\nthe Federal Government.” Alfred L. Snapp & Son, Inc. v.\\nPuerto Rico, ex rel., Barez, 458 U.S. 592, 610 n.16 (1982).\\nFor this reason and others elaborated below, we agree with the\\ndistrict court that Missouri lacks standing and therefore affirm.\\n\\n I. BACKGROUND\\n\\n Communities in northern North Dakota have long suffered\\nfrom water shortages. North Dakota and Reclamation—an\\nagency housed within the United States Department of Interior\\ncharged with, inter alia, managing and developing water\\nresources—began seeking a solution in the late 1980s. Their\\nefforts culminated in the Northwest Area Water Supply\\nProject. The Project will “withdraw water from the Missouri\\nRiver Basin and transport it via a 45-mile-long pipeline to the\\nHudson Bay Basin located in Northwest North Dakota.”\\nGov’t of Province of Manitoba v. Zinke, 849 F.3d 1111, 1114\\n(D.C. Cir. 2017). Over eighty thousand North Dakotans will\\ngain access to clean water.\\n\\n “The Project falls under the auspices of” NEPA, which\\n“imposes ‘a set of action-forcing procedures’ requiring federal\\nagencies to take a ‘hard look’ at any potential environmental\\nconsequences associated with their ‘proposals and actions’ and\\nto broadly disseminate relevant environmental information.”\\nId. at 1115 (quoting Dep’t of Transp. v. Pub. Citizen, 541 U.S.\\n752, 756–57 (2004); Robertson v. Methow Valley Citizens\\nCouncil, 490 U.S. 332, 350 (1989)). To that end, NEPA\\nrequires “all agencies of the Federal Government” to prepare\\nan Environmental Impact Statement (EIS) before taking a\\n“major Federal action[] significantly affecting the quality of the\\nhuman environment.” 42 U.S.C. § 4332(2)(C). An EIS is\\nnot required, however, if the agency completes an\\n\\f 4\\nEnvironmental Assessment and makes a Finding of No\\nSignificant Impact. New York v. Nuclear Regulatory\\nComm’n, 681 F.3d 471, 476 (D.C. Cir. 2012); see also 40\\nC.F.R. § 1501.4 (“In determining whether to prepare an\\nenvironmental impact statement the Federal agency shall . . .\\n[p]repare a finding of no significant impact (§ 1508.13), if the\\nagency determines on the basis of the environmental\\nassessment not to prepare a statement.”). NEPA itself does\\nnot provide a cause of action, W. Org. of Res. Councils v. Zinke,\\n892 F.3d 1234, 1241 (D.C. Cir. 2018); as a consequence, any\\nchallenge to agency action based on NEPA must be brought\\nunder the Administrative Procedure Act, 5 U.S.C. §§ 701 et\\nseq.\\n\\n We earlier held that Reclamation has failed to “comply\\nwith NEPA’s requirements” and has “left the Project mired in\\nlegal challenges” since 2002. Gov’t of Province of Manitoba,\\n849 F.3d at 1115. Our decision there sets forth in detail the\\nhistory of the litigation. Id. at 1114–17. We recount only the\\nessentials. There were two Project-related lawsuits against\\nReclamation before this one. Manitoba brought the first\\nchallenge, claiming Reclamation failed to “adequately grapple\\nwith potential ecological problems caused by transferring\\ntreatment-resistant biota into the Hudson Bay Basin.” Id. at\\n1115. The district court agreed, remanding to Reclamation its\\ninitial Finding of No Significant Impact. Gov’t of Province of\\nManitoba v. Norton, 398 F. Supp. 2d 41, 67 (D.D.C. 2005).\\nFour years later, Reclamation issued an EIS and Manitoba sued\\nagain. Gov’t of Province of Manitoba, 849 F.3d at 1116.\\nThis time, the State of Missouri also filed suit, alleging that\\nReclamation “did not properly account for cumulative effects\\nof water withdrawal from the Missouri River.” Id. The\\ndistrict court sided with both challengers, criticized\\nReclamation’s inadequate work and remanded for more NEPA\\nanalysis. Id.\\n\\f 5\\n In 2015, Reclamation issued a Supplemental\\nEnvironmental Impact Statement (SEIS) for the Project.\\nManitoba 1 and Missouri again brought challenges, leading to\\nthis appeal. Reclamation moved for summary judgment,\\narguing that Missouri failed to establish standing.\\nSpecifically, Reclamation claimed that a State cannot sue the\\nfederal government as parens patriae, Missouri’s sole basis for\\nstanding. Missouri did not dispute that it relied solely on a\\nparens patriae theory of standing but maintained that a State\\ncan, at least under some circumstances, sue the federal\\ngovernment in its parens patriae capacity. The district court\\nfirst noted that “Missouri is very clear that it sues in its role as\\nparens patriae on behalf of its residents” and “advances no\\nother basis for its standing.” Gov’t of Province of Manitoba v.\\nZinke, 273 F. Supp. 3d 145, 167–68 (D.D.C. 2017). It\\nexplained that under longstanding precedent, a State lacks\\nparens patriae standing to sue the federal government. Id. at\\n162–68. The district court dismissed the complaint—a\\ndecision from which Missouri now appeals. Our review is de\\nnovo. Scenic Am., Inc. v. U.S. Dep’t of Transp., 836 F.3d 42,\\n49 (D.C. Cir. 2016) (“We review the District Court’s decision\\n(or lack thereof) as to standing de novo.”).\\n\\n II. ANALYSIS\\n\\n Article III of the United States Constitution authorizes\\nfederal courts to decide only “Cases” and “Controversies.”\\nU.S. Const. art. III, § 2, cl. 1. “To present a justiciable case or\\ncontroversy, litigants must demonstrate standing, among other\\nrequirements.” Pub. Citizen v. Nat’l Highway Traffic Safety\\nAdmin., 489 F.3d 1279, 1289 (D.C. Cir. 2007). “The\\n‘irreducible constitutional minimum of standing’ contains\\nthree requirements.” Steel Co. v. Citizens for a Better Env’t,\\n\\n 1\\n Manitoba eventually settled with Reclamation.\\n\\f 6\\n523 U.S. 83, 102 (1998) (quoting Lujan v. Defenders of\\nWildlife, 504 U.S. 555, 560 (1992)). “The plaintiff must have\\n(1) suffered an injury in fact, (2) that is fairly traceable to the\\nchallenged conduct of the defendant, and (3) that is likely to be\\nredressed by a favorable judicial decision.” Spokeo, Inc. v.\\nRobins, 136 S. Ct. 1540, 1547 (2016). “[A]s the party\\ninvoking federal jurisdiction,” the plaintiff “bears the burden\\nof establishing these elements.” Id.\\n\\n A State’s standing depends on the capacity in which it\\ninitiates a lawsuit. Erwin Chemerinsky, Federal Jurisdiction\\n121 (7th ed. 2016) (“[A] distinction must be drawn between a\\ngovernment entity suing to remedy injuries that it has suffered\\nand suing in a representative capacity on behalf of its\\ncitizens.”). Two types of lawsuits are relevant here. The\\nfirst, a direct injury lawsuit, allows a State to sue to redress its\\nown injury. Cf. Wyoming v. Oklahoma, 502 U.S. 437, 448–49\\n(1992) (distinguishing between “claims of parens patriae\\nstanding” and “allegations of direct injury to the State itself”).\\nFor this first type of lawsuit, the State need meet only the\\nordinary demands of Article III—that is, establish injury-in-\\nfact, causation and redressability, West v. Lynch, 845 F.3d\\n1228, 1230 (D.C. Cir. 2017). The second type, a parens\\npatriae lawsuit, allows a State to sue in a representative\\ncapacity to vindicate its citizens’ interests. Pennsylvania v.\\nKleppe, 533 F.2d 668, 671 (D.C. Cir. 1976) (“[I]n bringing the\\naction also on behalf of all injured citizens of the state, and\\nupon the relation of four named individuals, Pennsylvania\\ninvokes a parens patriae theory of standing.”). For these\\nlawsuits, the State must do more than meet Article III’s\\nirreducible minimum; it must assert a quasi-sovereign interest\\n“apart from the interests of particular private parties.” Alfred\\nL. Snapp & Son, Inc., 458 U.S. at 607. The Supreme Court\\nhas held that, at a minimum, a State has a quasi-sovereign\\ninterest “in the health and well-being—both physical and\\n\\f 7\\neconomic—of its residents” and “in not being discriminatorily\\ndenied its rightful status within the federal system.” Id. at 607.\\n“One helpful indication in determining whether an alleged\\ninjury to the health and welfare of its citizens suffices to give\\nthe State standing to sue as parens patriae is whether the injury\\nis one that the State, if it could, would likely attempt to address\\nthrough its sovereign lawmaking powers.” Id.\\n\\n Missouri claims that this litigation asserts both a direct\\ninjury and a parens patriae injury. Both sides agree that the\\nProject will eventually divert billions of gallons of Missouri\\nRiver water each year to North Dakota communities.\\nMissouri asserts a direct injury: the large-scale diversion of\\nwater will allegedly harm its own interests by (among other\\nthings) damaging its riverfront properties (especially farmland\\nadjacent to the Missouri River) and its commercial navigation\\nbusinesses and by modifying its borders with neighboring\\nstates. Missouri also asserts that the Project will harm its\\ncitizens, a harm it seeks to allay in its quasi-sovereign—that is,\\nparens patriae—capacity. We address seriatim the two\\ntheories of standing.\\n\\n A. DIRECT INJURY\\n\\n Reclamation contends that Missouri forfeited its direct\\ninjury theory of standing. We agree. Absent exceptional\\ncircumstances, a party forfeits an argument by failing to press\\nit in district court. D.C. v. Straus, 590 F.3d 898, 903 (D.C.\\nCir. 2010); Adams v. Rice, 531 F.3d 936, 944–45 (D.C. Cir.\\n2008). And the ordinary rules of forfeiture apply to standing.\\nHuron v. Cobert, 809 F.3d 1274, 1280 (D.C. Cir. 2016)\\n(forfeiture “applies to standing, as much as to merits,\\narguments, because it is not the province of an appellate court\\nto ‘hypothesize or speculate about the existence of an injury\\n[Plaintiff] did not assert’ to the district court” (quoting Kawa\\n\\f 8\\nOrthodontics, LLP v. Secretary, U.S. Dep’t of the Treasury,\\n773 F.3d 243, 246 (11th Cir. 2014) (alteration in original))).\\nIn district court, Reclamation argued that Missouri as parens\\npatriae lacks standing to sue the federal government. Rather\\nthan preserve its direct injury theory, Missouri chose to rely\\nsolely on its parens patriae standing. This is textbook\\nforfeiture.\\n\\n Missouri responds that its complaint identifies a direct\\ninjury theory of standing and thus preserves that theory for our\\nconsideration. The complaint states that Missouri “brings this\\naction on its own behalf and as parens patriae for its residents.”\\nBut a threadbare allegation included in its complaint does not\\nhelp Missouri. A party forfeits an argument by mentioning it\\nonly “in the most skeletal way, leaving the court to do counsel’s\\nwork, create the ossature for the argument, and put flesh on its\\nbones.” Schneider v. Kissinger, 412 F.3d 190, 200 n.1 (D.C.\\nCir. 2005) (quoting United States v. Zannino, 895 F.2d 1, 17\\n(1st Cir. 1990)). On summary judgment, plaintiff Missouri\\nhad to identify record evidence establishing its standing to sue\\nReclamation. See Swanson Grp. Mfg. LLC v. Jewell, 790 F.3d\\n235, 240 (D.C. Cir. 2015); Abigail All. for Better Access to\\nDevelopmental Drugs v. Eschenbach, 469 F.3d 129, 132 (D.C.\\nCir. 2006) (“[T]he party invoking the court’s jurisdiction must\\nestablish the predicates for standing ‘with the manner and\\ndegree of evidence required at’ that stage of trial.” (quoting\\nLujan, 504 U.S. at 561)). The simple allegation that Missouri\\n“brings this action on its own behalf” does nothing to explain\\nMissouri’s standing under a direct injury theory or to identify\\nthe evidence required at summary judgment. 2\\n\\n\\n 2\\n At oral argument, Missouri contended that a party need not\\nbrief a “legally self-evident” theory of standing at summary\\njudgment. “Generally, arguments raised for the first time at oral\\nargument are forfeited.” U.S. ex rel. Davis v. D.C., 793 F.3d 120,\\n\\f 9\\n The only remaining question is whether an extraordinary\\ncircumstance excuses Missouri’s forfeiture. See Flynn v.\\nComm’r, 269 F.3d 1064, 1068–69 (D.C. Cir. 2001). As far as\\nwe can tell, nothing in the record manifests that Missouri’s\\nforfeiture of its direct injury theory was anything other than a\\ntactical decision. And Missouri does not argue otherwise.\\nAccordingly, we conclude that Missouri has forfeited its direct\\ninjury theory.\\n\\n B. PARENS PATRIAE CAPACITY\\n\\n Missouri faces an uphill climb in establishing standing in\\nits parens patriae capacity. The traditional rule, the so-called\\n“Mellon bar,” declares that a State lacks standing as parens\\npatriae to bring an action against the federal government.\\nMassachusetts v. Mellon, 262 U.S. 447, 485–86 (1923)\\n(“While the state, under some circumstances, may sue” as\\nparens patriae “for the protection of its citizens, it is no part of\\nits duty or power to enforce their rights in respect of their\\nrelations with the federal government.”); see also Alfred L.\\nSnapp & Son, Inc, 458 U.S. at 610 n.16; South Carolina v.\\nKatzenbach, 383 U.S. 301, 324 (1966); Florida v. Mellon, 273\\nU.S. 12, 18 (1927); Maryland People’s Counsel v. FERC, 760\\nF.2d 318, 320 (D.C. Cir. 1985). Missouri first counters that\\nthe Mellon bar does not apply to this litigation because it is\\ndisplaced by the APA. It also contends that the Supreme\\nCourt’s holding in Massachusetts v. EPA, 549 U.S. 497 (2007),\\nprecludes application of the Mellon bar here.\\n\\n 1. THE MELLON BAR APPLIES TO APA CASES\\n\\n Missouri contends that the Mellon bar does not apply to\\nlitigation the State brings against the federal government under\\n\\n127 (D.C. Cir. 2015). And Missouri offers no basis for excusing its\\nforfeiture.\\n\\f 10\\nthe APA. We have indeed recognized that the Mellon bar\\nspeaks to prudential, not Article III, standing which the courts\\ndesigned to prevent a State from encroaching on the federal\\ngovernment’s power. Maryland People’s Counsel, 760 F.2d\\nat 321–22; Kleppe, 533 F.2d at 676–77 (discussing Mellon bar\\npurpose); cf. Lexmark Int’l, Inc. v. Static Control Components,\\nInc., 572 U.S. 118, 128 & n.4 (2014) (explaining “prudential\\nstanding” label is misleading because doctrine concerns\\nwhether plaintiff has cause of action under relevant statute and\\n“‘the absence of a valid (as opposed to arguable) cause of\\naction does not implicate subject-matter jurisdiction, i.e., the\\ncourt’s statutory or constitutional power to adjudicate the\\ncase.”’ (quoting Verizon Md. Inc. v. Public Serv. Comm’n of\\nMd., 535 U.S. 635, 642–43 (2002))). Because the Mellon bar\\nis prudential, we have held that the Congress may by statute\\nauthorize a State to sue the federal government in its parens\\npatriae capacity. Maryland People’s Counsel, 760 F.2d at\\n322. Missouri believes the APA is such a statute and allows\\nits lawsuit against Reclamation to proceed.\\n\\n Our leading precedent in this area is Maryland People’s\\nCounsel v. FERC, 760 F.2d 318 (D.C. Cir. 1985). 3 There, we\\nconcluded that the judicial review provision included in the\\nNatural Gas Act of 1938 (NGA), Pub. L. No. 75-688, 52 Stat.\\n821 (codified at 15 U.S.C. §§ 717 et seq.), is not subject to the\\nMellon bar. Id. at 320–21 (citing 15 U.S.C. § 717r(b)). Our\\nanalysis is instructive. The NGA authorizes States to\\nparticipate in proceedings before the Federal Energy\\n\\n 3\\n Missouri asserts that earlier precedent, Pennsylvania v.\\nKleppe, 533 F.2d 668, 677 n.55 (D.C. Cir. 1976), held that the APA\\nabrogated the Mellon bar and allowed a State to sue the federal\\ngovernment in its parens patriae capacity. We did not conclude that\\nPennsylvania had standing in Kleppe; Missouri’s claim that Kleppe\\nadopted a bright-line rule that a State has parens patriae standing\\nunder the APA is, therefore, in error. Id. at 680.\\n\\f 11\\nRegulatory Commission (FERC). Id. It also gives States a\\ncause of action to sue FERC based on those proceedings. Id.\\nat 321. But States are generally not purchasers of natural gas.\\nId. This fact led us to infer that the NGA’s judicial review\\nprovision is “evidently designed to recognize precisely the\\ninterest of the states in protecting their citizens in this\\ntraditional governmental field of utility regulation—that is, the\\nstates’ parens patriae interest.” Id. Because the Congress\\nintended a State to sue FERC based on its “parens patriae\\ninterest[s],” we held that an NGA suit brought by a State is not\\nsubject to the Mellon bar. Id. at 321–22 (describing\\n“congressional elimination of the rule of Massachusetts v.\\nMellon” as “effective”).\\n\\n The APA generally provides a cause of action to any\\n“person . . . adversely affected or aggrieved by agency action.”\\n5 U.S.C. § 702. There is little doubt that a State qualifies as a\\n“person” under the APA. See Maryland Dep’t of Human Res.\\nv. Dep’t of Health & Human Servs., 763 F.2d 1441, 1445 n.1\\n(D.C. Cir. 1985) (“If a foreign government and its agencies are\\npersons within the meaning of the APA, it seems clear that a\\nstate and its agencies also are.”). To sue in its parens patriae\\ncapacity, moreover, a State must suffer an injury to its quasi-\\nsovereign interest, Alfred L. Snapp & Son, Inc., 458 U.S. at\\n607, and thus must be “adversely affected or aggrieved,” 5\\nU.S.C. § 702. Unlike the NGA, however, the APA evinces no\\ncongressional intent to authorize a State as parens patriae to\\nsue the federal government. The APA’s judicial review\\nprovision authorizes suit by a “person” challenging agency\\naction and the APA definition of “person,” by implication only,\\nincludes a State, 5 U.S.C. § 701(b)(2) (“‘[P]erson’ . . . ha[s] the\\nmeaning[] given . . . by section 551 of this title.”); 5 U.S.C.\\n§ 551(2) (“‘[P]erson’ includes an individual, partnership,\\ncorporation, association, or public or private organization other\\nthan an agency.”). The APA’s judicial review provision\\n\\f 12\\nallows a person to challenge agency action taken under many\\ndifferent statutes. See Block v. Cmty. Nutrition Inst., 467 U.S.\\n340, 345 (1984) (APA confers “a general cause of action”). It\\nis not linked to any particular statutory scheme and—unlike the\\nNGA—does not create an inference that the Congress intended\\na wholesale imprimatur allowing a State as parens patriae to\\nsue the federal government. Accordingly, the Mellon bar\\napplies to litigation that a State, using the APA, seeks to pursue\\nagainst the federal government. 4\\n\\n 2. THE MELLON BAR HAS NO EXCEPTION\\n\\n Missouri also insists that the holding in Massachusetts v.\\nEPA, 549 U.S. 497 (2007), creates an exception to the Mellon\\nbar that allows its lawsuit against Reclamation to proceed. In\\nthat case, Massachusetts petitioned the EPA to promulgate a\\nrule governing vehicular greenhouse gas emissions. Id. at\\n510. The EPA declined to regulate and Massachusetts sought\\njudicial review. Id. at 510–15. The United States Supreme\\nCourt concluded that Massachusetts had standing in its own\\nright to sue the EPA. Id. at 526. Its entire parens patriae\\ndiscussion appears in footnote seventeen, two sentences of\\nwhich are critical to Missouri’s argument. Id. at 520 n.17.\\nThe first declares that “there is a critical difference between\\nallowing a State ‘to protect her citizens from the operation of\\nfederal statutes’ (which is what Mellon prohibits) and allowing\\na State to assert its rights under federal law (which it has\\nstanding to do).” Id. (quoting Georgia v. Pennsylvania R. Co.,\\n324 U.S. 439, 447 (1945)). The second then states:\\n“Massachusetts does not here dispute that the Clean Air Act\\napplies to its citizens; it rather seeks to assert its rights under\\n\\n 4\\n We note that Missouri has not made an argument that\\nNEPA—as opposed to the APA—authorizes this suit\\nnotwithstanding the Mellon bar and thus we have no occasion to\\nconsider that argument.\\n\\f 13\\nthe Act.” Id. Missouri reads the footnote as establishing an\\nexception to the Mellon bar for litigation in which a State “does\\nnot challenge the validity of a federal statute but instead sues\\nthe federal government to assert the State’s own rights or those\\nof its citizens under federal statutes.”\\n\\n But the Supreme Court had no need to carve out an\\nexception to the Mellon bar in Massachusetts v. EPA because\\nMassachusetts did not sue in its parens patriae capacity.\\nAccord Center for Biological Diversity v. U.S. Dep’t of\\nInterior, 563 F.3d 466, 476–78 (D.C. Cir. 2009) (discussing\\nparens patriae analysis in Massachusetts v. EPA). It instead\\n“alleged a particularized injury in its capacity as a landowner.”\\nMassachusetts, 549 U.S. at 522. Because Massachusetts sued\\nto remedy its own injury rather than that of its citizens,\\nMassachusetts v. EPA is not a parens patriae case. There is\\nsome confusion on this score most possibly caused by the\\nopinion’s discussion of quasi-sovereign interests. Id. at 519–\\n20. But that discussion related to the Supreme Court affording\\nMassachusetts “special solicitude in [the] standing analysis.”\\nId at 520. The Court explained that Massachusetts is entitled\\nto “special solicitude” because (1) a State has a quasi-sovereign\\ninterest in “preserv[ing] its sovereign territory” and (2) the\\nCongress afforded “a concomitant procedural right to\\nchallenge the rejection of its rulemaking petition as arbitrary\\nand capricious.” Id. at 519–20; see also Texas v. United\\nStates, 809 F.3d 134, 151 (5th Cir. 2015) (applying special\\nsolicitude doctrine). Notwithstanding the quasi-sovereign-\\ninterests discussion, however, Massachusetts asserted its own\\nstatutory right and alleged its own harm to establish an injury-\\nin-fact, as footnote seventeen expressly recognizes,\\nMassachusetts, 549 U.S. at 520 n.17 (“Massachusetts does not\\nhere dispute that the Clean Air Act applies to its citizens; it\\nrather seeks to assert its rights under the Act.” (second\\nemphasis added)); see also id. at 522 (Massachusetts “has\\n\\f 14\\nalleged a particularized injury in its capacity as a coastal\\nlandowner”).\\n\\n Nor does the text of footnote seventeen support Missouri’s\\nproposed exception. The first three sentences of the footnote\\ndispute the dissent’s characterization of Mellon as supporting\\nthe proposition that a State cannot assert a quasi-sovereign\\ninterest when suing the federal government. Compare id. at\\n539 (Roberts, C.J., dissenting) (“[T]he Court overlooks the fact\\nthat our cases cast significant doubt on a State’s standing to\\nassert a quasi-sovereign interest—as opposed to a direct\\ninjury—against the Federal Government.”), with id. at 520 n.17\\n(“Mellon itself disavowed any such broad reading when it\\nnoted that the [Mellon] Court had been ‘called upon to\\nadjudicate, not rights of person or property, not rights of\\ndominion over physical domain, [and] not quasi-sovereign\\nrights actually invaded or threatened.’” (quoting 262 U.S. at\\n484–85)). For good measure, the two concluding sentences of\\nthe footnote distinguish the Massachusetts facts from those of\\nMellon. “In any event,” they explain, “there is a critical\\ndifference between allowing a State ‘to protect her citizens\\nfrom the operation of federal statutes’ (which is what Mellon\\nprohibits) and allowing a State to assert its rights under federal\\nlaw (which it has standing to do).” Id. (quoting Pennsylvania\\nR. Co., 324 U.S. at 447). The distinction is not, as Missouri\\nsuggests, between two types of parens patriae lawsuits, one\\npermissible and one not. It is between a parens patriae\\nlawsuit (what Mellon prohibits) and a State suing based on “its\\nrights under federal law” (not a parens patriae lawsuit at all).\\nSee Wyoming, 502 U.S. at 448–49 (1992) (“[C]laims of parens\\npatriae standing” differ from “allegations of direct injury to the\\nState itself.”); cf. Kleppe, 533 F.2d at 675 (describing parens\\npatriae lawsuit as “representative action by the state”).\\n\\f 15\\n Finally, Missouri’s reading of footnote seventeen, if\\nadopted, would establish an exception that makes little sense in\\nlight of the vertical federalism interest underlying the Mellon\\nbar. As we have explained, an “individual’s dual citizenship\\nin both state and nation, with separate rights and obligations\\narising from each, suggests that both units of government act\\nas parens patriae within their separate spheres of activity.” Id.\\nat 676–77. “The general supremacy of federal law” means\\n“that the federal parens patriae power should not, as a rule, be\\nsubject to the intervention of states seeking to represent the\\nsame interest of the same citizens.” Id. at 677. For that\\nreason, a “state can not have a quasi-sovereign interest\\nbecause” matters of federal law “fall[] within the sovereignty\\nof the Federal Government.” Id. It is the State’s\\nrepresentation that usurps the role of the federal government,\\nnot the legal theory underlying its complaint. Id. at 676–77.\\nThere is no reason to treat parens patriae actions alleging\\nconstitutional claims against the federal government\\ndifferently from those alleging federal statutory claims. We\\ndoubt the Supreme Court meant in footnote seventeen to create\\nan exception to the Mellon bar based on such a distinction.\\n\\n In the end, we are unpersuaded by Missouri’s argument\\nthat Massachusetts v. EPA alters our longstanding precedent\\nthat a State in general lacks parens patriae standing to sue the\\nfederal government. Accord Center for Biological Diversity,\\n563 F.3d at 476–78 (rejecting, in dicta, that Massachusetts v.\\nEPA creates exception to Mellon bar); Maryland People’s\\nCounsel, 760 F.2d at 320 (“[a] State does not have standing as\\nparens patriae to bring an action against the Federal\\nGovernment” (quoting Alfred L. Snapp & Son, Inc., 458 U.S.\\nat 610 n.16)); Michigan v. EPA, 581 F.3d 524, 529 (7th Cir.\\n2009) (per Wood, J.) (Massachusetts does not create exception\\nto Mellon bar); Commonwealth v. U.S. Dep’t of Educ., 340 F.\\nSupp. 3d 7, 14–16 (D.D.C. 2018) (same).\\n\\f 16\\n For the foregoing reasons, we affirm the judgment of the\\ndistrict court.\\n\\n So ordered.\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/4393797/\", \"author_raw\": \"Opinion for the Court filed by Circuit Judge HENDERSON\"}]}"},"judge1":{"kind":"string","value":"HENDERSON"},"judge2":{"kind":"string","value":"ROGERS"},"judge3":{"kind":"string","value":"SRINIVASAN"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/4616544/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":1,"string":"1"},"020lead_count":{"kind":"number","value":0,"string":"0"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: GOVERNMENT OF the Province of MANITOBA, Appellee State of Missouri, Ex Rel. Eric Schmitt, Missouri Attorney General's Office, Appellant v. David BERNHARDT, Secretary, U.S. Department of the Interior, Et Al., Appellees\nCourt: U.S. Court of Appeals for the District of Columbia Circuit\nDate decided: 2019-05-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\nUnited States Court of Appeals\n FOR THE DISTRICT OF COLUMBIA CIRCUIT\n\n\n\nArgued November 8, 2018 Decided May 3, 2019\n\n No. 17-5242\n\n GOVERNMENT OF THE PROVINCE OF MANITOBA,\n APPELLEE\n\n STATE OF MISSOURI, EX REL. ERIC SCHMITT,\n MISSOURI ATTORNEY GENERAL’S OFFICE,\n APPELLANT\n\n v.\n\n DAVID BERNHARDT, SECRETARY,\n U.S. DEPARTMENT OF THE INTERIOR, ET AL.,\n APPELLEES\n\n\n Appeal from the United States District Court\n for the District of Columbia\n (No. 1:02-cv-02057)\n\n\n Joshua M. Divine, Deputy Solicitor, Office of the Attorney\nGeneral for the State of Missouri, argued the cause for the\nappellant. Joshua D. Hawley, Attorney General, D. John\nSauer, First Assistant and Solicitor and Julie Marie Blake,\nDeputy Solicitor, were with him on brief. Laura E. Elsbury,\nTrial Counsel, and Eldon V. Greenberg entered appearances.\n\n Anna T. Katselas, Attorney, United States Department of\nJustice, argued the cause for the federal appellees. Jeffrey H.\n\f 2\nWood, Acting Assistant Attorney General, Eric Grant, Deputy\nAssistant Attorney General, and Robert J. Lundman, Attorney,\nwere with her on brief. Andrew C. Mergen, Attorney, entered\nan appearance.\n\n Nessa Horewitch Coppinger and Ryan J. Carra, Special\nAssistant Attorneys General, Office of the Attorney General\nfor the State of North Dakota, and Jennifer L. Verleger,\nAssistant Attorney General, were on brief for the appellee State\nof North Dakota. Scott M. DuBoff and Benjamin L. Lambiotte\nentered appearances.\n\n Before: HENDERSON, ROGERS and SRINIVASAN, Circuit\nJudges.\n\n Opinion for the Court filed by Circuit Judge HENDERSON.\n\n KAREN LECRAFT HENDERSON, Circuit Judge: The\nNorthwest Area Water Supply Project (Project) will someday\nsend clean water from the Missouri River Basin to parched\ncommunities in northern North Dakota. That day has not yet\ncome. For now, the Project’s construction remains bogged\ndown in long-running environmental litigation. This case, the\nmost recent leg of the litigation marathon, involves the State of\nMissouri’s complaint that the Bureau of Reclamation\n(Reclamation)—the federal agency responsible for carrying\nout the Project—violated the National Environmental Policy\nAct of 1969, Pub. L. No. 91-190, 83 Stat. 852 (1970) (codified\nas amended at 42 U.S.C. §§ 4321 et seq.) (NEPA), by failing\nto consider adequately how diverting billions of gallons of\nMissouri River water will affect downstream States.\n\n Missouri brought this lawsuit on behalf of its citizens to\nprevent the Project from causing them harm. In legal\nlanguage, Missouri sued in its parens patriae capacity. The\n\f 3\nproblem for Missouri is that, as a general matter, a “State does\nnot have standing as parens patriae to bring an action against\nthe Federal Government.” Alfred L. Snapp & Son, Inc. v.\nPuerto Rico, ex rel., Barez, 458 U.S. 592, 610 n.16 (1982).\nFor this reason and others elaborated below, we agree with the\ndistrict court that Missouri lacks standing and therefore affirm.\n\n I. BACKGROUND\n\n Communities in northern North Dakota have long suffered\nfrom water shortages. North Dakota and Reclamation—an\nagency housed within the United States Department of Interior\ncharged with, inter alia, managing and developing water\nresources—began seeking a solution in the late 1980s. Their\nefforts culminated in the Northwest Area Water Supply\nProject. The Project will “withdraw water from the Missouri\nRiver Basin and transport it via a 45-mile-long pipeline to the\nHudson Bay Basin located in Northwest North Dakota.”\nGov’t of Province of Manitoba v. Zinke, 849 F.3d 1111, 1114\n(D.C. Cir. 2017). Over eighty thousand North Dakotans will\ngain access to clean water.\n\n “The Project falls under the auspices of” NEPA, which\n“imposes ‘a set of action-forcing procedures’ requiring federal\nagencies to take a ‘hard look’ at any potential environmental\nconsequences associated with their ‘proposals and actions’ and\nto broadly disseminate relevant environmental information.”\nId. at 1115 (quoting Dep’t of Transp. v. Pub. Citizen, 541 U.S.\n752, 756–57 (2004); Robertson v. Methow Valley Citizens\nCouncil, 490 U.S. 332, 350 (1989)). To that end, NEPA\nrequires “all agencies of the Federal Government” to prepare\nan Environmental Impact Statement (EIS) before taking a\n“major Federal action[] significantly affecting the quality of the\nhuman environment.” 42 U.S.C. § 4332(2)(C). An EIS is\nnot required, however, if the agency completes an\n\f 4\nEnvironmental Assessment and makes a Finding of No\nSignificant Impact. New York v. Nuclear Regulatory\nComm’n, 681 F.3d 471, 476 (D.C. Cir. 2012); see also 40\nC.F.R. § 1501.4 (“In determining whether to prepare an\nenvironmental impact statement the Federal agency shall . . .\n[p]repare a finding of no significant impact (§ 1508.13), if the\nagency determines on the basis of the environmental\nassessment not to prepare a statement.”). NEPA itself does\nnot provide a cause of action, W. Org. of Res. Councils v. Zinke,\n892 F.3d 1234, 1241 (D.C. Cir. 2018); as a consequence, any\nchallenge to agency action based on NEPA must be brought\nunder the Administrative Procedure Act, 5 U.S.C. §§ 701 et\nseq.\n\n We earlier held that Reclamation has failed to “comply\nwith NEPA’s requirements” and has “left the Project mired in\nlegal challenges” since 2002. Gov’t of Province of Manitoba,\n849 F.3d at 1115. Our decision there sets forth in detail the\nhistory of the litigation. Id. at 1114–17. We recount only the\nessentials. There were two Project-related lawsuits against\nReclamation before this one. Manitoba brought the first\nchallenge, claiming Reclamation failed to “adequately grapple\nwith potential ecological problems caused by transferring\ntreatment-resistant biota into the Hudson Bay Basin.” Id. at\n1115. The district court agreed, remanding to Reclamation its\ninitial Finding of No Significant Impact. Gov’t of Province of\nManitoba v. Norton, 398 F. Supp. 2d 41, 67 (D.D.C. 2005).\nFour years later, Reclamation issued an EIS and Manitoba sued\nagain. Gov’t of Province of Manitoba, 849 F.3d at 1116.\nThis time, the State of Missouri also filed suit, alleging that\nReclamation “did not properly account for cumulative effects\nof water withdrawal from the Missouri River.” Id. The\ndistrict court sided with both challengers, criticized\nReclamation’s inadequate work and remanded for more NEPA\nanalysis. Id.\n\f 5\n In 2015, Reclamation issued a Supplemental\nEnvironmental Impact Statement (SEIS) for the Project.\nManitoba 1 and Missouri again brought challenges, leading to\nthis appeal. Reclamation moved for summary judgment,\narguing that Missouri failed to establish standing.\nSpecifically, Reclamation claimed that a State cannot sue the\nfederal government as parens patriae, Missouri’s sole basis for\nstanding. Missouri did not dispute that it relied solely on a\nparens patriae theory of standing but maintained that a State\ncan, at least under some circumstances, sue the federal\ngovernment in its parens patriae capacity. The district court\nfirst noted that “Missouri is very clear that it sues in its role as\nparens patriae on behalf of its residents” and “advances no\nother basis for its standing.” Gov’t of Province of Manitoba v.\nZinke, 273 F. Supp. 3d 145, 167–68 (D.D.C. 2017). It\nexplained that under longstanding precedent, a State lacks\nparens patriae standing to sue the federal government. Id. at\n162–68. The district court dismissed the complaint—a\ndecision from which Missouri now appeals. Our review is de\nnovo. Scenic Am., Inc. v. U.S. Dep’t of Transp., 836 F.3d 42,\n49 (D.C. Cir. 2016) (“We review the District Court’s decision\n(or lack thereof) as to standing de novo.”).\n\n II. ANALYSIS\n\n Article III of the United States Constitution authorizes\nfederal courts to decide only “Cases” and “Controversies.”\nU.S. Const. art. III, § 2, cl. 1. “To present a justiciable case or\ncontroversy, litigants must demonstrate standing, among other\nrequirements.” Pub. Citizen v. Nat’l Highway Traffic Safety\nAdmin., 489 F.3d 1279, 1289 (D.C. Cir. 2007). “The\n‘irreducible constitutional minimum of standing’ contains\nthree requirements.” Steel Co. v. Citizens for a Better Env’t,\n\n 1\n Manitoba eventually settled with Reclamation.\n\f 6\n523 U.S. 83, 102 (1998) (quoting Lujan v. Defenders of\nWildlife, 504 U.S. 555, 560 (1992)). “The plaintiff must have\n(1) suffered an injury in fact, (2) that is fairly traceable to the\nchallenged conduct of the defendant, and (3) that is likely to be\nredressed by a favorable judicial decision.” Spokeo, Inc. v.\nRobins, 136 S. Ct. 1540, 1547 (2016). “[A]s the party\ninvoking federal jurisdiction,” the plaintiff “bears the burden\nof establishing these elements.” Id.\n\n A State’s standing depends on the capacity in which it\ninitiates a lawsuit. Erwin Chemerinsky, Federal Jurisdiction\n121 (7th ed. 2016) (“[A] distinction must be drawn between a\ngovernment entity suing to remedy injuries that it has suffered\nand suing in a representative capacity on behalf of its\ncitizens.”). Two types of lawsuits are relevant here. The\nfirst, a direct injury lawsuit, allows a State to sue to redress its\nown injury. Cf. Wyoming v. Oklahoma, 502 U.S. 437, 448–49\n(1992) (distinguishing between “claims of parens patriae\nstanding” and “allegations of direct injury to the State itself”).\nFor this first type of lawsuit, the State need meet only the\nordinary demands of Article III—that is, establish injury-in-\nfact, causation and redressability, West v. Lynch, 845 F.3d\n1228, 1230 (D.C. Cir. 2017). The second type, a parens\npatriae lawsuit, allows a State to sue in a representative\ncapacity to vindicate its citizens’ interests. Pennsylvania v.\nKleppe, 533 F.2d 668, 671 (D.C. Cir. 1976) (“[I]n bringing the\naction also on behalf of all injured citizens of the state, and\nupon the relation of four named individuals, Pennsylvania\ninvokes a parens patriae theory of standing.”). For these\nlawsuits, the State must do more than meet Article III’s\nirreducible minimum; it must assert a quasi-sovereign interest\n“apart from the interests of particular private parties.” Alfred\nL. Snapp & Son, Inc., 458 U.S. at 607. The Supreme Court\nhas held that, at a minimum, a State has a quasi-sovereign\ninterest “in the health and well-being—both physical and\n\f 7\neconomic—of its residents” and “in not being discriminatorily\ndenied its rightful status within the federal system.” Id. at 607.\n“One helpful indication in determining whether an alleged\ninjury to the health and welfare of its citizens suffices to give\nthe State standing to sue as parens patriae is whether the injury\nis one that the State, if it could, would likely attempt to address\nthrough its sovereign lawmaking powers.” Id.\n\n Missouri claims that this litigation asserts both a direct\ninjury and a parens patriae injury. Both sides agree that the\nProject will eventually divert billions of gallons of Missouri\nRiver water each year to North Dakota communities.\nMissouri asserts a direct injury: the large-scale diversion of\nwater will allegedly harm its own interests by (among other\nthings) damaging its riverfront properties (especially farmland\nadjacent to the Missouri River) and its commercial navigation\nbusinesses and by modifying its borders with neighboring\nstates. Missouri also asserts that the Project will harm its\ncitizens, a harm it seeks to allay in its quasi-sovereign—that is,\nparens patriae—capacity. We address seriatim the two\ntheories of standing.\n\n A. DIRECT INJURY\n\n Reclamation contends that Missouri forfeited its direct\ninjury theory of standing. We agree. Absent exceptional\ncircumstances, a party forfeits an argument by failing to press\nit in district court. D.C. v. Straus, 590 F.3d 898, 903 (D.C.\nCir. 2010); Adams v. Rice, 531 F.3d 936, 944–45 (D.C. Cir.\n2008). And the ordinary rules of forfeiture apply to standing.\nHuron v. Cobert, 809 F.3d 1274, 1280 (D.C. Cir. 2016)\n(forfeiture “applies to standing, as much as to merits,\narguments, because it is not the province of an appellate court\nto ‘hypothesize or speculate about the existence of an injury\n[Plaintiff] did not assert’ to the district court” (quoting Kawa\n\f 8\nOrthodontics, LLP v. Secretary, U.S. Dep’t of the Treasury,\n773 F.3d 243, 246 (11th Cir. 2014) (alteration in original))).\nIn district court, Reclamation argued that Missouri as parens\npatriae lacks standing to sue the federal government. Rather\nthan preserve its direct injury theory, Missouri chose to rely\nsolely on its parens patriae standing. This is textbook\nforfeiture.\n\n Missouri responds that its complaint identifies a direct\ninjury theory of standing and thus preserves that theory for our\nconsideration. The complaint states that Missouri “brings this\naction on its own behalf and as parens patriae for its residents.”\nBut a threadbare allegation included in its complaint does not\nhelp Missouri. A party forfeits an argument by mentioning it\nonly “in the most skeletal way, leaving the court to do counsel’s\nwork, create the ossature for the argument, and put flesh on its\nbones.” Schneider v. Kissinger, 412 F.3d 190, 200 n.1 (D.C.\nCir. 2005) (quoting United States v. Zannino, 895 F.2d 1, 17\n(1st Cir. 1990)). On summary judgment, plaintiff Missouri\nhad to identify record evidence establishing its standing to sue\nReclamation. See Swanson Grp. Mfg. LLC v. Jewell, 790 F.3d\n235, 240 (D.C. Cir. 2015); Abigail All. for Better Access to\nDevelopmental Drugs v. Eschenbach, 469 F.3d 129, 132 (D.C.\nCir. 2006) (“[T]he party invoking the court’s jurisdiction must\nestablish the predicates for standing ‘with the manner and\ndegree of evidence required at’ that stage of trial.” (quoting\nLujan, 504 U.S. at 561)). The simple allegation that Missouri\n“brings this action on its own behalf” does nothing to explain\nMissouri’s standing under a direct injury theory or to identify\nthe evidence required at summary judgment. 2\n\n\n 2\n At oral argument, Missouri contended that a party need not\nbrief a “legally self-evident” theory of standing at summary\njudgment. “Generally, arguments raised for the first time at oral\nargument are forfeited.” U.S. ex rel. Davis v. D.C., 793 F.3d 120,\n\f 9\n The only remaining question is whether an extraordinary\ncircumstance excuses Missouri’s forfeiture. See Flynn v.\nComm’r, 269 F.3d 1064, 1068–69 (D.C. Cir. 2001). As far as\nwe can tell, nothing in the record manifests that Missouri’s\nforfeiture of its direct injury theory was anything other than a\ntactical decision. And Missouri does not argue otherwise.\nAccordingly, we conclude that Missouri has forfeited its direct\ninjury theory.\n\n B. PARENS PATRIAE CAPACITY\n\n Missouri faces an uphill climb in establishing standing in\nits parens patriae capacity. The traditional rule, the so-called\n“Mellon bar,” declares that a State lacks standing as parens\npatriae to bring an action against the federal government.\nMassachusetts v. Mellon, 262 U.S. 447, 485–86 (1923)\n(“While the state, under some circumstances, may sue” as\nparens patriae “for the protection of its citizens, it is no part of\nits duty or power to enforce their rights in respect of their\nrelations with the federal government.”); see also Alfred L.\nSnapp & Son, Inc, 458 U.S. at 610 n.16; South Carolina v.\nKatzenbach, 383 U.S. 301, 324 (1966); Florida v. Mellon, 273\nU.S. 12, 18 (1927); Maryland People’s Counsel v. FERC, 760\nF.2d 318, 320 (D.C. Cir. 1985). Missouri first counters that\nthe Mellon bar does not apply to this litigation because it is\ndisplaced by the APA. It also contends that the Supreme\nCourt’s holding in Massachusetts v. EPA, 549 U.S. 497 (2007),\nprecludes application of the Mellon bar here.\n\n 1. THE MELLON BAR APPLIES TO APA CASES\n\n Missouri contends that the Mellon bar does not apply to\nlitigation the State brings against the federal government under\n\n127 (D.C. Cir. 2015). And Missouri offers no basis for excusing its\nforfeiture.\n\f 10\nthe APA. We have indeed recognized that the Mellon bar\nspeaks to prudential, not Article III, standing which the courts\ndesigned to prevent a State from encroaching on the federal\ngovernment’s power. Maryland People’s Counsel, 760 F.2d\nat 321–22; Kleppe, 533 F.2d at 676–77 (discussing Mellon bar\npurpose); cf. Lexmark Int’l, Inc. v. Static Control Components,\nInc., 572 U.S. 118, 128 & n.4 (2014) (explaining “prudential\nstanding” label is misleading because doctrine concerns\nwhether plaintiff has cause of action under relevant statute and\n“‘the absence of a valid (as opposed to arguable) cause of\naction does not implicate subject-matter jurisdiction, i.e., the\ncourt’s statutory or constitutional power to adjudicate the\ncase.”’ (quoting Verizon Md. Inc. v. Public Serv. Comm’n of\nMd., 535 U.S. 635, 642–43 (2002))). Because the Mellon bar\nis prudential, we have held that the Congress may by statute\nauthorize a State to sue the federal government in its parens\npatriae capacity. Maryland People’s Counsel, 760 F.2d at\n322. Missouri believes the APA is such a statute and allows\nits lawsuit against Reclamation to proceed.\n\n Our leading precedent in this area is Maryland People’s\nCounsel v. FERC, 760 F.2d 318 (D.C. Cir. 1985). 3 There, we\nconcluded that the judicial review provision included in the\nNatural Gas Act of 1938 (NGA), Pub. L. No. 75-688, 52 Stat.\n821 (codified at 15 U.S.C. §§ 717 et seq.), is not subject to the\nMellon bar. Id. at 320–21 (citing 15 U.S.C. § 717r(b)). Our\nanalysis is instructive. The NGA authorizes States to\nparticipate in proceedings before the Federal Energy\n\n 3\n Missouri asserts that earlier precedent, Pennsylvania v.\nKleppe, 533 F.2d 668, 677 n.55 (D.C. Cir. 1976), held that the APA\nabrogated the Mellon bar and allowed a State to sue the federal\ngovernment in its parens patriae capacity. We did not conclude that\nPennsylvania had standing in Kleppe; Missouri’s claim that Kleppe\nadopted a bright-line rule that a State has parens patriae standing\nunder the APA is, therefore, in error. Id. at 680.\n\f 11\nRegulatory Commission (FERC). Id. It also gives States a\ncause of action to sue FERC based on those proceedings. Id.\nat 321. But States are generally not purchasers of natural gas.\nId. This fact led us to infer that the NGA’s judicial review\nprovision is “evidently designed to recognize precisely the\ninterest of the states in protecting their citizens in this\ntraditional governmental field of utility regulation—that is, the\nstates’ parens patriae interest.” Id. Because the Congress\nintended a State to sue FERC based on its “parens patriae\ninterest[s],” we held that an NGA suit brought by a State is not\nsubject to the Mellon bar. Id. at 321–22 (describing\n“congressional elimination of the rule of Massachusetts v.\nMellon” as “effective”).\n\n The APA generally provides a cause of action to any\n“person . . . adversely affected or aggrieved by agency action.”\n5 U.S.C. § 702. There is little doubt that a State qualifies as a\n“person” under the APA. See Maryland Dep’t of Human Res.\nv. Dep’t of Health & Human Servs., 763 F.2d 1441, 1445 n.1\n(D.C. Cir. 1985) (“If a foreign government and its agencies are\npersons within the meaning of the APA, it seems clear that a\nstate and its agencies also are.”). To sue in its parens patriae\ncapacity, moreover, a State must suffer an injury to its quasi-\nsovereign interest, Alfred L. Snapp & Son, Inc., 458 U.S. at\n607, and thus must be “adversely affected or aggrieved,” 5\nU.S.C. § 702. Unlike the NGA, however, the APA evinces no\ncongressional intent to authorize a State as parens patriae to\nsue the federal government. The APA’s judicial review\nprovision authorizes suit by a “person” challenging agency\naction and the APA definition of “person,” by implication only,\nincludes a State, 5 U.S.C. § 701(b)(2) (“‘[P]erson’ . . . ha[s] the\nmeaning[] given . . . by section 551 of this title.”); 5 U.S.C.\n§ 551(2) (“‘[P]erson’ includes an individual, partnership,\ncorporation, association, or public or private organization other\nthan an agency.”). The APA’s judicial review provision\n\f 12\nallows a person to challenge agency action taken under many\ndifferent statutes. See Block v. Cmty. Nutrition Inst., 467 U.S.\n340, 345 (1984) (APA confers “a general cause of action”). It\nis not linked to any particular statutory scheme and—unlike the\nNGA—does not create an inference that the Congress intended\na wholesale imprimatur allowing a State as parens patriae to\nsue the federal government. Accordingly, the Mellon bar\napplies to litigation that a State, using the APA, seeks to pursue\nagainst the federal government. 4\n\n 2. THE MELLON BAR HAS NO EXCEPTION\n\n Missouri also insists that the holding in Massachusetts v.\nEPA, 549 U.S. 497 (2007), creates an exception to the Mellon\nbar that allows its lawsuit against Reclamation to proceed. In\nthat case, Massachusetts petitioned the EPA to promulgate a\nrule governing vehicular greenhouse gas emissions. Id. at\n510. The EPA declined to regulate and Massachusetts sought\njudicial review. Id. at 510–15. The United States Supreme\nCourt concluded that Massachusetts had standing in its own\nright to sue the EPA. Id. at 526. Its entire parens patriae\ndiscussion appears in footnote seventeen, two sentences of\nwhich are critical to Missouri’s argument. Id. at 520 n.17.\nThe first declares that “there is a critical difference between\nallowing a State ‘to protect her citizens from the operation of\nfederal statutes’ (which is what Mellon prohibits) and allowing\na State to assert its rights under federal law (which it has\nstanding to do).” Id. (quoting Georgia v. Pennsylvania R. Co.,\n324 U.S. 439, 447 (1945)). The second then states:\n“Massachusetts does not here dispute that the Clean Air Act\napplies to its citizens; it rather seeks to assert its rights under\n\n 4\n We note that Missouri has not made an argument that\nNEPA—as opposed to the APA—authorizes this suit\nnotwithstanding the Mellon bar and thus we have no occasion to\nconsider that argument.\n\f 13\nthe Act.” Id. Missouri reads the footnote as establishing an\nexception to the Mellon bar for litigation in which a State “does\nnot challenge the validity of a federal statute but instead sues\nthe federal government to assert the State’s own rights or those\nof its citizens under federal statutes.”\n\n But the Supreme Court had no need to carve out an\nexception to the Mellon bar in Massachusetts v. EPA because\nMassachusetts did not sue in its parens patriae capacity.\nAccord Center for Biological Diversity v. U.S. Dep’t of\nInterior, 563 F.3d 466, 476–78 (D.C. Cir. 2009) (discussing\nparens patriae analysis in Massachusetts v. EPA). It instead\n“alleged a particularized injury in its capacity as a landowner.”\nMassachusetts, 549 U.S. at 522. Because Massachusetts sued\nto remedy its own injury rather than that of its citizens,\nMassachusetts v. EPA is not a parens patriae case. There is\nsome confusion on this score most possibly caused by the\nopinion’s discussion of quasi-sovereign interests. Id. at 519–\n20. But that discussion related to the Supreme Court affording\nMassachusetts “special solicitude in [the] standing analysis.”\nId at 520. The Court explained that Massachusetts is entitled\nto “special solicitude” because (1) a State has a quasi-sovereign\ninterest in “preserv[ing] its sovereign territory” and (2) the\nCongress afforded “a concomitant procedural right to\nchallenge the rejection of its rulemaking petition as arbitrary\nand capricious.” Id. at 519–20; see also Texas v. United\nStates, 809 F.3d 134, 151 (5th Cir. 2015) (applying special\nsolicitude doctrine). Notwithstanding the quasi-sovereign-\ninterests discussion, however, Massachusetts asserted its own\nstatutory right and alleged its own harm to establish an injury-\nin-fact, as footnote seventeen expressly recognizes,\nMassachusetts, 549 U.S. at 520 n.17 (“Massachusetts does not\nhere dispute that the Clean Air Act applies to its citizens; it\nrather seeks to assert its rights under the Act.” (second\nemphasis added)); see also id. at 522 (Massachusetts “has\n\f 14\nalleged a particularized injury in its capacity as a coastal\nlandowner”).\n\n Nor does the text of footnote seventeen support Missouri’s\nproposed exception. The first three sentences of the footnote\ndispute the dissent’s characterization of Mellon as supporting\nthe proposition that a State cannot assert a quasi-sovereign\ninterest when suing the federal government. Compare id. at\n539 (Roberts, C.J., dissenting) (“[T]he Court overlooks the fact\nthat our cases cast significant doubt on a State’s standing to\nassert a quasi-sovereign interest—as opposed to a direct\ninjury—against the Federal Government.”), with id. at 520 n.17\n(“Mellon itself disavowed any such broad reading when it\nnoted that the [Mellon] Court had been ‘called upon to\nadjudicate, not rights of person or property, not rights of\ndominion over physical domain, [and] not quasi-sovereign\nrights actually invaded or threatened.’” (quoting 262 U.S. at\n484–85)). For good measure, the two concluding sentences of\nthe footnote distinguish the Massachusetts facts from those of\nMellon. “In any event,” they explain, “there is a critical\ndifference between allowing a State ‘to protect her citizens\nfrom the operation of federal statutes’ (which is what Mellon\nprohibits) and allowing a State to assert its rights under federal\nlaw (which it has standing to do).” Id. (quoting Pennsylvania\nR. Co., 324 U.S. at 447). The distinction is not, as Missouri\nsuggests, between two types of parens patriae lawsuits, one\npermissible and one not. It is between a parens patriae\nlawsuit (what Mellon prohibits) and a State suing based on “its\nrights under federal law” (not a parens patriae lawsuit at all).\nSee Wyoming, 502 U.S. at 448–49 (1992) (“[C]laims of parens\npatriae standing” differ from “allegations of direct injury to the\nState itself.”); cf. Kleppe, 533 F.2d at 675 (describing parens\npatriae lawsuit as “representative action by the state”).\n\f 15\n Finally, Missouri’s reading of footnote seventeen, if\nadopted, would establish an exception that makes little sense in\nlight of the vertical federalism interest underlying the Mellon\nbar. As we have explained, an “individual’s dual citizenship\nin both state and nation, with separate rights and obligations\narising from each, suggests that both units of government act\nas parens patriae within their separate spheres of activity.” Id.\nat 676–77. “The general supremacy of federal law” means\n“that the federal parens patriae power should not, as a rule, be\nsubject to the intervention of states seeking to represent the\nsame interest of the same citizens.” Id. at 677. For that\nreason, a “state can not have a quasi-sovereign interest\nbecause” matters of federal law “fall[] within the sovereignty\nof the Federal Government.” Id. It is the State’s\nrepresentation that usurps the role of the federal government,\nnot the legal theory underlying its complaint. Id. at 676–77.\nThere is no reason to treat parens patriae actions alleging\nconstitutional claims against the federal government\ndifferently from those alleging federal statutory claims. We\ndoubt the Supreme Court meant in footnote seventeen to create\nan exception to the Mellon bar based on such a distinction.\n\n In the end, we are unpersuaded by Missouri’s argument\nthat Massachusetts v. EPA alters our longstanding precedent\nthat a State in general lacks parens patriae standing to sue the\nfederal government. Accord Center for Biological Diversity,\n563 F.3d at 476–78 (rejecting, in dicta, that Massachusetts v.\nEPA creates exception to Mellon bar); Maryland People’s\nCounsel, 760 F.2d at 320 (“[a] State does not have standing as\nparens patriae to bring an action against the Federal\nGovernment” (quoting Alfred L. Snapp & Son, Inc., 458 U.S.\nat 610 n.16)); Michigan v. EPA, 581 F.3d 524, 529 (7th Cir.\n2009) (per Wood, J.) (Massachusetts does not create exception\nto Mellon bar); Commonwealth v. U.S. Dep’t of Educ., 340 F.\nSupp. 3d 7, 14–16 (D.D.C. 2018) (same).\n\f 16\n For the foregoing reasons, we affirm the judgment of the\ndistrict court.\n\n So ordered.\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: GOVERNMENT OF the Province of MANITOBA, Appellee State of Missouri, Ex Rel. Eric Schmitt, Missouri Attorney General's Office, Appellant v. David BERNHARDT, Secretary, U.S. Department of the Interior, Et Al., Appellees\\nCourt: U.S. Court of Appeals for the District of Columbia Circuit\\nDate decided: 2019-05-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\nUnited States Court of Appeals\\n FOR THE DISTRICT OF COLUMBIA CIRCUIT\\n\\n\\n\\nArgued November 8, 2018 Decided May 3, 2019\\n\\n No. 17-5242\\n\\n GOVERNMENT OF THE PROVINCE OF MANITOBA,\\n APPELLEE\\n\\n STATE OF MISSOURI, EX REL. ERIC SCHMITT,\\n MISSOURI ATTORNEY GENERAL’S OFFICE,\\n APPELLANT\\n\\n v.\\n\\n DAVID BERNHARDT, SECRETARY,\\n U.S. DEPARTMENT OF THE INTERIOR, ET AL.,\\n APPELLEES\\n\\n\\n Appeal from the United States District Court\\n for the District of Columbia\\n (No. 1:02-cv-02057)\\n\\n\\n Joshua M. Divine, Deputy Solicitor, Office of the Attorney\\nGeneral for the State of Missouri, argued the cause for the\\nappellant. Joshua D. Hawley, Attorney General, D. John\\nSauer, First Assistant and Solicitor and Julie Marie Blake,\\nDeputy Solicitor, were with him on brief. Laura E. Elsbury,\\nTrial Counsel, and Eldon V. Greenberg entered appearances.\\n\\n Anna T. Katselas, Attorney, United States Department of\\nJustice, argued the cause for the federal appellees. Jeffrey H.\\n\\f 2\\nWood, Acting Assistant Attorney General, Eric Grant, Deputy\\nAssistant Attorney General, and Robert J. Lundman, Attorney,\\nwere with her on brief. Andrew C. Mergen, Attorney, entered\\nan appearance.\\n\\n Nessa Horewitch Coppinger and Ryan J. Carra, Special\\nAssistant Attorneys General, Office of the Attorney General\\nfor the State of North Dakota, and Jennifer L. Verleger,\\nAssistant Attorney General, were on brief for the appellee State\\nof North Dakota. Scott M. DuBoff and Benjamin L. Lambiotte\\nentered appearances.\\n\\n Before: HENDERSON, ROGERS and SRINIVASAN, Circuit\\nJudges.\\n\\n Opinion for the Court filed by Circuit Judge HENDERSON.\\n\\n KAREN LECRAFT HENDERSON, Circuit Judge: The\\nNorthwest Area Water Supply Project (Project) will someday\\nsend clean water from the Missouri River Basin to parched\\ncommunities in northern North Dakota. That day has not yet\\ncome. For now, the Project’s construction remains bogged\\ndown in long-running environmental litigation. This case, the\\nmost recent leg of the litigation marathon, involves the State of\\nMissouri’s complaint that the Bureau of Reclamation\\n(Reclamation)—the federal agency responsible for carrying\\nout the Project—violated the National Environmental Policy\\nAct of 1969, Pub. L. No. 91-190, 83 Stat. 852 (1970) (codified\\nas amended at 42 U.S.C. §§ 4321 et seq.) (NEPA), by failing\\nto consider adequately how diverting billions of gallons of\\nMissouri River water will affect downstream States.\\n\\n Missouri brought this lawsuit on behalf of its citizens to\\nprevent the Project from causing them harm. In legal\\nlanguage, Missouri sued in its parens patriae capacity. The\\n\\f 3\\nproblem for Missouri is that, as a general matter, a “State does\\nnot have standing as parens patriae to bring an action against\\nthe Federal Government.” Alfred L. Snapp & Son, Inc. v.\\nPuerto Rico, ex rel., Barez, 458 U.S. 592, 610 n.16 (1982).\\nFor this reason and others elaborated below, we agree with the\\ndistrict court that Missouri lacks standing and therefore affirm.\\n\\n I. BACKGROUND\\n\\n Communities in northern North Dakota have long suffered\\nfrom water shortages. North Dakota and Reclamation—an\\nagency housed within the United States Department of Interior\\ncharged with, inter alia, managing and developing water\\nresources—began seeking a solution in the late 1980s. Their\\nefforts culminated in the Northwest Area Water Supply\\nProject. The Project will “withdraw water from the Missouri\\nRiver Basin and transport it via a 45-mile-long pipeline to the\\nHudson Bay Basin located in Northwest North Dakota.”\\nGov’t of Province of Manitoba v. Zinke, 849 F.3d 1111, 1114\\n(D.C. Cir. 2017). Over eighty thousand North Dakotans will\\ngain access to clean water.\\n\\n “The Project falls under the auspices of” NEPA, which\\n“imposes ‘a set of action-forcing procedures’ requiring federal\\nagencies to take a ‘hard look’ at any potential environmental\\nconsequences associated with their ‘proposals and actions’ and\\nto broadly disseminate relevant environmental information.”\\nId. at 1115 (quoting Dep’t of Transp. v. Pub. Citizen, 541 U.S.\\n752, 756–57 (2004); Robertson v. Methow Valley Citizens\\nCouncil, 490 U.S. 332, 350 (1989)). To that end, NEPA\\nrequires “all agencies of the Federal Government” to prepare\\nan Environmental Impact Statement (EIS) before taking a\\n“major Federal action[] significantly affecting the quality of the\\nhuman environment.” 42 U.S.C. § 4332(2)(C). An EIS is\\nnot required, however, if the agency completes an\\n\\f 4\\nEnvironmental Assessment and makes a Finding of No\\nSignificant Impact. New York v. Nuclear Regulatory\\nComm’n, 681 F.3d 471, 476 (D.C. Cir. 2012); see also 40\\nC.F.R. § 1501.4 (“In determining whether to prepare an\\nenvironmental impact statement the Federal agency shall . . .\\n[p]repare a finding of no significant impact (§ 1508.13), if the\\nagency determines on the basis of the environmental\\nassessment not to prepare a statement.”). NEPA itself does\\nnot provide a cause of action, W. Org. of Res. Councils v. Zinke,\\n892 F.3d 1234, 1241 (D.C. Cir. 2018); as a consequence, any\\nchallenge to agency action based on NEPA must be brought\\nunder the Administrative Procedure Act, 5 U.S.C. §§ 701 et\\nseq.\\n\\n We earlier held that Reclamation has failed to “comply\\nwith NEPA’s requirements” and has “left the Project mired in\\nlegal challenges” since 2002. Gov’t of Province of Manitoba,\\n849 F.3d at 1115. Our decision there sets forth in detail the\\nhistory of the litigation. Id. at 1114–17. We recount only the\\nessentials. There were two Project-related lawsuits against\\nReclamation before this one. Manitoba brought the first\\nchallenge, claiming Reclamation failed to “adequately grapple\\nwith potential ecological problems caused by transferring\\ntreatment-resistant biota into the Hudson Bay Basin.” Id. at\\n1115. The district court agreed, remanding to Reclamation its\\ninitial Finding of No Significant Impact. Gov’t of Province of\\nManitoba v. Norton, 398 F. Supp. 2d 41, 67 (D.D.C. 2005).\\nFour years later, Reclamation issued an EIS and Manitoba sued\\nagain. Gov’t of Province of Manitoba, 849 F.3d at 1116.\\nThis time, the State of Missouri also filed suit, alleging that\\nReclamation “did not properly account for cumulative effects\\nof water withdrawal from the Missouri River.” Id. The\\ndistrict court sided with both challengers, criticized\\nReclamation’s inadequate work and remanded for more NEPA\\nanalysis. Id.\\n\\f 5\\n In 2015, Reclamation issued a Supplemental\\nEnvironmental Impact Statement (SEIS) for the Project.\\nManitoba 1 and Missouri again brought challenges, leading to\\nthis appeal. Reclamation moved for summary judgment,\\narguing that Missouri failed to establish standing.\\nSpecifically, Reclamation claimed that a State cannot sue the\\nfederal government as parens patriae, Missouri’s sole basis for\\nstanding. Missouri did not dispute that it relied solely on a\\nparens patriae theory of standing but maintained that a State\\ncan, at least under some circumstances, sue the federal\\ngovernment in its parens patriae capacity. The district court\\nfirst noted that “Missouri is very clear that it sues in its role as\\nparens patriae on behalf of its residents” and “advances no\\nother basis for its standing.” Gov’t of Province of Manitoba v.\\nZinke, 273 F. Supp. 3d 145, 167–68 (D.D.C. 2017). It\\nexplained that under longstanding precedent, a State lacks\\nparens patriae standing to sue the federal government. Id. at\\n162–68. The district court dismissed the complaint—a\\ndecision from which Missouri now appeals. Our review is de\\nnovo. Scenic Am., Inc. v. U.S. Dep’t of Transp., 836 F.3d 42,\\n49 (D.C. Cir. 2016) (“We review the District Court’s decision\\n(or lack thereof) as to standing de novo.”).\\n\\n II. ANALYSIS\\n\\n Article III of the United States Constitution authorizes\\nfederal courts to decide only “Cases” and “Controversies.”\\nU.S. Const. art. III, § 2, cl. 1. “To present a justiciable case or\\ncontroversy, litigants must demonstrate standing, among other\\nrequirements.” Pub. Citizen v. Nat’l Highway Traffic Safety\\nAdmin., 489 F.3d 1279, 1289 (D.C. Cir. 2007). “The\\n‘irreducible constitutional minimum of standing’ contains\\nthree requirements.” Steel Co. v. Citizens for a Better Env’t,\\n\\n 1\\n Manitoba eventually settled with Reclamation.\\n\\f 6\\n523 U.S. 83, 102 (1998) (quoting Lujan v. Defenders of\\nWildlife, 504 U.S. 555, 560 (1992)). “The plaintiff must have\\n(1) suffered an injury in fact, (2) that is fairly traceable to the\\nchallenged conduct of the defendant, and (3) that is likely to be\\nredressed by a favorable judicial decision.” Spokeo, Inc. v.\\nRobins, 136 S. Ct. 1540, 1547 (2016). “[A]s the party\\ninvoking federal jurisdiction,” the plaintiff “bears the burden\\nof establishing these elements.” Id.\\n\\n A State’s standing depends on the capacity in which it\\ninitiates a lawsuit. Erwin Chemerinsky, Federal Jurisdiction\\n121 (7th ed. 2016) (“[A] distinction must be drawn between a\\ngovernment entity suing to remedy injuries that it has suffered\\nand suing in a representative capacity on behalf of its\\ncitizens.”). Two types of lawsuits are relevant here. The\\nfirst, a direct injury lawsuit, allows a State to sue to redress its\\nown injury. Cf. Wyoming v. Oklahoma, 502 U.S. 437, 448–49\\n(1992) (distinguishing between “claims of parens patriae\\nstanding” and “allegations of direct injury to the State itself”).\\nFor this first type of lawsuit, the State need meet only the\\nordinary demands of Article III—that is, establish injury-in-\\nfact, causation and redressability, West v. Lynch, 845 F.3d\\n1228, 1230 (D.C. Cir. 2017). The second type, a parens\\npatriae lawsuit, allows a State to sue in a representative\\ncapacity to vindicate its citizens’ interests. Pennsylvania v.\\nKleppe, 533 F.2d 668, 671 (D.C. Cir. 1976) (“[I]n bringing the\\naction also on behalf of all injured citizens of the state, and\\nupon the relation of four named individuals, Pennsylvania\\ninvokes a parens patriae theory of standing.”). For these\\nlawsuits, the State must do more than meet Article III’s\\nirreducible minimum; it must assert a quasi-sovereign interest\\n“apart from the interests of particular private parties.” Alfred\\nL. Snapp & Son, Inc., 458 U.S. at 607. The Supreme Court\\nhas held that, at a minimum, a State has a quasi-sovereign\\ninterest “in the health and well-being—both physical and\\n\\f 7\\neconomic—of its residents” and “in not being discriminatorily\\ndenied its rightful status within the federal system.” Id. at 607.\\n“One helpful indication in determining whether an alleged\\ninjury to the health and welfare of its citizens suffices to give\\nthe State standing to sue as parens patriae is whether the injury\\nis one that the State, if it could, would likely attempt to address\\nthrough its sovereign lawmaking powers.” Id.\\n\\n Missouri claims that this litigation asserts both a direct\\ninjury and a parens patriae injury. Both sides agree that the\\nProject will eventually divert billions of gallons of Missouri\\nRiver water each year to North Dakota communities.\\nMissouri asserts a direct injury: the large-scale diversion of\\nwater will allegedly harm its own interests by (among other\\nthings) damaging its riverfront properties (especially farmland\\nadjacent to the Missouri River) and its commercial navigation\\nbusinesses and by modifying its borders with neighboring\\nstates. Missouri also asserts that the Project will harm its\\ncitizens, a harm it seeks to allay in its quasi-sovereign—that is,\\nparens patriae—capacity. We address seriatim the two\\ntheories of standing.\\n\\n A. DIRECT INJURY\\n\\n Reclamation contends that Missouri forfeited its direct\\ninjury theory of standing. We agree. Absent exceptional\\ncircumstances, a party forfeits an argument by failing to press\\nit in district court. D.C. v. Straus, 590 F.3d 898, 903 (D.C.\\nCir. 2010); Adams v. Rice, 531 F.3d 936, 944–45 (D.C. Cir.\\n2008). And the ordinary rules of forfeiture apply to standing.\\nHuron v. Cobert, 809 F.3d 1274, 1280 (D.C. Cir. 2016)\\n(forfeiture “applies to standing, as much as to merits,\\narguments, because it is not the province of an appellate court\\nto ‘hypothesize or speculate about the existence of an injury\\n[Plaintiff] did not assert’ to the district court” (quoting Kawa\\n\\f 8\\nOrthodontics, LLP v. Secretary, U.S. Dep’t of the Treasury,\\n773 F.3d 243, 246 (11th Cir. 2014) (alteration in original))).\\nIn district court, Reclamation argued that Missouri as parens\\npatriae lacks standing to sue the federal government. Rather\\nthan preserve its direct injury theory, Missouri chose to rely\\nsolely on its parens patriae standing. This is textbook\\nforfeiture.\\n\\n Missouri responds that its complaint identifies a direct\\ninjury theory of standing and thus preserves that theory for our\\nconsideration. The complaint states that Missouri “brings this\\naction on its own behalf and as parens patriae for its residents.”\\nBut a threadbare allegation included in its complaint does not\\nhelp Missouri. A party forfeits an argument by mentioning it\\nonly “in the most skeletal way, leaving the court to do counsel’s\\nwork, create the ossature for the argument, and put flesh on its\\nbones.” Schneider v. Kissinger, 412 F.3d 190, 200 n.1 (D.C.\\nCir. 2005) (quoting United States v. Zannino, 895 F.2d 1, 17\\n(1st Cir. 1990)). On summary judgment, plaintiff Missouri\\nhad to identify record evidence establishing its standing to sue\\nReclamation. See Swanson Grp. Mfg. LLC v. Jewell, 790 F.3d\\n235, 240 (D.C. Cir. 2015); Abigail All. for Better Access to\\nDevelopmental Drugs v. Eschenbach, 469 F.3d 129, 132 (D.C.\\nCir. 2006) (“[T]he party invoking the court’s jurisdiction must\\nestablish the predicates for standing ‘with the manner and\\ndegree of evidence required at’ that stage of trial.” (quoting\\nLujan, 504 U.S. at 561)). The simple allegation that Missouri\\n“brings this action on its own behalf” does nothing to explain\\nMissouri’s standing under a direct injury theory or to identify\\nthe evidence required at summary judgment. 2\\n\\n\\n 2\\n At oral argument, Missouri contended that a party need not\\nbrief a “legally self-evident” theory of standing at summary\\njudgment. “Generally, arguments raised for the first time at oral\\nargument are forfeited.” U.S. ex rel. Davis v. D.C., 793 F.3d 120,\\n\\f 9\\n The only remaining question is whether an extraordinary\\ncircumstance excuses Missouri’s forfeiture. See Flynn v.\\nComm’r, 269 F.3d 1064, 1068–69 (D.C. Cir. 2001). As far as\\nwe can tell, nothing in the record manifests that Missouri’s\\nforfeiture of its direct injury theory was anything other than a\\ntactical decision. And Missouri does not argue otherwise.\\nAccordingly, we conclude that Missouri has forfeited its direct\\ninjury theory.\\n\\n B. PARENS PATRIAE CAPACITY\\n\\n Missouri faces an uphill climb in establishing standing in\\nits parens patriae capacity. The traditional rule, the so-called\\n“Mellon bar,” declares that a State lacks standing as parens\\npatriae to bring an action against the federal government.\\nMassachusetts v. Mellon, 262 U.S. 447, 485–86 (1923)\\n(“While the state, under some circumstances, may sue” as\\nparens patriae “for the protection of its citizens, it is no part of\\nits duty or power to enforce their rights in respect of their\\nrelations with the federal government.”); see also Alfred L.\\nSnapp & Son, Inc, 458 U.S. at 610 n.16; South Carolina v.\\nKatzenbach, 383 U.S. 301, 324 (1966); Florida v. Mellon, 273\\nU.S. 12, 18 (1927); Maryland People’s Counsel v. FERC, 760\\nF.2d 318, 320 (D.C. Cir. 1985). Missouri first counters that\\nthe Mellon bar does not apply to this litigation because it is\\ndisplaced by the APA. It also contends that the Supreme\\nCourt’s holding in Massachusetts v. EPA, 549 U.S. 497 (2007),\\nprecludes application of the Mellon bar here.\\n\\n 1. THE MELLON BAR APPLIES TO APA CASES\\n\\n Missouri contends that the Mellon bar does not apply to\\nlitigation the State brings against the federal government under\\n\\n127 (D.C. Cir. 2015). And Missouri offers no basis for excusing its\\nforfeiture.\\n\\f 10\\nthe APA. We have indeed recognized that the Mellon bar\\nspeaks to prudential, not Article III, standing which the courts\\ndesigned to prevent a State from encroaching on the federal\\ngovernment’s power. Maryland People’s Counsel, 760 F.2d\\nat 321–22; Kleppe, 533 F.2d at 676–77 (discussing Mellon bar\\npurpose); cf. Lexmark Int’l, Inc. v. Static Control Components,\\nInc., 572 U.S. 118, 128 & n.4 (2014) (explaining “prudential\\nstanding” label is misleading because doctrine concerns\\nwhether plaintiff has cause of action under relevant statute and\\n“‘the absence of a valid (as opposed to arguable) cause of\\naction does not implicate subject-matter jurisdiction, i.e., the\\ncourt’s statutory or constitutional power to adjudicate the\\ncase.”’ (quoting Verizon Md. Inc. v. Public Serv. Comm’n of\\nMd., 535 U.S. 635, 642–43 (2002))). Because the Mellon bar\\nis prudential, we have held that the Congress may by statute\\nauthorize a State to sue the federal government in its parens\\npatriae capacity. Maryland People’s Counsel, 760 F.2d at\\n322. Missouri believes the APA is such a statute and allows\\nits lawsuit against Reclamation to proceed.\\n\\n Our leading precedent in this area is Maryland People’s\\nCounsel v. FERC, 760 F.2d 318 (D.C. Cir. 1985). 3 There, we\\nconcluded that the judicial review provision included in the\\nNatural Gas Act of 1938 (NGA), Pub. L. No. 75-688, 52 Stat.\\n821 (codified at 15 U.S.C. §§ 717 et seq.), is not subject to the\\nMellon bar. Id. at 320–21 (citing 15 U.S.C. § 717r(b)). Our\\nanalysis is instructive. The NGA authorizes States to\\nparticipate in proceedings before the Federal Energy\\n\\n 3\\n Missouri asserts that earlier precedent, Pennsylvania v.\\nKleppe, 533 F.2d 668, 677 n.55 (D.C. Cir. 1976), held that the APA\\nabrogated the Mellon bar and allowed a State to sue the federal\\ngovernment in its parens patriae capacity. We did not conclude that\\nPennsylvania had standing in Kleppe; Missouri’s claim that Kleppe\\nadopted a bright-line rule that a State has parens patriae standing\\nunder the APA is, therefore, in error. Id. at 680.\\n\\f 11\\nRegulatory Commission (FERC). Id. It also gives States a\\ncause of action to sue FERC based on those proceedings. Id.\\nat 321. But States are generally not purchasers of natural gas.\\nId. This fact led us to infer that the NGA’s judicial review\\nprovision is “evidently designed to recognize precisely the\\ninterest of the states in protecting their citizens in this\\ntraditional governmental field of utility regulation—that is, the\\nstates’ parens patriae interest.” Id. Because the Congress\\nintended a State to sue FERC based on its “parens patriae\\ninterest[s],” we held that an NGA suit brought by a State is not\\nsubject to the Mellon bar. Id. at 321–22 (describing\\n“congressional elimination of the rule of Massachusetts v.\\nMellon” as “effective”).\\n\\n The APA generally provides a cause of action to any\\n“person . . . adversely affected or aggrieved by agency action.”\\n5 U.S.C. § 702. There is little doubt that a State qualifies as a\\n“person” under the APA. See Maryland Dep’t of Human Res.\\nv. Dep’t of Health & Human Servs., 763 F.2d 1441, 1445 n.1\\n(D.C. Cir. 1985) (“If a foreign government and its agencies are\\npersons within the meaning of the APA, it seems clear that a\\nstate and its agencies also are.”). To sue in its parens patriae\\ncapacity, moreover, a State must suffer an injury to its quasi-\\nsovereign interest, Alfred L. Snapp & Son, Inc., 458 U.S. at\\n607, and thus must be “adversely affected or aggrieved,” 5\\nU.S.C. § 702. Unlike the NGA, however, the APA evinces no\\ncongressional intent to authorize a State as parens patriae to\\nsue the federal government. The APA’s judicial review\\nprovision authorizes suit by a “person” challenging agency\\naction and the APA definition of “person,” by implication only,\\nincludes a State, 5 U.S.C. § 701(b)(2) (“‘[P]erson’ . . . ha[s] the\\nmeaning[] given . . . by section 551 of this title.”); 5 U.S.C.\\n§ 551(2) (“‘[P]erson’ includes an individual, partnership,\\ncorporation, association, or public or private organization other\\nthan an agency.”). The APA’s judicial review provision\\n\\f 12\\nallows a person to challenge agency action taken under many\\ndifferent statutes. See Block v. Cmty. Nutrition Inst., 467 U.S.\\n340, 345 (1984) (APA confers “a general cause of action”). It\\nis not linked to any particular statutory scheme and—unlike the\\nNGA—does not create an inference that the Congress intended\\na wholesale imprimatur allowing a State as parens patriae to\\nsue the federal government. Accordingly, the Mellon bar\\napplies to litigation that a State, using the APA, seeks to pursue\\nagainst the federal government. 4\\n\\n 2. THE MELLON BAR HAS NO EXCEPTION\\n\\n Missouri also insists that the holding in Massachusetts v.\\nEPA, 549 U.S. 497 (2007), creates an exception to the Mellon\\nbar that allows its lawsuit against Reclamation to proceed. In\\nthat case, Massachusetts petitioned the EPA to promulgate a\\nrule governing vehicular greenhouse gas emissions. Id. at\\n510. The EPA declined to regulate and Massachusetts sought\\njudicial review. Id. at 510–15. The United States Supreme\\nCourt concluded that Massachusetts had standing in its own\\nright to sue the EPA. Id. at 526. Its entire parens patriae\\ndiscussion appears in footnote seventeen, two sentences of\\nwhich are critical to Missouri’s argument. Id. at 520 n.17.\\nThe first declares that “there is a critical difference between\\nallowing a State ‘to protect her citizens from the operation of\\nfederal statutes’ (which is what Mellon prohibits) and allowing\\na State to assert its rights under federal law (which it has\\nstanding to do).” Id. (quoting Georgia v. Pennsylvania R. Co.,\\n324 U.S. 439, 447 (1945)). The second then states:\\n“Massachusetts does not here dispute that the Clean Air Act\\napplies to its citizens; it rather seeks to assert its rights under\\n\\n 4\\n We note that Missouri has not made an argument that\\nNEPA—as opposed to the APA—authorizes this suit\\nnotwithstanding the Mellon bar and thus we have no occasion to\\nconsider that argument.\\n\\f 13\\nthe Act.” Id. Missouri reads the footnote as establishing an\\nexception to the Mellon bar for litigation in which a State “does\\nnot challenge the validity of a federal statute but instead sues\\nthe federal government to assert the State’s own rights or those\\nof its citizens under federal statutes.”\\n\\n But the Supreme Court had no need to carve out an\\nexception to the Mellon bar in Massachusetts v. EPA because\\nMassachusetts did not sue in its parens patriae capacity.\\nAccord Center for Biological Diversity v. U.S. Dep’t of\\nInterior, 563 F.3d 466, 476–78 (D.C. Cir. 2009) (discussing\\nparens patriae analysis in Massachusetts v. EPA). It instead\\n“alleged a particularized injury in its capacity as a landowner.”\\nMassachusetts, 549 U.S. at 522. Because Massachusetts sued\\nto remedy its own injury rather than that of its citizens,\\nMassachusetts v. EPA is not a parens patriae case. There is\\nsome confusion on this score most possibly caused by the\\nopinion’s discussion of quasi-sovereign interests. Id. at 519–\\n20. But that discussion related to the Supreme Court affording\\nMassachusetts “special solicitude in [the] standing analysis.”\\nId at 520. The Court explained that Massachusetts is entitled\\nto “special solicitude” because (1) a State has a quasi-sovereign\\ninterest in “preserv[ing] its sovereign territory” and (2) the\\nCongress afforded “a concomitant procedural right to\\nchallenge the rejection of its rulemaking petition as arbitrary\\nand capricious.” Id. at 519–20; see also Texas v. United\\nStates, 809 F.3d 134, 151 (5th Cir. 2015) (applying special\\nsolicitude doctrine). Notwithstanding the quasi-sovereign-\\ninterests discussion, however, Massachusetts asserted its own\\nstatutory right and alleged its own harm to establish an injury-\\nin-fact, as footnote seventeen expressly recognizes,\\nMassachusetts, 549 U.S. at 520 n.17 (“Massachusetts does not\\nhere dispute that the Clean Air Act applies to its citizens; it\\nrather seeks to assert its rights under the Act.” (second\\nemphasis added)); see also id. at 522 (Massachusetts “has\\n\\f 14\\nalleged a particularized injury in its capacity as a coastal\\nlandowner”).\\n\\n Nor does the text of footnote seventeen support Missouri’s\\nproposed exception. The first three sentences of the footnote\\ndispute the dissent’s characterization of Mellon as supporting\\nthe proposition that a State cannot assert a quasi-sovereign\\ninterest when suing the federal government. Compare id. at\\n539 (Roberts, C.J., dissenting) (“[T]he Court overlooks the fact\\nthat our cases cast significant doubt on a State’s standing to\\nassert a quasi-sovereign interest—as opposed to a direct\\ninjury—against the Federal Government.”), with id. at 520 n.17\\n(“Mellon itself disavowed any such broad reading when it\\nnoted that the [Mellon] Court had been ‘called upon to\\nadjudicate, not rights of person or property, not rights of\\ndominion over physical domain, [and] not quasi-sovereign\\nrights actually invaded or threatened.’” (quoting 262 U.S. at\\n484–85)). For good measure, the two concluding sentences of\\nthe footnote distinguish the Massachusetts facts from those of\\nMellon. “In any event,” they explain, “there is a critical\\ndifference between allowing a State ‘to protect her citizens\\nfrom the operation of federal statutes’ (which is what Mellon\\nprohibits) and allowing a State to assert its rights under federal\\nlaw (which it has standing to do).” Id. (quoting Pennsylvania\\nR. Co., 324 U.S. at 447). The distinction is not, as Missouri\\nsuggests, between two types of parens patriae lawsuits, one\\npermissible and one not. It is between a parens patriae\\nlawsuit (what Mellon prohibits) and a State suing based on “its\\nrights under federal law” (not a parens patriae lawsuit at all).\\nSee Wyoming, 502 U.S. at 448–49 (1992) (“[C]laims of parens\\npatriae standing” differ from “allegations of direct injury to the\\nState itself.”); cf. Kleppe, 533 F.2d at 675 (describing parens\\npatriae lawsuit as “representative action by the state”).\\n\\f 15\\n Finally, Missouri’s reading of footnote seventeen, if\\nadopted, would establish an exception that makes little sense in\\nlight of the vertical federalism interest underlying the Mellon\\nbar. As we have explained, an “individual’s dual citizenship\\nin both state and nation, with separate rights and obligations\\narising from each, suggests that both units of government act\\nas parens patriae within their separate spheres of activity.” Id.\\nat 676–77. “The general supremacy of federal law” means\\n“that the federal parens patriae power should not, as a rule, be\\nsubject to the intervention of states seeking to represent the\\nsame interest of the same citizens.” Id. at 677. For that\\nreason, a “state can not have a quasi-sovereign interest\\nbecause” matters of federal law “fall[] within the sovereignty\\nof the Federal Government.” Id. It is the State’s\\nrepresentation that usurps the role of the federal government,\\nnot the legal theory underlying its complaint. Id. at 676–77.\\nThere is no reason to treat parens patriae actions alleging\\nconstitutional claims against the federal government\\ndifferently from those alleging federal statutory claims. We\\ndoubt the Supreme Court meant in footnote seventeen to create\\nan exception to the Mellon bar based on such a distinction.\\n\\n In the end, we are unpersuaded by Missouri’s argument\\nthat Massachusetts v. EPA alters our longstanding precedent\\nthat a State in general lacks parens patriae standing to sue the\\nfederal government. Accord Center for Biological Diversity,\\n563 F.3d at 476–78 (rejecting, in dicta, that Massachusetts v.\\nEPA creates exception to Mellon bar); Maryland People’s\\nCounsel, 760 F.2d at 320 (“[a] State does not have standing as\\nparens patriae to bring an action against the Federal\\nGovernment” (quoting Alfred L. Snapp & Son, Inc., 458 U.S.\\nat 610 n.16)); Michigan v. EPA, 581 F.3d 524, 529 (7th Cir.\\n2009) (per Wood, J.) (Massachusetts does not create exception\\nto Mellon bar); Commonwealth v. U.S. Dep’t of Educ., 340 F.\\nSupp. 3d 7, 14–16 (D.D.C. 2018) (same).\\n\\f 16\\n For the foregoing reasons, we affirm the judgment of the\\ndistrict court.\\n\\n So ordered.\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2297,"cells":{"id":{"kind":"number","value":7335706,"string":"7,335,706"},"name":{"kind":"string","value":"Kelly MILLER v. MARRIOTT INTERNATIONAL LLC"},"name_abbreviation":{"kind":"string","value":"Miller v. Marriott Int'l LLC"},"decision_date":{"kind":"string","value":"2019-05-03"},"docket_number":{"kind":"string","value":"Civ. No. 18-cv-1101 (APM)"},"court":{"kind":"string","value":"U.S. Court of Appeals for the District of Columbia Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Introduction, Mehta\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/7253626/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"MEHTA"},"judge2":{"kind":"string","value":"MEHTA"},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/7335706/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: Kelly MILLER v. MARRIOTT INTERNATIONAL LLC\nCourt: U.S. Court of Appeals for the District of Columbia Circuit\nDate decided: 2019-05-03\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: Kelly MILLER v. MARRIOTT INTERNATIONAL LLC\\nCourt: U.S. Court of Appeals for the District of Columbia Circuit\\nDate decided: 2019-05-03\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2298,"cells":{"id":{"kind":"number","value":7336308,"string":"7,336,308"},"name":{"kind":"string","value":"AMERICAN HOSPITAL ASSOCIATION v. Alex M. AZAR II, United States Secretary of Health and Human Services"},"name_abbreviation":{"kind":"string","value":"Am. Hosp. Ass'n v. Azar"},"decision_date":{"kind":"string","value":"2019-05-06"},"docket_number":{"kind":"string","value":"Civil Action No.: 18-2084 (RC)"},"court":{"kind":"string","value":"U.S. Court of Appeals for the District of Columbia Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Contreras\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/7254228/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"CONTRERAS"},"judge2":{"kind":"string","value":"CONTRERAS"},"judge3":{"kind":"string","value":""},"exactly_three_caps":{"kind":"number","value":0,"string":"0"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/7336308/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: AMERICAN HOSPITAL ASSOCIATION v. Alex M. AZAR II, United States Secretary of Health and Human Services\nCourt: U.S. Court of Appeals for the District of Columbia Circuit\nDate decided: 2019-05-06\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: AMERICAN HOSPITAL ASSOCIATION v. Alex M. AZAR II, United States Secretary of Health and Human Services\\nCourt: U.S. Court of Appeals for the District of Columbia Circuit\\nDate decided: 2019-05-06\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}},{"rowIdx":2299,"cells":{"id":{"kind":"number","value":7336309,"string":"7,336,309"},"name":{"kind":"string","value":"MUSCOGEE CREEK INDIAN FREEDMEN BAND, INC. v. David BERNHARDT"},"name_abbreviation":{"kind":"string","value":"Muscogee Creek Indian Freedmen Band, Inc. v. Bernhardt"},"decision_date":{"kind":"string","value":"2019-05-06"},"docket_number":{"kind":"string","value":"Civil Action No. 18-1705 (CKK)"},"court":{"kind":"string","value":"U.S. Court of Appeals for the District of Columbia Circuit"},"casebody":{"kind":"string","value":"{\"judges\": \"Kollar, Kotelly\", \"parties\": \"\", \"opinions\": [{\"author\": \"\", \"type\": \"020lead\", \"text\": \"\", \"resource_uri\": \"https://www.courtlistener.com/api/rest/v4/opinions/7254229/\", \"author_raw\": \"\"}]}"},"judge1":{"kind":"string","value":"KOLLAR"},"judge2":{"kind":"string","value":"KOLLAR"},"judge3":{"kind":"string","value":"KOTELLY"},"exactly_three_caps":{"kind":"number","value":1,"string":"1"},"extra_judges":{"kind":"string","value":""},"judge_designations":{"kind":"string","value":"{}"},"opinions_count":{"kind":"number","value":1,"string":"1"},"majority_count":{"kind":"number","value":0,"string":"0"},"dissent_count":{"kind":"number","value":0,"string":"0"},"concurrence_count":{"kind":"number","value":0,"string":"0"},"other_count":{"kind":"number","value":1,"string":"1"},"primary_citation":{"kind":"string","value":""},"reporter":{"kind":"string","value":""},"volume":{"kind":"null"},"resource_url":{"kind":"string","value":"https://www.courtlistener.com/api/rest/v4/clusters/7336309/"},"precedential_status":{"kind":"string","value":"Published"},"010combined_count":{"kind":"number","value":0,"string":"0"},"020lead_count":{"kind":"number","value":1,"string":"1"},"030concurrence_count":{"kind":"number","value":0,"string":"0"},"035concurrenceinpart_count":{"kind":"number","value":0,"string":"0"},"040dissent_count":{"kind":"number","value":0,"string":"0"},"year":{"kind":"number","value":2019,"string":"2,019"},"month":{"kind":"number","value":5,"string":"5"},"messages":{"kind":"list like","value":[{"content":"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\n\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\nobject that encodes the following variables:\n\n- Petitioner (name, description, and general category)\n- Respondent (name, description, and general category)\n- Disposition of Case\n- Winning Party\n- Issue Area\n- Legal Provisions\n- Decision Direction\n- Lower Court Direction\n- Declaration of Unconstitutionality\n- Method (panel, en banc, or rehearing)\n- Who Appealed (original plaintiff vs. defendant)\n- Dissent Basis (procedural vs. merits — only if dissent exists)\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\n\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\nrules as closely as possible, treating the **Court of Appeals as \"the Court\"** and assuming\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\n\nTo encode these variables, start by determining the petitioner and respondent, following the\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\n\n==================================================\n1. INPUT FORMAT\n==================================================\n\nYou will receive input in two sections:\n\n[CASE_METADATA]\nCase name: <case name as in the caption>\nCourt: <name of the Court of Appeals, e.g. \"United States Court of Appeals for the Ninth Circuit\">\nDate decided: <YYYY-MM-DD or best approximation>\nOpinion type: <e.g. \"majority\", \"per curiam\", \"on-the-merits\", \"rehearing\", \"en banc\", etc.>\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\nAdditional notes: <any other metadata or summary, if provided>\n\n[CASE_TEXT]\n<full or excerpted opinion text here>\n[END_CASE]\n\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\nsubstantive discussion in the opinion.\n\n==================================================\n2. OUTPUT FORMAT\n==================================================\n\nYou must output ONLY a single JSON object with exactly these keys:\n\n- \"petitioner\"\n- \"respondent\"\n- \"case_disposition\"\n- \"winning_party\"\n- \"issue_area\"\n- \"legal_provisions\"\n- \"decision_direction\"\n- \"lower_court_direction\"\n- \"declaration_of_unconstitutionality\"\n- \"method\"\n- \"who_appealed\"\n- \"dissent_basis\" (only if the case has a dissenting opinion)\n- \"concurrence_type\" (only if the case has a concurring opinion)\n- \"concurrence_basis\" (only if the case has a concurring opinion)\n- \"justification\"\n\nSchema:\n\n- \"petitioner\": {\n \"name\": string, // short party name from caption; usually the appellant\n \"description\": string, // role and identity, e.g. \"federal criminal defendant appealing conviction\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"respondent\": {\n \"name\": string,\n \"description\": string, // e.g. \"United States as appellee\", \"private employer\", \"federal agency\"\n \"category\": integer, // 1–7 general litigant type (see Section 3.1)\n \"category_label\": string // label for the category code\n }\n\n- \"case_disposition\": {\n \"code\": integer, // must be one of the codes below\n \"label\": string\n }\n\n- \"winning_party\": {\n \"code\": integer, // 0, 1, or 2 as defined below\n \"label\": string\n }\n\n- \"issue_area\": {\n \"code\": integer, // 1–14 from the list below\n \"label\": string // short description of the main issue area\n }\n\n- \"issue_area_alt\": {\n \"code\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\n \"label\": string\n }\n\n- \"legal_provisions\": [\n {\n \"area_code\": integer, // 1–9 (law area codes below)\n \"area_label\": string,\n \"provision_text\": string // e.g. \"Fourth Amendment, search and seizure\", \"18 U.S.C. § 924(c)\"\n },\n ...\n ]\n\n- \"decision_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"lower_court_direction\": {\n \"code\": integer, // 1, 2, or 3 as defined below\n \"label\": string\n }\n\n- \"declaration_of_unconstitutionality\": {\n \"code\": integer, // 0 or 1 (see Section 3.8)\n \"label\": string // \"no\" or \"yes\"\n }\n\n- \"method\": {\n \"code\": integer, // 1–4 (see Section 3.9)\n \"label\": string\n }\n\n- \"who_appealed\": {\n \"code\": integer, // 1–4 (see Section 3.10)\n \"label\": string\n }\n\n- \"dissent_basis\": { // ONLY include if \"Has dissenting opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"concurrence_type\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"code\": integer, // 1–3 (see Section 3.12)\n \"label\": string\n }\n\n- \"concurrence_basis\": { // ONLY include if \"Has concurring opinion: Yes\" in metadata\n \"procedural\": integer, // 0–3 (see Section 3.11)\n \"merits\": integer // 0–3 (see Section 3.11)\n }\n\n- \"justification\": string // 2–4 sentences summarizing why you chose these codes.\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\n // (c) how that combination implied the decision_direction.code you chose, and\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\n\nYour entire response must be exactly one JSON object in this schema and nothing else.\n\n==================================================\n3. VARIABLE INTERPRETATION\n==================================================\n\n3.1 Petitioner and Respondent\n\n- Use the case caption, opinion type, and text to determine who is appealing.\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\n- Respondent = the party opposing the appeal (typically the appellee).\n- The \"name\" should be a reasonably short label from the caption.\n- The \"description\" should describe their role and identity (e.g., \"federal prisoner challenging sentence\",\n \"state official in civil-rights suit\", \"private corporation defendant\", \"federal agency\").\n\nFor each party, also assign a \"category\" code using this 7-category typology:\n\n1 = private business or corporation (including partnerships, sole proprietorships)\n2 = nonprofit organization, interest group, or union (as an institutional party)\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\n4 = sub-state government (city, county, municipality, school district, local official)\n5 = state government (state, governor, state agency, state official in official capacity)\n6 = tribal government or Indian nation\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\n\nChoose the category based on who the party IS, not what kind of case it is. When a government\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\n\n\n3.2 Disposition of Case\n\nCodes (Songer-style numbering):\n\n1 = affirmed (includes modified and affirmed)\n2 = reversed\n3 = reversed and remanded\n4 = vacated and remanded\n5 = affirmed in part, reversed (or vacated) in part\n6 = affirmed in part, reversed (or vacated) in part, and remanded\n7 = vacated\n8 = petition denied or appeal dismissed\n9 = stay, petition, or motion granted\n10 = certification to or from a lower court\n11 = affirmed, vacated, and remanded (without reversal)\n0 = no disposition\n\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\n or original authority (the word \"remand\" must appear in the opinion text).\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\n or vacatur (7) of the prior judgment.\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\"no disposition\").\n\n\n3.3 Winning Party\n\nCodes:\n\n0 = no favorable disposition for petitioning party apparent\n1 = petitioning party received a favorable disposition\n2 = favorable disposition for petitioning party unclear\n\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\n- A \"favorable disposition\" is one that materially improves the petitioner's position relative to the lower court judgment\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\n regardless of the case disposition.\n\n\n3.4 Issue Area\n\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\n\n1 = Criminal Procedure\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\n\n2 = Civil Rights\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\n\n3 = First Amendment\n (e.g., freedom of speech, press, association, religion, and related expression claims)\n\n4 = Due Process\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\n\n5 = Privacy\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\n\n6 = Attorneys\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\n\n7 = Unions\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\n\n8 = Economic Activity\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\n\n9 = Judicial Power\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\n\n10 = Federalism\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\n\n11 = Interstate Relations\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\n\n12 = Federal Taxation\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\n\n13 = Miscellaneous\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\n\n14 = Private Action\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\n\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\nIf multiple areas appear, choose the one most emphasized in the reasoning.\n\nIMPORTANT — AVOID MISCELLANEOUS (13):\n\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\napproximately. Before choosing 13, reconsider the following common mappings:\n\n - Medical malpractice, products liability, personal injury, breach of contract,\n admiralty, property disputes → 14 (Private Action)\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\n - Attorneys' fees, bar discipline → 6 (Attorneys)\n - Federal preemption of state law → 10 (Federalism)\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\n\nIf you DO choose issue_area.code = 13, you MUST also fill in \"issue_area_alt\" with your\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\nset \"issue_area_alt\" to the same code and label as \"issue_area\".\n\nISSUE AREA TIEBREAKING RULES:\n\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\n\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\n a civil-rights statute was violated.\n\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\n termination of benefits, property seizure in a civil case).\n\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\n primarily about whether it has the power to hear the case — i.e., the court resolves a\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\n\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\n statute preempts state regulation, use 10. If the holding is about the substance of a\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\n use 8.\n\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\n procedural fairness or property/liberty deprivation without an underlying discrimination\n allegation.\n\n\n3.5 Legal Provisions\n\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \"legal_provisions\".\n\nLaw Area codes (SCDB varLawArea):\n\n1 = Constitution (original text)\n An Article or Section of the original Constitution (not an Amendment).\n Examples: Article I (congressional power), Article II (executive power),\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\n and Credit Clause, Contracts Clause.\n\n2 = Constitutional Amendment\n Any Amendment to the Constitution, including the Bill of Rights.\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\n punishment), Fourteenth Amendment (equal protection, due process).\n\n3 = Federal Statute\n A statute enacted by Congress, cited by title and section of the U.S. Code or\n by its popular name. This is the most common category.\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\n\n4 = Court Rules\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\n Procedure, as well as local circuit rules.\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\n (prejudicial evidence).\n\n5 = Other\n Common law doctrines, equitable principles, or other legal authorities not fitting\n the categories above.\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\n of laches, implied contracts.\n\n6 = Infrequently litigated statutes\n Federal statutes that appear rarely in appellate litigation and are not well-known\n by popular name. Use this when the statute is obscure or highly specialized.\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\n obscure provisions of the Internal Revenue Code.\n\n8 = State or local law or regulation\n A state statute, state constitutional provision, local ordinance, or state/local\n regulation. Use this when the court applies or interprets state or local law rather\n than federal law.\n Examples: state tort law, state contract law, state criminal statute, local zoning\n ordinance, state environmental regulation.\n\n9 = No Legal Provision\n The opinion does not meaningfully rely on any identifiable legal provision. Very\n rare — use only when the court's analysis is purely factual or procedural without\n citing specific legal authority.\n\nFor each entry:\n- `area_code`: choose the single best area for the provision.\n- `area_label`: the corresponding label (e.g., \"Constitution\", \"Federal Statute\").\n- `provision_text`: identify the specific provision (e.g., \"Fourth Amendment, search and seizure\",\n \"42 U.S.C. § 1983\", \"Federal Rule of Civil Procedure 12(b)(6)\", \"state tort law\").\n\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\n\nDistinguishing area codes:\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\n- Use 5 for common law doctrines that are not codified in any statute or rule.\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\n\n\n3.6 Decision Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\nCRITICAL: The codes \"conservative\" and \"liberal\" are MECHANICAL LABELS defined by the SCDB\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\nTaxation case, regardless of the policy context. A decision upholding a government regulation\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\nbusiness. Do NOT let your general understanding of politics override these rules.\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\n\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\n\nissue_area.code | benefiting side | direction\n----------------|------------------------------------------------------------|----------\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\n | regulation, or small entities against large business |\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\n10 (Federalism) | federal authority over state authority | 2 (liberal)\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\n | with one of the patterns above |\n\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\nissue_area, and LAST look up the decision_direction from the table above by matching the\nissue_area.code with the side that benefited. Do NOT reason about direction from first\nprinciples — use the table.\n\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\n\n\n3.6.1 Worked Examples\n\nThe following three examples demonstrate correct mechanical application of the direction\nlookup table, including cases where the SCDB coding may seem counterintuitive:\n\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\n\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\n\n Coding:\n issue_area.code = 12 (Federal Taxation)\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\n says \"taxpayer → 1 (conservative)\"\n\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\n codes this as conservative (1) because the taxpayer benefited.\n\n\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\n\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\n\n Coding:\n issue_area.code = 1 (Criminal Procedure)\n winning_party.code = 0 (no favorable disposition for petitioner)\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\n row for code 1 says \"prosecution → 1 (conservative)\"\n\n\nEXAMPLE C — Economic Activity (issue_area.code = 8)\n\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\n affirms, upholding the regulation as within the agency's statutory authority.\n\n Coding:\n issue_area.code = 8 (Economic Activity)\n winning_party.code = 0 (no favorable disposition for petitioner/company)\n decision_direction = 2 (liberal) ← government regulation upheld against business;\n lookup table row for code 8 says \"govt regulation → 2 (liberal)\"\n\n NOTE: Even if one might view upholding a regulation as a \"pro-business\" outcome (e.g., it\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\n over a business challenge as liberal (2).\n\n\n3.6.2 Internal Consistency Check\n\nBefore you output the JSON, you MUST run the following consistency check:\n\n1. Identify issue_area.code.\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\n4. Verify that your decision_direction.code matches the table entry.\n5. If it does not match, CORRECT decision_direction.code to match the table.\n\n\n3.7 Lower Court Direction\n\nCodes:\n\n1 = conservative\n2 = liberal\n3 = unspecifiable\n\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\ncourt's judgment and the appellate court's disposition.\n\nUse this rule of thumb:\n\n1. First, identify the appellate disposition (case_disposition.code).\n2. Next, identify the decision_direction.code for the Court of Appeals.\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\n\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \"affirmed\"\n or 8 \"petition denied or appeal dismissed\"), then the lower court's direction is the SAME as decision_direction.code.\n\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \"reversed\",\n 3 \"reversed and remanded\", 4 \"vacated and remanded\", or 7 \"vacated\"), then the lower court's direction is the\n OPPOSITE of decision_direction.code.\n\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\n the lower court's direction should usually be the SAME as decision_direction.code.\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\n\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\n the lower court if possible; if not, use 3 (unspecifiable).\n\nWhen you set lower_court_direction, remember:\n- \"SAME\" means lower_court_direction.code = decision_direction.code.\n- \"OPPOSITE\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\n\n3.8 Declaration of Unconstitutionality\n\nCodes:\n\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\n1 = the court DID declare a statute, regulation, or government action unconstitutional\n\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\nregulations, state statutes, state constitutional provisions, and local ordinances.\n\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\nhold that something is unconstitutional. If the court upholds the constitutionality of the\nchallenged provision, code 0.\n\n\n3.9 Method\n\nCodes:\n\n1 = standard panel decision (typically 3 judges, first hearing)\n2 = panel rehearing (same panel reconsidering its prior decision)\n3 = en banc (full court or en banc panel rehearing a case)\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\n\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\nstatements like \"before the court en banc,\" \"on rehearing,\" \"upon reconsideration,\" or\n\"per curiam.\" If the metadata indicates more than 3 judges participated, this strongly\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\n\n\n3.10 Who Appealed\n\nCodes:\n\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\n3 = federal government on behalf of the original plaintiff\n4 = federal government on behalf of the original defendant\n\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\nhistory. The \"original plaintiff\" is the party who filed suit in the lower court; the \"original\ndefendant\" is the party who was sued. In criminal cases, the original plaintiff is typically the\ngovernment (prosecution) and the original defendant is the accused.\n\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\nordering (appellant is typically listed first).\n\n\n3.11 Dissent/Concurrence Basis (Conditional)\n\nIf the case metadata states \"Has dissenting opinion: Yes\" or \"Has concurring opinion: Yes\",\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\n\nFor each dimension (procedural / merits), use one of these codes:\n\n0 = the dissent/concurrence exists but does NOT address this type of issue\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\n3 = addresses an issue NOT discussed by the majority opinion\n\n\"dissent_basis\" (include ONLY if \"Has dissenting opinion: Yes\"):\n - \"procedural\": Does the dissent address procedural questions (jurisdiction, standing,\n standard of review, procedural default, timeliness, etc.)?\n - \"merits\": Does the dissent address the substantive legal merits (statutory interpretation,\n constitutional analysis, factual sufficiency, etc.)?\n\n\"concurrence_basis\" (include ONLY if \"Has concurring opinion: Yes\"):\n - \"procedural\": Does the concurrence address procedural questions?\n - \"merits\": Does the concurrence address the substantive legal merits?\n\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\n(the longest or most substantive).\n\nIf the metadata says \"Has dissenting opinion: No\", OMIT \"dissent_basis\" entirely from your output.\nIf the metadata says \"Has concurring opinion: No\", OMIT \"concurrence_type\" and \"concurrence_basis\" entirely from your output.\n\n\n3.12 Concurrence Type (Conditional)\n\nIf the case metadata states \"Has concurring opinion: Yes\", classify the concurrence as one of\nthe following types:\n\nCodes:\n\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\n\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\n like \"concurring in the result,\" \"concurring in the judgment,\" \"concurring in the result\n only,\" or \"I concur in the judgment but write separately because I disagree with the\n majority's analysis.\" The key indicator: the judge explicitly declines to join the majority\n opinion or distances themselves from the majority's reasoning.\n\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\n the majority opinion or only the result.\n\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\nwrites a special concurrence is qualitatively different from one where all judges agree on\nboth outcome and reasoning.\n\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\nmost substantive). If one is a regular concurrence and another is a special concurrence,\ncode based on the special concurrence (code 2), as it is more analytically informative.\n\n\n==================================================\n4. GENERAL RULES\n==================================================\n\n- Use metadata (case name, court, date, opinion type) to:\n - distinguish main merits opinions from rehearing or procedural opinions,\n - interpret how the appellate disposition relates to the prior judgment,\n - infer whether the case is criminal, civil rights, tax, etc.\n- If some information is missing, use the appropriate \"unspecifiable\" or \"no disposition\" code\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\n- Carefully follow the steps laid out in the introduction in order. In particular,\n decide who won the case (winning_party). Then, decide what the issue_area is.\n Only choose decision_direction once you have completed those steps, and follow the exact\n directions in Section 3.6.\n- In the justification, explicitly state who won, why (according to the disposition), and\n how that winner and the issue_area code together implied the direction code you chose.\n Reference the DIRECTION LOOKUP TABLE row you applied.\n- ALWAYS choose exactly one code for each coded variable where required.\n- NEVER output any keys other than the ones defined in the schema above.\n- Include \"dissent_basis\", \"concurrence_type\", and \"concurrence_basis\" ONLY when the metadata\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\n- NEVER output any numeric codes outside the permitted lists above.\n\n\n==================================================\n5. FINAL REQUIREMENT\n==================================================\n\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\n","role":"system"},{"content":"[CASE_METADATA]\nCase name: MUSCOGEE CREEK INDIAN FREEDMEN BAND, INC. v. David BERNHARDT\nCourt: U.S. Court of Appeals for the District of Columbia Circuit\nDate decided: 2019-05-06\nOpinion type: majority\nHas dissenting opinion: No\nHas concurring opinion: No\nAdditional notes: \n\n[CASE_TEXT]\n\n[END_CASE]","role":"user"}],"string":"[\n {\n \"content\": \"You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\\nin the codebook step by step and use the precise definitions of terms presented in the codebook below.\\n\\nYour task: Given metadata and text for a single federal appellate case, output a single JSON\\nobject that encodes the following variables:\\n\\n- Petitioner (name, description, and general category)\\n- Respondent (name, description, and general category)\\n- Disposition of Case\\n- Winning Party\\n- Issue Area\\n- Legal Provisions\\n- Decision Direction\\n- Lower Court Direction\\n- Declaration of Unconstitutionality\\n- Method (panel, en banc, or rehearing)\\n- Who Appealed (original plaintiff vs. defendant)\\n- Dissent Basis (procedural vs. merits — only if dissent exists)\\n- Concurrence Type (regular vs. special/result-only — only if concurrence exists)\\n- Concurrence Basis (procedural vs. merits — only if concurrence exists)\\n\\nYou are working with U.S. Courts of Appeals, not the Supreme Court. Apply the SCDB coding\\nrules as closely as possible, treating the **Court of Appeals as \\\"the Court\\\"** and assuming\\nthat the **lower court is, e.g., a federal district court** whose decision is being reviewed.\\n\\nTo encode these variables, start by determining the petitioner and respondent, following the\\ninstructions in Section 3.1. Then, find the disposition of the case and code it according\\nto Section 3.2. Knowing the disposition will guide your next step: determining if the petitioner\\nwas the winning party, following the directions in Section 3.3. Next, use the overall opinion content\\nto code the issue area as described in Section 3.4. This step will also inform the legal provisions\\ncoding as laid out in Section 3.5. With the winning party, disposition, and issue area fixed,\\ncarefully and precisely follow the directions in Section 3.6 to assign a decision direction for the opinion.\\nBased on that decision direction and the disposition, you can assign a lower court direction as well,\\nfollowing Section 3.7. Finally, justify your decisions in the manner described below.\\n\\n==================================================\\n1. INPUT FORMAT\\n==================================================\\n\\nYou will receive input in two sections:\\n\\n[CASE_METADATA]\\nCase name: <case name as in the caption>\\nCourt: <name of the Court of Appeals, e.g. \\\"United States Court of Appeals for the Ninth Circuit\\\">\\nDate decided: <YYYY-MM-DD or best approximation>\\nOpinion type: <e.g. \\\"majority\\\", \\\"per curiam\\\", \\\"on-the-merits\\\", \\\"rehearing\\\", \\\"en banc\\\", etc.>\\nHas dissenting opinion: <Yes or No, based on whether the input data contains a separate dissent>\\nHas concurring opinion: <Yes or No, based on whether the input data contains a separate concurrence>\\nAdditional notes: <any other metadata or summary, if provided>\\n\\n[CASE_TEXT]\\n<full or excerpted opinion text here>\\n[END_CASE]\\n\\nUse both metadata and text to code the variables. If metadata and text conflict, prefer the\\nsubstantive discussion in the opinion.\\n\\n==================================================\\n2. OUTPUT FORMAT\\n==================================================\\n\\nYou must output ONLY a single JSON object with exactly these keys:\\n\\n- \\\"petitioner\\\"\\n- \\\"respondent\\\"\\n- \\\"case_disposition\\\"\\n- \\\"winning_party\\\"\\n- \\\"issue_area\\\"\\n- \\\"legal_provisions\\\"\\n- \\\"decision_direction\\\"\\n- \\\"lower_court_direction\\\"\\n- \\\"declaration_of_unconstitutionality\\\"\\n- \\\"method\\\"\\n- \\\"who_appealed\\\"\\n- \\\"dissent_basis\\\" (only if the case has a dissenting opinion)\\n- \\\"concurrence_type\\\" (only if the case has a concurring opinion)\\n- \\\"concurrence_basis\\\" (only if the case has a concurring opinion)\\n- \\\"justification\\\"\\n\\nSchema:\\n\\n- \\\"petitioner\\\": {\\n \\\"name\\\": string, // short party name from caption; usually the appellant\\n \\\"description\\\": string, // role and identity, e.g. \\\"federal criminal defendant appealing conviction\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"respondent\\\": {\\n \\\"name\\\": string,\\n \\\"description\\\": string, // e.g. \\\"United States as appellee\\\", \\\"private employer\\\", \\\"federal agency\\\"\\n \\\"category\\\": integer, // 1–7 general litigant type (see Section 3.1)\\n \\\"category_label\\\": string // label for the category code\\n }\\n\\n- \\\"case_disposition\\\": {\\n \\\"code\\\": integer, // must be one of the codes below\\n \\\"label\\\": string\\n }\\n\\n- \\\"winning_party\\\": {\\n \\\"code\\\": integer, // 0, 1, or 2 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"issue_area\\\": {\\n \\\"code\\\": integer, // 1–14 from the list below\\n \\\"label\\\": string // short description of the main issue area\\n }\\n\\n- \\\"issue_area_alt\\\": {\\n \\\"code\\\": integer, // 1–14; your best non-Misc alternative if issue_area.code == 13, else same as issue_area.code\\n \\\"label\\\": string\\n }\\n\\n- \\\"legal_provisions\\\": [\\n {\\n \\\"area_code\\\": integer, // 1–9 (law area codes below)\\n \\\"area_label\\\": string,\\n \\\"provision_text\\\": string // e.g. \\\"Fourth Amendment, search and seizure\\\", \\\"18 U.S.C. § 924(c)\\\"\\n },\\n ...\\n ]\\n\\n- \\\"decision_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"lower_court_direction\\\": {\\n \\\"code\\\": integer, // 1, 2, or 3 as defined below\\n \\\"label\\\": string\\n }\\n\\n- \\\"declaration_of_unconstitutionality\\\": {\\n \\\"code\\\": integer, // 0 or 1 (see Section 3.8)\\n \\\"label\\\": string // \\\"no\\\" or \\\"yes\\\"\\n }\\n\\n- \\\"method\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.9)\\n \\\"label\\\": string\\n }\\n\\n- \\\"who_appealed\\\": {\\n \\\"code\\\": integer, // 1–4 (see Section 3.10)\\n \\\"label\\\": string\\n }\\n\\n- \\\"dissent_basis\\\": { // ONLY include if \\\"Has dissenting opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"concurrence_type\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"code\\\": integer, // 1–3 (see Section 3.12)\\n \\\"label\\\": string\\n }\\n\\n- \\\"concurrence_basis\\\": { // ONLY include if \\\"Has concurring opinion: Yes\\\" in metadata\\n \\\"procedural\\\": integer, // 0–3 (see Section 3.11)\\n \\\"merits\\\": integer // 0–3 (see Section 3.11)\\n }\\n\\n- \\\"justification\\\": string // 2–4 sentences summarizing why you chose these codes.\\n // You MUST explicitly say: (a) who won and why, (b) what issue_area.code is,\\n // (c) how that combination implied the decision_direction.code you chose, and\\n // (d) why the lower_court_direction is the same as or opposite to decision_direction.\\n\\nYour entire response must be exactly one JSON object in this schema and nothing else.\\n\\n==================================================\\n3. VARIABLE INTERPRETATION\\n==================================================\\n\\n3.1 Petitioner and Respondent\\n\\n- Use the case caption, opinion type, and text to determine who is appealing.\\n- Petitioner = the party seeking relief in the Court of Appeals (typically the appellant).\\n- Respondent = the party opposing the appeal (typically the appellee).\\n- The \\\"name\\\" should be a reasonably short label from the caption.\\n- The \\\"description\\\" should describe their role and identity (e.g., \\\"federal prisoner challenging sentence\\\",\\n \\\"state official in civil-rights suit\\\", \\\"private corporation defendant\\\", \\\"federal agency\\\").\\n\\nFor each party, also assign a \\\"category\\\" code using this 7-category typology:\\n\\n1 = private business or corporation (including partnerships, sole proprietorships)\\n2 = nonprofit organization, interest group, or union (as an institutional party)\\n3 = federal government (including U.S. as party, federal agencies like DOJ, IRS, EPA, SEC, NLRB, etc.)\\n4 = sub-state government (city, county, municipality, school district, local official)\\n5 = state government (state, governor, state agency, state official in official capacity)\\n6 = tribal government or Indian nation\\n7 = natural person (individual, including pro se litigants and individual officials sued personally)\\n\\nChoose the category based on who the party IS, not what kind of case it is. When a government\\nofficial is sued in their official capacity, code them as the relevant government level (3, 4, or 5).\\nWhen sued in their personal/individual capacity, code them as 7 (natural person).\\n\\n\\n3.2 Disposition of Case\\n\\nCodes (Songer-style numbering):\\n\\n1 = affirmed (includes modified and affirmed)\\n2 = reversed\\n3 = reversed and remanded\\n4 = vacated and remanded\\n5 = affirmed in part, reversed (or vacated) in part\\n6 = affirmed in part, reversed (or vacated) in part, and remanded\\n7 = vacated\\n8 = petition denied or appeal dismissed\\n9 = stay, petition, or motion granted\\n10 = certification to or from a lower court\\n11 = affirmed, vacated, and remanded (without reversal)\\n0 = no disposition\\n\\n- Use the text and opinion type (majority, rehearing, etc.) to identify what the Court of Appeals actually did.\\n- Only choose options 3, 4, or 6 if the opinion contains explicit instructions to remand the matter to the lower court\\n or original authority (the word \\\"remand\\\" must appear in the opinion text).\\n- For rehearing petitions, be explicit about whether the petition is granted (9), denied (8), or leads to modification\\n or vacatur (7) of the prior judgment.\\n- If the Court takes no substantive action on the merits (e.g., purely procedural opinion), use 0 (\\\"no disposition\\\").\\n\\n\\n3.3 Winning Party\\n\\nCodes:\\n\\n0 = no favorable disposition for petitioning party apparent\\n1 = petitioning party received a favorable disposition\\n2 = favorable disposition for petitioning party unclear\\n\\n- Treat the **petitioner** as the party seeking relief in the Court of Appeals.\\n- A \\\"favorable disposition\\\" is one that materially improves the petitioner's position relative to the lower court judgment\\n (e.g., reversal, vacatur, remand requiring relief, sentence reduction).\\n- For mixed outcomes (e.g., affirmed in part and reversed in part), assess whether, on balance, the petitioner is better off.\\n If clearly better off, use 1; if clearly not better off, use 0; if ambiguous, use 2.\\n- Note that an outcome favoring the petitioning party may be either an affirmation (if the lower court had ruled in favor of the petitioner)\\n OR a reversal (if the lower court had ruled against the petitioner). You should focus on whether the petitioner is better off,\\n regardless of the case disposition.\\n\\n\\n3.4 Issue Area\\n\\nChoose exactly one code and label from this list, based on the main legal/policy issue in the appeal:\\n\\n1 = Criminal Procedure\\n (e.g., search and seizure, arrest, interrogation, right to counsel, trial and sentencing rules, habeas)\\n\\n2 = Civil Rights\\n (e.g., equal protection, discrimination based on race or other protected traits, voting rights, school desegregation)\\n\\n3 = First Amendment\\n (e.g., freedom of speech, press, association, religion, and related expression claims)\\n\\n4 = Due Process\\n (e.g., non-criminal procedural fairness, property or liberty deprivations, economic regulation challenges framed as due process)\\n\\n5 = Privacy\\n (e.g., contraception, abortion, family relationships, intimate or sexual privacy, personal autonomy)\\n\\n6 = Attorneys\\n (e.g., attorney's fees, sanctions, bar admission and discipline, representation issues)\\n\\n7 = Unions\\n (e.g., labor relations, union membership and internal affairs, collective bargaining, union security)\\n\\n8 = Economic Activity\\n (e.g., antitrust, securities, regulation of business, commercial law, bankruptcy, financial regulation)\\n\\n9 = Judicial Power\\n (e.g., jurisdiction, standing, mootness, justiciability, sovereign immunity, standards of review, appellate procedure)\\n\\n10 = Federalism\\n (e.g., conflicts between federal and state authority, preemption, Tenth Amendment issues, state sovereign immunity vs federal power)\\n\\n11 = Interstate Relations\\n (e.g., disputes between states, boundary and water disputes, interstate compacts and obligations)\\n\\n12 = Federal Taxation\\n (e.g., federal income, corporate, estate, excise, and other federal tax issues)\\n\\n13 = Miscellaneous\\n (cases that genuinely do not fit any other issue area — see IMPORTANT note below)\\n\\n14 = Private Action\\n (e.g., private law disputes in property, contracts, torts, wills, estates, and similar matters)\\n\\nPick the **single best** issue area based on what the Court of Appeals treats as the central question.\\nIf multiple areas appear, choose the one most emphasized in the reasoning.\\n\\nIMPORTANT — AVOID MISCELLANEOUS (13):\\n\\nCode 13 should be used ONLY as a genuine last resort when NO other category applies even\\napproximately. Before choosing 13, reconsider the following common mappings:\\n\\n - Medical malpractice, products liability, personal injury, breach of contract,\\n admiralty, property disputes → 14 (Private Action)\\n - Workers' compensation (LHWCA, FELA, Longshore Act) → 7 (Unions) or 14 (Private Action)\\n - Bankruptcy, securities, antitrust, business regulation → 8 (Economic Activity)\\n - Social Security, disability, welfare benefits → 2 (Civil Rights)\\n - Attorneys' fees, bar discipline → 6 (Attorneys)\\n - Federal preemption of state law → 10 (Federalism)\\n - Procedural rehearing or jurisdictional questions → 9 (Judicial Power)\\n - Separation of powers, legislative veto → 13 (Miscellaneous) — this is a genuine use\\n\\nIf you DO choose issue_area.code = 13, you MUST also fill in \\\"issue_area_alt\\\" with your\\nbest-guess alternative code (the closest non-Misc category). If issue_area.code is not 13,\\nset \\\"issue_area_alt\\\" to the same code and label as \\\"issue_area\\\".\\n\\nISSUE AREA TIEBREAKING RULES:\\n\\nWhen a case implicates more than one issue area, apply these rules to select the primary one:\\n\\n- Criminal Procedure (1) vs. Civil Rights (2): If the court's holding concerns criminal\\n conviction, sentencing, or procedure itself (e.g., suppression of evidence, habeas review of\\n a conviction), use 1 even if discrimination or civil-rights statutes are mentioned. Use 2\\n only when the holding primarily addresses whether discriminatory treatment occurred or whether\\n a civil-rights statute was violated.\\n\\n- Criminal Procedure (1) vs. Due Process (4): If the party is a criminal defendant raising\\n due-process claims about trial procedure, sentencing, or conditions of confinement, use 1.\\n Use 4 only when the due-process claim arises in a non-criminal context (e.g., government\\n termination of benefits, property seizure in a civil case).\\n\\n- Judicial Power (9) vs. any other area: Many cases discuss jurisdiction, standing, or\\n justiciability before reaching the merits. Use 9 ONLY when the court's holding is\\n primarily about whether it has the power to hear the case — i.e., the court resolves a\\n jurisdictional or justiciability question and that resolution IS the outcome. If the court\\n establishes jurisdiction and then rules on the merits, use the substantive merits area instead.\\n\\n- Economic Activity (8) vs. Federalism (10): If the holding is about whether a federal\\n statute preempts state regulation, use 10. If the holding is about the substance of a\\n federal regulatory scheme (e.g., upholding or striking down an EPA rule on the merits),\\n use 8.\\n\\n- Civil Rights (2) vs. Due Process (4): If the claim involves alleged discrimination under\\n equal protection or a civil-rights statute, use 2. Use 4 only when the claim is about\\n procedural fairness or property/liberty deprivation without an underlying discrimination\\n allegation.\\n\\n\\n3.5 Legal Provisions\\n\\nFor each major legal provision the Court of Appeals applies or interprets, add an entry to \\\"legal_provisions\\\".\\n\\nLaw Area codes (SCDB varLawArea):\\n\\n1 = Constitution (original text)\\n An Article or Section of the original Constitution (not an Amendment).\\n Examples: Article I (congressional power), Article II (executive power),\\n Article III (judicial power), Supremacy Clause, Commerce Clause, Full Faith\\n and Credit Clause, Contracts Clause.\\n\\n2 = Constitutional Amendment\\n Any Amendment to the Constitution, including the Bill of Rights.\\n Examples: First Amendment (speech, religion), Fourth Amendment (search and\\n seizure), Fifth Amendment (due process, takings, self-incrimination), Sixth\\n Amendment (right to counsel, jury trial), Eighth Amendment (cruel and unusual\\n punishment), Fourteenth Amendment (equal protection, due process).\\n\\n3 = Federal Statute\\n A statute enacted by Congress, cited by title and section of the U.S. Code or\\n by its popular name. This is the most common category.\\n Examples: 42 U.S.C. § 1983 (civil rights), 28 U.S.C. § 1331 (federal question\\n jurisdiction), Title VII of the Civil Rights Act, Sherman Act § 1 (antitrust),\\n 18 U.S.C. § 924(c) (firearms), ERISA, CERCLA, ADA, FOIA, Sentencing Guidelines.\\n\\n4 = Court Rules\\n Federal Rules of Civil Procedure, Criminal Procedure, Evidence, or Appellate\\n Procedure, as well as local circuit rules.\\n Examples: Fed. R. Civ. P. 12(b)(6) (failure to state a claim), Fed. R. Civ. P.\\n 56 (summary judgment), Fed. R. Crim. P. 11 (plea agreements), Fed. R. Evid. 403\\n (prejudicial evidence).\\n\\n5 = Other\\n Common law doctrines, equitable principles, or other legal authorities not fitting\\n the categories above.\\n Examples: common law fraud, maritime law (general), equitable estoppel, doctrine\\n of laches, implied contracts.\\n\\n6 = Infrequently litigated statutes\\n Federal statutes that appear rarely in appellate litigation and are not well-known\\n by popular name. Use this when the statute is obscure or highly specialized.\\n Examples: Railway Labor Act, Packers and Stockyards Act, Suits in Admiralty Act,\\n obscure provisions of the Internal Revenue Code.\\n\\n8 = State or local law or regulation\\n A state statute, state constitutional provision, local ordinance, or state/local\\n regulation. Use this when the court applies or interprets state or local law rather\\n than federal law.\\n Examples: state tort law, state contract law, state criminal statute, local zoning\\n ordinance, state environmental regulation.\\n\\n9 = No Legal Provision\\n The opinion does not meaningfully rely on any identifiable legal provision. Very\\n rare — use only when the court's analysis is purely factual or procedural without\\n citing specific legal authority.\\n\\nFor each entry:\\n- `area_code`: choose the single best area for the provision.\\n- `area_label`: the corresponding label (e.g., \\\"Constitution\\\", \\\"Federal Statute\\\").\\n- `provision_text`: identify the specific provision (e.g., \\\"Fourth Amendment, search and seizure\\\",\\n \\\"42 U.S.C. § 1983\\\", \\\"Federal Rule of Civil Procedure 12(b)(6)\\\", \\\"state tort law\\\").\\n\\nInclude the one to three provisions central to the court's analysis. If the opinion does not meaningfully\\nrely on any legal provision (very rare), use a single entry with area_code 9 and a brief explanation.\\n\\nDistinguishing area codes:\\n- If the court interprets the CONSTITUTION ITSELF (e.g., Commerce Clause), use 1.\\n- If the court interprets a CONSTITUTIONAL AMENDMENT (e.g., Fourth Amendment), use 2.\\n- If the court interprets a FEDERAL STATUTE (the most common scenario), use 3.\\n- If the dispute is about a PROCEDURAL RULE (e.g., Rule 12(b)(6) motion), use 4.\\n- Use 8 for STATE LAW even if the case is in federal court on diversity jurisdiction.\\n- Use 5 for common law doctrines that are not codified in any statute or rule.\\n- Use 6 only for genuinely obscure federal statutes that would not be recognized by name.\\n\\n\\n3.6 Decision Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\n>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\\nCRITICAL: The codes \\\"conservative\\\" and \\\"liberal\\\" are MECHANICAL LABELS defined by the SCDB\\ncodebook. They are NOT your own assessment of political ideology. You MUST apply them exactly\\nas the lookup table below specifies, even when the result seems counterintuitive. For example,\\na decision favoring a taxpayer over the IRS is ALWAYS coded conservative (1) in a Federal\\nTaxation case, regardless of the policy context. A decision upholding a government regulation\\nis ALWAYS coded liberal (2) in an Economic Activity case, even if the regulation benefits\\nbusiness. Do NOT let your general understanding of politics override these rules.\\n<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<\\n\\nDIRECTION LOOKUP TABLE — apply mechanically based on issue_area.code and who benefits:\\n\\nissue_area.code | benefiting side | direction\\n----------------|------------------------------------------------------------|----------\\n1 (Crim. Pro.) | accused / convicted person / criminal defendant | 2 (liberal)\\n1 (Crim. Pro.) | prosecution / law enforcement / government | 1 (conservative)\\n2 (Civ. Rts.) | civil rights or civil liberties claimant | 2 (liberal)\\n2 (Civ. Rts.) | government defendant / party opposing civil rights claim | 1 (conservative)\\n3 (1st Amend.) | person asserting First Amendment protections | 2 (liberal)\\n3 (1st Amend.) | government restricting speech, press, religion, etc. | 1 (conservative)\\n4 (Due Proc.) | individual challenging deprivation of liberty or property | 2 (liberal)\\n4 (Due Proc.) | government upholding deprivation | 1 (conservative)\\n5 (Privacy) | person asserting privacy / autonomy / reproductive choice | 2 (liberal)\\n5 (Privacy) | government restricting privacy or autonomy | 1 (conservative)\\n7 (Unions) | union / workers / collective bargaining interests | 2 (liberal)\\n7 (Unions) | employer / management / anti-union interests | 1 (conservative)\\n8 (Econ. Act.) | workers, consumers, injured parties, environment, govt | 2 (liberal)\\n | regulation, or small entities against large business |\\n8 (Econ. Act.) | employers, large business, property owners, deregulation | 1 (conservative)\\n9 (Jud. Power) | broader court access / standing / review | 2 (liberal)\\n9 (Jud. Power) | narrower court access / standing / review | 1 (conservative)\\n10 (Federalism) | federal authority over state authority | 2 (liberal)\\n10 (Federalism) | state sovereignty over federal power | 1 (conservative)\\n12 (Fed. Tax.) | United States / IRS / federal taxing authority | 2 (liberal)\\n12 (Fed. Tax.) | taxpayer | 1 (conservative)\\n11,14 | use 3 (unspecifiable) unless decision clearly aligns | 3 (unspecifiable)\\n | with one of the patterns above |\\n\\nPROCEDURE: You MUST FIRST determine who won the case (winning_party), THEN identify the\\nissue_area, and LAST look up the decision_direction from the table above by matching the\\nissue_area.code with the side that benefited. Do NOT reason about direction from first\\nprinciples — use the table.\\n\\nIf, after applying the table, you cannot determine which side benefited, use 3 (unspecifiable).\\n\\n\\n3.6.1 Worked Examples\\n\\nThe following three examples demonstrate correct mechanical application of the direction\\nlookup table, including cases where the SCDB coding may seem counterintuitive:\\n\\nEXAMPLE A — Federal Taxation (issue_area.code = 12)\\n\\n Facts: A taxpayer appeals an IRS assessment to the Court of Appeals. The court reverses the\\n Tax Court, holding that the taxpayer's deductions were proper and the assessment was incorrect.\\n\\n Coding:\\n issue_area.code = 12 (Federal Taxation)\\n winning_party.code = 1 (petitioner/taxpayer received favorable disposition)\\n decision_direction = 1 (conservative) ← taxpayer won; lookup table row for code 12\\n says \\\"taxpayer → 1 (conservative)\\\"\\n\\n NOTE: Even though the taxpayer prevailed against the government, the SCDB mechanically\\n codes this as conservative (1) because the taxpayer benefited.\\n\\n\\nEXAMPLE B — Criminal Procedure (issue_area.code = 1)\\n\\n Facts: A criminal defendant appeals his conviction, arguing that evidence was obtained\\n through an unlawful search. The Court of Appeals affirms, holding the search was lawful.\\n\\n Coding:\\n issue_area.code = 1 (Criminal Procedure)\\n winning_party.code = 0 (no favorable disposition for petitioner)\\n decision_direction = 1 (conservative) ← prosecution/government benefited; lookup table\\n row for code 1 says \\\"prosecution → 1 (conservative)\\\"\\n\\n\\nEXAMPLE C — Economic Activity (issue_area.code = 8)\\n\\n Facts: A chemical company challenges an EPA water-quality regulation. The Court of Appeals\\n affirms, upholding the regulation as within the agency's statutory authority.\\n\\n Coding:\\n issue_area.code = 8 (Economic Activity)\\n winning_party.code = 0 (no favorable disposition for petitioner/company)\\n decision_direction = 2 (liberal) ← government regulation upheld against business;\\n lookup table row for code 8 says \\\"govt regulation → 2 (liberal)\\\"\\n\\n NOTE: Even if one might view upholding a regulation as a \\\"pro-business\\\" outcome (e.g., it\\n creates regulatory certainty), the SCDB mechanically codes government regulation prevailing\\n over a business challenge as liberal (2).\\n\\n\\n3.6.2 Internal Consistency Check\\n\\nBefore you output the JSON, you MUST run the following consistency check:\\n\\n1. Identify issue_area.code.\\n2. Identify which side won in the case (petitioner vs respondent) and what kind of party they are.\\n3. Look up the corresponding row in the DIRECTION LOOKUP TABLE above.\\n4. Verify that your decision_direction.code matches the table entry.\\n5. If it does not match, CORRECT decision_direction.code to match the table.\\n\\n\\n3.7 Lower Court Direction\\n\\nCodes:\\n\\n1 = conservative\\n2 = liberal\\n3 = unspecifiable\\n\\nUse the same DIRECTION LOOKUP TABLE as for Decision Direction (see Section 3.6), but applied to\\nthe **lower court's outcome**. You MUST determine the lower court's direction by comparing the lower\\ncourt's judgment and the appellate court's disposition.\\n\\nUse this rule of thumb:\\n\\n1. First, identify the appellate disposition (case_disposition.code).\\n2. Next, identify the decision_direction.code for the Court of Appeals.\\n3. Last, infer who benefited in the lower court and assign lower_court_direction as follows:\\n\\n- If the Court of Appeals clearly **leaves the lower court judgment in place** (e.g., case_disposition.code = 1 \\\"affirmed\\\"\\n or 8 \\\"petition denied or appeal dismissed\\\"), then the lower court's direction is the SAME as decision_direction.code.\\n\\n- If the Court of Appeals clearly **undoes the lower court judgment** (e.g., case_disposition.code = 2 \\\"reversed\\\",\\n 3 \\\"reversed and remanded\\\", 4 \\\"vacated and remanded\\\", or 7 \\\"vacated\\\"), then the lower court's direction is the\\n OPPOSITE of decision_direction.code.\\n\\n- For mixed outcomes (case_disposition.code = 5 or 6), compare who won more in the lower court vs on appeal:\\n * If, on balance, the petitioner is better off after the appeal than under the lower court judgment, then\\n the lower court's direction should usually be the OPPOSITE of decision_direction.code.\\n * If, on balance, the petitioner is worse off or no better off than under the lower court judgment, then\\n the lower court's direction should usually be the SAME as decision_direction.code.\\n * If you cannot determine who benefited more from the lower court judgment even approximately, use 3 (unspecifiable).\\n\\n- For stays, motions, certifications, or purely procedural dispositions (codes 9, 10, 0), infer who benefited in\\n the lower court if possible; if not, use 3 (unspecifiable).\\n\\nWhen you set lower_court_direction, remember:\\n- \\\"SAME\\\" means lower_court_direction.code = decision_direction.code.\\n- \\\"OPPOSITE\\\" means: if decision_direction.code = 1 (conservative), then lower_court_direction.code = 2 (liberal);\\n if decision_direction.code = 2 (liberal), then lower_court_direction.code = 1 (conservative).\\n\\n3.8 Declaration of Unconstitutionality\\n\\nCodes:\\n\\n0 = the court did NOT strike down any statute, regulation, or government action as unconstitutional\\n1 = the court DID declare a statute, regulation, or government action unconstitutional\\n\\nCode 1 if the court holds that a law, regulation, executive action, or government practice violates\\nthe Constitution (whether facial or as-applied). This includes striking down acts of Congress, federal\\nregulations, state statutes, state constitutional provisions, and local ordinances.\\n\\nDo NOT code 1 merely because the court discusses constitutional issues. The court must actually\\nhold that something is unconstitutional. If the court upholds the constitutionality of the\\nchallenged provision, code 0.\\n\\n\\n3.9 Method\\n\\nCodes:\\n\\n1 = standard panel decision (typically 3 judges, first hearing)\\n2 = panel rehearing (same panel reconsidering its prior decision)\\n3 = en banc (full court or en banc panel rehearing a case)\\n4 = per curiam (unsigned opinion — may overlap with codes 1 or 3)\\n\\nUse the opinion text, metadata, and case caption to determine the method. Look for explicit\\nstatements like \\\"before the court en banc,\\\" \\\"on rehearing,\\\" \\\"upon reconsideration,\\\" or\\n\\\"per curiam.\\\" If the metadata indicates more than 3 judges participated, this strongly\\nsuggests en banc (code 3). If none of these indicators are present, use 1 (standard panel).\\n\\n\\n3.10 Who Appealed\\n\\nCodes:\\n\\n1 = original plaintiff (or the equivalent, e.g. the Title VII complainant, habeas petitioner)\\n2 = original defendant (or the equivalent, e.g. the employer in a Title VII suit)\\n3 = federal government on behalf of the original plaintiff\\n4 = federal government on behalf of the original defendant\\n\\nDetermine who initiated the appeal by examining the case caption, opinion text, and procedural\\nhistory. The \\\"original plaintiff\\\" is the party who filed suit in the lower court; the \\\"original\\ndefendant\\\" is the party who was sued. In criminal cases, the original plaintiff is typically the\\ngovernment (prosecution) and the original defendant is the accused.\\n\\nIf the opinion describes a cross-appeal, code based on who filed the PRIMARY appeal (the one\\nthe court addresses as the main appeal). If you cannot determine who appealed, use 1 as default\\nfor criminal defendants (who are most commonly appellants) or your best judgment from the caption\\nordering (appellant is typically listed first).\\n\\n\\n3.11 Dissent/Concurrence Basis (Conditional)\\n\\nIf the case metadata states \\\"Has dissenting opinion: Yes\\\" or \\\"Has concurring opinion: Yes\\\",\\ncode whether that separate opinion addresses procedural issues, merits issues, or both.\\n\\nFor each dimension (procedural / merits), use one of these codes:\\n\\n0 = the dissent/concurrence exists but does NOT address this type of issue\\n1 = addresses the SAME issue as the majority and DISAGREES with the majority's resolution\\n2 = addresses the SAME issue as the majority and AGREES with the majority's resolution\\n3 = addresses an issue NOT discussed by the majority opinion\\n\\n\\\"dissent_basis\\\" (include ONLY if \\\"Has dissenting opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the dissent address procedural questions (jurisdiction, standing,\\n standard of review, procedural default, timeliness, etc.)?\\n - \\\"merits\\\": Does the dissent address the substantive legal merits (statutory interpretation,\\n constitutional analysis, factual sufficiency, etc.)?\\n\\n\\\"concurrence_basis\\\" (include ONLY if \\\"Has concurring opinion: Yes\\\"):\\n - \\\"procedural\\\": Does the concurrence address procedural questions?\\n - \\\"merits\\\": Does the concurrence address the substantive legal merits?\\n\\nIf multiple dissenting or concurring opinions exist, code based on the PRIMARY one\\n(the longest or most substantive).\\n\\nIf the metadata says \\\"Has dissenting opinion: No\\\", OMIT \\\"dissent_basis\\\" entirely from your output.\\nIf the metadata says \\\"Has concurring opinion: No\\\", OMIT \\\"concurrence_type\\\" and \\\"concurrence_basis\\\" entirely from your output.\\n\\n\\n3.12 Concurrence Type (Conditional)\\n\\nIf the case metadata states \\\"Has concurring opinion: Yes\\\", classify the concurrence as one of\\nthe following types:\\n\\nCodes:\\n\\n1 = regular concurrence — the concurring judge JOINED the majority opinion AND wrote or joined\\n a separate concurrence to add additional reasoning, emphasize a point, or note a limitation.\\n The key indicator: the judge agrees with BOTH the outcome AND the reasoning of the majority.\\n\\n2 = special concurrence / concurrence in result only — the concurring judge agrees with the\\n OUTCOME (disposition) but does NOT join the majority opinion's reasoning. Look for language\\n like \\\"concurring in the result,\\\" \\\"concurring in the judgment,\\\" \\\"concurring in the result\\n only,\\\" or \\\"I concur in the judgment but write separately because I disagree with the\\n majority's analysis.\\\" The key indicator: the judge explicitly declines to join the majority\\n opinion or distances themselves from the majority's reasoning.\\n\\n3 = cannot determine — the opinion text does not make clear whether the concurring judge joined\\n the majority opinion or only the result.\\n\\nThis distinction matters because special concurrences (code 2) signal reasoning disagreement\\nwithin a nominally unanimous disposition. A case where all judges agree on the outcome but one\\nwrites a special concurrence is qualitatively different from one where all judges agree on\\nboth outcome and reasoning.\\n\\nIf multiple concurring opinions exist, code based on the PRIMARY concurrence (the longest or\\nmost substantive). If one is a regular concurrence and another is a special concurrence,\\ncode based on the special concurrence (code 2), as it is more analytically informative.\\n\\n\\n==================================================\\n4. GENERAL RULES\\n==================================================\\n\\n- Use metadata (case name, court, date, opinion type) to:\\n - distinguish main merits opinions from rehearing or procedural opinions,\\n - interpret how the appellate disposition relates to the prior judgment,\\n - infer whether the case is criminal, civil rights, tax, etc.\\n- If some information is missing, use the appropriate \\\"unspecifiable\\\" or \\\"no disposition\\\" code\\n (e.g., 3 for direction, 11 for case_disposition); do not invent facts.\\n- Carefully follow the steps laid out in the introduction in order. In particular,\\n decide who won the case (winning_party). Then, decide what the issue_area is.\\n Only choose decision_direction once you have completed those steps, and follow the exact\\n directions in Section 3.6.\\n- In the justification, explicitly state who won, why (according to the disposition), and\\n how that winner and the issue_area code together implied the direction code you chose.\\n Reference the DIRECTION LOOKUP TABLE row you applied.\\n- ALWAYS choose exactly one code for each coded variable where required.\\n- NEVER output any keys other than the ones defined in the schema above.\\n- Include \\\"dissent_basis\\\", \\\"concurrence_type\\\", and \\\"concurrence_basis\\\" ONLY when the metadata\\n indicates the corresponding opinion type exists. Omit them entirely otherwise.\\n- NEVER output any numeric codes outside the permitted lists above.\\n\\n\\n==================================================\\n5. FINAL REQUIREMENT\\n==================================================\\n\\nAfter reading [CASE_METADATA] and [CASE_TEXT], respond ONLY with the JSON object in the schema\\nabove. Do not include any extra commentary, markdown, or explanation outside the JSON.\\n\",\n \"role\": \"system\"\n },\n {\n \"content\": \"[CASE_METADATA]\\nCase name: MUSCOGEE CREEK INDIAN FREEDMEN BAND, INC. v. David BERNHARDT\\nCourt: U.S. Court of Appeals for the District of Columbia Circuit\\nDate decided: 2019-05-06\\nOpinion type: majority\\nHas dissenting opinion: No\\nHas concurring opinion: No\\nAdditional notes: \\n\\n[CASE_TEXT]\\n\\n[END_CASE]\",\n \"role\": \"user\"\n }\n]","isConversational":true}}}],"truncated":false,"partial":false},"paginationData":{"pageIndex":22,"numItemsPerPage":100,"numTotalItems":31175,"offset":2200,"length":100}},"jwt":"eyJhbGciOiJFZERTQSIsImtpZCI6IjVHZDBvd0g5MTM2eDZjc1FvbE1zcktNWUZoRVFoUm5PVVVybEpjOUhaUEEifQ.eyJyZWFkIjp0cnVlLCJwZXJtaXNzaW9ucyI6eyJyZXBvLmNvbnRlbnQucmVhZCI6dHJ1ZX0sImlhdCI6MTc4NTA1NjYzOCwianRpIjoiNWNlMDlmOTktODYwZS00NmE0LWEyOGYtOTEyYThlNDFlYTBmIiwic3ViIjoiL2RhdGFzZXRzL2VpdGFucy1wdS9jbC1jb2RpbmctaW5wdXQiLCJleHAiOjE3ODUwNjAyMzgsImlzcyI6Imh0dHBzOi8vaHVnZ2luZ2ZhY2UuY28ifQ.tUD2mNCtHARvS3KembD-sLE_Bug6ZbKXq6cmPGsOI6fq7vqOymR19RbaulhKfVIEMT8jHaDD8tYTo0VUPr-kBg","displayUrls":true,"splitSizeSummaries":[{"config":"default","split":"train","numRows":31175,"numBytesParquet":1629387251}]},"discussionsStats":{"closed":0,"open":1,"total":1},"fullWidth":true,"hasGatedAccess":true,"hasFullAccess":true,"isEmbedded":false,"savedQueries":{"community":[],"user":[]}}">
id int64 | name string | name_abbreviation string | decision_date string | docket_number string | court string | casebody string | judge1 string | judge2 string | judge3 string | exactly_three_caps int64 | extra_judges string | judge_designations string | opinions_count int64 | majority_count int64 | dissent_count int64 | concurrence_count int64 | other_count int64 | primary_citation string | reporter string | volume null | resource_url string | precedential_status string | 010combined_count int64 | 020lead_count int64 | 030concurrence_count int64 | 035concurrenceinpart_count int64 | 040dissent_count int64 | year int64 | month int64 | messages list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
4,616,185 | Gregory Garvin v. Cook Investments Nw, Spnwy | 2019-05-02 | 18-35119 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Susan P. Graber, M. Margaret McKeown, and Morgan Christen, Circuit Judges.", "parties": "", "opinions": [{"author": "McKEOWN, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nGREGORY M. GARVIN, Acting United ... | SUSAN P GRABER | M MARGARET MCKEOWN | MORGAN CHRISTEN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616185/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,616,186 | Gerardo Vazquez v. Jan-Pro Franchising Int'l Inc. | 2019-05-02 | 17-16096 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Ronald M. Gould and Marsha S. Berzon, Circuit Judges, and Frederic Block, District Judge.", "parties": "", "opinions": [{"author": "BLOCK, District Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n GERARDO VAZQUEZ, GLOR... | RONALD M GOULD | MARSHA S BERZON | FREDERIC BLOCK | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616186/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,616,187 | Bokf, Na v. Robert Estes | 2019-05-02 | 18-15369 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Marsha S. Berzon and Michelle T. Friedland, Circuit Judges, and Daniel R. Dominguez, * District Judge.", "parties": "", "opinions": [{"author": "BERZON, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nBOKF, NA, ... | MARSHA S BERZON | MICHELLE T FRIEDLAND | DANIEL R DOMINGUEZ | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616187/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,616,652 | Mark Bradford v. Ron Davis | 2019-05-03 | 15-99018 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: MILAN D. SMITH, JR., PAUL J. WATFORD, and ANDREW D. HURWITZ, Circuit Judges.", "parties": "", "opinions": [{"author": "M. SMITH, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nMARK ALAN BRADFORD, ... | MILAN D SMITH JR | PAUL J WATFORD | ANDREW D HURWITZ | 1 | {"MILAN D SMITH JR": ", Circuit", "PAUL J WATFORD": ", Circuit", "ANDREW D HURWITZ": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616652/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,616,653 | Francis Hernandez v. Kevin Chappell | 2019-05-03 | 11-99013 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Kim McLane Wardlaw, Milan D. Smith, Jr., and Jacqueline H. Nguyen, Circuit Judges.", "parties": "", "opinions": [{"author": "NGUYEN, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nFRANCIS G. HERNANDEZ, ... | KIM MCLANE WARDLAW | MILAN D SMITH JR | JACQUELINE H NGUYEN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616653/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,616,654 | C.J.L.G., a Juvenile Male v. William Barr | 2019-05-03 | 16-73801 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Sidney R. Thomas, Chief Judge, and Susan P. Graber, M. Margaret McKeown, William A. Fletcher, Richard A. Paez, Marsha S. Berzon, Johnnie B. Rawlinson, Consuelo M. Callahan, Sandra S. Ikuta, Jacqueline H. Nguyen and Andrew D. Hurwitz, Circuit Judges.", "parties": "", "opinions": [{"author": "HURWITZ,... | SIDNEY R THOMAS | SUSAN P GRABER | M MARGARET MCKEOWN | 2 | WILLIAM A FLETCHER; RICHARD A PAEZ; MARSHA S BERZON; JOHNNIE B RAWLINSON; CONSUELO M CALLAHAN; SANDRA S IKUTA; JACQUELINE H NGUYEN; ANDREW D HURWITZ | {} | 4 | 0 | 1 | 2 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616654/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,616,655 | Boon Global Limited v. Usdc-Caoak | 2019-05-03 | 18-71347 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Richard A. Paez, Marsha S. Berzon, and Ryan D. Nelson, Circuit Judges.", "parties": "", "opinions": [{"author": "R. NELSON, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nIN RE BOON GLOBAL LIMITED; F8 ... | RICHARD A PAEZ | MARSHA S BERZON | RYAN D NELSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616655/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,616,992 | Wildearth Guardians v. Heather Provencio | 2019-05-06 | 17-17373 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: MICHAEL DALY HAWKINS, MILAN D. SMITH, JR., and ANDREW D. HURWITZ, Circuit Judges.", "parties": "", "opinions": [{"author": "M. SMITH, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nWILDEARTH GUARDIANS; GRAND ... | MICHAEL DALY HAWKINS | MILAN D SMITH JR | ANDREW D HURWITZ | 1 | {"MICHAEL DALY HAWKINS": ", Circuit", "MILAN D SMITH JR": ", Circuit", "ANDREW D HURWITZ": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616992/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,616,993 | Shyriaa Henderson v. United Student Aid Funds, Inc. | 2019-05-06 | 17-55373 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Dorothy W. Nelson, William A. Fletcher, and Jay S. Bybee, Circuit Judges.", "parties": "", "opinions": [{"author": "Judge D.W Nelson voted to deny the petition for", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\nSHYRIAA HENDERSON... | DOROTHY W NELSON | WILLIAM A FLETCHER | JAY S BYBEE | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616993/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,616,994 | Consumer Financial Protection v. Seila Law LLC | 2019-05-06 | 17-56324 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Susan P. Graber and Paul J. Watford, Circuit Judges, and Jack Zouhary, * District Judge.", "parties": "", "opinions": [{"author": "WATFORD, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n CONSUMER FINANCIAL PR... | SUSAN P GRABER | PAUL J WATFORD | JACK ZOUHARY | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616994/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,617,443 | Innovation Law Lab v. Kevin McAleenan | 2019-05-07 | 19-15716 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: O’SCANNLAIN, W. FLETCHER, and WATFORD, Circuit Judges.", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "FOR PUBLICATION FILED\n UNITED STATES COURT OF APPEALS MAY 7 2019\n ... | O'SCANNLAIN | W FLETCHER | WATFORD | 1 | {"O'SCANNLAIN": ", Circuit", "W FLETCHER": ", Circuit", "WATFORD": ", Circuit"} | 3 | 0 | 0 | 2 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617443/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
9,023,003 | INNOVATION LAW LAB Central American Resource Center of Northern California Centro Legal De La Raza University of San Francisco School of Law Immigration and Deportation Defense Clinic Al Otro Lado Tahirih Justice Center v. Kevin K. MCALEENAN, Acting Secretary of Homeland Security, in his official capacity U.S. Departme... | Innovation Law Lab v. McAleenan | 2019-05-07 | No. 19-15716 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Watford", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9016241/", "author_raw": "PER CURIAM"}, {"author": "", "type": "030concurrence", "text": "", "resource_uri": "https://www.courtlistener.com/api/re... | WATFORD | WATFORD | 0 | {} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/9023003/ | Published | 0 | 1 | 1 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,617,676 | Peter Wojciechowski v. Kohlberg Ventures, LLC | 2019-05-08 | 17-15966 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Ronald M. Gould and Richard A. Paez, Circuit Judges, and Janis Graham Jack,* District Judge.", "parties": "", "opinions": [{"author": "GOULD, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n PETER WOJCIECHOWSKI... | RONALD M GOULD | RICHARD A PAEZ | JANIS GRAHAM JACK | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617676/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,617,677 | Comcast of Sacramento I, LLC v. Sacramento Metropolitan Cable | 2019-05-08 | 17-16847 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Consuelo M. Callahan and N. Randy Smith, Circuit Judges, and Fernando M. Olguin,* District Judge.", "parties": "", "opinions": [{"author": "N.R. SMITH, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n C... | CONSUELO M CALLAHAN | N RANDY SMITH | FERNANDO M OLGUIN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617677/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,617,678 | Cedar Point Nursery v. Genevieve Shiroma | 2019-05-08 | 16-16321 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Edward Leavy, William A. Fletcher, and Richard A. Paez, Circuit Judges.", "parties": "", "opinions": [{"author": "PAEZ, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nCEDAR POINT NURSERY; FOWLER No.... | EDWARD LEAVY | WILLIAM A FLETCHER | RICHARD A PAEZ | 1 | {} | 2 | 0 | 1 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617678/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,618,172 | United States v. Roxanne Carpenter | 2019-05-09 | 17-10498 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: MICHAEL D. HAWKINS and MILAN D. SMITH, JR., Circuit Judges, and KATHRYN H. VRATIL, * District Judge.", "parties": "", "opinions": [{"author": "M. SMITH, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nUNITED STAT... | MICHAEL D HAWKINS | MILAN D SMITH JR | KATHRYN H VRATIL | 1 | {"MICHAEL D HAWKINS": "MILAN D SMITH, JR , Circuit", "MILAN D SMITH JR": "MILAN D SMITH, JR , Circuit", "KATHRYN H VRATIL": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4618172/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,618,683 | United States v. Selso Orona | 2019-05-10 | 17-17508 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before:Michael Daly Hawkins, Milan D. Smith, Jr., and Andrew D. Hurwitz, Circuit Judges.", "parties": "", "opinions": [{"author": "Opinion by Judge Hawkins", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nUNITED STATES OF AMERICA, ... | MICHAEL DALY HAWKINS | MILAN D SMITH JR | ANDREW D HURWITZ | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4618683/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,618,684 | United States v. Mario Ruvalcaba-Garcia | 2019-05-10 | 17-50288 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Susan P. Graber and Jay S. Bybee, Circuit Judges, and M. Douglas Harpool,* District Judge.", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n UNITED STATES OF AMERI... | SUSAN P GRABER | JAY S BYBEE | M DOUGLAS HARPOOL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4618684/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,618,685 | United States v. Mario Fultz | 2019-05-10 | 17-56002 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Ronald M. Gould and Jacqueline H. Nguyen, Circuit Judges, and Algenon L. Marbley, * District Judge.", "parties": "", "opinions": [{"author": "MARBLEY, District Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n UNITED ST... | RONALD M GOULD | JACQUELINE H NGUYEN | ALGENON L MARBLEY | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4618685/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,618,686 | Claudia Prado v. William Barr | 2019-05-10 | 17-72914 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Michael Daly Hawkins and Milan D. Smith, Jr., Circuit Judges, and Barbara M. G. Lynn, * District Judge.", "parties": "", "opinions": [{"author": "Opinion by Judge Hawkins", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n CLAUD... | MICHAEL DALY HAWKINS | MILAN D SMITH JR | BARBARA M G LYNN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4618686/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,619,007 | George Kayer v. Charles L. Ryan | 2019-05-13 | 09-99027 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: William A. Fletcher, John B. Owens, and Michelle T. Friedland, Circuit Judges.", "parties": "", "opinions": [{"type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nGEORGE RUSSELL KAYER, No. 09-99027\n ... | WILLIAM A FLETCHER | JOHN B OWENS | MICHELLE T FRIEDLAND | 1 | {} | 3 | 0 | 1 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619007/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,619,268 | George Kayer v. Charles L. Ryan | 2019-05-13 | 09-99027 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: William A. Fletcher, John B. Owens, and Michelle T. Friedland, Circuit Judges.", "parties": "", "opinions": [{"type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nGEORGE RUSSELL KAYER, No. 09-99027\n ... | WILLIAM A FLETCHER | JOHN B OWENS | MICHELLE T FRIEDLAND | 1 | {} | 3 | 0 | 1 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619268/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,619,265 | United States v. Steven Audette | 2019-05-14 | 17-10017 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: MICHAEL DALY HAWKINS, MILAN D. SMITH, JR., and ANDREW D. HURWITZ, Circuit Judges.", "parties": "", "opinions": [{"author": "M. SMITH, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nUNITED STATES OF AMERICA, ... | MICHAEL DALY HAWKINS | MILAN D SMITH JR | ANDREW D HURWITZ | 1 | {"MICHAEL DALY HAWKINS": ", Circuit", "MILAN D SMITH JR": ", Circuit", "ANDREW D HURWITZ": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619265/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,619,266 | Shannon Adamson v. Port of Bellingham | 2019-05-14 | 16-35314 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Ronald M. Gould and Sandra S. Ikuta, Circuit Judges, and John R. Tunheim, * District Judge.", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n SHANNON C. ADAMSON, Husband ... | RONALD M GOULD | SANDRA S IKUTA | JOHN R TUNHEIM | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619266/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,619,267 | Gabriel Moran v. the Screening Pros | 2019-05-14 | 12-57246 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: ANDREW J. KLEINFELD, MILAN D. SMITH, JR., and JACQUELINE H. NGUYEN, Circuit Judges.", "parties": "", "opinions": [{"author": "M. SMITH, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n GABRIEL FELIX MORAN, ... | ANDREW J KLEINFELD | MILAN D SMITH JR | JACQUELINE H NGUYEN | 1 | {"ANDREW J KLEINFELD": ", Circuit", "MILAN D SMITH JR": ", Circuit", "JACQUELINE H NGUYEN": ", Circuit"} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619267/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
9,023,000 | Shannon C. ADAMSON, Husband and Wife Nicholas Adamson, Husband and Wife v. PORT OF BELLINGHAM, a Washington Municipal Corporation | Adamson v. Port of Bellingham | 2019-05-14 | No. 16-35314 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9016238/"}]} | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/9023000/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||||
4,620,354 | United States v. Ravneet Singh | 2019-05-16 | 17-50337 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: MILAN D. SMITH, JR., PAUL J. WATFORD, and ANDREW D. HURWITZ, Circuit Judges.", "parties": "", "opinions": [{"author": "M. SMITH, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n\nUNITED STATES OF AMERICA, ... | MILAN D SMITH JR | PAUL J WATFORD | ANDREW D HURWITZ | 1 | {"MILAN D SMITH JR": ", Circuit", "PAUL J WATFORD": ", Circuit", "ANDREW D HURWITZ": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4620354/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,620,355 | Fernando Ponce Garcia v. United States | 2019-05-16 | 17-71759 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: MICHAEL DALY HAWKINS and MILAN D. SMITH, JR., Circuit Judges, and BARBARA M. G. LYNN, * District Judge.", "parties": "", "opinions": [{"author": "M. SMITH, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n FERNA... | MICHAEL DALY HAWKINS | MILAN D SMITH JR | BARBARA M G LYNN | 1 | {"MICHAEL DALY HAWKINS": "MILAN D SMITH, JR , Circuit", "MILAN D SMITH JR": "MILAN D SMITH, JR , Circuit", "BARBARA M G LYNN": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4620355/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,620,517 | Marcelo Martinez-Cedillo v. William P. Barr | 2019-05-16 | 14-71742 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: THOMAS, Chief Circuit Judge The motion to dismiss this", "parties": "", "opinions": [{"author": "The three-judge panel disposition in this case, which was designated as non", "type": "010combined", "text": "FILED\n FOR PUBLICATION\n ... | THOMAS | THOMAS | DISMISS | 1 | {"THOMAS": ", Chief Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4620517/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
9,023,002 | Fernando Ponce GARCIA v. United States | Garcia v. United States | 2019-05-16 | No. 17-71759 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Smith", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9016240/", "author_raw": ""}]} | NO_JUDGES | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/9023002/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||||
4,620,968 | Dewitt Lambert v. Tesla, Inc. | 2019-05-17 | 18-15203 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: SIDNEY R. THOMAS, Chief Judge, MILAN D. SMITH, JR., Circuit Judge, and KATHRYN H. VRATIL, * District Judge.", "parties": "", "opinions": [{"author": "M. SMITH, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n D... | SIDNEY R THOMAS | MILAN D SMITH JR | KATHRYN H VRATIL | 1 | {"SIDNEY R THOMAS": ", Chief", "MILAN D SMITH JR": ", Chief Judge, MILAN D SMITH, JR , Circuit", "KATHRYN H VRATIL": ", District"} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4620968/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,621,336 | Mary Murray v. Bej Minerals, LLC | 2019-05-20 | 16-35506 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Sidney R. Thomas, Chief Judge, and Kim McLane Wardlaw, Marsha S. Berzon, Jay S. Bybee, Consuelo M. Callahan, Sandra S. Ikuta, Mary H. Murguia, Morgan Christen, Paul J. Watford, Michelle T. Friedland, and Ryan D. Nelson, Circuit Judges.", "parties": "", "opinions": [{"author": "THOMAS, Chief Circuit ... | SIDNEY R THOMAS | KIM MCLANE WARDLAW | MARSHA S BERZON | 2 | JAY S BYBEE; CONSUELO M CALLAHAN; SANDRA S IKUTA; MARY H MURGUIA; MORGAN CHRISTEN; PAUL J WATFORD; MICHELLE T FRIEDLAND; RYAN D NELSON | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4621336/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,621,337 | Jose Alanniz v. William Barr | 2019-05-20 | 15-72792 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Dorothy W. Nelson and Consuelo M. Callahan, Circuit Judges, and Edward R. Korman,** District Judge.", "parties": "", "opinions": [{"author": "CALLAHAN, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n JOSE MA... | DOROTHY W NELSON | CONSUELO M CALLAHAN | EDWARD R KORMAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4621337/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
9,023,004 | Mary Ann MURRAY Lige M. Murray, Plaintiffs-Counter-Defendants-Appellees v. BEJ MINERALS, LLC RTWF, LLC, Defendants-Counter-Claimants-Appellants. | Murray v. BEJ Minerals, LLC | 2019-05-20 | No. 16-35506 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Murguia, Thomas", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9016243/", "author_raw": ""}, {"author": "", "type": "040dissent", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9... | MURGUIA | THOMAS | MURGUIA | 1 | {} | 2 | 0 | 1 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/9023004/ | Published | 0 | 1 | 0 | 0 | 1 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,621,667 | Janelle Perez v. City of Roseville | 2019-05-21 | 15-16430 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: A. Wallace Tashima and Sandra S. Ikuta, * Circuit Judges, and Donald W. Molloy, ** District Judge.", "parties": "", "opinions": [{"author": "IKUTA, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nJANELLE PEREZ, ... | A WALLACE TASHIMA | SANDRA S IKUTA | DONALD W MOLLOY | 1 | {} | 2 | 0 | 1 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4621667/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,622,105 | Isaias Lorenzo Lopez v. William Barr | 2019-05-22 | 15-72406 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Dorothy W. Nelson and Consuelo M. Callahan, Circuit Judges, and Edward R. Korman, * District Judge.", "parties": "", "opinions": [{"author": "KORMAN, District Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n ISAIAS LOR... | DOROTHY W NELSON | CONSUELO M CALLAHAN | EDWARD R KORMAN | 1 | {} | 2 | 0 | 1 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4622105/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,622,106 | Bd of Trustees Glazing Health v. Shannon Chambers | 2019-05-22 | 16-15588 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "", "parties": "", "opinions": [{"author": "THOMAS, Chief Judge", "type": "010combined", "text": "FOR PUBLICATION FILED\n UNITED STATES COURT OF APPEALS MAY 22 2019\n MOLLY C. DWYER, CLERK\n ... | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4622106/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||||||
4,623,708 | Bd of Trustees Glazing Health v. Shannon Chambers | 2019-05-22 | 16-15588 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "", "parties": "", "opinions": [{"author": "THOMAS, Chief Judge", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nTHE BOARD OF TRUSTEES OF THE No. 16-15588\nGLAZING HEALTH AND WELFARE\nTRUST; BOARD OF TRUSTEES OF THE D.C. No.\nSOU... | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4623708/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||||||
9,023,001 | The BOARD OF TRUSTEES OF the GLAZING HEALTH AND WELFARE TRUST Board of Trustees of the Southern Nevada Glaziers and Fabricators Pension Trust Fund Board of Trustees of the Plumbers and Pipefitters Union Local 525 Pension Plan the Board of Trustees of the Painters, Glaziers and Floorcoverers Joint Apprenticeship and Jou... | Bd. of Trs. of the Glazing Health & Welfare Trust v. Chambers | 2019-05-22 | No. 16-15588 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Thomas", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9016239/", "author_raw": ""}]} | THOMAS | THOMAS | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/9023001/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,623,707 | United States v. Johnny Smith | 2019-05-28 | 17-30248 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Raymond C. Fisher, Richard R. Clifton, and Consuelo M. Callahan, Circuit Judges.", "parties": "", "opinions": [{"author": "CALLAHAN, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nUNITED STATES OF AMERICA, ... | RAYMOND C FISHER | RICHARD R CLIFTON | CONSUELO M CALLAHAN | 1 | {} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4623707/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,624,092 | Denys Honcharov v. William Barr | 2019-05-29 | 15-71554 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: J. Clifford Wallace, Sandra S. Ikuta, and Morgan Christen, Circuit Judges.", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nDENYS HONCHAROV, AKA Denys No. 15-715... | J CLIFFORD WALLACE | SANDRA S IKUTA | MORGAN CHRISTEN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624092/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,624,093 | City of Albany v. Ch2m Hill, Inc. | 2019-05-29 | 18-35283 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: N. Randy Smith, Paul J. Watford, and Ryan D. Nelson, Circuit Judges.", "parties": "", "opinions": [{"author": "WATFORD, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nCITY OF ALBANY, an Oregon No... | N RANDY SMITH | PAUL J WATFORD | RYAN D NELSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624093/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,624,094 | Brad Tschida v. Jonathan Motl | 2019-05-29 | 18-35115 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: William A. Fletcher and Jay S. Bybee, Circuit Judges, and Larry A. Burns,* Chief District Judge.", "parties": "", "opinions": [{"author": "W. FLETCHER, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n BRAD TS... | WILLIAM A FLETCHER | JAY S BYBEE | LARRY A BURNS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624094/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,624,746 | United States v. Randy Graves | 2019-05-30 | 16-50276 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Richard A. Paez and Richard R. Clifton, Circuit Judges, and Gary S. Katzmann,* Judge.", "parties": "", "opinions": [{"author": "CLIFTON, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n UNITED STATES OF AMERI... | RICHARD A PAEZ | RICHARD R CLIFTON | GARY S KATZMANN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624746/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,624,747 | Sierra Club, Inc. v. U.S. Fish and Wildlife Serv. | 2019-05-30 | 17-16560 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: J. Clifford Wallace and Marsha S. Berzon, Circuit Judges, and Terrence Berg, * District Judge.", "parties": "", "opinions": [{"author": "BERG, District Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n SIERRA CLUB, INC.... | J CLIFFORD WALLACE | MARSHA S BERZON | TERRENCE BERG | 1 | {} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624747/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,624,748 | Randall Holl v. Usdc-Caoak | 2019-05-30 | 18-70568 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Michael Daly Hawkins and Milan D. Smith, Jr., Circuit Judges, and Barbara M. G. Lynn, * District Judge.", "parties": "", "opinions": [{"author": "Opinion by Judge Hawkins", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nIN RE RA... | MICHAEL DALY HAWKINS | MILAN D SMITH JR | BARBARA M G LYNN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624748/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,624,749 | Jiang Guan v. William Barr | 2019-05-30 | 17-71966 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Ronald M. Gould and Jacqueline H. Nguyen, Circuit Judges, and Roger T. Benitez, ** District Judge.", "parties": "", "opinions": [{"author": "NGUYEN, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\n JIANG GUAN, ... | RONALD M GOULD | JACQUELINE H NGUYEN | ROGER T BENITEZ | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624749/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,624,750 | Harvinder Singh v. American Honda Finance Corp. | 2019-05-30 | 17-35964 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Ronald M. Gould and Richard A. Paez, Circuit Judges, and Cynthia A. Bashant, * District Judge.", "parties": "", "opinions": [{"author": "GOULD, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nHARVINDER SINGH, ... | RONALD M GOULD | RICHARD A PAEZ | CYNTHIA A BASHANT | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624750/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,624,751 | Center for Biological Diversit v. Usfs | 2019-05-30 | 17-15790 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Marsha S. Berzon and Michelle T. Friedland, Circuit Judges, and Kathleen Cardone, * District Judge.", "parties": "", "opinions": [{"author": "BERZON, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nCENTER FOR BIO... | MARSHA S BERZON | MICHELLE T FRIEDLAND | KATHLEEN CARDONE | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624751/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
9,023,006 | IN RE Randall HOLL, Randall Holl, individually, on behalf of others similarly situated, and as a representative of the class v. United States District Court for the Northern District of California, Oakland, United Parcel Service, Inc., Real Party in Interest. | Holl v. U.S. Dist. Court for the N. Dist. of Cal. | 2019-05-30 | No. 18-70568 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Hawkins", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9016246/", "author_raw": ""}]} | HAWKINS | HAWKINS | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/9023006/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,625,275 | Doug Greisen v. Jon Hanken | 2019-05-31 | 17-35472 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: Raymond C. Fisher, Richard R. Clifton and Consuelo M. Callahan, Circuit Judges.", "parties": "", "opinions": [{"author": "FISHER, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nDOUG GREISEN, ... | RAYMOND C FISHER | RICHARD R CLIFTON | CONSUELO M CALLAHAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4625275/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,625,276 | Arizona Libertarian Party v. Katie Hobbs | 2019-05-31 | 17-16491 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: J. Clifford Wallace, A. Wallace Tashima, and M. Margaret McKeown, Circuit Judges.", "parties": "", "opinions": [{"author": "McKEOWN, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nARIZONA LIBERTARIAN PARTY; ... | J CLIFFORD WALLACE | A WALLACE TASHIMA | M MARGARET MCKEOWN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4625276/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,625,596 | Arizona Libertarian Party v. Katie Hobbs | 2019-05-31 | 17-16491 | U.S. Court of Appeals for the Ninth Circuit | {"judges": "Before: J. Clifford Wallace, A. Wallace Tashima, and M. Margaret McKeown, Circuit Judges.", "parties": "", "opinions": [{"author": "McKEOWN, Circuit Judge:", "type": "010combined", "text": "FOR PUBLICATION\n\n UNITED STATES COURT OF APPEALS\n FOR THE NINTH CIRCUIT\n\n\nARIZONA LIBERTARIAN PARTY; ... | J CLIFFORD WALLACE | A WALLACE TASHIMA | M MARGARET MCKEOWN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4625596/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,616,602 | NAYLOR FARMS, INC. ; Harrel's LLC, Plaintiffs-Appellees, v. CHAPARRAL ENERGY, LLC, Defendant-Appellant, Black Stone Minerals Company, L.P., Amicus Curiae. | Naylor Farms, Inc. v. Chaparral Energy, LLC | 2019-05-03 | 17-6146 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Moritz, Murphy, Eid", "parties": "", "opinions": [{"author": "MORITZ, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH Tenth ... | MORITZ | MURPHY | EID | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616602/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,616,656 | UNITED STATES of America, Plaintiff - Appellee, v. Alexander Christian MILES, Defendant - Appellant. | United States v. Miles | 2019-05-03 | 18-6119 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Hartz, Murphy, Carson", "parties": "", "opinions": [{"author": "HARTZ, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH Ten... | HARTZ | MURPHY | CARSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616656/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,990 | UNITED STATES of America v. Allari GUZMAN | United States v. Guzman | 2019-05-03 | No. 18-3135 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415424/"}]} | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443990/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||||
4,616,959 | UNITED STATES of America, Plaintiff - Appellee, v. Christopher Lee MARTINEZ, Defendant - Appellant. | United States v. Martinez | 2019-05-06 | 18-8007 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Hartz, Matheson, Eid", "parties": "", "opinions": [{"author": "HARTZ, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH Tenth Ci... | HARTZ | MATHESON | EID | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616959/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,617,295 | ADVANCED RECOVERY SYSTEMS, a Utah Limited Liability Company, Plaintiff Counterclaim Defendant, v. AMERICAN AGENCIES, a Pennsylvania Limited Liability Company, Defendant Counterclaimant Third-Party Plaintiff-Appellee, NRA Group, a Pennsylvania Limited Liability Company, A/K/A National Recovery Agency; Steven C. Kusic, C... | Advanced Recovery Sys. v. Am. Agencies, Ltd. | 2019-05-07 | 17-4202 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Bacharach, Baldock, Phillips", "parties": "", "opinions": [{"author": "BACHARACH, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\... | BACHARACH | BALDOCK | PHILLIPS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617295/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,617,344 | DINE CITIZENS AGAINST RUINING OUR ENVIRONMENT; San Juan Citizens Alliance; WildEarth Guardians; Natural Resources Defense Council, Plaintiffs-Appellants, v. David BERNHARDT, in His Official Capacity as Acting Secretary of the United States Department of the Interior; United States Bureau of Land Management, an Agency W... | Dine Citizens Against Ruining Our Env't v. Bernhardt | 2019-05-07 | 18-2089 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Briscoe, McKay, Holmes", "parties": "", "opinions": [{"author": "BRISCOE, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n ... | BRISCOE | MCKAY | HOLMES | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617344/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,617,407 | UTAH NATIVE PLANT SOCIETY; Grand Canyon Trust, Plaintiffs-Appellants, v. UNITED STATES FOREST SERVICE; Tom Tidwell, in His Official Capacity as Chief of the U.S. Forest Service, Defendants-Appellees. State of Utah; State of Alaska; State of Colorado; State of Idaho; State of Kansas; State of Nebraska; State of Wyoming;... | Utah Native Plant Society v. U.S. Forest Service | 2019-05-07 | 17-4074 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Briscoe, Baldock, Eid", "parties": "", "opinions": [{"type": "010combined", "text": "FILED\n United States Court of Appeals\n Tenth Circuit\n\n PUBLISH ... | BRISCOE | BALDOCK | EID | 1 | {} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617407/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,617,604 | John Thomas TALLEY, Plaintiff - Appellant, v. TIME, INC., D/B/A Sports Illustrated Magazine; George Dohrmann ; Thayer Evans, Defendants - Appellees. | Talley v. Time, Inc. | 2019-05-08 | 18-6169 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Matheson, Murphy, Eid", "parties": "", "opinions": [{"author": "MATHESON, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH ... | MATHESON | MURPHY | EID | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617604/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,619,076 | UNITED STATES of America Plaintiff - Appellee, v. Jason LOERA, Defendant - Appellant. | United States v. Loera | 2019-05-13 | 17-2180 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Lucero, Ebel, Phillips", "parties": "", "opinions": [{"author": "EBEL, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH Tenth... | LUCERO | EBEL | PHILLIPS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619076/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,619,689 | Steven M. PETERSEN ; Pauline Petersen, Petitioners - Appellants, v. COMMISSIONER OF INTERNAL REVENUE, Respondent - Appellee. John E. Johnstun; Larue A. Johnstun, Petitioners - Appellants, v. Commissioner of Internal Revenue, Respondent - Appellee. | Petersen v. Comm'r of Internal Revenue | 2019-05-15 | 17-9003; 17-9004 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Hartz, Phillips, Eid", "parties": "", "opinions": [{"author": "HARTZ, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH Tenth ... | HARTZ | PHILLIPS | EID | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619689/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,619,690 | Stephen HAMER, Plaintiff - Appellant, v. CITY OF TRINIDAD, Defendant - Appellee. Colorado Municipal League, Amicus Curiae. | Hamer v. City of Trinidad | 2019-05-15 | 17-1456 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Briscoe, Bacharach, Carson", "parties": "", "opinions": [{"author": "CARSON, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH ... | BRISCOE | BACHARACH | CARSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619690/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,620,920 | UNITED STATES of America, Plaintiff - Appellee, v. Armando MENDEZ, Defendant - Appellant. | United States v. Mendez | 2019-05-17 | 18-1259 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Hartz, Seymour, Holmes", "parties": "", "opinions": [{"author": "SEYMOUR, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH ... | HARTZ | SEYMOUR | HOLMES | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4620920/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,620,922 | Gale v. City and County of Denver | 2019-05-17 | 18-1269 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "", "parties": "", "opinions": [{"author": "Honorable Philip A. Brimmer, Chief Judge", "type": "010combined", "text": "United States Court of Appeals\n Tenth Circuit\n Office of the Clerk\n Byron Whit... | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4620922/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||||||
4,620,969 | Franklin GALE, Plaintiff-Appellant, v. the CITY AND COUNTY OF DENVER, Defendant-Appellee. | Gale v. City and County of Denver | 2019-05-17 | 18-1269 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Tymkovich, Bacharach, Moritz", "parties": "", "opinions": [{"author": "", "type": "010combined", "text": "FILED\n United States Court of Appeals\n Tenth Circuit\n\n ... | TYMKOVICH | BACHARACH | MORITZ | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4620969/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,621,587 | UNITED STATES of America, Plaintiff-Appellee, v. Wendy Marie YUREK, Defendant-Appellant. | United States v. Yurek (Wendy) | 2019-05-21 | 18-1134 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Bacharach, Baldock, Ebel", "parties": "", "opinions": [{"author": "BACHARACH, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH Tenth Circuit\n\n ... | BACHARACH | BALDOCK | EBEL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4621587/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,621,589 | Charles FARRAR, Petitioner - Appellant, v. Rick RAEMISCH, Executive Director, Colorado Department of Corrections; Cynthia Coffman, Attorney General, State of Colorado ; James Falk, Warden, Sterling Correctional Facility, Respondents - Appellees. Scholars of Federal Habeas Corpus, Amicus Curiae. | Farrar v. Raemisch | 2019-05-21 | 18-1005 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Bacharach, Baldock, Ebel", "parties": "", "opinions": [{"author": "BACHARACH, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH ... | BACHARACH | BALDOCK | EBEL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4621589/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,623,646 | STEVEN R.F., a Minor BY AND THROUGH His Mother Carrie FERNANDEZ, Plaintiff-Appellee, v. HARRISON SCHOOL DISTRICT NO. 2, and Various of Its Elected and Appointed Representatives in Their Official Capacities, Defendant - Appellant. | Steven R.F. by and Through Fernandez v. Harrison Sch. Dist. No. 2 | 2019-05-28 | 18-1327 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Briscoe, Lucero, Phillips", "parties": "", "opinions": [{"author": "BRISCOE, Circuit Judge.", "type": "010combined", "text": "FILED\n United States Court of Appeals\n PUBLISH ... | BRISCOE | LUCERO | PHILLIPS | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4623646/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,623,709 | Troy Michael KELL, Petitioner-Appellee, v. Larry BENZON, Warden Utah State Prison, Respondent-Appellant. | Kell v. Benzon | 2019-05-28 | 17-4191 | U.S. Court of Appeals for the Tenth Circuit | {"judges": "Bacharach, Baldock, Phillips", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9888594/", "author_raw": ""}, {"author": "", "type": "040dissent", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/... | BACHARACH | BALDOCK | PHILLIPS | 1 | {} | 5 | 0 | 3 | 0 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4623709/ | Published | 1 | 1 | 0 | 0 | 1 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,616,237 | UNITED STATES of America, Plaintiff-Appellee, v. Anthony Carl SPENCE, Defendant-Appellant. | United States v. Anthony Carl Spence | 2019-05-02 | 17-14976 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Carnes, Martin, Anderson", "parties": "", "opinions": [{"author": "ANDERSON, Circuit Judge:", "type": "010combined", "text": "Case: 17-14976 Date Filed: 05/02/2019 Page: 1 of 13\n\n\n\n [PUBLISH]\n\n IN THE UNITED ... | CARNES | MARTIN | ANDERSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616237/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,616,452 | CITY OF MIAMI, a Florida Municipal Corporation, Plaintiff-Appellant, v. WELLS FARGO & CO., Wells Fargo Bank, N.A., Defendants-Appellees. City of Miami, a Florida Municipal Corporation, Plaintiff-Appellant, v. Bank of America Corporation, Bank of America, N.A., Countrywide Financial Corporation, Countrywide Home Loans, ... | City of Miami v. Wells Fargo & Co. | 2019-05-03 | 14-14544; 14-14543 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Marcus, Wilson, Schlesinger", "parties": "", "opinions": [{"author": "MARCUS, Circuit Judge:", "type": "010combined", "text": "Case: 14-14544 Date Filed: 05/03/2019 Page: 1 of 76\n\n\n [PUBLISH]\n\n IN THE UNITED STA... | MARCUS | WILSON | SCHLESINGER | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616452/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,617,013 | Steven J. MYERS, Plaintiff-Counter Defendant-Appellant, v. UNITED STATES of America, Defendant-Counter Claimant-Appellee. | Steven J. Myers v. United States | 2019-05-06 | 18-11403 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Tjoflat, Jordan, Schlesinger", "parties": "", "opinions": [{"author": "PER CURIAM", "type": "010combined", "text": "Case: 18-11403 Date Filed: 05/06/2019 Page: 1 of 7\n\n\n [PUBLISH]\n\n IN THE UNITE... | TJOFLAT | JORDAN | SCHLESINGER | 1 | {} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617013/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,617,071 | Homero F. MERUELO, Petitioner-Appellant, v. COMMISSIONER OF INTERNAL REVENUE, Respondent-Appellee. | Homero F. Meruelo v. Commissioner of Internal Revenue | 2019-05-06 | 18-11909 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Pryor, Newsom, Vratil", "parties": "", "opinions": [{"author": "WILLIAM PRYOR, Circuit Judge:", "type": "010combined", "text": "Case: 18-11909 Date Filed: 05/06/2019 Page: 1 of 18\n\n\n [PUBLISH]\n\n ... | PRYOR | NEWSOM | VRATIL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617071/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,617,606 | UNITED STATES of America, Plaintiff-Appellee, v. David ROTHENBERG, Defendant-Appellant. | United States v. David Rothenberg | 2019-05-08 | 17-12349 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Carnes, Rosenbaum, Hull", "parties": "", "opinions": [{"author": "HULL, Circuit Judge:", "type": "010combined", "text": "Case: 17-12349 Date Filed: 05/08/2019 Page: 1 of 67\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED S... | CARNES | ROSENBAUM | HULL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4617606/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,618,173 | Nyreekis Jarnell Hunter v. Mike Hale | 2019-05-09 | 18-10487 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Before TJOFLAT, NEWSOM, and GILMAN, * Circuit Judges.", "parties": "", "opinions": [{"author": "NEWSOM, Circuit Judge:", "type": "010combined", "text": "Case: 18-10487 Date Filed: 05/09/2019 Page: 1 of 23\n\n\n [PUBLISH]\n\n\n\n ... | TJOFLAT | NEWSOM | GILMAN | 1 | {"TJOFLAT": ", Circuit", "NEWSOM": ", Circuit", "GILMAN": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4618173/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,618,174 | FLAT CREEK TRANSPORTATION, LLC, an Alabama Limited Liability Company, Plaintiff - Appellant, v. FEDERAL MOTOR CARRIER SAFETY ADMINISTRATION, Kenny Price, in His Capacity as Alabama Division Administrator (Federal Motor Carrier Safety Administration), Elaine L. Chao, in Her Capacity as Secretary of the United States Dep... | Flat Creek Transportation, LLC v. Federal Motor Carrier Safety Administration | 2019-05-09 | 17-14670 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Tjoflat, Newsom, Gilman", "parties": "", "opinions": [{"author": "NEWSOM, Circuit Judge:", "type": "010combined", "text": "Case: 17-14670 Date Filed: 05/09/2019 Page: 1 of 13\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATE... | TJOFLAT | NEWSOM | GILMAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4618174/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
8,443,998 | Anthony PIAZZA, as personal representative of the Estate of Ricky DeAngelo Hinkle, Nyreekis Jarnell Hunter, as personal representative of the Estate of Ricky DeAngelo Hinkle v. JEFFERSON COUNTY, ALABAMA, an Alabama county, individually, Mike Hale, Ron Eddings, Habimana Dukuzumuremyi, each individually | Piazza v. Jefferson Cnty. | 2019-05-09 | No. 18-10487 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Gilman, Newsom, Tjoflat", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415432/", "author_raw": ""}]} | GILMAN | NEWSOM | TJOFLAT | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8443998/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,618,970 | UNITED STATES of America, Plaintiff-Appellee, v. Isabel Yero GRIMON, Defendant-Appellant. | United States v. Isabel Yero Grimon | 2019-05-13 | 17-15011 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Marcus, Grant, Hull", "parties": "", "opinions": [{"author": "HULL, Circuit Judge:", "type": "010combined", "text": "Case: 17-15011 Date Filed: 05/13/2019 Page: 1 of 15\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COU... | MARCUS | GRANT | HULL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4618970/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,619,841 | United States v. Isabel Yero Grimon | 2019-05-13 | 17-15011 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Before MARCUS, GRANT and HULL, Circuit Judges.", "parties": "", "opinions": [{"author": "HULL, Circuit Judge:", "type": "010combined", "text": "Case: 17-15011 Date Filed: 05/13/2019 Page: 1 of 15\n\n\n [PUBLISH]\n\n\n\n ... | MARCUS | GRANT | HULL | 1 | {"MARCUS": ", Circuit", "GRANT": ", Circuit", "HULL": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619841/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,619,840 | ALLIANT TAX CREDIT 31, INC, a Florida Corporation, Alliant Tax Credit Fund XXVII, Ltd., a Florida Limited Partnership, Alliant Tax Credit Tax Credit XXVII, Inc, a Florida Corporation, Alliant Tax Credit XI, Inc., a Florida Corporation, Alliant Tax Credit XI, Ltd., a Florida Limited Partnership, Plaintiffs - Counter Def... | Alliant Tax Credit 31, Inc. v. M. Vincent Murphy, III | 2019-05-15 | 15-14634 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Tjoflat, Pryor, Murphy", "parties": "", "opinions": [{"author": "TJOFLAT, Circuit Judge:", "type": "010combined", "text": "Case: 15-14634 Date Filed: 05/15/2019 Page: 1 of 37\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES COURT O... | TJOFLAT | PRYOR | MURPHY | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4619840/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,620,939 | Rickey Thompson v. United States | 2019-05-17 | 18-10488 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Before WILLIAM PRYOR, GRANT and HULL, Circuit Judges.", "parties": "", "opinions": [{"author": "HULL, Circuit Judge:", "type": "010combined", "text": "Case: 18-10488 Date Filed: 05/17/2019 Page: 1 of 12\n\n\n [PUBLISH]\n\n\n\n\n ... | WILLIAM PRYOR | GRANT | HULL | 1 | {"WILLIAM PRYOR": ", Circuit", "GRANT": ", Circuit", "HULL": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4620939/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
8,444,004 | Rickey THOMPSON v. United States | Thompson v. United States | 2019-05-17 | No. 18-10488 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Grant, Hull, Pryor", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/8415439/", "author_raw": ""}]} | GRANT | HULL | PRYOR | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/8444004/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,621,540 | PLAYNATION PLAY SYSTEMS, INC., D.B.A. Gorilla Playsets, Plaintiff-Appellee, v. VELEX CORPORATION, D.B.A. Gorilla Gym, Defendant - Appellant. | PlayNation Play Systems, Inc. v. Velex Corporation | 2019-05-21 | 17-15226 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Wilson, Branch, Anderson", "parties": "", "opinions": [{"author": "WILSON, Circuit Judge:", "type": "010combined", "text": "Case: 17-15226 Date Filed: 05/21/2019 Page: 1 of 19\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED STATES ... | WILSON | BRANCH | ANDERSON | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4621540/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,621,978 | PlayNation Play Systems, Inc. v. Velex Corporation | 2019-05-21 | 17-15226 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Before WILSON, BRANCH, and ANDERSON, Circuit Judges.", "parties": "", "opinions": [{"author": "WILSON, Circuit Judge:", "type": "010combined", "text": "Case: 17-15226 Date Filed: 05/21/2019 Page: 1 of 19\n\n\n [PUBLISH]\n\n\n\n ... | WILSON | BRANCH | ANDERSON | 1 | {"WILSON": ", Circuit", "BRANCH": ", Circuit", "ANDERSON": ", Circuit"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4621978/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,621,977 | Willie B. SMITH, III, Petitioner - Appellant, v. COMMISSIONER, ALABAMA DEPARTMENT OF CORRECTIONS, Respondent - Appellee. | Willie B. Smith, III v. Commissioner, Alabama Department of Corrections | 2019-05-22 | 17-15043 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Wilson, Martin, Jordan", "parties": "", "opinions": [{"author": "WILSON, Circuit Judge:", "type": "010combined", "text": "Case: 17-15043 Date Filed: 05/22/2019 Page: 1 of 31\n\n\n [PUBLISH]\n\n\n\n IN THE UNITE... | WILSON | MARTIN | JORDAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4621977/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,622,317 | Bobby Joe LONG, Plaintiff-Appellant, v. SECRETARY, DEPARTMENT OF CORRECTIONS, Warden, Florida State Prison, John Does, as Designee of Barry Reddish, and/or Mark S. Inch, Defendants-Appellees. | Bobby Joe Long v. Secretary, Department of Corrections | 2019-05-22 | 19-11942 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Carnes, Marcus, Jordan", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/9888572/", "author_raw": ""}, {"author": "", "type": "030concurrence", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4... | CARNES | MARCUS | JORDAN | 1 | {} | 4 | 0 | 0 | 2 | 2 | null | https://www.courtlistener.com/api/rest/v4/clusters/4622317/ | Published | 1 | 1 | 1 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,622,513 | Bobby Joe Long v. Secretary, Department of Corrections | 2019-05-22 | 19-11942 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Before ED CARNES, Chief Judge, MARCUS, and JORDAN, Circuit Judges.", "parties": "", "opinions": [{"author": "ED CARNES, Chief Judge", "type": "010combined", "text": "Case: 19-11942 Date Filed: 05/22/2019 Page: 1 of 18\n\n\n [PUBLISH]\n\... | ED CARNES | MARCUS | JORDAN | 1 | {"ED CARNES": ", Chief", "MARCUS": ", Circuit", "JORDAN": ", Circuit"} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4622513/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,622,512 | UNITED STATES of America, Plaintiff-Appellant, v. ASKINS & MILLER ORTHOPAEDICS, P.A., Roland v. Askins, III, Philip H. Askins, Defendants-Appellees. | United States v. Askins & Miller Orthopaedics, P.A. | 2019-05-23 | 18-11434 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Marcus, Grant, Hull", "parties": "", "opinions": [{"author": "GRANT, Circuit Judge:", "type": "010combined", "text": "Case: 18-11434 Date Filed: 05/23/2019 Page: 1 of 24\n\n\n [PUBLISH]\n\n IN THE UNITED STATES COURT... | MARCUS | GRANT | HULL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4622512/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,622,769 | Calvin Lee WORD, Petitioner, v. U.S. COMMODITY FUTURES TRADING COMMISSION, Louie G. Stidham, June C. Stidham, Respondents. | Calvin Lee Word v. U.S. Commodity Futures Trading Commission | 2019-05-23 | 16-15302 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Wilson, Pryor, Tallman", "parties": "", "opinions": [{"author": "TALLMAN, Circuit Judge:", "type": "010combined", "text": "Case: 16-15302 Date Filed: 05/23/2019 Page: 1 of 14\n\n\n [PUBLISH]\n\n IN T... | WILSON | PRYOR | TALLMAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4622769/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,623,035 | UNITED STATES of America, Plaintiff - Appellee, v. Darrell Mark BABCOCK, Defendant - Appellant. | United States v. Darrell Mark Babcock | 2019-05-24 | 17-13678 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Pryor, Newsom, Vratil", "parties": "", "opinions": [{"author": "NEWSOM, Circuit Judge:", "type": "010combined", "text": "Case: 17-13678 Date Filed: 05/24/2019 Page: 1 of 32\n\n\n [PUBLISH]\n\n\n\n IN... | PRYOR | NEWSOM | VRATIL | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4623035/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,623,249 | United States v. Darrell Mark Babcock | 2019-05-24 | 17-13678 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Before WILLIAM PRYOR and NEWSOM, Circuit Judges, and VRATIL, * District Judge.", "parties": "", "opinions": [{"author": "NEWSOM, Circuit Judge:", "type": "010combined", "text": "Case: 17-13678 Date Filed: 05/24/2019 Page: 1 of 32\n\n\n ... | WILLIAM PRYOR | NEWSOM | VRATIL | 1 | {"WILLIAM PRYOR": ", Circuit", "NEWSOM": ", Circuit", "VRATIL": ", District"} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4623249/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
4,623,250 | CLUB MADONNA, INC., a Florida Corporation D.B.A. Club Madonna, Plaintiff - Appellant, v. CITY OF MIAMI BEACH, a Florida Municipal Corporation, Defendant - Appellee. | Club Madonna, Inc. v. City of Miami Beach | 2019-05-24 | 17-13934 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Carnes, Rosenbaum, Dubina", "parties": "", "opinions": [{"author": "ROSENBAUM, Circuit Judge:", "type": "010combined", "text": "Case: 17-13934 Date Filed: 05/24/2019 Page: 1 of 23\n\n\n [PUBLISH]\n\n IN THE UNITED STAT... | CARNES | ROSENBAUM | DUBINA | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4623250/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,624,027 | S&M BRANDS, INC., Plaintiff - Appellant, v. State of GEORGIA EX REL., Christopher M. CARR, Attorney General, Defendant - Appellee. | S&M Brands, Inc. v. State of Georgia Ex Rel. | 2019-05-29 | 17-13261 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Tjoflat, Rosenbaum, Ungaro", "parties": "", "opinions": [{"author": "TJOFLAT, Circuit Judge:", "type": "010combined", "text": "Case: 17-13261 Date Filed: 05/29/2019 Page: 1 of 11\n\n\n [PUBLISH]\n\n\n IN... | TJOFLAT | ROSENBAUM | UNGARO | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624027/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,624,568 | A&M GERBER CHIROPRACTIC LLC, as Assignee of Conor Carruthers, on Behalf of Itself and All Others Similarly Situated, Plaintiff - Appellee, v. GEICO GENERAL INSURANCE COMPANY, Defendant - Appellant. | A&M Gerber Chiropractic LLC v. GEICO General Insurance Company | 2019-05-30 | 17-15606 | U.S. Court of Appeals for the Eleventh Circuit | {"judges": "Wilson, Branch, Vinson", "parties": "", "opinions": [{"author": "VINSON, District Judge:", "type": "010combined", "text": "Case: 17-15606 Date Filed: 05/30/2019 Page: 1 of 23\n\n\n [PUBLISH]\n\n\n\n IN THE UNITED... | WILSON | BRANCH | VINSON | 1 | {} | 2 | 0 | 0 | 1 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4624568/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
4,616,544 | GOVERNMENT OF the Province of MANITOBA, Appellee State of Missouri, Ex Rel. Eric Schmitt, Missouri Attorney General's Office, Appellant v. David BERNHARDT, Secretary, U.S. Department of the Interior, Et Al., Appellees | Gvt. Province of Manitoba v. David Bernhardt | 2019-05-03 | 17-5242 | U.S. Court of Appeals for the District of Columbia Circuit | {"judges": "Henderson, Rogers, Srinivasan", "parties": "", "opinions": [{"author": "Opinion for the Court filed by Circuit Judge HENDERSON", "type": "010combined", "text": "United States Court of Appeals\n FOR THE DISTRICT OF COLUMBIA CIRCUIT\n\n\n\nArgued November 8, 2018 Decided May 3, 2019\n... | HENDERSON | ROGERS | SRINIVASAN | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/4616544/ | Published | 1 | 0 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | |||
7,335,706 | Kelly MILLER v. MARRIOTT INTERNATIONAL LLC | Miller v. Marriott Int'l LLC | 2019-05-03 | Civ. No. 18-cv-1101 (APM) | U.S. Court of Appeals for the District of Columbia Circuit | {"judges": "Introduction, Mehta", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/7253626/", "author_raw": ""}]} | MEHTA | MEHTA | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/7335706/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
7,336,308 | AMERICAN HOSPITAL ASSOCIATION v. Alex M. AZAR II, United States Secretary of Health and Human Services | Am. Hosp. Ass'n v. Azar | 2019-05-06 | Civil Action No.: 18-2084 (RC) | U.S. Court of Appeals for the District of Columbia Circuit | {"judges": "Contreras", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/7254228/", "author_raw": ""}]} | CONTRERAS | CONTRERAS | 0 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/7336308/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... | ||||
7,336,309 | MUSCOGEE CREEK INDIAN FREEDMEN BAND, INC. v. David BERNHARDT | Muscogee Creek Indian Freedmen Band, Inc. v. Bernhardt | 2019-05-06 | Civil Action No. 18-1705 (CKK) | U.S. Court of Appeals for the District of Columbia Circuit | {"judges": "Kollar, Kotelly", "parties": "", "opinions": [{"author": "", "type": "020lead", "text": "", "resource_uri": "https://www.courtlistener.com/api/rest/v4/opinions/7254229/", "author_raw": ""}]} | KOLLAR | KOLLAR | KOTELLY | 1 | {} | 1 | 0 | 0 | 0 | 1 | null | https://www.courtlistener.com/api/rest/v4/clusters/7336309/ | Published | 0 | 1 | 0 | 0 | 0 | 2,019 | 5 | [
{
"content": "You are an expert legal coding assistant trained to classify U.S. federal Courts of Appeals\ncases using an adaptation of the Supreme Court Database (SCDB_2023_01) codebook. You follow the coding procedure\nin the codebook step by step and use the precise definitions of terms presented in the code... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.